Techniques for determining circadian rhythm chronotypes

Abstract

A method, system, and device for determining a circadian rhythm chronotype are described. The system may be configured to receive a first set of physiological data collected over a period of time and to receive a second set of physiological data collected over a previous sleep day. Additionally, the system may be configured to classify the first set of physiological data into a circadian rhythm chronotype using a machine learning model. The system may then compare the determined circadian rhythm chronotype with the received second set of physiological data. The system may cause a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof to be displayed on a graphical user interface of a user device.

Description

Technical Field

[0001] [Cross - Reference] This application claims the benefit of U.S. Non - Provisional Application No. 18 / 320,943, entitled "TECHNIQUES FOR DETERMINIG A CIRCADIAN RHYTHM CHRONOTYPE", filed on May 19, 2023 by KARSIKAS et al., which claims the benefit of U.S. Provisional Application No. 63 / 344,800, entitled "TECHNIQUES FOR DETERMINIG A CIRCADIAN RHYTHM CHRONOTYPE", filed on May 23, 2022 by KARSIKAS et al., which is assigned to the assignee of this application and is hereby expressly incorporated by reference herein.

[0002] [Technical Field] The following relates to wearable devices and data processing, including techniques for determining a circadian rhythm chronotype.

Background Art

[0003] Some wearable devices can be configured to collect data associated with body temperature and heart rate from a user. For example, some wearable devices can be configured to determine a user's chronotype associated with one or more physiological parameters or characteristics. However, conventional chronotype techniques implemented by wearable devices may only consider a limited number of inputs or variables, and as a result, may lead to inaccurate chronotype classifications, so their usefulness may be limited.

Brief Description of the Drawings

[0004]

Figure 1

[0005]

Figure 2

[0006]

Figure 3

[0007]

Figure 4

[0008]

Figure 5

[0009]

Figure 6

[0010]

Figure 7

[0011]

Figure 8

[0012]

Figure 9

[0013]

Figure 10

[0014]

Figure 11

[0015]

Figure 12

Figure 13

DETAILED DESCRIPTION OF THE INVENTION

[0016] Some wearable devices can be configured to collect physiological data from a user, including body temperature data, heart rate data, heart rate variability (HRV) data, sleep data, respiration data, and the like. The acquired physiological data can be used to analyze behavioral and physiological characteristics associated with the user, such as exercise, sleep patterns, activity patterns, and the like. Many users are seeking more insight into their physical health, including sleep patterns, activity, and overall physical well-being. In particular, many users may be seeking more insight into their circadian rhythm, chronotype, and misalignment with the circadian rhythm. However, typical tracking or health devices and applications lack the ability to provide robust determinations and insights for several reasons.

[0017] First, the procedures for determining and understanding a chronotype may rely on self-reported scales or questionnaires that introduce many biases into the calculations. The questionnaire may consist of a series of questions regarding an individual's preferences for sleep, activity time onset, activity time offset, sleep regularity, etc. However, self-reported assessments can be subjective. Second, even devices that are wearable or measure the user's biomarkers, typical devices and applications lack the ability to collect other physiological, behavioral, or contextual inputs from the user that can be combined with measured physiological parameters such as body temperature data and sleep data to more comprehensively understand the complete set of physiological contributors to the user's circadian rhythm and related chronotype.

[0018] Aspects of the present disclosure relate to techniques for determining a circadian rhythm chronotype. In particular, a computing device of the present disclosure may receive physiological data collected over a period of time from a wearable device associated with a user. The physiological data may include at least nighttime body temperature data, activity data, sleep pattern data, or some combination or subset of these measurements. Aspects of the present disclosure may use a machine learning model to classify physiological data from a wearable device into a circadian rhythm chronotype based on nighttime body temperature data, activity data, sleep pattern data, or a combination thereof. As will be described in more detail below, the circadian rhythm chronotype classification may additionally or alternatively include different physiological inputs and / or different chronotype classifications as inputs.

[0019] For the purposes of the present disclosure, terms such as "circadian rhythm chronotype", "circadian chronotype" or "circadian profile" may be used to refer to an individual's circadian rhythmicity related to sleep, diet, physical activity patterns, etc. The circadian rhythm is a biological internal process that is executed in the background of daily functions and regulates the user's 24-hour cycle (or approximately 24-hour cycle). The circadian rhythm regulates biological functions and processes including, but not limited to, the sleep-wake cycle, arousal level, digestion, body temperature, hormone release, etc. In some cases, the user's circadian rhythm (e.g., internal clock) is externally sensitive and may be affected by lifestyle choices and other factors. For example, being exposed to light at different times of the day, crossing multiple time zones, and working various shifts can be examples of affecting the internal clock.

[0020] In some cases, a determined circadian rhythm chronotype may be compared with physiological data received from a previous calendar day (e.g., including the previous night's sleep for the night preceding the current calendar day). For example, a determined circadian rhythm chronotype may be compared with sleep data from last night's sleep. In such cases, the system may determine whether the user's latest sleep data is consistent with the user's determined circadian rhythm chronotype. During circadian rhythm inconsistencies, the body system stops functioning optimally, and many users may suffer from significant sleep disorders, for example, due to circadian rhythm inconsistencies, and may also suffer from other symptoms that indicate a decrease in arousal level, academic performance, athletic performance, quality of life, and an increased risk of insomnia and chronic health conditions (e.g., sleep disorders, hypersensitivity, anxiety, obesity, diabetes, depression, and seasonal affective disorder).

[0021] In some cases, determining the circadian rhythm chronotype and detecting inconsistencies early on may reduce the risk of later-life health problems, particularly cardiovascular disease and cognitive impairment. In such cases, techniques for determining the circadian rhythm chronotype are desired in order to improve quality of life, sleep, and mood, and to reduce future health risks. For example, methods and techniques that help the user understand their circadian rhythm chronotype in a personalized way, and methods that optimize lifestyle changes to reduce inconsistencies, may be desired.

[0022] Some aspects of the present disclosure are directed to measuring and / or receiving physiological data or signals that are regulated and affected by the circadian rhythm. For example, the signals can include, but are not limited to, sleep-wake cycles, physical activity, body temperature, heart rate, recovery time, and the like. In some implementations, the computing device can cause the graphical user interface (GUI) of the user device to display a graphical representation of the averaging of one or more measured or calculated physiological parameters or characteristics, such as sleep pattern data, over a period of time. For example, the graphical representation can include the averaging of one or more measured or calculated physiological parameters over a period of time and a second set of physiological data including sleep data from at least the previous night's sleep.

[0023] In such cases, the computing device can generate a behavioral and physiological picture of the user's 24-hour clock from the user's physiological data. For example, the system can include wake time and bedtime (e.g., sleep time), the user's sleep regularity in the time frame in which the report is processed, the distribution of physical activity (e.g., metabolic equivalent of task (MET) data of tasks) indicating the user's energy consumption at different times of the day, the user's overall sleep body temperature change, or a combination thereof, and can create a prototype report from the circadian rhythm-related data.

[0024] The techniques described herein can notify a user of a determined circadian rhythm chronotype in various ways, including graphical representations of averaging over a period of time. For example, the system may cause the GUI of the user device to display a message or other notification that notifies the user of the determined circadian rhythm chronotype, and may provide recommendations to the user. In one example, the GUI may display a recommended time for the user to be active, a recommended wake-up time for the user to wake up, a recommended bedtime for the user to go to bed, a recommended sleep duration, a recommended time for the user to take a break, or a combination thereof. The GUI may also include graphics / text indicating an inconsistency between the received additional physiological data and the determined circadian rhythm chronotype. In such cases, the message or notification may be generated based on the inconsistency.

[0025] In some cases, understanding the user's circadian rhythm chronotype can enable the user to schedule sleep and daily activities so that the body can function based on the user's individualized circadian rhythm. For example, by determining and understanding the circadian rhythm chronotype, the user can improve mental, emotional, and physical performance by considering that the wake time line differs between morning and evening individuals throughout the day, and can recommend bedtime and wake-up times that match the user's determined chronotype, thereby improving the user's overall health.

[0026] Aspects of the present disclosure are first described in the context of a system that supports collection of physiological data from a user via a wearable device. Additional aspects of the present disclosure are described in the context of exemplary timing diagrams and exemplary GUIs. Aspects of the present disclosure are further illustrated and described with reference to apparatus diagrams, system diagrams, and flowcharts related to techniques for determining a circadian rhythm chronotype.

[0027] FIG. 1 shows an example of a system 100 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. The system 100 includes a plurality of electronic devices (e.g., wearable device 104, user device 106) that can be worn and / or operated by one or more users 102. The system 100 further includes a network 108 and one or more servers 110.

[0028] The electronic devices can include any electronic device known in the art, including wearable device 104 (e.g., ring wearable device, watch wearable device, etc.), user device 106 (e.g., smartphone, laptop, tablet). The electronic devices associated with each user 102 can include one or more of the following functions: namely, 1) measuring physiological data, 2) storing the measured data, 3) processing the data, 4) providing an output to the user 102 based on the processed data (e.g., via a GUI), and 5) communicating data with each other and / or with other computing devices. Different electronic devices may perform one or more of these functions.

[0029] Exemplary wearable device 104 can include a ring computing device (hereinafter, “ring”) configured to be worn on a finger of user 102, a wrist computing device (such as a smartwatch, fitness band or bracelet) configured to be worn on a wrist of user 102, and / or a head-mounted computing device (such as glasses / goggles), etc. Wearable device 104 can also include bands, straps (such as flexible or non-flexible bands or straps), stick-on sensors, etc., which can be disposed at other positions such as around the head (such as a forehead headband), around the arm (such as a forearm band and / or an upper arm band), and / or around the leg (such as a thigh or calf band), behind the ear, under the arm, etc. Wearable device 104 can also be attached to or included in clothing items. For example, wearable device 104 can be included in a pocket and / or a pouch of clothing. As another example, wearable device 104 can be clipped and / or pinned to clothing, or can be maintained in the vicinity of user 102 in other ways. Exemplary clothing items can include, but are not limited to, hats, shirts, gloves, pants, socks, tops (such as jackets) and undergarments. In some implementations, wearable device 104 can be included with other types of devices such as training / sports devices used during physical activity. For example, wearable device 104 can be attached to or included in a bicycle, skis, tennis racket, golf club and / or training weights.

[0030] Much of the present disclosure may be described in the context of the ring wearable device 104. Accordingly, the terms "ring 104", "wearable device 104" and similar terms may be used interchangeably herein unless otherwise specified. However, herein, it is contemplated that aspects of the present disclosure may be implemented using other wearable devices (e.g., watch wearable devices, necklace wearable devices, bracelet wearable devices, earring wearable devices, anklet wearable devices, etc.), so the use of the term "ring 104" should not be considered limiting.

[0031] In some aspects, the user device 106 may include a handheld mobile computing device such as a smartphone and a tablet computing device. The user device 106 may also include a personal computer such as a laptop and a desktop computing device. Other exemplary user devices 106 may include a server computing device that can communicate with other electronic devices (e.g., via the Internet). In some implementations, the computing device may include a medical device such as an external wearable computing device (e.g., a Holter monitor). The medical device may also include an implantable medical device such as a pacemaker and a defibrillator. Other exemplary user devices 106 may include home computing devices such as Internet of Things (IoT) devices (e.g., IoT devices), smart TVs, smart speakers, smart displays (e.g., video call displays), hubs (e.g., wireless communication hubs), security systems, smart appliances (e.g., thermostats and refrigerators), and fitness devices.

[0032] Some electronic devices (e.g., wearable device 104, user device 106) may measure physiological parameters of each user 102, such as photoplethysmography waveforms, continuous skin temperature, pulse waveforms, respiratory rate, heart rate, heart rate variability (HRV), actigraphy, galvanic skin response, pulse oxygen concentration, blood oxygen concentration (SpO2), blood glucose level (e.g., glucose metrics), and / or other physiological parameters. Some electronic devices that measure physiological parameters may also perform some / all of the calculations described herein. Some electronic devices may not measure physiological parameters, but may perform some / all of the calculations described herein. For example, a ring (e.g., wearable device 104), a mobile device application, or a server computing device may process received physiological data measured by other devices.

[0033] In some implementations, user 102 may operate or be associated with multiple electronic devices, some of which may measure physiological parameters and some of which may process the measured physiological parameters. In some implementations, user 102 may have a ring (e.g., wearable device 104) that measures physiological parameters. User 102 may have or be associated with a user device 106 (e.g., a mobile device, a smartphone), where wearable device 104 and user device 106 are communicatively coupled to each other. In some cases, user device 106 may receive data from wearable device 104 and perform some / all of the calculations described herein. In some implementations, user device 106 may also measure physiological parameters described herein, such as motion / activity parameters.

[0034] For example, as shown in FIG. 1, a first user 102-a (User 1) may operate or be associated with a wearable device 104-a (e.g., a ring 104-a) and a user device 106-a that can operate as described herein. In this example, the user device 106-a associated with user 102-a may process / store physiological parameters measured by the ring 104. In comparison, a second user 102-b (User 2) may be associated with a ring 104-b, a clock wearable device 104-c (e.g., a clock 104-c), and a user device 106-b, where the user device 106-b associated with user 102-b may process / store physiological parameters measured by the ring 104-b and / or the clock 104-c. Further, the nth user 102-n (User N) may be associated with a configuration of electronic devices (e.g., a ring 104, a user device 106-n) described herein. In some aspects, the wearable devices 104 (e.g., a ring 104, a clock 104) and other electronic devices may be communicatively coupled to the user device 106 of each user 102 via Bluetooth®, Wi-Fi, and other wireless protocols.

[0035] In some implementations, the ring 104 (e.g., the wearable device 104) of the system 100 may be configured to collect physiological data from each user 102 based on arterial blood flow in the user's finger. In particular, the ring 104 may utilize one or more LEDs (e.g., a red LED, a green LED, etc.) that emit light on the palm side of the user's finger to collect physiological data based on arterial blood flow in the user's finger. Generally, terms such as light-emitting components, light-emitting elements, etc. may include, but are not limited to, LEDs, micro-LEDs, mini-LEDs, laser diodes (LDs) (e.g., vertical cavity surface emitting lasers (VCSELs)), etc.

[0036] In some cases, system 100 may be configured to collect physiological data from each user 102 based on the blood flow diffused in the microvascular bed of the skin including capillaries and arterioles. For example, system 100 may collect PPG data based on the measured amount of blood diffused in the microvascular system of capillaries and arterioles. In some implementations, the ring 104 may use a combination of both green and red LEDs to acquire physiological data. The physiological data may include any physiological data known in the art, including but not limited to body temperature data, accelerometer data (e.g., movement / motion data), heart rate data, HRV data, blood oxygen level data, or any combination thereof.

[0037] Red and green LEDs have been found to have their own advantages, such as when acquiring physiological data through different parts of the body under different conditions (e.g., bright / dark, active / inactive). Therefore, the use of both green and red LEDs can offer several advantages over other solutions. For example, green LEDs have been found to exhibit better performance during exercise. Additionally, using a plurality of LEDs (e.g., green and red LEDs) dispersed around the ring 104 has been found to exhibit superior performance compared to wearable devices that utilize LEDs placed close to each other, such as within a watch wearable device. Furthermore, the blood vessels in the finger (e.g., arteries, capillaries) are more accessible via LEDs compared to the blood vessels in the wrist. In particular, the arteries in the wrist are located at the bottom of the wrist (e.g., the palm side of the wrist), which means that only capillaries are accessible at the top of the wrist (e.g., the back side of the wrist) where wearable watch devices and similar devices are typically worn. Thus, utilizing LEDs and other sensors within the ring 104 has been found to exhibit superior performance compared to wearable devices worn on the wrist, as the ring 104 can have greater access to arteries (compared to capillaries), thereby resulting in stronger signals and more valuable physiological data. In some cases, the system 100 may be configured to collect physiological data from each user 102 based on the blood flow diffused in the microvascular bed of the skin including capillaries and arterioles. For example, the system 100 may collect PPG data based on the measured amount of measured blood diffused in the microvascular system of capillaries and arterioles.

[0038] The electronic devices of system 100 (e.g., user device 106, wearable device 104) may be communicatively coupled to one or more servers 110 via a wired or wireless communication protocol. For example, as shown in FIG. 1, an electronic device (e.g., user device 106) may be communicatively coupled to one or more servers 110 via network 108. Network 108 may implement a Transmission Control Protocol and Internet Protocol (TCP / IP) such as the Internet, or may implement other network 108 protocols. The network connection between network 108 and each electronic device can facilitate the transfer of data via email, web, text messages, mail, or any other suitable form of interaction within computer network 108. For example, in some implementations, ring 104-a associated with first user 102-a may be communicatively coupled to user device 106-a, where user device 106-a is communicatively coupled to server 110 via network 108. In additional or alternative cases, wearable device 104 (e.g., ring 104, watch 104) may be communicatively coupled directly to network 108.

[0039] System 100 may provide an on-demand database service between user device 106 and one or more servers 110. In some cases, server 110 may receive data from user device 106 via network 108, store and analyze the data. Similarly, server 110 may provide data to user device 106 via network 108. In some cases, server 110 may be located in one or more data centers. Server 110 may be used for data storage, management, and processing. In some implementations, server 110 may provide a web-based interface to user device 106 via a web browser.

[0040] In some embodiments, system 100 may detect the period during which user 102 is sleeping and classify (e.g., sleep stage classify) the period during which user 102 is sleeping into one or more sleep stages. For example, as shown in FIG. 1, user 102-a may be associated with wearable device 104-a (e.g., ring 104-a) and user device 106-a. In this example, ring 104-a may collect physiological data associated with user 102-a, including body temperature, heart rate, HRV, respiratory rate, etc. In some embodiments, the data collected by ring 104-a may be input into a machine learning classifier, where the machine learning classifier is configured to determine the time period during which user 102-a is sleeping (has slept). Further, the machine learning classifier may be configured to classify the time period into different sleep stages, including wake-sleep stage, rapid eye movement (REM) sleep stage, light sleep stage (non-REM (NREM)), and deep sleep stage (NREM). In some embodiments, the classified sleep stages may be displayed to user 102-a via the GUI of user device 106-a. Sleep stage classification may be used to provide user 102-a with feedback regarding the user's sleep pattern, such as recommended bedtime and recommended wake-up time. Further, in some implementations, the sleep stage classification techniques described herein may be used to calculate scores for each user, such as Sleep Scores and Readiness Scores.

[0041] In some aspects, system 100 may further improve physiological data collection, data processing procedures, and other techniques described herein by leveraging features derived from the circadian rhythm. The term circadian rhythm may refer to a natural internal process that regulates an individual's sleep-wake cycle and repeats approximately every 24 hours. In this regard, the techniques described herein may utilize a circadian rhythm adjustment model to improve physiological data collection, analysis, and data processing. For example, the circadian rhythm adjustment model may be input into a machine learning classifier along with physiological data collected from user 102 via wearable device 104-a. In this example, the circadian rhythm adjustment model may be configured to "weight" or adjust physiological data collected over the user's natural approximately 24-hour circadian rhythm. In some implementations, the system may initially start with a "baseline" circadian rhythm adjustment model, use physiological data collected from each user 102 to modify the baseline model, and generate a customized, individualized circadian rhythm adjustment model specific to each user 102.

