Sleep score based on physiological information

Abstract

The present disclosure relates to sleep scoring based on physiological information. Assessing sleep quality of a user in conjunction with an electronic device having one or more physiological sensors includes detecting that the user is attempting to fall asleep; and collecting physiological information associated with the user. The disclosed method of assessing sleep quality can include determining respective values of one or more sleep quality metrics based at least in part on the collected physiological information and at least one wake rest heart rate of the user, the one or more sleep quality metrics including a first set of sleep quality metrics associated with sleep quality of a plurality of users and a second set of sleep quality metrics associated with historical sleep quality of the user; and determining a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics.

Description

[0001] Divisional Statement

[0002] This application is a divisional application of Chinese Patent Application No. 201810201652.X, filed on March 12, 2018, which claims priority to U.S. Provisional Patent Application No. 62 / 650, 1 10, filed on March 30, 2018, the contents of which are incorporated herein by reference in their entirety. TECHNICAL FIELD

[0003] The present disclosure relates generally to the field of computing devices having one or more sensors that collect physiological information of a user. BACKGROUND

[0004] Computing devices, such as wearable computing devices, can incorporate or interact with one or more sensors for receiving physiological information of a user that is used for health-based assessments. SUMMARY

[0005] As computing devices become more ubiquitous and portable, they are showing many advantages in the field of health monitoring and diagnosis. Computing devices, particularly those that can be worn or carried by a user, can include one or more sensors that detect physiological information about the user and / or the environment surrounding the user. This information can be used to observe, detect, or diagnose various health conditions outside of a traditional clinic or laboratory setting. For example, in the context of sleep therapy, a portable or wearable electronic device can detect when a user moves during the night or monitor various physiological factors such as heart rate. In addition, the computing device can record and interpret the detected information about the user and / or the environment to determine a health assessment. As in the previous example, the wearable electronic device can record a relatively high frequency of movement by the user while sleeping and generate an assessment of a restless sleep period for the user.

[0006] Assessments of sleep quality can be achieved in various ways. For example, a patient can be monitored overnight using instruments such as electrodes and electroencephalogram (EEG) machines in a sleep laboratory. In contrast, another diagnostic technique disclosed in a journal article can involve a patient self-assessing the quality of sleep during the night. However, factors such as discomfort and unreliability present challenges to these well-established sleep quality assessment techniques. Thus, there is a need for a reliable, user-friendly method of determining sleep quality. For example, by determining the sleep quality of a user wearing a portable electronic device in the comfort of their home, reliable physiological information can be obtained and analyzed without the need for extensive laboratory instruments.

[0007] Certain embodiments disclosed herein provide systems, devices, and methods for assessing sleep quality of a user based on collected physiological and / or environmental data. Some embodiments implement a computing device having one or more sensors for collecting physiological data from a user and / or environmental data from the surrounding environment. For example, a portable computing device worn on the wrist of a user can include a sensor that detects the heart rate of the user and a sensor that detects the external temperature. Further, some embodiments implement a computing device or computing system configured to determine a value of one or more sleep quality metrics using the collected physiological and / or environmental information and to create a unified score of sleep quality using the determined values of the sleep quality metrics. For example, the same portable computing device worn on the wrist of the user can determine a value of a sleep restlessness metric and use the sleep restlessness metric value to determine a unified score of sleep quality of the user.

[0008] As described herein, in some implementations, the present disclosure relates to biometric monitoring devices. In the present disclosure, the term "biometric monitoring device" is used according to its broad and ordinary meaning and can be applied in various contexts herein to refer to any type of biometric tracking device, personal health monitoring device, portable monitoring device, portable biometric monitoring device, and the like. In some embodiments, a biometric monitoring device according to the present disclosure can be a wearable device, such as can be designed to be worn (e.g., continuously) by a person (i.e., a "user," a "wearer," etc.). Such a biometric monitoring device can be configured to gather data about activities performed by the wearer or about the physiological state of the wearer while being worn. Such data can include data representative of the external environment surrounding the wearer or representative of the wearer's interaction with the environment. For example, the data can include motion data about the movements of the wearer, external light, external noise, air quality, and / or physiological data obtained by measuring various physiological characteristics of the wearer, such as heart rate, perspiration level, and the like.

[0009] In some cases, a biometric monitoring device can utilize other devices external to the biometric monitoring device, such as an external heart rate monitor in the form of an EKG sensor for obtaining heart rate data or a GPS receiver in a smartphone for obtaining location data. In such cases, the biometric monitoring device can communicate with these external devices using a wired or wireless communication connection. The concepts disclosed and discussed herein can be applied to both standalone biometric monitoring devices and biometric monitoring devices that utilize sensors or functionality provided in external devices (e.g., external sensors, sensors or functionality provided by a smartphone, etc.).

[0010] In some implementations, the method of assessing sleep quality of a user is performed at one or more electronic devices (e.g., a wearable computing device and / or a biometric monitoring device), where at least one electronic device has one or more processors, one or more physiological sensors, and memory for storing programs to be executed by the one or more processors. The electronic device can detect that the user initially attempts to fall asleep, for example, by detecting a lack of motion and / or other physiological or environmental factors such as ambient light conditions or body temperature for a threshold period of time. In some embodiments, physiological information of the user is collected or received, including at least one sleep heart rate, such as an average heart rate since attempting to fall asleep or since detecting the onset of sleep. A value of one or more sleep quality metrics can be determined based at least in part on the collected physiological information and at least one wake rest heart rate of the user. For example, the wearable computing device can collect heart rate information of the user during a period of time between sleep sessions (e.g., while awake) and determine an average heart rate value (e.g., a wake rest heart rate) for a period of relative inactivity or minimal exertion during the day. Further, a unified score of sleep quality of the user can be determined based at least in part on the determined sleep quality metric values.

[0011] In some implementations, the method includes presenting a representation of the unified score to the user and / or generating the representation of the unified score. For example, the representation of the score is a number between 1 and 100, or a qualitative assessment of good, medium, or poor sleep quality.

[0012] In some implementations, the one or more sleep quality metrics include a first set of sleep quality metrics associated with sleep quality of a plurality of users, and a second set of sleep quality metrics associated with historical sleep quality of the user. In some implementations, determining the unified score of sleep quality includes determining a respective metric score for each of the one or more sleep quality metrics, and applying a respective weighting to each of the one or more sleep quality metrics.

[0013] In some implementations, the method includes determining a wake rest heart rate of the user prior to detecting that the user attempts to fall asleep. For example, an electronic device worn by the user periodically detects and records a heart rate (e.g., a speed of heartbeats) of the user during one or more periods of time when the user is awake, and determines an average, median, or another representative value of the wake rest heart rate.

[0014] In some implementations, collecting physiological information about the user includes collecting one or more sets of values associated with: movement of the user, total sleep duration, total deep sleep duration, duration of wake after sleep onset (WASO), total rapid eye movement (REM) sleep duration, total light sleep duration, breathing pattern of the user, breathing disturbances of the user, and / or body temperature of the user.

[0015] In some implementations, the method further includes collecting sleep quality feedback information from the user and / or receiving the collected sleep quality feedback, and determining a unified score of sleep quality of the user based at least in part on the sleep quality feedback information. For example, the user can be prompted to answer one or more questions about perceived sleep quality after waking from a sleep session. In this same example, answers to the one or more questions can each be assigned a value that is combined to determine the unified sleep score.

[0016] In some implementations, determining respective values of the one or more sleep quality metrics includes comparing at least one sleep heart rate of the user to at least one resting heart rate of the user. For example, a particular user can have an average wake resting heart rate of 75 beats per minute during a particular day, and an average sleep heart rate of 45 beats per minute during a corresponding night. In this same example, if either value is relatively different from the user's historical average, this can indicate a change in health or sleep quality.

[0017] In some implementations, the method includes detecting that the user began sleeping, and determining a duration from attempting to fall asleep to beginning to sleep. For example, the wearable computing device can detect that the user has laid down in a dimly lit environment to attempt to fall asleep at 11 :05 pm, and has transitioned from wakefulness to non-rapid eye movement (NREM) sleep or rapid eye movement (REM) sleep at 11 : 15 pm.

[0018] In some implementations, the method includes detecting that the user woke up after the detected beginning to sleep, and determining respective values of the one or more sleep quality metrics in response to detecting that the user woke up. For example, detecting that the user entered a wake state triggers determining the one or more sleep quality metrics, and can also trigger generating a unified score of sleep quality.

[0019] In some implementations, detecting that the user is attempting to fall asleep includes detecting contact between the device and the user. In certain embodiments, the electronic device is configured to be worn by the user. While certain embodiments are disclosed herein in the context of a wearable electronic device being worn by a user, it should be understood that detection of physiological activity and / or determination of a unifying sleep score and sleep quality metrics according to the present disclosure can be performed by any suitably configured electronic device, including but not limited to a computer, a server system, a smartphone, a tablet, a laptop, and an electronic device configured to be placed under a user (e.g., a bed, a pillow, a blanket, or a mattress) during a sleep session.

[0020] In some implementations, the method of assessing sleep quality of a user is performed at one or more electronic devices, where at least one electronic device has one or more processors, one or more physiological sensors, and memory for storing programs to be executed by the one or more processors. The electronic device can detect that the user is initially attempting to fall asleep, and / or receive one or more signals indicative of the user attempting to fall asleep; collect physiological information associated with the user and / or receive the collected physiological information associated with the user; determine respective values of one or more sleep quality metrics based at least in part on the collected physiological information, where the one or more sleep quality metrics include a first set of sleep quality metrics associated with sleep quality of a plurality of users and a second set of sleep quality metrics associated with historical sleep quality of the user; and determine a unifying score of sleep quality based at least in part on the values of the one or more sleep quality metrics.

[0021] In some implementations, determining the unifying score of sleep quality includes using a first weighting for the first set of sleep quality metrics and a second weighting for the second set of sleep quality metrics. In some implementations, the first set of sleep quality metrics is associated with clinical sleep quality data of a demographic comparable to the user, and the second set of sleep quality metrics is associated with historical physiological information about the user over a minimum of M days and a maximum of N days.

[0022] In some implementations, collecting physiological information about the user includes collecting at least one sleep heart rate, and determining respective values of the one or more sleep quality metrics includes using at least one wakeful resting heart rate of the user.

