Interactive methods to improve measurement accuracy of wearable devices

By using a PPG sensor to detect motion artifacts and guiding users to create controlled motion artifacts, the method improves the accuracy of wearable device readings, addressing the challenge of motion artifacts and enhancing user experience with wearable devices.

WO2024235471A1PCT designated stage expired Publication Date: 2024-11-21HUAWEI TECH CO LTD +1
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
PCT/EP2023/063342
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Wearable devices often suffer from inaccurate physiological data readings due to motion artifacts, which existing solutions fail to effectively filter out, especially when the watch band strap is too loose or during physical activity.

Method used

The method involves using a PPG sensor to detect changes in blood flow and unwanted motion artifacts, providing users with instructions to create controlled motion artifacts detectable by a motion sensor, allowing for accurate determination of the attachment's tightness or looseness, and offering feedback through visual, auditory, and haptic elements to correct the attachment.

Benefits of technology

This approach enhances measurement accuracy by eliminating the impact of unintentional motion artifacts, providing a flexible and effective solution that does not require complex calibration procedures, resulting in improved user experience and consistent health data readings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2023063342_21112024_PF_FP_ABST
    Figure EP2023063342_21112024_PF_FP_ABST
Patent Text Reader

Abstract

A method and system for improving measurement accuracy of a wearable device (2) comprising a health sensor (3), a motion sensor (4), and attachment means (5). The method includes detecting uncontrolled motion artifacts (13) in the health sensor signal (12) indicating inaccurate readings of the health sensor (3); and intentionally creating controlled motion artifacts (16) through various hand gestures (15) of a user (1) to be detected by the motion sensor (4), and thereby allowing to calibrate optimal tightness of the attachment means (5) to eliminate the impact of the uncontrolled motion artifacts (13) on physiological data readings.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] INTERACTIVE METHODS TO IMPROVE MEASUREMENT ACCURACY OF WEARABLE DEVICES

[0002] TECHNICAL FIELD

[0003] The disclosure relates to wearable devices, and more particularly systems and methods to improve measurement accuracy of physiological data sensors in wearable devices.

[0004] BACKGROUND

[0005] Wearable devices that measure physiological parameters often suffer from motion artifacts, which can lead to inaccurate readings. To minimize motion artifacts, wearable devices incorporate various features, such as motion sensors, adhesive materials, and algorithms that filter out or correct for erroneous data. However, these solutions may not be effective in all situations, especially when attachment means, such as a watch band strap is too loose, or when the user is engaged in physical activity.

[0006] US2017075426A1 describes a smart watch with a wristband having a hybrid sensor that includes photoplethysmographic (PPG) and PZE sensor. The hybrid sensor detects gestures and band tightness. The smart watch continuously captures a PPMG signal and performs low- power analysis of the signal to detect probable gesture activity. The user adjusts the wristband having the PPMG sensor from a baseline fit level to tighter fit levels over time. However, this solution only focuses on improving gesture detection accuracy.

[0007] US20200000351A1 describes a smart watch having a PPG sensor. An optimal wristband tightness pressure for PPG can be measured and audio feedback can be provided to help the user adjust the wrist band tightness to an optimal pressure and optimize the PPG readings. In this prior art solution the PPG sensor reading itself is slightly improved but there is no disclosure about eliminating motion artifacts.

[0008] US2020146629A describes a wearable device wherein in a reference wearing position the target physiological parameter detected by the wearable device is accurate. The accuracy of measuring the target physiological parameter can be improved by using a PPG signal but there is no disclosure about eliminating motion artifacts to improve measurement accuracy. The smartwatch simply informs the user on the display interface that the current wearing position is excessively tight, and the user needs to loosen the tightness of the wristband. US2016255944A describes a wearable electronic device wherein health data is obtained from a PPG sensor with improved quality and accuracy. In this solution the PPG sensor detects tightness and requests to return the fit of the wearable electronic device to the user's preferred fit.

[0009] None of the described prior art solutions are capable of filtering out unwanted motion artifacts in physiological data measurement via an interactive method to improve measurement accuracy of the wearable device.

