System and method for adjusting heart rate measurement accuracy of wearable device

Abstract

A method for adjusting heart rate measurement accuracy of a wearable device includes: obtaining, by a data module, a plurality of pieces of data from a plurality of data sources, where the plurality of pieces of data includes user activity data, user information, and environmental conditions related to a user; determining a skin attribute of the user based on the obtained plurality of pieces of data; emitting, by the transmitter module, infrared (IR) radiation and visible light at an intensity level for measuring the heart rate of the user; receiving, by the receiver module, scattered IR radiation resulting from the interaction of the emitted IR radiation and the emitted visible light based on a skin condition and an environmental condition of the user; determining, by a correlation module, a scattered radiation vector based on the scattered IR radiation; determining, by a detection module, a wavelength of visible light to be adjusted based on the scattered radiation vector; and adjusting the wavelength of the visible light by the emitter module.

Description

Technical Field

[0001] This disclosure relates to heart rate measurement, and more specifically, to a system and method for improving the accuracy of heart rate measurement in wearable devices. Background Technology

[0002] Heart rate provides insight into overall heart health. Over time, an increased heart rate can indicate various conditions such as coronary artery disease and valvular heart problems. Detecting these conditions in their early stages can be beneficial for intervention and providing treatment to protect the heart from further damage. Furthermore, heart rate is a vital sign used to monitor health, track exercise, and guide a user's recovery process. Therefore, routine heart rate measurements can be used to monitor the progress of cardiovascular disease treatment or a user's overall health.

[0003] Various methods, such as photoplethysmography (PPG) sensors in wearable devices like smartwatches, can be used to measure heart rate. While smartwatches offer a simple and convenient way to monitor heart rate, readings are often inaccurate because the devices cannot account for different environmental conditions and factors, such as skin type, how the watch is worn, physical activity, gender, and age. These inaccuracies can pose significant challenges for healthcare professionals and lead to misdiagnosis of conditions such as high blood pressure, arrhythmias, or heart disease. Furthermore, inaccurate readings can negatively impact an individual's mental health, causing worry and anxiety.

[0004] Therefore, there is a need for a system or method that can fully take these environmental conditions and factors into account during heart rate measurement and improve the accuracy of heart rate measurement in wearable devices.

[0005] Some methods for heart rate measurement involve optical devices for determining pulse rate, which may be included, for example, in wearable monitoring devices that include motion sensors and PPG sensors. For instance, the PPG sensor may include a periodic light source, a photodetector, and circuitry for determining the user's heart rate based on the output of the photodetector. However, these methods may not take into account the user's skin attributes corresponding to their activity or environment. Furthermore, other methods may involve continuous heart rate monitoring and analysis, for example, by selecting from two or more different heart rate detection modes, and may provide automated suggestions regarding changes in sleep, recovery time, exercise habits, etc. However, these methods may not take into account the user's skin attributes corresponding to their activity or environment.

[0006] Therefore, it is necessary to overcome the aforementioned drawbacks associated with these methods in order to improve the accuracy of heart rate measurement in wearable devices. Summary of the Invention

[0007] Technical solution According to one aspect of this disclosure, a method for adjusting the accuracy of heart rate measurement in a wearable device includes: obtaining multiple data points from multiple data sources by a data module, wherein the multiple data points include user activity data, user information, and environmental conditions related to a user; determining the user's skin attributes based on the obtained multiple data points; emitting infrared (IR) radiation and visible light at an intensity level for measuring the user's heart rate by a transmitter module; receiving scattered IR radiation generated by the interaction of the emitted IR radiation and the emitted visible light based on the user's skin condition and environmental conditions by a receiver module; determining a scattered radiation vector based on the scattered IR radiation by a correlation module; determining the wavelength of the visible light to be adjusted by a detection module based on the scattered radiation vector; and adjusting the wavelength of the visible light by the transmitter module.

[0008] User activity data may include the user's physical activity data, user information may include at least one of the user's electronic health record data, disease information, age, gender and location, and environmental conditions may include the temperature and humidity of the user's environment.

[0009] Multiple data sources may include at least one of the user's electronic health record data, photoplethysmography sensor, temperature sensor, accelerometer, and gyroscope.

[0010] The method may further include: using an input module included in the data module to determine user demographic data based on user information obtained from multiple data sources; and using a skin attribute extraction module included in the data module to determine skin attributes based on user demographic data obtained from the input module and at least one of electronic health record data, physical activity data, temperature data, and humidity data obtained from multiple data sources.

[0011] The operation of determining a user's skin attributes may include: using a skin type vector determination submodule to determine a user's skin type vector based on at least one of electronic health record data and historical data provided by the user, wherein the skin type vector indicates at least one of dry skin quantity, oily skin quantity, and normal skin quantity based on the user's skin condition; using a sweat quantity determination submodule to determine sweat quantity based on a machine learning model based on user demographic data, physical activity data, temperature data, and humidity data; and using a vector merger to determine skin attributes by merging the skin type vector determined by the skin type vector determination submodule and the sweat quantity determined by the sweat quantity determination submodule.

[0012] User demographic data, multiple data points, and user skin attributes can be stored in a database.

