CN117084644B

CN117084644B - A method, device and wearable device for detecting user physiological characteristic indicators

Info

Publication number: CN117084644B
Application number: CN202311306184.XA
Authority: CN
Inventors: 刘泽新
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-10-10
Filing date: 2023-10-10
Publication date: 2024-03-29
Anticipated expiration: 2043-10-10
Also published as: CN117084644A

Abstract

Embodiments of the present application provide a method, device and wearable device for detecting user physiological characteristic indicators, which relate to the technical field of wearable devices. This solution is used to improve the accuracy of wearable devices in detecting user physiological characteristic indicators in user exercise scenarios. The solution includes: acquiring PPG signals and motion signals collected by the motion sensor of the wearable device. The multi-channel PPG signals are determined by the PPG signals collected separately by each channel of the PPG sensor; based on the multi-channel PPG signals and multiple reference signals, determine Multiple signal combinations, multiple reference signals include: infrared signal, green light signal and motion signal; according to the predicted value of physiological characteristic indicators and the main frequency of each reference signal, the energy proportion of each signal combination is calculated; according to each The energy proportion of the signal combination selects a target signal combination that periodically meets the requirements from a variety of signal combinations; predicts the target value of the user's physiological characteristic index based on the target signal combination.

Description

Method and device for detecting physiological characteristic index of user and wearable device

Technical Field

The embodiment of the application relates to the technical field of wearable equipment, in particular to a method and a device for detecting physiological characteristic indexes of a user and the wearable equipment.

Background

With the improvement of living standard, people are focusing on health problems of themselves and families. More and more users use wearable devices (such as smartwatches and smartbracelets) to monitor physiological characteristic parameters of the human body (e.g. step count, sleep, heart rate, blood pressure). For heart rate monitoring on wearable devices, measurement is typically performed by photoplethysmography (PPG). The PPG irradiates the skin of a human body with a light-emitting diode (LED), and the change in reflected light intensity caused by blood flow is measured with a photodiode, thereby obtaining a periodic signal corresponding to heart rhythm.

However, PPG signals are susceptible to factors such as motion state and wearing environment, and further contain a lot of noise, which seriously affects the accuracy of heart rate prediction.

Disclosure of Invention

The embodiment of the application provides a method and device for detecting physiological characteristic indexes of a user and wearable equipment.

In a first aspect, an embodiment of the present application provides a method for detecting a physiological characteristic index of a user, including: an electronic device (e.g., a wearable device) acquires multiple photoplethysmography (PPG) signals and motion signals acquired by a motion sensor of the wearable device, e.g., multiple PPG signals are determined from PPG signals acquired by channels of a PPG sensor of the wearable device, respectively. The electronic device combines the multiple PPG signals with multiple reference signals to obtain multiple signal combinations, the multiple reference signals at least including: infrared signals, green light signals and motion signals acquired by a sensor module of the wearable device. Wherein one signal combination comprises: one of the reference signals and one of the multiple PPG signals, different signal combinations include different reference signals and PPG signals. And the electronic equipment calculates the energy duty ratio of each signal combination in the plurality of signal combinations according to the physiological characteristic index predicted value and the main frequency of each reference signal. And then the electronic equipment selects a target signal combination which meets the requirement periodically from a plurality of signal combinations according to the energy ratio of each signal combination, and predicts the target value of the physiological characteristic index of the user by using the target signal combination.

In the method provided by the embodiment of the invention, multiple paths of PPG signals and multiple reference signals are combined to obtain multiple signal combinations, because each signal combination comprises one path of PPG signal and one reference signal, the subsequent electronic equipment can calculate the energy ratio of each signal combination, and select the target signal combination with the periodicity meeting the requirements from the multiple signal combinations to predict the heart rate according to the periodicity of each signal combination.

In a possible implementation manner of the first aspect, the electronic device predicts a target value of the physiological characteristic index of the user using the target signal combination, including: for example, if the electronic device has a neural network model, the electronic device may input the target signal combination into the neural network model to obtain the target value of the physiological characteristic index of the user.