[0010] SUMMARY

[0011] It is an object to provide an improved method and device for improving measurement accuracy of a wearable device which overcomes or at least reduces the problems mentioned above, such as inaccurate sensor readings due to motion artifacts, and challenges with tight or loose watch band straps during physical activity.

[0012] The proposed solution overcomes the above problems by intentionally creating controlled motion artifacts to eliminate the impact of unintentional motion artifacts on physiological data and provide more accurate readings to the user. The proposed method and device use a PPG sensor to measure changes in blood flow and unwanted motion artifacts. The device can then provide instructions to the user to create controlled motion artifacts based on the type of motion artifacts that are present. The user can then perform specific gestures to introduce controlled motion artifacts detectable by a motion sensor, which allows accurate determination of how loose or tight the attachment of the wearable device is, which can then be corrected by providing feedback via visual, auditory, and haptic elements.

[0013] The foregoing and other objects are achieved by the features of the independent claims. Further implementation forms are apparent from the dependent claims, the description and the figures.

[0014] According to a first aspect, there is provided a computer implemented comprising the steps of receiving a health sensor signal from a health sensor of a wearable device, the health sensor signal comprising physiological data readings of a user of the wearable device; detecting uncontrolled motion artifacts in the health sensor signal indicating inaccurate readings of the health sensor; providing controlled motion instructions for the user of the wearable device for creating controlled motion artifacts detectable by a motion sensor of the wearable device; receiving a motion sensor signal from the motion sensor, the motion sensor signal comprising the controlled motion artifacts; determining a state of the attachment means of the wearable device by analyzing the motion sensor signal; and providing feedback for the user based on the state of the attachment means.

[0015] Such a method provides a unique and practical approach to addressing the challenge of the effect of motion artifacts on physiological data readings in wearable devices, and thereby and for providing more accurate readings to the user. The intentional creation of controlled motion artifacts provides a more flexible and effective solution that can be tailored to different types of motion artifacts and does not necessarily require the user to adjust the band strap, which may not be feasible in all situations, such as during physical activity or when the user prefers to wear the device more loosely. The solution thus increases the efficiency of physiological data measurement by eliminating the need for complex calibration procedures, which results in an overall enhanced user experience with wearable devices.

[0016] In a possible implementation form of the first aspect detecting the uncontrolled motion artifacts in the health sensor signal is based on continuously monitoring the health sensor signal and detecting abnormal physiological data readings outside of a predefined normal physiological data range.

[0017] In a further possible implementation form of the first aspect detecting the uncontrolled motion artifacts further comprises assigning a type for the uncontrolled motion artifacts based on the divergence from the normal physiological data range, and wherein the controlled motion instructions are based on the type of uncontrolled motion artifacts detected in the health sensor signal, so that the solution can be tailored for different situations, and during physical activities.

[0018] In one embodiment the wearable device is configured to be attached to the hand of the user.

[0019] In a possible implementation form of the first aspect the state of the attachment means of the wearable device corresponds to the attachment means being arranged too tight, too lose, or correctly on the hand of the user; and providing the controlled motion instructions for the user comprises instructing the user to perform a hand gesture to introduce the controlled motion artifacts in the sensor signal, thereby providing an easy to understand and interactive method for the user to get more accurate device readings, which results in an interactive and intuitive feedback system.

[0020] The ability to provide feedback to the user about the tightness of the watch strap can also help ensure that the sensors are properly positioned for accurate health data measurement. In a possible implementation form of the first aspect the hand gesture comprises horizontally rotating the hand or waving the hand by moving the hand in the air, thereby providing an easy to understand and interactive method for the user.

[0021] In another possible implementation form of the first aspect the hand gesture comprises opening and closing the fist, thereby providing another easy to understand and interactive method for the user.

[0022] Both these options offer a user-friendly and practical method to introduce controlled motion artifacts in physiological data measurement, and enable tailored and precise control of motion artifacts based on the instructions provided by the device.

[0023] In a possible implementation form of the first aspect the health sensor is a PPG sensor which allows monitoring blood volume changes in the microvascular system, thereby providing valuable health data for the user.

[0024] In a possible implementation form of the first aspect the motion sensor is an accelerometer, and wherein the motion sensor signal comprises acceleration data readings resulting from motion of the wearable device, thereby providing an accurate way of sensing the motion of the wearable device.