[0042] In some embodiments, system 100 may utilize other biological rhythms to further improve the collection, analysis, and processing of physiological data based on the phases of these other rhythms. For example, if a weekly rhythm is detected within an individual's baseline data, the model may be configured to adjust the "weight" of the data by day of the week. Biological rhythms that may require adjustment to the model in this way include: 1) ultradian (faster than a 24-hour rhythm, including sleep cycles during sleep and variations in measured physiological variables between wakefulness and sleep states ranging from less than one hour to several hours of periodicity); 2) circadian rhythms; 3) non-endogenous daily rhythms that are imposed on top of circadian rhythms, such as work schedules; 4) weekly rhythms, or other artificial time periods imposed externally (e.g., in a virtual culture with a 12-day "week," a 12-day rhythm can be used); 5) ovarian rhythms over multiple days in women and spermatogenesis rhythms in men; 6) lunar rhythms (relevant to people living in conditions with little or no artificial lighting); and 7) seasonal rhythms.

[0043] Biological rhythms are not necessarily steady rhythms. For example, many women experience variability in the length of their ovarian cycles over multiple cycles, and ultradian rhythms are not expected to occur at exactly the same time or with the same periodicity across days, even within a user. Therefore, signal processing techniques sufficient to quantify the frequency composition while maintaining the temporal resolution of these rhythms in physiological data can be used to improve the detection of these rhythms, assign the phase of each rhythm to each measured instant, and thereby modify the adjustment model and the comparison of time intervals. Biological rhythm-adjusted models and parameters can be added as needed in linear or non-linear combinations to more accurately capture the dynamic physiological baseline of an individual or group of individuals.

[0044] In some aspects, each device of system 100 may support techniques for determining a circadian rhythm chronotype based on data collected by wearable device 104. In particular, the system 100 illustrated in FIG. 1 may support techniques for determining the circadian rhythm chronotype of user 102 and causing user device 106 corresponding to user 102 to display a graphical representation of an averaging of sleep pattern data over a period of time (e.g., the most recent 30 or 60 days) of the sleep pattern data for sleep pattern data from the previous night's sleep.

[0045] For example, as shown in FIG. 1, user 1 (user 102-a) may be associated with wearable device 104-a (e.g., ring 104-a) and user device 106-a. In this example, ring 104-a may collect data associated with user 102-a, including continuous nocturnal body temperature data, activity data, sleep pattern data, heart rate, etc. As used herein, "continuous" nocturnal body temperature may refer to the ability of system 100 to sample the body temperature of user 102-a continuously during the day and / or night at a sufficient rate (e.g., 1 sample per minute) to provide sufficient body temperature data for the analysis described herein.

[0046] In some aspects, the data collected by ring 104-a may be used to classify physiological data from wearable device 104-a into the circadian rhythm chronotype of user 1 using a machine learning model. Determination of the circadian rhythm chronotype may be performed by any of the components of system 100, including ring 104-a, user device 106-a associated with user 1, one or more servers 110, or any combination thereof. Once the circadian rhythm chronotype is determined, system 100 may optionally cause a graphical representation indicating the determined chronotype, one or more physiological parameters used to classify the chronotype, or some combination of this information to be displayed on the GUI of user device 106-a.

[0047] For example, system 100 may cause the GUI of user device 106-a to display an averaging of at least sleep pattern data over a certain period. In other examples, system 100 may cause the GUI of user device 106-a to display the sleep pattern data of user 1 from the previous night's sleep. In some examples, this information may be simultaneously displayed in a way that enables the user to easily view multiple types of information overlaid on a time scale (such as the face of a 24-hour clock, etc.), such that multiple insights or relationships between different physiological parameters or chronotypes (such as average bedtime or wake-up time compared to last night's bedtime or wake-up time) may become apparent.

[0048] In some implementations, upon receiving physiological data (e.g., including at least consecutive night-time body temperature data, activity data, and sleep pattern data), system 100 may use a machine learning model to classify the physiological data into circadian rhythm chronotypes (e.g., determine whether the person is active, has a regular sleep schedule, etc.). In some examples, system 100 can overlay an averaging of at least sleep pattern data over a certain period and a graphical representation of sleep pattern data from the previous night's sleep onto a circular representation of a 24-hour time span. In such a case, system 100 can cause the GUI of user device 106-a to display a first segment including the averaging of sleep pattern data over a certain period and a second segment including sleep pattern data from the previous night's sleep.

[0049] In some cases, system 100 can display the first segment and the second segment to user 1 (e.g., via the GUI of user device 106). In some implementations, system 100 can generate an alert, message, or recommendation to user 1 (e.g., via ring 104-a, user device 106-a, or both) based on the determined circadian rhythm chronotype, where the alert can provide insights regarding a mismatch between the received physiological data and the determined circadian rhythm chronotype. In some cases, the message can provide insights regarding the recommended times for exercise, waking up, going to bed, resting, or combinations thereof.

[0050] One of ordinary skill in the art should understand that one or more aspects of the present disclosure may be implemented in system 100 to additionally or alternatively solve other problems other than those described above. Further, aspects of the present disclosure may provide a technical improvement to the "conventional" systems or processes described herein. However, the present specification and the accompanying drawings only include exemplary technical improvements resulting from implementing aspects of the present disclosure, and thus do not represent all of the technical improvements provided within the scope of the claims.

[0051] FIG. 2 shows an example of system 200 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. System 200 may implement system 100 or may be implemented by system 100. In particular, system 200 shows examples of ring 104 (e.g., wearable device 104), user device 106, and server 110 as described with reference to FIG. 1.

[0052] In some aspects, ring 104 may be configured to be worn around a user's finger and may determine one or more physiological parameters of the user when worn around the user's finger. Exemplary measurements and determinations may include, but are not limited to, the user's skin temperature, pulse waveform, respiratory rate, heart rate, HRV, blood oxygen level (SpO2), blood glucose level (e.g., glucose metrics), etc.

[0053] System 200 further includes a user device 106 (such as a smartphone) that communicates with the ring 104. For example, the ring 104 may communicate wirelessly and / or wiredly with the user device 106. In some implementations, the ring 104 may send measured and processed data (such as body temperature data, photoplethysmograph (PPG) data, motion / accelerometer data, ring input data, etc.) to the user device 106. The user device 106 may also send data such as firmware / configuration updates of the ring 104 to the ring 104. The user device 106 may process the data. In some implementations, the user device 106 may send the data to the server 110 for processing and / or storage.

[0054] The ring 104 may include a housing 205, which may include an inner housing 205-a and an outer housing 205-b. In some aspects, the housing 205 of the ring 104 may store or otherwise include various components of the ring, including but not limited to device electronics, a power source (such as a battery 210 and / or a capacitor), and one or more substrates (such as a printed circuit board) that interconnect the device electronics and / or the power source. The device electronics may include device modules (such as hardware / software) such as a processing module 230-a, a memory 215, a communication module 220-a, a power module 225, etc. The device electronics may also include one or more sensors. Exemplary sensors may include one or more temperature sensors 240, a PPG sensor assembly (such as a PPG system 235), and one or more motion sensors 245.

[0055] The sensor may include an associated module (not shown) configured to communicate with each component / module of the ring 104 and generate signals associated with each sensor. In some aspects, each of the components / modules of the ring 104 may be communicatively coupled to each other via a wired or wireless connection. Further, the ring 104 may include additional and / or alternative sensors or other components configured to collect physiological data from the user, including, for example, optical sensors (such as LEDs), oximeters, and the like.

[0056] The ring 104 illustrated and described with reference to FIG. 2 is provided for illustrative purposes only. Thus, the ring 104 may include additional or alternative components such as those shown in FIG. 2. Other rings 104 may be manufactured that provide the functionality described herein. For example, a ring 104 having fewer components (such as sensors) may be manufactured. In a particular example, a ring 104 may be manufactured having a single temperature sensor 240 (or other sensor), a power source, and device electronics configured to read the single temperature sensor 240 (or other sensor). In another specific example, the temperature sensor 240 (or other sensor) may be attached to the user's finger (using, for example, an adhesive, wrap, clamp, spring clamp, etc.). In this case, the sensor may be wired to another computing device, such as a wrist-worn computing device, that reads the temperature sensor 240 (or other sensor). In other examples, a ring 104 may be manufactured that includes additional sensors and processing capabilities.

[0057] The housing 205 may include one or more housing 205 components. The housing 205 may include an outer housing 205-b component (such as a shell) and an inner housing 205-a component (such as a molding). The housing 205 may also include additional components (such as additional layers) not explicitly illustrated in FIG. 2. For example, in some implementations, the ring 104 may include one or more insulating layers that electrically insulate device electronics and other conductive materials (such as electrical traces) from the outer housing 205 (such as a metal outer housing 205-b). The housing 205 may provide structural support for device electronics, the battery 210, the substrate, and other components. For example, the housing 205 may protect device electronics, the battery 210, and the substrate from mechanical forces such as pressure and shock. The housing 205 may also protect device electronics, the battery 210, and the substrate from water and / or other chemicals.

[0058] The outer housing 205-b may be manufactured from one or more materials. In some implementations, the outer housing 205-b may include a metal such as titanium, which may be relatively lightweight and provide strength and wear resistance. The outer housing 205-b may also be manufactured from other materials such as polymers. In some implementations, the outer housing 205-b may be both decorative and protective.

[0059] The inner housing 205-a may be configured to interface with a user's finger. The inner housing 205-a may be formed from a polymer (such as a medical grade polymer) or other material. In some implementations, the inner housing 205-a may be transparent. For example, the inner housing 205-a may be transparent to light emitted by a PPG LED. In some implementations, the inner housing 205-a may be molded over the outer housing 205-b. For example, the inner housing 205-a may include a polymer that is molded (such as injection molded) to conform to the outer housing 205 metal shell.

[0060] The ring 104 may include one or more substrates (not shown). Device electronics and the battery 210 may be included on one or more substrates. For example, the device electronics and the battery 210 may be mounted on one or more substrates. Exemplary substrates may include one or more printed circuit boards (PCBs) such as flexible PCBs (e.g., polyimide). In some implementations, the electronics / battery 210 may include surface mount devices (e.g., surface-mount technology (SMT) devices) on a flexible PCB. In some implementations, one or more substrates (e.g., one or more flexible PCBs) may include electrical traces that provide electrical communication between the device electronics. The electrical traces may also connect the battery 210 to the device electronics.

[0061] The device electronics, the battery 210, and the substrate may be arranged within the ring 104 in various ways. In some implementations, a substrate including the device electronics may be attached along the lower portion (e.g., the lower half) of the ring 104 such that sensors (e.g., the PPG system 235, the temperature sensor 240, the motion sensor 245, and other sensors) interface with the underside of the user's finger. In these implementations, the battery 210 may be included along the upper portion of the ring 104 (e.g., on a separate substrate).

[0062] The various components / modules of the ring 104 represent the functionality (e.g., circuitry and other components) that may be included in the ring 104. A module may include any discrete and / or integrated electronic circuit components that implement analog and / or digital circuitry capable of generating the functions attributable to the modules herein. For example, a module may include analog circuitry (e.g., amplifier circuitry, filtering circuitry, analog / digital conversion circuitry, and / or other signal conditioning circuitry). A module may also include digital circuitry (e.g., combinational logic circuitry or sequential logic circuitry, memory circuitry, etc.).

[0063] The memory 215 (memory module) of the ring 104 may include any volatile, non-volatile, magnetic or electrical medium, such as a random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically erasable programmable ROM (EEPROM), flash memory or any other memory device. The memory 215 may store any of the data described herein. For example, the memory 215 may be configured to store data (such as operation data, body temperature data, PPG data) collected by each sensor and the PPG system 235. Further, the memory 215 may include instructions that, when executed by one or more processing circuits, cause the module to perform various functions attributable to the modules herein. The device electronics of the ring 104 described herein are merely an example of device electronics. Thus, the types of electronic components used to implement the device electronics may vary based on design considerations.

[0064] The functions attributable to the modules of the ring 104 described herein may be embodied as one or more processors, hardware, firmware, software, or any combination thereof. Describing different features as modules is intended to emphasize different functional aspects and does not necessarily imply that such modules must be implemented by separate hardware / software components. Rather, the functionality associated with one or more modules may be executed by separate hardware / software components or integrated within a common hardware / software component.

[0065] The processing module 230-a of the ring 104 may include one or more processors (e.g., processing units), microcontrollers, digital signal processors, system-on-chips (SoCs), and / or other processing devices. The processing module 230-a communicates with the modules included in the ring 104. For example, the processing module 230-a may send data to and receive data from modules of the ring 104, such as sensors, and other components. As described herein, the modules may be implemented by various circuit components. Thus, the modules may sometimes also be referred to as circuits (e.g., communication circuits and power circuits).

[0066] The processing module 230-a may communicate with the memory 215. The memory 215 may include computer-readable instructions that, when executed by the processing module 230-a, cause the processing module 230-a to perform various functions attributable to the processing module 230-a. In some implementations, the processing module 230-a (e.g., a microcontroller) may include additional features associated with other modules, such as communication functions provided by the communication module 220-a (e.g., an integrated Bluetooth (R) Low Energy transceiver) and / or additional on-board memory 215.

[0067] Communication module 220-a may include circuitry to provide wireless communication and / or wired communication with user device 106 (e.g., communication module 220-b of user device 106). In some implementations, communication modules 220-a, 220-b may include wireless communication circuitry such as Bluetooth circuitry and / or Wi-Fi circuitry. In some implementations, communication modules 220-a, 220-b may include wired communication circuitry such as universal serial bus (USB) communication circuitry. Using communication module 220-a, ring 104 and user device 106 may be configured to communicate with each other. Ring processing module 230-a may be configured to transmit data to / from user device 106 via communication module 220-a. Exemplary data may include, but is not limited to, motion data, body temperature data, pulse waveform, heart rate data, HRV data, PPG data, and status updates (e.g., charge status, battery charge level, and / or ring 104 configuration settings). Ring processing module 230-a may also be configured to receive updates (e.g., software / firmware updates) and data from user device 106.

[0068] The ring 104 may include a battery 210 (e.g., a rechargeable battery 210). Exemplary batteries 210 may include lithium-ion or lithium-polymer type batteries 210, although various battery 210 options are possible. The battery 210 may be charged wirelessly. In some implementations, the ring 104 may include a power source other than the battery 210, such as a capacitor. The power source (e.g., the battery 210 or capacitor) may have a curved shape that conforms to the curve of the ring 104. In some aspects, a charger or other power source may include additional sensors that can be used to collect data or supplement the data collected by the ring 104 itself. Further, the charger or other power source for the ring 104 may function as a user device 106, in which case the charger or other power source for the ring 104 is configured to receive data from the ring 104, store and / or process the data received from the ring 104, and communicate the data between the ring 104 and the server 110.

[0069] In some aspects, the ring 104 includes a power module 225 that may control the charging of the battery 210. For example, the power module 225 may interface with an external wireless charger that charges the battery 210 when interfacing with the ring 104. The charger may include a data structure that mates with the data structure of the ring 104 to generate a specific orientation with the ring 104 during charging. The power module 225 may also regulate the voltage of the device electronics, regulate the power output to the device electronics, and monitor the charge state of the battery 210. In some implementations, the battery 210 may include a protection circuit module (PCM) that protects the battery 210 from high current discharge, overvoltage during charging, and undervoltage during discharging. The power module 225 may also include electrostatic discharge (ESD) protection.

[0070] One or more temperature sensors 240 may be electrically coupled to the processing module 230-a. The temperature sensor 240 may be configured to generate a body temperature signal (e.g., body temperature data) indicative of the body temperature read or sensed by the temperature sensor 240. The processing module 230-a may determine the user's body temperature at the location of the temperature sensor 240. For example, in the ring 104, the body temperature data generated by the temperature sensor 240 may indicate the user's body temperature (e.g., skin temperature) at the user's finger. In some implementations, the temperature sensor 240 may be in contact with the user's skin. In other implementations, a portion of the housing 205 (e.g., the inner housing 205-a) may form a barrier (e.g., a thin thermal conductivity barrier) between the temperature sensor 240 and the user's skin. In some implementations, the portion of the ring 104 configured to contact the user's finger may have a thermally conductive portion and a thermally insulating portion. The thermally conductive portion may conduct heat from the user's finger to the temperature sensor 240. The thermally insulating portion may insulate the portion of the ring 104 (e.g., the temperature sensor 240) from the ambient temperature.

[0071] In some implementations, the temperature sensor 240 may be configured to generate a digital signal (e.g., body temperature data) that the processing module 230-a may use to determine the body temperature. As another example, if the temperature sensor 240 includes a passive sensor, the processing module 230-a (or the temperature sensor 240 module) may measure the current / voltage generated by the temperature sensor 240 and determine the body temperature based on the measured current / voltage. Exemplary temperature sensors 240 may include thermistors such as negative temperature coefficient (NTC) thermistors, or other types of sensors including resistors, transistors, diodes, and / or other electrical / electronic components.

[0072] The processing module 230-a may sample the user's body temperature over time. For example, the processing module 230-a may sample the user's body temperature according to a sampling rate. An exemplary sampling rate may include 1 sample per second, but the processing module 230-a may be configured to sample the body temperature signal at other sampling rates higher or lower than 1 sample per second. In some implementations, the processing module 230-a may continuously sample the user's body temperature throughout the day and night. By sampling at a sufficient rate throughout the day (e.g., 1 sample per second), sufficient body temperature data for the analysis described herein may be provided.

[0073] The processing module 230-a may store the sampled body temperature data in the memory 215. In some implementations, the processing module 230-a may process the sampled body temperature data. For example, the processing module 230-a may determine an average body temperature value for a certain time period. In one example, the processing module 230-a may sum all the body temperature values collected in one minute and divide by the number of samples in one minute to determine the average body temperature value per minute. In a specific example where the body temperature is sampled at 1 sample per second, the average body temperature may be the sum of all the sampled body temperatures in one minute divided by 60 seconds. The memory 215 may store the average body temperature value over time. In some implementations, the memory 215 may store the average body temperature (e.g., 1 per minute) instead of the sampled body temperatures to conserve memory 215.

[0074] The sampling rate that can be stored in the memory 215 can be configurable. In some implementations, the sampling rate may be the same throughout the day and night. In other implementations, the sampling rate may be changed throughout the day / night. In some implementations, the ring 104 may filter / reject body temperature readings such as large spikes in body temperature that do not indicate physiological changes (e.g., temperature spikes from a hot shower). In some implementations, the ring 104 may filter / reject body temperature readings that may be unreliable due to other factors such as excessive movement during exercise (e.g., as indicated by the motion sensor 245).

[0075] The ring 104 (e.g., the communication module) may send the sampled body temperature data and / or the average body temperature data to the user device 106 for storage and / or further processing. The user device 106 may transfer the sampled body temperature data and / or the average body temperature data to the server 110 for storage and / or further processing.

