Wearable computing device with optical sensor for indirectly determining position of force applied to user interface

Abstract

A wearable computing device includes a housing having an upper side and an underside, wherein the underside of the housing is opposite the upper side of the housing and is configured to contact a body part of a user when the wearable computing device is worn by the user. The wearable computing device also includes a user interface disposed on an upper side of the housing. The wearable computing device also includes a sensor disposed on the underside of the housing that outputs one or more optical readings when a force is applied to the user interface. The wearable computing device also includes one or more processors that determine a location at which a force is applied to the user interface based on the one or more optical readings output by the sensor.

Description

Technical Field

[0001] The present disclosure relates generally to wearable computing devices and more particularly to wearable computing devices that can use optical sensors to determine the location of a force applied to a user interface of the wearable computing device. Background Art

[0002] A wearable computing device (e.g., a wristwatch) may include a display for displaying content to a user (e.g., the time, date, functionality of the wearable computing device, etc.). Some wearable computing devices may collect data about activities performed by a user or about a physiological state of the user. Such data may include data representing the surrounding environment surrounding the user or the user's interaction with the environment. For example, the data may include motion data about the user's movement and / or physiological data obtained by measuring various physiological characteristics of the user, such as heart rate, sweat level, etc. Some wearable computing devices may include touch-sensitive displays, while other wearable computing devices may include non-touch-sensitive displays. Summary of the invention

[0003] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the description which follows, or may be learned from the description, or may be learned by practicing example embodiments.

[0004] In an example embodiment, a wearable computing device is provided. The wearable computing device includes a housing having an upper side and a lower side, wherein the lower side of the housing is opposite to the upper side of the housing and is configured to contact a body part of the user when the wearable computing device is worn by the user. The wearable computing device also includes a user interface disposed on the upper side of the housing and a sensor disposed on the lower side of the housing. The sensor is configured to output one or more optical readings when a force is applied to the user interface. The wearable computing device may also include one or more processors configured to determine a location where a force is applied to the user interface based on the one or more optical readings output by the sensor.

[0005] In some implementations, the sensor may include a photoplethysmography (PPG) sensor configured to monitor a user's heart rate when the wearable computing device is worn by the user, and the PPG sensor includes one or more light emitting diodes and a plurality of detectors.

[0006] In some implementations, the sensor may include at least three photoplethysmography (PPG) sensors, and at least one of the at least three PPG sensors is spaced apart from another of the at least three PPG sensors in a first direction and a second direction.

[0007] In some implementations, the one or more processors may be configured to perform one or more functions of the wearable computing device based on the location at which the force is applied to the display as determined by the one or more processors.

[0008] In some implementations, one or more processors may be configured to determine the location where the force is applied to the user interface based on whether the area of ​​the user interface to which the force is applied corresponds to a first area or a second area, the first area being different from the second area. For example, the first area may be larger than the second area.

[0009] In some implementations, when the area of ​​the display where the force is applied corresponds to a first area, one or more processors may be configured to determine the magnitude of each of the one or more optical readings based on a first model having a first scale parameter that reflects a first variance of the force applied to the user interface, and when the area of ​​the display where the force is applied corresponds to a second area, one or more processors may be configured to determine the magnitude of each of the one or more optical readings based on a second model having a second scale parameter that reflects a second variance of the force applied to the user interface, the second variance being different from the first variance.

[0010] In some implementations, one or more processors may be configured to determine the position where the force is applied to the user interface based on the value of each of the optical readings output by the sensor and by applying a loss function to minimize the difference between the actual position where the force is applied and the estimated position where the force is applied. In such implementations, one or more processors may be configured to use the value of each of the one or more optical readings output by the sensor and the known (i.e., predefined and stored) position of the sensor to estimate the position where the force is applied by applying a loss function to determine the position where the force is applied to the user interface. Then, the estimated position obtained from minimizing the loss function can be used as the determined position where the force is applied. Specifically, determining the position where the force is applied can therefore include an estimate of the position obtained using the application of a loss function, wherein the loss function includes the value of each of the one or more optical readings and the known position of the sensor at the lower side of the housing of the wearable computing device. The loss function may also include a probability density function that determines the probability that the optical reading output by the optical sensor is corrupted by measurement noise. In some implementations, the probability density function may be a standard Gaussian function that is used to reconstruct the position of the force applied based on measurements from one or more sensors.

[0011] In some implementations, the one or more processors may be configured to apply the loss function by performing a two-dimensional grid search method or a gradient descent search method.

[0012] In some implementations, the user interface includes a non-touch-sensitive display configured to display a plurality of elements corresponding to a plurality of selectable functions of the wearable computing device. In response to an increase in a noise level of the sensor exceeding a threshold, the one or more processors may be configured to control the display to stop displaying one or more of the plurality of elements, and in response to determining that a location at which the force is applied to the display corresponds to a remaining first element of the plurality of elements displayed on the display, the one or more processors may also be configured to execute a first selectable function corresponding to the remaining first element of the plurality of selectable functions based on the determined location.

[0013] In some implementations, the user interface includes multiple imitation buttons, which respectively correspond to multiple selectable functions of the wearable computing device, and in response to determining a position where a force is applied to a first imitation button of the multiple imitation buttons of the user interface, one or more processors are configured to execute a first selectable function of the multiple selectable functions corresponding to the first imitation button based on the determined position.

[0014] In some implementations, the user interface includes a display, and the display is a non-touch sensitive display.

[0015] In some implementations, the sensor may include a photoplethysmography (PPG) sensor configured to monitor a user's heart rate when the wearable computing device is worn by the user, and the one or more processors may be configured to recognize a gesture of the user based on one or more optical readings output by the PPG sensor. The one or more processors may be configured to perform a function of the computer wearable device based on the gesture of the user recognized by the one or more processors.

[0016] In some implementations, the wearable computing device may also include at least one of an accelerometer or a gyroscope, and the one or more processors may be configured to recognize a gesture of the user based on one or more optical readings output by the PPG sensor and one or more outputs of at least one of the accelerometer or the gyroscope.

[0017] In an example embodiment, a computer-implemented method is provided. The computer-implemented method includes receiving (e.g., by one or more processors of the wearable computing device) an optical reading output by a sensor disposed on a lower side of the housing when a force is applied to a user interface disposed on an upper side of a housing of a wearable computing device. The lower side of the housing is opposite to the upper side of the housing and is configured to contact a body part of the user when the wearable computing device is worn by the user. The method may also include determining, by the one or more processors of the wearable computing device, a location where the force is applied to the user interface based on one or more received optical readings.

[0018] In some implementations, the method may also include executing one or more functions of the wearable computing device based on the location at which the force is applied to the user interface as determined by the one or more processors.

[0019] In some implementations, the method may also include displaying instructions on a display of the user interface instructing the user to calibrate the wearable computing device by indicating areas of the display to which forces are to be applied.

[0020] In some implementations, the method may also include: when the area of ​​force indicated by the user corresponds to a first area, determining the amplitude of each of the one or more optical readings based on a first model having a first scale parameter, the first scale parameter reflecting a first variance of the force to be applied to the display; and when the area of ​​force indicated by the user corresponds to a second area, determining the amplitude of each of the one or more optical readings based on a second model having a second scale parameter, the second scale parameter reflecting a second variance of the force to be applied to the display, the first area being larger than the second area, and the first variance being larger than the second variance.

[0021] In some implementations, the method may also include determining the location where the force is applied to the user interface based on the value of each of the optical readings output by the sensor and by applying a loss function to minimize the difference between the actual location where the force is applied and the estimated location where the force is applied.

[0022] In some implementations, the method may further include displaying, on a non-touch-sensitive display of the user interface, a plurality of elements corresponding to a plurality of selectable functions of the wearable computing device, and in response to an increase in a noise level of the sensor exceeding a threshold, controlling the display to stop displaying one or more of the plurality of elements, and in response to determining that a position at which the force is applied to the user interface corresponds to a remaining first element of the plurality of elements displayed on the display, executing a first selectable function of the plurality of selectable functions corresponding to the remaining first element based on the determined position.

[0023] In an example embodiment, a non-transitory computer-readable medium is provided that stores instructions executable by one or more processors of a wearable computing device. The non-transitory computer-readable medium stores instructions, including instructions that cause one or more processors to receive one or more optical readings output by a sensor disposed on a lower side of a housing of the wearable computing device when a force is applied to a user interface disposed on an upper side of the housing, wherein the lower side of the housing is opposite to the upper side of the housing and is configured to contact a body part of the user when the wearable computing device is worn by the user. The non-transitory computer-readable medium stores instructions, including instructions that cause one or more processors to determine a location where a force is applied to the user interface based on the one or more received optical readings. The non-transitory computer-readable medium stores instructions, including instructions to perform one or more functions of the wearable computing device based on the location where a force is applied to the user interface as determined by the one or more processors. The non-transitory computer-readable medium may store additional instructions for performing other aspects of the wearable computing device and computer-implemented methods as described herein.