[0013] The method may further include: using a controller included in the transmitter module to receive input from the data module and the detection module, and determining the intensity level of visible light based on red light coefficients and green light coefficients, wherein visible light includes red light and green light; and using a modulator included in the transmitter module to emit IR radiation as well as green light and red light based on the determined intensity level.

[0014] The method may also include at least one of the following operations: using a wavelength division multiplexing (WDM) splitter to separate light of different wavelengths; and using a WDM combiner to combine light of different wavelengths into one output channel.

[0015] The method may further include: detecting scattered IR radiation using a photodetector and converting the scattered IR radiation into an electrical signal; amplifying the electrical signal using a preamplifier; filtering the electrical signal using a filter based on filter coefficients, wherein the filter coefficients depend on the wavelength of visible light; improving the quality of the electrical signal using at least one of an amplifier and a limiter; improving the signal-to-noise ratio of the electrical signal, reducing distortion of the electrical signal, and minimizing interference of the electrical signal through a gain control submodule; processing the electrical signal using a decision circuit, which may include at least one of a low-pass filter and a comparator; and providing the electrical signal to a relevant module.

[0016] The operation of determining the scattered radiation vector may include: receiving scattered IR radiation from the receiver module by a photoplethysmography sensor and determining the amount of absorbed IR radiation and the amount of absorbed visible light, wherein the absorbed visible light may include at least one of green and red light; and determining the scattered radiation vector by a radiation vector creation submodule and identifying biases by using a machine learning model to correlate the amount of IR radiation absorption and visible light absorption with the amount of absorption at similar wavelengths corresponding to multiple skin attributes stored in a database.

[0017] The method may further include: determining the red light coefficient and green light coefficient by the detection module based on the scattered radiation vector; and determining the intensity level of visible light using a coefficient generation neural network based on the determined red light coefficient and the determined green light coefficient.

[0018] According to one aspect of this disclosure, a system for adjusting the accuracy of heart rate measurement in a wearable device includes: a data module configured to acquire multiple data points from multiple data sources, wherein the multiple data points may include user activity data, user information, and environmental conditions, and to determine a user's skin attributes based on the acquired multiple data points; a transmitter module configured to emit infrared (IR) radiation and visible light at an intensity level for measuring the user's heart rate; a receiver module configured to receive scattered IR radiation generated by the interaction of the emitted IR radiation and the emitted visible light based on the user's skin condition and environmental conditions; a correlation module configured to determine a scattered radiation vector based on the scattered IR radiation; and a detection module configured to determine the wavelength of the visible light to be adjusted based on the scattered radiation vector. The transmitter module is also configured to adjust the wavelength of visible light.

[0019] User activity data may include user physical activity data, user information may include at least one of the user's electronic health record data, disease information, age, gender and location, and environmental conditions may include at least one of the user's environment temperature and humidity.

[0020] Multiple data sources may include at least one of the user's electronic health record data, photoplethysmography sensor, temperature sensor, accelerometer, and gyroscope.

[0021] According to one aspect of this disclosure, a non-transitory computer-readable recording medium is provided, wherein the instructions, when executed by at least one processor of a means for improving the accuracy of heart rate measurement in a wearable device, cause the means to perform the following operations: a data module obtains multiple data from multiple data sources, wherein the multiple data may include user activity data, user information, and environmental conditions related to a user; determines a user's skin attributes based on the obtained multiple data; a transmitter module emits infrared (IR) radiation and visible light at an intensity level for measuring the user's heart rate; a receiver module receives scattered IR radiation generated by the interaction of the emitted IR radiation and the emitted visible light based on the user's skin condition and environmental conditions; a correlation module determines a scattered radiation vector based on the scattered IR; a detection module determines the wavelength of the visible light to be adjusted based on the scattered radiation vector; and the transmitter module adjusts the wavelength of the visible light.

[0022] The foregoing description of the invention is merely illustrative and is not intended to be limiting in any way. Other aspects, embodiments, and features will become apparent from the accompanying drawings and the following detailed description, in addition to the illustrative aspects, embodiments, and features described above. Attached Figure Description

[0023] The above and other aspects, features, and advantages of specific embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings, in which: Figure 1 A flowchart illustrating a method for improving the accuracy of heart rate measurement in a wearable device according to one or more embodiments is depicted; Figure 2 A block diagram of a system for performing a method for improving the accuracy of heart rate measurement in a wearable device, according to one or more embodiments, is depicted; Figure 3 A block diagram of a data module according to one or more embodiments is depicted; Figure 4 A block diagram of a skin attribute extraction module according to one or more embodiments is depicted; Figure 5 An exemplary embodiment of determining the amount of sweat by a sweat amount determination submodule according to one or more embodiments is described; Figure 6 A flowchart illustrating a method for determining skin properties according to one or more embodiments is depicted. Figure 7a A block diagram of a transmitter module according to one or more embodiments is depicted; Figure 7b A graphical representation of wavelength division multiplexing utilized by a transmitter module according to one or more embodiments is depicted; Figure 8 A block diagram of a receiver module according to one or more embodiments is depicted; Figure 9 A block diagram of relevant modules according to one or more embodiments is depicted; Figure 10 A flowchart illustrating a method for determining a scattered radiation vector according to one or more embodiments is depicted; Figure 11a A first use case for improving the accuracy of heart rate measurement in wearable devices according to one or more embodiments is described; and Figure 11b A second use case for improving the accuracy of heart rate measurement in wearable devices according to one or more embodiments is described. Detailed Implementation