[0076] The ring 104 is shown as including a single temperature sensor 240, but the ring 104 may include a plurality of temperature sensors 240 at one or more locations, such as being disposed along the inner housing 205-a near the user's finger. In some implementations, the temperature sensor 240 may be a stand-alone temperature sensor 240. Additionally or alternatively, one or more temperature sensors 240 may be included together with other components such as an accelerometer and / or a processor (e.g., may be packaged together with other components).

[0077] Processing module 230-a may acquire and process data from multiple temperature sensors 240 in the same way as described for a single temperature sensor 240. For example, processing module 230 may individually sample, average, and store body temperature data from each of the multiple temperature sensors 240. In other examples, processing module 230-a may sample the sensors at different rates and average / store different values for different sensors. In some implementations, processing module 230-a may be configured to determine a single body temperature based on the average of two or more body temperatures determined by two or more temperature sensors 240 at different positions on the finger.

[0078] The temperature sensors 240 on the ring 104 may acquire the distal body temperature at the user's finger (e.g., any finger). For example, one or more temperature sensors 240 on the ring 104 may acquire the user's body temperature from the underside of the finger or at different positions on the finger. In some implementations, the ring 104 may continuously acquire the distal body temperature (e.g., at a sampling rate). Although the distal temperature measured by the ring 104 on the finger is described herein, other devices may measure body temperature at the same / different positions. In some cases, the distal body temperature measured at the user's finger may be different from the body temperature measured at the user's wrist or other external body location. Additionally, the distal body temperature measured at the user's finger (e.g., "shell" body temperature) may be different from the user's core body temperature. Thus, the ring 104 may provide a useful body temperature signal that may not be acquired at other internal / external locations of the body. In some cases, continuous body temperature measurements at the finger may capture body temperature variations (e.g., small or large variations) that may not be apparent from core body temperature. For example, continuous body temperature measurements at the finger may capture minute-by-minute or hourly body temperature variations that provide additional insights not provided by other body temperature measurements at other locations on the body.

[0079] Ring 104 may include a PPG system 235. The PPG system 235 may include one or more optical transmitters that transmit light. The PPG system 235 may also include one or more optical receivers that receive the light transmitted by the one or more optical transmitters. The optical receiver may generate a signal (hereinafter referred to as a "PPG" signal) indicating the amount of light received by the optical receiver. The optical transmitter may illuminate an area of the user's finger. The PPG signal generated by the PPG system 235 may indicate the perfusion of blood in the illuminated area. For example, the PPG signal may indicate a change in the amount of blood in the illuminated area caused by the user's pulse pressure. The processing module 230-a may sample the PPG signal and determine the user's pulse waveform based on the PPG signal. The processing module 230-a may determine various physiological parameters such as the user's respiratory rate, heart rate, HRV, oxygen saturation, and other circulatory parameters based on the user's pulse waveform.

[0080] In some implementations, the PPG system 235 may be configured as a reflective PPG system 235 in which the optical receiver receives transmitted light reflected through an area of the user's finger. In some implementations, the PPG system 235 may be configured as a transmissive PPG system 235 in which the optical transmitter and the optical receiver are arranged opposite each other such that light is transmitted directly to the optical receiver through a portion of the user's finger.

[0081] The number and ratio of transmitters and receivers included in the PPG system 235 may vary. Exemplary optical transmitters may include light emitting diodes (LEDs). The optical transmitter may transmit light in the infrared spectrum and / or other spectra. Exemplary optical receivers may include, but are not limited to, photosensors, phototransistors, and photodiodes. The optical receiver may be configured to generate a PPG signal in response to the wavelength received from the optical transmitter. The positions of the transmitter and the receiver may vary. Additionally, a single device may include a reflective and / or transmissive PPG system 235.

[0082] In some implementations, the PPG system 235 shown in FIG. 2 may include a reflective PPG system 235. In these implementations, the PPG system 235 may include a centrally located photoreceiver (e.g., below the ring 104) and two optical transmitters located on both sides of the photoreceiver. In this implementation, the PPG system 235 (e.g., the photoreceiver) may generate a PPG signal based on the light received from one or both of the optical transmitters. In other implementations, other arrangements, combinations, and / or configurations of one or more optical transmitters and / or photoreceivers are contemplated.

[0083] The processing module 230-a may control one or both of the optical transmitters to transmit light while sampling the PPG signal generated by the photoreceiver. In some implementations, the processing module 230-a may cause the optical transmitter with the stronger received signal to transmit light while sampling the PPG signal generated by the photoreceiver. For example, the selected optical transmitter may continuously emit light while the PPG signal is being sampled at a sampling rate (e.g., 250 Hz).

[0084] By sampling the PPG signal generated by the system 235, a pulse waveform can be obtained, which may be referred to as "PPG". The pulse waveform may show blood pressure versus time for multiple cardiac cycles. The pulse waveform may include peaks indicating the cardiac cycle. Additionally, the pulse waveform may include respiratory induced variations that can be used to determine the respiratory rate. In some implementations, the processing module 230-a may store the pulse waveform in the memory 215. The processing module 230-a may process the pulse waveform when it is generated and / or the pulse waveform from the memory 215 to determine the user's physiological parameters described herein.

[0085] The processing module 230-a can determine the user's heart rate based on the pulse waveform. For example, the processing module 230-a can determine the heart rate (e.g., the number of beats per minute) based on the time between the peaks of the pulse waveform. The time between the peaks may be referred to as the interbeat interval (IBI). The processing module 230-a may store the determined heart rate value and the IBI value in the memory 215.

[0086] The processing module 230-a can determine the HRV over time. For example, the processing module 230-a may determine the HRV based on the variation of the IBl. The processing module 230-a may store the HRV value over time in the memory 215. Further, the processing module 230-a can determine the user's respiratory rate over time. For example, the processing module 230-a may determine the respiratory rate based on the frequency modulation, amplitude modulation, or baseline modulation of the user's IBI value over a certain period. The respiratory rate may be calculated per breath per minute, or may be calculated as another respiratory rate (e.g., breaths per 30 seconds). The processing module 230-a may store the value of the user's respiratory rate over time in the memory 215.

[0087] The ring 104 may include one or more motion sensors 245 such as one or more accelerometers (e.g., 6-D accelerometers) and / or one or more gyroscopes (gyros). The motion sensor 245 can generate a motion signal indicating the motion of the sensor. For example, the ring 104 may include one or more accelerometers that generate an acceleration signal indicating the acceleration of the accelerometer. As another example, the ring 104 may include one or more gyro sensors that generate a gyro signal indicating the change in angular motion (e.g., angular velocity) and / or orientation. The motion sensor 245 may be included in one or more sensor packages. An exemplary accelerometer / gyro sensor is the Bosch (registered trademark) BMI160 inertial micro electro-mechanical system (MEMS) sensor that can measure angular velocity and acceleration in three perpendicular axes.

[0088] The processing module 230-a may sample the motion signal at a sampling rate (e.g., 50 Hz) and determine the motion of the ring 104 based on the sampled motion signal. For example, the processing module 230-a may sample the acceleration signal to determine the acceleration of the ring 104. As another example, the processing module 230-a may sample the gyro signal to determine the angular motion. In some implementations, the processing module 230-a may store the motion data in the memory 215. The motion data may include the sampled motion data and the motion data calculated based on the sampled motion signals (e.g., acceleration and angle values).

[0089] The ring 104 may store various data described herein. For example, the ring 104 may store body temperature data such as raw sampled body temperature data and calculated body temperature data (e.g., average temperature). As another example, the ring 104 may store PPG signal data such as a pulse waveform and data calculated based on the pulse waveform (e.g., heart rate value, IBI value, HRV value, and respiratory rate value). The ring 104 may also store motion data such as sampled motion data indicating linear motion and angular motion.

[0090] Ring 104 or another computing device may calculate and store additional values based on the sampled / computed physiological data. For example, the processing module 230 may calculate and store various metrics such as sleep metrics (e.g., sleep score), activity metrics, and readiness metrics. In some implementations, the additional values / metrics may be referred to as "derived values". Ring 104 or another computing / wearable device may calculate various values / metrics regarding exercise. Exemplary derived values of the motion data may include, but are not limited to, a motion count value, regularity values, intensity values, metabolic equivalence of task values (METs) of a task, and direction values. The motion count, regularity values, intensity values, and METs may indicate the amount of the user's motion over time (e.g., speed / acceleration). The direction value may indicate how Ring 104 is oriented with respect to the user's finger and whether Ring 104 is worn on the left hand or the right hand.

[0091] In some implementations, the motion count and regularity values may be determined by counting the number of acceleration peaks within one or more periods (e.g., one or more periods of 30 seconds to 1 minute). The intensity value may indicate the number of motions and the associated intensity of the motion (e.g., acceleration value). The intensity value may be classified as low, medium, and high according to the associated threshold acceleration value. METs may be determined based on the intensity of the motion during a 104 period (e.g., 30 seconds), the regularity / irregularity of the motion, and the number of motions associated with different intensities.

[0092] In some implementations, the processing module 230-a may compress the data stored in the memory 215. For example, after performing calculations based on the sampled data, the processing module 230-a may delete the sampled data. As another example, the processing module 230-a may average the data over a longer period to reduce the number of values stored. In a specific example, if the average body temperature of a user over one minute is stored in the memory 215, the processing module 230-a may calculate the average body temperature over five minutes for storage and then erase the one-minute average body temperature data. The processing module 230-a may compress the data based on various factors such as the total amount of memory 215 used / available and / or the elapsed time since the ring 104 last sent data to the user device 106.

[0093] The user's physiological parameters can be measured by the sensors included in the ring 104, but other devices may also measure the user's physiological parameters. For example, the user's body temperature can be measured by the temperature sensor 240 included in the ring 104, but other devices may also measure the user's body temperature. In some examples, other wearable devices (e.g., wrist devices) may include sensors that measure the user's physiological parameters. Additionally, medical devices such as external medical devices (e.g., wearable medical devices) and / or implantable medical devices may measure the user's physiological parameters. One or more sensors on any type of computing device may be used to implement the techniques described herein.

[0094] Physiological measurements may be performed continuously throughout the day and / or night. In some implementations, physiological measurements may be performed during the day portion and / or the night portion. In some implementations, physiological measurements may be performed in response to the user determining that they are in a particular state, such as an active state, a resting state, and / or a sleep state. For example, the ring 104 may be able to perform physiological measurements in a resting / sleep state in order to obtain a cleaner physiological signal. In one example, the ring 104 or other device / system may detect when the user is at rest and / or sleeping and obtain physiological parameters (such as body temperature) of the detected state. The device / system may use the resting / sleep physiological data and / or other data when the user is in other states in order to implement the techniques of the present disclosure.

[0095] In some implementations, as described above herein, the ring 104 may be configured to collect, store, and / or process data and may transfer any of the data described herein to the user device 106 for storage and / or processing. In some aspects, the user device 106 includes a wearable application 250, an operating system (OS), a web browser application (such as web browser 280), one or more additional applications, and a GUI 275. The user device 106 may further include other modules and components, including sensors, audio devices, tactile feedback devices, and the like. The wearable application 250 may include an example of an application (such as an "app") that may be installed on the user device 106. The wearable application 250 may be configured to obtain data from the ring 104, store the obtained data, and process the obtained data, as described herein. For example, the wearable application 250 may include a user interface (UI) module 255, an acquisition module 260, a processing module 230-b, a communication module 220-b, and a storage module (such as database 265) configured to store application data.

[0096] The various data processing operations described in this specification can be performed by the ring 104, the user device 106, the server 110, or any combination thereof. For example, in some cases, data collected by the ring 104 may be pre-processed and sent to the user device 106. In this example, the user device 106 may perform some data processing operations on the received data, send the data to the server 110 for data processing, or do both. For example, in some cases, the user device 106 may perform operations that require relatively low processing power and / or operations that require relatively low latency, while the user device 106 may send data to the server 110 to process operations that require relatively high processing power and / or operations that can tolerate relatively high latency.

[0097] In some aspects, the ring 104, the user device 106, and the server 110 of the system 200 can be configured to evaluate the user's sleep pattern. In particular, each component of the system 200 can collect data from the user via the ring 104 and be used to generate one or more scores (e.g., sleep score, readiness score) for the user based on the collected data. For example, as previously described herein, the ring 104 of the system 200 can be worn by the user to collect data including body temperature, heart rate, HRV, etc. from the user. The data collected by the ring 104 can be used to determine when the user is asleep to evaluate the user's sleep for a given "sleep day". In some aspects, the scores can be calculated for each sleep day of the user such that the first sleep day is associated with the first score set and the second sleep day is associated with the second score set. The scores can be calculated for each sleep day based on the data collected by the ring 104 during each respective sleep day. The scores can include, but are not limited to, sleep scores, readiness scores, etc.

[0098] In some cases, a "sleep day" may align with the traditional calendar day such that a given sleep day extends from midnight to midnight of each calendar day. In other cases, the sleep day may be offset relative to the calendar day. For example, the sleep day may extend from 6:00 PM (18:00) of one calendar day to 6:00 PM (18:00) of the next calendar day. In this example, 6:00 PM may function as a "cut-off time", in which case data collected from the user before 6:00 PM is counted for the current sleep day and data collected from the user after 6:00 PM is counted for the next sleep day. Due to the fact that most individuals sleep the most at night, by offsetting the sleep day relative to the calendar day, system 200 can evaluate the user's sleep pattern in a way that aligns with the user's sleep schedule. In some cases, the user can selectively adjust the timing of the sleep day relative to the calendar day (e.g., via a GUI) so as to align the sleep day with the period during which each user typically sleeps.

[0099] In some implementations, each user's overall score (e.g., sleep score, readiness score) for each day can be determined / calculated based on one or more "contributors", "factors", or "contributing factors". For example, a user's overall sleep score can be calculated based on a set of contributing factors that includes total sleep, efficiency, rest, REM sleep, deep sleep, latency, timing, or any combination thereof. The sleep score can include any amount of contributing factors. The "total sleep" contributing factor may refer to the sum of the total sleep periods of a sleep day. The "efficiency" contributing factor may reflect the percentage of time spent sleeping compared to the time spent awake while in bed, and can be calculated using the average efficiency of the long sleep periods (e.g., primary sleep periods) of a sleep day, weighted by the duration of each sleep period. The "rest" contributing factor may indicate how peaceful the user's sleep is, and can be calculated using the average of all sleep periods of a sleep day, weighted by the duration of each period. The rest contributing factor can be based on the "wake-up count" (e.g., the total of all wake-ups (when the user wakes up) detected during different sleep periods), excessive movement, and the "got up count" (e.g., the total of all got-ups (when the user gets up from the bed) detected during different sleep periods).

[0100] The "REM sleep" contributing factor may refer to the total REM sleep duration over all sleep periods on a sleep day that includes REM sleep. Similarly, the "deep sleep" contributing factor may refer to the total deep sleep duration over all sleep periods on a sleep day that includes deep sleep. The "latency" contributing factor may mean the time it takes for the user to fall asleep (e.g., average, median, longest), and may be calculated using the average of long sleep periods throughout the sleep day, weighted by the duration of each period and the number of such durations (e.g., the integration of a given sleep stage or multiple sleep stages may be its own contributing factor or may weight other contributing factors). Finally, the "timing" contributing factor may refer to the relative timing of sleep periods within a sleep day and / or calendar day, and may be calculated using the average of all sleep periods on the sleep day, weighted by the duration of each period.

[0101] As another example, the user's overall readiness score may be calculated based on a set of contributing factors that include sleep, sleep balance, heart rate, HRV balance, recovery index, body temperature, activity, activity balance, or any combination thereof. The readiness score may include any amount of contributing factors. The "sleep" contributing factor may refer to the combined sleep score of all sleep periods within a sleep day. The "sleep balance" contributing factor may refer to the cumulative duration of all sleep periods within a sleep day. In particular, the sleep balance can show the user whether the sleep the user has obtained over a period (e.g., the past two weeks) is balanced with the user's needs. Typically, adults need 7 - 9 hours of sleep per night to be healthy, maintain concentration, and perform at their best mentally and physically. However, since it is normal to have nights when one doesn't sleep well, the sleep balance contributing factor takes into account long-term sleep patterns to determine whether each user's sleep needs are being met. The "resting heart rate" contributing factor may indicate the lowest heart rate from the longest sleep period (e.g., the main sleep period) on the sleep day and / or the lowest heart rate from a nap that occurs after the main sleep period.

[0102] Continuing in relation to the "contributing factors" (e.g., factors, contributing factors) of the preparation score, the "HRV balance" contributing factor may indicate the highest average HRV from the main sleep period and from the naps that occur after the main sleep period. The HRV balance contributing factor can help the user track their recovery status by comparing the user's HRV trend over a first period (e.g., two weeks) to the average HRV over some longer second period (e.g., three months). The "recovery index" contributing factor may be calculated based on the longest sleep period. The recovery index measures the time it takes for the user's resting heart rate to stabilize during the night. A very good sign of recovery is for the user's resting heart rate to stabilize in the first half of the night, at least six hours before the user wakes up, leaving time for the body to recover for the next day. The "body temperature" contributing factor can be calculated based on the longest sleep period (e.g., the main sleep period), or based on the naps that occur after the longest sleep period if the user's highest body temperature during the naps is at least 0.5 °C higher than the highest body temperature during the longest period. In some embodiments, the ring may measure the user's body temperature while the user is sleeping, and the system 200 may display the user's average body temperature relative to the user's baseline body temperature. If the user's body temperature is outside the normal range (e.g., clearly above or below 0.0), the body temperature contributing factor may be highlighted (e.g., put in a "Pay attention" state) or otherwise generate an alert to the user.

[0103] In some embodiments, the system 200 may support techniques for determining the circadian rhythm chronotype. In particular, each component of the system 200 may use a machine learning model to classify physiological data from the wearable device 104 into a circadian rhythm chronotype based on receiving physiological data (e.g., including continuous nightly body temperature data, activity data, sleep pattern data, or additional or alternative physiological parameters). The user's circadian rhythm chronotype can be predicted by utilizing the temperature sensor, heart rate sensor, etc. on the ring 104 of the system 200.

[0104] System 200 can compare a determined circadian rhythm chronotype with sleep pattern data from the night before the current calendar day. In such a case, System 200 can display to user 102 a graphical representation of an averaging over at least a certain period of the sleep pattern data (e.g., the most recent 90 days or some other configurable period) with respect to the sleep pattern data from the night before the current calendar day.

[0105] For example, as previously described herein, the ring 104 of System 200 can be worn by user 102 and collect physiological data from user 102, including continuous nightly body temperature data, activity data, sleep pattern data, etc. The ring 104 of System 200 may collect physiological data from user 102 based on arterial blood flow, which can provide a more accurate measurement signal compared to measuring venous blood flow. However, the concepts described herein may also be applicable to measurements obtained from venous blood flow or from some combination of arterial and venous blood flow.

[0106] The physiological data may be collected continuously. In some implementations, the processing module 230-a can sample the user's body temperature continuously throughout the day and night. Sampling at a sufficient rate throughout the day (e.g., 1 sample per minute) can provide sufficient body temperature data for the analysis described herein. In some implementations, the ring 104 can continuously acquire body temperature data, activity data, sleep pattern data, heart rate data, etc. (e.g., at the sampling rate). The data collected by the ring 104 can be used to determine a circadian rhythm chronotype. Examples of circadian rhythm chronotype determination are further shown and described with reference to FIGS. 3 and 6.