[0024] These and other features, aspects and advantages of various embodiments of the present disclosure will be better understood with reference to the following description, drawings and appended claims.The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate example embodiments of the present disclosure and, together with the description, serve to explain the relevant principles. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] A detailed discussion of example embodiments for persons of ordinary skill in the art is set forth in this specification with reference to the accompanying drawings, in which:

[0026] Figure 1 An example wearable computing device according to one or more example embodiments of the present disclosure is depicted;

[0027] Figure 2 An exploded view of an example wearable computing device is described according to one or more example embodiments of the present disclosure;

[0028] Figure 3 An example block diagram depicting a wearable computing device according to one or more example embodiments of the present disclosure;

[0029] Figure 4A and Figure 4B depicts a top view of an example wearable computing device according to one or more example embodiments of the present disclosure;

[0030] Figure 4C depicts a bottom view of an example wearable computing device according to one or more example embodiments of the present disclosure;

[0031] Figure 5A and Figure 5B depicts a graph of forces applied to a display of a wearable computing device and a corresponding signal response of a sensor according to one or more example embodiments of the present disclosure;

[0032] Fig. 6A and Figure 6B depicts example compression Gaussian responses corresponding to different scale parameters according to one or more example embodiments of the present disclosure;

[0033] Fig. 7A and Figure 7B depicts example observations according to one or more example embodiments of the present disclosure;

[0034] Fig. 8A and Figure 8B depicts an example determination of a location of a force applied to a display based on a loss function result according to one or more example embodiments of the present disclosure;

[0035] Fig. 9A and Fig. 9B depicts another example determination of a location of a force applied to a display based on a loss function result according to one or more example embodiments of the present disclosure;

[0036] Fig. 10A and Fig. 10B depicts an example determination of the location of a force applied to a display based on a loss function result in a noisy environment according to one or more example embodiments of the present disclosure;

[0037] Fig.11 Depicting example response signals of various sensors of a wearable computing device for detecting a user's gesture according to one or more example embodiments of the present disclosure;

[0038] Fig. 12A and Fig. 12B depicts an example single-hand gesture of a user and a corresponding heat map reconstructed from a PPG sensor according to one or more example embodiments of the present disclosure; and

[0039] Fig.13 and Fig.14 Each shows a flow diagram of an example non-limiting computer-implemented method according to one or more example embodiments of the present disclosure. DETAILED DESCRIPTION

[0040] Reference will now be made to embodiments of the present disclosure, one or more examples of which are shown in the accompanying drawings. Each example is provided by way of explanation of the present disclosure and is not intended to limit the present disclosure. In fact, it will be apparent to those skilled in the art that various modifications and changes may be made to the present disclosure without departing from the scope or spirit of the present disclosure. For example, a feature shown or described as part of one embodiment may be used together with another embodiment to produce yet another embodiment. Therefore, the present disclosure is intended to cover modifications and changes within the scope of the appended claims and their equivalents.

[0041] The terms used herein are used to describe example embodiments and are not intended to limit and / or constrain the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular forms "one", "an", "said", and "the" are also intended to include plural forms. In the present disclosure, terms such as "including", "having", "comprising", etc. are used to specify features, numbers, steps, operations, elements, components, or combinations thereof, but do not exclude the presence or addition of one or more of features, elements, steps, operations, elements, components, or combinations thereof.

[0042] It will be understood that although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited to these terms. Instead, these terms are used to distinguish one element from another element. For example, without departing from the scope of the present disclosure, a first element may be referred to as a second element, and a second element may be referred to as a first element.

[0043] The term "and / or" includes a combination of multiple related listed items or any of the multiple related listed items. For example, the scope of the expression or phrase "A and / or B" includes the item "A", the item "B" and the combination of the items "A and B".

[0044] In addition, the scope of the expression or phrase "at least one of A or B" is intended to include all of the following: (1) at least one of A; (2) at least one of B; and (3) at least one of A and at least one of B. Likewise, the scope of the expression or phrase "at least one of A, B, or C" is intended to include all of the following: (1) at least one of A; (2) at least one of B; (3) at least one of C; (4) at least one of A and at least one of B; (5) at least one of A and at least one of C; (6) at least one of B and at least one of C; and (7) at least one of A, at least one of B, and at least one of C.

[0045] Examples of the present disclosure relate to a wearable computing device that can be worn, for example, on a user's wrist. For example, the wearable computing device may include a watch. The wearable computing device includes a housing having an upper side and a lower side. The lower side of the housing is opposite to the upper side of the housing and is configured to contact a body part of the user when the wearable computing device is worn by the user. The wearable computing device also includes a user interface disposed on the upper side of the housing and a sensor disposed on the lower side of the housing. The sensor may be configured to output one or more optical readings when a force is applied to the user interface. The wearable computing device may also include one or more processors configured to determine the location where the force is applied to the user interface based on one or more optical readings output by the sensor and the loss function described herein. The user interface is a tangible medium through which a user interacts with the wearable computing device. In an example, the user interface disposed on the upper side of the housing may include, for example, a display (which may be non-touch-sensitive), one or more faux buttons, or a combination of a display and one or more faux buttons.

[0046] In an example embodiment, a wearable computing device may include a housing having a display (which may be non-touch sensitive) on an upper side of the housing and a sensor on a lower side of the housing. The lower side of the housing is opposite to the upper side of the housing and is configured to contact a body part of the user when the wearable computing device is worn by the user. The sensor may be used to indirectly sense the location of the user's touch on the display. For example, when the user presses the display, the optical reading from the sensor may fluctuate based on the location where the user presses. The optical reading from the sensor located closer to the location where the user presses senses more optical back reflections than another sensor located farther away from the location where the user presses. For example, based on the optical readings obtained from the sensor, one or more processors may determine the location of the user's touch on the display, and a function of the wearable computing device corresponding to the determined location may be executed. Determining the location may involve estimating a location parameter (e.g., location coordinates) based on a loss function implemented using the optical readings.

[0047] As an example, the display may display four different visual elements on a graphical user interface of the display in corresponding quadrants of the display, each visual element corresponding to a separate function of the wearable computing device. If a user applies a force to the upper left quadrant of the display, for example to "select" a function represented by a visual element displayed in the quadrant, the sensor may output a corresponding optical reading in response to the applied force. For example, a first sensor located closest to the location where the force is applied to the display may output a signal having a higher amplitude or higher value than a second sensor located further away from the location where the force is applied to the display. One or more processors may receive one or more optical readings from each of the sensors and determine the location where the force is applied to the display based on the one or more optical readings output by the sensors. If the one or more processors determine that the force is applied to a location corresponding to the upper left quadrant of the display based on the received one or more optical readings, the one or more processors may execute a function corresponding to the visual element displayed in the upper left quadrant of the display.

[0048] The sensor may include, for example, a multipath photoplethysmography (PPG) sensor, which may also be used to monitor the user's heart rate. The PPG sensor may include one or more emitters (e.g., light emitting diodes (LEDs)) and multiple detectors (e.g., two or more photodiodes). The detectors may be spaced apart from each other at various locations on the underside of the housing to increase the accuracy of estimating the location of the user's touch on the display.

[0049] In an example, the sensor may include at least three PPG sensors, and at least one of the at least three PPG sensors is spaced apart from another PPG sensor of the at least three PPG sensors in a first direction (e.g., X-axis) and a second direction (e.g., Y-axis). That is, the at least three PPG sensors are not arranged in a linear manner.

[0050] One or more processors may be configured to determine the location where the force is applied to the display based on whether the area of ​​the display where the force is applied corresponds to a first area or a second area, wherein the first area is different from the second area. For example, in the case where the user applies his thumb to the display, the area of ​​the display where the force is applied is larger than the case where the user applies his index finger to the display. As another example, in the case where the user has large fingers (e.g., relative to the average human finger size of males and / or females), it can be considered that the area of ​​the display where the force is applied will be larger than the case where the user has an average-sized finger. Therefore, during calibration of the wearable computing device, the user may provide an input to the wearable computing device (e.g., via a mechanical button) indicating the size or area of ​​the display to be used to receive the force applied from the user. The input may indicate an area size (e.g., a first area or a second area), which may be used to determine a value of a scale parameter (e.g., a first scale parameter or a second scale parameter). The value of the scale parameter may indicate or describe the spread of a Gaussian response used to analyze an optical signal output from a sensor to determine the location of the force applied to the display. As is well known, a Gaussian response, when plotted, generally has a symmetrical "bell curve" shape. For a given application of force to a particular location, the size of the area to which the force is applied affects the magnitude of the compression, with the magnitude of the force being greatest at the center location of the force. The distribution of the magnitude of the force (and accordingly the pressure) decreases (e.g., exponentially) at points located further away from the center location of the force. A larger area will have a greater spread than a smaller area.

[0051] For example, if the user applies force to the display with the thumb, a higher variance response will be experienced, and a higher scale parameter may be appropriate (e.g., a value of 10). On the other hand, if the user applies force to the display with the index finger, a lower variance response will be experienced, and a lower scale parameter value may be appropriate (e.g., a value of 1).

[0052] The scale parameter value can be implemented in a model that describes the touch response amplitude of the sensor recorded by the wearable computing device. For example, the touch response amplitude recorded by the wearable computing device can be approximately modeled as a single-mode Gaussian function: .

[0053] Here, (x, y) represents the coordinates of the specific sensor reading the PPG fluctuations (i.e., the coordinates of the specific detector, which may be a photodiode). The term (x_press, y_press) represents the real-valued coordinates of the location where the force is applied to the top of the wearable computing device. The scale parameter describes the "spreadiness" of the Gaussian response - as explained above, and is used to model the captured optical readings based on the Gaussian function to account for the area covered by a user-specific or user-group-specific touch.

[0054] For example, when the area of ​​the user interface (e.g., a display and / or an imitation button) where the force is applied corresponds to a first area (e.g., for a large finger size or for a thumb), one or more processors may be configured to determine the amplitude of each of the one or more optical readings output by the sensor based on a first model having a first scale parameter (e.g., having a value of 10), the first scale parameter reflecting or describing a first variance of the force applied to the user interface. Alternatively or additionally, when the area of ​​the user interface (e.g., a display and / or an imitation button) where the force is applied corresponds to the first area, one or more processors may be configured to determine the location where the force is applied to the user interface using a first loss function having a first scale parameter (e.g., having a value of 10), the first scale parameter reflecting or describing a first variance of the force applied to the user interface.

[0055] For example, when the area of ​​the user interface (e.g., a display and / or an imitation button) to which the force is applied corresponds to a second area (e.g., for normal or small finger sizes or for an index finger), one or more processors may be configured to determine the amplitude of each of the one or more optical readings output by the sensor based on a second model having a second scale parameter (e.g., having a value of 1), the second scale parameter reflecting a second variance of the force applied to the user interface. Alternatively or additionally, when the area of ​​the user interface (e.g., a display and / or an imitation button) to which the force is applied corresponds to the second area, one or more processors may be configured to use a second loss function having a second scale parameter (e.g., having a value of 1) to determine the location where the force is applied to the user interface using a second Gaussian model, the second scale parameter reflecting or describing a second variance of the force applied to the user interface. Here, the first variance is different from (e.g., greater than) the second variance.

