Techniques for determining and managing fitness fatigue scores

Abstract

A fitness fatigue score for the user for the current day is provided. The fitness fatigue score can be determined based at least in part on first data acquired over a first period of time, second data acquired over a second period of time shorter in duration than the first period of time, and third data acquired over a third period of time longer in duration than the first period of time. The first data includes heart rate measurements of the user over the first period of time. The second data includes one or more sleep metrics for a plurality of sleep events of the user over the second period of time. The third data includes heart rate variability of the user over the third period of time. Furthermore, exercise recommendations for the current day can be generated based on the fitness fatigue score.

Description

[Technical Field]

[0001] Related Applications This application claims priority to U.S. Patent Application No. 17 / 891,428, filed August 19, 2022, which is incorporated by reference herein in its entirety. [Background technology]

[0002] Recent advances in technology, including technology available via consumer devices, have led to corresponding advances in health detection and monitoring. For example, devices such as fitness trackers and smart watches can determine information about the pulse or movement of a person wearing the device. However, technical challenges exist regarding the amount and type of health information that can be determined using such devices, due to limitations in the collection of such information due to the capabilities of conventional devices. In particular, conventional devices are limited in their ability to accurately and automatically detect parameters that are indicative of a user's stress.

[0003] Accordingly, the present disclosure is directed to technical solutions / advantages to the above-mentioned technical problems. Accordingly, the present disclosure is directed to systems and methods for calculating a stress score for a user of a wearable device. In certain embodiments, for example, the stress score can be calculated using electrodermal activity (EDA) data collected from an EDA sensor while the user is wearing the wearable device. More specifically, because the sympathetic nervous system can cause micro-perspiration throughout a person's body, conductance between the EDA sensor on the wearable device and the user's hand or fingertip increases as sweating levels increase. Thus, when the user's palm or fingers are positioned adjacent to the EDA sensor, the EDA sensor can generate data that the wearable device can use to accurately and automatically calculate the user's stress. Summary of the Invention

[0004] Aspects and advantages of the present invention will be set forth in part in the description that follows, or may be obvious from the description, or may be learned by practice of the invention.

[0005] In one aspect, according to an embodiment of the present disclosure, a method for determining a fitness fatigue score of a user is provided. The method includes acquiring first data of the user over a first period of time. The first data includes a plurality of heart rate measurements of the user over the first period of time. The method includes acquiring second data of the user over a second portion of time shorter in duration than the first period of time. The second data includes one or more sleep metrics for a plurality of sleep events of the user over the second period of time. The method includes acquiring third data of the user over a third period of time longer in duration than the first period of time. The third data includes heart rate variability data of the user over the third period of time. The method includes determining a fitness fatigue score of the user for the current day based at least in part on the first data, the second data, and the third data. The method includes displaying the fitness fatigue score on a display screen of the electronic device.

[0006] In some embodiments, the one or more sleep metrics may include the duration of each of the multiple sleep events. Alternatively or additionally, the one or more sleep metrics may include the time at which each of the sleep events occurred.

[0007] In some embodiments, the first period of time can include the 14 days immediately preceding the current day. Alternatively or additionally, the second period of time can include the 7 days immediately preceding the current day. In some embodiments, the third period of time can include the 30 days immediately preceding the current day.

[0008] In some embodiments, the method includes determining a current day exercise recommendation based at least in part on the fitness fatigue score determined for the current day. The method includes causing a display screen of the electronic device to display the exercise recommendation. In some embodiments, the recommendation may be for the user to refrain from exercising for the current day when the fitness fatigue score for the current day is less than a first threshold. In some implementations, the recommendation may be for the user to engage in a first physical activity for the current day when the fitness fatigue score for the current day is greater than the first threshold and less than a second threshold. In some embodiments, the recommendation may be for the user to engage in a second physical activity for the current day when the fitness fatigue score for the current day is greater than a second threshold. The second physical activity may be more intense than the first physical activity.

[0009] In some embodiments, determining the user's fitness fatigue score for the current day includes determining a first sub-score based on the first data. Determining the user's fitness fatigue score further includes determining a second sub-score based on the second data and determining a third sub-score based at least in part on the third data. Further, determining the fitness fatigue score includes determining the user's fitness fatigue score for the current day based at least in part on the first sub-score, the second sub-score, and the third sub-score. In some embodiments, the first sub-score is weighted more heavily than each of the second sub-score and the third sub-score.

[0010] In some embodiments, determining the fitness fatigue score includes determining that the first sub-score is less than a threshold value and determining that the fitness fatigue score for the day is the first sub-score.

[0011] In some embodiments, determining the first sub-score based on the first data includes determining a preliminary value for each of a plurality of heart rate measurements included in the first data. Determining the first sub-score further includes determining that the preliminary values ​​of one or more of the heart rate measurements are greater than a threshold. Determining the first sub-score still further includes determining the first sub-score based at least in part on the one or more heart rate measurements whose preliminary values ​​are greater than the threshold.

[0012] In some embodiments, determining a preliminary value for each of the heart rate measurements includes determining a resting heart rate of the user based at least in part on the first data and determining a maximum heart rate of the user based at least in part on an age of the user. Determining the preliminary values ​​further includes determining a preliminary value for each of the plurality of heart rate measurements based at least in part on a comparison of each of the heart rate measurements to the resting heart rate of the user and the maximum heart rate of the user.

[0013] In some embodiments, the heart rate variability data includes heart rate variability measurements taken during each of a plurality of sleep events occurring over a third period of time. Further, determining the third sub-score based at least in part on the heart rate variability data includes determining a root mean square of successive differences of heart rate variability measurements associated with a first sleep event of the plurality of sleep events. The first sleep event may correspond to a temporally most recent sleep event of the plurality of sleep events. The method includes determining the third sub-score based at least in part on a comparison of the heart rate variability measurement associated with the first sleep event to a heart rate variability measurement of at least one other sleep event of the plurality of sleep events.

[0014] Various embodiments according to the present disclosure are now described with reference to the drawings. [Brief explanation of the drawings]

[0015] [Figure 1A]1 illustrates an exemplary device that can be used to obtain and analyze user health information, according to various embodiments. [Figure 1B] 1 illustrates an exemplary device that can be used to obtain and analyze user health information, according to various embodiments. [Figure 2] 1 illustrates an exemplary set of devices that can communicate in accordance with various embodiments. [Figure 3] 1 illustrates an exemplary stress score algorithm that may be utilized in accordance with various embodiments. [Figure 4] 1 illustrates an exemplary interface that may be provided in accordance with various embodiments. [Figure 5] 1 illustrates an exemplary interface that may be provided in accordance with various embodiments. [Figure 6] 1 illustrates an exemplary interface that may be provided in accordance with various embodiments. [Figure 7] 1 illustrates an exemplary process for determining a stress score that may be utilized in accordance with various embodiments. [Figure 8] 1 illustrates an exemplary process for monitoring a user's stress that may be utilized in accordance with various embodiments. [Figure 9] 1 illustrates an exemplary environment in which aspects of various embodiments may be implemented. [Figure 10] 1 illustrates a flow diagram of a method for determining a fitness fatigue score according to some embodiments of the present disclosure. [Figure 11] 1 illustrates a flow diagram of a method for determining a first sub-score of a fitness fatigue score according to some embodiments of the present disclosure. [Figure 12] 10 illustrates a flow diagram of a method for determining a third sub-score of a fitness fatigue score according to some embodiments of the present disclosure. [Figure 13] 1 illustrates a graphical user interface displaying a fitness fatigue score on a display screen of an electronic device according to some embodiments of the present disclosure. [Figure 14] 1 illustrates a graphical user interface displaying a fitness fatigue score on a display screen of a wearable computing device, according to some embodiments of the present disclosure. [Figure 15] 1 illustrates a graphical user interface for a fitness fatigue score on a display screen of a mobile computing device, according to some embodiments of the present disclosure. [Figure 16] 1 illustrates a graphical user interface that displays exercise recommendations to a user according to the user's fitness fatigue score, according to some embodiments of the present disclosure. [Figure 17] 1 illustrates a graphical user interface displaying a user's fitness fatigue score over a period of time, according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] In the following description, various embodiments are described. For purposes of explanation, specific configurations and details are set forth to provide a thorough understanding of the embodiments. However, it will also be apparent to those skilled in the art that the embodiments may be practiced without the specific details. Furthermore, well-known features may be omitted or simplified so as not to obscure the described embodiments.

[0017] As computing devices become more ubiquitous and portable, many advantages are being seen in the field of health monitoring and diagnostics. Computing devices, particularly those that can be worn or carried by a user, may include one or more sensors to detect physiological information about the user and / or the environment around the user. This information can be used to observe, detect, or diagnose various health conditions outside of a traditional clinic or laboratory setting. For example, in the context of stress monitoring, a portable or wearable electronic device may be able to detect when a user's sympathetic nerves cause minute amounts of sweating throughout the user's body. Furthermore, the computing device may be able to record and interpret the detected information about the user and / or the environment to determine a health assessment. As in the example above, a wearable electronic device may be able to record relatively high-frequency skin conductance responses (SCRs) and examine the number of skin conductance spikes within a sliding window of time to generate an assessment that the user is experiencing stress.