[0024] Numerous specific details are set forth in the following description to provide a thorough understanding of this disclosure. However, it will be apparent to those skilled in the art that these specific details are merely illustrative and not intended to be limiting. Additionally, it will be noted that systems and / or methods are shown only in block diagram form to avoid obscuring this disclosure. It should be understood that various omissions and equivalent substitutions may be made as appropriate or necessary to cover various applications or implementations without departing from the spirit or scope of this disclosure. Furthermore, it should be understood that the wording and terminology used herein are for the purpose of clarity and should not be considered limiting.

[0025] Furthermore, in this specification, references to "an embodiment" or "embodiment" mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of this disclosure. The phrase "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. Furthermore, the term "an" as used herein does not imply a limitation of quantity, but rather indicates the presence of at least one of the mentioned items. In addition, various features that may be demonstrated by some embodiments but not by others are described. Similarly, various requirements are described that may be requirements for some embodiments but not for others.

[0026] Wearable devices, such as smartwatches, offer a convenient and accessible way to monitor an individual's heart rate. However, these devices do not provide accurate heart rate measurements, especially under changing environmental conditions and factors. Inaccuracies in these measurements often occur due to environmental conditions and factors such as skin type, how the watch is worn, physical activity, gender, and age.

[0027] Improving the accuracy of heart rate measurements in these wearable devices could benefit the achievement of reliable and effective readings for a variety of clinical, research, and personal purposes.

[0028] Figure 1 A flowchart illustrating a process 100 for improving the accuracy of heart rate measurement in a wearable device according to one or more embodiments is shown. (This can be combined with...) Figure 2 The system illustrated in the diagram is used to explain the method. In the flowchart, each box may represent a module, segment, or portion of code, which may include one or more operable instructions for implementing one or more specified logical functions. It should also be noted that in some embodiments, the one or more functions shown as included in a box may occur in a different order than shown in the figures. For example, Figure 1Two consecutive blocks shown in the flowchart may execute substantially simultaneously, or these blocks may sometimes execute in reverse order, depending on the functionality involved. Any process description or block in the flowchart should be understood as representing a module, segment, or portion of code comprising one or more operable instructions for implementing a specific logical function or step in the process, and alternative implementations are included within the scope of the example embodiments, wherein functionality may not execute in the order shown or discussed (including substantially simultaneously or in reverse order), depending on the functionality involved. Furthermore, process descriptions or blocks in the flowchart should be understood as representing decisions made by hardware structures such as state machines.

[0029] like Figure 1 As shown, process 100 can begin at operation 102 and proceed to operation 110.

[0030] In operation 102, multiple data points, including user activity data, user information, and environmental conditions, can be obtained from a data source (e.g., data source 201), and the user's skin attributes can be determined based on the obtained data. In one embodiment, user activity data may include data about the user's physical activity (such as the number of steps taken, the duration of physical activity, and the intensity of activity). User information may include, but is not limited to, information about the user from at least one electronic health record, disease information, age, gender, and location, and environmental conditions may include, but are not limited to, the temperature and humidity of the user's environment. The multiple data points that can be obtained from data source 201 may include the user's electronic health record data 306 and data from a photoplethysmography (PPG) sensor 308, a temperature sensor 310, an accelerometer 312, and a gyroscope 314.

[0031] Next, in operation 104, infrared (IR) radiation and visible light may be emitted. In one embodiment, IR radiation and visible light (which may include red and green light of appropriate intensity levels) may be emitted for measuring the user's heart rate. The transmitter module 204 may use a wavelength division multiplexing (WDM) splitter or combiner to separate light of different wavelengths and combine light of different wavelengths into a single output channel.

[0032] Next, in operation 106, scattered IR radiation generated by the interaction of emitted IR radiation and visible light can be received based on the user's skin condition and environmental conditions. It should be noted that IR radiation scattering can occur because the skin absorbs and reflects light of different wavelengths to varying degrees depending on factors such as skin pigmentation, blood flow, and environmental conditions (such as temperature and humidity). By analyzing the scattered IR radiation, the wearable device can provide accurate heart rate measurements.

[0033] Next, in operation 108, a scattered radiation vector corresponding to the received IR radiation can be determined. In one embodiment, the scattered radiation vector can be determined by a machine learning model that compares the amount of IR radiation absorption and visible light absorption determined from the scattered IR radiation with the amount of absorption at similar wavelengths from database 211 to identify discrepancies. The scattered radiation vector can represent user attributes (such as the user's skin attributes during physical activity). In an embodiment, the scattered radiation vector can provide information such as the presence of sweat due to a user with dry skin walking slowly or performing jogging.