In a possible implementation manner of the first aspect, the electronic device predicts a target value of the physiological characteristic index of the user using the target signal combination, including: the electronic device may provide the target signal combination to the other device such that the other device inputs the target signal combination into the neural network model to obtain a target value of the physiological characteristic index of the user. And then the other equipment feeds back the target value of the physiological characteristic index of the user to the electronic equipment, the scheme can realize the interaction between the electronic equipment and the other equipment to obtain the target value of the physiological characteristic index of the user, and the calculated amount of the electronic equipment can be reduced.

In one possible implementation manner of the first aspect, the multiple paths of PPG signals include a PPG signal acquired by each channel of a PPG sensor of the wearable device separately and a PPG average signal obtained by the PPG signals acquired by each channel separately.

In one possible implementation of the first aspect, the multiple PPG signals include PPG signals acquired separately by channels of a PPG sensor of the wearable device.

It can be appreciated that the PPG sensor of the wearable device may be a PPG sensor having a plurality of channels, each channel may collect a path of PPG signal when the PPG sensor collects PPG signals, and then the electronic device may average the PPG signals collected by each channel separately to obtain a PPG average signal. Of course, a weight value may be configured for each channel, and then a PPG average signal may be obtained according to the weight value of each channel and one path of PPG signal acquired by the channel respectively.

In a possible implementation manner of the first aspect, the electronic device selects a target signal combination that is periodically satisfactory from a plurality of signal combinations according to an energy ratio of each signal combination, including: the electronic device selects at least one signal combination with a front energy ratio from the plurality of signal combinations according to the energy ratio of the plurality of signal combinations. The electronic device selects a signal combination which is periodically satisfactory from the at least one signal combination as a target signal combination.

Since the earlier the energy ratio of a set of signal combinations indicates that the signal combination is closer to the heart rate/blood pressure/blood oxygen saturation of the user, the target value of the finally predicted physiological characteristic index can be made more accurate and closer to the value of the actual physiological characteristic index of the user by selecting a periodically satisfactory signal combination from at least one of the signal combinations that is earlier in energy ratio as the target signal combination for predicting the target value of the physiological characteristic index of the user.

In a possible implementation manner of the first aspect, the electronic device selects a signal combination that is periodically satisfactory from at least one signal combination as the target signal combination, including: the electronic device calculates a periodic intensity for each of the at least one signal combination. The electronic device selects a signal combination which meets the requirement of periodicity from at least one signal combination as a target signal combination according to the periodical intensity of each signal combination.

In this embodiment, the signal combination with periodicity meeting the requirement may refer to that the periodic strength of a group of signal combinations is greater than or equal to a preset periodic strength.

In a possible implementation manner of the first aspect, the periodicity of the target signal combination is a signal combination with the strongest periodicity of the plurality of signal combinations.

Since the PPG signal used for detecting heart rate/blood pressure/blood oxygen saturation and the like is a signal with relatively strong periodicity, when the interference of the signal is relatively small, the periodicity of the PPG signal is relatively strong, and when the user is in a motion state, the collected PPG signal may have relatively large interference, so that the periodicity of the PPG signal is destroyed, and therefore, by selecting the signal combination with the strongest periodicity as the target signal combination, the target value of the physiological characteristic index predicted according to the target signal combination can be made more accurate.

In a possible implementation manner of the first aspect, the physiological characteristic index predicted value is a preset value, or the physiological characteristic index predicted value is a target value of a physiological characteristic index of the user predicted in the P-1 th round, or the physiological characteristic index predicted value is predicted by one path of target PPG signals and motion signals in the multiple paths of PPG signals, where P is greater than or equal to 2.

For example, when the target value of the physiological characteristic index of the user is predicted in the P-th round, the target value of the physiological characteristic index of the user predicted in the P-1-th round can be adopted, so that the target value of the finally predicted physiological characteristic index can be more accurate through repeated (such as p=3) iterative training.

In a possible implementation manner of the first aspect, the method provided in an embodiment of the present application further includes, before calculating the energy ratio of each of the plurality of signal combinations according to the physiological characteristic index prediction value and the dominant frequencies of the plurality of reference signals: the electronic device selects a target PPG signal from the multiple PPG signals. The electronic device determines a physiological characteristic index prediction value according to the target PPG signal and the motion signal. For example, the electronic device inputs the target PPG signal and the motion signal into the neural network model to obtain the physiological characteristic index prediction value.