[0018] Approaches according to various embodiments provide for the determination, prediction, and / or monitoring of factors that may be indicative of stress or other such conditions in a user. In at least one embodiment, this determination may be made based at least in part on data collected by a wearable computer, such as device 100 shown in the embodiment of FIG. 1A. In various embodiments described herein, a person may wear or utilize device 100 that can automatically measure or determine at least some aspects of the person's health or well-being. In particular, as shown in FIG. 1A, device 100 is a smartwatch 104, although other devices, such as smart or connected fitness bands or trackers, watches, rings, earphones, phones, clothing, etc., may also be utilized within the scope of various embodiments. In this example, a person may wear device 100 on their arm 102 or wrist and view content, which may include health information, on the device's display 106. In many embodiments, display 106 is a touch-sensitive display that allows a person to input or annotate information about their health or status, as described elsewhere herein.

[0019] 1B , device 100 may include various measurement components 152, 154 (also referred to herein as sensors), as shown in a rear view 150 of device 100. More specifically, as shown, device 100 may include one or more internal sensors 152 and / or one or more external sensors 154, which may include any suitable type of sensor that can be used to measure or detect information about a user, such as EDA sensors and / or motion and temperature sensors. Furthermore, in one embodiment, measurement components 152, 154 may include or be associated with an optical measurement subsystem. In this example, the optical measurement subsystem includes at least one optical emitter and at least one optical receiver. The emitters can emit light of one or more wavelengths that may be reflected from the surface of the wearer's skin or may travel below the surface and be diffusely reflected and detected by at least one of the emitters. Such an optical assembly can enable a smartwatch to measure various types of information over the time a person wears the device. In yet other embodiments, external sensor(s) 154 may include EDA sensors that are easily accessible by the user's palm or fingers, allowing the user to easily contact the EDA sensors such that the sensors generate data that device 100 can use to accurately and automatically calculate the user's stress. Thus, the present disclosure is tied to practical applications of accurately and automatically calculating a user's stress through EDA sensor(s) 154.

[0020] FIG. 2 illustrates an exemplary environment 200 in which aspects of various embodiments can be implemented. In this example, a person may have several different devices capable of communicating using at least one wireless communication protocol. In this example, a user may have a smartwatch 202 or fitness tracker that the user desires to be able to communicate with a smartphone 204 and a tablet computer 206. The ability to communicate with multiple devices allows the user to use an application installed on either the smartphone 204 or the tablet computer 206 to obtain information from the smartwatch 202, such as heart rate data captured using sensors on the smartwatch. The user may also desire that the smartwatch 202 be able to communicate with a service provider 208, or other such entity, that can obtain and process data from the smartwatch and provide functionality not otherwise available on the smartwatch or an application installed on the individual device. The smartwatch 202 may communicate with the service provider 208 through at least one network 210, such as the Internet or a cellular network, or may in turn communicate via a wireless connection, such as Bluetooth, to one of the individual devices that may communicate via the at least one network. There may be several other types or reasons for communication in various embodiments.

[0021] In addition to simply being able to communicate, users may also want devices to be able to communicate in some way or using certain aspects. For example, users may want communications between devices to be secure, especially if the data may include personal health data or other such communications. Device or application providers may also need to protect this information, at least in some circumstances. Users may want devices to be able to communicate with each other simultaneously rather than sequentially. This may be especially true when pairing may be required, as users may prefer that each device be paired at most once, or that manual pairing not be required. Users may also want communications to be as standards-based as possible, which is often not the case with various proprietary formats, not just so that little or no manual intervention on the part of the user is required, but also so that the device can communicate with as many other types of devices as possible. Thus, users may want to walk around a room with one device and have such device automatically communicate with other target devices with little or no effort on the part of the user. In various conventional approaches, devices utilize communication technologies such as Wi-Fi to communicate with other devices using wireless local area networking (WLAN). Smaller or lower volume devices, such as many Internet of Things (IoT) devices, instead utilize communication technologies such as Bluetooth®, particularly Bluetooth Low Energy (BLE), which consumes very little power.

[0022] 2 enables data to be captured, processed, and displayed in several different ways. For example, data may be captured using sensors on the smartwatch 202, but due to limited resources on the smartwatch, the data may be transferred to the smartphone 204 or service provider 208 (or cloud resources) for processing, and the results of that processing may then be presented back to the user on another such device associated with the user, such as the smartwatch 202, smartphone 204, or tablet computer 206. In at least some embodiments, the user may also be able to use an interface on any of these devices to provide input, such as health data, that may then be considered when making that decision.

[0023] In at least one embodiment, data determined for a user can be used to determine state information, such as may be related to the user's current stress level or state. At least some of this data can be determined using sensors or components capable of measuring or detecting aspects of the user, while other data can be manually entered by the user or obtained in other ways. In at least one embodiment, a stress determination algorithm can be utilized that takes several different inputs as inputs, which can be obtained manually, automatically, or in other ways. In at least one embodiment, such an algorithm can take various types of factors and use them to generate a stress score. One such stress score can be calculated as shown in approach 300 of FIG. 3. In this example, the stress score is calculated as a weighted sum of different types of factors. In at least one embodiment, these types of factors can include inputs such as sleep characteristics (e.g., restlessness, fragmentation), activity characteristics (e.g., relative AZM, relative step count), and / or cardiac characteristics (e.g., HF / LF HRV, high resting heart rate), and electrodermal activity (EDA), which can be used to measure galvanic skin response. In at least one embodiment, these factors can be normalized and then weights can be determined through testing, machine learning, or other such approaches.

[0024] In at least one embodiment, these factors may consist of at least 12 different metrics. However, it should be understood that different numbers, selections, types, or variations can be used with different algorithms according to various embodiments. A first feature type related to sleep features may include features such as: A sleep score restlessness value can provide a measure of the amount of movement during sleep, which can be normalized for a person over a period of time, such as 30 days. Restless sleep is a known physiological stress marker. A disruption feature can indicate the number of times a person was awake for more than a threshold amount of time (WASO), such as 30 minutes, which can be normalized as an average over a period of time, such as 30 days. Disrupted sleep is also known to be a physiological stress marker. A sleep reservoir level indicates, for example, how well a person slept last week, with more distant dates having less impact on the normalized score at the population level. This metric analyzes a user's sleep from the past week to account for the fact that multiple nights of poor sleep are not necessarily restorative with one night of sleep. Overall sleep duration can also cause poor emotional control, so that situations that may not be stress-inducing after a full night of sleep can become stressful. In at least one embodiment, a set of constants can be determined and / or utilized to calculate the rate at which a user's sleep reservoir level depletes. The sleep reservoir level can represent the accumulated amount of restful sleep a user has had over a recent period, such as the past seven days of sleep. If the user has had somewhat intermittent sleep, very light sleep, or very short sleep, this reservoir level will deplete and approach zero, albeit at different rates. If the user is very well rested and has had at least seven hours of sleep in each of the past seven days, this value may be closer to the maximum normalized value of one (1). Such an approach can map sleep calculations to a normalized sleep reservoir scale using specific constants that can determine the rate at which a user depletes their sleep and how particular sleep periods may accumulate in terms of sleep.In one embodiment, it is determined that the initial sleep period does not count as restful sleep, and only sleep beyond that initial period counts as restful sleep. After this initial period, it can be determined that the user is accumulating sleep. The state or type of sleep after that initial period can then determine the amount or rate of restorative rest.

[0025] The duration of deep sleep and / or REM sleep may indicate the number of minutes of deep sleep and the percentage of REM (rapid eye movement) sleep in the most recent night, normalized using demographic group averages over a period of time, such as the past 30 days. The deep sleep latency feature may indicate the number of minutes after sleep onset before first entering deep sleep, which may be normalized using individual averages over the past 30 days. Longer latency between sleep onset and the first deep sleep period is known to be a physiological stress marker.

[0026] In at least one embodiment, there may be several different activity features. This may include, for example, an Activity Zone Minute (AZM) feature, which includes weekly activity zone fractions normalized using a population level compared to the recommended 150 / week. The feature value may increase when the AZM is higher or lower than the 150 range. In at least some embodiments, these fractions may be determined using sensors on the device, such as motion and heart rate sensors. Because light to moderate exercise acts as a "shield" against stress, too little weekly activity may result in elevated cortisol levels, making a person more susceptible to events perceived as stressors. Because exercise is by definition a stressor, too much weekly activity may result in fatigue. A stressor represents a stimulus or event that causes a state of strain or tension, thus producing a stress response. A stress response, or symptom, represents the physiological and psychological changes the body experiences in response to a stressor in an attempt to maintain homeostasis. Multiple stress responses may be elicited by a single stressor. The psychological stress response describes the relationship between a person and the environment they appraise as taxing or excessive to their resources and endangering their well-being. Another feature may be a step count value, corresponding to the total number of steps taken over a period of time, such as per day. This can be normalized using demographic group averages over a period of time, such as 30 days. Because light to moderate exercise acts as a "shield" against stress, taking too few steps daily may result in elevated cortisol levels, making a person more susceptible to events they perceive as stressors. Because exercise is by definition a stressor, taking too many steps daily may result in fatigue. There may also be other factors indicative of activity, and different types of data may be analyzed to determine different types or amounts of activity.

