Methods, Systems, and Devices for Improved Skin Temperature Monitoring

Abstract

To provide computer-implemented methods, systems, and devices for improved skin temperature monitoring.SOLUTION: Accurate estimates of skin and ambient temperature are generated based on determinations and comparisons of skin and internal device temperature sensor measurements contained on or within example devices. The estimates of skin and ambient temperature measurements facilitate monitoring skin and core temperature changes, detecting physiological events of a wearer of example devices, and determining whether skin temperature changes are environmentally or physiologically induced.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Field The present disclosure generally relates to health monitoring and wearable devices for health monitoring. More specifically, the present disclosure relates to methods and devices for improved skin temperature monitoring.

Background Art

[0002] Background Skin temperature data may be dominated by fluctuations in ambient temperature. Therefore, in devices that provide skin temperature monitoring, inaccuracies may occur that are independent of sensor error. There is a need for methods, systems, and devices for distinguishing physiologically induced changes in skin temperature from environmentally induced changes in skin temperature.

Summary of the Invention

[0003] Summary Aspects and advantages of embodiments of the present disclosure will be set forth in part in the description which follows, or can be learned from the description, or can be learned through practice of the embodiments.

Means for Solving the Problems

[0004] One exemplary aspect of the present disclosure is directed to a method executed by a computer for providing improved skin temperature monitoring. The method includes a computing system including one or more computing devices determining an internal device temperature of the wearable device based on sensor data received from an internal device temperature sensor included in the wearable device worn by a user. The method also includes the computing system determining a first estimate of the skin temperature of the user based on sensor data received from a skin temperature sensor included on or in the wearable device. Next, the method includes the computing system estimating an ambient air temperature based at least in part on the first estimate of the skin temperature and the internal device temperature. Next, the method includes the computing system refining the first estimate of the skin temperature based at least in part on the estimated ambient air temperature to generate a second estimate of the skin temperature.

[0005] Another exemplary aspect of the present disclosure is directed to a wearable device, the wearable device including a device housing configured to be worn by a user, one or more processors included within the device housing, one or more skin temperature sensors included on or within the device housing and configured to generate skin temperature sensor data, one or more internal device temperature sensors included within the device housing and configured to generate internal device temperature sensor data, and a non-transitory computer-readable memory included within the device housing and storing instructions that, when executed by the one or more processors, cause the wearable device to perform operations. In particular, the operations include determining an internal device temperature within the device housing based at least in part on the internal device temperature sensor data received from the one or more internal device temperature sensors included within the wearable device, determining a first estimated value of the skin temperature of the user based on sensor data received from a skin temperature sensor included on or within the device housing, and estimating an ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature. The operations further include improving the first estimated value of the skin temperature based at least in part on the estimated ambient air temperature to generate a second estimated value of the skin temperature.

[0006] Another exemplary aspect of the present disclosure is directed to a method executed by a computer for providing improved skin temperature monitoring. The method includes a computing system including one or more computing devices determining an internal device temperature of a wearable device based on sensor data received from an internal device temperature sensor included within the wearable device worn by a user. Next, the method includes the computing system determining a first estimated value of the skin temperature of the user based on sensor data received from a skin temperature sensor included on or within the wearable device. Next, the method includes the computing system improving the first estimated value of the skin temperature based at least in part on the internal device temperature of the wearable device to generate a second estimated value of the skin temperature. Next, the method includes the computing system determining one or more physiological events based at least in part on the second estimated value of the skin temperature.

[0007] A detailed description of embodiments directed to those skilled in the art is set forth in the specification with reference to the accompanying drawings.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION Summary Generally, the present disclosure is directed to health monitoring and wearable devices for health monitoring, such as methods and devices for improved skin temperature monitoring. In particular, exemplary aspects of the present disclosure include computer-implemented methods for providing improved skin temperature monitoring. The methods of the present disclosure enable observing significant changes in a person's core body temperature and identifying physiological trends and events related to the person's health.

[0010] More specifically, a person's skin temperature is expected to change with fluctuations in that person's core body temperature. Sometimes, there may be a positive correlation between a person's skin temperature and the person's core body temperature, but at other times, this relationship can result in an inverse change. For example, a person's body may raise its core body temperature to generate heat, during which perfusion of the limbs is reduced, so it is expected that the skin temperature will be low while the person's core body temperature is rising. These physiologically induced developments enable observing trends from comparisons of temperature data streams that may not be possible by observing other data streams. On the other hand, changes in skin temperature can also be governed by fluctuations in ambient temperature, so it is difficult to identify changes in skin temperature associated with physiological changes. For this reason, there is a need for a method to distinguish between physiologically induced changes in skin temperature and changes caused by the environment.

[0011] In view of such problems, the present disclosure provides a computer-executed system and method for improved skin temperature monitoring. In some implementations, the method of the present disclosure includes a computing system determining an internal temperature of a wearable device based at least in part on sensor data from one or more sensors included within a wearable device worn by a user. In one example, the wearable device may be a wristband, bracelet, watch, armband, ring placed around a user's finger, or any other wearable product that may include sensors as described in the present disclosure. As another example, one or more sensors that measure the internal temperature of the device may be included within the housing of the wearable device and may not be in thermal contact with the user's skin. When one or more sensors that measure the internal temperature of the device are arranged according to this example, the sensors may correlate with the user's skin temperature, but may also be more susceptible to the influence of the outside air temperature, for example compared to a dedicated skin temperature sensor.

[0012] According to another aspect, the method of the present disclosure includes a computing system determining a first estimate of a user's skin temperature based on sensor data received from one or more skin temperature sensors that are in thermal contact with the user and included within a wearable device. In another example, the wearable device may include a thermally conductive baseplate configured to contact the user's skin. In this example, one or more skin temperature sensors may be configured to measure the temperature of the baseplate. When one or more sensors that measure the first estimate of the user's skin temperature are arranged in this manner, the sensors can be made less susceptible to the influence of the outside air temperature, for example compared to the internal device temperature sensors and / or dedicated ambient air temperature sensors described above.