As an example, the target PPG signal may be any one of the multiple PPG signals, although the target PPG signal may also be a PPG average signal of the multiple PPG signals. The embodiments of the present application are not limited in this regard. Because each channel of the PPG sensor has advantages and disadvantages, the quality of the PPG signals collected by each channel has differences, and therefore, the accuracy of obtaining the physiological characteristic index predicted value can be higher by selecting the PPG average signal corresponding to the PPG signals collected by each channel as the target PPG signal.

In a possible implementation manner of the first aspect, before the electronic device acquires multiple paths of PPG signals and a motion signal acquired by a motion sensor of the wearable device, a method provided by an embodiment of the present application further includes: in a case where the user wears the wearable device, in response to the heart rate detection command, the wearable device acquires a PPG signal through a PPG sensor of the wearable device, and acquires an acceleration ACC signal as a motion signal through a running sensor of the wearable device. The electronic device performs preprocessing on the PPG signal and the acceleration ACC signal acquired by the PPG sensor to obtain ACC effective spectrum data corresponding to the ACC signal and PPG effective spectrum data corresponding to the PPG signal, wherein the preprocessing at least comprises filtering processing. The electronic equipment calculates the power spectral density PSD of the PPG effective spectral data and the power spectral density PSD of the ACC effective spectral data respectively and performs normalization processing so as to obtain a plurality of paths of PPG signals and motion signals.

In a possible implementation manner of the first aspect, the physiological characteristic index includes: one or more of heart rate, blood pressure, or blood oxygen saturation.

In a possible implementation manner of the first aspect, the electronic device predicts a target value of a physiological characteristic index of the user according to the target signal combination, including: the electronic device inputs the target signal combination into the neural network model to obtain a target value of the physiological characteristic index of the user.

In a second aspect, an embodiment of the present application provides a device for detecting a physiological characteristic index of a user, where the device includes: the acquisition unit is used for acquiring multipath photoplethysmogram PPG signals and motion signals acquired by a motion sensor of the wearable device, wherein the multipath PPG signals are determined by PPG signals acquired by channels of the PPG sensor of the wearable device respectively. A determining unit, configured to determine a plurality of signal combinations according to a plurality of PPG signals and a plurality of reference signals, where the plurality of reference signals at least includes: infrared signals, motion signals and green light signals acquired by infrared sensors of the wearable equipment; wherein one of said signal combinations comprises: one of the reference signals and one of the multiple PPG signals, different signal combinations include different reference signals and PPG signals. The processing unit is used for calculating the energy duty ratio of each signal combination in the plurality of signal combinations according to the physiological characteristic index predicted value and the main frequencies of the plurality of reference signals, and selecting a target signal combination which periodically meets the requirements from the plurality of signal combinations according to the energy duty ratio of each signal combination; and the prediction unit is used for predicting the target value of the physiological characteristic index of the user according to the target signal combination.

In a possible implementation manner of the second aspect, the multiple paths of PPG signals include a PPG average signal obtained by respectively acquiring one path of PPG signal by each channel of a PPG sensor of the wearable device and one path of PPG signal respectively acquired by each channel.

In a possible implementation manner of the second aspect, the processing unit is specifically configured to select, from a plurality of signal combinations, at least one signal combination having a front energy ratio according to the energy ratio of each signal combination, and to select, as the target signal combination, the signal combination having a periodicity that meets the requirement from the at least one signal combination.

In a possible implementation manner of the second aspect, the apparatus may further include: a calculation unit for calculating a period intensity of each of at least one of the signal combinations. And the processing unit is specifically used for selecting the signal combination which meets the requirement in periodicity from at least one signal combination as the target signal combination according to the periodical intensity of each signal combination.

In a possible implementation manner of the second aspect, the period intensity of the target signal combination is the signal combination with the strongest period intensity of the plurality of signal combinations.

In a possible implementation manner of the second aspect, the predicted value of the physiological characteristic index is a preset value, that is, the predicted value of the physiological characteristic index is pre-stored in an electronic device such as a i.e. a device, so that when the method provided by the application is used for first-round predicting the target value of the physiological characteristic index of the user, the preset value can be used to calculate the energy duty ratio of each signal combination.