[0025] In a possible implementation form of the first aspect the state of the attachment means of the wearable device corresponds to the attachment means being arranged too tight, too lose, or correctly on a body part of the user; and if the state of the attachment means is determined to be too tight or too lose, the method further comprises providing adjustment instructions for the user for loosening or tightening the attachment means respectively. This allows for easy correction of data readings through an interactive adjustment.

[0026] In a possible implementation form of the first aspect the method further comprises, after providing the adjustment instructions, providing second controlled motion instructions for creating second controlled motion artifacts detectable by the motion sensor of the wearable device; receiving an adjusted motion sensor signal from the motion sensor comprising the second controlled motion artifacts; determining an adjusted state of the attachment means of the wearable device by analyzing the adjusted motion sensor signal; and providing feedback for the user based on the adjusted state of the attachment means; wherein if the adjusted state of the attachment means is determined to be too tight or too lose, the feedback comprises further instructions for the user for loosening or tightening the attachment means respectively and for creating adjusted controlled motion artifacts, and the method comprises repeating the steps until the adjusted state of the attachment means is determined to be correct; and wherein if the adjusted state of the attachment means is determined to be correct, the feedback comprises a notification for the user of successful completion of the calibration process. This allows for a simple but effective iterative adjustment process for the user until accurate health data readings are possible. The continuous and iterative calibration also helps ensuring that the user is getting accurate and consistent health data readings over time.

[0027] In a possible implementation form of the first aspect the feedback for the user comprises physiological data readings based on the health sensor signal; and an indication of accuracy of the physiological data readings of the health sensor corresponding to the state of the attachment means of the wearable device, thereby helping the user easily assessing accuracy of the health readings and draw the correct health related conclusions.

[0028] In a possible implementation form of the first aspect providing the feedback comprises providing at least one of a visual feedback via a user interface, auditory feedback via an audio interface, or haptic feedback via haptic actuators arranged in the wearable device. These alternative feedback options can provide real-time feedback for a wide demographic, with various abilities or impediments.

[0029] According to a second aspect, there is provided a wearable device comprising a health sensor; a motion sensor; attachment means; a feedback unit; and a control unit configured to receive a health sensor signal from the health sensor, the health sensor signal comprising physiological data readings of a user of the wearable device; detect uncontrolled motion artifacts in the health sensor signal indicating inaccurate readings of the health sensor; provide controlled motion instructions for the user of the wearable device via the feedback unit for introducing controlled motion artifacts detectable by a motion sensor of the wearable device; receive a motion sensor signal from the motion sensor, the motion sensor signal comprising the controlled motion artifacts; determine a state of the attachment means of the wearable device by analyzing the motion sensor signal; and provide feedback for the user via the feedback unit based on the state of the attachment means.

[0030] Such a wearable device provides a unique and practical approach to addressing the challenge of the effect of motion artifacts on physiological data readings, and thereby and for providing more accurate readings to the user. The intentional creation of controlled motion artifacts provides a more flexible and effective solution that can be tailored to different types of motion artifacts and does not necessarily require the user to adjust the band strap, which may not be feasible in all situations, such as during physical activity or when the user prefers to wear the device more loosely.

[0031] In a possible implementation form of the second aspect the motion sensor is an accelerometer, wherein the motion sensor signal comprises acceleration data readings resulting from motion of the wearable device, thereby providing an accurate way of sensing the motion of the wearable device.

[0032] In a possible implementation form of the second aspect the feedback unit comprises at least one of a user interface configured for providing visual feedback for a user, such as a display of the wearable device itself, or a display of a connected device such as a smartphone; an audio interface configured for providing auditory feedback for the user, such as a speaker of the wearable device itself, a speaker of a connected device such as a smartphone, or a connected wireless audio device; or haptic actuators arranged in the wearable device and configured for providing haptic feedback, such as vibration or pulsation, for the user. These alternative feedback units can provide solutions for a wide demographic, with various abilities or impediments.

[0033] These and other aspects will be apparent from and the embodiment(s) described below.