[0056] In other words, one or more processors may be configured to determine the location of the force applied to the user interface based on a first scale parameter when the force applied to the user interface corresponds to a first area of ​​the user interface (e.g., corresponding to the size of a user's thumb), and one or more processors may be configured to determine the location of the force applied to the user interface based on a second scale parameter when the force applied to the user interface corresponds to a second area of ​​the user interface (e.g., corresponding to the size of a user's index finger). In this case, the first scale parameter is greater than the second scale parameter, and the first area is greater than the second area.

[0057] According to an example of the present disclosure, one or more processors of the wearable computing device may receive a number of observations corresponding to the number of sensors from the sensors at a given point in time. For example, if the wearable computing device has N PPG sensors (specifically N detectors), the one or more processors of the wearable computing device may receive N observations from the detectors.

[0058] Thus, if the wearable computing device has 3 detectors, then one or more processors of the wearable computing device may receive 3 observations at a given point in time (ie, 1 observation from each of the detectors).

[0059] According to some implementations, the closer the sensor's detector observation point is to the center of the Gaussian response of the force applied to the display, the more PPG fluctuations the sensor reads, and the higher the output value of the sensor can be (e.g., a value of 0.98). The farther the PD is, the lower the output value can be (e.g., from 0.98 to 0.92).

[0060] For example, one or more processors may be configured to determine the location where the force is applied to the display based on an optical reading of a sensor among the sensors having the highest value among the one or more optical readings output by the sensors. For example, one or more processors may be configured to determine the location where the force is applied to the display based on the highest amplitude among the amplitudes of the one or more optical readings output from the sensors. For example, one or more processors may be configured to determine the location where the force is applied to the display based on one or more amplitudes of the amplitudes of the one or more optical readings output from the sensors and the loss function described herein.

[0061] Examples of the present disclosure also relate to a non-transitory computer-readable medium that stores instructions that can be executed by one or more processors of a wearable computing device. The instructions may include instructions that cause one or more processors to receive one or more optical readings output by a sensor disposed on the lower side of the housing when a force is applied to a display disposed on the upper side of the housing of the wearable computing device. The lower side of the housing may be opposite to the upper side of the housing and configured to contact a body part of the user when the wearable computing device is worn by the user. The instructions may also include instructions that cause one or more processors to determine the location where the force is applied to the display based on the one or more received optical readings.

[0062] The instructions may also include instructions to cause the one or more processors to perform one or more functions of the wearable computing device based on the location where the force is applied to the display. Example functions of the wearable computing device may include checking health information about the user, such as blood pressure, making and / or receiving phone calls, sending and / or receiving text messages, obtaining the current time, setting a timer, stopwatch function, controlling an external device, such as a household appliance, etc.

[0063] The instructions may also include instructions for causing one or more processors to display a graphical user interface that instructs the user to calibrate the wearable computing device by indicating the area of ​​the display to which the force of the display will be applied. When the area of ​​the force indicated by the user corresponds to the first area, the instructions also include instructions for causing the one or more processors to determine the amplitude of each of the one or more optical readings based on a first model with a first scale parameter, the first scale parameter reflecting the first variance of the force to be applied to the display. When the area of ​​the force indicated by the user corresponds to the second area, the instructions also include instructions for causing the one or more processors to determine the amplitude of each of the one or more optical readings based on a second model with a second scale parameter, the second scale parameter reflecting the second variance of the force to be applied to the display. For example, the first area may be larger than the second area, and the first variance may be larger than the second variance. The instructions may also include instructions for causing the one or more processors to determine the location where the force is applied to the display based on the highest amplitude among the amplitudes of the one or more optical readings.

[0064] The instructions may also include causing the one or more processors to determine a location where the force is applied to the display based on an optical reading of a sensor among the sensors having a highest value among the one or more optical readings received by the one or more processors.

[0065] Examples of the present disclosure also relate to a computer-implemented method for a wearable computing device. The method may include: when a force is applied to a display disposed on an upper side of a housing of the wearable computing device, receiving one or more optical readings output by a sensor disposed on a lower side of the housing. The lower side of the housing may be opposite to the upper side of the housing and configured to contact a body part of the user when the wearable computing device is worn by the user. The method may also include: determining, by one or more processors of the wearable computing device, a location where the force is applied to the display based on the one or more received optical readings.

[0066] The method may also include: performing one or more functions of the wearable computing device based on the location where the force is applied to the display. Example functions of the wearable computing device may include checking health information about the user such as blood pressure, making and / or receiving phone calls, sending and / or receiving text messages, obtaining the current time, setting a timer, stopwatch function, controlling an external device such as a household appliance, etc.

[0067] The method may also include: displaying a graphical user interface that instructs the user to calibrate the wearable computing device by indicating an area of ​​the display to which the force of the display is to be applied. When the area of ​​the force indicated by the user corresponds to the first area, the method may include: determining the amplitude of each of the one or more optical readings based on a first model having a first scale parameter, the first scale parameter reflecting a first variance of the force to be applied to the display. When the area of ​​the force indicated by the user corresponds to the second area, the method may include: determining the amplitude of each of the one or more optical readings based on a second model having a second scale parameter, the second scale parameter reflecting a second variance of the force to be applied to the display. For example, the first area may be larger than the second area, and the first variance may be larger than the second variance. The method may include: determining the location where the force is applied to the display based on the highest amplitude among the amplitudes of the one or more optical readings. The method may include: determining the location where the force is applied to the display based on one or more amplitudes of the amplitudes of the one or more optical readings output from the sensor and the loss function described herein.

[0068] The method may include determining a location where a force is applied to the display based on an optical reading of a sensor among the sensors having a highest value among one or more optical readings received by the one or more processors.

[0069] According to examples described herein, one or more processors of a wearable computing device can determine the location where a user touches an element or portion at the upper side of the wearable computing device by calculating an estimate of a position parameter (e.g., position coordinates) based on a loss function that is optimized to find the true value coordinate location where a force is applied to the upper side of the wearable computing device. In an example, given that an observation (e.g., obs_1) may be corrupted by Gaussian measurement noise, the probability channel can be written as: .

[0070] Here, the G(.) function describes the probability density of a standard Gaussian function that can be used to reconstruct the location of force application using measurements obtained from sparsely provided and distributed detectors. For example, the probability of receiving the observed value for each observation in the observation N is calculated based on the candidate touch events (i.e., the candidate locations where the force is estimated to be applied). Whatever candidate touch event maximizes the probability (or minimizes the loss) can be considered the most likely location of the force (i.e., the touch event). For example, the expression for the negative log-likelihood of all observations can be used to find the true value press coordinates, as follows:

[0071] In the above expressions, the terms "x_1, y_1", "x_2, y_2", and "x_N, y_N" correspond to the position of each PPG detector, which is known. The terms "obs_1", "obs_2", and "obs_N" correspond to the observed values ​​of the corresponding detectors. The term "scale k" is a scale parameter value that describes the spread of the Gaussian response as described herein. The term "x_press, y_press" corresponds to the value to be estimated (i.e., the X, Y coordinate values ​​of the position of the force). For example, in a three-channel PPG sensor where there are three detectors, N can be equal to three.

[0072] Because the example loss function is variable depending on two parameters of interest (x_press, y_press) that are unknown at the time of observation, a two-dimensional grid search can be performed to estimate (x_press, y_press) by finding a global loss minimization solution. For example, one or more processors can be configured to execute a program to perform a direct search, in which each X, Y coordinate pair (e.g., corresponding to an area of ​​the display) is tested as a candidate touch event to obtain a result that achieves minimum loss. The candidate touch event that achieves the lowest loss (i.e., the minimum error) between can correspond to the estimated touch position. As another example, one or more processors can implement a known gradient descent method to obtain such a result (X, Y coordinates): the result (X, Y coordinates) achieves the minimum loss. The gradient descent search method can utilize random candidate touch events (i.e., random candidate X, Y coordinates) to obtain a result that achieves the minimum loss, rather than a direct search report in which all candidate touch events are tested. The gradient descent search method can use a smaller search space and is therefore computationally cheaper than the direct search method, thereby saving energy and time. The present disclosure is not limited to direct search methods or gradient descent search methods, and other methods for minimizing the loss function can also be implemented.

[0073] In one or more examples, the user interface may include a non-touch-sensitive display that displays a plurality of selectable functions of the wearable computing device. In response to an increase in the noise level of the sensor exceeding a threshold value (e.g., a signal-to-noise ratio greater than 10 dB), the one or more processors may be configured to control the display so that the number of the plurality of selectable functions displayed on the display may be reduced, and the one or more processors may be configured to perform a function among the plurality of selectable functions based on the position at which the force determined by the one or more processors is applied to the display. For example, when the wearable computing device is not firmly held to a body part of the user and / or due to a low battery condition, the noise level of the sensor may increase, so that one or more optical readings may be affected by the noise, and the accuracy of the sensor may be reduced. When the noise level of the sensor exceeds a threshold value (e.g., a signal-to-noise ratio greater than 10 dB), the number of the plurality of selectable functions displayed on the display may be reduced (e.g., reducing the icons displayed on the display from ten icons to four icons). Ceasing to display one or more of the plurality of selectable functions (i.e., reducing the number of the plurality of selectable functions displayed on the display) may expand the space on the display for displaying each of the remaining selectable functions. Thus, even if the accuracy of detecting or determining the location of the force applied to the display may be reduced due to noise encountered or experienced by the sensor, the likelihood that the one or more processors can accurately execute the function intended by the user to select can be increased. By varying the number of selectable functions displayed on the display, the noise conditions encountered by the sensor can be masked.

[0074] In one or more examples, the user interface may additionally or alternatively include a plurality of imitation buttons, each corresponding to a plurality of selectable functions of the wearable computing device. One or more processors may be configured to execute a function among the plurality of selectable functions of the computer wearable device based on the position at which the force is applied relative to the corresponding positions of the plurality of imitation buttons. For example, an imitation button (or imitation switch) may represent or indicate a function of the wearable computing device that can be performed by the wearable computing device. However, the imitation button may not be mechanically or electrically connected (e.g., via a switch or capacitive sensor) to implement the function of the wearable computing device. Alternatively, one or more processors may be configured to execute a function of the computer wearable device among the plurality of selectable functions based on the position at which the force is applied relative to the corresponding positions of the plurality of imitation buttons.