[0023] The present disclosure includes certain embodiments of an electronic device that includes one or more physiological sensors, one or more processors, memory, and control circuitry configured to: detect that a user is attempting to fall asleep; collect physiological information about the user including at least one sleep heart rate; determine respective values of one or more sleep quality metrics using the collected physiological information and at least one wake rest heart rate of the user; and determine a unified score of sleep quality of the user using the respective values of the one or more sleep quality metrics. Further, the control circuitry can be configured to perform any of the methods described herein.

[0024] The present disclosure includes certain embodiments of a non-transitory computer- readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by an electronic device having one or more physiological sensors, cause the device to: detect that a user is attempting to fall asleep; collect physiological information about the user including at least one sleep heart rate; determine respective values of one or more sleep quality metrics using the collected physiological information and at least one wake rest heart rate of the user; and determine a unified score of sleep quality of the user using the respective values of the one or more sleep quality metrics. Further, the non-transitory computer-readable storage medium can include instructions to perform any of the methods described herein.

[0025] The present disclosure includes certain embodiments of a method of performing sleep quality assessment at a sleep quality assessment server that includes one or more processors and memory for storing programs to be executed by the one or more processors to implement processes to: receive physiological information about a user, the physiological information including at least one sleep heart rate and at least one wake rest heart rate of the user; determine respective values of one or more sleep quality metrics using the collected physiological information; and determine a unified score of sleep quality of the user using the respective values of the one or more sleep quality metrics. The method can further include sending the unified sleep score and / or the determined values of sleep quality metrics to a wearable computing device and / or an external computing device, such as a smartphone. Further, the sleep quality assessment server can be configured to perform any of the methods described herein with respect to electronic devices and / or servers.

[0026] In some implementations, the method includes sending the determined values of the one or more sleep quality metrics to an electronic device. In some implementations, the electronic device is a wearable computing device and / or the electronic device is an external computing device. In some implementations, the electronic device has a display configured to present the unified score and / or the determined values of the one or more sleep quality metrics. In some implementations, determining the unified score of sleep quality includes determining a respective metric score for each of the one or more sleep quality metrics and using a respective weighting for each of the one or more sleep quality metrics. In some implementations, the method includes receiving sleep quality feedback information collected from the user (e.g., at the wearable computing device and / or at the external computing device) and determining the unified score of sleep quality of the user by additionally using the collected sleep quality feedback information. In some implementations, determining the respective values of the one or more sleep quality metrics includes comparing at least one sleep heart rate of the user to at least one wake rest heart rate of the user. In some implementations, the method includes receiving a trigger to determine the unified score of sleep quality (e.g., receiving a notification that the user has woken up or has requested the score) and determining the respective values of the one or more sleep quality metrics in response to receiving the trigger to determine the unified score of sleep quality. In some implementations, the method includes updating a profile database with the received physiological information and / or the determined values of the sleep quality metrics and / or the unified sleep score. In some implementations, determining the respective values of the one or more sleep quality metrics (e.g., of the user) includes retrieving values of the one or more sleep quality metrics corresponding to a plurality of users (e.g., other users in a demographic similar to the user).

[0027] The present disclosure includes certain implementations of a method of performing sleep quality assessment at a sleep quality assessment server including one or more processors and memory for storing programs to be executed by the one or more processors to implement processes described below, such as: receiving physiological information about a user; determining respective values of one or more sleep quality metrics using the collected physiological information, wherein the one or more sleep quality metrics include a first set of sleep quality metrics associated with sleep quality of a plurality of users and a second set of sleep quality metrics associated with historical sleep quality of the user; and determining a unified score of sleep quality of the user using the respective values of the one or more sleep quality metrics. The method can further include sending the unified sleep score and / or the determined values of the sleep quality metrics to a wearable computing device and / or an external computing device, such as a smartphone. Further, the sleep quality assessment server can be configured to perform any of the methods described herein with respect to an electronic device and / or server.

[0028] In one implementation, the at least one wake rest heart rate comprises a representative value of one or more heart rate values of a user heart rate value during a period of relative inactivity while the user is awake.

[0029] According to an aspect, a method of assessing sleep quality of a user at an electronic device having one or more processors and a non-transitory computer-readable storage medium is provided, the method comprising: receiving one or more signals indicative of an attempt by the user to fall asleep; receiving physiological information associated with the user including at least one sleep heart rate, the physiological information generated by one or more physiological sensors of the electronic device; determining respective values of one or more sleep quality metrics based at least in part on the physiological information and at least one wake rest heart rate of the user; and determining a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics.

[0030] According to another aspect, an electronic device is provided, comprising: one or more physiological sensors; one or more processors; a non-transitory computer-readable storage medium; and control circuitry configured to: detect an attempt by a user to fall asleep; collect physiological information associated with the user including at least one sleep heart rate; determine respective values of one or more sleep quality metrics based at least in part on the collected physiological information and at least one wake rest heart rate of the user; and determine a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics.

[0031] According to yet another aspect, a non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device having one or more physiological sensors, cause the device to: detect an attempt by a user to fall asleep; collect physiological information associated with the user including at least one sleep heart rate; determine respective values of one or more sleep quality metrics based at least in part on the collected physiological information and at least one wake rest heart rate of the user; and determine a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics. BRIEF DESCRIPTION OF DRAWINGS

[0032] For the sake of explanation, various embodiments are depicted in the drawings and should not be construed as limiting the scope of the present disclosure. Furthermore, various features of the disclosed embodiments can be combined in additional embodiments that are part of the present disclosure. Throughout the drawings, reference numbers can be repeated between drawings for the sake of explanation, and do not necessarily refer to the same or similar features.

[0033] FIG. 1is a block diagram illustrating an embodiment of a computing device according to one or more embodiments.

[0034] FIG. 2A Shown are perspective front and side views of a wearable computing device according to one or more embodiments.

[0035] FIG. 2B Shown are perspective back and side views of a wearable computing device according to one or more embodiments.

[0036] FIG. 3 is a table of sleep quality assessment metrics and associated physiological data according to one or more embodiments.

[0037] FIG. 4A is a block diagram of determining a basis for a unified sleep score according to one or more embodiments.

[0038] FIG. 4B is a table of benchmarks for determining a unified sleep score according to one or more embodiments.

[0039] FIG. 5 A network relationship between a wearable computing device and an external computing device is illustrated according to one or more embodiments.

[0040] FIG. 6 A system of client devices and server systems for performing sleep quality assessments is shown in accordance with one or more embodiments.

[0041] FIG. 7A An embodiment of a wearable computing device with a display for presenting a representation of a unified sleep score is shown in accordance with one or more embodiments.

[0042] FIG. 7B An embodiment of a wearable computing device with a touch screen display for presenting a representation of a unified sleep score is shown in accordance with one or more embodiments.

[0043] FIG. 8 A flow chart illustrating a process for determining a sleep quality assessment according to one or more embodiments is shown.

[0044] FIG. 9 A flow chart illustrating a process for determining a sleep quality assessment according to one or more embodiments is shown. DETAILED DESCRIPTION

[0045] The headings provided herein are for convenience only and do not necessarily affect the scope or meaning of the claimed invention.In the various drawings, like reference numerals and names may or may not indicate the same elements.

[0046] While certain preferred embodiments and examples are disclosed herein, the inventive subject matter extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses and modifications and equivalents thereof. Thus, it is to be understood that the scope of the claimed disclosure is not to be limited to the specific embodiments disclosed and that modifications and / or substitutions by one with ordinary skill in the art are considered to be within the scope of the disclosure. For example, in any of the methods or processes disclosed herein, the acts or operations can be performed in any suitable order and are not necessarily limited to any particular disclosed order. Also, various operations described herein can be described as multiple discrete operations; however, these operations can be performed as a more continuous process, e.g., in accordance with the flow diagrams. In addition, the structures, systems and / or devices described herein can be embodied as integrated components or as separate components. To facilitate comparison with various embodiments, certain aspects and advantages of these embodiments are described. Not necessarily all such aspects or advantages can be achieved with any particular embodiment. Thus, for example, various embodiments can be performed in an manner that achieves or optimizes one advantage or a group of advantages as taught herein without necessarily achieving other aspects or advantages as can also be taught or suggested herein.

[0047] Portable computing device

[0048] Systems, devices, and / or methods / processes in accordance with the present disclosure can include or be implemented in connection with a biometric monitoring device. Embodiments of the present disclosure can provide a biometric monitoring device configured to collect physiological data of a user from one or more physiological biometric sensors and / or environmental data from one or more environmental sensors. Embodiments of the present disclosure can also provide a biometric monitoring device configured to analyze and interpret the collected data and / or communicate with another computing device to analyze and interpret the collected data. It will be understood that while the concepts and discussions included herein are presented in the context of a biometric monitoring device, these concepts can also be applied to other contexts if appropriate hardware is available. For example, some or all of the relevant sensor functionality can be incorporated in one or more external computing devices (e.g., a smartphone) or computing systems (e.g., a server) that are communicatively coupled to the biometric monitoring device.

[0049] FIG. 1is a block diagram illustrating an embodiment of a computing device 100 in accordance with one or more embodiments disclosed herein. In certain embodiments, the computing device 100 can be worn by a user 10, such as with respect to embodiments in which the computing device 100 is a wearable biometric or physiological monitoring device. For example, the computing device 100 can include a wearable biometric monitoring device configured to gather data regarding activities performed by the wearer or regarding the physiological state of the wearer. Such data can include data representative of the ambient environment surrounding the wearer or the wearer’s interaction with the environment. For example, the data can include motion data regarding movement of the wearer, ambient light, ambient noise, air quality, etc., and / or physiological data obtained by measuring various physiological characteristics of the wearer, such as heart rate, body temperature, blood oxygen level, perspiration level, etc. While certain embodiments are disclosed herein in the context of a wearable biometric monitoring device, it should be understood that the biometric / physiological monitoring and health assessment principles and features disclosed herein can be applicable to any suitable or desired type of computing device or combination of computing devices, whether wearable or not.

[0050] The computing device 100 can include one or more audio and / or visual feedback modules 130, such as an electronic touchscreen display unit, a light emitting diode (LED) display unit, an audio speaker, an LED light, or a buzzer. In certain embodiments, the one or more audio and / or visual feedback modules 130 can be associated with a front face of the computing device 100. For example, in wearable embodiments of the computing device 100, the electronic display can be configured to be externally presented to a user viewing the computing device 100.