[0034] BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In the following detailed portion of the present disclosure, the aspects, embodiments and implementations will be explained in more detail with reference to the example embodiments shown in the drawings, in which:

[0036] Fig. 1 shows a flow diagram of a method for improving measurement accuracy of a wearable device in accordance with an example of the embodiments of the disclosure;

[0037] Fig. 2 shows a side view of a wearable device in accordance with an example of the embodiments of the disclosure;

[0038] Fig. 3 illustrates different possible embodiments of a feedback unit in a wearable device in accordance with exemplary embodiments of the disclosure;

[0039] Fig. 4 shows a flow diagram of providing instructions for a userfor hand gestures in accordance with exemplary embodiments of the disclosure;

[0040] Fig. 5 shows a flow diagram of an iterative method for improving measurement accuracy of a wearable device in accordance with an example of the embodiments of the disclosure;

[0041] Fig. 6 illustrates in a block diagram the main components of a wearable device in accordance with an example of the embodiments of the disclosure; and Figs. 7 and 8 illustrate wearing tightness detection test results using different hand gestures in accordance with exemplary embodiments of the disclosure.

[0042] DETAILED DESCRIPTION

[0043] In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant disclosure. However, it should be apparent to those skilled in the art that the present disclosure may be practiced without such details. In other instances, well known methods, procedures, systems, components, and / or circuitry have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present disclosure.

[0044] In the descriptions of the individual figures below, steps and features that are the same or similar to corresponding steps and features previously described or shown herein are denoted by the same reference numeral as previously used for simplicity.

[0045] Fig. 1 illustrates a simplified flowchart of a computer-implemented method for improving measurement accuracy of a wearable device 2 according to an example of the disclosure.

[0046] As shown in Fig. 2, the wearable device 2 comprises a health sensor 3, a motion sensor 4, and attachment means 5 for attaching to a body part of a user 1 , as well as s feedback unit 6 for providing feedback to the user 1 regarding the state of the attachment means 5 as will be described below.

[0047] As shown in Fig. 1 , the method includes receiving a health sensor signal 12 from the health sensor 3 of the wearable device 2, the health sensor signal 12 comprising physiological data readings of the user 1.

[0048] The health sensor 3 can be a PPG sensor configured to measure changes in blood flow and detect motion artifacts in the physiological data, wherein the health sensor signal 12 is an optically obtained plethysmogram that allows to monitor blood volume changes in the microvascular system. Conventional PPG sensors comprise two main components: lightemitting diodes (LEDs) and photodetectors (PDs).

[0049] The health sensor signal 12 is continuously monitored to detect abnormal physiological data readings outside of a predefined normal physiological data range indicating inaccurate readings of the health sensor 3. These abnormal physiological data readings are linked to uncontrolled motion artifacts 13 which can originate from various physical activity of the user, such as working out or running, if the attachment means 5 is not holding the health sensor 3 at an optimal distance from the skin if the user 1 , as shown in for example in Fig. 2.

[0050] Once such uncontrolled motion artifacts 13 are detected in the health sensor signal 12, an alert message is provided to the user 1 on the wearable device 2, together with controlled motion instructions 14 for creating controlled motion artifacts 16 detectable by the motion sensor 4 of the wearable device 2.

[0051] The motion sensor 4 can be an accelerometer, wherein the motion sensor signal 17 comprises acceleration data readings resulting from motion of the wearable device 2 that are received in the form of a motion sensor signal 17.

[0052] In the motion sensor signal 17 the controlled motion artifacts 16 created by the user 1 can be detected and, based on previous calibrations done on the device 2 either before purchase or done by the user 1 as part of an initial setup, a state 18 of the attachment means 5 of the wearable device 2 can be determined by analyzing the motion sensor signal 17 and comparing the motion sensor signal 17 to pre-recorded patterns linked to different predefined states 18.

[0053] The state 18 of the attachment means 5 of the wearable device 2 can correspond to the attachment means 5 being arranged too tight, too lose, or correctly on the body part, such as the hand of the user 1 .

[0054] Once the state 18 of the attachment means 5 is determined a feedback 19 is provided for the user 1 as will be explained below, indicating a need for calibration.