[0013] According to another aspect of the present disclosure, a computing system may estimate the ambient air temperature based at least in part on a first estimated value of skin temperature and an internal device temperature. In some implementations, the computing system estimates the ambient air temperature by determining the difference between the first estimated value of skin temperature and the internal temperature of the wearable device. In one example the estimated ambient air temperature may be the result of one or more smoothing or curve fitting processes of a dataset corresponding to the temperature difference as described above. In some implementations, the computing system may estimate the ambient air temperature by processing the first estimated value of skin temperature and the internal temperature of the wearable device with a machine learning model. As an example, the machine learning model may include a linear regression model, a neural network (e.g., a recurrent neural network), or a clustering model. In some implementations, the computing system may receive the ambient air temperature as a prediction output by the machine learning model.

[0014] According to another aspect of the present disclosure, a computing system may generate an intermediate estimated value of skin temperature based at least in part on a first estimated value of skin temperature and an internal device temperature. This intermediate estimated value of skin temperature can be further refined based at least in part on the ambient temperature estimate to help generate a second estimated value of skin temperature. In one example, the intermediate estimated value of skin temperature may be the result of one or more smoothing or curve fitting processes of a dataset corresponding to the temperature difference as described above. In some implementations, the computing system may generate the intermediate estimated value of skin temperature by processing the first estimated value of skin temperature and the internal temperature of the wearable device with a machine learning model. As an example, the machine learning model may include a linear regression model, a neural network (e.g., a recurrent neural network), or a clustering model. In some implementations, the computing system may receive the intermediate estimated value of skin temperature as a prediction output by the machine learning model.

[0015] In some implementations, the computing system may adjust the ambient air temperature estimate based at least in part on additional ambient sensor data obtained from additional ambient sensors included within the wearable device. In some implementations, the additional ambient sensors may include a position sensor (e.g., a global positioning sensor), a geo sensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, a heart rate sensor, and other physiological sensors. In one example, the computing system may observe whether the ambient light sensor included within the wearable device is covered. In this example, the computing system may be able to infer a warmer ambient temperature based on the ambient light sensor being covered, which may be useful for determining a skin temperature estimate, and thus a physiological trend, based on the skin temperature, changes in the skin temperature, and the rate of change of the skin temperature. In some implementations, the computing system may adjust the ambient air temperature estimate based at least in part on sleep data of the user collected by the wearable device. In some implementations, examples of sleep data may include data indicating whether the user is awake or asleep, a sleep coefficient of the user, and a heart rate of the user. When the user is asleep, the data may also include information indicating whether the user is moving (e.g., changing positions) and a characterization of the type of sleep the user is experiencing (e.g., restless sleep, light sleep, deep sleep, rapid eye movement (REM) sleep). In one example, the computing system may be able to infer that a change in the position of a sleeping user is a function of the user's thermoregulation cycle, and thus may be useful for determining the user's core body temperature based at least in part on a second estimate of the user's skin temperature.

[0016] According to another aspect of the present disclosure, the method includes the computing system improving a first estimate of skin temperature based at least in part on an intermediate estimate of the ambient air temperature or skin temperature that is estimated, to generate a second estimate of skin temperature. In one example, the second estimate of skin temperature can be the result of one or more smoothing or curve fitting processes on a dataset corresponding to the estimated ambient air temperature. In some implementations, the computing system modifies a confidence value associated with the second estimate of skin temperature or the estimated ambient air temperature. As an example, the confidence value can increase as the temperature difference between the first estimate of skin temperature or the estimated ambient air temperature and the internal temperature of the wearable device decreases. Stated another way, a decrease in the temperature difference between the first estimate of skin temperature or the estimated ambient air temperature and the internal temperature of the wearable device can be the same as an increase in confidence in the second estimate of skin temperature. Also, as another example, a smaller temperature difference can mean that it is less likely that the ambient temperature is causing a change in the user's skin temperature. The confidence value can increase as the temperature difference between the first estimate of skin temperature or the estimated ambient air temperature and the internal temperature of the wearable device decreases. Stated another way, a decrease in the temperature difference between the first estimate of skin temperature or the estimated ambient air temperature and the internal temperature of the wearable device can be the same as an increase in confidence in the second estimate of skin temperature. Also, as another example, a smaller temperature difference can mean that it is less likely that the ambient temperature is causing a change in the user's skin temperature.

[0017] According to another aspect of the present disclosure, the method includes the computing system determining one or more physiological events of the user based at least in part on the second estimate of skin temperature. In some implementations, the physiological events can include fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort. Detection of a physiological event can include detection of the state of a physiological event, such as detection of the start of a physiological event, determination of the current ongoing state of the event, and / or prediction regarding the future state of the event (e.g., a fever peak expected to occur within the next six hours). In one example, the computing system can detect a fever by smoothing a dataset of second estimates of skin temperature collected after an increase in the user's skin temperature.

[0018] In some implementations, a computing system may estimate a user's core body temperature based on a second estimate of skin temperature. In one example, the estimated user's core body temperature may be based on second estimates of skin temperature collected at different frequencies and during different sleep stages of the user (e.g., awake or asleep). In some implementations, the computing system may distinguish between physiologically induced changes in core body temperature and environmentally induced changes in core body temperature. In some implementations, the computing system may monitor the rate of change of the second estimate of skin temperature to detect transitions in the second estimate of skin temperature. As an example, the computing system may determine a physiological event based on the detected transition. In some examples, the physiological event may include the onset of fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort.