[0051] The computing device 100 includes a control circuit 110. While certain modules and / or components are shown in the block diagram of FIG. 1 as being part of the control circuit 110, it should be understood that control circuits associated with computing devices 100 and / or other components or devices in accordance with the present disclosure can include additional components and / or circuitry, such as one or more of the additionally shown components of FIG. 2. FIG. 1 FIG. 1 While certain modules and / or components are shown in the block diagram of FIG. 1 as being part of the control circuit 110, it should be understood that control circuits associated with computing devices 100 and / or other components or devices in accordance with the present disclosure can include additional components and / or circuitry, such as one or more of the additionally shown components of FIG. 2. FIG. 1 While certain modules and / or components are shown in the block diagram of FIG. 1 as being part of the control circuit 110, it should be understood that control circuits associated with computing devices 100 and / or other components or devices in accordance with the present disclosure can include additional components and / or circuitry, such as one or more of the additionally shown components of FIG. 2.

[0052] ​The control circuit 110 can include one or more processors, data storage devices, and / or electrical connectivity. For example, the control circuit 110 can include one or more processors configured to execute operating code of the computing device 100, such as firmware, etc., where such code can be stored in one or more data storage devices of the computing device 100. In one embodiment, the control circuit 110 is implemented on a SoC (system on a chip), although those skilled in the art will recognize that other hardware / firmware implementations are possible.

[0053] The control circuit 110 can include a sleep quality assessment module 113. The sleep quality assessment module 113 can include one or more hardware and / or software components or features configured to assess the sleep quality of a user, optionally using input from one or more environmental sensors 155 (e.g., ambient light sensors) and information from the biometric module 141. In certain embodiments, the sleep assessment module 111 includes a sleep score determination module 113 configured to determine a uniform score of sleep quality using information accumulated by the sleep assessment module 111, such as one or more values of biometrics determined by the biometric computation module 142 of the biometric module 141. In certain embodiments, the biometric module 141 is in optional communication with one or more internal physiological sensors 140 embedded or integrated in the biometric monitoring device 100. In certain embodiments, the biometric module 141 is in optional communication with one or more external physiological sensors 145 (e.g., electrodes or sensors integrated in another electronic device) that are not embedded or integrated in the biometric monitoring device 100. Examples of internal physiological sensors 140 and external physiological sensors 145 include, but are not limited to, sensors for measuring body temperature, heart rate, blood oxygen level, and movement.

[0054] The computing device can also include one or more data storage modules 151, which can include any suitable or desirable type of data storage that can be volatile or non-volatile, such as solid state memory. The solid state memory of the computing device 100 can include any of a variety of technologies, such as flash memory integrated circuits, phase change memory (PC-RAM or PRAM), programmable metallization cell RAM (PMC-RAM or PMCm), ovonic unified memory (OUM), resistive RAM (RRAM), NAND memory, NOR memory, EEPROM, ferroelectric memory (FeRAM), MRAM, or other discrete NVM (non-volatile solid state memory) chips. The data storage 151 can be used to store system data, such as operating system data and / or system configuration or parameters. The computing device 100 can also include data storage used as buffers and / or buffer memory for use by the control circuit 110 in operation.

[0055] The data storage module 151 can include various sub-modules, including but not limited to one or more of: a sleep detection module for detecting an attempt by the user 10 to fall asleep or to initiate sleep; an information collection module for managing the collection of physiological and / or environmental data related to sleep quality assessment; a sleep quality metric calculation module for determining a value of one or more sleep quality metrics described in the present disclosure; a unified score determination module for determining a representation of a unified score of sleep quality described in the present disclosure; a presentation module for managing the presentation of sleep quality assessment information to the user 10; a heart rate determination module for determining a value and pattern of one or more types of heart rate of the user 10; a feedback management module for collecting and interpreting sleep quality feedback from the user 10.

[0056] The computing device 100 also includes a power storage device 153, which can include a rechargeable battery, one or more capacitors, or other charge-holding devices. Power stored by the power storage module 153 can be used by the control circuit 110 for operation of the computing device 100, such as for powering the touch screen display 130. The power storage module 153 can receive power through the host interface 176 or through other means.

[0057] The computing device 100 can include one or more environmental sensors 155. Examples of such environmental sensors 155 include, but are not limited to, sensors for measuring ambient light, external (non-human body) temperature, altitude, and global positioning system (GPS) data.

[0058] The computing device 100 can also include one or more connectivity components 170, which can include, for example, a wireless transceiver 172. The wireless transceiver 172 can be communicatively coupled to one or more antenna devices 195, which can be configured to wirelessly transmit and / or receive data and / or power signals to and / or from the computing device using, but not limited to, peer-to-peer, WLAN, or cellular communications. For example, the wireless transceiver 172 can be used to communicate data and / or power between the computing device 100 and an external host system (not shown), which can be configured to interface with the computing device 100. In certain embodiments, the computing device 100 can include additional host interface circuitry and / or components 176, such as a wired interface component for communicatively coupling with a host device or system to receive data and / or power from and / or transmit data to the host device or system.

[0059] The connection circuitry 170 can also include a user interface component 174 for receiving user input. For example, the user interface 174 can be associated with one or more audio / visual feedback modules 130, where a touch screen display is configured to receive user input from a user in contact therewith. The user interface module 174 can also include one or more buttons or other input components or features.

[0060] The connection circuitry 170 can also include a host interface 176, which can be, for example, an interface for communicating with a host device or system (not shown) over a wired or wireless connection. The host interface 176 can be associated with any suitable or desired communication protocol and / or physical connector, such as Universal Serial Bus (USB), micro-USB, WiFi, Bluetooth, FireWire, PCle, etc. For wireless connections, the host interface 176 can be in conjunction with the wireless transceiver 172.

[0061] While certain functional modules and components are shown and described herein, it will be appreciated that the authentication management functionality in accordance with the present disclosure can be implemented using a variety of different approaches. For example, in some implementations, the control circuitry 110 can include one or more processors controlled by computer-executable instructions stored in memory in order to provide functionality such as described herein. In other implementations, such functionality can be provided in the form of one or more specially designed circuits. In some implementations, such functionality can be provided by one or more processors controlled by computer-executable instructions stored in memory coupled with one or more specially designed circuits. Various examples of hardware that can be used to implement the concepts outlined herein include, but are not limited to, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and general purpose microprocessors coupled with memory that store executable instructions to control the general purpose microprocessor.

[0062] Wearable computing device

[0063] In some implementations, the portable computing device, such as the portable computing device 100, can be configured to provide authentication management functionality in accordance with the present disclosure. For example, the portable computing device 100 can be configured to provide functionality such as described herein. FIG. 1The computing device 100 can be designed such that it can be inserted into a wearable housing or into one or more of a variety of different wearable housings (e.g., a wristband housing, a waistband clip housing, a pendant housing, a housing configured to attach to a piece of exercise equipment such as a bicycle, etc.). In other implementations, a portable computing device, such as a computing device integrated in a non-removable manner into a wristband, can be designed to be worn in a limited manner and can be specialized for being worn on a person's wrist (or perhaps ankle). Regardless of the configuration, a wearable computing device having one or more physiological and / or environmental sensors can be configured to collect physiological and / or environmental data in accordance with the various embodiments disclosed herein. The wearable computing device can also be configured to analyze and interpret the collected physiological and / or environmental data to perform a sleep quality assessment of a user (e.g., wearer) of the computing device or can be configured to communicate with another computing device or server that performs the sleep quality assessment.

[0064] The shape and size of the wearable computing device in accordance with the embodiments and implementations described herein can be suitable for coupling to (e.g., fastening to, worn by, carried by, etc.) a user's body or clothing. FIG. 2A An example of a wearable computing device 201 is shown in FIG. 2. FIG. 2A Front and side perspective views of a wearable computing device 201 are shown. The wearable computing device 201 includes both a computing device 200 and a band portion 207. In certain embodiments, the band portion 207 includes a first portion and a second portion that can be connected by a clasp portion 209. The computing device portion 200 can be insertable and can have any suitable or desired size. The size of the wearable computing device can generally be relatively small so as to not introduce attention to the wearer, and thus the size of an optional touch screen display 230 can be relatively small relative to certain other computing devices. The computing device 200 can be designed to be wearable for extended periods of time without discomfort and without interfering with normal daily activities or sleep.

[0065] The electronic display 230 can include any type of electronic display known in the art. For example, the display 230 can be a liquid crystal display (LCD) or an organic light emitting diode (OLED) display, such as a transmissive LCD or OLED display. The electronic display 230 can be configured to provide brightness, contrast, and / or color saturation characteristics in accordance with display settings maintained by control circuitry and / or other internal components / circuitry of the computing device 200.

[0066] The touch screen 230 can be a capacitive touch screen, such as a surface capacitive touch screen or a projected capacitive touch screen, which can be configured to be responsive to contact with a charge-holding member or tool, such as a human finger.

[0067] A wearable computing device such as a biometric monitoring device according to the present disclosure can incorporate one or more existing functional components or modules designed for determining one or more physiological metrics associated with a user (e.g., wearer) of the device, such as a heart rate sensor (e.g., a photoplethysmograph sensor), a body temperature sensor, an ambient temperature sensor, and the like. Such components / modules can be disposed on or associated with an underside / backside of the biometric monitoring device, and can be in contact or substantially in contact with human skin when the biometric monitoring device is worn by a user. For example, in the case of a biometric monitoring device worn on a user's wrist, the physiological metric components / modules can be associated with an underside / backside of the device substantially opposite the display and touching the user's arm.

[0068] In one embodiment, the physiological and / or environmental sensors (sources and / or detectors) can be disposed on an internal or skin side of the wearable computing device (i.e., a side of the computing device that contacts, touches, and / or faces the skin of a user (hereinafter referred to as the "skin side")). In another embodiment, the physiological and / or environmental sensors can be disposed on one or more sides of the device, including the skin side of the device and one or more sides of the device that face or are exposed to the external environment (environmental sides).

[0069] FIG. 2B is FIG. 2A Perspective back and side views of a wearable biometric monitoring device 201. The wearable biometric monitoring device 201 includes a band portion 207 that can be configured to be latched or fastened around a user's arm or other appendage via any suitable or desirable type of fastening mechanism. For example, a hook-and-loop fastener assembly 209 can be used to fasten the band 207. In certain embodiments, the band 207 is designed to have shape memory to facilitate wrapping around a user's arm.

[0070] The wearable biometric monitoring device 201 includes a biometric monitoring device assembly 200 that can be at least partially fastened to the band 207. FIG. 2BThe view of FIG. 2B illustrates the back side 206 (also referred to herein as the "underside") of the biometric monitoring device 200, which is, for example, generally faceable and / or contactable with skin or clothing associated with a user's arm. In this context, the term "back side" and "underside" is used according to its broad and ordinary meaning, and the term can be used in certain contexts to refer to a side, panel, area, component, portion, and / or surface of the biometric monitoring device that is positioned and / or arranged substantially opposite a user display, whether exposed outside the device or at least partially inside an electronic package or housing of the device.