[0075] In one or more examples, the wearable computing device may also include an accelerometer and / or a gyroscope to detect or sense motion data of the wearable computing device (e.g., for counting the number of steps of a user). The sensor may include a PPG sensor that is also configured to monitor the heart rate of a user of the wearable computing device.

[0076] The movement of the user's hand affects arterial pressure and volume structure (muscle / tendon), thereby producing a characteristic dip in reflection / absorption reflected in the PPG signal. The PPG sensor can spatially capture the arterial pressure distribution over a two-dimensional area (e.g., in the x and y directions) on the underside of the housing of the wearable computing device. One or more processors can be configured to recognize the user's gesture based on one or more optical readings output by the PPG sensor, and one or more processors can be configured to perform a function of the computer wearable device (or another device) based on the user's gesture recognized by the one or more processors. The one or more processors can be configured to recognize the user's gesture based on one or more optical readings output by the PPG sensor together with one or more outputs of the accelerometer and / or gyroscope.

[0077] In one or more examples, the user's gesture may include a hand gesture, including a clenched fist, a pinching gesture using fingers, a clenched hand, and the like. The gesture may be mapped to a corresponding function of the wearable computing device (e.g., to make a phone call), or a function of another device that may be controllable by the wearable computing device through recognition of the gesture (e.g., to operate a household appliance). In one or more examples, the wearable computing device may recognize a gesture based on one or more optical readings output by the PPG sensor. For example, each gesture may correspond to a corresponding optical signal output by the PPG sensor, so that the gesture may be correctly recognized. In an example, the optical signal output by the PPG sensor may be analyzed to recognize the gesture (e.g., by classifying the output optical reading via a machine learning algorithm, by comparing the optical signal with a known optical signal corresponding to the corresponding gesture, etc.). In order to more accurately analyze the optical signal, the portion of the optical reading attributed to the user's heart rate may be filtered out. For example, a high-pass heart rate filtering operation may be performed relative to the optical reading to remove the heart rate (arterial pulse), so that most of the optical readings used to recognize the gesture correspond to or are attributed to the movement of the user's body part (e.g., hand).

[0078] Examples of the present disclosure provide several technical effects, benefits and / or improvements of computing technology and wearable computing device technology. For example, according to one or more examples of the present disclosure, the location of a touch on a display can be indirectly sensed by a sensor disposed on the lower side of a housing of a wearable computing device, which contacts a body part of the user when the wearable computing device is worn by the user. Therefore, the wearable computing device does not need to have a touch-sensitive display, thereby reducing the number of components included in the wearable computing device. In addition, according to one or more examples of the present disclosure, the wearable computing device utilizes a sensor that may be pre-existing in the wearable computing device. For example, the pre-existing sensor may include a PPG sensor for other purposes such as detecting the heart rate of the user. Therefore, there is no need to add additional sensors to the wearable computing device to determine the location of the user's touch on the display. As another example, according to one or more examples of the present disclosure, the wearable computing device can utilize less power than a wearable computing device including a touch-sensitive display. As another example, according to one or more examples of the present disclosure, the wearable computing device can utilize less space than a wearable computing device including a touch-sensitive display. Thus, the wearable computing device may be smaller and smoother, or may provide space for other components that may not be installed if a touch-sensitive display is provided in the wearable computing device. As another example, according to one or more examples of the present disclosure, the wearable computing device may not include a display at all, and the functions of the wearable computing device may be implemented using simulated buttons associated with corresponding functions of the wearable computing device. Alternatively, according to one or more examples of the present disclosure, the wearable computing device may include a display as well as simulated buttons, wherein the functions of the wearable computing device may be implemented using the display and the simulated buttons or only using the simulated buttons associated with the corresponding functions of the wearable computing device.

[0079] Now referring to the accompanying drawings, Figures 1 to 4B An example of a wearable computing device 100 is shown according to an example of the present disclosure. Figure 1 An example wearable computing device 100 is shown that can be worn, for example, on an arm 102 (eg, a wrist) of a user. For example, the wearable computing device 100 can include a housing 110 (eg, a body). Figure 2An exploded view of a wearable computing device 100 is shown, wherein a housing 110 includes an upper side 110a and a lower side 110b, and the housing 110 may define a cavity 112 in which one or more electronic components (e.g., disposed on one or more printed circuit boards) are disposed. For example, the wearable computing device 100 may include a printed circuit board 120 disposed within the cavity 112. In addition, one or more electronic components may be disposed on the printed circuit board 120. The wearable computing device 100 may also include a battery (not shown) disposed within the cavity 112 defined by the housing 110. The wearable computing device 100 may also include various sensors 170 disposed within the cavity 112 defined by the housing 110. For example, the sensor 170 may include a multi-path photoplethysmography (PPG) sensor 172 disposed at the lower side 110b of the housing 110, which may be used to monitor the heart rate of the user. The PPG sensor 172 may include one or more emitters (e.g., light emitting diodes (LEDs)) and a plurality of detectors (e.g., photodiodes). The light emitted from the one or more emitters is transmitted in a direction toward a body part of the user (e.g., a portion of the user's wrist) that is in contact with the lower side 110b of the housing 110. The light then interacts with the user's blood vessels, where the light is modified to a degree affected by the current blood volume in the blood vessels. The modified light is directed back to the PPG detector by reflection and / or refraction. The PPG detector generates data (e.g., one or more signals) reflecting the current blood volume of the user's blood vessels that receive the light emitted from the one or more emitters. For example, the sensor 170 may also include an accelerometer 174, which may be used to capture motion information about the wearable computing device 100. For example, the sensor 170 may also include a gyroscope 176, which may also be used to capture motion information about the wearable computing device 100.

[0080] The wearable computing device 100 may include a first band 130 and a second band 132. As shown, the first band 130 may be coupled to the housing 110 at a first location on the housing. Conversely, the second band 132 may be coupled to the housing at a second location on the housing 110. Additionally, the first band 130 and the second band 132 may be coupled to each other to secure the housing 110 to the user's arm 102.

[0081] In some examples, the first strap 130 can include a buckle or clasp (not shown). Additionally, the second strap 132 can include a plurality of holes (not shown) spaced apart from one another along the length of the second strap 132. In such implementations, a prong of a buckle associated with the first strap 130 can extend through one of a plurality of openings defined by the second strap 132 to couple the first strap 130 to the second strap 132. It should be appreciated that any suitable type of fastener can be used to couple the first strap 130 to the second strap 132. For example, in some implementations, the first strap 130 and the second strap 132 can include magnets. In such implementations, the first strap 130 and the second strap 132 can be magnetically coupled to each other to secure the housing 110 to the user's arm 102.

[0082] The wearable computing device 100 may include a cover 140 positioned on the housing 110 such that the cover 140 is positioned on top of (above) the display 182. In this way, the cover 140 may protect the display 182 from scratches. In some implementations, the wearable computing device 100 may include a seal (not shown) positioned between the housing 110 and the cover 140. For example, a first surface of the seal may contact the housing 110, and a second surface of the seal may contact the cover 140. In this way, the seal between the housing 110 and the cover 140 may prevent liquid (e.g., water) from entering the cavity 112 defined by the housing 110.

[0083] It should be understood that the cover 140 can be optically transparent so that a user can view information displayed on the display 182. For example, in some implementations, the cover 140 can include a glass material. However, it should be understood that the cover 140 can include any suitable optically transparent material.

[0084] Figure 3 An example block diagram of a wearable computing device 100 is shown according to one or more example embodiments of the present disclosure. The wearable computing device 100 may include one or more processors 150, one or more memory devices 160, one or more sensors 170, and a user interface 180.

[0085] For example, the one or more processors 150 may be any suitable processing device that may be included in the wearable computing device 100. For example, such processors 150 may include one or more of a processor, a processor core, a controller and an arithmetic logic unit, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an image processor, a microcomputer, a field programmable array, a programmable logic unit, an application specific integrated circuit (ASIC), a microprocessor, a microcontroller, etc. and combinations thereof, including any other device capable of responding to and executing instructions in a defined manner. The one or more processors 150 may be a single processor or a plurality of processors operatively connected (e.g., in parallel).

[0086] The memory 160 may include one or more non-transitory computer-readable storage media, such as a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), and a flash memory, a USB drive, a volatile memory device such as a random access memory (RAM), a hard disk, a floppy disk, a Blu-ray disk, or an optical medium such as a CD ROM disk and a DVD, and combinations thereof. However, examples of the memory 160 are not limited to the above description, and the memory 160 may be implemented by other various devices and structures as will be understood by those skilled in the art.

[0087] For example, the memory 160 may store instructions that, when executed, cause the one or more processors 150 to determine a location where a force is applied to the display 182 based on one or more received optical readings output by the PPG sensor 172, as described according to examples of the present disclosure. For example, the memory 160 may store instructions that, when executed, cause the one or more processors 150 to perform one or more functions of the wearable computing device 100 based on the determined location, as described according to examples of the present disclosure.

[0088] Memory 160 may also include data 162 and instructions 164 that may be retrieved, manipulated, created, or stored by one or more processors 150. In some example embodiments, such data may be accessed and used as input to determine where a force is applied to display 182 based on one or more optical readings (signals) output by PPG sensor 172. In some examples, memory 160 may include data and instructions for executing one or more processes to perform one or more functions of wearable computing device 100 based on where a force is applied to display 182 determined by one or more processors.

[0089] The wearable computing device 100 may include a user interface 180 configured to receive input from a user by the user applying force to the user interface (e.g., via a thumb, finger, or input device such as a stylus or pen). The wearable computing device 100 may perform a function in response to receiving input from the user (e.g., checking health information about the user such as blood pressure, making and / or receiving a phone call, sending and / or receiving a text message, obtaining the current time, setting a timer, a stopwatch function, controlling an external device such as a household appliance, etc.).