[0034] Subsequently, in operation 110, the wavelength of the visible light to be regulated can be determined and sent to transmitter module 204. In one embodiment, the wavelength of the visible light to be regulated can be determined based on the scattered radiation vector and sent to transmitter module 204 to improve the accuracy of heart rate measurement based on environmental conditions.

[0035] Figure 2 This is a block diagram of a system 200 for improving the accuracy of heart rate measurement in a wearable device according to one or more embodiments. In the embodiments, the wearable device may include, but is not limited to, a fitness tracker, wristband, watch, augmented reality glasses, smart glasses, or any other electronic device worn, implanted, or embedded in the body. In the embodiments, system 200 may be a wearable device, may include a wearable device, or may be included in a wearable device, but the embodiments are not limited thereto.

[0036] System 200 may include a data module 202 for obtaining multiple data points from a data source (e.g., data source 201), including user activity data, user information, and environmental conditions. User activity data may include data about the user's physical activities. User information may include, but is not limited to, information from at least one electronic health record, disease information, age, gender, and location. Environmental conditions may include, but are not limited to, the temperature and humidity of the user's environment. It should be noted that data module 202 may be configured to obtain data for measuring accurate heart rate. Data module 202 may also be configured to determine the user's skin attributes based on the obtained data, as described below. Figure 3 Describe an example.

[0037] Figure 3This is a block diagram illustrating an example of a data module 202 according to one or more embodiments. As shown, the data module 202 may include an input module 302 and a skin attribute extraction module 304, and may be configured to obtain multiple data points from a data source 201, which includes a user's electronic health record data 306 and data from a PPG sensor 308, a temperature sensor 310, an accelerometer 312, and a gyroscope 314. It should be noted that the electronic health record data 306 may be obtained from various sources, including medical institutions such as hospitals, primary care facilities, and rehabilitation centers, and is integrated into the electronic health record system to provide a comprehensive overview of the user's medical history. The PPG sensor 308 may be configured to detect changes in blood flow and sweat, the temperature sensor 310 may be configured to measure changes in skin temperature and sweat, the accelerometer 312 may be configured to detect user activity and monitor watch wear, and the gyroscope 314 may be configured to determine the orientation of the wearable device.

[0038] In one embodiment, input module 302 may be configured to determine user demographic data 316 based on user information obtained from a data source, and skin attribute extraction module 304 may be configured to determine skin attributes 318 using user demographic data from input module 302 and / or body activity data 408, temperature data 410, and humidity data 412 from data source 201, as will be described below. Figure 4 A detailed explanation of the example follows. User demographic data 316 from input module 302, user skin attributes 318 from skin attribute extraction module 304, and multiple data points from data source 201 can be stored in database 211. In this embodiment, database 211 may store information such as skin temperature, current physical activity time, calories burned during current physical activity, humidity, age, gender, weight, height, amount of sweat, and other relevant metrics.

[0039] Figure 4 This is a block diagram of a skin attribute extraction module 304 according to one or more embodiments. Figure 4As shown, the skin attribute extraction module 304 may include a skin type vector determination submodule 402 for determining a user's skin type vector using electronic health record data 306 from data source 201 and / or historical data provided by the user. In an embodiment, the electronic health record data may incorporate the user's comprehensive medical history, including data related to allergies, clinical vital signs, overall health status, diagnoses and related medications, laboratory results, medical procedures experienced, and other relevant medical data. The skin type vector may include or indicate dry skin values, oily skin values, and normal skin values ​​based on dry skin conditions and oily skin conditions. Dry skin conditions may include eczema, psoriasis, xerosis, ichthyosis, and other similar conditions that may cause the skin to become itchy, peel, or crack, while oily skin conditions may include acne, seborrheic dermatitis, contact dermatitis, and other related conditions that may cause the skin to appear oily or greasy. In an embodiment, the skin type vector may include three dimensions (such as dry skin values, oily skin values, and normal skin values), as shown in Table 1 below: Table 1: Skin type vectors based on different skin conditions [Table 1]

[0040] As shown in Table 1, the skin type vector can depend on the values ​​of dry skin condition, oily skin condition, and normal skin condition. The dry skin value can be the sum of the coefficients of all dry skin conditions the user is experiencing, while the oily skin value can be the sum of the coefficients of all oily skin conditions the user is experiencing. The normal skin value depends on the dry skin value and the oily skin value, and is calculated using Equation 1 below: [Equation 1] Normal skin measurement value = [1 - Dry skin measurement value - Oily skin measurement value] If the normal skin measurement value calculated using this equation is negative, the normal skin measurement value can be set to "0".

[0041] It should be noted that each skin value can be calculated based on a coefficient for a significant skin condition. In an example, the coefficient for dry skin conditions such as ichthyosis could be 0.9, because ichthyosis can cause severe dryness, roughness, scaling, and thickening of the skin. The coefficient for psoriasis could be 0.8, because this type of skin condition causes significant dryness, while the coefficient for eczema could be 0.7, taking into account that this condition causes moderate dryness. The coefficient for xerosis could be 0.6, taking into account that this condition causes noticeable but not severe dryness and peeling.