In a possible implementation manner of the second aspect, the predicted value of the physiological characteristic index is a target value of the physiological characteristic index of the user predicted in the P-1 th round, and P is an integer greater than or equal to 2. For example, the electronic device such as the wearable device can utilize the method provided by the application to perform multiple iterations to determine the target value of the physiological characteristic index of the user, and then before each iteration, the electronic device such as the wearable device can utilize the target value of the physiological characteristic index of the user calculated in the previous iteration before the previous iteration to calculate the energy ratio of each signal combination.

In a possible implementation manner of the second aspect, the physiological characteristic index prediction value is predicted by one target PPG signal and the motion signal in multiple M PPG signals. The electronic equipment such as wearable equipment can utilize one target PPG signal and one predicted physiological characteristic index predicted value of the motion signal in the multiple M paths of PPG signals before the target value of the physiological characteristic index of the first-round user is predicted by utilizing the method provided by the application, and then the target value of the physiological characteristic index of the first-round user is predicted by utilizing the predicted value of the physiological characteristic index.

In a possible implementation manner of the second aspect, the selecting unit is further configured to select a target PPG signal from multiple PPG signals. And the prediction unit is also used for determining a physiological characteristic index predicted value according to the target PPG signal and the motion signal.

In one possible implementation manner of the second aspect, the target PPG signal is a PPG average signal.

In a possible implementation manner of the second aspect, the acquisition unit is configured to, when the wearable device is worn by a user, respond to a signal detection command triggered by the user or when a physiological index detection period of the wearable device is reached, consider that the signal detection command is detected, obtain, by the wearable device, a photoplethysmogram PPG signal through a PPG sensor of the wearable device, and obtain, by an operation sensor of the wearable device, an acceleration ACC signal. The processing unit is further used for preprocessing the photoplethysmogram PPG signal and the acceleration ACC signal to obtain ACC effective spectrum data corresponding to the ACC signal and PPG effective spectrum data corresponding to the PPG signal, and the preprocessing at least comprises filtering processing; the processing unit is further used for respectively calculating PSD of the PPG effective spectrum data and PSD of the ACC effective spectrum data, and carrying out normalization processing to obtain multipath PPG signals and motion signals acquired by the motion sensor of the wearable device.

In a possible implementation manner of the second aspect, the physiological characteristic index includes: one or more of heart rate, blood pressure, or blood oxygen saturation.

In a possible implementation manner of the second aspect, the prediction unit is specifically configured to input the target signal combination into the neural network model to obtain the target value of the physiological characteristic index of the user.

In a third aspect, embodiments of the present application provide an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the various possible implementations as in the first aspect or the first aspect when the computer program is executed.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the various possible implementations of the first aspect or aspects.

In a fifth aspect, embodiments of the present application provide a chip comprising a processor; the processor is configured to read and execute a computer program stored in the memory to perform the various possible implementations as in the first aspect or the first aspect.

Drawings

Fig. 1 is a schematic view of a scenario provided in an embodiment of the present application;

fig. 2A is a schematic diagram of a principle of detecting heart rate by using a PPG sensor according to an embodiment of the present disclosure;

fig. 2B is a schematic structural diagram of a wearable device according to an embodiment of the present application;

FIG. 3 is a flowchart of a method for detecting a physiological characteristic index of a user according to an embodiment of the present application;

FIGS. 4a and 4b are diagrams illustrating energy ratios of different signal combinations according to embodiments of the present application;

FIG. 4c is a schematic diagram illustrating the duty cycle of a channel selection scheme in a different scenario according to an embodiment of the present application;

FIG. 5 is a flowchart illustrating another method for detecting a physiological characteristic index of a user according to an embodiment of the present application;

FIG. 6 is a schematic diagram of the difference between the target value and the actual value of each round of iterative training in multiple rounds according to the embodiment of the present application;

fig. 7 is a schematic structural diagram of a device for detecting a physiological characteristic index of a user according to an embodiment of the present application.