[0090] For example, the wearable computing device 100 may be connected to one or more external devices 190 in a wireless and / or wired manner. The wearable computing device 100 may be connected to the external device 190 through a network 300 such as a local area network (LAN), a wireless local area network (WLAN), a wide area network (WAN), a personal area network (PAN), a virtual private network (VPN), etc. For example, wireless communication between the wearable computing device 100 and the external device 190 may be performed via signals of a wireless LAN, Wi-Fi, Bluetooth, ZigBee, Wi-Fi Direct (WFD), Ultra Wideband (UWB), Infrared Data Association (IrDA), Bluetooth Low Energy (BLE), Near Field Communication (NFC), Radio Frequency (RF) signals, etc. For example, the wired communication connection may be performed via a USB cable, a two-strand cable, a coaxial cable, an optical fiber cable, an Ethernet cable, etc.

[0091] The user interface 180 may include a display 182 that displays information that can be viewed by the user (e.g., time, date, biometric information, notifications, etc.). For example, the display 182 may be a non-touch-sensitive display. For example, the display 182 may include a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, an active matrix organic light emitting diode (AMOLED), a flexible display, a 3D display, a plasma display panel (PDP), a cathode ray tube (CRT) display, etc. However, the present disclosure is not limited to these example displays and may include other types of displays. That is, the non-touch-sensitive display 182 may not use an electrical conductor (e.g., like a capacitive touch display or a resistive display) to change the capacitance or resistance of a circuit to sense a touch event via conduction. Therefore, the non-touch-sensitive display 182 does not include a touch panel that may include a conductive layer and / or a resistive layer of a circuit system. The display 182 may include various layers, including one or more of a display surface, a polarizing layer, a liquid crystal layer, a backlight, a glass substrate, etc. In some implementations, the display 182 can have a square or rectangular shape, or can be annular in shape (eg, oval, circular, etc.) However, it should be appreciated that the display 182 can have any suitable shape.

[0092] exist Figure 4A In the example of FIG. 1 , the display 182 displays various functions F1, F2, F3, F4 that the wearable computing device 100 can perform in corresponding quadrants of the display 182. For example, the functions may be displayed using visual elements such as text and / or by using symbols (e.g., icons) that inform the user of the corresponding functions to be performed. For example, in response to the user applying a force to the lower right quadrant of the display 182 where function F4 is represented, the PPG detectors 172a, 172b, 172c may output corresponding optical readings (signals) S1, S2, S3 (see FIG. 1 ) in response to the applied force. Figure 4C and FIG. 5A to FIG. 5B ). For example, the first PPG detector 172a located closest to the position where the force is applied to the display 182 may output a signal S1 having a higher amplitude or a higher value than the outputs S2 and S3 of the second and third PPG detectors 172b, 172c located farther away from the position where the force is applied to the display 182. The one or more processors 150 may receive one or more optical readings (signals) from each of the PPG detectors 172a, 172b, 172c, and determine the position where the force is applied to the display 182 based on the one or more optical readings (signals) output by the PPG detectors 172a, 172b, 172c. In response to the one or more processors 150 determining that the force is applied to the position corresponding to the lower right quadrant of the display 182 based on the received one or more optical readings (signals), the one or more processors 150 may execute a function F4 displayed in the lower right quadrant of the display 182.

[0093] The user interface 180 may additionally or alternatively include one or more buttons 184 for receiving input from a user by the user applying force to the one or more buttons 184. Figure 1 As shown, one or more buttons 184c may be included on one or more peripheral sides of the wearable computing device 100. The one or more buttons 184c may be known buttons that include mechanical components and / or circuits to implement functions of the wearable computing device 100 (e.g., setting the time, changing the settings and / or views of the display 182, selecting options displayed on the display 182). Additionally or alternatively, the one or more buttons 184 may also include one or more imitation buttons 184a, 184b. For example, in Figure 4B, the imitation buttons 184a, 184b are disposed on the upper side 110a of the housing 110, adjacent to the display 182. The imitation buttons 184a, 184b may represent or indicate functions F3, F4 of the wearable computing device 100 that may be performed by the wearable computing device 100. For example, the imitation button 184a may include a label, symbol, or other indication to notify the user of the function F3 to be performed, and the imitation button 184b may include a label, symbol, or other indication to notify the user of the function F4 to be performed. In another example, the wearable computing device 100 may not include the display 182, and the upper side of the housing 110 may include one or more imitation buttons 184a, 184b for receiving user input. The imitation buttons 184a, 184b may not be mechanically and / or electrically connected (e.g., via a switch or capacitive sensor) to other components of the wearable computing device 100 to implement the functions of the wearable computing device 100.

[0094] For example, in response to a user applying a force to the imitation button 184b, the PPG detectors 172a, 172b, 172c may output corresponding optical readings (signals) S1, S2, S3 in response to the applied force (see Figure 4C and FIG. 5A to FIG. 5B ). For example, the first PPG detector 172a located closest to the position where the force is applied to the imitation button 184b may output a signal S1 having a higher amplitude or a higher value than the outputs S2 and S3 of the second and third PPG detectors 172b, 172c located farther away from the position where the force is applied to the imitation button 184b. The one or more processors 150 may receive one or more optical readings (signals) from each of the PPG detectors 172a, 172b, 172c, and determine the position where the force is applied to the upper side of the housing 110 based on the one or more optical readings (signals) output by the PPG detectors 172a, 172b, 172c. In response to the one or more processors 150 determining that the force is applied to the position corresponding to the imitation button 184b based on the received one or more optical readings (signals), the one or more processors 150 may execute the function F4 represented by the imitation button 184b.

[0095] refer to Figure 4C , shows a bottom view of an example wearable computing device according to one or more example embodiments of the present disclosure. The wearable computing device 100 may include multiple PPG sensors, for example, to help reject motion artifacts. Each PPG sensor may correspond to a combination of a light source and a corresponding detector. For example, in Figure 4C In FIG. 1 , there are three PPG sensors: a combination of LED 172d and detector 172a, a combination of LED 172d and detector 172b, and a combination of LED 172d and detector 172c. However, the present disclosure is not limited to Figure 4C , and the wearable computing device 100 may include two PPG sensors or more than three PPG sensors. In addition, more than one LED may be included, so that different detectors may be combined with different LEDs and / or each detector may be combined with one or more LEDs to output a PPG signal. For example, multiple detectors may be arranged in a circular or elliptical arrangement, wherein the multiple detectors may be spaced apart from each other at regular or irregular intervals. Figure 4C , detector 172a is spaced apart from detector 172c in the horizontal or "X" direction, and is spaced apart from detector 172b in both the horizontal (X) direction and the vertical or "Y" direction. Detector 172b is spaced apart from both detectors 172a and 172c in the horizontal (X) direction and the vertical (Y) direction. Detector 172c is spaced apart from detector 172a in the horizontal (X) direction, and is spaced apart from detector 172b in both the horizontal (X) direction and the vertical (Y) direction. LED 172d is spaced apart from detector 172b in the vertical (Y) direction, and is spaced apart from both detectors 172a and 172c in each of the horizontal (X) direction and the vertical (Y) direction. However, the configuration of the detectors and LEDs may be different. Figure 4C The configuration shown in FIG. 1 is different, and the present disclosure is not limited to Figure 4C .

[0096] The PPG sensor can use a light source and a photodetector at the surface of a user's body part to measure the volume changes of blood circulation, thereby optically measuring biometric information such as heart rate. The light source (e.g., one or more LEDs) emits light to the body part, and the photodetector measures the light reflected from the body part, where the amount of reflected light can indicate biometric information about the user (e.g., blood flow, blood volume, etc.). The light source can emit infrared light, and the color of the LED can be red, green, or yellow. The PPG signal may include various components, such as: a DC component (or DC offset), which represents the constant absorption of light passing through the tissue; and an AC component generated by the heartbeat (heart activity) that affects the blood volume, which depends on the systolic and diastolic periods.

[0097] As disclosed herein, when a force (e.g., direct or indirect force) is applied to a body part of a user where the PPG sensor is located, the PPG signal output by the PPG sensor may also be affected. The change in the PPG signal due to the force may be used to detect an event (e.g., a touch event on the display 182 when a force is applied to the display 182 of the wearable computing device 100).

[0098] For example, when a user applies a force (e.g., a pressing action) to the upper side 110a of the wearable computing device 100 (e.g., a user interface 180 including the display 182 and / or the simulated buttons 184a, 184b), the optical reading (signal) from the PPG sensor 172 disposed on the lower surface of the wearable computing device 100 fluctuates based on the location where the user applies the force. For example, a detector of the PPG sensor located closest to the location where the force is applied will sense more optical back reflections than another detector located further away from the location where the force is applied. The one or more processors may be configured to determine or estimate (e.g., using a sparse pixel maximum likelihood decoder) the location where the force is applied to the display (e.g., an X, Y location on the user interface 180 including the display 182 and / or the simulated buttons 184a, 184b).

[0099] For example, the touch response amplitude output by the detector when a force is applied to the upper portion of the wearable computing device 100 (eg, the display 182) can be approximately modeled as a single-mode Gaussian function: Here, (x, y) represents the coordinates of a particular detector (e.g., a photodiode) that reads the PPG fluctuations. The term (x_press, y_press) represents the real-valued coordinates of where the force is applied to the upper portion of the wearable computing device. The scale parameter k describes the "spreadiness" of the Gaussian response, which refers to FIG. 6A to FIG. 10B Explain in more detail.

[0100] For example, typically for a given application of force to a particular location, the magnitude of the force is greatest at a center location of the force, and the magnitude distribution of the force decreases (e.g., exponentially) at points located away from the center location of the force. When modeling a Gaussian response, a scale parameter k can be determined based on whether the area of ​​the display to which the force is applied corresponds to a first area or a second area, where the first area is larger than the second area. For example, in the case where a user applies their thumb to the display, the area of ​​the display to which the force is applied is larger than in the case where the user applies their index finger to the display. As another example, in the case where the user has large fingers (e.g., relative to an average human finger size for males and / or females), the area of ​​the display to which the force is applied can be considered larger than in the case where the user has an average sized finger.