[0042] Furthermore, the coefficient for oily skin conditions (such as seborrheic dermatitis) can be 0.9, because this skin condition leads to excessive oil production. The coefficient for acne can be 0.7, because it produces a moderate amount of oil, while the coefficient for contact dermatitis can be 0.3, taking into account that this condition results in relatively less oil production.

[0043] The skin attribute extraction module 304 may further include a sweat volume determination submodule 404, used to determine sweat volume by utilizing a machine learning model based on user demographic data 316 from input module 302 and body activity data 408, temperature data 410, and humidity data 412 from data source 201. In embodiments, heart rate measurements obtained using the PPG sensor 308 may be directly dependent on humidity, body activity, and temperature, as these factors can affect the skin and further distort PPG readings.

[0044] In this embodiment, low humidity and low temperature may reduce skin barrier function, making the skin more susceptible to mechanical stress and promoting the release of pro-inflammatory cytokines and cortisol from keratinocytes. These conditions may lead to an increase in the number of dermal mast cells, resulting in a more intense skin response to skin irritants and allergens. Therefore, the sweat volume determination submodule 404 can use a machine learning model to determine the amount of sweat, such as... Figure 5 What is depicted.

[0045] In this embodiment, under specific humidity and temperature conditions, skin may redden due to sweat, and this color change may affect PPG readings. Machine learning models can be used to detect such conditions and adjust the readings so that the color change does not affect the actual heart rate measurement.

[0046] Figure 5 An example is shown where the amount of sweat is determined by a submodule for determining the amount of sweat. For example... Figure 5 As shown, a noise reduction factor (denoted as "NRF") can be determined for physical activity, which can be, for example, one of low, medium, and high. In one embodiment, the sweat volume determination submodule 404 can use a machine learning model to determine the noise reduction factor. In another embodiment, the noise reduction factor can be user-defined. Furthermore, the sweat volume determination submodule 404 can use a machine learning model to determine a skin condition factor (denoted as "SCF") for received temperature data 410 and humidity data 412. In an embodiment, the skin condition factor can be determined based on the type of humidity (such as high, medium, and low) and the type of temperature (such as cold, neutral, and hot), where the temperature type can correspond to dry, neutral, and sweating, respectively.

[0047] After determining both the noise reduction factor and the skin condition factor, the sweat volume determination submodule 404 can use these two factors to accurately calculate the amount of sweat present on the skin.

[0048] The skin attribute extraction module 304 may further include a vector merger 406 for determining skin attribute 318 by merging a skin type vector received from the skin type vector determination submodule 402 and a sweat volume determination submodule 404. In an embodiment, the vector merger 406 may use a machine learning model to determine skin attribute 318 containing information about sweat and skin. It should be noted that the values ​​for each dimension of the skin type vector and sweat volume can be in the range of 0 to 1, as shown in Table 2 below: Table 2: Different skin attributes for different skin types and sweat volume.

[0049] [Table 2]

[0050] As shown in Table 2, skin attribute 318 may include both a skin type vector and sweat volume. For example, when the skin type vector is 0.8 (indicating highly oily skin) and the sweat volume is 0.3, due to the presence of oil on the skin, skin attribute 318 may indicate that the sweat factor affects the dryness factor or renders the dryness factor ineffective. As another example, when the skin type vector is 0.6 (indicating oily skin) and the sweat volume is 0.6, the skin attribute may indicate that both the sweat factor and the dryness factor should be considered. As yet another example, when the skin type vector is 0.4 (indicating dry skin) and the sweat volume is 0.2, due to dry skin and low sweat volume, the skin attribute may indicate that the dryness factor affects the sweat factor or renders the sweat factor ineffective. As yet another example, when the skin type vector is 0.7 (indicating highly oily skin) and the sweat volume is 0.8, due to the presence of oil on the skin, the skin attribute may indicate that the sweat factor affects the dryness factor or renders the dryness factor ineffective.

[0051] Reference Figure 6 It describes a method for determining skin properties. For example... Figure 6 As shown, in operation 602, at least one of electronic health record data 306 from data source 201 and historical data provided by the user can be used to determine the user's skin type vector. In one embodiment, the skin type vector may include at least one of dry skin quantity, oily skin quantity, and normal skin quantity based on skin condition (e.g., dry skin condition and oily skin condition). Next, in operation 604, the amount of sweat can be determined by using a machine learning model, using user demographic data 316 from input module 302 and body activity data 408, temperature data 410, and humidity data 412 from data source 210. Subsequently, in operation 606, skin attribute 318 can be determined by merging the skin type vector received from skin type vector determination submodule 402 and the amount of sweat received from sweat amount determination submodule 404.

[0052] Refer again Figure 2 The system 200 may further include a transmitter module 204 configured to emit IR radiation and visible light at appropriate intensity levels for measuring a user's heart rate. In one embodiment, the transmitter module 204 may include, for example, Figure 7a The multiple sub-modules shown.