[0019] The methods and devices of the present disclosure provide many technical effects and advantages, including obtaining a more reliable estimate of a person's true skin temperature, observing significant changes in a person's core body temperature, and identifying physiological trends and events related to a person's health.

[0020] Also, the present disclosure enables improvement of data received from sensors within a wearable device by combining and analyzing data from multiple sensors so that a user can observe not only raw data but also trends and events inferred from that data. In this way, the present disclosure can also save device space and processor usage by eliminating the need for additional sensors within the wearable device. Additionally, the present disclosure enables a more accurate device for monitoring skin temperature by implementing the device's sensors in a more efficient, predictable, and useful manner.

[0021] Next, with reference to the drawings, embodiments of the present disclosure will be described in more detail. Exemplary methods, systems, and devices FIG. 1 shows a front view of an exemplary wearable device 100 according to an embodiment of the present disclosure. Although the wearable device 100 in FIG. 1 is a wristwatch, the systems and methods of the present disclosure can be applied to any different types of wearable devices, such as, for example, a list band, a bracelet, a wristwatch, an armband, a headband, glasses, earphones, a ring placed around a user's finger, clothing embedded with a computer, and / or any other wearable products that may include sensors as described in the present disclosure. The wearable device 100 can be configured using a display 102, a device housing 104, and a band 106.

[0022] In some implementations, the wearable device 100 can be configured to communicate data to the user via the display 102 and / or any other data output devices such as a tactile device, a light emitting diode, etc. The data communicated can include data regarding skin temperature, heart rate, sleep state (e.g., light sleep, deep sleep, and REM sleep), sleep coefficient (e.g., sleep score), and other physiological data of the user (e.g., blood oxygen concentration). Also, the display 102 can be configured to communicate data from additional ambient sensors included in or on the wearable device 100. Exemplary information from these additional ambient sensors communicated by the display 102 can include the location, altitude, and weather of a location associated with the user. The display 102 can also communicate data regarding the user's motion (e.g., whether the user is stationary, walking, and / or running).

[0023] In some implementations, display 102 may be configured to display information regarding the user's physiological events. Exemplary physiological events that may be displayed include the user's fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort. Additionally, display 102 can communicate information regarding the detection of the user's physiological events. By being thus configured, display 102 can communicate to the user the detection or determination of the state of a physiological event, such as the detection of the onset of a physiological event, the determination of the current ongoing state of the event, and / or the prediction regarding the future state of the event (e.g., a fever peak expected to occur within the next six hours).

[0024] Also, display 102 or other data input devices (e.g., various touch sensors and / or physical buttons, switches, or toggles) may be configured to receive data input by the user. Examples of data input by the user may include symptoms, sleep situation, ovulation, information regarding menstruation, and other physiological information regarding the user's health.

[0025] Device housing 104 may be configured to include one or more sensors. Exemplary sensors included in device housing 104 may include a skin temperature sensor, an internal device temperature sensor, a position sensor (e.g., GPS), a motion sensor, an altitude sensor, a heart rate sensor, and other physiological sensors (e.g., a blood oxygen concentration sensor). Device housing 104 may be configured to include one or more processors.

[0026] Band 106 can be configured to fix wearable device 100 around the user's arm, for example, by connecting the ends of band 106 with a buckle, clasp, or other similar fastening device, thereby enabling wearable device 100 to be worn by the user.

[0027] FIG. 2 shows a rear view of an exemplary wearable device 100 according to an embodiment of the present disclosure. The wearable device 100 can be configured using a base plate 202. Also, the wearable device 100 can be configured using one or more sensors 204 that can be attached to the base plate 202. Exemplary sensors 204 can include a skin temperature sensor, a position sensor (e.g., GPS), a motion sensor, an altitude sensor, a heart rate sensor, an altimeter temperature sensor, and other physiological sensors (e.g., a blood oxygen concentration sensor). The base plate 202 can be thermally conductive and can be configured to be in thermal contact with the user and / or the skin temperature sensor when the wearable device 100 is worn by the user. For example, when worn, the base plate can be pressed against the user's skin. Similarly, the skin temperature sensor can be configured to generate a temperature reading of the base plate. Thus, the base plate 202 can be configured to enable measurement of the user's skin temperature when the base plate 202 is in thermal contact with the user (e.g., the temperature of the base plate serves as a proxy for the user's skin temperature).

[0028] In some implementation examples, a base plate is used to read the temperature of the user's skin, but other approaches can also be used, such as a temperature sensor configured to directly contact the user's skin. In another example, an infrared sensor can be included in the device 100 (e.g., inside the housing 104) and can be used to measure the temperature of the user's skin using infrared rays. For example, the infrared rays can pass through an opening in the base plate 202. In another example, one or more temperature sensors can be incorporated into the band 106 and can be used to measure the temperature of the user's skin. For example, one or more temperature sensors can be woven into a fabric version of the band 106.

[0029] FIG. 3 shows an internal side view of an exemplary wearable device 100 showing an internal device temperature sensor 302 included within a device housing 104 according to an exemplary embodiment of the present disclosure. The internal device temperature sensor 302 may be configured to measure the temperature of the internal space of the device housing 104 (e.g., the internal device temperature) and generate data regarding the temperature. Also, the internal device temperature sensor 302 may be composed of a plurality of internal device temperature sensors. The internal device temperature sensor 302 may be included within the device housing 104 of the wearable device 100, but typically is not in thermal contact with the user's skin. In one example, the internal device temperature sensor 302 may be attached to the inside of the device housing 104 (e.g., other than the base plate 202). In another example, the internal device temperature sensor 302 may be attached to a printed circuit board (e.g., a “motherboard”) of the device 100.