[0101] Thus, during calibration of the wearable computing device, the user may provide input to the wearable computing device indicating a size or area of ​​the display that will be used to receive the force applied from the user. The input may indicate an area size (e.g., a first area or a second area) that may be used to determine a scale parameter (e.g., a first scale parameter k1 or a second scale parameter k2). The scale parameter may indicate or describe the spread of a Gaussian response that may be used to analyze the optical signal output from the PPG sensor 172 to determine the location of the force applied to the display 182.

[0102] Fig. 6A and Figure 6B Depicted are example compression Gaussian responses corresponding to different scale parameters according to one or more example embodiments of the present disclosure. For example, if the user applies force to the display 182 with the thumb, a higher variance response 610 will be experienced, and a higher scale parameter k1 may be appropriate (e.g., a value of 10). On the other hand, if the user applies force to the display 182 with the index finger, a lower variance response 620 will be experienced, and a lower scale parameter value k2 may be appropriate (e.g., a value of 1).

[0103] The scale parameter values ​​(e.g., k1 and k2) can be implemented in the above model (e.g., using a Gaussian function , which describes the touch response amplitude of the PPG sensor 172 recorded by the wearable computing device 100.

[0104] For example, when the area of ​​the display 182 where the force is applied corresponds to a first area (e.g., for a large finger size or for a thumb), the one or more processors 150 may be configured to determine the amplitude of each of the one or more optical readings output by the PPG sensor 172 based on a first model having a first scale parameter k1 (e.g., having a value of 10), the first scale parameter reflecting or describing a first variance of the force applied to the display 182.

[0105] For example, when the area of ​​the display 182 to which the force is applied corresponds to the second area (e.g., for a normal or small finger size or for an index finger), the one or more processors 150 may be configured to determine the magnitude of each of the one or more optical readings output by the PPG sensor 172 based on a second model having a second scale parameter k2 (e.g., having a value of 1) that reflects a second variance of the force applied to the display 182. Here, the first variance is greater than the second variance.

[0106] In other words, when the force applied to the display 182 corresponds to a first area of ​​the display 182 (e.g., corresponding to the size or surface area of ​​the user's thumb), the one or more processors 150 may be configured to determine the location of the force applied to the display 182 based on the first scale parameter k1, and when the force applied to the display 182 corresponds to a second area of ​​the display 182 (e.g., corresponding to the size or surface area of ​​the user's index finger), the one or more processors 150 may be configured to determine the location of the force applied to the display 182 based on the second scale parameter k2. In this case, the first scale parameter k1 is greater than the second scale parameter k2, and the first area is greater than the second area. For example, the first area and the second area may correspond to known or empirically obtained values ​​of the average fingertip area of ​​the thumb or index finger, and may also be classified according to the user's gender. As an example, the first area may correspond to approximately 5 cm 2 Up to 6 cm 2 (the approximate surface area of ​​the thumb tip), and the second area may correspond to approximately 2.5 cm 2 Up to 3.5 cm 2 (Approximate surface area of ​​the tip of your index finger).

[0107] For example, during calibration of the wearable computing device 100, the user may provide input to the wearable computing device 100 indicating a size or area of ​​the display 182 that will be used to receive a force applied from the user. For example, the wearable computing device 100 may display information on the display 182 requesting the user to indicate a preferred finger (e.g., thumb or index finger) that will be used to provide input (force) to the display 182. For example, the user may select a preferred finger using a button 184c disposed on a peripheral portion of the wearable computing device 100, similar to how a user may set the time or date in a known watch. The user may additionally and / or alternatively input their gender to further determine the scale parameter k for selecting an appropriate model to be utilized.

[0108] According to an example of the present disclosure, the one or more processors 150 of the wearable computing device 100 may receive a number of observations corresponding to the number of sensors from the PPG sensors 172 at a given point in time. For example, if the wearable computing device has N PPG sensors 172 (specifically N detectors 172a-c), the one or more processors 150 of the wearable computing device 100 may receive N observations from the detectors 172a-172c.

[0109] like Figure 4CAs shown, the wearable computing device 100 has three detectors 172a-172c. The one or more processors 150 of the wearable computing device 100 may receive three observations (ie, one observation from each of the detectors 172a-172c) at a given point in time.

[0110] Fig. 7A and Figure 7B 182 , the closer the detector observation point of the detector is to the center of the Gaussian response of the force applied to the display 182, the more PPG fluctuations the detector reads, and the output value of the sensor can be higher, while detectors located farther away have lower values. For example, in Fig. 7A , the outputs of detectors 172a-172c are overlaid on top of the pressed Gaussian function 710, with the darker shading indicating the center of the Gaussian function corresponding to the actual touch location. Detector 172c outputs a value of 0.98, while detectors 172a and 172b output values ​​of 0.92 and 0.94, respectively. One or more processors 150 can determine or estimate the location of the force applied to display 182 based on the values ​​of each of detectors 172a-172c to be in the middle right portion of display 182. For example, in Figure 7B , detector 172c outputs a value of 0.91, while detectors 172a and 172b output values ​​of 0.83 and 0.89, respectively. One or more processors 150 can determine or estimate the location of the force applied to display 182 based on the values ​​of each of detectors 172a-172c in the upper right portion of display 182, noting that detectors 172b and 172c have relatively similar values ​​compared to the value output by detector 172a.

[0111] The one or more processors 150 may be configured to determine the position where the force is applied to the display 182 based on the optical reading value having the highest value (e.g., the highest voltage value) of the PPG sensor 172 among the PPG sensors 172. For example, the one or more processors 150 may be configured to determine the position where the force is applied to the display 182 based on the highest amplitude among the amplitudes of the one or more optical reading values ​​output from the PPG sensors 172.

[0112] The one or more processors 150 may be configured to determine the location where the force is applied to the display 182 based on a loss function that is optimized to find the true value coordinate location where the force is applied to the display 182. In an example, given that an observation (e.g., obs_1) may be corrupted by Gaussian measurement noise, the probability channel may be written as: .

[0113] Here, the G(.) function describes the probability density of a standard Gaussian function that can be used to reconstruct the location of force application using measurements obtained from sparsely provided and distributed detectors. For example, the probability of receiving the observed value for each observation in the observation N is calculated based on the candidate touch events (i.e., the candidate locations where the force is estimated to be applied). Whatever candidate touch event maximizes the probability (or minimizes the loss) can be considered the most likely location of the force (i.e., the touch event). For example, the expression for the negative log-likelihood of all observations can be used to find the true value press coordinates, as follows:

[0114] In the above expressions, the terms "x_1, y_1", "x_2, y_2", and "x_N, y_N" correspond to the position of each PPG detector, which is known. The terms "obs_1", "obs_2", and "obs_N" correspond to the observed values ​​of the corresponding detectors. The term "scale k" is a scale parameter value that describes the spread of the Gaussian response as described herein. The term "x_press, y_press" corresponds to the value to be estimated (i.e., the X, Y coordinate values ​​of the position of the force). For example, in a three-channel PPG sensor where there are three detectors, N can be equal to three.

[0115] Because the example loss function is variable depending on two parameters of interest (x_press, y_press) that are unknown at the time of observation, a two-dimensional grid search can be performed to estimate (x_press, y_press) by finding a global loss minimization solution. For example, one or more processors 150 can be configured to execute a program to perform a direct search, in which each X, Y coordinate pair (e.g., corresponding to an area of ​​the display) is tested as a candidate touch event to obtain a result that achieves the minimum loss. The candidate touch event that achieves the lowest loss (i.e., the minimum error) between can correspond to the estimated touch position. As another example, one or more processors 150 can implement a known gradient descent method to obtain a result (X, Y coordinates) that achieves the minimum loss. The gradient descent search method can utilize random candidate touch events (i.e., random candidate X, Y coordinates) to obtain such a result: the result obtains the minimum loss, rather than obtaining a direct search report in which all candidate touch events are tested. The gradient descent search method can use a smaller search space and is therefore computationally cheaper than the direct search method, thereby saving energy and time. The present disclosure is not limited to direct search methods or gradient descent search methods, and other methods for minimizing the loss function can also be implemented.

[0116] Fig. 8A and Figure 8BAn example estimation of the location of the force applied to the display based on the loss function result according to one or more example embodiments of the present disclosure is shown. Fig. 8A , the estimated location of the force applied to the display 182 (upper right corner) is indicated by reference numeral 810. The location of the force has been determined by one or more processors 150 using a Figure 4C The actual value of the force is represented by reference numeral 820. A Gaussian compression response 830 is also shown in the background to provide additional context. For example, Figure 8B The corresponding loss function result 840 is shown, where the outer band 850 represents the most likely position of the minimization result, where the estimated position 810 also corresponds.

[0117] Fig. 9A and Fig. 9B Another example estimation of the location of the force applied to the display based on the loss function result according to one or more example embodiments of the present disclosure is shown. Fig. 9A In FIG. 1 , the estimated or determined location of the force applied to the display 182 (lower right corner) is indicated by reference numeral 910. The location of the force has been determined by one or more processors 150 using a method such as Figure 4C The actual value of the force is represented by reference numeral 920. A Gaussian compression response 930 is also shown in the background to provide additional context. For example, Fig. 9B The corresponding loss function result 940 is shown, where the outer band 950 represents the most likely position of the minimization result, where the estimated position 910 also corresponds.

[0118] In some cases, noise may affect the output of the PPG sensor 172. For example, when the wearable computing device 100 is not securely held to a body part of the user, the noise level experienced by the PPG sensor 172 may increase. In another example, the noise level experienced by the PPG sensor 172 may increase due to a low battery condition, where the amount of light output by the light source (e.g., LED 172d) is reduced (e.g., low power mode). When the PPG sensor 172 experiences noise, the optical reading may be affected by the noise, and the accuracy of the PPG sensor 172 may be reduced.