[0107] Referring to system 200 shown in FIG. 2, the ring 104 may be worn by user 102 and may collect data associated with user 102 day and night (e.g., continuously). The ring 104 may collect data (such as body temperature, sleep, MET, heart rate) and transmit the collected data to the user device 106. In some cases, the user device 106 may transfer (e.g., relay, transmit) the data received from the ring 104 to the server 110 for processing. Additionally or alternatively, the user device 106 and / or the ring 104 may perform processing on the collected data.

[0108] Continuing with the same example, the ring 104, the user device 106, the server 110, or any combination thereof may determine a circadian rhythm chronotype based on the collected data. Once the circadian rhythm chronotype is determined, the server 110 may transmit an indicator of the circadian rhythm chronotype to the user device 106. Alternatively, if the user device 106 performs data processing, the user device 106 may generate an indicator of the determined circadian rhythm chronotype. In this example, when the user next opens the wearable application 250, the indicator of the determined circadian rhythm chronotype may be presented to the user via the GUI 275 of the user device 106. This process and some exemplary but non-limiting examples of user interfaces are further described with reference to FIG. 8.

[0109] For the purposes of this disclosure, the terms "circadian rhythm chronotype", "circadian chronotype", "circadian profile", and similar terms may be used interchangeably. In some cases, the system 100 (e.g., the user device 106, the server 110) may be configured to receive data collected from the user 102 via the ring 104 and determine a circadian rhythm chronotype.

[0110] FIG. 3 shows an example of a system 300 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. System 300 may implement, or be implemented by, system 100, system 200, or both. In particular, system 300 shows examples of a ring 104 (e.g., wearable device 104), user device 106, and server 110 as described with reference to FIG. 1.

[0111] System 300 may include an algorithm for characterizing a chronotype. In such a case, system 300 may determine a circadian rhythm chronotype from one or more data sources. As further described herein, when system 300 receives a data volume that meets a threshold, system 300 may determine a circadian rhythm chronotype. If system 300 determines that the data volume does not meet the threshold, system 300 may refrain from determining a circadian rhythm chronotype. System 300 may include one or more processing pipelines and a collective estimation for each processing pipeline. For example, system 300 may classify each set of physiological data into a different chronotype (e.g., to determine whether the user is an "active person" or has a "regular sleep schedule", etc.). Then, system 300 may determine a circadian rhythm chronotype based on the classification of each set of physiological data.

[0112] At 305, system 300 may receive input parameters. The input parameters may include user identification information (e.g., the user's ID (identity), length of history (e.g., the number of days system 300 has received data), timeline (e.g., start date of receiving physiological data and end date of receiving physiological data), configuration parameters, data thresholds, or combinations thereof.

[0113] At 310, system 300 may receive sleep data. For example, system 300 may receive physiological data associated with a user from a wearable device over a certain period of time. The physiological data may include at least sleep pattern data. In some cases, the sleep pattern data may also include sleep regularity data. In such cases, system 300 may load sleep summary data (e.g., sleep data, sleep pattern data, or both) within a time frame (e.g., a certain period of time) and process the sleep summary data. In some examples, the sleep pattern data may include at least the time when the user goes to sleep every night (or enters the bed but is not yet asleep) and the time when the user wakes up in the morning.

[0114] At 315, system 300 may check a data threshold. For example, system 300 may determine whether the amount of received sleep data meets the threshold. System 300 may determine that the amount of received sleep data does not meet the threshold. In such cases, system 300 may refrain from extracting sleep data. For example, system 300 may determine that it does not contain a sufficient amount of data for the system 300 to estimate the sleep chronotype. In other examples, system 300 may determine that the amount of received sleep data meets the threshold (e.g., is above the threshold).

[0115] The threshold may be an example of a history length indicating the number of days for which system 300 receives sleep data. In such cases, the threshold may be predetermined by system 300 receiving the threshold at 305 before receiving sleep data at 310. System 300 may identify the history length and determine whether the amount of received sleep data meets the threshold. In some examples, the threshold may be 90 consecutive nights in the same time zone. However, this threshold may be configured and / or changed over time by the user or system 300.

[0116] At 320, system 300 may extract sleep data. For example, system 300 may discard sleep data that may be affected by jet lag (e.g., across two or more time zones). System 300 may extract sleep data based on a determination that the gaps between measurements of the received sleep data are minimal (e.g., the sleep data has been received continuously for 90 nights). In some cases, system 300 may check a data threshold and extract sleep data in response to determining that the data meets the threshold.

[0117] System 300 may extract the most recent "n" (e.g., history length) long sleep data. In such cases, system 300 may narrow down a subset of the sleep data to process (e.g., including the measurement date). For example, system 300 may extract sleep data measured during a history length (e.g., a certain period). Extracting sleep data at 320 may trigger a data processing pipeline for body temperature data, MET data, and / or heart rate data, as described herein.

[0118] At 325, system 300 may derive sleep metrics. For example, system 300 may determine that the sleep data (e.g., sleep pattern data) includes wake-up time, bedtime, sleep duration, or a combination thereof. In such cases, system 300 may identify the user's average wake-up time, average bedtime, average sleep duration, or a combination thereof over that certain period. In some cases, system 300 may determine a sleep regularity index based on receiving physiological data (e.g., sleep data).

[0119] At 330, system 300 may estimate a sleep chronotype. For example, system 300 may classify physiological data from a wearable device into chronotypes associated with sleep patterns. In some cases, system 300 may determine a sleep chronotype (e.g., a third chronotype referred to elsewhere in this specification) based on having determined a sleep regularity metric. System 300 may input the physiological data into a machine learning classifier. In such a case, system 300 may use machine learning to classify a sleep chronotype, determine a circadian rhythm chronotype, or both.

[0120] At 335, system 300 may receive temperature data. For example, system 300 may receive physiological data associated with a user from a wearable device over a period of time. The physiological data may include at least continuous nighttime temperature data, continuous daytime temperature data, or both. In such a case, system 300 may load continuous nighttime temperature data within a time frame (e.g., a period of time) and process the continuous nighttime temperature data. The continuous nighttime temperature data may be loaded and processed based on extracting sleep data. For example, system 300 may filter down the data according to the narrowed (e.g., extracted) sleep time. In such a case, system 300 may discard the daytime temperature data and store the nighttime temperature data.

[0121] At 340, the system 300 may aggregate body temperature data. For example, the system 300 may determine an aggregated time series by calculating the 75th percentile of data points measured at the same time on different days. In such cases, the system 300 may determine an aggregated sleep body temperature. For example, the system 300 may generate a pool of measured values (e.g., including body temperature values and timestamps of body temperature values) over a period of weeks or months of sleep data. In some cases, the system 300 may discard body temperature values for nighttime spikes and / or baseline changes that may indicate outliers compared to the remaining body temperature data. In some examples, the system 300 may record consecutive nightly body temperature data for the most recent 90 nights of sleep data.

[0122] The body temperature time series may be filtered to include data that may be measured during bedtime. The system 300 may quantize the nighttime body temperature data into minute bins and collect all body temperature values recorded in each minute-long bin. In such cases, the system 300 may aggregate the distribution of body temperature values per minute and extract the 75th percentile of the bin distribution for each minute length. The 75th percentile of each bin may create a time series representing the aggregated body temperature signal and the overall body temperature change over 90 consecutive nights, which may be further described with respect to FIG. 4.

[0123] If there are body temperature values measured in at least 20% of the underlying nights, the system 300 may assign the 75th percentile of each bin (e.g., 1-minute intervals) as the representative body temperature within that bin. The number of values within each bin may be stored as a weight for the representative value. In some cases, the first 30 minutes of the aggregated body temperature signal may be omitted in calculations where the body temperature is stable and thus has an upward trend for many users. In such cases, discarding the first 30-minute portion of the body temperature values may prevent problems in fitting functions to the data, such as spline fitting distortion.

[0124] At 345, system 300 may fit a spline (or other mathematical function) to the aggregated sleep body temperature. For example, system 300 may fit a 5th degree univariate spline to the aggregated temperature signal using the derived weights (e.g., the interval of each bin length and / or the number of values in the bin). In such a case, system 300 may fit the spline to the time series. System 300 may fit the spline in response to the aggregation of the body temperature data.

[0125] At 350, the lowest body temperature value may be determined. The lowest body temperature value may be determined based on fitting a spline to the aggregated sleep body temperature. In such a case, the lowest body temperature value may include the time of the lowest body temperature value and the value of the lowest body temperature value. For example, system 300 may identify the time of night associated with the lowest nocturnal body temperature based on receiving physiological data. To determine the lowest body temperature value, system 300 may determine whether 90 percent of the spline fit values are greater than the local minimum. In some cases, system 300 may determine the highest and / or lowest body temperature values. In some cases, system 300 may identify two or more lowest temperature values. In such a case, system 300 may select the lowest lowest body temperature value.

[0126] If system 300 is unable to determine the lowest body temperature value, system 300 may refrain from deriving a body temperature metric. If the lowest body temperature value is not determined, system 300 may not be able to estimate the body temperature chronotype. In some cases, system 300 may determine whether the difference between the 95th percentile and the 5th percentile of the aggregated body temperature signal meets a threshold. If the difference meets the threshold, system 300 may derive a body temperature metric. If system 300 determines that the difference does not meet the threshold, system 300 may refrain from deriving a body temperature metric.

[0127] At 355, system 300 may derive body temperature metrics. For example, system 300 may derive body temperature metrics in response to determining a body temperature minimum. At 360, system 300 may estimate a body temperature chronotype. For example, system 300 may classify physiological data from a wearable device into a first chronotype associated with continuous nocturnal body temperature data. In some cases, classifying physiological data into a first chronotype associated with continuous nocturnal body temperature data may be in response to identifying the time of night associated with the nocturnal body temperature minimum. System 300 may input body temperature data into a machine learning classifier. In such a case, system 300 may use machine learning to classify a body temperature chronotype, determine a circadian rhythm chronotype, or both. In some cases, system 300 may classify physiological data from a wearable device into a first chronotype associated with continuous nocturnal body temperature data, sleep pattern data, activity data, or a combination thereof.

[0128] At 365, system 300 may receive MET data. For example, system 300 may receive physiological data associated with a user from a wearable device over a period of time. The physiological data may include at least activity data. In such a case, system 300 may load the MET data and process the MET data. The MET data may be loaded and processed based on having extracted sleep data.

[0129] At 370, system 300 may aggregate MET data. At 375, system 300 may check data thresholds. For example, system 300 may determine whether the amount of received MET data meets the threshold. System 300 may determine that the amount of received MET data does not meet the threshold. In such cases, system 300 may refrain from deriving MET metrics. For example, system 300 may determine that the system 300 does not contain a threshold amount of data for estimating the MET chronotype. In other examples, system 300 may determine that the amount of received MET data meets (e.g., is greater than or equal to) the threshold.

[0130] The threshold may be an example of the history length indicating the number of days for which system 300 receives MET data. In such cases, the threshold may be predetermined such that system 300 receives the threshold at 305 before receiving MET data at 365. System 300 may identify the history length and determine whether the amount of received MET meets the threshold. In some examples, the threshold may be 90 consecutive days in the same time zone. At 380, system 300 may derive MET metrics. For example, system 300 may derive MET metrics in response to determining that the MET data meets the threshold.

[0131] At 385, system 300 may estimate the MET chronotype. For example, system 300 may classify physiological data from a wearable device into a second chronotype associated with activity data. System 300 may input the MET data into a machine learning classifier. In such cases, system 300 may use machine learning to classify the MET chronotype, determine the circadian rhythm chronotype, or both.

[0132] At 390, system 300 may receive heart rate data. For example, system 300 may receive physiological data associated with a user from a wearable device over a period of time. The physiological data may include at least heart rate data. In such a case, system 300 may load the heart rate data and process the heart rate data. The heart rate data may be loaded and processed based on having extracted sleep data.

[0133] At 392, system 300 may estimate a heart rate chronotype. For example, system 300 may classify physiological data from a wearable device into a fourth chronotype associated with the heart rate data in response to receiving the physiological data. In such a case, system 300 may receive the heart rate data and use the heart rate data to determine a heart rate chronotype.

[0134] At 395, system 300 may determine a circadian rhythm chronotype based on continuous nocturnal body temperature data and a first chronotype, a second chronotype, and a third chronotype. In some examples, system 300 may determine a circadian rhythm chronotype based on continuous nocturnal body temperature data, a first chronotype, a second chronotype, a third chronotype, or a combination thereof. For example, system 300 may determine a circadian rhythm chronotype based on continuous nocturnal body temperature data and in response to having determined a sleep chronotype, a body temperature chronotype, a MET chronotype, a heart rate chronotype, or a combination thereof. In some cases, the circadian rhythm chronotype may be determined in response to inputting physiological data into a machine learning classifier.

[0135] System 300 may determine a circadian rhythm chronotype based on the amount of sleep data measured within a certain period of time meeting a threshold. In such a case, System 300 may determine a circadian rhythm chronotype based on sleep summary data and at least an estimated value of the sleep, body temperature, and / or MET chronotype. System 300 may fuse estimated values derived from different sources into one collective estimated chronotype for the circadian rhythm chronotype. Thus, by enabling a more complete and accurate determination of the circadian rhythm chronotype, the techniques described herein may enable System 300 to provide the user with improved insights and guidance that better correlate with the user's overall health.

[0136] FIG. 4 shows an example of a timing diagram 400 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. The timing diagram 400 may implement or be implemented by an aspect of System 100, System 200, System 300, or a combination thereof. For example, in some implementations, the timing diagram 400 may be displayed to the user 102 via the GUI 275 of the user device 106 as shown in FIG. 2.

[0137] As will be described in more detail herein, the system can be configured to determine a circadian rhythm chronotype. In some cases, the user's deep body temperature pattern throughout the night can be an indicator that can characterize the user's chronotype. For example, skin temperature and sleep timeline at night can determine the temperature chronotype. Thus, timing diagram 400-a shows the relationship between the user's body temperature data and the time (e.g., minutes since midnight) since midnight. In this regard, the plurality of dashed vertical lines shown in timing diagram 400-a may be understood to refer to "aggregated body temperature data 405" as described with reference to block 340 of FIG. 3. In this regard, the solid curve shown in timing diagram 400-a may be understood to refer to "fitted spline 410" as described with reference to block 345 of FIG. 3. In this regard, the single dashed vertical line in timing diagram 400-a may be referred to as "body temperature minimum 415" as described with reference to block 350 of FIG. 3.

[0138] In some cases, the system can determine or estimate the user's body temperature minimum 415 based on the user's continuous night-time body temperature data collected via the ring. In some implementations, the system can determine a temperature chronotype, a circadian rhythm chronotype, or both in response to receiving continuous night-time skin temperature data. The skin temperature data may be collected in one-minute increments (e.g., frequency).

[0139] In some cases, a system (such as a ring, user device, server) may receive physiological data associated with a user from a wearable device. The physiological data may include at least body temperature data, and may also include heart rate data along with other physiological measurements or derived values. The body temperature data may be continuously collected by the wearable device. The physiological measurements may be performed continuously throughout the day and / or night. For example, in some implementations, the ring may be configured to continuously acquire physiological data (such as body temperature data, sleep data, heart rate, MET data, etc.) according to one or more measurement cycles over the course of each day / sleep day. In other words, the ring may continuously acquire physiological data from the user regardless of the “trigger conditions” for performing such measurements. In some cases, continuous body temperature measurements on the finger may capture body temperature fluctuations (such as small or large fluctuations) that may not be apparent in core body temperature. For example, continuous body temperature measurements on the finger may capture minute-by-minute or hour-by-hour body temperature fluctuations that provide additional insights not provided by other body temperature measurements at other locations on the body or, if the user manually measures their body temperature once a day.

[0140] The timing diagram 400-a shown in FIG. 4 shows the relative timing of the nocturnal body temperature minimum 415 in relation to the minutes from midnight. For example, the nocturnal body temperature minimum may be a value of about 35.9 degrees Celsius 150 minutes after midnight (e.g., 2:30 am). In some cases, the body temperature chronotype may be determined based on the nocturnal time associated with the nocturnal body temperature minimum 415. For example, a body temperature chronotype that characterizes a user as a “morning type” user may include the nocturnal minimum body temperature 415 at the mid-sleep time point, while a body temperature chronotype that characterizes a user as a “night type” user may include the nocturnal body temperature minimum 415 in the second half of the user's sleep (e.g., after the mid-sleep time point). In some cases, the difference in the nocturnal time of the body temperature minimum 415 between “morning type” and “night type” users may be two hours.

[0141] The system can fit a spline 410 to the aggregated body temperature data 405 using the time series of the aggregated body temperature data 405. In such a case, the system can use the aggregated body temperature data 405 to characterize the fitted spline 410 into different categories. For example, the timing diagram 400-a shown in FIG. 4 illustrates a U-shaped fitted spline 410. The U-shaped fitted spline 410 can illustrate that the aggregated body temperature data 405 decreases, reaches a minimum value (e.g., body temperature minimum value 415), and increases before waking up time.

[0142] In other examples, the fitted spline 410 may include a constant downward slope. In such a case, the aggregated body temperature data 405 may always show a downward trend throughout the night. In other examples, the fitted spline 410 may include a constant upward slope throughout the night.

[0143] In some examples, the system may determine that the received body temperature data does not meet a threshold. In such a case, the system may identify the user as a "rare syncers" if there is a possibility that the system does not receive sufficient body temperature data to determine the aggregated body temperature data 405, the fitted spline 410, the body temperature minimum value 415, or a combination thereof. In some cases, the cluster of the user's aggregated body temperature data 405 may occur within a tight (e.g., narrow) range, and as a result, the up and down of the time series (e.g., aggregated body temperature data 405) may be of low accuracy and reliability. The tight range can be an example of the change in the minimum body temperature along the y-axis. In such a case, the system may discard the body temperature data and refrain from using the body temperature data to determine the circadian rhythm chronotype.

[0144] The timing diagram 400-b shown in FIG. 4 illustrates the relative timing of sleep regularity for weekends, weekdays, and both. For example, the timing diagram 400-b illustrates the relationship between the user's sleep and the day of the week. In this regard, the dotted bars shown in the timing diagram 400-b may be understood to refer to "sleep time 420". The sleep time 420 may include a wake-up time, a bedtime, a sleep duration, or a combination thereof. In this regard, the black bars shown in the timing diagram 400-b may be understood to refer to "interquartile range 425". In some cases, the system may determine or estimate a sleep chronotype, a circadian rhythm chronotype, or both based on the sleep pattern data.