Detailed Description

In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", etc. are used to distinguish the same item or similar items having substantially the same function and effect. For example, the first signal and the second signal are merely for distinguishing different syntax parsing results, and the sequence thereof is not limited. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ.

In this application, the terms "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

PPG is a non-invasive detection technology that converts a biological signal of a human body into an electrical signal by using an optical principle, specifically, directs LED light to skin, receives light that is reflected or transmitted after being absorbed by skin tissue by a photosensor, and converts the electrical signal obtained by the photosensor into a digital signal to obtain a PPG signal.

The method is widely used for health monitoring of human body in the aspects of physiological heart rate, blood oxygen, pressure and the like due to the advantages of noninvasive, simple, portable and the like. The heart rate is one of parameters for measuring the heart beat capacity, and has important medical significance for accurate detection of the heart rate. In an ideal case, the PPG signal is able to accurately detect heart rate values at various moments in the human body. However, due to noise influence of complex scenes such as hardware, temperature, motion and the like, the true signal of the PPG is distorted, so that the accuracy of heart rate calculation is greatly restricted. The motion artifact is the most affected, which causes the loss or deformation of the wave crest and the wave trough on the PPG time domain signal, so that the accuracy of the time domain counting method is reduced, the frequency domain is displayed as the abnormity of the PPG spectrum peak, the main frequency of the PPG signal at the current moment cannot be accurately positioned, and the accurate result is difficult to obtain. Therefore, how to adaptively eliminate complex noise in the PPG signal and improve the heart rate detection accuracy is an important problem.

The method for detecting the physiological characteristic index of the user can be applied to electronic equipment such as mobile phones and wearable equipment, for example, the wearable equipment can be intelligent watches, intelligent bracelets and the like, and the specific type of the electronic equipment is not limited.

The wearable device provided by the embodiment of the application is a portable device which can be integrated to the skin, clothes or accessories of a user, has a computing function, and can be connected with a mobile phone and various terminal devices. By way of example, the wearable device may be a smart watch, a smart wristband, a portable music player, a health monitoring device, a computing or gaming device, a smart phone, accessories, and the like. In some embodiments, the wearable device may be a watch worn around the wrist of the user.

The electronic device comprises a PPG sensor, a motion sensor (such as an ACC sensor) and a sensor module. The PPG sensor has M-1 channels, each channel of the M channels is used for collecting one path of PPG signals, in other words, the PPG sensor can collect M-1 paths of PPG signals, namely PPG signals 1-M-1. As an example, M may be equal to 5, i.e. there may be a 4-channel PPG sensor in the electronic device. The sensor module is used for collecting green light signals and infrared signals, and LEDs of the sensor module can emit light sources with different wavelengths so as to collect the green light signals and the infrared signals. Of course, the infrared signal and the green signal in the present application may also be collected by different sensor modules, which is not limited in the embodiment of the present application.

As an example, the heart rate detection principle of PPG: the volume of human blood will change with the heart rhythm, and the light intensity received by the light sensor will change with the heart rhythm. The light intensity variation signal can be converted into an electrical signal by PPG Analog Front End (AFE) chip adjustment, thereby calculating the heart rate value.

Principle of detecting blood oxygen saturation of PPG: by measuring the concentration of oxygen and hemoglobin by utilizing the difference of absorption spectra of hemoglobin and deoxyhemoglobin in oxygen to red light (660 nm) and infrared light (940 nm), a continuous dynamic blood oxygen monitoring PPG signal can be provided.

Fig. 1 is a schematic view of a scenario provided in an embodiment of the present application, where, as shown in fig. 1 (a), the smart watch has a multi-channel PPG sensor (e.g., a four-channel PPG sensor) and can detect parameter values, such as heart rate values, of physiological characteristic indexes of a human body by using PPG technology. Optionally, the wearable device may display the heart rate value.

Optionally, the system architecture may further include a terminal device wirelessly connected to the wearable device, where the terminal device may receive and display the heart rate value sent by the smart watch for viewing by the user.