[0030] FIG. 4 shows an internal side view of an exemplary wearable device 100 showing a skin temperature sensor 402 included within a device housing 104 according to an exemplary embodiment of the present disclosure. In some implementations, the skin temperature sensor 402 may be configured to physically contact the user. In this way, the skin temperature sensor 402 may measure the user's skin temperature and generate data regarding the temperature. In other implementations, the wearable device 100 may include a thermally conductive base plate 202 configured to be in thermal contact with both the skin temperature sensor 402 and the user's skin. In such an embodiment, the skin temperature sensor 402 may be configured to measure the temperature of the base plate 202, which also represents the temperature of the user's skin, and generate data regarding the temperature. In yet other implementations, an infrared sensor may be included within the device 100 (e.g., within the housing 104) and may be used to measure the temperature of the user's skin using infrared light. For example, the infrared light may pass through an opening in the base plate 202. Also, the skin temperature sensor 402 may be composed of a plurality of skin temperature sensors (e.g., a plurality of different sensors taking a plurality of different approaches as described herein). Other arrangements are possible.

[0031] FIG. 5 shows the flow of steps of an exemplary skin temperature noise removal method 500 according to an embodiment of the present disclosure. In step 502, the skin temperature noise removal method 500 may obtain the internal device temperature of the wearable device 100 worn by the user. Obtaining the internal temperature of the wearable device 100 in step 502 may be at least partially based on sensor data from one or more internal device temperature sensors 302 included on or in the wearable device 100. In another example, obtaining the internal temperature of the wearable device 100 in step 502 may be at least partially based on data from temperature sensors included in other components of the device 100, such as temperature sensors present in the accelerometer and charging circuit that generate temperature data as part of monitoring and calibrating their own outputs. In the next step 504, the skin temperature noise removal method 500 may obtain a first estimated value of the user's skin temperature. Obtaining the first estimated value of the user's skin temperature in step 504 may be at least partially based on sensor data received from one or more skin temperature sensors 402 included in the wearable device 100 that are in physical and / or thermal contact with the user. In another example, obtaining the first estimated value of the user's skin temperature in step 504 may be at least partially based on sensor data from one or more skin temperature sensors 402 that are in thermal contact with the base plate 202. In this example, the base plate 202 may also be configured to be in thermal contact with the user's skin when the wearable device 100 is worn by the user.

[0032] In step 506, the skin temperature noise removal method 500 may estimate the ambient air temperature based at least in part on the first estimated value of the skin temperature from step 504 and the internal device temperature of the wearable device 100 from step 502. The estimated value of the ambient air temperature in step 506 may be based on obtaining the difference between the first estimated value of the skin temperature from step 504 and the internal device temperature of the wearable device 100 from step 502. In another example, the estimated value of the ambient air temperature in step 506 may be the result of one or more smoothing or curve fitting processes of a dataset corresponding to the temperature difference between the first estimated value of the skin temperature from step 504 and the temperature of the internal device of the wearable device 100 in step 502.

[0033] In step 506, the skin temperature noise removal method 500 may also generate an intermediate estimated value of the skin temperature based at least in part on the first estimated value of the skin temperature from step 504 and the internal device temperature of the wearable device 100 from step 502. The intermediate estimated value of the skin temperature from step 506 can be further refined based at least in part on the ambient temperature estimated value to be useful for generating a second estimated value of the skin temperature in step 508 of the skin temperature noise removal method 500. The intermediate estimated value of the skin temperature in step 506 may be the result of one or more smoothing or curve fitting processes of a dataset corresponding to the temperature difference between the first estimated value of the skin temperature from step 504 and the internal device temperature of the wearable device 100 in step 502.

[0034] In yet another example, the estimated ambient air temperature or the intermediate estimated skin temperature in step 506 can be obtained by processing the first estimated skin temperature from step 504 and the internal temperature of the wearable device from step 502 with a machine learning model. In such an implementation, the estimated ambient air temperature or the intermediate estimated skin temperature in step 506 can be the predicted output of the machine learning model. For example, the machine learning model may be trained with a supervised learning approach on a training dataset that includes pairs of input data and ground truth labels. For example, for each pair, the input data may include exemplary skin temperature and internal device temperature readings, while the ground truth label may include the ground truth ambient temperature. For example, the training dataset can be collected over time from situations where the wearable device is operating in an environment with a known ambient temperature. In some implementations, the training dataset can be generated using sensors present in a test chamber that allows for the control of various temperatures including those representing the user's skin and the ambient environment. By training with such a training dataset, the machine learning model can be configured to generate a predicted ambient temperature or an intermediate estimated skin temperature based on the skin temperature and the internal device temperature. The machine learning model can be any form of model including various neural networks (e.g., feedforward neural networks, recurrent neural networks, transformer networks, etc.), linear models, support vector machines, clustering models, etc.

[0035] In another example, the estimated ambient air temperature in step 506 can be adjusted based at least in part on additional ambient sensor data obtained from additional ambient sensors included on or in the wearable device 100 In one example, the estimated ambient air temperature in step 506 can be adjusted based at least in part on sleep data input by the user and collected by the wearable device 100 and / or other ambient data as described herein.

[0036] In step 508, skin temperature noise removal method 500 generates a second estimated value of the user's skin temperature by refining a first estimated value of the skin temperature based at least in part on the intermediate estimated value of the ambient air temperature or skin temperature from step 506. The second estimated value of the skin temperature generated in step 508 can be the result of one or more smoothing or curve fitting processes on a data set corresponding to the intermediate estimated value of the ambient air temperature or skin temperature. In another example, one or more smoothing or curve fitting processes on the data set can take into account minor body position changes of the user, such as when the user covers or removes a blanket, and other similar behavioral factors (e.g., general movement of the user). In this example, one or more smoothing or curve fitting processes can modify the signal of the skin temperature data points such that the signal is less susceptible to the influence of temperature peaks caused by these behavioral factors.