[0053] Figure 7a This is a block diagram of a transmitter module 204 according to one or more embodiments. The transmitter module 204 may include a controller 702 for receiving input from a data module 202 and a detection module 210, and determining an appropriate intensity level of visible light based on red and green light coefficients. In one embodiment, the visible light includes red and green light. It should be noted that green light has a shorter wavelength, higher frequency, and greater energy than red light, which allows it to penetrate deeper into the pores of the skin than red light. Therefore, green light can be used for operations corresponding to deeper layers of the skin, while red light can be used for operations affecting the surface layers of the skin. The controller may be configured to operate based on skin conditions. The transmitter module 204 may also include a modulator 704 for performing modulation of the amplitude, frequency, or phase of infrared radiation (IR) and green and red light to achieve a determined intensity level and for emission for measuring a user's heart rate. In one embodiment, the transmitter module 204 may use a WDM splitter or combiner to separate different wavelength ranges and combine different wavelength signals into a single output channel, such as... Figure 7b As shown.

[0054] Reference Figure 7b This depicts a graphical representation of WDM. For example, Figure 7b Scenario 721 depicts a scenario where a WDM can be used as a combiner or multiplexer to perform the combination of different spectral bands to obtain optimal results, where signals from different spectral bands are aggregated or combined into a single output channel. For example, in the presence of red and green light signals, a third output signal is created by aggregating or combining these two signals. As another example, Figure 7b Scenario 722 depicts a scenario where WDM can be used as a splitter or demultiplexer to separate different wavelength ranges (especially visible wavelengths under specific conditions). When the input signal has a wide bandwidth, it can be split into output components as needed.

[0055] Refer again Figure 2 The system 200 may further include a receiver module 206 for receiving scattered IR radiation generated by the interaction of emitted IR radiation and visible light with the user's skin condition based on environmental conditions, and providing the user with heart rate. In one embodiment, the receiver module 206 may include, for example, Figure 8 The multiple sub-modules shown.

[0056] Reference Figure 8 The diagram depicts a block diagram of receiver module 206. Receiver module 206 may include a photodetector 802 for detecting scattered infrared radiation and converting it into an electrical signal. Receiver module 206 may also include a preamplifier 804 and a filter 806, wherein the preamplifier 804 amplifies the electrical signal, and the filter 806 filters the amplified signal based on filter coefficients. In one embodiment, the filter coefficients may depend on the transmitted wavelength. In another embodiment, the filter coefficients may depend on the specific filtering requirements of the signal being processed and the type of filter being used. After filtering the signal, additional processing may be performed to increase the signal strength and reduce any unwanted noise or distortion. For example, receiver module 206 may use an amplifier and limiter submodule 808 to improve the quality of the filtered signal. In an embodiment, amplifier and limiter submodule 808 may include an amplifier and a limiter, wherein the amplifier is configured to increase the strength of the filtered signal to an appropriate level for further processing, and the limiter is configured to ensure that the signal does not exceed a specific amplitude to prevent any unwanted distortion or signal clipping. Receiver module 206 may further include a gain control submodule 810 and a decision circuit 812, wherein the gain control submodule 810 is used to improve the signal-to-noise ratio of the amplified signal, reduce the distortion of the amplified signal, and minimize the interference of the amplified signal, and the decision circuit 812 is used to process the amplified signal and provide a signal suitable for the associated module 208. In an embodiment, the decision circuit 812 may include at least one of a low-pass filter and a comparator.

[0057] Refer again Figure 2 The system 200 may further include a correlation module 208 for determining a scattered radiation vector based on the received IR radiation. In one embodiment, the correlation module 208 may include, for example, Figure 9 The PPG sensor 902 and radiation vector creation submodule 904 are shown.

[0058] Figure 9 This is a block diagram of related modules 208 according to one or more embodiments. For example... Figure 9 As shown, the PPG sensor 902 can be configured to receive scattered IR radiation from the receiver module 206, and is also configured to determine the amount of absorbed IR radiation and absorbed visible light (such as green and red light). The radiation vector creation submodule 904 can be configured to determine the scattered radiation vector.

[0059] The radiation vector creation submodule 904 can also be configured to identify discrepancies by using a machine learning model to correlate the amounts of IR radiation absorption and visible light absorption with the amounts of absorption at similar wavelengths corresponding to various skin attributes stored in database 211. In one embodiment, database 211 may be a multidimensional structure storing attributes such as skin attributes of different users, green light absorption, red light absorption, IR radiation absorption, age, and gender. Table 3 illustrates an embodiment of information that may be stored in database 211.

[0060] Table 3: Attributes that can be stored in a database [Table 3]

[0061] As shown in Table 3, database 211 can store information such as skin attributes [0.8, 0.3], algorithmic heart rate (96) calculated using embodiments of this disclosure, and current heart rate (95) from a watch when a male user aged 22 and weighing 95 kg is sweating due to slow walking. Similarly, database 211 can store skin attributes of different users under different conditions, algorithmic heart rate calculated according to embodiments of this disclosure, and current heart rate from a watch.

[0062] In this embodiment, the radiation vector creation submodule 904 can use Equation 2 below to calculate the scattered radiation vector, and can use Equation 3 below to calculate the algorithmic heart rate: [Equation 2] Scattered radiation vector (SRV) = ((K[0] + K[1] – 1) / 10) + 1) [Equation 3] Algorithm heart rate = INT((K[0]+K[1]–1) / 10)+1)×(CHR) In Equations 2 and 3 above, K can represent skin properties, K[0] can represent the dryness or moisture content of the skin, K[1] can represent the oil content of the skin, and CHR can represent the current heart rate calculated by the watch without considering any factors.