[0119] Fig. 10A and Fig. 10B An example estimation of the location of the force applied to the display based on the loss function result in a noisy environment according to one or more example embodiments of the present disclosure is shown. Fig. 10A , the estimated location of the force applied to the display 182 (lower right corner) is represented by reference numeral 1010 and is Fig. 9AThe force position has been processed by one or more processors 150 using the example Figure 4C The value of the detector output configured in the example is calculated or determined. Gaussian press response 1030 is also shown in the background to provide additional context. For example, Fig. 10B The corresponding loss function result 1040 is shown, where the outer band 1050 represents the most likely position of the minimization result, where the estimated position 1010 also corresponds.

[0120] In one or more example embodiments, in response to the noise level of the PPG sensor 172 increasing beyond a threshold, the one or more processors 150 may be configured to control the display 182 so that the number of the plurality of selectable functions displayed on the display 182 may be reduced. For example, the number of selectable functions displayed on the display 182 may be reduced. Figure 4A 182 to display only functions F1 (on the upper half of the display 182) and F2 (on the lower half of the display 182). Thus, when the noise level of the sensor exceeds a threshold, the number of the plurality of selectable functions displayed on the display 182 may be reduced (e.g., the icons displayed on the display 182 are reduced from ten icons to four icons). Ceasing to display one or more of the plurality of selectable functions (i.e., reducing the number of the plurality of selectable functions displayed on the display 182) may expand the space on the display 182 for displaying each of the remaining selectable functions. Thus, even if the accuracy of the detection or determination of the location of the force applied to the display 182 may be reduced due to the noise encountered or experienced by the PPG sensor 172, the possibility that the one or more processors 150 can accurately execute the function intended by the user to select may be increased. In addition, by increasing the accuracy of the determination of the location by changing (reducing) the number of selectable functions displayed on the display 182, the noise condition encountered by the PPG sensor 172 may be masked and not noticed by the user, thereby improving the user experience.

[0121] In one or more examples, the wearable computing device 100 may include an accelerometer 174 and / or a gyroscope 176 to detect or sense motion data of the wearable computing device 100. As described herein, the wearable computing device 100 may include a PPG sensor 172 configured to monitor the heart rate of a user when the wearable computing device 100 is worn by the user.

[0122] The movement of the user's hand affects arterial pressure and volume structure (muscle / tendon), thereby producing a characteristic drop in reflection / absorption reflected in the PPG signal. The PPG sensor 172 can spatially capture the arterial pressure distribution over a two-dimensional area on the lower side 110b of the housing 110 of the wearable computing device 100 (e.g., in the x and y directions). The one or more processors 150 can be configured to recognize the user's gesture based on one or more optical readings output by the PPG sensor 172, and the one or more processors 150 can be configured to perform a function of the computer wearable device 100 (or another device) based on the user's gesture recognized by the one or more processors 150. The one or more processors 150 can be configured to recognize the user's gesture based on one or more optical readings output by the PPG sensor 172 together with one or more outputs of the accelerometer 174 and / or the gyroscope 176. The output of the accelerometer 174 and / or the gyroscope 176 can be used additionally or alternatively to confirm the output of the PPG sensor 172—the validity of the user performing the gesture.

[0123] In one or more examples, the user's gesture may include a hand gesture, including clenching a fist, pinching gestures using fingers, clenching hands, etc. The gesture may be mapped to a corresponding function of the wearable computing device (e.g., to make a phone call), or a function of another device that can be controlled by the wearable computing device 100 through the recognition of the gesture (e.g., to operate a household appliance). In one or more examples, the one or more processors 150 may recognize a gesture based on one or more optical readings output by the PPG sensor 172. For example, each gesture may correspond to a corresponding optical signal output by the PPG sensor 172, so that the gesture may be correctly recognized. In an example, the optical signal output by the PPG sensor 172 may be analyzed to recognize the gesture (e.g., classifying the output optical reading via a machine learning algorithm, by comparing the optical signal with a known optical signal corresponding to the corresponding gesture, etc.). In order to more accurately analyze the optical signal, the portion of the optical reading attributed to the user's heart rate may be filtered out. For example, a high-pass heart rate filtering operation may be performed with respect to the optical reading to remove the heart rate (arterial pulse) so that most of the optical readings used to recognize the gesture correspond to or are attributed to the movement of the user's hand.

[0124] Fig.11 1 shows example response signals of various sensors of a wearable computing device for detecting a user's gesture according to one or more example embodiments of the present disclosure. Fig.11 , when the user makes a pinch gesture at times corresponding to reference numerals 1110a, 1110b, and 1110c, output signals of the accelerometer 174, the gyroscope 176, and the PPG sensor 172 undergo unique or significant changes. Fig.11The PPG signal shown is obtained after high-pass heart rate filtering, which results in a unique wavelet-like pattern in the PPG signal.

[0125] For example, in Fig.11 In , motion information / data is collected via accelerometers along three axes (Y axis 1120a, X axis 1120b, and Z axis 1120c). Fig.11 In , motion information / data is collected along three axes (Y axis 1130a, X axis 1130b, and Z axis 1130c) via a gyroscope. Fig.11 , the PPG optical reading includes information / data collected from six channels: PPG channel 1 data 1140a, PPG channel 2 data 1140b, PPG channel 3 data 1140c, channel 4 data 1140d, PPG channel 5 data 1140e, and PPG channel 6 data 1140f. The signals output by the accelerometer 174 and / or the gyroscope 176 may be analyzed in conjunction with the signals output by the PPG sensor 172 to determine a gesture of the user's hand (e.g., a pinch gesture). However, in some examples, only the signals output by the PPG sensor 172 may be used to determine the gesture of the user's hand. Based on the determination of the gesture, a corresponding function of the wearable computing device 100 and / or the external device 190 may be performed.

[0126] For example, multiple PPG optical readings can be obtained by multiplexing. For example, multiple LEDs can also be used to obtain multiple optical readings from different combinations of detectors and LEDs, thereby obtaining spatial backscatter diversity. For example, in a configuration where three LEDs and three detectors are included in the PPG sensor 172, in a multiplexing operation where the first LED is turned on (lit), each of the three detectors can receive reflected light and output a corresponding signal. When the second LED is turned on next, each of the three detectors can receive reflected light and output a corresponding second signal, and when the third LED is turned on last, each of the three detectors can receive reflected light and output a corresponding third signal. In such a configuration, a total of nine PPG optical readings can be obtained to provide a spatial perfusion index distribution change for accurate classification of hand states. In addition, as described above, the signals output by the accelerometer 174 and / or the gyroscope 176 can be analyzed in conjunction with the signals output by the PPG sensor 172 to determine the gesture of the user's hand. However, in some examples, only the signals output by the PPG sensor 172 can be used to determine the gesture of the user's hand.

[0127] Fig. 12A and Fig. 12BDepicted are example single-hand gestures of a user and corresponding heatmaps reconstructed from the output optical readings of a PPG sensor according to one or more example embodiments of the present disclosure. Fig. 12A In , when the user makes a first gesture (e.g., by tilting the hand upward), a first heat map 1210 is generated, and Fig. 12B , when the user makes a second gesture (e.g., by tilting the hand downward), a second heat map 1230 is generated. By comparing Fig. 12A and Fig. 12B It can be seen that Fig. 12A The thermal characteristics corresponding to the portion 1220 in FIG. Fig. 12B The thermal signatures corresponding to the portions 1240 in the image are very different. Each gesture may have a unique or identifiable thermal map that may be correlated with the output optical readings from the PPG sensor 172, such that the wearable computing device 100 may recognize or determine the gesture based on the output optical readings from the PPG sensor 172. The determination of the gesture may be performed using a probability density of a standard Gaussian function that may be used to determine the gesture using measurements obtained from sparsely provided and distributed detectors 172a-172c, similar to the method described above for determining the location of a touch on the user interface 180 of the wearable computing device 100. Based on the determination of the gesture, a corresponding function of the wearable computing device 100 and / or the external device 190 may be performed.

[0128] Examples of the present disclosure also relate to computer-implemented methods of wearable computing devices. Fig.13 and Fig.14 Each shows a flow diagram of an example non-limiting computer-implemented method according to one or more example embodiments of the present disclosure.

[0129] refer to Fig.13 In the example computer-implemented method 1300, at operation 1310, the one or more processors 150 may receive an optical reading (signal) output by the PPG sensor 172 when a force is applied to the user interface 180 (e.g., including a display and / or one or more imitation buttons 184a, 184b) disposed on the upper side 110a of the housing 110. The PPG sensor 172 is disposed on the lower side 110b of the housing 110, which is disposed opposite to the upper side 110a of the housing 110 (e.g., as shown in FIG. Figure 2). The lower side 110b of the housing 110 may be configured to contact a body part of the user when the wearable computing device 100 is worn by the user. At operation 1320, the method may also include: determining, by one or more processors 150 of the wearable computing device 100, the location where the force is applied to the user interface 180 based on one or more received optical readings. At operation 1330, the method may also include: the one or more processors 150 performing one or more functions of the wearable computing device 100 based on the determined location where the force is applied to the user interface 180. Example functions of the wearable computing device 100 may include checking health information about the user such as blood pressure, making and / or receiving phone calls, sending and / or receiving text messages, obtaining the current time, setting a timer, a stopwatch function, controlling an external device 190 such as a household appliance, an electronic device such as a television, and the like.

[0130] refer to Fig.14 In an example computer-implemented method 1400, at operation 1410, a graphical user interface is displayed on the display 182, the graphical user interface instructing the user to calibrate the wearable computing device 100 by indicating the area of ​​the display 182 to which force will be applied. For example, the calibration instructions may ask the user whether they prefer to use the index finger (second area) to provide input or the thumb (first area). For example, additionally or alternatively, the calibration instructions may ask the user whether they are male or female. For example, additionally or alternatively, the calibration instructions may ask the user whether they have hands and / or fingers greater than a threshold, which may suggest that the first area should be set (greater than the threshold) or the second area should be set (equal to or less than the threshold). For example, if the user has a ring size greater than ten, the first area setting may be assumed. For example, if the user has a finger length greater than 7.5 inches (measured from the tip of the longest finger to the crease under the palm), the first area setting may be assumed. At operation 1420, the user may provide input (e.g., via a user interface such as Figure 1 As shown, one or more buttons 184c located on the perimeter of the wearable computing device 100, the input indicates the area of ​​force as the first area or the second area.