[0037] In another example, generating a second estimated value of the user's skin temperature in step 508 can include modifying a confidence value associated with the second estimated value of the skin temperature or the estimated ambient air temperature. In such an example, the confidence value can increase as the temperature difference between the first estimated value of the skin temperature or the estimated ambient air temperature and the internal temperature of wearable device 100 decreases. In this example, the decrease in the temperature difference between the first estimated value of the skin temperature or the estimated ambient air temperature and the internal temperature of wearable device 100 can be the same as an increase in confidence in the second estimated value of the skin temperature.

[0038] In some implementations, at step 508, the second estimated skin temperature value can be obtained by processing the first estimated skin temperature value from step 504, the intermediate estimated skin temperature value from step 506, and the estimated ambient temperature from step 506 with a machine learning model. In such implementations, the second estimated skin temperature value at step 508 can be the predicted output of the machine learning model. For example, the machine learning model may be trained with a supervised learning approach using a training data set that includes pairs of input data and ground truth labels. For example, for each pair, the input data may include exemplary estimated skin temperature and ambient temperature readings, while the ground truth label may include the ground truth skin temperature. For example, the training data set can be collected over time from situations where the wearable device is operating with a more accurate skin temperature sensor. By training with such a training data set, the machine learning model can be configured to generate improved skin temperature readings (e.g., that reflect only physiological events and not environmental events). In some implementations, the training data set can be generated using sensors present within a test chamber that allows for control of various temperatures including temperatures representative of the user's skin and the ambient environment. The machine learning model can be any form of model including various neural networks (e.g., feed-forward neural networks, recurrent neural networks, transformer networks, etc.), linear models, support vector machines, clustering models, etc.

[0039] FIG. 6 shows an exemplary physiological event detection system 600 according to an embodiment of the present disclosure. In one example, the physiological event detection system 600 can receive inputs in the form of additional ambient condition sensor data 602, internal device temperature sensor data 604, skin temperature sensor data 606, and sleep data 608.

[0040] The additional ambient condition sensor data 602 is optional and may include data from position sensors (such as global positioning sensors), geo sensors, weather sensors, motion sensors, altitude sensors, altimeter temperature sensors, ambient light sensors, heart rate sensors, and other physiological sensors (such as blood oxygen sensors) included on or within the wearable device 100. For example, by determining the user's position via a position sensor, information from various databases regarding local ambient conditions (such as temperature or other weather data) can be obtained and used to guide the process. Similarly, data regarding heart rate and other physiological sensors can help understand temperature changes that occur physiologically rather than environmentally.

[0041] The internal device temperature sensor data 604 may include data from one or more internal device temperature sensors 302 included on or within the wearable device 100. The skin temperature sensor data 606 may include data from one or more skin temperature sensors 402 included on or within the wearable device 100 and in thermal contact with either the user or the base plate 202 of the wearable device 100.

[0042] The sleep data 608 may include data collected by the wearable device 100 or input by the user. Examples of sleep data may include data indicating whether the user is awake or asleep, the user's sleep coefficient, and the user's heart rate. In this example, when the user is asleep, the sleep data 608 may also include information indicating whether the user is moving and a characterization of the type of sleep the user is experiencing (such as restless sleep, light sleep, deep sleep, REM sleep).

[0043] In this example of the physiological event detection system 600, by executing the skin temperature noise removal method 500, data inputs 602 and 608 can be processed in combination with the processing of data inputs 604 and 606. As a component 610 of the physiological event detection system 600, a physiological event of the user can be detected based at least in part on data inputs 602 and 608 and a second estimated value of the skin temperature generated by executing the noise removal method 500. In such an example, the physiological events from component 610 can include fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort.

[0044] The detection 610 of physiological events can include the detection or determination of the state of a physiological event such as the start of a physiological event, and / or a prediction regarding the future state of the event (e.g., a fever peak expected to occur within the next 6 hours). In another example, the detection 610 of physiological events can include smoothing a data set of a second estimated value of the skin temperature collected after an increase in the user's skin temperature.

[0045] In component 612 of the physiological event detection system 600, the system can infer a physiological event. Inferring a physiological event in component 612 can include one or more processors included in the device housing 104 causing the display 102 to communicate information regarding the physiological event detected from component 610 to the user.

[0046] FIG. 7 shows another example of the physiological event detection system 600 according to an embodiment example of the present disclosure. In this example, the physiological event detection system 600 can receive the same inputs 602, 604, 606, and 608 as received in the physiological event detection system of FIG. 6. Also, the system of FIG. 7 can detect and infer the same physiological events as described above with respect to FIG. 6.

[0047] The physiological event detection system 600 of FIG. 7 can be configured to process the internal device temperature sensor data 604 and the skin temperature sensor data 606 with a machine learning model 702. In this exemplary configuration, the machine learning model 702 may include a linear regression model, a neural network (e.g., a recurrent neural network), or a clustering model. In such an example, the physiological event detection system 600 may receive an estimated ambient air temperature or an intermediate estimated skin temperature as a predicted output by the machine learning model 702. Using the estimated ambient air temperature or the intermediate estimated skin temperature received in this way, the true skin temperature of the user wearing the wearable device 100 can also be estimated. In component 706, the physiological event detection system 600 of FIG. 7 may also be configured to detect and monitor the transition (e.g., the rate of change) of the estimated ambient air temperature and the true skin temperature of the user. In this configuration, the detection of the temperature transition in 706 may contribute to the detection of the physiological event in component 610 and the inference of the physiological event in 612.