[0063] Table 4 illustrates an example of calculating the scattered radiation vector for different skin properties and using the scattered radiation vector to calculate the algorithmic heart rate and the actual heart rate based on the current heart rate stored in database 211.

[0064] Table 4: Determination of scattered radiation vector, algorithmic heart rate, and actual heart rate for different skin properties [Table 4]

[0065] As can be seen from Table 4, there may be a very small difference between the algorithm heart rate and the actual heart rate.

[0066] Reference Figure 10 A flowchart illustrating a method for determining the scattered radiation vector is shown. Figure 10 As shown, in operation 1002, scattered IR radiation can be received from receiver module 206, and the amount of absorbed IR radiation and absorbed visible light (such as green and red light) can be determined. Then, in operation 1004, a scattered radiation vector can be determined, and discrepancies can be identified, for example, by using a machine learning algorithm to correlate the amounts of IR radiation absorption and visible light absorption with the amounts of absorption at similar wavelengths corresponding to various skin attributes stored in a database.

[0067] Refer again Figure 2 The system 200 may also include a detection module 210. The detection module 210 may be configured to determine the wavelength of the visible light to be modulated based on the scattered radiation vector and send it to the transmitter module 204 to improve the accuracy of heart rate measurement based on environmental conditions. In one embodiment, the detection module 210 may determine red and green light coefficients based on the scattered radiation vector and use a coefficient generation neural network to generate an appropriate intensity level of visible light for emission based on the determined red and green light coefficients. Table 5 shows different red and green light coefficients for different scattered radiation vectors, taking into account a normalization factor of 1000.

[0068] Table 5: Red and Green Coefficients for Different Scattered Radiation Vectors [Table 5]

[0069] If the deviation is identified, the red light coefficient and green light coefficient can be calculated using the following equation 4: [Equation 4] Red light:green light coefficient = (absolute difference between red light and green light × scattered radiation vector) / normalization factor Reference Figure 11a This describes the first use case for improving the accuracy of heart rate measurement in wearable devices. For example... Figure 11aAs shown, a user may attempt to measure heart rate in a humid environment. However, a heart rate measurement performed according to the comparative example may provide a heart rate measurement 1111 that includes erroneous heart rate readings, caused by the absorption of infrared radiation by sweat due to humid weather, which may cause the user to feel anxious or worried. Conversely, embodiments of this disclosure provide a heart rate measurement 1112 that includes accurate heart rate readings by adjusting the wavelength / intensity of at least one of the IR radiation emitted by the PPG sensor 308 and light according to the humid environment. For example, embodiments of this disclosure allow the wavelength of the IR radiation to be adjusted to improve the accuracy of the heart rate measurement 1112 by determining the amount of absorbed IR radiation based on environmental conditions, determining the appropriate wavelength to be transmitted based on the amount of scattered IR radiation and the user's skin properties. Embodiments of this disclosure continuously monitor environmental conditions to evaluate the effectiveness of the adjusted wavelength.

[0070] Reference Figure 11b This describes a second use case for improving the accuracy of heart rate measurement in wearable devices. For example... Figure 11b As shown, a user can attempt to measure heart rate while performing strenuous exercise. However, a heart rate measurement performed according to the comparative example may provide a heart rate measurement 1121 that includes erroneous heart rate readings, where the erroneous heart rate readings are due to the absorption of IR radiation by sweat caused by exercise, which may cause the user to feel anxious or worried. In contrast, embodiments of this disclosure provide a heart rate measurement 1122 that includes accurate heart rate readings by adjusting the wavelength / intensity of at least one of the IR radiation and light emitted by the PPG sensor 308 according to the environment and strenuous exercise.

[0071] Therefore, it has been seen that the system and method for improving the accuracy of heart rate measurement in wearable devices according to this disclosure achieve the above-described objectives. Although specific embodiments of this disclosure have been described in detail above, the scope of this disclosure is not limited to the described embodiments. Various changes and modifications should be construed as falling within the scope of this disclosure as defined by the appended claims.

Claims

1. A method for adjusting the accuracy of heart rate measurement in a wearable device, the method comprising: The data module obtains multiple data points from multiple data sources, including user activity data, user information, and environmental conditions related to the user. The user's skin attributes are determined based on the obtained multiple data points; The transmitter module emits infrared (IR) radiation and visible light at an intensity level used to measure the user's heart rate; The receiver module receives scattered IR radiation generated by the interaction between emitted IR radiation and emitted visible light, based on the user's skin condition and the environmental conditions. The scattered radiation vector is determined by the relevant modules based on the scattered IR radiation; The detection module determines the wavelength of the visible light to be modulated based on the scattered radiation vector; and The wavelength of the visible light is adjusted by the transmitter module.

2. The method as described in claim 1, wherein, The user activity data includes the user's physical activity data. The user information includes at least one of the user's electronic health record data, disease information, age, gender, and location. The environmental conditions include the temperature and humidity of the user's environment.