If the user wants to measure the current heart rate, the user may trigger the smart watch to display an interface shown in (b) in fig. 1, where the interface includes a heart rate detection control, the user may click on the heart rate detection control to trigger a PPG sensor in the smart bracelet to start collecting PPG signals of the user, that is, PPG signals 1 to 4, as shown in (c) of fig. 1 and fig. 2A, taking the PPG sensor to detect the heart rate as an example, the PPG sensor irradiates the skin of the human body with a light-emitting diode (LED), and measures a change in reflected light intensity caused by blood flow with a photodiode, so as to obtain a periodic signal corresponding to heart rhythm, for example, in the case of collecting PPG signals 1 to 4, an infrared signal and a motion signal of the user, the smart watch may predict the heart rate of the user and display the heart rate of the user by a method provided by the embodiment of the present application, as shown in (d) of fig. 1.

It can be appreciated that in the case where the user clicks the heart rate detection control, the ACC sensor, the sensor module and the PPG sensor in the smart watch work synchronously to collect the ACC signal, the infrared signal, the green signal and the multi-path PPG signal, respectively.

For convenience of explanation, fig. 1 and the following embodiments describe a wearable device by taking a smart watch as an example.

Fig. 2B is a schematic functional block diagram of a wearable device provided by some embodiments of the present application. Illustratively, the wearable device 100 may be a smart watch or a smart bracelet, or the like. Referring to fig. 2B, the wearable device 100 may include, for example, a processor 110, a sensor module 130, a display screen 140, a memory 160, a power supply module 170, an audio device 180, a wireless communication module 191, and a mobile communication module 192.

It is to be understood that the components shown in fig. 2B do not constitute a particular limitation of the wearable device 100, and that the wearable device 100 may also include more or less components than illustrated, or may combine certain components, or may split certain components, or may have a different arrangement of components.

The processor 110 may include one or more processing units, such as: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors. The controller may be, among other things, a neural hub and a command center of the wearable device 100. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution. In other embodiments, memory may also be provided in processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to reuse the instruction or data, it can be directly recalled from the memory, avoiding repeated accesses, reducing the latency of the processor 110, and thus improving the efficiency of the wearable device 100.

In an embodiment of the present application, the processor 110 may be configured to: multiple PPG signals and motion signals are acquired, and the multiple PPG signals and multiple reference signals are combined to obtain multiple signal combinations, wherein the multiple reference signals at least comprise: infrared signals, green light signals and motion signals acquired by a sensor module of the wearable equipment; calculating the energy duty ratio of each signal combination in a plurality of signal combinations according to the physiological characteristic index predicted value and the main frequency of each reference signal; and finally, selecting a target signal combination which meets the requirement periodically from a plurality of signal combinations according to the energy duty ratio of each signal combination, and predicting the target value of the physiological characteristic index of the user by using the target signal combination.

Optionally, where the wearable device is a smart watch or smart bracelet, the wearable device may further include a rotatable input device, which may be a mechanical device, that the user contacts such that the rotatable input device rotates to enable functions or operations of the wearable device 100 to start, scroll the list, page switch, rotate unlock, desktop icon zoom, adjust signals (e.g., adjust the size of the volume or brightness), etc. In some embodiments, the user may contact the rotatable input device, and may further cause other forms of movement, such as panning or tilting, of the rotatable input device, so as to implement other functions or operations of the wearable device, for example, by pressing the rotatable input device to implement powering on or powering off the wearable device.

It is understood that the wearable device 100 may include one or more rotatable input means.

The sensor module 130 may include one or more sensors, for example, may include a PPG sensor 130A, a pressure sensor 130B, a capacitance sensor 130C, an acceleration sensor 130D, an ambient light sensor 130E, a proximity light sensor 130F, a touch sensor 130G, a light sensor 130H, and the like. It should be understood that fig. 2B is merely an example of a few sensors, and in practical applications, the wearable device 100 may further include more or fewer sensors, or use other sensors with the same or similar functions instead of the above-listed sensors, and the like, and the embodiments of the present application are not limited.