[0048] FIG. 8 shows another example of the physiological event detection system 600 according to an embodiment of the present disclosure. In this example, the system 600 may receive the same inputs 602, 604, 606, and 608 as received in the physiological event detection systems of FIGS. 6 and 7. Also, the system of FIG. 8 may detect and infer the same physiological events as described above with respect to FIGS. 6 and 7, including the input related to the detection of the temperature transition from component 706.

[0049] The physiological event detection system 600 of FIG. 8 can be configured using a component 802 that determines the difference between the internal temperature of the wearable device 100 and a first estimate of the skin temperature of the user wearing the wearable device 100. In component 804 of the physiological event detection system 600, the system can estimate an intermediate estimate of the ambient air temperature or skin temperature based on this difference. By using the estimated intermediate estimate of the ambient air temperature or skin temperature from 804 to generate a second estimate of the user's skin temperature, the effect of the ambient air temperature on the user's skin temperature can also be estimated. Also, the physiological event detection system 600 can be configured to correct a confidence value associated with the second estimate of the skin temperature or the estimated ambient air temperature from 804. In this configuration of the physiological event detection system 600, the confidence value can increase as the temperature difference between the first estimate of the skin temperature or the estimated ambient air temperature and the internal temperature of the wearable device decreases. Also, the smaller the temperature difference obtained in 802, the less likely it may mean that the estimated ambient air temperature is affecting the second estimate of the skin temperature. The second estimate of the skin temperature in 802 can also be used to estimate the user's core body temperature. In such a configuration, the physiological event detection system 600 can distinguish between physiologically induced changes in core body temperature and environmentally induced changes in core body temperature.

[0050] FIG. 9 shows an exemplary computing system according to an embodiment of the present disclosure. The computing system can include a user computing device (e.g., the wearable device 100) shown in FIG. 9. In some implementations, the user computing device can be connected to a server computing system via a network. The server and the network are not shown in FIG. 9.

[0051] A user device as shown in FIG. 9 may include one or more processors and a memory. The one or more processors can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.), and can be one processor or multiple processors operably connected. The memory can include one or more non-transitory computer-readable storage media such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory can store data and instructions that are executed by the processor to cause the computing system of FIG. 9 to perform operations. Exemplary operations include the flow of steps of the skin temperature noise removal method 500, as well as performing the tasks of the components described in the various configurations of the physiological event detection system of FIGS. 6, 7, and 8.

[0052] Also, the user device of FIG. 9 may include one or more user input components for receiving user input. For example, the user input component can be a touch sensor-type component (e.g., the display 102 of the wearable device 100) that reacts to the touch of a user input object (e.g., a finger or a stylus). The touch sensor-type component can function to implement a virtual keyboard. Exemplary user input received by the computing system of FIG. 9 can include information regarding symptoms, sleep status, ovulation, menstruation, and other physiological information regarding the user's health.

[0053] In addition, the user device of FIG. 9 may include one or more sensors, including one or more skin temperature sensors 402 and one or more internal device temperature sensors 302. The skin temperature sensors 402 and the internal device temperature sensors 302 may include negative temperature coefficient (NTC) thermistors, resistance temperature detectors (RTDs), thermocouples, and semiconductor-based sensors. Additional sensors of the computing system of FIG. 9 may be position sensors (e.g., GPS), motion sensors, altitude sensors, heart rate sensors, and other physiological sensors (e.g., blood oxygen concentration sensors). The position sensor may be a cellular-based or satellite-based GPS sensor. Exemplary motion sensors include passive infrared (PIR), microwave, and dual-tech / hybrid motion sensors. Exemplary altitude sensors include barometric altimeters (e.g., aneroid barometers) and radio altimeters. Exemplary heart rate sensors include optically transmitted pulse sensors (e.g., photoplethysmography (PPG)) and electrocardiogram (ECD) sensors.

[0054] A server computing system (not shown in FIG. 9) may include one or more processors and memory. The one or more processors can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or multiple processors operably connected. The memory can include one or more non-transitory computer-readable storage media such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory can store data and instructions that are executed by the processor to cause the server computing system to perform operations.

[0055] In some implementations, a server computing system includes or is implemented by one or more server computing devices. In an example where the server computing system includes multiple server computing devices, such server computing devices may operate according to a sequential computing architecture, a parallel computing architecture, or some combination thereof.

[0056] The network can be any kind of communication network, such as a local area network (e.g., intranet), a wide area network (e.g., Internet), or some combination thereof, and can include any number of wired or wireless links. Generally, communication over the network can be carried by any kind of wired and / or wireless connection using a variety of communication protocols (e.g., TCP / IP, HTTP, SMTP, FTP), encodings or formats (e.g., HTML, XML), and / or protection schemes (e.g., VPN, secure HTTP, SSL).

[0057] In some implementations, the user device of FIG. 9 can store or include one or more machine learning models. For example, the machine learning model can be or include various machine learning models such as various neural networks (e.g., feedforward neural networks, recurrent neural networks, transformer networks, etc.), linear models, support vector machines, clustering models, etc.

[0058] In some implementations, one or more machine learning models are received from a server computing system via a network, stored in the memory of a user device, and then can be used or otherwise implemented by one or more processors. In some implementations, a user computing device can implement multiple parallel instances of a single machine learning model.

[0059] In addition to or instead of this, one or more machine learning models can be included in a server computing system that communicates with the user device of FIG. 9 according to a client-server relationship, or otherwise stored in and implemented by the server computing system. For example, a machine learning model can be implemented by a server computing system as part of a web service (such as a data augmentation service). Thus, one or more models can be stored and implemented on the user device of FIG. 9, and / or one or more models can be stored and implemented in a server computing system. Additionally, some or all operations can be performed at one location or multiple locations.