[0071] The wearable biometric monitoring device 201 can include one or more buttons 203, which can provide a mechanism for user input. The wearable biometric monitoring device 201 can also include a device housing, which can include one or more of steel, aluminum, plastic, and / or other rigid structures. The housing 208 can be used to protect the biometric monitoring device 200 and / or internal electronics / components associated therewith from physical damage and / or becoming fragmented. In certain embodiments, the housing 208 is at least partially waterproof.

[0072] The back side 206 of the biometric monitoring device 200 can have associated therewith an optical physiometric sensor 243, which can include one or more sensor components, such as one or more light sources 240 and / or light detectors 245, which collection of one or more sensor components can represent an example of the internal physiometric sensor 140 of FIG. 1. FIG. 1 The optical physiometric sensor 243 includes, in certain embodiments, a form of a protrusion that protrudes from the back surface of the biometric monitoring device 200. The sensor components can be used to determine one or more physiometrics of a user wearing the wearable biometric monitoring device 201. For example, the optical physiometric sensor components associated with the sensor 243 can be configured to provide readings for determining heart rate (e.g., in beats per minute (BPM)), blood oxygen (e.g., Sp02), blood pressure, or other physiometrics. In certain embodiments, the biometric monitoring device 200 also includes a charger mating recess 207.

[0073] While the sensor 243 is shown in certain figures herein as including a protrusion, it should be understood that a backside sensor module according to the present disclosure can or can not be associated with a protrusion form. In certain embodiments, the protrusion form on the backside of the device can be designed to engage the user's skin with a greater force than the surrounding device body. In certain embodiments, an optical window or light-transmissive structure can be incorporated in a portion of the protrusion 243. The light emitter 240 and / or detector 245 of the sensor module 243 can be disposed or arranged in the protrusion 243 in close proximity to the window or light-transmissive structure. In this way, when attached to the user's body, the window portion of the protrusion 243 of the biometric monitoring device 200 can engage the user's skin with a greater force than the surrounding device body, thereby providing a more secure physical coupling between the user's skin and the optical window. That is, the protrusion 243 can cause a consistent contact between the biometric monitoring device and the user's skin, which can reduce the amount of stray light measured by the photodetector 245, reduce relative motion between the biometric monitoring device 200 and the user, and / or provide an improved local pressure on the user's skin, some or all of which can improve the quality of the cardiac signals of interest generated by the sensor module. Notably, the protrusion 243 can contain other sensors that benefit from close proximity and / or secure contact with the user's skin. These sensors can be included in addition to the heart rate sensor, or can be included in place of the heart rate sensor, and can include sensors such as skin temperature sensors (e.g., non-contact thermopiles with optical windows or thermistors connected to the outer surface of the protrusion by thermal epoxy), pulse oximeters, blood pressure sensors, EMG or galvanic skin response (GSR) sensors.

[0074] Collecting physiological information and / or environmental information

[0075] The wearable computing device 201 can be configured to collect one or more types of physiological data and / or environmental data from embedded sensors and / or external devices, and pass or relay this information to other devices, including devices that can be used as an internet-accessible source of data, allowing the collected data to be viewed, for example, using a web browser or web-based application. For example, while a user is wearing the wearable computing device 201, the wearable computing device 201 can use one or more biometric sensors to calculate and store the number of steps taken by the user. The wearable computing device 201 can then send data representative of the number of steps taken by the user to a web service, a computer, a mobile phone, or an account on a health station, where the user can store, process, and visualize the data. In fact, the wearable computing device 201 can measure or calculate a number of other physiological metrics in addition to or instead of the number of steps taken by the user. These physiological metrics include, but are not limited to: energy expenditure, e.g., calories burned, floors climbed and / or descended, heart rate, heart rate variability, heart rate recovery, location and / or direction obtained, e.g., through GPS or similar systems, altitude, walking speed and / or distance traveled, swimming laps, detected swimming stroke type and count, bicycle distance and / or speed, blood pressure, blood sugar, skin conductance, skin temperature and / or body temperature, muscle state measured through electromyography, brain activity measured through electroencephalography, body weight, body fat, caloric intake, nutritional intake from food, drug intake, sleep period, e.g., clock time, sleep phase, sleep quality and / or duration, pH level, hydration level, respiration rate, and other physiological metrics.

[0076] The wearable computing device 201 can also measure or calculate metrics related to the environment surrounding the user, such as barometric pressure, weather conditions (e.g., temperature, humidity, pollen count, air quality, rain / snow conditions, wind speed), light exposure (e.g., ambient light, ultraviolet light exposure, time and / or duration spent in the dark), noise exposure, radiation exposure, and magnetic fields. Further, a wearable computing device 201 or system that aggregates data streams from the wearable computing device 201 can calculate metrics derived from these data. For example, a device or system can calculate a user's stress and / or relaxation levels through a combination of heart rate variability, skin conductance, noise pollution, and body temperature. Similarly, a wearable computing device 201 or system that aggregates data streams from the wearable computing device 201 can determine values corresponding to sleep quality metrics derived from these data. For example, a device or system can calculate the quality of a user's restless sleep and / or rapid eye movement (REM) sleep through a combination of heart rate variability, blood oxygen levels, sleep duration, and body temperature. In another example, a wearable computing device 201 can determine the efficacy of a medical intervention (e.g., a drug) through a combination of drug intake, sleep data, and / or activity data. In yet another example, a biometric monitoring device or system can determine the efficacy of an allergy medication through a combination of pollen data, drug intake, sleep data, and / or activity data. These examples are provided for illustration only and are not intended to be limiting or exhaustive. Additional embodiments and implementations of sensor devices can be found in U.S. Patent No. 9,167,991, filed June 8, 2011, entitled "Portable Biometric Monitoring Devices and Methods of Operating Same," which is incorporated by reference herein in its entirety.

[0077] Sleep quality metric

[0078] As noted above, there is a need for reliable and user-friendly methods in the field of sleep therapy and sleep quality assessment. FIG. 3Table 300 is a table of sleep quality assessment metrics and associated physiological data according to one or more embodiments of the present disclosure. Table 300 includes a metrics column 302 and an input column 304 and three rows of sleep quality metrics types, namely user goal-driven metrics 306, user normalized metrics 308, and population normalized metrics 310. In some embodiments, the inputs in input column 304 include directly detected physiological sensor readings and / or environmental sensor readings (e.g., instantaneous heart rate), while in some embodiments, the inputs in input column 304 include intermediate parameters derived from directly detected physiological sensor readings and / or environmental sensor readings (e.g., average heart rate over a sleep session). Additional embodiments and implementations of collecting and interpreting physiological sensor readings and / or environmental sensor readings for sleep quality assessment can be found in U.S. Patent Application No. 15 / 438,643, filed February 21, 2017, entitled "Methods and Systems for Labeling Sleep States," which is incorporated by reference herein in its entirety.

[0079] The various sleep quality metrics conveyed in table 300 are each associated with a different diagnostic basis for sleep quality. For example, one aspect of good sleep health is having sufficient total sleep duration corresponding to the age, sex, and overall health of the respective user. A first type of sleep quality metric that can be used to determine a unified sleep score is goal-driven 306. Goal-driven metrics 306 can require input from the user to set one or more sleep goals, and can require feedback from the user regarding perceived sleep quality. Goal-driven metrics 306 include, but are not limited to, total sleep time metrics and sleep consistency metrics.

[0080] Determining the value of the total sleep time metric can rely on one or more inputs, including but not limited to a minimum target duration of a sleep goal specified by the user, a maximum target duration of a sleep goal, and / or a target range of a sleep goal. For example, a biometric monitoring device that performs a sleep quality assessment can prompt the user to input a target for sleep duration to be achieved for a given night (e.g., at least 7 hours of sleep tonight), or to input a target for sleep duration to be achieved each night (e.g., 7 to 8 hours of sleep each night). Determining the value of the total sleep time metric can also rely on a determined value of total sleep duration to be achieved by the user for a corresponding sleep session. For example, a wearable computing device can detect that the user went to sleep at 11 PM on Monday and woke up at 6 AM on Tuesday, for a total sleep duration of 7 hours. In some embodiments, the onset of sleep and the onset of wakefulness are detected by one or more physiological sensors. Determining the value of the total sleep time metric can use the user-specified sleep goal and the detected total sleep duration for a corresponding sleep session (e.g., for a given night), and generate a value corresponding to an achievement level for meeting the user-specified goal. For example, if the user intends to sleep at least 7 hours and the total sleep duration is 7.5 hours, then the total sleep time metric will have a maximum value (e.g., ten-tenths or 100%) in a given range of possible values.

[0081] Another possible goal-driven metric 306 is sleep consistency. In some implementations, the value of the sleep consistency metric relies on feedback obtained from the user after waking from a sleep session. For example, a biometric monitoring device can detect that the user has woken from a night of sleep and prompt the user to provide a self-assessment of perceived sleep quality or restfulness. This feedback can be in a numerical format (e.g., seven-tenths) or in a subjective form that is converted to a numerical value (e.g., good = 1, fair = 0, poor = -1).

[0082] A second type of sleep quality metric that can be used to determine a unified sleep score is user normalization 308. The user normalization metric 308 is specific to a corresponding user for whom a sleep assessment is being performed, and relies on historical physiological information about the user. In certain embodiments, determining a corresponding value of the corresponding user normalization metric 308 can require at least M days (e.g., at least 7 days) of detected physiological data and / or environmental data. In some embodiments, determining a corresponding value of the corresponding user normalization metric 308 can use up to N days (e.g., up to the most recent 30 days) of most recently detected physiological data and / or environmental data. The user normalization metric 308 can include, but is not limited to, a restlessness metric, a long wakefulness metric, and a heart rate metric.