[0055] In essence, the disclosed method helps to improve measurement accuracy of the wearable device 2 by intentionally creating controlled motion artifacts 16 to eliminate the impact of uncontrolled motion artifacts 13 on physiological data readings, and thereby results in more accurate readings to the user 1.

[0056] Fig. 3 illustrates different alternatives for communicating with the user 1 via a feedback unit 6 of the wearable device 2. The feedback unit 6 is designed to work in conjunction with the controlled motion artifact 16 creation to provide the user 1 with the necessary information to adjust and improve the accuracy of health data readings. The feedback unit 6 may include any or all of visual, auditory, and haptic elements to provide a multi-sensory experience for the user 1. When the device detects uncontrolled motion artifacts 13 during data collection, it can provide visual feedback via a user interface 8, such as a display screen of the wearable device 2 or a linked terminal device 11 such as a touch screen of a smartphone, to alert the user of the issue. The user interface 8 can be the same interface used to provide detailed health data. In addition, the device's user interface 8 can display a message or icon indicating the tightness or looseness of a watch strap and the accuracy of the health data readings.

[0057] An audio interface 9 can provide auditory feedback (i.e. , a beep or tone) to alert the user to changes in their physiological data readings and then provide controlled motion instructions 14 or adjustment instructions 20 in the form of spoken instructions to guide the user 1 on how to adjust their movements or watch strap.

[0058] Alternatively, or in addition, haptic actuators 10 arranged in the wearable device can provide haptic feedback, such as vibration or pulsation, to the user 1 both to alert them of the uncontrolled motion artifacts 13 and need for calibration, as well as to notify the user 1 upon the (un)successful completion of the calibration process.

[0059] Fig. 4 illustrates alternative examples for providing controlled motion instructions 14 for the user 1 , by instructing the user 1 to perform different hand gestures 15 to introduce the controlled motion artifacts 16 in the sensor signal.

[0060] The device 2 first displays a notification on the user interface 2, instructing the user 1 to to perform different hand gesture 15. This hand gesture 15 creates a controlled motion artifact 16 that can be used to calibrate and improve the accuracy of the health sensor 3 (i.e., PPG) data. The motion sensor(s) 4 of the device 2, such as an accelerometer and / or gyroscope can detect the motion of the hand and calculate the level of controlled motion artifacts 16 that are being generated.

[0061] One example of a hand gesture 15 is moving the hand in a specific manner based on instructions from the watch 2 to determine the tightness or looseness of the watch strap 5, such as by horizontally rotating the hand or waving the hand. The user 1 can perform this gesture 15 in different ways to introduce controlled motion artifacts 15 that can help counteract the impact of uncontrolled motion artifacts 13 on the physiological data. The device 2 can then provide feedback 19 to the user 1 based on the tightness or looseness of the watch strap 5 and optionally also about the accuracy of the health data readings. Another hand gesture 15 involves opening and closing the fist in a specific way to reduce uncontrolled motion artifacts 13 and improve the accuracy of health data. The device 2 can provide instructions on how to perform this gesture and when to do so. The user 1 can then perform this gesture 15 to introduce controlled motion artifacts 16 that can help filter out uncontrolled motion artifacts 13 and improve the accuracy of the health data.

[0062] In an example, a type information can be assigned for the uncontrolled motion artifacts 13 based on the divergence from the normal physiological data range in the health sensor signal 12, and this type information can be used for providing various types of controlled motion instructions 14 for the user 1 .

[0063] For example, the uncontrolled motion artifacts 13 can indicate that the strap 5 is too loose, in which case controlled motion instructions 14 would include a hand gesture 15 of horizontally rotating the hand.

[0064] In another example, the uncontrolled motion artifacts 13 can indicate that the strap 5 is too tight, in which case controlled motion instructions 14 would include a hand gesture 15 of opening and closing the fist.

[0065] Fig. 5 shows a flow diagram of an iterative method that helps ensuring that the user 1 is getting accurate and consistent health data readings over time.

[0066] As described before, the device 2 can detect if the attachment means 5, for example a watch strap, is too tight or too loose and provide feedback 19 to perform a calibration. Once the state 18 of the attachment means 5 is determined to be too tight or too lose, the device 2 can provide adjustment instructions 20 on how to adjust the strap (i.e. to loosen or tighten the strap) and when to do so, depending on the type and severity of the uncontrolled motion artifacts 13 present in the health sensor signal 12.