[0060] Exemplary data FIG. 10 shows an exemplary graph of temperature data for a wearable device 100 according to an embodiment of the present disclosure. In FIG. 10, temperature measurements of the wearable device 100 are shown at various times and in different usage states by the user of the wearable device 100. Also, FIG. 10 includes a characterization of the magnitude of any variations in the temperature data, and how those variations compare to the time and whether the user is wearing the wearable device 100.

[0061] FIG. 11 shows an exemplary graph of temperature data from the internal device temperature sensor 302 and the skin temperature sensor 402 according to an embodiment example of the present disclosure. In FIG. 11, the temperature measurement values of the internal device temperature sensor 302 and the skin temperature sensor 402 are shown in different usage states by the user of the wearable device 100 at various times. FIG. 11 represents the recording of temperature data from both sensors 302 and 402 based on the time and whether the user is wearing the wearable device. FIG. 11 further shows the time periods when the temperature difference between the measurement value of the internal device temperature sensor 302 and the measurement value of the skin temperature sensor 402 is maximum and minimum. The time period when the temperature difference between the two temperature sensors 302 and 402 is minimum (for example, the difference value is less than the threshold value) is identified and shaded in FIG. 11. The time period with the minimum temperature difference also correlates with a high confidence value for the estimated value of the user's skin temperature, that is, the ambient temperature is less likely to cause a change in the skin temperature of the user of the wearable device 100.

[0062] FIG. 12 shows an exemplary graph of differential temperature data from the internal device temperature sensor 302 and the skin temperature sensor 402 according to an embodiment example of the present disclosure. FIG. 12 is related to the graph shown in FIG. 11, but instead plots the value of the temperature difference between the temperature measurement value of the internal device temperature sensor 302 and the temperature measurement value of the skin temperature sensor 402. FIG. 12 provides an alternative representation (for example, compared with FIG. 11) for explaining the time periods when the temperature difference value is maximum and minimum. The time period when the temperature difference between the two temperature sensors 302 and 402 is minimum (for example, the temperature difference value is less than the threshold value) is identified and shaded in FIG. 12. Similar to FIG. 11, the time period with the minimum temperature difference also correlates with a high confidence value for the estimated value of the user's skin temperature, that is, the ambient temperature is less likely to cause a change in the skin temperature of the user of the wearable device 100.

[0063] FIG. 13 shows a graph of exemplary temperature data of a plurality of wearable devices 100 according to an embodiment of the present disclosure. In particular, the graph of FIG. 13 plots the temperature measurements of the fuel gauge and the skin temperature sensor 402 included in the wearable device 100, how they vary when exposed to a defined ambient temperature environment over a defined period of time, and whether the wearable device 100 is on the user's wrist.

[0064] FIG. 14 shows a graph showing an exemplary linear regression model of ambient temperature estimation prediction according to an embodiment of the present disclosure. In FIG. 14, the ambient temperature estimation prediction is compared with temperature sensor data from a source including ambient and phantom ground truth sensors (further including an altimeter temperature sensor, a skin temperature sensor 402, and an internal device temperature sensor 302) over a defined period of time.

[0065] FIG. 15 shows a graph of exemplary skin temperature variations versus days from fever according to an embodiment of the present disclosure. In particular, FIG. 15 plots the variation of the user's average skin temperature with respect to the days before and after fever for true temperature data and smoothed temperature data.

[0066] FIG. 16 shows a graph of exemplary temperature variations incorporating sleep data according to an embodiment of the present disclosure. More specifically, FIG. 16 represents a record of temperature data from the internal device temperature sensor 302 and the skin temperature sensor 402 included in the wearable device 100, obtained over a defined period of time during which the sleep time and the state of whether the user is wearing the wearable device 100 are identified and shaded. FIG. 16 also shows the count values of the measurements of the internal device and skin temperature sensors obtained during the same period.

[0067] Additional disclosure The technology described in this specification refers to servers, databases, software applications, and other computer-based systems, as well as the operations performed and information transmitted between such systems. The inherent flexibility of computer-based systems allows for a wide variety of possible configurations, combinations, and divisions of tasks and functions among components. For example, the processes described in this specification can be executed using a single device or component, or using multiple devices or components that function in combination. Databases and applications can be implemented on a single system or distributed across multiple systems. Distributed components can operate sequentially or in parallel.

[0068] Although the present subject matter has been described in detail with respect to various specific examples of its embodiments, each example is provided for illustrative purposes and is not intended to limit the disclosure. Those skilled in the art will be able to readily make changes, variations, and equivalents to such embodiments upon obtaining the above understanding. Accordingly, the disclosure is not intended to exclude such modifications, variations, and / or additional incorporations of the present subject matter that will be readily apparent to those skilled in the art. For example, still other embodiments can be obtained by using features illustrated or described as part of one embodiment in conjunction with another embodiment. Accordingly, the disclosure is intended to cover such changes, variations, and equivalents.

[0069] In particular, FIGS. 1-16 each show steps performed in a specific order for purposes of illustration and description, but the methods of the disclosure are not limited to the specifically shown order or arrangement. The various steps of the skin temperature noise removal method 500 and the physiological event detection system 600 can be omitted, reordered, combined, and / or adapted in various ways without departing from the scope of the disclosure.