[0083] In some implementations, a value of the restlessness metric is determined using a value of detected movement of the user during the sleep session. The degree of movement can be based on a duration of detected movement while the user is asleep. For example, if the computing device worn by the user while asleep detects that the user remained nearly motionless for 6 hours out of a 7 hour sleep session, this can indicate a low degree of movement during the sleep session. The degree of movement can be based on a vigor of detected movement while the user is asleep. For example, if the user had a nightmare and moved with force or speed, such movement can indicate a high degree of movement during the sleep session. The value of the restlessness metric can also depend on a value of total sleep duration detected. For example, if 15 minutes of movement is detected during an 8 hour sleep session, this indicates less overall restlessness than if 15 minutes of movement is detected during a 5 hour sleep session. The value or weighting of the restlessness metric value can also involve comparing the current assessment of restlessness to historical values of the restlessness metric for the user. For example, if the user typically has a relatively calm, low movement night's sleep, then a high restlessness night's score has a relatively high standard deviation from the norm, and can be weighted more negatively than if the user typically has a restless sleep. Similarly, in this same example, if the user typically has a restless night's sleep, then a low restlessness night's score can be weighted more positively than if the user typically has a calm night's sleep, as compared to a user who typically has a calm night's sleep.

[0084] In some implementations, a value of the long wakefulness metric is determined using a value representative of the total duration between detected wakefulness sessions or sleep sessions. For example, if the user gets up multiple times during a given night, then the value of the long wakefulness metric can be low, indicating that the user does not have long continuous sleep sessions. Similar to the restlessness metric, determining the value or weighting of the long wakefulness metric value can involve comparing the determined value of the long wakefulness metric to historical values of the long wakefulness metric for the respective user.

[0085] In some implementations, a value of the heart rate metric is determined using one or more heart rate parameters. Determining the value of the heart rate metric can include using a value representative of an average heart rate of the user during the sleep session (e.g., 45 heartbeats per minute). For example, if the user has an average sleep heart rate that is above a particular threshold (e.g., 60 heartbeats per minute), this can result in a lower value of the heart rate metric. The average sleep heart rate of the user can also be compared to a historical average sleep heart rate of the user over several days to assess whether the currently determined average sleep heart rate is abnormally high or abnormally low for the user.

[0086] In some implementations, the value of the heart rate metric includes an assessment of the user's wake rest heart rate during a long duration of wakefulness prior to detecting that the user is attempting to fall asleep (e.g., during the day prior to nighttime sleep). For example, a user's average heart rate during the day can be 55 beats per minute, and an average sleep heart rate can be 53 beats per minute. This unusually small difference between the user's average rest heart rate during the day and the user's average sleep heart rate when the user is asleep can result in a low value for the heart rate metric, which indicates that the user can not be having good nighttime sleep. In some implementations, detecting that the sleep heart rate (e.g., average, median, or instantaneous) value is above the wake rest heart rate value is an indication of poor sleep quality. Thus, the heart rate metric can be assigned a low value, and / or the weight of the heart rate metric value can be increased in determining the population-normalized score and / or the unified sleep score.

[0087] The use of the user's wake rest heart rate can also be indicative of a mental or physical health condition (e.g., a cold or anxiety) that can affect the detected and / or perceived sleep quality. For example, if the user has a relatively high rest heart rate for a number of consecutive days or weeks, this can correspond to a relatively high sleep heart rate for the same number of days or weeks. Thus, the weighting of the average sleep heart rate value can be decreased to compensate for such changes in the user's physical and / or mental health. While the examples of detecting heart rate have involved average values, in some implementations another statistical basis can be used to assess the user's corresponding heart rate. For example, the entire heart rate pattern can be analyzed for a given time period (e.g., total sleep duration). For a given heart rate parameter, a median heart rate value can be used instead of an average heart rate value. Extreme values of heart rate over a time period can also be filtered out before performing statistical operations to determine a representative value of the corresponding type of heart rate.

[0088] A third type of sleep quality metric that can be used to determine the unified sleep score is population normalization 310. The population normalization metric 308 is a sleep quality metric assessed with respect to a plurality of users. In certain embodiments, determining a corresponding value of the corresponding population normalization metric 310 includes comparing the determined value for the user to values determined for other users in a similar population (e.g., same gender, same age range, same profession). The population normalization metric 310 can include, but is not limited to, a deep sleep metric, a rapid eye movement (REM) metric, a duration metric for wake after sleep onset (WASO), and a respiratory disturbance metric. The population normalization metric can be correlated to the sleep quality assessment systems of multiple users described herein and / or clinical data obtained from sleep therapy resources, such as sleep lab readings for various patients.

[0089] In some implementations, a value of a deep sleep metric is determined using a value of a duration of time that the user experienced deep sleep during a total sleep duration. In some embodiments, the value of the deep sleep metric is determined using a total duration of non-rapid eye movement (NREM) sleep, while in some embodiments, the total duration of deep sleep is a subset of time within the total duration of NREM sleep. For example, the total duration of deep sleep is determined to include time when the frequency of the user's brain waves is less than 1 Hz. Physiologically, deep sleep is associated with new memory consolidation, physical restoration, and mental restoration. Thus, a relatively low value of the duration of deep sleep, as compared to a plurality of users, can result in a low value of the deep sleep metric.

[0090] In some implementations, a value of a rapid eye movement (REM) sleep metric is determined using a value of a duration of time that the user experienced REM sleep during a total sleep duration. In some implementations, the duration of REM sleep and / or NREM sleep and / or deep sleep is determined based on detected movement, heart rate, breathing patterns, brain activity, and / or body temperature of the user. REM sleep deprivation is associated with mental health issues and physical health issues, thus, a relatively low value of the duration of REM sleep, as compared to a plurality of users, can result in a low value of the REM sleep metric.

[0091] In some implementations, a value of a wake after sleep onset (WASO) metric is determined using a value of a total time or average time between sleep sessions that the user experienced during a total sleep duration. For example, the user can wake up three times during the night due to nightmares or environmental disturbances, and have a total value of 45 minutes of time between sleep sessions. Continuous sleep is associated with improved durations of REM and deep sleep, thus, a relatively high total time value or average time value between sleep sessions, as compared to a plurality of users, can result in a low value of the WASO metric.

[0092] In some implementations, a value of a respiratory disturbance metric is determined using a value of a duration of time that the user experienced apneic breathing during a total sleep duration. For example, while asleep, the wearable computing device worn by the user can detect a pulse oximeter reading of less than 90%, which indicates a low blood oxygen level and suggests that the user has been apneic breathing. In this example, the user can wake up, begin breathing again, and have a pulse oximeter reading of greater than 90% or another threshold value for a period of time. While a pulse oximeter is one example of a physiological sensor used to determine respiratory disturbances, the measurement of the duration of time that the user experienced apneic breathing during sleep is not limited to this example. For example, the duration of time of apneic breathing can also be detected through brain activity. Threshold levels of blood oxygen levels, brain activity, and / or breathing activity used to determine a high level of respiratory disturbances can be determined through a plurality of users.

[0093] While table 300 depicts several sleep quality metrics and several types of sleep quality metrics that can be used by a biometric monitoring device to determine a unified score for sleep quality, it should be understood that additional sleep quality metrics can be used. Furthermore, in some implementations, a subset of the sleep quality metrics shown in table 300 can be used to determine a sleep quality score. For example, a wearable computing device that does not have a sensor for determining breathing disturbances does not use a breathing disturbance metric to determine a unified score for sleep quality for the purpose of sleep quality assessment.

[0094] Generating a unified score of sleep quality

[0095] FIG. 4A 4 is a block diagram of determining a benchmark for a unified sleep score according to one or more embodiments. In some implementations, an overall user normalized score is determined using one or more goal-driven metrics and one or more user normalized metrics, each of which is described above with respect to FIG. 3 In some implementations, goal-driven metrics are not used to determine the overall user normalized score. In some implementations, as described above with respect to FIG. 3 As described, the population-standardized measures are used to determine an overall population-standardized score.

[0096] The determination of the user normalized score and the group normalized score depends on which specific sleep quality metrics are used and the weight of each sleep quality metric selected when calculating each score. For example, when determining the user normalized score, the total sleep time and goal-driven sleep quality metrics can be given relatively high weights, while the restlessness metric can be given relatively low weights or determined not to be used. In some implementations, the selection of the sleep metric used to determine the user normalized score and / or the group normalized score depends on the performance of the biometric monitoring device used to perform the user's sleep assessment. For example, if the computing device worn by the user cannot measure heart rate, then the heart rate metric is not used to determine the user normalized score.

[0097] The weighting basis for the sleep metrics used to determine the user-normalized score and / or the population-normalized score can be changed automatically or manually. For example, atypical values for a respective sleep quality metric can result in a higher weighting than the default weighting for that respective sleep quality metric, or can limit the upper or lower bounds for the associated score. As the user develops better sleep habits, the weighting basis can also change over time in order to incentivize the user to continually achieve better sleep quality. When the user sleeps for a minimum threshold amount of the total sleep period (e.g., the night), the weighting basis can be adjusted from the default basis after a period of time in which physiological data and / or environmental data is collected. The user can also be able to adjust the weighting basis for one or more sleep quality metrics in determining a unified score for overall sleep quality that depends on various goal-driven metrics, user-normalized metrics, and / or population-normalized metrics. For example, the user can be able to indicate that restlessness is closely tied to perceived sleep quality, resulting in an increased weighting for that metric. In some implementations, one or more population-normalized metrics are given more weight than one or more user-normalized metrics, while in some implementations, one or more user-normalized metrics are given more weight than one or more population-normalized metrics.

[0098] After determining the respective user-normalized score and the respective population-normalized score for sleep quality, the unified score for sleep quality is determined using the user-normalized score and the population-normalized score. In some implementations, there is a weighting component for each of the user-normalized score and the population-normalized score in determining the unified sleep score. As described above with respect to the weighting basis for each of the user-normalized score and the population-normalized score, the weighting component can be adjusted manually or automatically.

[0099] FIG. 4B Table 402 is an example of a basis for determining a unified sleep score according to one or more implementations. The example of table 402 is non-limiting and is merely used to illustrate one particular technique for generating a unified score for sleep quality using a user-normalized score and a population-normalized score. As described with respect to FIG. 3 and FIG. 4A The user-normalized score can be based on one or more of a heart rate metric, a total sleep time metric, a sleep consistency metric, a restlessness metric, and a time between sleep sessions metric. It should be understood that this is a non-limiting score basis for generating a user-normalized score, and the user-normalized score can be based on additional user-specific sleep quality metrics not described herein. As described with respect to FIG. 3 and FIG. 4AThe population-normalized score can be based on one or more of deep sleep metric, REM metric, WASO metric, and respiratory disturbance metric. It should be understood that this is a non-limiting scoring benchmark for generating a population-normalized score, and that the population-normalized score can be based on additional population-normalized sleep quality metrics not described herein.