[0027] In at least one embodiment, various cardiac features may be included in stress determination. One cardiac feature is deep sleep high frequency (HF) versus low frequency (LF) heart rate value (HRV). In at least one embodiment, this captures the sympathovagal balance between sympathetic and parasympathetic activity and can be normalized by demographic group averages over a period of time, such as 30 days. When insufficient deep sleep and REM sleep occur, emotional control becomes more difficult, so situations that may not induce stress after a full night of sleep can become stressful. Heart rate variability (HRV) quantifies the variability of the time between heartbeats. Many different HRV metrics exist, including low frequency (LF) power versus high frequency (HF) power, which quantifies sympathovagal balance, with higher numbers indicating more SNS activity and lower numbers indicating more PNS activity. Because deep sleep is the most restful sleep, this metric only considers LF / HR-HRV during periods of deep sleep, when SNS is highest during the day. Another feature may relate to elevated resting heart rate (HR), which may correspond to the amount and magnitude of resting HR above a threshold, which may be normalized using an individual's average value over a period of time, such as 30 days. An elevated heart rate while resting during the day is a sign of elevated sympathovagal balance, meaning there is too much sympathetic nervous system (SNS) activity and not enough parasympathetic nervous system (PNS) activity. Stress can result in elevated sympathovagal balance, but many other things can also cause elevated heart rate, including anemia, caffeine, alcohol, fever, high or low blood pressure, electrolyte imbalance (possibly due to dehydration), hyperthyroidism, smoking, or medications.

[0028] Sleep heart rate above resting heart rate (RHR) can indicate the percentage of time during sleep that a user's HR is above resting HR, which can be normalized using an absolute metric as a raw percentage. Like elevated resting HR, this is also a measure of sympatho-vagal balance, but quantifies HR during sleep instead of daytime. Many factors can increase this metric, particularly if you consume alcohol before sleep. A fitness fatigue score can be calculated that balances the fatigue effects of exercise and the fitness effects of exercise into a single score, which can be normalized using an individual's minimum / maximum range over a period of time, such as 30-90 days. This score measures a person's long-term fitness level, as measured through heart rate, and the dual contribution of exercise to short-term fatigue. Similar to weekly activity and daily steps, high fatigue levels are, by definition, stressful, requiring rest. Fitness fatigue can treat a person's heart as a linear system. By measuring heart rate over a period of time, a cumulative representation of the body's fatigue, quantified by a fitness fatigue score, can be obtained. When a user experiences a high heart rate event such as exercise, the score has time to drop to reflect the fatiguing effects of this exercise, after which the score has time to rise to reflect the fact that the body is more adapted to exercise, more resilient, and better prepared for future exercise events.

[0029] In at least one embodiment, EDA data can also be considered a stress determinant, as described above. Approaches for capturing or determining EDA data are described in a co-pending application entitled "DETECTION AND RESPONSE TO AROUSAL ACTIVATIONS," incorporated herein by reference in its entirety for all purposes. Sympathetic nervous system activity causes sweating, and EDA measures the amount of conductance across a user's skin to quantify the current amount of SNS activity. Because this metric does not measure PNS, at least in some embodiments, it, unlike other cardiac-related metrics, may not provide a true measure of sympathovagal balance, rather than simply SNS activity. Feature values ​​may relate to EDA activity during meditation and check-in sessions. For example, if a user uses EDA sessions to record a meditation or "check-in" session, their average EDA score across all sessions can then be compared to their baseline value, and features can receive a score of, for example, 0, 1, or 2 points. If the session was not recorded, they may receive 1 point. In one embodiment, a user who did not record an EDA that day may receive 1 point, while a user who did a guided EDA session (regardless of alignment) receives 2 points, and a user who did an unguided EDA session uses the average value of the session compared to the past 30 days of valid EDA sessions. If the session is higher than the average, they receive 0 points. If the session is about the average, the user receives 1 point. If the session is below the average, the user receives 2 points.

[0030] In at least one embodiment, the weighting of EDA in the stress score calculation may vary, as it may depend in part on factors such as the accuracy of the EDA value or the relative importance of that data to an individual user. In at least one embodiment, EDA can serve as a proxy for quantifying the amount of sympathetic nervous system activity. This data may represent the instantaneous occurrence of this activity. Because the sympathetic nervous system can cause minute amounts of sweating throughout a person's body, conductance between the sensor and the user's hand or fingertip increases as sweat levels increase. When greater conductance is detected, this may represent greater sympathetic nervous system activity. In at least one embodiment, at least two different EDA metrics can be monitored. The first metric is a metric of color called skin conductance level, which examines the absolute level over time and whether that value is increasing or decreasing. The second metric represents skin conductance response (SCR), which examines the number of spikes in skin conductance within a sliding window of time, such as a one-minute window. Thus, the SCR can represent the number of spikes per minute at the EDA conductance level. In at least one embodiment, continuous EDA determinations can be made for such purposes, while discrete or periodic EDA signals may not support such granularity of determination.

[0031] In at least one embodiment, an algorithm can utilize at least some of these and / or other such characteristics to generate a stress score representing a user's current, past, or future stress state. A system or service utilizing such a score can provide real-time metrics that can be correlated with physical stress and / or perceived stress. Such systems can provide manual input by the user, such as collecting data related to physical or perceived stress. In at least one embodiment, such systems can obtain the results of a Perceived Stress Scale (PSS) survey that measures a wide range of users' chronic stress. Such systems can also generate daily physiological stress and / or stress capacity metrics. In at least one embodiment, the algorithm can calculate a stress score that represents an "expert-guided" determination of physiological stress that can be inverted to reflect stress capacity and / or resilience. In at least one embodiment, a low stress capacity or resilience score may indicate a high level of stress, while a high resilience score may indicate readiness for the day's cognitive / emotional / physical demands.

[0032] FIG. 4 illustrates an exemplary display or interface that may be provided to a user in accordance with at least one embodiment. In this example, a first interface 400 provides information including a stress score field and an option to obtain additional stress data. A second interface 410 provides a set of stress scores plotted over time, in this case, over a particular week. Such information may help a user identify trends as well as correlate events on different days with different stress levels or scores. As shown, a user may be able to provide feedback on different levels of stress, which may also be plotted by day for comparison. A third interface 420 may provide other information, such as mood, over the week or period. In at least one embodiment, there may be various subscores or components to the stress score, which may relate to reactivity, exertion balance, or sleep patterns or scores. A fourth interface 430 may allow a user to provide feedback on their current mood or state.

[0033] FIG. 5 illustrates additional interfaces that may be provided to a user according to other embodiments. In this example, each interface presents information related to stress resilience rather than a stress score, which may be interpreted as an absolute level of stress by the user. A first interface 500 may present a stress resilience score and the last presented stress state (and the time at which that state was presented). A second interface 510 may be presented to a user who has not yet begun to enter or acquire stress resilience data, such as when at least some data or permission may be required from the user before presentation. A third interface 520 provides a different view of stress resilience over time, including data for individual stress resilience components, as described above. Such interfaces may also allow a user to provide new, additional, or updated feedback that can be used in determining such values ​​for presentation.

[0034] 6 illustrates additional interfaces that can be provided to a user according to yet other embodiments. A first interface page 600 presents another view of stress resilience over time, and in particular, rather than presenting a resilience value, presents a distribution of stress levels or states on various days. A second interface 610 presents information to help the user understand these scores, what goes into the scores, and what different scores represent. A variety of other data and interfaces can also be used according to various embodiments.

[0035] In at least one embodiment, the data can be categorized into three stress score groups: an exertion group, a cardiac group, and a sleep pattern group. In such an embodiment, the exertion group can include data on weekly activity, daily steps, and a fitness fatigue score or exertion balance. The cardiac group can include elevated resting HR, sleep HR over RHR, deep sleep HRV, and potentially EDA. This data can represent the user's nervous system, reactivity, neural stimulation, neural gauges, and stimulation. The sleep pattern group can include data on sleep restlessness, sleep fragmentation, deep sleep latency, deep sleep duration, and REM sleep duration, as well as sleep reservoir level.

[0036] In at least one embodiment, the stress score may have a value ranging from 0 to 100, where a value of 100 may mean that the user's body is showing many signs of stress. Alternatively, a stress resilience score of 100 may mean that the user is showing little to no signs of stress. Other values ​​or metrics may also be used.

[0037] Such interfaces and information may attempt to provide a holistic management tool. Thus, such an approach may analyze both physical and mental stress. An interface may be provided that quickly allows a user to obtain their daily or current stress score, along with other scores, such as a sleep score. Such information may also help a user reflect on their mood and remind the user to record or provide that information. As described above, a user may also have access to additional data, such as a stress details page, where the user can obtain additional information about their current stress state or score and the various components used in its determination. In at least some embodiments, a user may be able to drill down into data components to obtain additional information of interest. In some embodiments, there may be multiple views available, such as if a user wishes to see trends over a day, a week, or a month. As shown in various embodiments, sensors and devices may be able to provide data about physical stress, but for at least certain types of mental stress data, the user may be the best source of mental stress data. The user may be able to record their current mood or perceived stress level or provide other such information. In at least one embodiment, the user may be prompted to enter mood or stress data after an EDA scan to provide improved correlation. Such an approach may help incorporate EDA data into a holistic view of the user's physical and mental health. In some embodiments, the device may provide periodic or continuous EDA measurements, which can be used to dynamically update stress determinations over time.