[0145] The system may use the sleep pattern data to characterize the user into different categories (e.g., sleep chronotype). For example, the timing diagram 400-b shown in FIG. 4 illustrates a regular sleeper. In such a case, the sleep times 420 for weekends and weekdays are consistent between the weekend and the weekday, indicating that the user wakes up at the same (e.g., consistent) time every day and goes to bed at the same (e.g., consistent) time every day. For example, the lower portion of the sleep time 420 on the weekend may align with the lower portion of the sleep time 420 on the weekday. The upper portion of the sleep time 420 on the weekend may align with the upper portion of the sleep time 420 on the weekday. The wake-up time may be illustrated as the upper portion of the sleep time 420, and the bedtime may be illustrated as the lower portion of the sleep time 420. The interquartile range 425 may represent the variability of the changes in sleep data over a certain period. In such a case, a shorter interquartile range 425 may indicate less variation in the bedtime and wake-up time, while a longer interquartile range 425 may indicate more variation in the bedtime and wake-up time.

[0146] In some cases, the timing diagram may illustrate an irregular sleeper. In such cases, the sleep times 420 on weekends and weekdays may not be consistent between weekends and weekdays, indicating that the user wakes up at different times on weekends and / or weekdays and goes to bed at different times on weekends and / or weekdays. For example, the lower part of the sleep time 420 on weekends may not match (e.g., be longer or shorter) the lower part of the sleep time 420 on weekdays. The upper part of the sleep time 420 on weekends may not match (e.g., be longer or shorter) the upper part of the sleep time 420 on weekdays. In such cases, the interquartile range 425 may be longer than the interquartile range 425 as shown in the timing diagram 400-b so as to indicate higher variability in the sleep pattern data.

[0147] In some cases, the timing diagram may illustrate an irregular sleeper. In such cases, the sleep time 420 on weekdays may be shorter than the sleep time on weekends. For example, the timing diagram may indicate that the user accumulates a sleep debt during weekdays and sleeps longer during weekends. For example, the lower and upper parts of the sleep time 420 on weekdays may each not match (e.g., be shorter) the lower and upper parts of the sleep time 420 on weekends. In such cases, the interquartile range 425 may be shorter so as to indicate less variability in the sleep pattern data between weekends and weekdays.

[0148] In some cases, the system may determine a sleep regularity metric. The sleep regularity metric may indicate how uniformly the user sleeps. In some cases, the sleep regularity metric may take into account naps recorded by the user or received by the system. In some examples, irregular bedtimes and wake times may be associated with an increased risk of various diseases. Since the sleep regularity metric can measure the consistency of the user's sleep timeline, users who frequently change their sleep timing and light exposure patterns may experience a mismatch between their circadian rhythm and sleep / wake cycle. Irregular sleep can reduce the user's daily performance and cognitive function and is associated with risk factors that threaten health. In such cases, having a regular sleep pattern may be beneficial to the user's overall health. In some cases, adherence to the user's established sleep pattern can contribute to the quality of the user's sleep and thus can be a factor contributing to the user's sleep score and readiness score.

[0149] Timing diagram 400-c shown in FIG. 4 illustrates the relative timing of activity patterns related to the times of a single calendar day. For example, timing diagram 400-c illustrates the relationship between the user's average MET and time. In this regard, the solid line shown in timing diagram 400-c may be understood to refer to "activity data 430". In some cases, the system may determine or estimate a MET chronotype, a circadian rhythm chronotype, or both based on activity data 430.

[0150] The system may use the amount of average MET (e.g., activity data 430) and the times associated with the average MET to characterize the user into different categories (e.g., activity chronotypes). For example, timing diagram 400-c shown in FIG. 4 shows a user who is active in the morning. The aggregated MET time series (e.g., activity data 430) may indicate how active the user was over the course of a day within a certain period. The peak of activity data 430 is before 10:00 am, indicating that the user is a morning-active user.

[0151] In other examples, the activity data 430 may indicate how active a user is in the evening. In such cases, the activity data 430 may have a low MET value in the morning and the MET value may increase as the day progresses. For example, the peak of the activity data 430 may be in the evening. In some cases, the activity data 430 may indicate how inactive a user is. In such cases, the activity data 430 may be constant (e.g., stable) throughout the day. For example, the average MET value may be low and the same (e.g., a horizontal line along the x-axis) throughout the day.

[0152] In some examples, the activity data 430 may indicate how active a user is at specific times of the day. For example, the activity data 430 may include one or more distinguishable peaks throughout the day. In some cases, a single distinguishable peak may indicate that the user is active at a very specific time, regularly (e.g., at the same time over a period such as a day, a week, a month, etc.). In other examples, a peak with a wider bandwidth and lower amplitude may indicate that the user is regularly active over a certain period within a time frame.

[0153] In some examples, the system may determine that the received activity data 430 does not meet a threshold. In such cases, the system may identify the user as a "non-permanent wearer" or "nighttime wearer", in which case the system may not receive sufficient activity data 430 to determine an activity chronotype. For example, the activity data 430 may not be available or may be partially unavailable during the day. In such cases, the system may discard the activity data 430 and refrain from using the activity data 430 to determine a circadian rhythm chronotype.

[0154] FIG. 5 shows an example of a graphical representation 500 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. The graphical representation 500 may implement or be implemented by aspects of the system 100, system 200, system 300, timing diagram 400, or any combination thereof. For example, the graphical representation 500 may be displayed on the GUI 275 of the user device 106 (e.g., user devices 106-a, 106-b, 106-c) corresponding to the user 102.

[0155] The graphical representation 500 may include a circular representation 505 of a 24-hour time span. For example, the system may overlay one or more physiological parameters, or an aggregation or characterization of one or more physiological parameters, over a 24-hour time span. In one non-limiting example, the system may overlay the averaging of at least continuous nocturnal body temperature data, activity data, sleep pattern data, or some combination or subset of this data over a certain period (e.g., the most recent 60 or 90 days) onto the circular representation 505 of the 24-hour time span. In some cases, the circular representation 505 may include other shapes such as rectangles, ellipses, triangles, etc.

[0156] In some cases, the graphical representation 500 may include a first segment 510, a second segment 515, and a third segment 520. The first segment 510 may include the averaging of continuous nocturnal body temperature data over a certain period. In such a case, the system 200 may cause the GUI 275 of the user device to display the first segment 510 of the circular representation 505 of the 24-hour time span, which includes the averaging of continuous nocturnal body temperature data over a certain period. In some examples, the first segment 510 may include an arched segment that represents the averaging of continuous nocturnal body temperature data over a certain period as a colored gradient indicating the change in nocturnal body temperature over the entire sleep time.

[0157] For example, the continuous nighttime body temperature may be included in the outermost circular line with a colored gradient. The colored gradient may be an example of a red-blue gradient where the red segment indicates a higher nighttime body temperature than the blue segment indicating a lower nighttime body temperature. For example, in the case of a user who experiences a higher nighttime body temperature towards midnight, the red segment may be displayed towards the center of the first segment 510, while the blue segment may be displayed towards the end of the first segment 510. In other examples, the colored gradient may be an example of a blue gradient where the dark blue segment indicates a lower nighttime body temperature than the bright blue segment indicating a higher nighttime body temperature. For example, the dark blue segment may be displayed towards the center of the first segment 510, while the brighter blue segment may be displayed towards the end of the first segment 510. In such a case, the colored gradient of the first segment 510 may enable the user to quickly and effectively identify the nighttime hours during which the lowest nighttime body temperature occurs. The time and value of the lowest nighttime body temperature may indicate whether the user is a morning person or a night person. The first segment 510 may include the average of the continuous nighttime body temperature data for the past 30 days, 60 days, or 90 days, or other configurable periods including weekends and weekdays.

[0158] In some cases, the second segment 515 may include averaging over a certain period of activity data. In such a case, the system 200 may cause the GUI 275 of the user device to display the second segment 515 of the circular representation 505 of the 24-hour time span including averaging over a certain period of activity data. In some examples, the second segment 515 may include a curved segment that represents the averaging over a certain period of activity data as a graph plot showing the relative change in activity level over the 24-hour time span.

[0159] For example, the graphical representation 500 may include activity tracking. In the case of a user who is active at regular times during the day, the second segment 515 may include a distinct shape. For example, the second segment 515 may not be visible to the user during the time the user is sleeping, thereby indicating that the user is not active during nighttime hours. As shown in FIG. 5, the second segment 515 may indicate that the user is active in the morning (e.g., between 8:00 - 9:00 AM) such that the second segment 515 is most visible during morning hours. The second segment 515 may extend inward from the outer perimeter of the circular representation 505 towards the center of the circular representation 505. In some cases, the second segment 515 may be displayed during evening hours, thereby indicating that the user is active during evening hours. The shape volume of the second segment 515 may be associated with the amount of activity. For example, a larger volume of the second segment 515 may indicate that the user is more active during that time period throughout the day compared to other time periods. The second segment 515 may include the average of the activity data for the past 30 days, 60 days, or 90 days, or other configurable periods including weekends and weekdays.

[0160] In some cases, the third segment 520 may include an averaging of sleep pattern data over a certain period. In such cases, the system 200 may cause the GUI 275 of the user device to display the third segment 520 of the circular representation 505 of the 24 - hour time span including the averaging of sleep pattern data over a certain period. In some examples, the third segment 520 may include a wedge - shaped segment representing the averaging of sleep pattern data over a certain period. The third segment 520 may include a first side 525 indicating the time the user goes to bed, a second side 530 indicating the time the user wakes up, and a third curved side 535 adjacent to the circular representation 505 of the 24 - hour time span. In such cases, the third segment 520 may indicate the bedtime, wake - up time, sleep time, or a combination thereof.

[0161] For example, the graphical representation 500 may indicate that the user goes to bed at 10:00 PM and wakes up at 8:00 AM. The crispness of the first side 525 and the second side 530 may indicate the regularity of the sleep data. For example, if the first side 525 and / or the second side 530 include faint or hard-to-see lines, this may be a visual indication that the user has an irregular bedtime, wake-up time, or both. In other examples, if the first side 525 and / or the second side 530 include clear or visible or distinct lines, this may be a visual indication that the user has a regular bedtime, wake-up time, or both. The third segment 520 may include the average of the sleep pattern data for the past 30 days, 60 days, or 90 days, or other configurable periods including weekends and weekdays.

[0162] In some examples, the graphical representation 500 may include one or more parameters 540. For example, the one or more parameters 540 may be an example of an indication of the current time. In other examples, the one or more parameters 540 may be an example of a message or alert indicating heart rate data, an indication of the menstrual cycle, respiratory rate data, or a combination thereof. In such cases, the system may cause the GUI 275 of the user device to display the one or more parameters 540 with respect to a circular representation 505 of a 24-hour time span including the averaging of heart rate data, an indication of the menstrual cycle, respiratory rate data, or a combination thereof over a certain period. In some cases, the one or more parameters 540 may overlay the graphical representation 500 with respect to the circular representation 505 of the 24-hour time span.

[0163] The graphical representation 500 may enable a user to visualize long-term habits on the user interface components of a 24-hour clock. The graphical representation 500 may show the user's bedtime and wake-up time, nighttime body temperature, and activity data. In such cases, the system may provide the user with insights into important variables that factor into determining a circadian profile (e.g., a circadian rhythm chronotype). The graphical representation 500 may be an example of a report generated to display a picture of changes in the user's internal clock, seasonal changes, the effects of travel, lifestyle habits, or combinations thereof.

[0164] In some cases, the graphical representation 500 may include a static rendering. By applying a smoothing function to the activity data (e.g., the second segment 515) and obfuscating the exact boundaries of the user's bedtime and wake-up time (e.g., the first side 525 and the second side 530 of the third segment 520 respectively), the system may display to the user an interactive and useful tool for providing insights into the user's lifestyle. Patterns determined from received biosignals (e.g., physiological data) may classify the user into several categories including, but not limited to, morning people, night people, very active people, inactive people, or combinations thereof. In such cases, the graphical representation 500 may classify the user into those who align well with their circadian rhythm chronotype and those who do not.

[0165] FIG. 6 shows an example of a system 600 that supports techniques for determining a circadian rhythm chronotype according to aspects of the present disclosure. The system 600 may implement or be implemented by the system 100, the system 200, the system 300, or combinations thereof. In particular, the system 600 shows examples of the ring 104 (e.g., the wearable device 104), the user device 106, and the server 110 as described with reference to FIG. 1.

[0166] System 600 may include an algorithm for the characterization of chronotypes. In such a case, System 600 may determine a circadian rhythm chronotype from one or more data sources. As further described herein, when System 600 receives a data amount that meets a threshold, System 600 may determine a circadian rhythm chronotype. If System 600 determines that the data amount does not meet the threshold, System 600 may refrain from determining a circadian rhythm chronotype. System 600 may include one or more processing pipelines and a collective estimation for each processing pipeline.

[0167] At 605, System 600 may receive input parameters. The input parameters may include user identification information (e.g., the user's ID), the length of the history (e.g., the number of days for which System 600 receives data), the time line (e.g., the start date for receiving physiological data and the end date for receiving physiological data), configuration parameters, data thresholds, or combinations thereof.

[0168] At 610, System 600 may receive sleep data. For example, System 600 may receive physiological data associated with a user from a wearable device over a certain period. The certain period may be an example of 90 consecutive calendar days. The physiological data may include at least sleep pattern data. In some cases, the sleep pattern data may include sleep regularity data. In such a case, System 600 may load sleep summary data (e.g., sleep data, sleep pattern data, or both) within a time frame (e.g., a certain period) and process the sleep summary data. In some examples, the sleep pattern data may include at least the time the user goes to sleep every night (or enters the bed but is not yet asleep), the time the user wakes up in the morning, the sleep duration, or combinations thereof.

[0169] For example, system 600 may receive, from a wearable device, a first set of physiological data measured from a user by the wearable device and collected over a period of time. The first set of physiological data may include at least sleep data. In some examples, system 600 may receive, from the wearable device, a second set of physiological data measured from the user by the wearable device and collected over the previous sleep day. For example, the second set of physiological data may include sleep pattern data from the previous night. In such cases, the previous night may be an example of the night immediately preceding the current calendar day. In some examples, the sleep data of the first set of physiological data and the second set of physiological data may include sleep data derived from naps taken over one or more calendar days. For example, the first set of physiological data may include sleep data from naps measured over a period of time (e.g., 90 consecutive calendar days). The second set of physiological data may include sleep data from naps measured on the calendar day immediately preceding the current calendar day.

[0170] At 615, the system 600 may check data thresholds. For example, the system 600 may determine whether the amount of received sleep data meets a threshold. The system 600 may determine that the amount of received sleep data meets the threshold (e.g., is greater than or equal to the threshold). In other examples, the system 600 may determine that the amount of received sleep data does not meet the threshold. In such cases, the system 600 may refrain from extracting sleep data. For example, the system 600 may determine that it does not contain a sufficient amount of data to estimate the circadian chronotype. For example, the system 600 may determine that the wearable device may not be worn frequently enough within a certain period, that the number of sleep measurement instances received by the wearable device within a certain period is less than 30, that the wearable device is worn partially during sleep, that the wearable device is not synchronized, that high-frequency data is overwritten, that the user has moved across different time zones such that the system 600 may not collect sufficient data within the same time zone, or a combination thereof.

[0171] The threshold may be an example of a history length indicating the number of days the system 600 receives sleep data. In such cases, the threshold may be predetermined by the system 600 receiving the threshold at 605 before receiving sleep data at 610. The system 600 may identify the history length and determine whether the amount of received sleep data meets the threshold. In some examples, the threshold may be 90 consecutive nights in the same time zone, more than 30 sleep measurement instances during 90 consecutive nights, or both. However, this threshold may be configured and / or changed over time by the user or the system 600.

[0172] At 620, system 600 may extract sleep data. For example, system 600 may discard sleep data that may be affected by jet lag (e.g., across two or more time zones). In such cases, system 600 may extract and discard sleep data measured in a time zone that is more than one hour away from the most frequently occurring time zone. System 600 may extract sleep data based on a determination that the gaps between measurements of the received sleep data are minimal (e.g., the sleep data has been received continuously for 90 nights). In some cases, system 600 may check a data threshold and extract sleep data in response to determining that the data meets the threshold.

[0173] System 600 may extract the most recent "n" (e.g., history length) long sleep data. In such cases, system 600 may narrow down a subset of the sleep data to be processed (e.g., including the measurement date). For example, system 600 may extract sleep data measured during a history length (e.g., a certain period). In some cases, system 600 may extract and discard sleep data to avoid outliers in the sleep data from affecting the estimation of the circadian rhythm chronotype. In other examples, system 600 may extract sleep data associated with sleep sessions longer than three hours and / or extract a single sleep session per calendar day. Extracting sleep data at 620 may trigger the data processing pipeline for body temperature data and / or MET data as described herein.

[0174] At 625, system 600 may derive sleep metrics. For example, system 600 may determine that the sleep data (e.g., sleep pattern data) includes a wake-up time, a bedtime, a sleep duration, or a combination thereof. In such cases, system 600 may identify the user's average wake-up time, average bedtime, average sleep duration, or a combination thereof over a certain period.

[0175] In some examples, system 600 may identify a median bedtime, a median wake time, a standard deviation of a sleep midpoint, or a combination thereof. In such cases, system 600 may process the sleep pattern data of the first set of physiological data to extract at least the standard deviation of the sleep midpoint, the median wake time at which the user wakes up, the median bedtime at which the user goes to bed, or a combination thereof. For example, system 600 may extract from the sleep data a median bedtime, a median wake time, a standard deviation of a sleep midpoint, an average wake time, an average bedtime, an average sleep time, or a combination thereof.

[0176] In some cases, system 600 may input the first set of physiological data into a machine learning model. For example, system 600 may input sleep data, sleep metrics, extracted sleep data, or a combination thereof into a machine learning model. In response to inputting the first set of physiological data into the machine learning model, system 600 may use the machine learning model to classify the first set of physiological data into a circadian rhythm chronotype. For example, system 600 may estimate a circadian rhythm chronotype using the derived sleep metrics and a linear regression model as described herein.

[0177] At 630, system 600 may receive temperature data. For example, system 600 may receive physiological data associated with a user from a wearable device over a period of time. The physiological data may include at least continuous nighttime temperature data, continuous daytime temperature data, or both. In such cases, system 600 may load the continuous nighttime temperature data within a time frame (e.g., a period of time) and process the continuous nighttime temperature data. The continuous nighttime temperature data may be loaded and processed based on extracting sleep data. For example, system 600 may filter down the data according to the narrowed (e.g., extracted) sleep time. In such cases, system 300 may discard the daytime temperature data and store the nighttime temperature data.

[0178] At 635, the system 600 may aggregate body temperature data. For example, the system 600 may generate a pool of measured values (including, for example, body temperature values and timestamps of body temperature values) over a period of sleep data for several weeks or months. In some cases, the system 600 may discard body temperature values for nighttime spikes and / or baseline changes that may indicate outliers compared to the remaining body temperature data. In some examples, the system 300 may record consecutive nightly body temperature data for the most recent 90 nights of sleep data. In such cases, the system 600 may record body temperature data corresponding to the same calendar day on which the sleep data (e.g., 90 nights of sleep data) was recorded. The body temperature time series may be filtered to include data that may be measured during bedtime.