3. The method as described in claim 1, wherein, The multiple data sources include at least one of the user's electronic health record data, photoplethysmography sensor, temperature sensor, accelerometer, and gyroscope.

4. The method of claim 1, further comprising: Using the input module included in the data module, user demographic data are determined based on the user information obtained from the plurality of data sources; as well as The skin attributes are determined using a skin attribute extraction module included in the data module, based on the user demographic data obtained from the input module and at least one of electronic health record data, physical activity data, temperature data, and humidity data obtained from the plurality of data sources.

5. The method of claim 4, wherein, The operation of determining the user's skin attributes includes: The skin type vector determination submodule determines the user's skin type vector based on at least one of the electronic health record data and historical data provided by the user, wherein the skin type vector indicates at least one of dry skin quantity, oily skin quantity, and normal skin quantity based on the user's skin condition; The sweat volume determination submodule uses a machine learning model to determine sweat volume based on the user's demographic data, physical activity data, temperature data, and humidity data; and The vector merger determines the skin attribute by merging the skin type vector determined by the skin type vector determination submodule and the sweat volume determined by the sweat volume determination submodule.

6. The method of claim 4, wherein, The user demographic data, the multiple data entries, and the user's skin attributes are stored in a database.

7. The method of claim 1, further comprising: The controller included in the transmitter module receives input from the data module and the detection module, and determines the intensity level of the visible light based on red and green light coefficients, wherein the visible light includes red and green light; and Using a modulator included in the transmitter module, IR radiation, as well as the green light and the red light, are emitted based on a determined intensity level.

8. The method of claim 1, further comprising at least one of the following operations: Using wavelength division multiplexing (WDM) splitters to separate light of different wavelengths; and A WDM combiner is used to combine light of different wavelengths into a single output channel.

9. The method of claim 1, further comprising: The scattered IR radiation is detected using a photodetector and converted into an electrical signal; The electrical signal is amplified using a preamplifier; The electrical signal is filtered using a filter based on filter coefficients, wherein the filter coefficients depend on the wavelength of the visible light; Use at least one of an amplifier and a limiter to improve the quality of the electrical signal; A gain control submodule is used to improve the signal-to-noise ratio of the electrical signal, reduce the distortion of the electrical signal, and minimize the interference of the electrical signal; The electrical signal is processed using a decision circuit comprising at least one of a low-pass filter and a comparator; and The electrical signal is provided to the relevant module.

10. The method of claim 1, wherein, The operation of determining the scattered radiation vector includes: The scattered IR radiation is received from the receiver module by a photoplethysmography sensor, and the amount of absorbed IR radiation and the amount of absorbed visible light are determined, wherein the absorbed visible light includes at least one of green and red light; and The scattered radiation vector is determined by a radiation vector creation submodule, and biases are identified by using a machine learning model to correlate the amount of IR radiation absorption and visible light absorption with the amount of absorption at similar wavelengths corresponding to multiple skin attributes stored in a database.

11. The method of claim 1, further comprising: The detection module determines the red light coefficient and green light coefficient based on the scattered radiation vector; as well as The intensity level of the visible light is determined using a coefficient-generating neural network based on a determined red light coefficient and a determined green light coefficient.

12. A system for adjusting the accuracy of heart rate measurement in a wearable device, the system comprising: The data module is configured to obtain multiple data points from multiple data sources and determine the user's skin attributes based on the obtained multiple data points, wherein the multiple data points include user activity data, user information, and environmental conditions; The transmitter module is configured to emit infrared (IR) radiation and visible light at an intensity level used to measure the user's heart rate; The receiver module is configured to receive scattered IR radiation generated by the interaction of emitted IR radiation and emitted visible light, based on the user's skin condition and the environmental conditions. The relevant modules are configured to determine the scattered radiation vector based on the scattered IR radiation; and The detection module is configured to determine the wavelength of the visible light to be modulated based on the scattered radiation vector. The transmitter module is also configured to adjust the wavelength of the visible light.

13. The system of claim 12, wherein, The user activity data includes the user's physical activity data. The user information includes at least one of the user's electronic health record data, disease information, age, gender, and location. The environmental conditions include at least one of the temperature and humidity of the user's environment.

14. The system of claim 12, wherein, The multiple data sources include at least one of the user's electronic health record data, photoplethysmography sensor, temperature sensor, accelerometer, and gyroscope.

15. A non-transitory computer-readable recording medium for storing instructions, wherein, When the instructions are executed by at least one processor of a device for measuring heart rate in a wearable device, the device causes the device to perform the following operations: The data module obtains multiple data points from multiple data sources, including user activity data, user information, and environmental conditions related to the user. The user's skin attributes are determined based on the obtained multiple data points; The transmitter module emits infrared (IR) radiation and visible light at an intensity level used to measure the user's heart rate; The receiver module receives scattered IR radiation generated by the interaction between emitted IR radiation and emitted visible light, based on the user's skin condition and the environmental conditions. The scattered radiation vector is determined by the relevant modules based on the scattered IR; The detection module determines the wavelength of the visible light to be modulated based on the scattered radiation vector; and The wavelength of the visible light is adjusted by the transmitter module.

Images