[0038] In at least one embodiment, the stress score determination algorithm considers various factors that may affect a user's stress level. Weighting of these factors can be determined across users or across different types of users. In at least some embodiments, these weightings can also be tailored for individual users to improve accuracy. For example, a sleep stage algorithm can be used to distinguish periods of sleep that may have a significant impact on a particular user's stress level. Furthermore, examining factors such as HRV of specific sleep states relative to the entire night can provide additional insight. For example, combining deep sleep duration with REM sleep duration can provide valuable insight because these periods are generally more restorative. There can be a significant difference between achieving 8 hours of light sleep, 4 hours of light sleep, and 4 hours of deep and REM sleep. Furthermore, mental stress levels may have a more severe impact on different users than physical stress levels, and both can be taken into account by such an algorithm. Additional benefits can be obtained by examining different types of metrics across different domains of exercise or exertion, sleep, and proxies of autonomic nervous system activity using both heart rate / heart rate variability and EDA or other such data. A useful benefit to the user may also be to compare physical stress levels with perceived stress levels so that the user can better understand stress.

[0039] In at least some embodiments, stress determination may be a linear or nonlinear combination of weighted and normalized factors, which may be normalized based on individual, demographic, or other such groupings. In some embodiments, some factors may need to be inverted if some indicate higher stress levels while others represent lower stress levels. For example, in one embodiment, inverted factors include deep sleep duration and REM sleep duration, sleep reservoir level, and fitness fatigue score. Some factors may utilize a z-score-based approach, such as where a z-score of 1 represents one standard deviation above the mean. As mentioned above, factors may also be normalized across different time periods and different groupings, such as per user or demographic group. In some embodiments, a ranging function may be applied after z-scoring to place all values ​​into a determined range, such as between 0 and 1. In some embodiments, this may involve linear adjustment and linear interpolation.

[0040] In at least one embodiment, stress scores can be determined such that a single score, such as 80 on a scale of 100, represents the same stress level, or stress resilience, for all users. In other embodiments, values ​​can mean different things to different users, such as, for example, a first user may have an average stress level of 50, while another user may have an average stress level of 80, and thus a value of 70 can mean different things to those two users.

[0041] Additionally, different factors may be considered for different algorithms or different users. For example, a highly active user may utilize a different algorithm than a less active user, while different algorithms may also be utilized for different devices where different types of inputs are available or where the user has the option to disable certain sensors or limit the type of data collected. In one embodiment, at least three categories of factors may be collected, including sleep features, activity features, and cardiac features (or "reactive" features). In some embodiments, EDA or similar data may also be utilized. In some embodiments, factors within these categories that may be utilized include restlessness, fragmentation, sleep reservoir level, deep sleep duration / REM sleep duration, deep sleep latency, active zone minutes or activity level, steps or movement, deep sleep HRV, elevated HR at rest, sleep HR above RHR, and fitness fatigue score. Other factors may include various movement or activity metrics and exertion balance metrics. If available, additional factors may include blood pressure, blood composition, respiratory rate, body temperature, metabolic data, blood glucose level, weight or composition, mental state, perceived stress, depression, activity type, or current movement pattern (e.g., walking). Other factors may include nightmares, voice prosody / tone / pressure, blood cortisol / epinephrine / norepinephrine levels, low-density lipoprotein (LDL) levels, BMI x exercise, gender-specific values, or mood log data.

[0042] Referring now to FIG. 7 , a flow diagram of one embodiment of an exemplary process 700 for determining an available user stress score is shown. It should be understood that, for processes described herein, there may be additional, fewer, or alternative steps performed in a similar or alternative order, or at least partially in parallel, within various embodiments, unless otherwise noted. In this embodiment, as shown at (702), process 700 includes activating a stress determination for a user associated with a wearable device. This activation may come from the user, the wearable device, or an associated device, among other such sources. As part of the determination, as shown at (704), process 700 includes receiving data regarding the user's state, which may be related to heart rate, sleep state, EDA, activity, or other such information described and suggested herein, from one or more sensors or components on the wearable device. As shown at (706), process 700 includes obtaining additional user-provided data, which may be related to the user's perceived state data. Using at least a portion of this data and other relevant data, process 700 includes calculating a stress score (or stress resilience score) for the user, as shown at (708). This stress score or stress value may relate to various stress metrics, such as the user's current stress level or stress resilience level. In this example, process 700 includes taking at least one action on the wearable device (or associated device) based at least in part on this calculated score, as shown at (710). These actions may include any of a variety of different actions, which may relate to generating an interface, presenting data, providing notifications, updating or modifying the operation of the wearable device, or taking other such actions.

[0043] FIG. 8 illustrates another exemplary process 800 for monitoring a user's stress that can be utilized in accordance with various embodiments. In this example, as shown at (802), process 800 includes activating stress monitoring for a user associated with a wearable device. An initial stress determination can be made as described with respect to FIG. 7. During monitoring, as shown at (804), process 800 includes receiving new or updated sensor data and / or user-provided data. As shown at (806), process 800 includes calculating an updated stress score based at least in part on this new or updated data. As shown at (808), process 800 includes analyzing changes in the stress score, such as with respect to a previous value determination. As shown at (810), process 800 includes determining whether the change is an actionable change, such as a change that exceeds a change threshold, falls outside an acceptable range, or meets an action threshold. If not, then process 800 can continue receiving new and updated data. If the change is determined to be an actionable change, then at least one action can be taken as shown in response to the change (812), which may include those described with respect to the initial stress score calculation above.

[0044] FIG. 9 illustrates components of an exemplary system 900 that can be utilized in accordance with various embodiments. In this example, system 900 includes at least one processor 902, such as a central processing unit (CPU) or graphics processing unit (GPU), for executing instructions that can be stored in a memory device 904, such as flash memory or DRAM, among other options. As would be apparent to one skilled in the art, a device can include many types of memory, data storage, or computer-readable media, such as data storage for program instructions for execution by the processor. The same or separate storage can be used for images or data, removable memory can be made available for sharing information with other devices, and any number of communication approaches can be utilized for sharing with other devices. Additionally, as illustrated, system 900 includes any suitable display 906, such as a touchscreen, organic light-emitting diode (OLED), or liquid crystal display (LCD). However, the device could communicate information through other means, such as via audio speakers, a projector, or the like.

[0045] A tracker or similar device includes at least one motion-detecting sensor, which may include at least one input / output (I / O) element 910 of the device, as shown. Such sensors can determine and / or detect the orientation and / or movement of the system 900. Such elements may include, for example, an accelerometer, an inertial sensor, an altimeter, or a gyroscope operable to detect device movement (e.g., rotational movement, angular displacement, tilt, position, orientation, movement along a nonlinear path, etc.). Orientation-determining elements may also include an electronic or digital compass capable of indicating a direction (e.g., north or south) in which the device is determined to be pointing (e.g., relative to a major axis or other such orientation). The I / O element 910 may also be used to determine the location of the device (or a user of the device). Such positioning elements may include a GPS or similar position-determining element(s) operable to determine the relative coordinates of the device's location. Positioning elements may include wireless access points, base stations, etc., which broadcast location information or enable signal triangulation to determine the device's location. Other positioning elements may include QR codes, bar codes, RFID tags, NFC tags, etc. that enable the device to detect and receive location information or identifiers that allow the device to obtain location information (e.g., by mapping the identifier to a corresponding location). Various embodiments may include one or more such elements in any suitable combination. I / O elements 910 may also include one or more biometric sensors, light sensors, barometric pressure sensors (e.g., altimeters, etc.), etc.

[0046] As described above, some embodiments use a factor(s) to track the user's location and / or movement. Upon determining the device's initial location (e.g., using GPS), some embodiment devices may track the device's location by using a factor(s), or in some examples, by using the orientation determination factor(s) described above, or a combination thereof. As should be understood, the algorithm or mechanism used to determine the location and / or orientation may depend, at least in part, on the selection of factors available to the device. The exemplary device also includes one or more wireless components 912 operable to communicate with one or more electronic devices within communication range of a particular wireless channel. The wireless channel may be any suitable channel used to allow devices to communicate wirelessly, such as a Bluetooth, cellular, NFC, or Wi-Fi channel. It should be understood that the system 900 may have one or more conventional wired communication connections known in the art. The system 900 also includes one or more power components 908, such as a battery operable to be charged via a conventional plug-in approach or by other approaches, such as capacitive charging via proximity to a power mat or other such device. In some embodiments, system 900 can include at least one additional input / output device 910 capable of receiving conventional input from a user. This conventional input can include, for example, push buttons, a touchpad, a touchscreen, a wheel, a joystick, a keyboard, a mouse, a keypad, or any other such device or element by which a user can enter commands into the device. These input / output devices can also be connected by wireless infrared or Bluetooth or other links in some embodiments. Some devices can also include a microphone or other audio capture element to accept voice or other audio commands.For example, a device may not include any buttons at all, but may be controlled solely by a combination of visual and voice commands, allowing a user to control the device without having to make contact with it.

[0047] As mentioned above, many embodiments include at least some combination of one or more emitters 916 and one or more detectors 918 for measuring data of one or more metrics of a human body, such as a person wearing a tracker device. In some embodiments, this may include at least one imaging element, such as one or more cameras, capable of capturing images of the surrounding environment and imaging a user, people, or objects in the device's vicinity. The image capture element may include any suitable technology, such as a CCD image capture element having sufficient resolution, focusing range, and viewing area to capture images of a user as the user operates the device. Methods for capturing images using a camera element with a computing device are well known in the art and will not be described in detail herein. It should be understood that image capture can be performed using a single image, multiple images, periodic imaging, continuous image capture, image streaming, etc. Additionally, the device may include the ability to start and / or stop image capture, for example, upon receiving a command from a user, an application, or another device.