[0067] The iterative process includes, after providing the adjustment instructions 20, providing second controlled motion instructions 21 for creating second controlled motion artifacts 16 detectable by the motion sensor 4 of the wearable device 2, in order to confirm whether the adjustment by the user 1 was successful.

[0068] In order to do this, an adjusted motion sensor signal 22 is received from the motion sensor 4 comprising the second controlled motion artifacts 16, and an adjusted state 23 of the attachment means 5 of the wearable device 2 is determined by analyzing the adjusted motion sensor signal 22, similarly as described before.

[0069] If the adjusted state 23 of the attachment means 5 is determined to be too tight or too lose, further instructions 24 are communicated for the user 1 for loosening or tightening the attachment means 5 respectively and for creating adjusted controlled motion artifacts 16. The process includes repeating these steps until the adjusted state 23 of the attachment means 5 is determined to be correct.

[0070] The device 2 provides feedback 19 in form of a notification 25 for the user 1 of successful completion of the calibration process.

[0071] The device 2 then continues to monitor the physiological data and provides feedback 19 to the user on the optimal tightness of the strap throughout the day to ensure accurate readings.

[0072] Fig. 6 illustrates in a block diagram the main components of a wearable device 2 in accordance with an example of the disclosure. The wearable device 2 comprises, as described before, a health sensor 3, a motion sensor 4, attachment means 5, and a feedback unit 6. The feedback unit 6 can be any or all of a user interface 8 configured for providing visual feedback for a user 1 , an audio interface 9 configured for providing auditory feedback for the user 1 , or haptic actuators 10 arranged in the wearable device 2 and configured for providing haptic feedback for the user 1 .

[0073] The wearable device 2 further comprises a control unit 7 configured to execute the process steps described before, i.e. to receive a health sensor signal 12 from the health sensor 3, the health sensor signal 12 comprising physiological data readings of a user 1 of the wearable device 2; to detect uncontrolled motion artifacts 13 in the health sensor signal 12 indicating inaccurate readings of the health sensor 3; to provide controlled motion instructions 14 for the user 1 of the wearable device 2 via the feedback unit 6 for introducing controlled motion artifacts 16 detectable by a motion sensor 4 of the wearable device 2; to receive a motion sensor signal 17 from the motion sensor 4, the motion sensor signal 17 comprising the controlled motion artifacts 16; to determine a state 18 of the attachment means 5 of the wearable device 2 by analyzing the motion sensor signal 17; and to provide feedback 19 for the user 1 via the feedback unit 6 based on the state 18 of the attachment means 5.

[0074] Generally, the word “module”, “unit,” or “block,” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions. A module, a unit, or a block described herein may be implemented as software and / or hardware and may be stored in any type of non-transitory computer-readable medium or other storage device. In some embodiments, a software module / unit / block may be compiled and linked into an executable program. It will be appreciated that software modules can be callable from other modules / units / blocks or from themselves, and / or may be invoked in response to detected events or interrupts. Software modules / units / blocks configured for execution on computing devices (e.g., control unit 7 as illustrated in FIG. 6) may be provided on a computer readable medium, such as a compact disc, a digital video disc, a flash drive, a magnetic disc, or any other tangible medium, or as a digital download (and can be originally stored in a compressed or installable format that needs installation, decompression, or decryption prior to execution). Such software code may be stored, partially or fully, on a storage device of the executing computing device, for execution by the computing device. Software instructions may be embedded in a firmware, such as an EPROM. It will be further appreciated that hardware modules / units / blocks may be included of connected logic components, such as gates and flipflops, and / or can be included of programmable units, such as programmable gate arrays or processors. The modules / units / blocks or computing device functionality described herein may be implemented as software modules / units / blocks, but may be represented in hardware or firmware. In general, the modules / units / blocks described herein refer to logical modules / units / blocks that may be combined with other modules / units / blocks or divided into sub-modules / sub-units / sub-blocks despite their physical organization or storage.