[0100] A user-normalized score can be determined and converted to a value on a pre-set numerical range (e.g., -4 to 1, or 0 to 4, or 1 to 100). Similarly, a population-normalized score can be determined and converted to a value on a pre-set numerical range. The non-limiting example shown in table 402 illustrates a range of values for the user-normalized score, from a worst value of -4 to a best value of 1, and a range of values for the population-normalized score, from a worst value of -1 to a best value of 1. In some embodiments, the user-normalized score and the population-normalized score use the same range of scoring values. A non-limiting example calculation of a unified score for sleep quality combines the determined user-normalized score and population-normalized score, multiplies the sum by 10, and adds 80 to the result in order to obtain a final value in a range from a worst value of 30 to a best value of 100.

[0101] Sleep quality assessment system

[0102] In certain embodiments described in the present disclosure, the wearable computing device is capable of and configured to collect physiological sensor readings of the user and determine values for one or more sleep quality metrics and / or a unified sleep score. However, in some embodiments, the wearable computing device or another portable electronic device used to detect physiological information of the user is in communication with another computing device configured to determine these values. FIG. 5 A network relationship 500 between a wearable computing device 502 and an external computing device 504 is shown, in accordance with one or more embodiments.

[0103] As described throughout this disclosure, the wearable computing device 502 can be configured to collect one or more types of physiological data and / or environmental data from embedded sensors and / or external devices, and to transmit or relay such information to other devices over one or more networks 506. In some implementations, this includes relaying information to a device that can be used as an Internet-accessible data source, allowing the collected data to be viewed, for example, using a web browser or web-based application at an external computing device 504. For example, when a user is asleep and wearing the wearable computing device 502, the wearable computing device 502 can use one or more biometric sensors to calculate and optionally store the user's sleep heart rate. The wearable computing device 502 can then send data representative of the user's sleep heart rate over the network 506 to a web service, computer, mobile phone, or account on a health station where the user can store, process, and visualize the data.

[0104] While the example wearable computing device 502 is shown with a touch screen display, it should be understood that the wearable computing device 502 can not have any type of display unit, or can have various audio and / or visual feedback components such as light emitting diodes (LEDs) (of various colors), a buzzer, a speaker, or a display with limited functionality. The wearable computing device 502 can be configured to be attached to the user's body or clothing, such as a wristband, watch, ring, electrode, finger clip, toe clip, chest strap, ankle strap, or a device that is placed in a pocket. Additionally, the wearable computing device 502 can alternatively be embedded in something that comes into contact with the user, such as clothing, a mattress, blanket, pillow, or another accessory that is involved in a sleep activity.

[0105] Communication between the wearable computing device 502 and the external device 504 can be facilitated by one or more networks 506. In some implementations, the one or more networks 506 include one or more of a self-organizing network, a peer-to-peer communication link, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a wireless WAN (WWAN), a metropolitan area network (MAN), a portion of the Internet, a portion of the Public Switched Telephone Network (PSTN), a cellular telephone network, or any other type of network. Communication between the wearable computing device 502 and the external device 504 can also be performed through a direct wired connection. The direct wired connection can be associated with any suitable or desirable communication protocol and / or physical connector, such as Universal Serial Bus (USB), micro-USB, WiFi, Bluetooth, FireWire, PCIe, etc.

[0106] Various computing devices can communicate with the wearable computing device 502 to facilitate sleep quality assessment. FIG. 5 As shown, the example external computing device 504 is a smartphone with a display 508. The external computing device 504 can be any computing device capable of assessing the value of one or more sleep quality metrics and / or unified sleep score, such as, but not limited to, a smartphone, a personal digital assistant (PDA), a mobile phone, a tablet computer, a personal computer, a laptop computer, a smart TV, and / or a video game console. FIG. 5 , an external computing device 504 can be implemented to determine one or more sleep quality metrics and / or a unified sleep score. For example, a user wears a wearable computing device 502 configured as a bracelet that has one or more physiological sensors but no display. In this example, during the night, while the user sleeps, the wearable computing device 502 records the user's heart rate, movement, body temperature, and blood oxygen level, as well as room temperature and ambient light levels, and periodically transmits this information to the external computing device 504. Alternatively, the wearable computing device 502 can store and transmit the collected physiological data and / or environmental data and transmit this data to the external computing device 504 in response to a trigger, such as detecting that the user has woken up after a period of sleep. In some implementations, the user must be awake for a threshold period of time in order to set the trigger (e.g., awake for at least 10 minutes), and / or awake for a threshold period of time after having experienced a threshold sleep period (e.g., awake for at least 5 minutes after at least 6 hours of sleep). In some implementations, a trigger for determining one or more values ​​of the sleep quality metric and / or the unified sleep score is detection of a command executed at the external computing device 504 , such as a manual or automatically executed instruction to synchronize collected physiological data and / or environmental data and determine a unified sleep score.

[0107] The example external computing device 504 illustrates that in some implementations, the external computing device 504 can present values ​​of one or more sleep quality metrics and / or a unified sleep score. This can be presented to a user of the wearable computing device 502 (e.g., the wearer), or can be presented, for example, to a sleep therapy provider for the user, such as a doctor or caregiver. In some implementations, the external computing device 504 determines one or more values ​​of one or more sleep quality metrics and / or a unified sleep score and sends this information back to the wearable computing device 502 via one or more networks 506 so that the one or more values ​​thus determined can be presented to the user of the wearable computing device (e.g., the wearer). This will be discussed below with respect to FIG. 7A and FIG. 7B Additional information regarding presenting values ​​of a unified sleep score and / or one or more sleep quality metrics is discussed in the context of FIG.

[0108] FIG. 6 A system 600 for performing sleep quality assessment of client devices and server system 608 is shown in accordance with one or more embodiments. In some implementations, a sleep quality assessment system or platform is implemented across multiple electronic devices. Wearable computing devices 502a, 502b, and 502c can have similar features as described above with respect to the wearable computing devices 502 in FIG. 5 FIG. 5 FIG. 5

[0109] In some implementations of the sleep quality assessment system 600, one or more wearable computing devices, such as wearable computing device 502a, are directly connected to one or more networks 506, which connect to server system 608, and optionally to one or more external computing devices, such as external computing devices 504a, 504b, and / or 504c. In some implementations, one or more external computing devices 504a, 504b, and / or 504c are interconnected (or another type of communication interconnection) in a local area network (LAN) 604 that is connected to one or more networks 506. The LAN 604 can interconnect one or more external computing devices, such as devices 504a, 504b, or 504c, and one or more wearable computing devices, such as 502c. In some implementations, one or more wearable computing devices, such as wearable computing device 502b, are connected to one or more networks 506, which are indirectly connected to one or more external computing devices 504 through the LAN 604, which are connected to one or more networks 506. In some implementations, one or more wearable computing devices, such as wearable computing device 502b, are directly connected to one or more networks 506, and are indirectly connected to the one or more networks through the LAN 604 as described above. For example, wearable computing device 502b is connected to smart phone 504b through a Bluetooth connection, smart phone 504b is connected to server system 608 through network 506, and wearable computing device 502b is also connected to server system 608 through network 506.

[0110] Sleep quality assessment server

[0111] ​​​The sleep quality assessment system 600 can implement the server system 608 to collect detected physiological sensor readings and / or environmental sensor readings from one or more wearable computing devices, such as the illustrated devices 502a, 502b, and 502c. In some implementations, the server system 608 can also collect values of sleep quality assessment metrics and / or a unified sleep score from one or more wearable computing devices, such as the illustrated devices 502a, 502b, and 502c, and / or from one or more external computing devices, such as the illustrated devices 504a, 504b, and 504c. For example, the wearable computing device 502a is not associated with an external computing device, and thus, the wearable computing device transmits collected physiological data to the server system 608 while the user 602a is sleeping, which analyzes the received data to determine values of one or more sleep quality metrics and a unified sleep score to transmit back to the wearable computing device 502a. In another example, the wearable computing device 502b transmits collected physiological data to the server system 608 and the external computing device 504a while the user 602b is sleeping (or has already slept). In this example, the external computing device 504a determines values of one or more sleep quality metrics and a unified sleep score, while the server system 608 uses the received physiological data to update a user profile for the user 602b stored in the profile database 614.

[0112] In some implementations, the server system 608 is implemented on one or more standalone data processing apparatuses or on a distributed computer network. In some embodiments, the server system 108 also employs various virtual devices and / or services of third-party service providers (e.g., third-party cloud service providers) to provide underlying computing resources and / or infrastructure resources of the server system 108. In some embodiments, the server system 108 includes, without limitation, a handheld computer, a tablet computer, a laptop computer, a desktop computer, or a combination of any two or more of these data processing devices or other data processing devices.

[0113] The server system 608 can include one or more processors or processing units 610 (e.g., CPUs) and one or more network interfaces 618 including I / O interfaces to external computing devices and wearable computing devices. In some implementations, the server system 608 includes memory 612 and one or more communication buses for interconnecting these components. The memory 612 includes high-speed random access memory, such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; and optionally includes non-volatile memory, such as one or more magnetic disk storage devices, one or more optical disk storage devices, one or more flash memory devices, or one or more other non-volatile solid state storage devices. The memory 612 optionally includes one or more storage devices remotely located from the one or more processing units 610. The memory 612, or alternately the non-volatile memory within the memory 612, comprises a non-transitory computer readable storage medium. In some implementations, the non-transitory computer readable storage medium of memory 612, or the memory 612 stores one or more programs, modules, and data structures. These programs, modules, and data structures can include, but are not limited to, one or more of: an operating system including procedures for handling various basic system services and for performing hardware dependent tasks; a network communication module for connecting the server system 608 to other computing devices (e.g., the wearable computing devices 502a, 502b, and 502c and / or the external computing devices 504a, 504b, and 504c), wherein the network communication module is connected to one or more networks 506 via the one or more network interfaces 618 (wired or wireless).