[0131] When the area of ​​force indicated by the user corresponds to the first area, the method may include operation 1430, which includes determining the magnitude of each of the one or more optical readings based on a first model having a first scale parameter k1, the first scale parameter reflecting a first variance of the force to be applied to the display 182. When the area of ​​force indicated by the user corresponds to the second area, the method may include operation 1450, which includes determining the magnitude of each of the one or more optical readings based on a second model having a second scale parameter k2, the second scale parameter reflecting a second variance of the force to be applied to the display 182. For example, the first area may be larger than the second area, and the first variance may be larger than the second variance. At each of operations 1440 and 1460, the method may include: the one or more processors 150 determining the position where the force is applied to the display 182 based on the highest magnitude among the magnitudes of the one or more optical readings. The method may also include: determining the position where the force is applied to the display 182 based on the optical reading of the PPG sensor 172 among the PPG sensors 172 having the highest value among the one or more optical readings received by the one or more processors 150.

[0132] Other operations of the calibration process may include: asking the user to apply force to the display 182 at various known (predetermined) points on the display 182, and saving the signal output in response to the memory 160 as data 162, which can be used as a lookup table for comparing future output signals obtained from the PPG sensor 172 and / or for guiding decisions on the location of application of force based on the loss function as described herein.

[0133] Aspects of the above-described example embodiments may be recorded in a non-transitory computer-readable medium including program instructions for implementing various operations embodied by a computer. The medium may also include data files, data structures, etc., alone or in combination with program instructions. Examples of non-transitory computer-readable media include magnetic media, such as hard disks, floppy disks, and tapes; optical media, such as CD ROMs, Blu-ray discs, and DVDs; magneto-optical media, such as optical discs; and other hardware devices specifically configured to store and execute program instructions, such as semiconductor memories, read-only memories (ROMs), random access memories (RAMs), flash memories, USB memories, etc. Examples of program instructions include both machine codes such as those generated by a compiler and files containing higher-level codes that can be executed by a computer using an interpreter. Program instructions may be executed by one or more processors. The described hardware devices may be configured to act as one or more software modules in order to perform the operations of the above-described embodiments, and vice versa. In addition, non-transitory computer-readable storage media may be distributed between computer systems connected via a network, and computer-readable codes or program instructions may be stored and executed in a decentralized manner. Furthermore, the non-transitory computer-readable storage medium may also be embodied in at least one application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0134] Each block of the flow chart may represent a unit, module, segment or portion of code, which includes one or more executable instructions for implementing one or more specified logical functions. It should also be noted that in some alternative implementations, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may actually be executed substantially concurrently (simultaneously), or the blocks may sometimes be executed in reverse order, depending on the functionality involved.

[0135] Although the present disclosure has been described with respect to various example embodiments, each example is provided by way of explanation, not limitation of the present disclosure. Those skilled in the art, after understanding the foregoing, may easily produce changes, modifications, and equivalents of such embodiments. Therefore, the present disclosure does not exclude such modifications, changes, and / or additions to the disclosed subject matter that would be readily understood by those of ordinary skill in the art. For example, a feature shown or described as part of one embodiment may be used together with another embodiment to produce yet another embodiment. Therefore, the present disclosure is intended to cover such changes, modifications, and equivalents.

Claims

1. A wearable computing device, comprising: a housing comprising an upper side and a lower side, wherein the lower side of the housing is opposite the upper side of the housing and is configured to contact a body part of a user when the wearable computing device is worn by the user; a user interface disposed on the upper side of the housing; a sensor disposed on the underside of the housing, the sensor configured to output one or more optical readings when a force is applied to the user interface; as well as One or more processors configured to determine a location of the user interface where the force is applied based on the one or more optical readings output by the sensor.

2. The wearable computing device of claim 1, wherein The sensor includes a photoplethysmography (PPG) sensor configured to monitor a heart rate of the user when the wearable computing device is worn by the user, and The PPG sensor includes one or more light emitting diodes and a plurality of detectors.

3. The wearable computing device of claim 1 , wherein The sensors include at least three photoplethysmography (PPG) sensors, and At least one PPG sensor of the at least three PPG sensors is spaced apart from another PPG sensor of the at least three PPG sensors in a first direction and a second direction.

4. The wearable computing device of claim 1 , wherein The one or more processors are configured to perform one or more functions of the wearable computing device based on the force being applied to the location of the user interface as determined by the one or more processors.

5. The wearable computing device of claim 1 , wherein The one or more processors are configured to determine the location of the user interface where the force is applied based on whether the area of ​​the user interface to which the force is applied corresponds to a first area or a second area, the first area being different from the second area.

6. The wearable computing device of claim 5, wherein: When the area of ​​the user interface to which the force is applied corresponds to the first area, the one or more processors are configured to determine a magnitude of each of the one or more optical readings based on a first model having a first scale parameter, the first scale parameter reflecting a first variance of the force applied to the user interface, and When the area of ​​the user interface to which the force is applied corresponds to the second area, the one or more processors are configured to determine the amplitude of each of the one or more optical readings based on a second model having a second scale parameter, wherein the second scale parameter reflects a second variance of the force applied to the user interface, the second variance being different from the first variance.

7. The wearable computing device of claim 6, wherein The one or more processors are configured to determine the location at which the force is applied to the user interface based on the value of each of the one or more optical readings output by the sensor and by applying a loss function to minimize a difference between an actual location at which the force is applied and an estimated location at which the force is applied.

8. The wearable computing device of claim 7, wherein The one or more processors are configured to apply the loss function by performing a two-dimensional grid search method or a gradient descent search method.

9. The wearable computing device of claim 1 , wherein The user interface includes a non-touch-sensitive display configured to display a plurality of elements corresponding to a plurality of selectable functions of the wearable computing device, In response to the noise level of the sensor increasing beyond a threshold, the one or more processors are configured to control the non-touch-sensitive display to stop displaying one or more of the plurality of elements, and In response to determining that the position at which the force is applied to the non-touch-sensitive display corresponds to a remaining first element of the multiple elements displayed on the non-touch-sensitive display, the one or more processors are also configured to execute a first selectable function of the multiple selectable functions corresponding to the remaining first element based on the determined position.

10. The wearable computing device of claim 1, wherein The user interface includes a plurality of imitation buttons, the plurality of imitation buttons respectively corresponding to a plurality of selectable functions of the wearable computing device, and In response to determining that the force is applied to the position of a first imitation button of the multiple imitation buttons of the user interface, the one or more processors are configured to execute a first selectable function of the multiple selectable functions corresponding to the first imitation button based on the determined position.

11. The wearable computing device of claim 1 , wherein The user interface includes a non-touch sensitive display.

12. The wearable computing device of claim 1, wherein the sensor comprising a photoplethysmography (PPG) sensor configured to monitor a heart rate of the user when the wearable computing device is worn by the user, The one or more processors are configured to recognize a gesture of the user based on the one or more optical readings output by the PPG sensor, and The one or more processors are configured to execute a function of the computer wearable device based on the gesture of the user recognized by the one or more processors.

13. The wearable computing device of claim 12, further comprising: at least one of an accelerometer or a gyroscope, in The one or more processors are configured to recognize the gesture of the user based on the one or more optical readings output by the PPG sensor and one or more outputs of the at least one of the accelerometer and the gyroscope.

14. A computer-implemented method comprising: receiving one or more optical readings output by a sensor disposed on a lower side of a housing of a wearable computing device when a force is applied to a user interface disposed on an upper side of the housing, wherein the lower side of the housing is opposite the upper side of the housing and is configured to contact a body part of a user when the wearable computing device is worn by the user; as well as The location where the force is applied to the user interface is determined by one or more processors of the wearable computing device based on one or more received optical readings output by the sensor.

15. The computer-implemented method of claim 14, further comprising: One or more functions of the wearable computing device are performed based on the force being applied to the location of the user interface as determined by the one or more processors.

16. The computer-implemented method of claim 14, further comprising: Instructions are displayed on a display of the user interface, the instructions instructing a user to calibrate the wearable computing device by indicating an area of ​​the display to which the force is to be applied.

17. The computer-implemented method of claim 16, further comprising: determining a magnitude of each of the one or more optical readings based on a first model having a first scale parameter reflecting a first variance of the force to be applied to the display when the region of the force indicated by the user corresponds to a first region, and The amplitude of each of the one or more optical readings is determined based on a second model having a second scale parameter reflecting a second variance of the force to be applied to the display when the area of ​​the force indicated by the user corresponds to a second area, the first area is larger than the second area, and the first variance is larger than the second variance.

18. The computer-implemented method of claim 14, further comprising: The location at which the force is applied to the user interface is determined based on the value of each of the one or more optical readings output by the sensor and by applying a loss function to minimize the difference between the actual location at which the force is applied and the estimated location at which the force is applied.

19. The computer-implemented method of claim 14, further comprising: displaying, on a non-touch-sensitive display of the user interface, a plurality of elements corresponding to a plurality of selectable functions of the wearable computing device; In response to a noise level of the sensor increasing beyond a threshold, controlling the display to cease display of one or more of the plurality of elements; as well as In response to determining that the location where the force is applied to the user interface corresponds to a remaining first element of the plurality of elements displayed on the display, a first selectable function of the plurality of selectable functions corresponding to the remaining first element is executed based on the determined location.

20. A non-transitory computer-readable medium storing instructions executable by one or more processors of a wearable computing device, the instructions comprising: instructions causing the one or more processors to receive one or more optical readings output by a sensor disposed on a lower side of a housing of the wearable computing device when a force is applied to a user interface disposed on an upper side of the housing, wherein the lower side of the housing is opposite the upper side of the housing and is configured to contact a body part of a user when the wearable computing device is worn by the user; as well as Instructions cause the one or more processors to determine a location of the user interface where the force is applied based on the one or more received optical readings.

Images