[0048] The emitter 916 and detector 918 of FIG. 9 may also be used to obtain optical photoplethysmogram (PPG) measurements, in one example. Some PPG techniques rely on detecting light at a single spatial location or adding signals obtained from two or more spatial locations. Both of these approaches result in a single spatial measurement from which a heart rate (HR) estimate (or other physiological metric) can be determined. In some embodiments, the PPG device uses a single light source coupled to a single detector (i.e., a single optical path). Alternatively, the PPG device may use multiple light sources coupled to a single detector or multiple detectors (i.e., two or more optical paths). In other embodiments, the PPG device uses multiple detectors coupled to a single light source or multiple light sources (i.e., two or more optical paths). In some cases, the light source(s) may be configured to emit one or more of green light, red light, and / or infrared light. For example, the PPG device may use a single light source and two or more photodetectors, each configured to detect a particular wavelength or wavelength range. In some cases, each detector is configured to detect a different wavelength or wavelength range from the others. In other cases, two or more detectors are configured to detect the same wavelength or wavelength range. In still other cases, one or more detectors are configured to detect a specific wavelength or wavelength range that is different from one or more other detectors. In embodiments using multiple optical paths, the PPG device may determine an average of the signals resulting from the multiple optical paths before determining an HR estimate or other physiological metric. Such PPG devices may not be able to resolve or individually utilize the individual signals resulting from the multiple optical paths.

[0049] 9 , system 900 may further include one or more processors 902 coupled to a memory device 904, a display 906, a bus, one or more input / output (I / O) elements 910, and a wireless network component 912, among other such options. However, in certain embodiments, the display and / or I / O device may be omitted. In one embodiment, system 900 may be part of a wristband, and display 906 is configured so that the display faces away from the outside of the user's wrist when the user wears the wristband. In other embodiments, the display may be omitted, and data detected by system 900 may be transmitted via at least one network 920 to a host computer 922 using a wireless network interface via near field communication (NFC), Bluetooth, Wi-Fi, or other suitable wireless communication protocol for analysis, display, reporting, or other use.

[0050] The device 904 may include RAM, ROM, FLASH memory, or other non-transitory digital data storage and may include a control program including sequences of instructions that, when loaded from memory and executed by the processor 902, cause the processor 902 to perform the functions described herein. The emitter 916 and the detector 918 may be coupled directly or indirectly to a bus using driver circuits that enable the processor 902 to drive the emitter 916 and obtain signals from the detector 918. The host computer 922 may communicate with the wireless network component 912 via one or more networks 920, which may include one or more local area networks, wide area networks, and / or internetworks using either terrestrial or satellite links. In some embodiments, the host computer 922 executes control programs and / or application programs configured to perform some of the functions described herein.

[0051] In some embodiments, each emitter 916 can be controlled individually, or each detector 918 can be read out individually when multiple detectors are used; in such embodiments, PPG sensor data along several different optical paths can be collected. A control program can utilize the collected data to provide more accurate estimates of HR and / or other physiological metrics. In related aspects, the processor 902 and other component(s) of the PPG device can be implemented as a system-on-chip (SoC), which can include one or more central processing unit (CPU) cores that use one or more reduced instruction set computing (RISC) instruction sets and / or other software and hardware to support the PPG device.

[0052] In various embodiments, the emitter 916 (or light source) may include an electronic semiconductor light source such as an LED, or may generate light using either a filament, phosphor, or laser. In some implementations, each of the light sources emits light having the same center wavelength or within the same wavelength range. In other cases, at least one light source may emit light having a different center wavelength than another of the light sources. The center wavelength of the light emitted by the light sources may be in the range of 495 nm to 570 nm. For example, a particular green light source may emit light having a center wavelength of 528 nm. In other embodiments, one or more of the light sources may emit red light (e.g., a center wavelength of 660 nm) or IR light (e.g., a center wavelength of 940 nm). In some embodiments, one or more of the light sources may emit light having a peak wavelength typically in the range of 650 nm to 940 nm. For example, in various embodiments, a particular red light source may emit light with a peak wavelength of 660 nm, and one or more infrared light sources may emit light with a peak wavelength ranging from 750 nm to 1700 nm. By way of example and not limitation, a particular infrared light source may emit light with a peak wavelength of 730 nm, 760 nm, 850 nm, 870 nm, or 940 nm. Some commercially available light sources, such as LEDs, may provide output at approximately 20 nm intervals with a center wavelength tolerance of + / - 10 nm from the manufacturer's specified wavelength, so one possible range of useful peak wavelengths for the light sources is 650 nm to 950 nm. A green light source may be configured to emit light having a wavelength ranging from 495 nm to 570 nm. For example, a particular green light source may emit light having a wavelength of 528 nm. The green light source, like the pair of red and infrared light sources, may be positioned equidistant from the photodetector. For example, if the distance between the photodetector and the center of the first red light source is 2 mm, then the distance between the photodetector and the green light source may also be 2 mm (e.g., equidistant). In some other cases, the distance between the photodetector and one or more light sources is not equidistant. Furthermore, in some embodiments, one or more of the light sources may include a single LED package that emits multiple wavelengths, such as green, red, and infrared wavelengths, at the same or substantially the same (e.g., less than 1 mm difference) location relative to the detectors.Such an LED may include multiple semiconductor elements co-located using a single die within a single package.

[0053] The spacing between the light sources may be measured from the side of the light source or the center of the light source. For example, the light sources may be configured so that the center of each light source is a first distance from the edge of the nearest one of the photodetectors. In some embodiments, the first distance may be 2 mm. In some implementations, each light source is located a second distance from the nearest one of the light sources, and each photodetector is located a third distance from the nearest one of the photodetectors. In some embodiments, the second and third distances are the same as the first distance. In other embodiments, each of the second and third distances is different from the first distance. The second distance may be the same as or different from the third distance. The size of a particular spacing may depend on several factors, and the present disclosure does not limit embodiments to any particular spacing. For example, spacings ranging from 1 mm (or less) to 10 mm will work in various embodiments.

[0054] In some embodiments, independent control of all light sources is provided. In other embodiments, several light sources are controlled together as a group or bank. An advantage of independent control of each light source, or independent readout from each of multiple detectors (e.g., obtaining independent signals based on the same or different wavelengths of light from each of multiple detectors), is that a multiple light path approach may be used to improve estimation of HR and / or other physiological metrics, as further described herein.

[0055] The photodetector may include one or more sensors adapted to detect wavelengths of light emitted from the light source. A particular light source coupled with a particular detector may include a sensor, such as a PPG sensor. Because the first and second PPG sensors may share components, such as the same light source and / or detector, or may have different components, the term "PPG sensor" may refer to any such arrangement in addition to having its ordinary meaning. However, actual embodiments may use multiple components in implementing a PPG sensor. The term "PPG device" may refer to a device including a PPG sensor in addition to having its ordinary meaning. In one embodiment, the photodetector may include one or more detectors for detecting light of each different wavelength used by the light source. For example, the first detector may be configured to detect light having a wavelength of 560 nm, the second detector may be configured to detect light having a wavelength of 940 nm, and the third detector may be configured to detect light having a wavelength of 528 nm. Examples include photodiodes fabricated from semiconductor materials and having optical filters that accept only light of a specific wavelength or range of wavelengths. The photodetector may include any of a photodiode, a phototransistor, a charge-coupled device (CCD), a thermopile detector, a microbolometer, or a complementary metal-oxide semiconductor (CMOS) sensor. The photodetector may include multiple detector elements, as further described herein. One or more of the detectors may include a bandpass filter circuit.

[0056] In other embodiments, the detector may include one or more detectors configured to detect multiple wavelengths of light. For example, a single detector may be configured to tune to different frequencies based on data received from an electronic digital microprocessor coupled to the detector. Alternatively, a single detector may include multiple active regions, each sensitive to a given wavelength range. In one embodiment, a single detector is configured to detect light having wavelengths in the red and IR frequencies, and a second detector is configured to detect light having wavelengths in the green frequency range. Furthermore, each of the light sources may use one or more of the different wavelengths of light described above.

[0057] In one embodiment, the photodetector can be mounted within a housing with one or more filters configured to filter out wavelengths of light other than those emitted by the light source. For example, a portion of the housing can be covered with a filter that filters out ambient light other than those emitted by the light source. For example, a signal from the light source can be received by the photodetector through an ambient light filter that filters out ambient light sources that produce ambient light with wavelengths different from those detected by the detector. While LEDs and photodiodes are used as examples of light sources and photodetectors, respectively, the techniques described herein can be extended to other types of light sources, such as edge-emitting lasers, surface-emitting lasers, and LED-excited phosphors that produce broadband light. The techniques described herein can be extended to other combinations of light sources and detectors. For example, a PPG device may include (i) a single or multiple LEDs and a multi-element photodetector (e.g., a camera sensor), (ii) an LED array and a single or multiple photodiodes, (iii) a broadband LED-excited phosphor and detector array with a wavelength-selective filter on each detector, (iv) a spatial light modulator (SLM) (e.g., a digital micromirror device [DMD] or a liquid crystal on silicon [LCoS] device) and a single or multiple LEDs, other combinations thereof, or other configurations of light sources and detectors.

[0058] Certain flow charts are presented herein to illustrate various methods that may be performed by example embodiments. The flow charts illustrate example algorithms that may be programmed using any suitable programming environment or language to create machine code executable by a CPU or microcontroller of a PPG device. In other words, the flow charts, together with the description provided herein, are algorithmic disclosures of aspects of the claimed subject matter, presented at the same level of detail typically used to convey the subject matter among those skilled in the art to which this disclosure pertains. Various embodiments may be coded using assembly, C, Objective-C, C++, JAVA, or other human-readable language, and then compiled, assembled, or otherwise translated into machine code that can be loaded into a ROM, EPROM, or other recordable memory of an activity monitoring device that is coupled to a CPU or microcontroller and then executed by the CPU or microcontroller.