[0114] The memory 612 can also include a unified score determination module 614 for determining values of one or more sleep quality metrics and / or a unified sleep score using collected physiological data and / or environmental data of one or more users (e.g., received from one or more wearable computing devices or external computing devices), as previously described in the present disclosure with respect to FIG. 3 、 FIG. 4A and FIG. 4BThe memory 612 can also include a profile database 616 that stores user profiles for users of the sleep quality assessment system 600, in which a respective user profile for a user can include a user identifier (e.g., an account name or handle), login credentials for the sleep quality assessment system, an email address or preferred contact information, wearable computing device information (e.g., model), demographic parameters for the user (e.g., age, gender, profession, etc.), historical sleep quality information, and sleep quality trends identified for the user (e.g., as a restless sleeper, among others). In some implementations, the physiological information collected for multiple users of the sleep quality assessment system 600 (e.g., users 602a, 602b, and 602c) provides a more robust population-normalized sleep metric, as described above with respect to FIG. 3 , FIG. 4A and FIG. 4B For example, user 602a is a 35-year-old female veterinarian, and user 602b is a 34-year-old female veterinarian, and as their demographic characteristics are closely related, each of their respective historical sleep quality physiological data and / or metrics are used to determine one or more population-normalized sleep for one another. In some implementations, a user can opt in or opt out of providing sleep quality assessment information for population-normalized determinations for other users. In some implementations, a user’s sleep quality information can be incorporated into population-normalized sleep quality metric information used to determine values for one or more sleep quality metrics for the user themselves.

[0115] Presentation of a unified score of sleep quality

[0116] FIG. 7A Embodiments of wearable computing devices 700a and 700b are shown, each having a display for presenting a representation of a unified sleep score, in accordance with one or more embodiments. FIG. 7A The computing devices 700a and 700b each show a generally rectangular display. The computing device 700a shows a set of light-emitting diodes (LEDs) that some wearable computing devices can have that indicate a status or, in this context, a unified score of sleep quality. For example, as shown in the display 702a, 3 of 4 LEDs are illuminated can indicate a better unified sleep quality score.

[0117] In certain embodiments, the computing device 700b can be configured to display text and / or other visual elements on the display 702b. The display 702b of the computing device 700b can appear as a relatively small display, where depiction of a large amount of information can be undesirable and / or impractical. Thus, the display 702b of the wearable computing device 700b, which has limited display capabilities, can simply depict a numerical representation and / or a subjective representation (e.g., good, poor, average) of a unified score of sleep quality.

[0118] FIG. 7B Embodiments of wearable computing devices with touch screen displays for presenting representations of unified sleep scores are shown in accordance with one or more embodiments. FIG. 7B Wearable computing devices 704a and 704b are shown with substantially rectangular, horizontally arranged displays 706a and 706b, respectively. The display 706a shows that, in some implementations, a unified score of sleep quality can be depicted along with more detailed information about sleep quality metrics that contribute to the unified score of sleep quality. In some implementations, a user can scroll through the detailed information on the display 706a. The display 706b shows that a representation of a unified score of sleep quality can be in the form of a graphic, an emoji, a background color, or another audiovisual representation other than a number or text.

[0119] Method of assessing sleep quality

[0120] FIG. 8 A flowchart of a process 800 for determining a sleep quality assessment in accordance with the present disclosure is shown. In certain embodiments, the process 800 can be performed, at least in part, by a computing device having one or more physiological sensors and / or environmental sensors and / or by a control circuit of the computing device. For example, in performing at least a portion of the process 800, a user can wear a computing device on a wrist or other body part, or otherwise attach the computing device to him or her. The process 800 can be performed using one or more sleep quality metrics based on detected physiological and / or environmental information to assess a quality of sleep experienced by a user. In some implementations, the process 800 is performed, at least in part, by multiple electronic devices (e.g., a wearable computing device and an external computing device), and in some implementations, the process 800 is performed, at least in part, by a sleep quality assessment server (e.g., with respect to the server system 608 and wearable computing device described above). FIG. 6 The server system 608 and wearable computing device described above.

[0121] In certain embodiments, the user can be detected to be in an awake state prior to performing step 802 of process 800. For example, the user can be detected to be awake from 7:01 AM to 10:59 PM and not attempting to sleep. When the user attempts to sleep, one or more measurable physiological parameters can be detected in connection with measuring a sleep quality metric. In certain embodiments, process 800 can be performed in connection with a wearable computing device worn around the wrist or other location of the user, for example. In certain embodiments, sleep quality assessment process 800 can be initiated when the user puts on the device and / or brings the device into contact with the user's skin and / or the user lies down in a reclined position. Alternatively, sleep quality assessment process in accordance with the present disclosure can be initiated after a predetermined period of time in a stationary state, or in connection with a request to initiate a sleep assessment procedure.

[0122] At block 802, process 800 involves detecting that the user is attempting to sleep or receiving one or more signals indicative of the user attempting to sleep. For example, the user can be wearing a computing device that detects that the user has assumed a reclined position, that ambient light is low, and / or that the device is in contact with the user but relatively motionless. In some implementations, process 800 includes detecting that the user has begun sleeping, or receiving one or more signals indicative of the user beginning to sleep and determining a duration of time from attempting to sleep to beginning to sleep. In some implementations, sleep attempt detection is performed automatically based on one or more physiological and / or environmental sensor readings, while in some implementations sleep attempt detection is performed based on manual input by the user (e.g., pressing a button on a wearable computing device or indicating an attempt to sleep in an application on a wearable or external computing device).

[0123] At block 804, process 800 involves collecting (or receiving) physiological information associated with the user, including at least one sleep heart rate. For example, the sleep heart rate can be an average of user heart rate values measured periodically during the total duration of sleep (e.g., during a night of sleep). In some implementations, the physiological information is collected periodically and / or upon detecting some change in condition (e.g., movement). In some implementations, the physiological information is still collected while the user is awake, such as during the period of time between attempting to sleep and beginning to sleep or during a wakeful period of time prior to the user being awake for a long period of time (e.g., waking up in the morning). In some implementations, collecting physiological information about the user includes collecting one or more sets of values associated with: movement of the user, total sleep duration, total deep sleep duration, duration of wake after sleep onset (WASO), total rapid eye movement (REM) sleep duration, total light sleep duration, breathing pattern of the user, breathing disturbances of the user, and temperature of the user.

[0124] At block 806, the process 800 involves determining respective values of one or more sleep quality metrics based at least in part on the collected physiological information. In some implementations, determining the respective values of the one or more sleep quality metrics includes using at least one wake rest heart rate of the user. For example, determining the value of the heart rate metric includes comparing the average sleep heart rate of the collected physiological information to an average wake rest heart rate detected and computed prior to the user attempting to fall asleep. In some implementations, the wake rest heart rate is determined periodically during a period of sustained wakefulness prior to the user entering a sleep state. In some implementations, the wake rest heart rate is the lowest rest heart rate value detected while the user is awake. In some implementations, determining the respective values of the one or more sleep quality metrics includes comparing at least one sleep heart rate of the user to at least one wake rest heart rate of the user. In some implementations, determining the respective values of the one or more sleep quality metrics includes comparing at least one sleep heart rate of the user to a threshold value.

[0125] In certain embodiments, the one or more sleep quality metrics include a first set of sleep quality metrics associated with sleep quality of a plurality of users and a second set of sleep quality metrics associated with historical sleep quality of the user. In certain embodiments, the process 800 further includes detecting that the user woke up after the detected onset of sleep and, in response to detecting that the user woke up, determining the respective values of the one or more sleep quality metrics.

[0126] At block 808, the process 800 includes determining a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics. In certain embodiments, determining the unified score of sleep quality includes determining a respective metric score for each of the one or more sleep quality metrics and applying a respective weighting to each of the one or more sleep quality metrics. In some embodiments, the process 800 includes collecting sleep quality feedback information from the user and determining the unified score of sleep quality of the user based at least in part on the collected sleep quality feedback information.

[0127] At block 810, the process 800 involves presenting a representation of the unified score or generating instructions to provide a representation of the unified score to the user. For example, as shown in FIGS. 8A-8B, the representation of the unified score can vary according to the audiovisual feedback capabilities of the wearable and / or biometric monitoring device. The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another example, the server system 608 of FIG. 6 sends instructions to the wearable computing device to present the unified sleep quality assessment score 85 on the display of the wearable computing device. FIG. 7A and FIG. 7B The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another example, the server system 608 of FIG. 6 sends instructions to the wearable computing device to present the unified sleep quality assessment score 85 on the display of the wearable computing device. FIG. 6 The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another example, the server system 608 of FIG. 6 sends instructions to the wearable computing device to present the unified sleep quality assessment score 85 on the display of the wearable computing device.

[0128] FIG. 9A process 900 for determining a sleep quality assessment according to one or more embodiments of the disclosure is shown. The process 900 can be performed, at least in part, by a computing device having one or more physiological sensors and / or environmental sensors and / or by a control circuit of the computing device. For example, a user can wear the computing device on a wrist or other body part, or otherwise attach the computing device to himself or herself while at least a portion of the process 900 is performed. The process 900 can be performed using one or more sleep quality metrics based on detected physiological and / or environmental information to assess a quality of sleep experienced by the user. In some implementations, the process 900 is performed, at least in part, by multiple electronic devices (e.g., a wearable computing device and an external computing device), and in some implementations, the process 900 is performed, at least in part, by a sleep quality assessment server (e.g., with respect to the server system 608 and the wearable computing device described above). FIG. 6 The server system 608 and the wearable computing device described above.

[0129] At block 902, the process 900 involves detecting that the user is attempting to fall asleep or receiving one or more signals indicative of the user attempting to fall asleep. For example, the user is wearing the computing device, which detects that the user has assumed a reclining position, that ambient light is weak, and / or that the device is in contact with the user but is relatively still. In some implementations, the process 900 includes detecting that the user begins to sleep, or receiving one or more signals indicative of the user beginning to sleep and determining a duration of time from attempting to fall asleep to beginning to sleep.

[0130] At block 904, the process 900 involves collecting physiological information associated with the user. In some implementations, collecting physiological information associated with the user includes collecting one or more sets of values associated with: movement of the user, total sleep duration, total deep sleep duration, duration of wake after sleep onset (WASO), total rapid eye movement (REM) sleep duration, total light sleep duration, breathing pattern of the user, breathing disturbances of the user, and temperature of the user.

[0131] At block 906, the process 900 involves determining respective values of one or more sleep quality metrics based at least in part on the collected physiological information, where the one or more sleep quality metrics include a first set of sleep quality metrics associated with sleep quality of a plurality of users and a second set of sleep quality metrics associated with historical sleep quality of the user. In some implementations, determining the respective values of the one or more sleep quality metrics includes using at least one wake rest heart rate of the user. For example, determining the value of the heart rate metric includes using an average sleep heart rate of the collected physiological information and an average wake rest heart rate detected and calculated prior to the user attempting to fall asleep. In some implementations, determining the respective values of the one or more sleep quality metrics includes comparing at least one sleep heart rate of the user to at least one wake rest heart rate of the user. In certain embodiments, the process 900 further includes detecting that the user woke up after the detected onset of sleep or receiving one or more signals indicative of the user waking up and, in response to detecting that the user woke up, determining the respective values of the one or more sleep quality metrics.