[0075] It will be understood that when a unit, module or engine is referred to as being “on”, “connected to” or “coupled to” another unit, module, or engine, it may be directly on, connected or coupled to, or communicate with the other unit, module, or engine, or an intervening unit, module, or engine may be present, unless the context clearly indicates otherwise. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0076] Figs. 7 and 8 illustrate wearing tightness detection test results using different hand gestures in accordance with exemplary embodiments of the disclosure.

[0077] The total accelerometer rms results for both the horizontal wrist rotation and opening / closing the fist gesture decrease as the tightness of the smartwatch strap 5 increases. This suggests that both hand gestures 15 are capable of detecting differences in strap tightness using accelerometer data.

[0078] The range of values for each hand gesture 15 and tightness level is distinct enough to allow for accurate detection of different levels of strap tightness. This means that the device 2 can reliably distinguish between different levels of tightness and provide feedback 19 to the user 1 . The range of values for the horizontal wrist rotation gesture is larger than that for the fist open / close gesture, indicating that the horizontal wrist rotation gesture may be more sensitive to changes in strap tightness.

[0079] Based on the range of values seen in the test results, the inventors concluded that both the horizontal wrist rotation and fist open / close gestures are effective in detecting different levels of smartwatch strap tightness but they differ in their sensitivity and ability to distinguish between different levels of tightness.

[0080] The horizontal wrist rotation gesture appears to be more sensitive to changes in strap tightness and has a larger range of values, indicating that it may be more suitable for detecting subtle changes in tightness. This gesture may be more useful for detecting loose fit, but it can also be effective in detecting moderate and tight fit.

[0081] On the other hand, the fist open / close gesture has a smaller range of values, but it may be more suitable for distinguishing between different levels of tightness. This gesture may be more useful for detecting tight fit, but it can also be effective in detecting moderate and loose fit.

[0082] The various aspects and implementations have been described in conjunction with various embodiments herein. However, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed subject-matter, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measured cannot be used to advantage. A computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0083] The reference signs used in the claims shall not be construed as limiting the scope.

Claims

CLAIMS1. A computer-implemented method for improving measurement accuracy of a wearable device (2) comprising a health sensor (3), a motion sensor (4), and attachment means (5), the method comprising: receiving a health sensor signal (12) from a health sensor (3) of a wearable device (2), the health sensor signal (12) comprising physiological data readings of a user (1) of the wearable device (2); detecting uncontrolled motion artifacts (13) in the health sensor signal (12) indicating inaccurate readings of the health sensor (3); providing controlled motion instructions (14) for the user (1) of the wearable device (2) for creating controlled motion artifacts (16) detectable by a motion sensor (4) of the wearable device (2); receiving a motion sensor signal (17) from the motion sensor (4), the motion sensor signal (17) comprising said controlled motion artifacts (16); determining a state (18) of the attachment means (5) of the wearable device (2) by analyzing said motion sensor signal (17); and providing feedback (19) for the user (1) based on the state (18) of the attachment means (5).

2. The method according to claim 1 , wherein detecting said uncontrolled motion artifacts (13) in the health sensor signal (12) is based on continuously monitoring the health sensor signal (12) and detecting abnormal physiological data readings outside of a predefined normal physiological data range.

3. The method according to claim 2, wherein detecting said uncontrolled motion artifacts (13) further comprises assigning a type for said uncontrolled motion artifacts (13) based on the divergence from said normal physiological data range, and wherein said controlled motion instructions (14) are based on the type of uncontrolled motion artifacts (13) detected in the health sensor signal (12).

4. The method according to any preceding claim, wherein the wearable device (2) is configured to be attached to the hand of the user (1); wherein said state (18) of the attachment means (5) of the wearable device (2) corresponds to the attachment means (5) being arranged too tight, too lose, or correctly on the hand of the user (1); andwherein providing said controlled motion instructions (14) for the user (1) comprises instructing the user (1) to perform a hand gesture (15) to introduce said controlled motion artifacts (16) in the sensor signal.

5. The method according to claim 4, wherein the hand gesture (15) comprises horizontally rotating the hand or waving the hand by moving the hand in the air.

6. The method according to claim 4, wherein the hand gesture (15) comprises opening and closing the fist.

7. The method according to any preceding claim, wherein the health sensor (3) is a PPG sensor configured to monitor blood volume changes in the microvascular system.