[0059] In one embodiment, the signals obtained from the multiple optical paths may be processed to filter or reject signal components associated with user motion using a computer program to identify motion components of the signal and remove the identified motion components from the decoded signal, leaving the cardiac components as the remaining or final signal.

[0060] In one embodiment, signals may be collected during various daytime or nighttime activities, such as those associated with periods of walking, exercise, or sleep. Other on-device sensors, including accelerometers, gyroscopes, or altimeters, may be used to classify or detect activities or human postures as a basis for developing appropriate filters. These filters or signal processing methods may be used to target and reduce variability in PPG data with multiple optical paths. By way of example and not limitation, accelerometer data may be used to develop signal processing methods to filter data, examine specific postures, and remove other body orientations. This may help reduce noise in the data and obtain a better estimate of the corresponding physiological variables for the corresponding optical paths.

[0061] In various embodiments, the approaches described herein may be performed by firmware running on a monitoring device or tracker device, or by one or more secondary devices, such as a mobile device, server, or host computer, paired to the monitoring device. For example, the monitoring device may perform operations related to generating signals that are uploaded to or otherwise communicated with a server, which performs operations to remove the motion component and create final estimates for HR, SpO2, and / or other physiological metrics. Alternatively, the monitoring device may perform operations related to generating monitoring signals and removing the motion component to generate final estimates for HR, SpO2, and / or other physiological metrics local to the monitoring device. In this case, the final estimates may be uploaded to or otherwise communicated with a server, such as a host computer, which performs other operations using the values.

[0062] Exemplary monitoring or tracker devices can collect one or more types of physiological and / or environmental data from one or more sensor(s) and / or external devices and communicate or relay such information to another device (e.g., a host computer or other server) so that the collected data can be viewed, for example, using a web browser or network-based application. For example, while worn by a user, the tracker device may perform biometric monitoring by calculating and storing the user's step count using one or more sensor(s). The tracker device may transmit data representing the user's step count to a web service (e.g., www.fitbit.com), a computer, a mobile phone, and / or an account on a health station, where the data can be stored, processed, and / or visualized by the user. The tracker device may measure or calculate other physiological metric(s) in addition to or instead of the user's step count. Such physiological metric(s) may include, but are not limited to, energy expenditure such as calories burned, number of stairs climbed, HR, heart rate waveform, HR variability, HR recovery, respiration, SpO2, blood volume, blood glucose, skin hydration and skin pigmentation level, location and / or direction (e.g., via GPS, Global Navigation Satellite System (GLONASS), or similar systems), elevation, walking speed and / or distance traveled, swimming lap count, detected swimming stroke type and count, cycling distance and / or speed, blood glucose, skin conductance, skin temperature and / or body temperature, muscle condition measured by electromyography, brain activity measured by electroencephalography, weight, body fat, caloric intake, nutrient intake from food, medication intake, sleep period (e.g., time of day, sleep phase, sleep quality and / or duration), pH level, hydration level, respiratory rate, and / or other physiological metric.

[0063] An exemplary tracker or monitoring device may also measure or calculate (e.g., with one or more environmental sensor(s)) metrics related to the environment around the user, such as, for example, barometric pressure, weather conditions (e.g., temperature, humidity, pollen count, air quality, precipitation / snow conditions, wind speed), light exposure (e.g., ambient light, ultraviolet (UV) light exposure, time and / or duration spent in darkness), noise exposure, radiation exposure, and / or magnetic fields. Additionally, the tracker device (and / or host computer and / or other server) may collect data from one or more sensors of the device and calculate metrics derived from such data. For example, the tracker device may calculate a user's stress or relaxation level based on a combination of HR variability, skin conductance, noise pollution, and / or sleep quality. In another example, the tracker device may determine the effectiveness of a medical intervention, such as medication, based on a combination of data related to medication intake, sleep, and / or activity. In yet other examples, the tracker device may determine the effectiveness of allergy medication based on a combination of data related to pollen levels, medication intake, sleep, and / or activity. These examples are provided for illustrative purposes only and are not intended to be limiting or exhaustive.

[0064] An exemplary monitoring device may include a computer-readable storage medium reader, a communication device (e.g., a modem, a network card (wireless or wired), and an infrared communication device), and working memory, as described above. The computer-readable storage medium reader may be configured to interface with or receive computer-readable storage media, which represent remote, local, fixed, and / or removable storage devices and storage media for containing, storing, transmitting, and retrieving, temporarily and / or more permanently, computer-readable information. Monitoring systems and various devices also typically include several software applications, modules, services, or other elements located within at least one working memory device, including an operating system and application programs such as a client application or web browser. It should be recognized that alternative embodiments may have numerous variations from those described above. For example, specialized hardware may also be used, and / or particular elements may be implemented in hardware, software (including portable software such as applets), or both. Additionally, connections to other computing devices, such as network input / output devices, may be used.

[0065] Storage media and other non-transitory computer-readable media embodying code or portions of code can include any suitable media known or used in the art, such as volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data, including, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and that can be accessed by a system device. Based on the disclosure and teachings provided herein, one skilled in the art will appreciate other ways and / or methods to implement the various embodiments.

[0066] Referring now to FIG. 10 , a flow diagram of a computer-implemented method 1000 for determining a user's fitness fatigue score for the current day (e.g., today) is provided in accordance with an embodiment of the present disclosure. Method 1000 may be implemented, for example, by system 900 described above with reference to FIG. 9 . More specifically, one or more steps of method 1000 may be performed by processor 902 ( FIG. 9 ) on a wearable computing device (e.g., smartwatch 104 or 202). Alternatively or additionally, one or more steps of method 1000 may be performed by a computing device that is remote to the smartwatch (e.g., host computer 922 of FIG. 9 ). FIG. 10 depicts steps performed in a particular order for purposes of illustration and explanation. Those skilled in the art, using the disclosure provided herein, will understand that various steps of method 1000 may be adapted, modified, rearranged, performed simultaneously, or modified in various ways without departing from the scope of the present disclosure.

[0067] At (1002), the method 1000 may include obtaining first data of a user over a first period of time. The first data may include a plurality of heart rate measurements of the user over the first period of time. In some embodiments, the first period of time may include 14 days (e.g., 2 weeks) immediately preceding the current day for which the fitness fatigue score is being determined.

[0068] At (1004), method 1000 may include obtaining second data of the user over a second time period shorter in duration than the first time period. The second data may include one or more sleep metrics for a plurality of different sleep events of the user over the second time period. For example, in some embodiments, the one or more sleep metrics may include the duration of each of the sleep events and the time at which each of the sleep events occurred. In some embodiments, the second time period may include the seven days (e.g., one week) immediately preceding the current day for which the fitness fatigue score is being determined.

[0069] At (1006), the method 1000 may include obtaining third data for the user over a third time period that is longer in duration than the first time period. The third data may include heart rate variability data for the user over the third time period. In some embodiments, the third time period may include the 30 days (e.g., one month) immediately preceding the current day for which the fitness fatigue score is being determined.

[0070] At 1008, the method 1000 may include determining a fitness fatigue score for the user for the current day based at least in part on the first data obtained at 1002, the second data obtained at 1004, and the third data obtained at 1006. In some embodiments, the fitness fatigue score may include a numeric value ranging from 0 to 100.

[0071] At 1010, method 1000 may include causing a display screen of the electronic device to display the fitness fatigue score determined at 1008. For example, in some embodiments, the fitness fatigue score may be displayed on a display screen of a wearable device worn by a user (e.g., smartwatch 104 of FIG. 1A and smartwatch 202 of FIG. 2). Alternatively or additionally, the fitness fatigue score may be displayed on a display screen of a mobile computing device communicatively coupled to the wearable computing device (e.g., smartphone 204 or tablet 206 of FIG. 2).

[0072] At 1012, method 1000 may include determining a recommendation for exercise for the current day based at least in part on the fitness fatigue score determined at 1010 for the current day. For example, in some embodiments, the recommendation may vary depending on the fitness fatigue score. If the fitness fatigue score determined at 1008 is less than a first threshold (e.g., about 30), the recommendation may include a planned exercise for the current day (e.g., rest). Alternatively, if the fitness fatigue score determined at 1008 is greater than the first threshold and less than a second threshold (e.g., about 65), the recommendation may include a first exercise activity (e.g., low heart rate exercise). Furthermore, the recommendation may include a second exercise activity that is more intense than the first exercise activity (e.g., high-intensity aerobic exercise) if the fitness fatigue score determined at 1008 is greater than a second threshold.

[0073] Referring now to FIG. 11 , a flow diagram of a method 1100 for determining a fitness fatigue score is provided in accordance with some embodiments of the present disclosure. Method 1100 can be implemented, for example, by system 900 described above with reference to FIG. 9 . More specifically, one or more steps of method 1000 can be performed by processor 902 ( FIG. 9 ) on a wearable computing device (e.g., smartwatch 104 or 202). Alternatively or additionally, one or more steps of method 1000 can be performed by a computing device that is remote to the smartwatch (e.g., host computer 922 of FIG. 9 ). FIG. 11 depicts steps performed in a particular order for purposes of illustration and explanation. Those skilled in the art, using the disclosure provided herein, will understand that various steps of method 1100 can be adapted, modified, rearranged, performed simultaneously, or modified in various ways without departing from the scope of the present disclosure.