Claims

Claim 1 A method, executed by a computer, for providing skin temperature monitoring, the method comprising: a computing system including one or more computing devices determining an internal device temperature of the wearable device based on first sensor data received from a first sensor included on or in the wearable device worn by a user; the computing system determining a first estimated value of the skin temperature of the user based on second sensor data received from a second sensor included on or in the wearable device, wherein at least one of the first sensor, the second sensor, or both includes at least one of a position sensor, a geosensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, or a heart rate sensor included on or in the wearable device, and the method further comprises: the computing system estimating an ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature; the computing system improving the first estimated value of the skin temperature based at least in part on the estimated ambient air temperature to generate a second estimated value of the skin temperature. Claim 2 The method, executed by a computer, according to claim 1, further comprising the computing system determining one or more physiological events based at least in part on the second estimated value of the skin temperature. Claim 3 The method, executed by a computer, according to claim 2, wherein the one or more physiological events include at least one of the onset of fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort. Claim 4 The computing system determining the one or more physiological events based at least in part on the second estimated value of the skin temperature comprises: the computing system estimating a core body temperature of the user based at least in part on the second estimated value of the skin temperature. The method executed by a computer according to claim 2 or claim 3, wherein the computing system comprises distinguishing between a change in the user's core body temperature caused physiologically and a change in the user's core body temperature caused by the environment.

5. The computing system determining the one or more physiological events based at least in part on the second estimated value of the skin temperature is the computing system monitoring a rate of change of the second estimated value of the skin temperature to detect a transition of the second estimated value of the skin temperature; and The method executed by a computer according to claim 2 or claim 3, wherein the computing system comprises determining the one or more physiological events based at least in part on the detected transition of the second estimated value of the skin temperature.

6. The computing system estimating the ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature is the computing system obtaining a difference between the first estimated value of the skin temperature and the internal device temperature; and The method executed by a computer according to any one of claims 1 to 5, wherein the computing system comprises estimating the ambient air temperature based at least in part on the difference between the first estimated value of the skin temperature and the internal device temperature.

7. The computing system estimating the ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature is processing the first estimated value of the skin temperature and the internal device temperature with a machine learning model; and receiving the ambient air temperature as a prediction output by the machine learning model. The method executed by a computer according to any one of claims 1 to 5.

8. The computing system estimating the ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature is The computing system includes adjusting an estimated value of the ambient air temperature based at least in part on additional sensor data from the first sensor, the second sensor, or a third sensor, where the third sensor includes at least one of a position sensor, a geo sensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, or a heart rate sensor included on or within the wearable device. The method is executed by a computer according to any one of claims 1 to 5.

9. The computing system estimating the ambient air temperature based at least in part on the first estimated value of the skin temperature and the internal device temperature is The computing system includes adjusting the ambient air temperature based at least in part on sleep data of the user collected by the wearable device. The method is executed by a computer according to any one of claims 1 to 5.

10. The computing system improving the first estimated value of the skin temperature based at least in part on the estimated ambient air temperature to generate a second estimated value of the skin temperature includes modifying a confidence value associated with the second estimated value of the skin temperature. The method is executed by a computer according to any one of claims 1 to 9.

11. Modifying the confidence value associated with the second estimated value of the skin temperature includes increasing the confidence value as a temperature difference between the first estimated value of the skin temperature and the internal device temperature decreases. The method is executed by a computer according to claim 10.

12. The first sensor is configured to physically contact the user. The method is executed by a computer according to any one of claims 1 to 11.

13. A wearable device, A device housing configured to be worn by a user, A computer included in the device housing and having one or more processors, A first sensor included on or in the device housing and configured to generate skin temperature sensor data A second sensor included in or on the device housing and configured to generate internal device temperature sensor data, wherein the first sensor, the second sensor, or both include at least one of a position sensor, a geo sensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, or a heart rate sensor included in or on the wearable device. A wearable device included in the device housing and having a non-transitory computer-readable memory storing instructions that, when executed by the one or more processors, cause the wearable device to perform the method executed by a computer according to any one of claims 1 to 12. **Claim 14** A method executed by a computer for providing skin temperature monitoring, the method comprising: A computing system including one or more computing devices determining an internal device temperature of the wearable device based on internal sensor data received from a first sensor included in or on the wearable device worn by a user. The computing system determining a first estimate of the skin temperature of the user based on skin sensor data received from a second sensor included in or on the wearable device, wherein the first sensor, the second sensor, or both include at least one of a position sensor, a geo sensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, or a heart rate sensor included in or on the wearable device, and the method further comprises: The computing system improving the first estimate of the skin temperature based at least in part on the internal device temperature of the wearable device to generate a second estimate of the skin temperature. The computing system determining one or more physiological events based at least in part on the second estimate of the skin temperature. **Claim 15** The computing system improving the first estimate of the skin temperature based at least in part on the internal device temperature of the wearable device comprises: processing the first estimate of the skin temperature and the internal device temperature with a machine learning model; receiving, as a prediction output by the machine learning model, the second estimate of the skin temperature, the method executed by a computer according to claim 14.

16. The computing system improving the first estimate of the skin temperature at least partially based on the internal device temperature of the wearable device to generate a second estimate of the skin temperature comprises modifying a confidence value associated with the second estimate of the skin temperature, the method executed by a computer according to claim 14.

17. Modifying the confidence value associated with the second estimate of the skin temperature comprises decreasing the confidence value as the temperature difference between the first estimate of the skin temperature and the internal device temperature increases, the method executed by a computer according to claim 16.

18. Improving the first estimate of the skin temperature at least partially based on the internal device temperature of the wearable device to generate a second estimate of the skin temperature further comprises adjusting the second estimate of the skin temperature at least partially based on additional sensor data from the first sensor, the second sensor, or a third sensor, the third sensor including at least one of a position sensor, a geo sensor, a weather sensor, a motion sensor, an altitude sensor, an altimeter temperature sensor, an ambient light sensor, or a heart rate sensor included in the wearable device, the method executed by a computer according to claim 14.

19. The one or more physiological events include at least one of the onset of fever, circadian rhythm, menstrual cycle, ovulation, heat stress, and thermal comfort, the method executed by a computer according to claim 14.

20. A program including instructions that, when executed by one or more processors of a computer, cause the computer to implement the method executed by a computer according to any one of claims 1 to 12 and claims 14 to 19.

Images