8. The method according to any preceding claim, wherein the motion sensor (4) is an accelerometer, and wherein the motion sensor signal (17) comprises acceleration data readings resulting from motion of the wearable device (2).

9. The method according to any preceding claim, wherein said state (18) of the attachment means (5) of the wearable device (2) corresponds to the attachment means (5) being arranged too tight, too lose, or correctly on a body part of the user (1); and wherein if the state (18) of the attachment means (5) is determined to be too tight or too lose, the method further comprises: providing adjustment instructions (20) for the user (1) for loosening or tightening said attachment means (5) respectively.

10. The method according to claim 9, wherein the method further comprises, after providing said adjustment instructions (20): providing second controlled motion instructions (21) for creating second controlled motion artifacts (16) detectable by the motion sensor (4) of the wearable device (2); receiving an adjusted motion sensor signal (22) from the motion sensor (4) comprising said second controlled motion artifacts (16); determining an adjusted state (23) of the attachment means (5) of the wearable device (2) by analyzing said adjusted motion sensor signal (22); and providing feedback (19) for the user (1) based on the adjusted state (23) of the attachment means (5);wherein if the adjusted state (23) of the attachment means (5) is determined to be too tight or too lose, the feedback (19) comprises further instructions (24) for the user (1) for loosening or tightening said attachment means (5) respectively and for creating adjusted controlled motion artifacts (16), and the method comprises repeating the steps until the adjusted state (23) of the attachment means (5) is determined to be correct; and wherein if the adjusted state (23) of the attachment means (5) is determined to be correct, the feedback (19) comprises a notification (25) for the user (1) of successful completion of the calibration process.

11. The method according to any preceding claim, wherein said feedback (19) for the user (1) comprises physiological data readings based on the health sensor signal (12); and an indication of accuracy of the physiological data readings of the health sensor (3) corresponding to the state (18) of the attachment means (5) of the wearable device (2).

12. The method according to any preceding claim, wherein providing said feedback (19) comprises providing at least one of: visual feedback via a user interface (8), auditory feedback via an audio interface (9), or haptic feedback via haptic actuators (10) arranged in the wearable device (2).

13. A wearable device (2) comprising: a health sensor (3); a motion sensor (4); attachment means (5); a feedback unit (6); and a control unit (7) configured to receive a health sensor signal (12) from the health sensor (3), the health sensor signal (12) comprising physiological data readings of a user (1) of the wearable device (2); detect uncontrolled motion artifacts (13) in the health sensor signal (12) indicating inaccurate readings of the health sensor (3); provide controlled motion instructions (14) for the user (1) of the wearable device (2) via said feedback unit (6) for introducing controlled motion artifacts (16) detectable by a motion sensor (4) of the wearable device (2); receive a motion sensor signal (17) from the motion sensor (4), the motion sensor signal (17) comprising said controlled motion artifacts (16); determine a state (18) of the attachment means (5) of the wearable device (2) by analyzing said motion sensor signal (17); andprovide feedback (19) for the user (1) via said feedback unit (6) based on the state (18) of the attachment means (5).

14. The wearable device (2) according to claim 13, wherein the motion sensor (4) is an accelerometer, and wherein the motion sensor signal (17) comprises acceleration data readings resulting from motion of the wearable device (2).

15. The wearable device (2) according to any one of claims 13 or 14, wherein said feedback unit (6) comprises at least one of: - a user interface (8) configured for providing visual feedback for a user (1), an audio interface (9) configured for providing auditory feedback for the user (1), or haptic actuators (10) arranged in the wearable device (2) and configured for providing haptic feedback for the user (1).

Citation Information

Patent Citations

  • Dynamic Fit Adjustment for Wearable Electronic Devices

    US20160255944A1

  • Techniques for gesture recognition using photoplethysmographic (PPMG) sensor and low-power wearable gesture recognition device using the same

    US20170075426A1

  • Smart watch accessory for improved PPG heart rate reading

    US20200000351A1

  • Wearing prompt method for wearable device and apparatus

    US20200146629A1

  • Methods and apparatus for improving signal quality in wearable biometric monitoring devices

    EP3804612A1