[0074] At 1102, method 1100 may include determining a first sub-score (e.g., an H-score) based at least in part on the first data obtained at 1002 of method 1000 shown in FIG. 10 . For example, the first sub-score may be determined at least in part based on a plurality of heart rate measurements taken by one or more biometric sensors of a wearable computing device worn by the user over a first period of time (e.g., approximately 14 days). In some embodiments, the first sub-score may be determined at least in part based on the amount of time that heart rate measurements collected for the user over the first period of time were above a threshold indicating that the user is stressed (e.g., due to exercise). For example, the number of minutes that the user's heart rate was above the threshold may be determined, and the first sub-score may then be determined therefrom. More specifically, if the heart rate data was above a threshold amount for a threshold time yesterday, this may indicate that the user engaged in strenuous physical activity (e.g., running, swimming, etc.) yesterday and may be fatigued by that physical activity. It should be appreciated that the threshold heart rate may be specific to the user based at least in part on the user's resting heart rate and the user's maximum heart rate, which is a function of the user's age.

[0075] At 1104, method 1100 may include determining a second sub-score (e.g., an S-score) based at least in part on the second data acquired at 1004 of method 1000 shown in FIG. 10 . For example, the second sub-score may be determined based at least in part on one or more sleep metrics for each of the user's multiple sleep events that occurred during a second period (e.g., approximately seven days). In some embodiments, the one or more sleep metrics may include the duration of each of the multiple sleep events. Alternatively or additionally, the one or more sleep metrics may include the time each of the sleep events started and ended. For example, in some embodiments, the second sub-score may be high if the user sleeps at least a threshold number of hours each night (e.g., approximately seven hours). Conversely, the second sub-score may be low if the user sleeps less than the threshold amount each night.

[0076] In some implementations, the second subscore may be a function of the time the user spends in one or more sleep stages for one or more of the plurality of sleep events occurring over a second period (e.g., seven days). For example, the second subscore may be higher when the user spends a threshold amount of time in a restorative stage of sleep (e.g., deep sleep or rapid eye movement) for one or more of the sleep events. It should be understood that the threshold amount of time required in a restorative stage of sleep may be a function of the user's age.

[0077] In some implementations, the second subscore may be a function of the time of day for one or more of the sleep events during the second period (e.g., seven days). For example, if the second data indicates that the user took naps during the day and consequently slept less at night, the second subscore may be lower than if the user did not take naps and slept longer each night.

[0078] At (1106), method 1100 may include determining a third sub-score (e.g., a T-score) based at least in part on the third data obtained at (1006) of method 1000 shown in Figure 10. Details of this step are described in more detail with reference to Figure 13.

[0079] At (1108), the method 1100 may include determining a fitness fatigue score based at least in part on the first subscore (e.g., an H-score), the second subscore (e.g., an S-score), and the third subscore (e.g., a T-score). In some embodiments, the first subscore, the second subscore, and the third subscore may each comprise a numerical value in the range of 0 to 100.

[0080] In some embodiments, the first sub-score determined in (1102), the second sub-score determined in (1104), and the third sub-score determined in (1106) may each be weighted differently. For example, in some embodiments, the first sub-score (e.g., H-score) may be weighted more heavily than the second sub-score (e.g., S-score) and the third sub-score (T-score). For example, in some embodiments, the first sub-score may account for half of the fitness fatigue score. Further, in some embodiments, the fitness fatigue score may be the first sub-score. For example, the fitness fatigue score may be the first sub-score if the first sub-score is below a threshold value (e.g., about 30). In such implementations, it should be appreciated that if the first sub-score is determined to be below the threshold value, the second sub-score and the third sub-score become meaningless.

[0081] Referring now to Figure 12, a flow diagram of a method 1200 for determining a first sub-score (e.g., H-score) of a fitness fatigue score in accordance with an embodiment of the present disclosure is provided. Method 1200 may be implemented, for example, by system 900 described above with reference to Figure 9. Figure 12 shows steps performed in a particular order for purposes of illustration and explanation. Those skilled in the art, using the disclosure provided herein, will understand that various steps of method 1200 may be adapted, modified, rearranged, performed simultaneously, or modified in various ways without departing from the scope of the present disclosure.

[0082] At (1202), the method 1200 may include determining a resting heart rate of the user based at least in part on a plurality of heart rate measurements included in first data obtained over a first period of time.

[0083] At 1204, method 1200 may include determining a maximum heart rate for the user based at least in part on the user's age. For example, in some embodiments, the user's maximum heart rate may be determined by subtracting the user's age from 220 beats per minute. For example, if the user is 40 years old, the user's maximum heart rate may be 180 beats per minute.

[0084] At (1206), method 1200 may include determining a reserve value for each of a plurality of heart rate measurements included in the first data acquired over the first time period. The reserve value may be used to distinguish heart rate measurements taken when the user is stationary (e.g., lying down, sitting, etc.) from heart rate measurements taken when the user is engaged in physical activity (e.g., running, walking, cycling, yoga, etc.). For example, in some embodiments, the heart rate reserve value may be determined based at least in part on the user's resting heart rate determined at (1202), the user's maximum heart rate determined at (1204), and the user's instantaneous heart rate (i.e., one of the plurality of heart rate measurements). In some embodiments, the reserve value may be a numeric value ranging from 0 to 1.

[0085] At 1208, method 1200 may determine, based at least in part on the preliminary value determined at 1206, that a subset of the plurality of heart rate measurements is associated with the physical activity. For example, in some embodiments, heart rate measurements having a preliminary value that is less than a threshold (e.g., about 0.4) may be disregarded, while the subset of heart rate measurements having a preliminary value equal to or greater than the threshold may be used to determine the first sub-score. In this manner, the preliminary value may reduce the amount of data (e.g., heart rate measurements) that must be considered to determine the first sub-score indicative of the user's fatigue due to the physical activity over the first period of time.

[0086] At (1210), method 1200 may include determining a first sub-score based at least in part on a subset of the heart rate measurements included in the first data. For example, in some embodiments, the duration for which the user's heart rate reserve has been above a threshold may be determined. Additionally, in some embodiments, the amount of time that has elapsed since the user's heart rate reserve has been above the threshold may be determined. In some embodiments, the first sub-score may be determined based at least in part on one or both of these parameters (e.g., the duration for which the heart rate reserve has been above the threshold, the duration of time since the user's heart rate reserve last exceeded the threshold). Alternatively or additionally, the first sub-score, in some embodiments, may include a numeric value between 0 and 100 to indicate how fatigued the user is from physical activity occurring over the first period of time.

[0087] Referring now to FIG. 13 , a flow diagram of a method 1300 for determining a third sub-score (e.g., a T-score) of a fitness fatigue score is provided in accordance with an embodiment of the present disclosure. Method 1300 can be implemented, for example, by system 900 described above with reference to FIG. 9 . More specifically, one or more steps of method 1000 can be performed by processor 902 ( FIG. 9 ) on a wearable computing device (e.g., smartwatch 104 or 202). Alternatively or additionally, one or more steps of method 1000 can be performed by a computing device that is remote to the smartwatch (e.g., host computer 922 of FIG. 9 ). FIG. 13 depicts steps performed in a particular order for purposes of illustration and explanation. Those skilled in the art, using the disclosure provided herein, will understand that various steps of method 1300 can be adapted, modified, rearranged, performed simultaneously, or modified in various ways without departing from the scope of the present disclosure.

[0088] At 1302, method 1300 may include determining a root mean square of successive differences (RMSSD) of a heart rate variability (HRV) measurement of the user for each of a plurality of sleep events occurring over a third time period. It should be appreciated that the RMSSD of the HRV measurements may be determined from biometric data (e.g., a PPG signal) obtained from one or more biometric sensors (e.g., a PPG sensor) of the wearable computing device.

[0089] At (1304), the method 1300 may include comparing the RMSSD of the user's HRV during the user's most recent sleep event during the third time period to the RMSSD of the HRV of at least one previous sleep event that occurred during the third time period.

[0090] At 1306, method 1300 may include determining a third sub-score based at least in part on the comparison that occurs at 1304. In some embodiments, the third sub-score may be 0 when the RMSSD of the user's HRV during the user's most recent sleep event is lower than the RMSSD of the user's HRV during one of the previous sleep events that occurred during the third time period. Conversely, the third sub-score may be 100 when the RMSSD of the user's HRV during the user's most recent sleep event is higher than the RMSSD of the user's HRV during one of the previous sleep events that occurred during the third time period.

[0091] 14 , a fitness fatigue score (e.g., a daily readiness score) may be displayed on a display screen of a wearable computing device (e.g., smart watch 202 shown in FIG. 2 ). As shown, the fitness fatigue score may be a single numeric value. For example, a fitness fatigue score of 98 for the day may indicate that the user is ready to engage in physical activity, such as a high-intensity workout. If the fitness fatigue score for the day were lower (e.g., about 50 or about 20), the recommendation generated based on the fitness fatigue score would be different. For example, the recommendation might be for the user to engage in a low-intensity workout or, alternatively, to refrain from physical activity for the day.