[0132] At block 908, the process 900 includes determining a unified score of sleep quality of the user based at least in part on the respective values of the one or more sleep quality metrics. In certain embodiments, determining the unified score of sleep quality includes determining a respective metric score for each of the one or more sleep quality metrics and at least partially based on a respective weighting of each of the one or more sleep quality metrics. In some embodiments, the process 900 includes collecting sleep quality feedback information from the user or receiving collected sleep quality information and determining the unified score of sleep quality of the user based at least in part on the collected sleep quality feedback information.

[0133] At block 910, the process 900 involves presenting a representation of the unified score to the user or generating a representation of the unified score to be presented to the user. For example, as shown in FIGS. 8A-8C, the representation of the unified score can vary according to the audiovisual feedback capabilities of the wearable and / or biometric monitoring device. The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another embodiment, the server system 608 of FIG. 6 transmits instructions to the wearable computing device to present the unified assessment score 85 of sleep quality on a display of the wearable computing device. FIG. 7A and FIG. 7B The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another embodiment, the server system 608 of FIG. 6 transmits instructions to the wearable computing device to present the unified assessment score 85 of sleep quality on a display of the wearable computing device. FIG. 6 The representation of the unified score can include any of alphanumeric characters, graphics, sounds, lights, patterns, and animations. In another embodiment, the server system 608 of FIG. 6 transmits instructions to the wearable computing device to present the unified assessment score 85 of sleep quality on a display of the wearable computing device.

[0134] Additional embodiments

[0135] Depending on the embodiment, certain acts, events, or functions can be performed in a different sequence, can be added, merged, or left out altogether. Accordingly, not all described acts or events are necessary to practice the processes in certain embodiments. Additionally, in certain embodiments, acts or events can be performed concurrently, e.g., through multi-threaded processing, interrupt processing, or via substantially simultaneous processing of two or more processors or processor cores.

[0136] Certain methods and / or processes described herein can be implemented in and / or performed by software code modules executed by one or more general purpose and / or special purpose computers. The term "module" refers to logic embodied in hardware and / or firmware, or to a collection of software instructions, possibly having entry and exit points, written in a programming language, such as, for example, C or C++. A software module can be compiled and linked into an executable program or installed in a dynamic linking library, or it can be written in an interpreted programming language such as, for example, BASIC, Perl, or Python. It will be appreciated that software modules can be callable from other modules or from themselves, and / or can be invoked in response to detected events or interrupts. Software instructions can be embedded in firmware, such as an Erasable Programmable Read Only Memory (EPROM). It will be further appreciated that hardware modules can be comprised of connected logic units, such as gates and flip-flops, and / or can be comprised of programmable units, such as programmable gate arrays, application specific integrated circuits, and / or processors. The modules described herein are preferably implemented as software modules, but can also be implemented in hardware and / or firmware. Additionally, although invoked modules can in some embodiments be compiled separately, in other embodiments the modules can represent a subset of the instructions of a separately compiled program, and can have no interface available to other logic of the program.

[0137] In certain embodiments, code modules can be implemented in and / or stored on any type of computer-readable media and / or other computer storage devices. In some systems, data input to the system (and / or metadata), data generated by the system, and / or data used by the system can be stored in any type of computer data repositories, such as relational databases and / or flat file systems. Any of the systems, methods, and processes described herein can include interfaces configured to allow interaction with patients, health care practitioners, administrators, other systems, components, programs, etc.

[0138] Conditional language used herein, such as, among others, "can," "could," "might," "may," "e.g.," and the like, unless specifically stated otherwise, or otherwise understood within the context as used by those of ordinary skill in the art, is intended in its ordinary sense and is generally intended to convey that certain embodiments include, while other embodiments do not necessarily include, certain features, elements and / or steps. Thus, such conditional language is not generally intended to imply that features, elements and / or steps are in any way required in one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without author or promoter input or prompting, whether these features, elements and / or steps are included or are to be performed in any particular embodiment. The terms "comprising," "including," "having" and the like, as well as the terms "consisting essentially of and "consisting of are intended to be synonymous, unless specifically stated otherwise, of an open transition that is inclusive of, in an open-ended fashion, additional elements, features, acts, operations, etc. to those described herein. Additionally, the term "or" is intended to be inclusive, unless specifically stated otherwise, in its polymeric meaning of "and / or," such that any of the items listed can be included, singly or in combination with any of the other items listed. Unless specifically stated otherwise, conjunctive language such as the phrase "at least one of X, Y and Z," is understood to convey the meaning of "X, Y or Z," and thus, the conjunctive language is not necessarily intended to imply that at least one of X, at least one of Y and at least one of Z each must be present in some embodiments.

[0139] References herein to "certain embodiments," "certain implementations," or "embodiments" mean one, more or all embodiments. The appearance of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily referring to one or more particular embodiments. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the purview of one of ordinary skill in the art to effect such feature, structure, or characteristic in connection with a different embodiment, whether or not the different embodiment is described or otherwise presented in this specification. Thus, embodiments described herein include all embodiments that can be claimed using the elements and / or combinations of the elements found throughout the description and the accompanying drawings.

[0140] It is to be understood that in the description of embodiments above, various features that are described in association with a particular embodiment, or in a particular figure, can sometimes be combined with features described in association with another embodiment, or in another figure. It is also to be understood that the methods of the disclosure should not be viewed as having the intent to require any of the features in any of the claims to be present in one embodiment or in a particular figure. Furthermore, any of the components, features, or steps described in any of the embodiments herein can be used in any other embodiment or with any other embodiment. Also, no component, feature, step, or set of components, features, or steps is essential or indispensable to any embodiment. Accordingly, the scope of the application disclosed herein and claimed in the above claims is not limited by the specific embodiments described above, but is determined only by a reasonable interpretation of the above claims.

Claims

1. A method comprising: obtaining, by one or more sensors of a wearable device worn by the person, a first resting heart rate of the person during a wake period; obtaining, from the one or more sensors, a second resting heart rate of the person during a sleep period; obtaining pulse oximetry data during the sleep period from the one or more sensors; obtaining, by the one or more sensors, motion data during the sleep period; as well as A unified score for the person's sleep quality is determined, by one or more processors, based at least in part on the first resting heart rate, the second resting heart rate, the pulse oximetry data, and the motion data.

2. The method according to claim 1, wherein Determining the unified score of the person's sleep quality includes: determining, by the one or more processors, a first component of the unified score based at least in part on the first resting heart rate and the second resting heart rate; determining, by the one or more processors, a second component of the unified score based at least in part on the pulse oximetry data; and A third component of the unified score is determined, by the one or more processors, based at least in part on the motion data.

3. The method according to claim 2, wherein: Determining the first component of the unified score includes determining, by the one or more processors, the first component based at least in part on a comparison of the second resting heart rate to the first resting heart rate.

4. The method according to claim 2, wherein: Determining the first component of the unified score includes: assigning a first value to the first component when the second resting heart rate is lower than the first resting heart rate; and When the second resting heart rate is higher than the first resting heart rate, the first component is assigned a second value, the second value being lower than the first value.

5. The method according to claim 2, wherein: Determining the second component of the unified score includes: determining, by the one or more processors, an occurrence of one or more breathing disorders while the person is sleeping based at least in part on the pulse oximetry data; The second component is determined by the one or more processors based at least in part on one or more metrics associated with the one or more breathing disorders.

6. The method according to claim 5, wherein: The one or more breathing disturbances occur when the person's pulse oximetry reading is below a threshold for a threshold amount of time.

7. The method according to claim 2, wherein: Determining the third component includes: determining, by the one or more processors, an amount of time the person was mobile during the sleep period; and The third component is determined by the one or more processors based at least in part on the amount of time the person moves during the sleep period.

8. The method according to claim 2, wherein: Each of the first component, the second component, and the third component is weighted differently.

9. The method according to claim 1, further comprising: The one or more processors cause the unified score to be displayed on a display of the wearable device or an electronic device separate from the wearable device.

10. A wearable device comprising: one or more biometric sensors; one or more motion sensors; and One or more processors configured to perform operations comprising: obtaining, via the one or more biometric sensors, a first resting heart rate of the person during a wake period; obtaining, via the one or more biometric sensors, a second resting heart rate of the person during a sleep period; obtaining pulse oximetry data of the person during the sleep period via the one or more biometric sensors; obtaining motion data during the sleep period via the one or more motion sensors; and A unified score for the person's sleep quality is determined based at least in part on the first resting heart rate, the second resting heart rate, the pulse oximetry data, and the motion data.

11. The wearable device according to claim 10, wherein: The one or more biometric sensors include a photoplethysmography (PPG) sensor.

12. The wearable device according to claim 10, wherein: The one or more motion sensors include an accelerometer.

13. The wearable device according to claim 10, wherein: Determining the unified score of the person's sleep quality includes: determining, by the one or more processors, a first component of the unified score based at least in part on the first resting heart rate and the second resting heart rate; determining a second component of the unified score based at least in part on the pulse oximetry data; and A third component of the unified score is determined based at least in part on the motion data.

14. The wearable device according to claim 13, wherein: Determining the first component of the unified score includes determining the first component based at least in part on a comparison of the second resting heart rate to the first resting heart rate.

15. The wearable device according to claim 14, wherein: Determining the first component of the unified score includes: assigning a first value to the first component when the second resting heart rate is lower than the first resting heart rate; and When the second resting heart rate is higher than the first resting heart rate, the first component is assigned a second value, the second value being lower than the first value.

16. The wearable device according to claim 13, wherein: Determining the second component of the unified score includes: determining an occurrence of one or more breathing disorders while the person was sleeping based at least in part on the pulse oximetry data; The second component is determined based at least in part on one or more metrics associated with the one or more breathing disorders.

17. The wearable device according to claim 13, wherein: Determining the third component includes: determining an amount of time the person was mobile during the sleep period; and The third component is determined based at least in part on the amount of time the person is moving during the sleep period.

18. The wearable device according to claim 13, wherein: Determining the third component includes: The third component is determined based at least in part on a comparison of an amount of time the person was moving during the sleep period and an amount of time the person was moving during one or more previous sleep periods.

19. The wearable device according to claim 12, wherein: The operations further include: The one or more processors cause the unified score to be displayed on a display of the wearable device or an electronic device separate from the wearable device.

Images