[0179] At 640, the system 600 may check data thresholds. For example, the system 600 may determine whether the amount of received body temperature data meets a threshold. In some examples, the system 600 may determine that the amount of received body temperature data meets the threshold (e.g., is greater than or equal to the threshold). The system 600 may determine that the amount of received body temperature data does not meet the threshold. In such cases, the system 600 may refrain from deriving a body temperature chronotype. For example, the system 600 may determine that the system 600 does not contain a sufficient amount of data to estimate a circadian rhythm chronotype.

[0180] In such cases, the system 600 may determine that the wearable device may not be worn very frequently within a certain period, that the number of sleep measurement instances received by the wearable device within a certain period is less than 30, that the wearable device is partially worn during sleep, that the wearable device is not synchronized, that high-frequency data is overwritten, that the system 600 may not collect sufficient data within the same time zone because the user has moved across different time zones, or a combination thereof. For example, if high-frequency data is overwritten, skin temperature data may be missing from the received physiological parameters.

[0181] The threshold may be an example of the history length indicating the number of days the system 600 receives sleep data. In such cases, the threshold may be predetermined by the system 600 receiving the threshold at 605 before receiving body temperature data at 630. The system 600 may identify the history length and determine whether the amount of received body temperature data meets the threshold. In some examples, the threshold may be 90 consecutive nights in the same time zone. However, this threshold may be configured and / or changed over time by the user or the system 600.

[0182] At 645, the system 600 may derive body temperature metrics. For example, the system 600 may derive body temperature metrics in response to checking a data threshold. The system 600 may process consecutive nightly body temperature data by an application to extract at least the average skin temperature, the average skin temperature of the five highest body temperature values in a 24-hour time span, the average skin temperature of the five lowest body temperature values in a 24-hour time span, or a combination thereof. For example, the system 600 may generate the user's daily body temperature rhythm to derive body temperature metrics. In such cases, the system 600 may derive the time of the average skin temperature of the five highest body temperature values at consecutive times within a 24-hour time span, the time of the average skin temperature of the five lowest body temperature values at consecutive times within a 24-hour time span, the average skin temperature, or a combination thereof.

[0183] In some cases, system 600 may input body temperature data, body temperature metrics, extracted body temperature data, or combinations thereof into a machine learning model. In response to inputting a first set of physiological data into the machine learning model, system 600 may use the machine learning model to classify the first set of physiological data into a circadian rhythm chronotype. For example, system 600 may estimate a circadian rhythm chronotype using the derived body temperature metrics and a linear regression model as described herein.

[0184] At 650, system 600 may receive MET data. For example, system 600 may receive physiological data associated with a user from a wearable device over a period of time. The physiological data may include at least activity data. In such a case, system 600 may load the MET data and process the MET data. The MET data may be loaded and processed based on the extraction of sleep data.

[0185] At 655, system 600 may aggregate the MET data. At 660, system 600 may check a data threshold. For example, system 600 may determine whether the amount of received MET data meets a threshold. System 600 may determine that the amount of received MET data meets the threshold (e.g., is above the threshold). In other examples, system 600 may determine that the amount of received MET data does not meet the threshold. In such a case, system 600 may refrain from deriving MET metrics. For example, system 600 may determine that the system 600 does not contain a threshold amount of data for estimating a circadian rhythm chronotype.

[0186] In such cases, the system 600 may determine that the system 600 does not contain a sufficient amount of data to estimate the circadian rhythm chronotype. For example, the system 600 may determine that the wearable device may not be worn frequently enough within a certain period, that the number of sleep measurement instances received by the wearable device within a certain period is less than 30, that the wearable device is partially worn during sleep, that the wearable device is not synchronized, that high-frequency data is overwritten, that the user has moved across different time zones, so that the system 600 may not collect sufficient data within the same time zone, or a combination thereof. By wearing the wearable device partially during sleep, the MET data during the day may be lost. In such cases, the system 600 may refrain from extracting features from the user's MET data and / or physical activity data during the day. If the wearable device is not synchronized frequently enough, the MET data may be missing from the received physiological data.

[0187] The threshold may be an example of the history length indicating the number of days the system 600 receives MET data. In such cases, the threshold may be predetermined by the system 600 receiving the threshold at 605 before receiving MET data at 650. The system 600 may identify the history length and determine whether the amount of received MET meets the threshold. In some examples, the threshold may be 90 consecutive days at the same time. The system 600 may record MET data including the most recent 90 nights of sleep data. In such cases, the system 600 may record MET data corresponding to the same calendar day on which the sleep data was recorded (e.g., the most recent 90 nights of sleep data).

[0188] At 665, the system 600 may derive MET metrics. For example, the system 600 may derive MET metrics in response to determining that MET data meets a threshold. The system 600 may process activity (e.g., MET) data of a first set of physiological data by an application to extract at least an average MET value, the time the user is active, or both. For example, the system 600 may calculate a rest-activity rhythm and extract (e.g., derive) MET metrics. In such a case, the system 600 may extract from the rest-activity rhythm the average MET value for the most active continuous 10 hours within a 24-hour span, the average MET value for the least active continuous 5 hours within a 24-hour span, the midpoint MET value for the most active continuous 10 hours within a 24-hour span, the midpoint MET value for the least active continuous 5 hours within a 24-hour span, the time at which maximum physical activity is measured, or a combination thereof.

[0189] In some cases, the system 600 may input MET data, MET metrics, the extracted MET data, or a combination thereof into a machine learning model. The system 600 may use the machine learning model to classify the first set of physiological data into a circadian rhythm chronotype in response to inputting the first set of physiological data into the machine learning model. For example, the system 600 may estimate a circadian rhythm chronotype using the derived MET metrics and a linear regression model as described herein.

[0190] At 670, the system 600 may determine a circadian rhythm chronotype based on sleep data, body temperature data, MET data, or a combination thereof. In some examples, the system 600 may determine a circadian rhythm chronotype based on derived metrics of sleep, body temperature, MET, or a combination thereof. In some cases, the circadian rhythm chronotype may be determined in response to inputting physiological data (e.g., the first set of physiological data) into a machine learning classifier.

[0191] In some cases, system 600 may output a number from 16 to 86 corresponding to the morningness-eveningness questionnaire (MEQ) score, where 16 represents the most extreme evening-type user and 86 represents the most extreme morning-type user. The estimated MEQ score can be mapped to the midpoint of sleep. For example, in response to determining the estimated circadian rhythm chronotype, system 600 may determine the midpoint of the user's sleep. The midpoint of sleep can be measured from 0:00 am. The midpoint of sleep (e.g., including the sleep-wake cycle) may be affected by the circadian rhythm chronotype. In such cases, system 600 may determine the midpoint of sleep based on the user's circadian rhythm chronotype. In some cases, the midpoint of sleep for morning-type users may have an earlier midpoint of sleep compared to the midpoint of sleep for intermediate-type and evening-type users.

[0192] System 600 may determine the relationship between the MEQ score and the midpoint of sleep. For example, system 600 may estimate the circadian rhythm chronotype and, in response to determining the circadian rhythm chronotype, may determine the relationship between the MEQ score and the midpoint of sleep. In some cases, the relationship between the MEQ score and the midpoint of sleep may be linear. In such cases, the linear relationship may create a mapping to associate the optimal midpoint of sleep with each MEQ score.

[0193] System 600 may determine the circadian rhythm chronotype based on the amount of measured sleep data within a certain period meeting a threshold. System 600 may fuse the estimated values derived from different sources into one collectively estimated chronotype of the circadian rhythm chronotype. In this way, by enabling a more complete and accurate determination of the circadian rhythm chronotype, the techniques described herein may enable system 600 to provide the user with improved insights and guidance that better correlate with the user's overall health.

[0194] As described herein with reference to FIG. 7, system 600 may compare a determined circadian rhythm chronotype with a second set of received physiological data (e.g., sleep data from the previous night). System 600 may cause a message associated with the comparison, the determined circadian rhythm chronotype, the second set of received physiological data, or a combination thereof to be displayed on the GUI of the user device, as described with reference to FIG. 8.

[0195] FIG. 7 shows an example of a graphical representation 700 that supports techniques for determining a circadian rhythm chronotype, according to an aspect of the present disclosure. The graphical representation 700 may implement, or be implemented by, aspects of system 100, system 200, system 300, timing diagram 400, system 600, or any combination thereof. For example, the graphical representation 700 may be displayed on the GUI 275 of a user device 106 (e.g., user devices 106-a, 106-b, 106-c) corresponding to user 102.

[0196] The graphical representation 700 may include a circular representation 705 of a 24-hour time span. For example, the system may overlay one or more physiological parameters, or an aggregation or characterization of one or more physiological parameters, over the 24-hour time span. In one non-limiting example, the system may overlay the determined circadian rhythm chronotype and sleep data from the previous night's sleep over the circular representation 705 of the 24-hour time span, as described with reference to FIG. 6.

[0197] In some cases, the graphical representation 700 may include a first segment 710 representing sleep pattern data from the previous night's sleep and a second segment 715 representing the determined circadian rhythm chronotype. The first segment 710 may include the wake-up time when the user woke up today, the bedtime when the user went to bed the previous night, the midpoint 720-a of the user's sleep from the previous night, the sleep time of the previous night, or a combination thereof. For example, the graphical representation 700 may indicate that the user went to bed at 10:00 PM the previous night and woke up at 6:00 AM. The midpoint 720-a may indicate that the midpoint of the user's sleep was at 2:15 AM. The first side may indicate the time when the user goes to bed, and the second side may indicate the time when the user wakes up.

[0198] In such a case, the system may cause the GUI 275 of the user device to display a first segment 710 of the circular representation 705 of the 24-hour time span, including sleep pattern data from the previous night. In some examples, the first segment 710 may include an arc-shaped segment representing sleep pattern data from the previous night. For example, the sleep pattern data of the previous night may be included in the outermost circular line of the first color. The first segment 710 may also include a midpoint 720-a representing the midpoint of the user's sleep from the previous night. In such a case, the midpoint 710-a of the first segment 710 may enable the user to quickly and effectively identify the time of night when the midpoint of the user's sleep occurs. The time of the midpoint 720-a may indicate whether the user is a morning person or a night person.

[0199] In some cases, the graphical representation 700 may include a second segment 715 that represents the averaging of sleep pattern data of a first set of physiological data over a certain period. The second segment 715 may include the average wake-up time when the user wakes up, the average bedtime when the user goes to bed, the average mid-sleep point 720 - b hours, the average sleep duration, or a combination thereof. For example, the graphical representation 700 may indicate that the user goes to bed on average at 11:00 PM and wakes up at 7:00 AM. The mid-point 720 - b may indicate that the average mid-point of the user's sleep is at 2:45 AM. The first side may indicate the average time when the user goes to bed, and the second side may indicate the average time when the user wakes up.

[0200] In such cases, the system may cause the GUI 275 of the user device to display a second segment 715 of a circular representation 705 of a 24 - hour time span that includes the averaging of sleep pattern data of a first set of physiological data over a certain period. In some examples, the second segment 715 may include an arc-shaped segment that represents the averaging of sleep pattern data of a first set of physiological data over a certain period. For example, the average sleep pattern data may be included in the innermost circular line of a second color that is different from the first color. The second segment 715 may include a mid-point 720 - b that represents the average mid-point of the user's sleep. In such cases, the second segment 715 may enable the user to quickly and effectively compare the sleep pattern data from the previous night with the user's determined circadian rhythm chronotype. The time of the mid-point 720 - a may indicate whether the user is a morning person or a night person. In such cases, the first segment 710 may be easily compared with the second segment 715 to determine whether the user's sleep the previous night is consistent with the determined circadian rhythm chronotype.

[0201] For example, the system may compare a determined circadian rhythm chronotype (e.g., the second segment 715) with a second set of received physiological data (e.g., the first segment 710). The system may compare one or more characteristics of the determined circadian rhythm chronotype with received sleep data from the previous night's sleep. For example, the system may compare sleep data associated with the determined circadian rhythm chronotype with received sleep data from the previous night's sleep.

[0202] In such a case, the averaging of the sleep pattern data of the first set of physiological data over a period of time can be compared with the sleep pattern data collected over the previous sleep days. For example, the system may compare the average wake-up time at which the user wakes up with the wake-up time from the previous night, the average bedtime at which the user goes to bed with the bedtime from the previous night, the average sleep duration with the sleep duration from the previous night, the average mid-sleep point with the mid-sleep point from the previous night, or combinations thereof.

[0203] In some examples, the graphical representation 700 may include one or more parameters. For example, the one or more parameters may be an example of an indication of the current time. In other examples, the one or more parameters 540 may be an example of a message or alert indicating heart rate data, an indication of the menstrual cycle, respiratory rate data, activity data, body temperature data, or combinations thereof. In such a case, the system may cause the GUI 275 of the user device to display the one or more parameters with respect to the circular representation 705 of the 24-hour time span. In some cases, the one or more parameters may overlay the graphical representation 700 with respect to the circular representation 705 of the 24-hour time span. In some cases, the graphical representation 700 may be an example of a report generated to display a picture of the user's body clock changes, seasonal changes, effects of travel, lifestyle habits, or combinations thereof.

[0204] The graphical representation 700 can enable a user to visualize long-term habits on a 24-hour clock user interface component. The graphical representation 700 may show the user's bedtime and wake-up time with respect to the user's determined circadian rhythm chronotype. In such a case, the system may determine a circadian profile (e.g., a circadian rhythm chronotype) and provide the user with insights regarding important variables that factor into providing recommendations (e.g., activities, sleep, etc.) for today when a comparison of a first segment 710 (e.g., sleep data from the previous night) and a second segment 715 (e.g., the determined circadian rhythm chronotype) is given.

[0205] In some cases, the graphical representation 700 may include a static rendering. In such a case, the system may display to the user interactive and useful tools to provide insights into the user's lifestyle. Patterns determined from received biosignals (e.g., physiological data) may classify the user into several categories including, but not limited to, for example, morning people, night people, very active people, inactive people, or combinations thereof. In such a case, the graphical representation 700 may classify the user into users who are well-aligned with their circadian rhythm chronotype and users who are not aligned with their circadian rhythm chronotype.

[0206] FIG. 8 shows an example of a GUI 800 that supports techniques for determining a circadian rhythm chronotype according to aspects of the present disclosure. The GUI 800 may implement aspects of the system 100, system 200, system 300, timing diagram 400, system 600, or any combination thereof, or may be implemented by them. For example, the GUI 800 may be an example of the GUI 275 of a user device 106 (e.g., user devices 106-a, 106-b, 106-c) corresponding to the user 102.

[0207] In some examples, the GUI 800 shows a series of application pages 802 that can be presented to the user 102 via the GUI 800 (e.g., the GUI 275 shown in FIG. 2). The system can generate a personalized tracking experience on the GUI 275 of the user device 106 to determine the circadian rhythm chronotype. Continuing with the above example, after determining the circadian rhythm chronotype, when the wearable application 250 is opened, an application page 802-a can be presented to the user 102 via the GUI 800. The GUI 800 can display an alert 805, a graphical representation 810, a message 815, or a combination thereof. The graphical representation 810 can be an example of the graphical representation 500 described with reference to FIG. 5, the graphical representation 700 described with reference to FIG. 7, a part of the graphical representation 500, a part of the graphical representation 700, or a combination thereof.

[0208] In some implementations, the user device and / or the server may generate an alert 805 associated with the determined circadian rhythm chronotype and / or an inconsistency in the circadian rhythm chronotype, and this alert may be displayed to the user via the GUI 800. In such a case, the application page 802-a may display an indication of the determined circadian rhythm chronotype via the alert 805. For example, the application page 802-a may include the alert 805 on the home page.

[0209] As described herein, if the user's determined circadian rhythm chronotype is inconsistent with the received physiological data, the server may send an alert 805 to the user, where the alert 805 is associated with the inconsistency. In particular, the alert 805 generated and presented to the user via the GUI 800 may be associated with the circadian rhythm chronotype inconsistency and a recommendation to return to the user's baseline determined circadian rhythm chronotype. In some cases, the alert 805 may display a recommendation on how to adjust the lifestyle within the day of the determined inconsistency and / or within several days after the determined inconsistency.

[0210] For example, after determining the circadian rhythm chronotype, the system may receive additional physiological data associated with the user from a wearable device. In response to receiving the additional physiological data, the system may determine a mismatch between the received additional physiological data and the determined circadian rhythm chronotype. In such a case, the system may determine a deviation (e.g., a circadian mismatch) from the determined circadian rhythm chronotype.

[0211] In response to determining a mismatch between the received additional physiological data and the determined circadian rhythm, the user may receive an alert 805 that can display a message associated with the mismatch. For example, the alert 805 can indicate to the user when the user's physiological data deviates from the determined circadian rhythm chronotype. In such a case, the system may cause the GUI 800 of the user device to display the alert 805, the message 815, or both, associated with the mismatch. The alert 805 may be configurable / customizable such that the user can receive different alerts 805 based on the determined circadian rhythm chronotype, the mismatch, or both. In some cases, the alert 805 may indicate the effect of the user's menstrual cycle on the determined circadian rhythm chronotype.

[0212] In some cases, the user may take corrective measures to address the mismatch before the system displays the alert 805. In such a case, the system may receive physiological data associated with the corrective measures and the system may refrain from displaying the alert 805 (e.g., disable the alert 805). In some examples, the system may adjust the alert 805 based on the physiological data received associated with the corrective measures.

[0213] In addition, in some implementations, the application page 802-a may display, for each day, one or more scores of the user (e.g., a sleep score, a readiness score, an activity goal progress). Further, in some cases, inconsistencies may be used to update (e.g., correct) one or more scores associated with the user (e.g., a sleep score, a readiness score). That is, data associated with the inconsistency of the circadian rhythm chronotype may be used to update the user's scores for subsequent calendar days after the inconsistency is detected. In some cases, the readiness score may be updated based on the inconsistency. In some cases, the message 815-a displayed to the user via the GUI 800 of the user device may indicate how the inconsistency has affected the overall score (e.g., the overall readiness score) and / or individual contributing factors. The system may be configured to dynamically update and compare the sleep regularity metric. The GUI 800 may display the sleep regularity metric for the displayed time period.

[0214] Referring to FIG. 5, the application page 802-a may display a graphical representation 810. For example, the system may cause the GUI 800 of the user device to display a graphical representation 810 of the averaging of at least continuous nighttime body temperature data, activity data, and sleep pattern data over a certain period. Based on the detected pattern, the system can provide additional context and insights regarding the graphical representation 810, thereby enhancing the value to the user by helping the user understand the graphical representation 810.

[0215] Referring to FIG. 7, application pages 802-a and 802-b may each display graphical representations 810-a and 810-b. For example, the system may cause the GUI 800 of the user device to display a graphical representation 810-a of the user's sleep pattern data for the previous night's sleep compared to the determined circadian rhythm chronotype. As described herein, the graphical representation 810-a may also include text indicating how the midpoint of the user's sleep aligns with the determined circadian rhythm chronotype. The graphical representation 810-a may be an example of a part of the graphical representation 810-b.