[0092] 15-17, various screens of a mobile application executing on a mobile computing device (e.g., smartphone 204 shown in FIG. 2) are provided in accordance with some embodiments of the present disclosure. As shown, screen 1500 may show the user's daily readiness score (e.g., fitness fatigue score) for the current day. Additionally, screen 1500 may show subscores of the daily readiness score such as activity (e.g., a first subscore), recent sleep (e.g., a second subscore), and heart rate variability (e.g., a third subscore). Screen 1502 may include a recommended workout for the user to try for the current day based on the user's daily readiness score. Additionally, screen 1504 may show the daily readiness score determined for the user over the past week. In this manner, the user can see how their readiness score has changed over the past week.

[0093] A wearable computing device according to exemplary aspects of the present disclosure can provide numerous technical effects and advantages. For example, the wearable computing device can generate and display a user's fitness fatigue score for the current day. Furthermore, the wearable computing device can generate notifications regarding the user's exercise for the current day based at least in part on the user's fitness fatigue score. In particular, the wearable computing device can generate a recommendation for the user to engage in a strenuous activity (e.g., running) when the fitness fatigue score indicates that the user is sufficiently rested. Conversely, the wearable computing device can generate a recommendation for the user to engage in a less strenuous activity (e.g., walking) or refrain from exercising when the fitness fatigue score indicates that the user is not sufficiently rested. Furthermore, because the fitness fatigue score is determined based on biometric data collected by a biometric sensor in the wearable computing device, the fitness fatigue score can be a better indicator of the user's current energy level compared to the user's own assessment of their energy level. For example, instances may arise in which a user may feel ready to engage in strenuous activity when, in fact, the user is fatigued and therefore not ready to engage in strenuous activity. However, because the fitness fatigue score is determined based on biometric data rather than how the user feels, the fitness fatigue score may provide a more objective indicator of a user's readiness to engage in strenuous activity. In this way, a wearable computing device according to the present disclosure may provide exercise recommendations based on an objective metric (e.g., a fitness fatigue score), thereby reducing or eliminating instances where a user feels ready to engage in strenuous activity but their biometrics indicate otherwise.

[0094] In addition to the above, users may be provided with controls that allow them to choose both whether and when the systems, programs, or features described herein may enable the collection of user information (e.g., information about the user's social network, social behavior, or activities, occupation, user preferences, or the user's current location), as well as whether the user is sent content or communications from the server. Furthermore, certain data may be handled in one or more ways so that personally identifiable information is removed before it is stored or used. For example, the user's identity may be handled in such a way that personally identifiable information about the user cannot be determined, or if location information is obtained (e.g., to the city, zip code, or state level), the user's geographic location may be generalized so that the user's specific location cannot be determined. Thus, users may control what information is collected about them, how that information is used, and what information is provided to them. To that end, any information collected about users as described herein will be kept private and confidential and will not be used or disclosed inappropriately.

[0095] Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense, but it will be apparent that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention as set forth in the appended claims.

Claims

1. 1. A computer-implemented method for determining a user's fitness fatigue score, comprising: acquiring first data of the user over a first period of time, the first data including a plurality of heart rate measurements of the user over the first period of time, the computer-implemented method further comprising: acquiring second data of the user over a second time period shorter in duration than the first time period, the second data including one or more sleep metrics for a plurality of sleep events of the user over the second time period, the second data including one or more sleep metrics for a plurality of sleep events of the user over the second time period, the computer-implemented method further comprising: acquiring third data of the user over a third time period longer in duration than the first time period, the third data including heart rate variability data of the user over the third time period, the third data comprising heart rate variability data of the user over the third time period, the computer-implemented method further comprising: determining the fitness fatigue score for the user for the current day based at least in part on the first data, the second data, and the third data; displaying the fitness fatigue score on a display screen of an electronic device; A computer-implemented method comprising:

2. determining an exercise recommendation for the day based at least in part on the fitness fatigue score for the day; displaying the recommendations on the display screen of the electronic device; and The computer-implemented method of claim 1 further comprising:

3. the recommendation is that the user refrain from exercising on the day when the fitness fatigue score on the day is less than a first threshold; the recommendation is for the user to engage in a first physical activity for the current day when the fitness fatigue score for the current day is greater than the first threshold but less than a second threshold; the recommendation is for the user to engage in a second physical activity for the current day when the fitness fatigue score for the current day is greater than the second threshold, the second physical activity being more strenuous for the user than the first physical activity; 3. The computer-implemented method of claim 2.

4. Determining the fitness fatigue score for the user for the day may include: determining a first sub-score based at least in part on the first data; determining a second sub-score based at least in part on the second data; and determining a third sub-score based at least in part on the third data; and determining the fitness fatigue score for the user for the day based at least in part on the first sub-score, the second sub-score, and the third sub-score; 10. The computer-implemented method of claim 1, comprising:

5. 5. The computer-implemented method of claim 4, wherein the first sub-score is weighted more heavily than each of the second sub-score and the third sub-score.

6. determining the fitness fatigue score comprises: determining that the first sub-score is less than a threshold; determining that the fitness fatigue score for the current day is the first sub-score; 5. The computer-implemented method of claim 4, comprising:

7. Determining the first sub-score based on the first data includes: determining a preliminary value for each of the plurality of heart rate measurements included in the first data; determining that the preliminary value of one or more heart rate measurements of the plurality of heart rate measurements collected over the first time period is greater than a threshold; determining the first sub-score based at least in part on the one or more heart rate measurements; 5. The computer-implemented method of claim 4, comprising:

8. Determining the preliminary values ​​for each of the heart rate measurements may include: determining a resting heart rate of the user based at least in part on the first data; determining a maximum heart rate of the user based at least in part on an age of the user; determining the preliminary value for each of the plurality of heart rate measurements based at least in part on a comparison of each respective heart rate measurement to the user's resting heart rate and the user's maximum heart rate; 8. The computer-implemented method of claim 7, comprising:

9. the heart rate variability data includes heart rate variability measurements taken during each of a plurality of sleep events occurring over the third period of time; Determining the third sub-score based at least in part on the heart rate variability data includes: determining a root mean square of successive differences of heart rate variability measures associated with a first sleep event of the plurality of sleep events, the first sleep event being most recent of the plurality of sleep events; and determining the third sub-score further comprising: determining the third sub-score based at least in part on a comparison of the heart rate variability measure associated with the first sleep event to heart rate variability measures associated with at least one other sleep event of the plurality of sleep events; 5. The computer-implemented method of claim 4, comprising:

10. The computer-implemented method of claim 1 , wherein the one or more sleep metrics include a duration of each of the plurality of sleep events and a time at which each of the plurality of sleep events occurred.

11. the first period includes the 14 days immediately preceding the current day; the second period includes the seven days immediately preceding the current day; the third period includes the 30 days immediately preceding the day; 10. The computer-implemented method of claim 1.

12. The computer-implemented method of claim 1 , wherein the electronic device comprises a wearable computing device or a mobile computing device worn by the user.

13. 1. A wearable computing device, comprising: A display screen; one or more biometric sensors; one or more processors; Equipped with the one or more processors: configured to acquire first data of a user over a first period of time, the first data including a plurality of heart rate measurements of a user wearing the wearable computing device, and the one or more processors further: configured to acquire second data of the user over a second time period shorter in duration than the first time period, the second data including one or more sleep metrics for a plurality of sleep events of the user, and the one or more processors further: configured to acquire third data of the user over a third time period longer in duration than the first time period, the third data including heart rate variability data of the user, and the one or more processors further: receiving the fitness fatigue score for the user for the current day based at least in part on the first data, the second data, and the third data; displaying the fitness fatigue score of the user on the display screen; configured to: Wearable computing devices.

14. The one or more processors further comprise: further configured to cause the display screen to display exercise recommendations based at least in part on the fitness fatigue score of the user. The wearable computing device of claim 13 .

15. the recommendation is that the user refrain from exercising on the day when the fitness fatigue score on the day is less than a first threshold; the recommendation is for the user to engage in a first physical activity for the current day when the fitness fatigue score for the current day is greater than the first threshold but less than a second threshold; the recommendation is for the user to engage in a second physical activity for the current day when the fitness fatigue score for the current day is greater than the second threshold, the second physical activity being more strenuous for the user than the first physical activity; 15. The wearable computing device of claim 14.

16. the first period includes the 14 days immediately preceding the current day; the second period includes the seven days immediately preceding the current day; the third period includes the 30 days immediately preceding the day; The wearable computing device of claim 13 .

17. 14. The wearable computing device of claim 13, wherein the one or more sleep metrics include a duration of each of the plurality of sleep events and a time at which each of the plurality of sleep events occurred.

18. The wearable computing device of claim 13 , wherein the fitness fatigue score comprises a numerical value ranging from 0 to 100.

19. A non-transitory computer-readable medium storing instructions executable by one or more processors of an electronic device, the instructions comprising: instructions for acquiring first data of a user over a first period of time, the first data including a plurality of heart rate measurements of the user over the first period of time, the instructions further comprising: instructions for acquiring second data of the user over a second time period shorter in duration than the first time period, the second data including one or more sleep metrics for a plurality of sleep events of the user over the second time period, the instructions further comprising: instructions for acquiring third data of the user over a third time period longer in duration than the first time period, the third data including heart rate variability data of the user over the third time period, the instructions further comprising: instructions for determining a fitness fatigue score for the user for the current day based at least in part on the first data, the second data, and the third data; instructions for causing the one or more processors of the electronic device to display the fitness fatigue score on a display screen; 1. A non-transitory computer-readable medium comprising:

Images