[0216] In some cases, the graphical representation 810 may be socially shared by using user interface tools for social sharing. The graphical representation 810 may provide the user with a cross-section of the moment for each individual component of the graphical representation 810. For example, message 815-a may indicate, with respect to the graphical representation 810, "You are highly active, awake" or "You are sleeping, temperature heading down". In such cases, the user may compare the long-term pattern with the pattern of today, yesterday, or last week. In some cases, the graphical representation 810 may include dynamic components such that different segments may be animated and / or highlighted when the user moves from one segment to a different segment.

[0217] The GUI 800 may also include a message 815 including insights, recommendations, etc. associated with the determined circadian rhythm chronotype. The server of the system may cause the GUI 800 of the user device to display the message 815 associated with the determined circadian rhythm chronotype. The user device 106 may display recommendations and / or information associated with the determined circadian rhythm chronotype via the message 815. As described above, the accurately determined circadian rhythm chronotype can be beneficial to the overall health of the user by providing the user with metrics that enable the user to understand how changes in behavior (e.g., sleep, exercise, diet, and mood improvement) can help improve the user's overall health and reduce the occurrence of circadian rhythm chronotype inconsistencies.

[0218] The system may cause the GUI 800 of the user device 106 to display a message 815-a associated with a comparison of the determined sleep pattern chronotype with a second set of received physiological data (e.g., sleep pattern data from the previous night), the determined circadian rhythm chronotype, the second set of received physiological data, or a combination thereof. For example, the graphical representation 810-a may show the averaging of the sleep pattern data of the first set of physiological data over a certain period (e.g., used to determine the circadian rhythm chronotype), the sleep pattern data from the previous night, the average wake-up time when the user wakes up, the average bedtime when the user goes to bed, the average mid-sleep point time, the average sleep duration, or a combination thereof.

[0219] Continuing with the above example, after selecting the graphical representation 810, an application page 802-b may be presented to the user 102 via the GUI 800. As shown in FIG. 8, the application page 802-b may display a message 815-c associated with the determined circadian rhythm chronotype. In such a case, the system may cause the GUI 800 of the user device to display a message 815 that can provide recommendations to the user based on the determined circadian rhythm chronotype.

[0220] Application page 802-b may display a message 815-c that may indicate "You are physically active in the morning. You go to bed relatively early and wake up early. Your body temperature during sleep reaches its lowest value at around 3 o'clock" or "You are a very active morning type!" In some cases, message 815-c may indicate "You are a night owl" or "You are an early bird". In other examples, message 815-c may indicate "You are a late morning type. You are somewhat of a morning type, but not extremely so." In such cases, message 815-c may provide the user with insights regarding morning-type individuals. For example, message 815-c may indicate "Morning types with early bedtimes may have a lower risk of cardiovascular disease, less obesity, and a lower risk of mental disorders such as depression and anxiety."

[0221] In some cases, message 815-b may indicate how the user's nightly sleep (e.g., with respect to sleep pattern data) aligns with the user's recommended bedtime and wake-up times. For example, message 815-b may indicate the alignment of the user's sleep and whether the user's sleep the previous night aligns with the determined circadian rhythm chronotype. In such cases, message 815-b may indicate whether the user's current sleep pattern data (e.g., sleep data from the previous night) is before, after, or aligned with the determined circadian rhythm chronotype. For example, message 815-b may indicate "The midpoint of your sleep was 46 minutes before your chronotype."

[0222] In some examples, the message 815-b may state, "You are within 85% of the recommended pattern. Keep it up!" In some cases, the graphical representation 810 may be configured to focus on individual aspects by filtering out or dimming other parts of the graphical representation 810 and receiving specific insights regarding the focused aspect. For example, a user may highlight (e.g., select) the activity data of the graphical representation 810, and the message 815 may state, "The activity pattern indicates that you are performing regular activities during morning hours and is well aligned with your recommended activity window."

[0223] If the system can detect an inconsistency in the circadian rhythm chronotype, the message 815-b may provide suggestions to the user to improve the user's overall health. For example, the message may state, "If you really seem to be lacking energy today, how about switching to rest mode today?" or "Since you went to bed later than usual, please focus on rest today." In such cases, accurately determining the circadian rhythm chronotype and detecting the inconsistency can improve the accuracy and efficiency of the preparation score and the activity score.

[0224] The message 815-b may include a time table or a calendar view to enable the user to adjust the time span and examine the body clock. For example, the message 815-b may include a toggle that enables the user to select the duration of time for averaging shown on the graphical representation 810-b. For example, the message may include toggles for selecting the number of months (e.g., from March to June), the number of weekdays (e.g., only Saturdays and Sundays, Mondays to Sundays, etc.), the number of weeks (e.g., two weeks), or a combination thereof.

[0225] After selecting message 815-c, application page 802-c may be presented to user 102 via GUI 800. For example, message 815-d and message 815-e may include the recommended time when the user is active, the recommended wake-up time when the user wakes up, the recommended bedtime when the user goes to bed, the recommended sleep time, the recommended time when the user takes a break, or a combination thereof.

[0226] In some cases, message 815-e may state "Are you sleepy? Your body has fallen into an energy slump of the afternoon dip. Don't worry if you feel lazy. The energy peak will come within an hour." In such a case, message 815-e may further provide insights regarding the recommended time for exercise, concentration, etc. For example, application page 802-c may display message 815-e that may state "For maximum cardiovascular efficiency and muscle strength, the optimal time for exercise is from 2:30 PM to 5:00 PM." In other examples, message 815-e may state "Let's make good use of the early morning. Exercise later in the morning to boost energy and start your day off right." In some cases, message 815-3 may state "Take advantage of the mid-afternoon and focus on the task at hand. Do your work in the mid-afternoon and complete the task efficiently and effectively." The personalized insights may indicate aspects of the collected physiological data (e.g., contributing factors within the physiological data) used to determine the circadian rhythm chronotype. In some cases, message 815 may provide personalized insights regarding graphical representation 810.

[0227] Application page 802-c may display a message 815-d indicating an optimal sleep schedule for the user. In some cases, the message 815-d may include a schedule recommended for the user, including bedtime, wake-up time, exercise time, concentration time, break time, or combinations thereof. For example, the message 815-d may state, "6:00 - 6:30 AM: The sharpest blood pressure increase, optimal wake-up time. 6:00 AM - 12:00 PM: High concentration, suitable for deep and creative work. 1:30 - 2:00 PM: Afternoon dip. A period of low energy. Please take it easy during this time." The message 815-d may indicate the recommended bedtime, wake-up time, mid-sleep point, or combinations thereof. In such cases, the message 815 may recommend the bedtime and / or wake-up time based on the determined circadian rhythm chronotype.

[0228] In some cases, the message 815 may show how the information collected from the user's daily portrait can be used in travel mode to adjust the user's body clock from jet lag and support the user's recovery in the new time zone. For example, the message 815 may indicate melatonin expression estimation, wake time line estimation, exercise time line recommendation, more personalized bedtime recommendation, light therapy assistance, or combinations thereof associated with jet lag.

[0229] For example, the determined circadian rhythm chronotype can be used to propose a bedtime in the new time zone based on the user's determined circadian rhythm chronotype, the time of the lowest nocturnal body temperature derived from historical data in the original time zone, the user's sleep history statistics, or combinations thereof. In such cases, the message 815 may provide recommendations for adjusting / planning the user's sleep-wake schedule for the first few days in the new time zone.

[0230] In some cases, the user may log symptoms or moments via user input 820. For example, the system may receive a user input (e.g., a tag) and log symptoms associated with a relaxed state (e.g., the user experiencing a certain moment). In some examples, the system may identify a moment of recovery when the user is in a relaxed state. In such cases, the system may determine a circadian rhythm chronotype based on identifying the moment of recovery. For example, the system may use the recovery time to determine the circadian rhythm chronotype.

[0231] In some implementations, the system may be configured to receive user input 820 regarding the determined circadian rhythm chronotype in order to train a classifier (e.g., supervised learning for a machine learning classifier) to improve circadian rhythm chronotype determination techniques. For example, the user device may display the determination of the circadian rhythm chronotype. Thereafter, the user may enter one or more user inputs such as the onset of symptoms, confirmation of the determined circadian rhythm chronotype, etc. These user inputs 820 may then be input to the classifier to train the classifier. In other words, user input 820 may be used to verify or confirm the determined circadian rhythm chronotype.

[0232] FIG. 9 shows a block diagram 900 of a device 905 that supports techniques for determining a circadian rhythm chronotype, according to an aspect of the present disclosure. Device 905 may include an input module 910, an output module 915, and a wearable application 920. Device 905 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0233] The input module 910 may provide means for receiving information such as packets, user data, control information, or any combination thereof, associated with various information channels (e.g., control channels, data channels, information channels related to disease detection techniques). The information may be passed to other components of the device 905. The input module 910 may utilize a single antenna or a set of multiple antennas.

[0234] The output module 915 may provide means for transmitting signals generated by other components of the device 905. For example, the output module 915 may transmit information such as packets, user data, control information, or any combination thereof, associated with various information channels (e.g., control channels, data channels, information channels related to disease detection techniques). In some examples, the output module 915 may be located in the same place as the input module 99 within the transceiver module. The output module 915 may utilize a single antenna or a set of multiple antennas.

[0235] For example, the wearable application 920 may include a data acquisition component 925, a sleep component 930, a data classifier 935, a chronotype component 940, or any combination thereof. In some examples, the wearable application 920 or its various components may be configured to perform various operations (e.g., receive, monitor, transmit) using the input module 910, the output module 915, or both, or in other ways in cooperation with these. For example, the wearable application 920 may receive information from the input module 910, transmit information to the output module 915, or be integrated in combination with the input module 910, the output module 915, or both, to receive information, transmit information, or perform various other operations as described herein.

[0236] The wearable application 920 can support the determination of a circadian rhythm chronotype in an application that runs on the operating system of a user device and is associated with a wearable device, according to the embodiments disclosed herein. The data acquisition component 925 can be configured as means for receiving, from the wearable device, a first set of physiological data measured from the user by the wearable device over a certain period of time, or otherwise support this, and the first set of physiological data includes at least nocturnal body temperature data, activity data, and sleep pattern data. The sleep component 930 can be configured as means for receiving, from the wearable device, a second set of physiological data measured from the user by the wearable device over the previous sleep day, or otherwise support this, and the second set of physiological data includes at least sleep pattern data. The data classifier 935 can be configured as means for classifying the first set of physiological data into a circadian rhythm chronotype using a machine learning model, at least partially based on inputting the first set of physiological data into the machine learning model, or otherwise support this. The chronotype component 940 can be configured as means for comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process the data received from the wearable device, or otherwise support this. The user interface component 945 can be configured as means for causing a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof, or otherwise support this.

[0237] FIG. 10 shows a block diagram 1000 of a wearable application 1020 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. Wearable application 1020 may be an example of a wearable application or wearable application 920, or aspects of both, as described herein. Wearable application 1020 or its various components may be examples of means for performing various aspects of techniques for determining a circadian rhythm chronotype as described herein. For example, wearable application 1020 may include a data acquisition component 1025, a sleep component 1030, a data classifier 1035, a chronotype component 1040, a user interface component 1045, or any combination thereof. Each of these components may communicate with each other directly or indirectly (e.g., via one or more buses).

[0238] Wearable application 1020 may support the determination of a circadian rhythm chronotype in an application that runs on the operating system of a user device and is associated with a wearable device, according to embodiments disclosed herein. The data acquisition component 1025 may be configured as means for receiving, from the wearable device, a first set of physiological data measured from the user by the wearable device over a certain period, or may support this in other ways. The first set of physiological data includes at least nocturnal body temperature data, activity data, and sleep pattern data. The sleep component 1030 may be configured as means for receiving, from the wearable device, a second set of physiological data measured from the user by the wearable device over the previous sleep day, or may support this in other ways. The second set of physiological data includes at least sleep pattern data. The data classifier 1035 may be configured as means for classifying the first set of physiological data into a circadian rhythm chronotype using a machine learning model, at least partially based on inputting the first set of physiological data into the machine learning model, or may support this in other ways. The chronotype component 1040 may be configured as means for comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device, or may support this in other ways. The user interface component 1045 may be configured as means for causing a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof, or may support this in other ways.

[0239] In some examples, the user interface component 1045 can be configured as means for causing a graphical user interface of a user device to display a graphical representation of the averaging of sleep pattern data of a first set of physiological data over a period of time, or may otherwise support this.

[0240] In some examples, the averaging of sleep pattern data includes the average wake-up time at which the user wakes up, the average bedtime at which the user goes to bed, the average mid-sleep point time, the average sleep duration, or combinations thereof.

[0241] In some examples, the user interface component 1045 can be configured as means for overlaying a graphical representation of the averaging of sleep pattern data of a first set of physiological data over a period of time onto a representation of a 24-hour time span, or may otherwise support this.

[0242] In some examples, the user interface component 1045 can be configured as means for causing a graphical user interface of a user device to display a segment of a representation of a 24-hour time span that includes the averaging of sleep pattern data of a first set of physiological data over a period of time, or may otherwise support this.

[0243] In some examples, the segment represents the averaging of sleep pattern data of a first set of physiological data over a period of time as a shaped portion having a first side indicating the average time at which the user goes to bed, a second side indicating the average time at which the user wakes up, and a midpoint located between the first side and the second side and indicating the average time of the user's mid-sleep point.

[0244] In some examples, the data acquisition component 1025 may be configured as, or otherwise support, a means for identifying the time of night associated with the minimum nocturnal body temperature, at least in part based on receiving a first set of physiological data. Classifying the first set of physiological data into a circadian rhythm chronotype is based at least in part on identifying the time of night associated with the minimum nocturnal body temperature.

[0245] In some examples, the data classifier 1035 may be configured as, or otherwise support, a means for an application to process the sleep pattern data of the first set of physiological data to extract the standard deviation of the sleep midpoint, the median wake-up time at which the user wakes up, the median bedtime at which the user goes to bed, or a combination thereof. In some examples, the data classifier 1035 may be configured as, or otherwise support, a means for an application to process the activity data of the first set of physiological data to extract at least the average task metabolic equivalent (MET) value, the time during which the user is active, or both. In some examples, the data classifier 1035 may be configured as, or otherwise support, a means for an application to process the nocturnal body temperature data to extract at least the average skin temperature, the average skin temperature of a plurality of maximum body temperature values over a continuous 24-hour time span, the average skin temperature of a plurality of minimum body temperature values over a continuous 24-hour time span, or a combination thereof. In some examples, classifying the first set of physiological data into a circadian rhythm chronotype is based at least in part on an application processing the sleep pattern data, the activity data, and the nocturnal body temperature data.

[0246] In some examples, the chronotype component 1040 may be configured as, or otherwise support, a means for determining a mismatch between the received second set of physiological data and the determined circadian rhythm chronotype, at least in part based on comparing the determined circadian rhythm chronotype with the received second set of physiological data.

[0247] In some examples, the message includes a recommended time for the user to be active, a recommended wake-up time for the user to wake up, a recommended bedtime for the user to go to bed, a recommended sleep time, a recommended time for the user to take a break, a recommended time for the user to concentrate, a sleep consistency message, a sleep inconsistency message, or a combination thereof.

[0248] In some examples, the nocturnal body temperature data includes consecutive nocturnal body temperature data.

[0249] In some examples, the wearable device includes a wearable ring device.

[0250] In some examples, the wearable device collects a first set of physiological data and a second set of physiological data from the user based on arterial blood flow, capillary blood flow, arteriolar blood flow, or a combination thereof.

[0251] FIG. 11 shows a diagram of a system 1100 including a device 1105 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. The device 1105 may be an example of the components of the device 1005 as described herein, or may include the components of the device 905. The device 1105 may include an example of the user device 906 as previously described herein. The device 1105 may include components for bidirectional communication, including components for transmitting and receiving communications between the wearable device 104 and the server 110, such as a wearable application 1120, a communication module 1110, an antenna 1115, user interface components 1125, a database (application data) 1130, a memory 1135, and a processor 1140. These components may be electronically communicating or may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1145).

[0252] The communication module 1110 may manage input and output signals for the device 1105 via the antenna 1115. The communication module 1110 may include an example of the communication module 220-b of the user device 106 described with reference to FIG. 2. In this regard, the communication module 1110 may manage communication with the ring 104 and the server 110 as illustrated in FIG. 2. The communication module 1110 may also manage peripheral devices not integrated into the device 1105. In some cases, the communication module 1110 may represent a physical connection or port to an external peripheral device. In some cases, the communication module 1110 may utilize an operating system such as iOS (registered trademark), ANDROID (registered trademark), MS-DOS (registered trademark), MS-WINDOWS (registered trademark), OS / 2 (registered trademark), UNIX (registered trademark), LINUX (registered trademark) or another known operating system. In other cases, the communication module 1110 may represent or interact with wearable devices (such as the ring 104), modems, keyboards, mice, touchscreens or similar devices. In some cases, the communication module 1110 may be implemented as part of the processor 1140. In some examples, the user may interact with the device 1105 via the communication module 1110, the user interface component 1125, or a hardware component controlled by the communication module 1110.

[0253] In some cases, device 1105 may include a single antenna 1115. However, in other cases, device 1105 may have two or more antennas 1115, which can transmit or receive multiple wireless transmissions simultaneously. Communication module 1110 may communicate bidirectionally via one or more antennas 1115, via a wired link or a wireless link as described herein. For example, communication module 1110 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Communication module 1110 may also include a modem for modulating packets and providing the modulated packets to one or more antennas 1115 for transmission and demodulating packets received from one or more antennas 1115.

[0254] User interface component 1125 may manage data storage and processing within database 1130. In some cases, the user may interact with user interface component 1125. In other cases, user interface component 1125 may operate automatically without user interaction. Database 1130 may be an example of a single database, a distributed database, multiple distributed databases, a data store, a data lake, or an emergency backup database.

[0255] Memory 1135 may include RAM and ROM. Memory 1135 may store computer-readable and computer-executable software that, when executed, causes processor 1140 to perform various functions described herein. In some cases, memory 1135 may include a BIOS that can control basic hardware or software operations, among other things, such as interaction with peripheral components or devices.

[0256] Processor 1140 may include an intelligent hardware device (e.g., a general-purpose processor, DSP, CPU, microcontroller, ASIC, FPGA, programmable logic device, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some cases, processor 1140 may be configured to operate a memory array using a memory controller. In other cases, the memory controller may be incorporated into processor 1140. Processor 1140 may be configured to execute computer-readable instructions stored in memory 1135 to perform various functions (e.g., functions or tasks that support a method and system for a sleep staging algorithm).

[0257] Wearable application 1120 may support the determination of a circadian rhythm chronotype in an application that runs on the operating system of a user device and is associated with a wearable device, according to an embodiment disclosed herein. For example, wearable application 1120 may be configured as means for receiving, from a wearable device, a first set of physiological data measured from a user by the wearable device over a period of time, or may support this in other ways, where the first set of physiological data includes at least nocturnal body temperature data, activity data, and sleep pattern data. Wearable application 1120 may be configured as means for receiving, from the wearable device, a second set of physiological data measured from a user by the wearable device over the previous sleep day, or may support this in other ways, where the second set of physiological data includes at least sleep pattern data. Wearable application 1120 may be configured as means for classifying the first set of physiological data into a circadian rhythm chronotype using a machine learning model, at least partially based on inputting the first set of physiological data into the machine learning model, or may support this in other ways. Wearable application 1120 may be configured as means for comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device, or may support this in other ways. Wearable application 1120 may be configured as means for causing a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof, or may support this in other ways.

[0258] By including or configuring the wearable application 1120 in accordance with the examples described herein, the device 1105 can support techniques for improving communication reliability, reducing latency, enhancing the user experience related to reducing processing, reducing power consumption, more efficiently utilizing communication resources, improving coordination between devices, extending battery life, improving the utilization rate of processing capabilities, and the like.

[0259] The wearable application 1120 may include an application (e.g., “app”), program, software, or other components that are configured to facilitate communication with the ring 104, server 110, other user devices 106, and the like. For example, the wearable application 1120 may be configured to receive data (e.g., physiological data) from the ring 104, perform processing operations on the received data, transmit and receive data with the server 110, and present the data to the user 102, and may include an application executable on the user device 106.

[0260] FIG. 12 is a flowchart showing a method 1200 that supports techniques for determining a circadian rhythm chronotype according to an aspect of the present disclosure. The operations of the method 1200 may be implemented by a user device or a component thereof as described herein. For example, the operations of the method 1200 may be performed by a user device as described with reference to FIGS. 1 to 11. In some examples, the user device may execute a set of instructions for controlling the functional elements of the user device to perform the described functions. Additionally or alternatively, the user device may use dedicated hardware to perform aspects of the described functions.

[0261] At 1205, the method may include receiving, from a wearable device, a first set of physiological data measured from a user by the wearable device and collected over a period of time, where the first set of physiological data includes at least nocturnal body temperature data, activity data, and sleep pattern data. The operation of block 1205 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1205 may be performed by data acquisition component 1025, as described with reference to FIG. 10.

[0262] At 1210, the method may include receiving, from a wearable device, a second set of physiological data measured from a user by the wearable device and collected over the previous sleep day, where the second set of physiological data includes at least sleep pattern data. The operation of block 1210 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1210 may be performed by sleep component 1030, as described with reference to FIG. 10.

[0263] At 1215, the method may include using a machine learning model to classify the first set of physiological data into a circadian rhythm chronotype, based at least in part on inputting the first set of physiological data into the machine learning model. The operation of block 1215 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1215 may be performed by data classifier 1035, as described with reference to FIG. 10.

[0264] At 1220, the method may include comparing the determined circadian rhythm chronotype with the second set of received physiological data by an application configured to process data received from the wearable device. The operation of block 1220 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1220 may be performed by chronotype component 1040, as described with reference to FIG. 10.

[0265] At 1225, the method may include causing a graphical user interface of a user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the second set of received physiological data, or a combination thereof. The operation of block 1225 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1225 may be performed by user interface component 1045 as described with reference to FIG. 10.

[0266] FIG. 13 is a flowchart showing a method 1300 that supports techniques for determining a circadian rhythm chronotype, according to an aspect of the present disclosure. The operations of method 1300 may be implemented by a user device or components thereof, as described herein. For example, the operations of method 1300 may be performed by a user device as described with reference to FIGS. 1-11. In some examples, the user device may execute a set of instructions that control functional elements of the user device to perform the described functions. Additionally or alternatively, the user device may use dedicated hardware to perform aspects of the described functions.

[0267] At 1305, the method may include receiving, from a wearable device, a first set of physiological data measured from a user by the wearable device over a period of time, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data. The operation of block 1305 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1305 may be performed by data acquisition component 1025 as described with reference to FIG. 10.

[0268] At 1310, the method may include receiving, from a wearable device, a second set of physiological data measured from a user by the wearable device over a previous sleep day, the second set of physiological data including at least sleep pattern data. The operation of block 1310 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1310 may be performed by sleep component 1030 as described with reference to FIG. 10.

[0269] At 1315, the method may include using a machine learning model to classify a first set of physiological data into a circadian rhythm chronotype, based at least in part on inputting the first set of physiological data into the machine learning model. The operation of block 1315 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1315 may be performed by data classifier 1035 as described with reference to FIG. 10.

[0270] At 1320, the method may include comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device. The operation of block 1320 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1320 may be performed by chronotype component 1040 as described with reference to FIG. 10.

[0271] At 1325, the method may include determining a mismatch between the received second set of physiological data and the determined circadian rhythm chronotype, based at least in part on a comparison of the determined circadian rhythm chronotype with the received second set of physiological data. The operation of block 1325 may be performed according to the examples disclosed herein. In some examples, aspects of the operation of 1325 may be performed by chronotype component 1040 as described with reference to FIG. 10.

[0272] At 1330, the method may include causing a graphical user interface of a user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof. The operations of block 1330 may be performed according to the examples disclosed herein. In some examples, aspects of the operations of 1330 may be performed by the user interface component 1045, as described with reference to FIG. 10.

[0273] Note that the above-described method illustrates possible implementations, and the operations and steps may be rearranged or otherwise modified, and other implementations are possible. Further, aspects from two or more of the above methods may be combined.

[0274] Describe a method for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device. The method includes receiving, from the wearable device, a first set of physiological data measured from a user by the wearable device over a period of time, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data; receiving, from the wearable device, a second set of physiological data measured from the user by the wearable device over a previous sleep day, the second set of physiological data including at least sleep pattern data; classifying, using a machine learning model, the first set of physiological data into a circadian rhythm chronotype, based at least in part on inputting the first set of physiological data into the machine learning model; comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device; and displaying, on a graphical user interface of the user device, a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof.

[0275] An apparatus for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device will be described. The apparatus includes a processor, a memory coupled to the processor, and instructions stored in the memory. The instructions cause the apparatus to receive, from the wearable device, a first set of physiological data measured from a user by the wearable device over a certain period, where the first set of physiological data includes at least nighttime body temperature data, activity data, and sleep pattern data; receive, from the wearable device, a second set of physiological data measured from a user by the wearable device over a previous sleep day, where the second set of physiological data includes at least sleep pattern data; classify the first set of physiological data into a circadian rhythm chronotype using a machine learning model, at least partially based on inputting the first set of physiological data into the machine learning model; compare the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device; and cause a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof, which may be executable by the processor.

[0276] Another device for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device will be described. The device includes means for receiving, from the wearable device, a first set of physiological data measured from a user by the wearable device over a certain period, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data; means for receiving, from the wearable device, a second set of physiological data measured from a user by the wearable device over the previous sleep day, the second set of physiological data including at least sleep pattern data; means for classifying the first set of physiological data into a circadian rhythm chronotype using a machine learning model, based at least in part on inputting the first set of physiological data into the machine learning model; means for comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device; and means for causing a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof to be displayed on a graphical user interface of the user device.

[0277] Describes a non-transitory computer-readable medium storing code for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device. The code is to receive, from the wearable device, a first set of physiological data measured from the user by the wearable device and collected over a period of time, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data; to receive, from the wearable device, a second set of physiological data measured from the user by the wearable device and collected over the previous sleep day, the second set of physiological data including at least sleep pattern data; to classify the first set of physiological data into a circadian rhythm chronotype using a machine learning model, based at least in part on inputting the first set of physiological data into the machine learning model; to compare the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device; and to cause a processor to execute instructions for causing a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof.

[0278] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for causing a graphical user interface of a user device to display a graphical representation of an averaging of sleep pattern data of a first set of physiological data over a period of time.

[0279] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the averaging of sleep pattern data includes an average wake-up time at which the user wakes up, an average bedtime at which the user goes to bed, an average mid-sleep point time, an average sleep duration, or a combination thereof.

[0280] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for overlaying a graphical representation of the averaging of sleep pattern data of a first set of physiological data over a period of time onto a representation of a 24-hour time span.

[0281] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for causing a graphical user interface of a user device to display a segment of a representation of a 24-hour time span that includes the averaging of sleep pattern data of a first set of physiological data over a period of time.

[0282] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the segment is represented as a shaped portion having a first side indicating the average time the user goes to bed, a second side indicating the average time the user wakes up, and a midpoint located between the first side and the second side and indicating the average time of the user's mid-sleep point, which averages the sleep pattern data of the first set of physiological data over a period of time.

[0283] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for identifying the time of night associated with the lowest body temperature at night, at least partially based on receiving the first set of physiological data, and classifying the first set of physiological data into a circadian chronotype may be at least partially based on identifying the time of night associated with the lowest body temperature at night.

[0284] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may include operations, features, means, or instructions for processing sleep pattern data of a first set of physiological data by an application to extract a standard deviation of sleep midpoints, a median wake-up time at which the user wakes up, a median bedtime at which the user goes to bed, or a combination thereof, processing activity data of the first set of physiological data by the application to extract at least an average metabolic equivalent of task (MET) value, the time the user is active, or both, processing nighttime body temperature data by the application to extract at least an average skin temperature, an average skin temperature of a plurality of maximum body temperature values for a continuous 24-hour time span, an average skin temperature of a plurality of minimum body temperature values for a continuous 24-hour time span, or a combination thereof, and classifying the first set of physiological data into a circadian rhythm chronotype may be based at least in part on processing, by the application, sleep pattern data, activity data, and nighttime body temperature data.

[0285] Some examples of the methods, apparatuses, and non-transitory computer-readable media described herein may further include operations, features, means, or instructions for determining an inconsistency between a second set of received physiological data and a determined circadian rhythm chronotype, based at least in part on comparing the determined circadian rhythm chronotype with the second set of received physiological data.

[0286] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the message includes a recommended time when the user can be active, a recommended wake-up time at which the user wakes up, a recommended bedtime at which the user goes to bed, a recommended sleep duration, a recommended time when the user takes a break, a recommended time when the user can concentrate, a sleep alignment message, a sleep misalignment message, or a combination thereof.

[0287] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the nighttime body temperature data includes continuous nighttime body temperature data.

[0288] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the wearable device includes a wearable ring device.

[0289] In some examples of the methods, apparatuses, and non-transitory computer-readable media described herein, the wearable device collects a first set of physiological data and a second set of physiological data from the user based on arterial blood flow, capillary blood flow, arteriolar blood flow, or a combination thereof.

[0290] In connection with the accompanying drawings, the descriptions set forth herein describe exemplary configurations and do not represent all examples that may be implemented or that are within the scope of the claims. The term "exemplary" as used herein means "serving as an example, instance, or illustration" and does not mean "preferred" or "advantageous over other examples." The detailed description includes specific details for the purpose of providing an understanding of the technologies described. However, these technologies may be practiced without these specific details. In some examples, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0291] In the accompanying drawings, similar components or features may have the same reference labels. Further, various components of the same type may be followed by a reference label with a hyphen and may be distinguished by a second label that differentiates the similar components. When only the first reference label is used in the specification, the description is applicable to any one of the similar components having the same first reference label regardless of the second reference label.

[0292] The information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced through the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0293] The various illustrative blocks and modules described in connection with the disclosure of this specification may be implemented or executed in any combination of a general purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller or state machine. The processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors associated with a DSP core or any other such configuration).

[0294] The functions described in this specification may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions may be stored or transmitted as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of the present disclosure and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or any combination thereof. The features implementing the functions may also be physically located in various positions, including being distributed such that parts of the functions are implemented at different physical locations. Also, as used herein, including in the claims, the "or" used in a list of items (e.g., a list of items preceded by phrases such as "at least one of" or "one or more of") indicates an inclusive list, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase "based on" shall not be construed to refer to a closed set of conditions. For example, an exemplary step described as "based on condition A" may be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" shall be construed in the same manner as the phrase "at least partially based on".

[0295] A computer-readable medium includes both a non-transitory computer storage medium and a communication medium including any medium that facilitates transfer of a computer program from one location to another. The non-transitory storage medium may be any available medium that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, the non-transitory computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), compact disc (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer or a general purpose or special purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if software is transmitted from a website, server or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, microwave, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, microwave are included in the definition of the medium. As used herein, disk (disk or disc) includes CD, laser disk, optical disk, digital versatile disk (DVD), floppy disk and Blu-ray (registered trademark) disk, where disk (disk) typically magnetically reproduces data, while disk (disc) optically reproduces data using a laser. Combinations of the above are also included within the scope of computer-readable media.

[0296] The description in this specification is provided to enable those skilled in the art to make or use the present disclosure. Various modifications to the present disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Accordingly, the present disclosure is not limited to the embodiments and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device, comprising: receiving, from the wearable device, a first set of physiological data measured from a user by the wearable device and collected over a certain period, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data; receiving, from the wearable device, a second set of physiological data measured from the user by the wearable device and collected over the previous sleep day, the second set of physiological data including at least sleep pattern data; using a machine learning model to classify the first set of physiological data into the circadian rhythm chronotype, based at least in part on inputting the first set of physiological data into the machine learning model; comparing, by an application configured to process data received from the wearable device, the determined circadian rhythm chronotype with the second set of received physiological data; displaying, on a graphical user interface of the user device, a message associated with the comparison, the determined circadian rhythm chronotype, the second set of received physiological data, or a combination thereof. A method comprising the above steps.

2. The method according to claim 1, further comprising displaying, on the graphical user interface of the user device, a graphical representation of the averaging of the sleep pattern data of the first set of physiological data over the certain period. The method according to claim 1, further comprising the above step.

3. The method according to claim 2, wherein the averaging of the sleep pattern data includes an average wake-up time when the user wakes up, an average bedtime when the user goes to bed, an average mid-sleep point time, an average sleep duration, or a combination thereof. The method according to claim 2, including the above step.

4. The method according to claim 2, further comprising overlaying the graphical representation of the averaging of the sleep pattern data of the first set of physiological data over a certain period on a representation of a 24-hour time span. The method according to claim 2, further comprising the above step.

5. Causing the graphical user interface of the user device to display a segment of the representation of the 24-hour time span, including the averaging of the sleep pattern data of the first set of the physiological data over the certain period of time. The method according to claim 4, further comprising.

6. The segment represents the averaging of the sleep pattern data of the first set of the physiological data over the certain period of time as a shaped portion having a first side indicating the average time when the user goes to bed, a second side indicating the average time when the user gets up, and a midpoint located between the first side and the second side and indicating the average time of the user's sleep midpoint. The method according to claim 5.

7. Further comprising the step of identifying the time of night associated with the lowest body temperature at night, at least partially based on receiving the first set of the physiological data, and classifying the first set of the physiological data into the circadian rhythm chronotype is at least partially based on identifying the time of night associated with the lowest body temperature at night. The method according to claim 1.

8. The application processes the sleep pattern data of the first set of the physiological data to extract the standard deviation of the sleep midpoint, the median wake-up time when the user wakes up, the median bedtime when the user goes to bed, or a combination thereof; The application processes the activity data of the first set of the physiological data to extract at least the average metabolic equivalent of task (MET) value, the time when the user is active, or both; The application processes the night-time body temperature data to extract at least the average skin temperature, the average skin temperature of a plurality of maximum body temperature values in a continuous 24-hour time span, the average skin temperature of a plurality of minimum body temperature values in a continuous 24-hour time span, or a combination thereof; Further comprising, and classifying the first set of the physiological data into the circadian rhythm chronotype is at least partially based on the application processing the sleep pattern data, the activity data, and the night-time body temperature data. The method according to claim 1.

9. Determining a mismatch between the second set of the received physiological data and the determined circadian rhythm chronotype, at least partially based on comparing the determined circadian rhythm chronotype with the second set of the received physiological data The method according to claim 1, further comprising

10. The message includes a recommended time for the user to be active, a recommended wake-up time for the user to wake up, a recommended bedtime for the user to go to bed, a recommended sleep time, a recommended time for the user to take a break, a recommended time for the user to concentrate, a sleep alignment message, a sleep mismatch message, or a combination thereof The method according to claim 1

11. The nocturnal body temperature data includes continuous nocturnal body temperature data The method according to claim 1

12. The wearable device includes a wearable ring device The method according to claim 1

13. The wearable device collects the first set of the physiological data and the second set of the physiological data from the user based on arterial blood flow, capillary blood flow, arteriolar blood flow, or a combination thereof The method according to claim 1

14. An apparatus for determining a circadian rhythm chronotype in an application that is executed on an operating system of a user device and is associated with a wearable device, comprising a processor a memory coupled to the processor instructions stored in the memory, which cause the apparatus to receive, from the wearable device, a first set of physiological data measured from a user by the wearable device and collected over a certain period, wherein the first set of physiological data includes at least nocturnal body temperature data, activity data, and sleep pattern data receive, from the wearable device, a second set of physiological data measured from the user by the wearable device and collected over the previous sleep day, wherein the second set of physiological data includes at least sleep pattern data classify the first set of the physiological data into the circadian rhythm chronotype using the machine learning model, at least partially based on inputting the first set of the physiological data into the machine learning model An application configured to process data received from the wearable device compares the determined circadian rhythm chronotype with the second set of the received physiological data; causes a graphical user interface of the user device to display a message associated with the comparison, the determined circadian rhythm chronotype, the second set of the received physiological data, or a combination thereof; instructions executable by the processor to cause the above; A device comprising.

15. The instructions cause the device to cause a graphical user interface of the user device to display a graphical representation of an averaging of the sleep pattern data of the first set of the physiological data over the certain period; The device according to claim 14, further executable by the processor to cause the above.

16. The averaging of the sleep pattern data includes an average wake-up time at which the user wakes up, an average bedtime at which the user goes to bed, an average sleep midpoint time, an average sleep time, or a combination thereof. The device according to claim 15.

17. The instructions cause the device to overlay the graphical representation of the averaging of the sleep pattern data of the first set of the physiological data over the certain period on a representation of a 24-hour time span. The device according to claim 15, further executable by the processor to cause the above.

18. A non-transitory computer-readable medium storing code for determining a circadian rhythm chronotype in an application that runs on an operating system of a user device and is associated with a wearable device, the code comprising: receiving, from the wearable device, a first set of physiological data measured from a user by the wearable device and collected over a certain period, the first set of physiological data including at least nocturnal body temperature data, activity data, and sleep pattern data; Receiving, from the wearable device, a second set of physiological data measured from the user by the wearable device over the previous sleep day, wherein the second set of physiological data includes at least sleep pattern data; Classifying the first set of physiological data into the circadian rhythm chronotype using the machine learning model, based at least in part on inputting the first set of physiological data into the machine learning model; Comparing the determined circadian rhythm chronotype with the received second set of physiological data by an application configured to process data received from the wearable device; Causing a message associated with the comparison, the determined circadian rhythm chronotype, the received second set of physiological data, or a combination thereof to be displayed on a graphical user interface of the user device; A non-transitory computer-readable medium including instructions executable by a processor for the purposes of. **Claim 19** The instructions Cause a graphical representation of an averaging of the sleep pattern data of the first set of physiological data over the period of time to be displayed on the graphical user interface of the user device The non-transitory computer-readable medium according to claim 18, which is further executable by the processor for the purposes of. **Claim 20** The averaging of the sleep pattern data includes an average wake-up time at which the user wakes up, an average bedtime at which the user goes to bed, an average mid-sleep point time, an average sleep duration, or a combination thereof. The non-transitory computer-readable medium according to claim 19.

Images