The PPG sensor 130A may be used to detect heart rate, i.e. the number of beats per unit time. In some embodiments, PPG sensor 130A may include a light transmitting unit and a light receiving unit. The light transmitting unit may irradiate a light beam into a human body (such as a blood vessel), the light beam is reflected/refracted in the human body, and the reflected/refracted light is received by the light receiving unit to obtain an optical signal. Since the transmittance of blood changes during the fluctuation, the emitted/refracted light changes, and the optical signal detected by the PPG sensor 130A also changes. The PPG sensor 130A may convert the optical signal into an electrical signal, determining the heart rate to which the electrical signal corresponds. In the embodiment of the present application, the PPG sensor 130A may be disposed in the rotatable input device or in the housing of the wearable apparatus 100, and the function of PPG detection may be achieved by the optical signal detected by the PPG sensor 130A. The PPG sensor 130A in the embodiment of the present application has a plurality of channels, each for acquiring one path of PPG signal.

The pressure sensor 130B is configured to sense a pressure signal, and may convert the pressure signal into an electrical signal. In some embodiments, pressure sensor 130B may be disposed on display screen 140. The pressure sensor 130B is of various kinds, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like.

The capacitive sensor 130C may be used to detect the capacitance between two electrodes to achieve a particular function. In some embodiments, the capacitance sensor 130C may be used to detect a capacitance between the human body and the wearable device 100, which may reflect whether the contact between the human body and the wearable device is good, and may be applied to Electrocardiography (ECG) detection, where the human body may act as one electrode.

The acceleration sensor 130D may be used to detect the magnitude of acceleration of the wearable device 100 in various directions (typically three axes). The wearable device 100 is a wearable device, when a user wears the wearable device 100, the wearable device 100 moves under the driving of the user, so that the acceleration of the acceleration sensor 130D in each direction can reflect the movement state of the human body. For example, the acceleration sensor 130D in the embodiment of the present application is used to collect ACC signals of the user.

An ambient light sensor 130E for sensing an ambient light parameter. For example, the ambient light parameter may include the ambient light intensity or a coefficient of ultraviolet light in the ambient light, or the like. The wearable device 100 may adaptively adjust the brightness of the display screen according to the perceived intensity of ambient light. The ambient light sensor 130E may also be used to automatically adjust white balance during photographing. Ambient light sensor 130E may also cooperate with proximity light sensor 130F to detect whether wearable device 100 is in a pocket to prevent false touches. Proximate to the light sensor 130F, may include, for example, a Light Emitting Diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. The wearable device 100 emits infrared light outwards through the light emitting diode. The wearable device 100 detects infrared reflected light from nearby objects using a photodiode. When sufficient reflected light is detected, it may be determined that there is an object in the vicinity of the wearable device 100. When insufficient reflected light is detected, the wearable device 100 may determine that there is no object in the vicinity of the wearable device 100. The wearable device 100 can detect that the user holds the wearable device 100 close to the ear to talk by using the proximity light sensor 130F, so as to automatically extinguish the screen to achieve the purpose of saving electricity. The proximity light sensor 130F may also be used in holster mode, pocket mode to automatically unlock or lock the screen.

The touch sensor 130G may be disposed on a display screen, and the touch sensor 130G and the display screen form a touch screen, which is also referred to as a "touch screen". The touch sensor 130G is for detecting a touch operation acting thereon or thereabout. The touch sensor 130G may communicate the detected touch operation to the processor to determine the type of touch event. Visual output associated with a touch operation may be provided through a display screen. In other embodiments, the touch sensor 130G may also be disposed on the surface of the display screen at a different location than the display screen.

The light sensor 130H may be used to detect the rotation angle and rotation direction (counterclockwise or clockwise) of a rotatable input device, such as a crown, to obtain angle data, such that the processor processes rotation-related traffic based on the angle data.

The display screen 140 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), a mini, a Micro led, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like. In some embodiments, a touch sensor may be disposed in the display screen to form a touch screen, which is not limited in this embodiment. It will be appreciated that in some embodiments, the wearable device 100 may or may not include the display 140, for example, when the wearable device 100 is a wristband, the display may or may not be included, and when the wearable device 100 is a wristwatch, the display may be included.

Memory 160 may be used to store computer-executable program code including instructions. The processor 110 executes various functional applications of the wearable device 100 and data processing by executing instructions stored in the memory. The memory 160 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), etc., as embodiments of the present application are not limited.

The power module 170 may power various components in the wearable device 100, such as the processor 110, the sensor module 130, and the like. In some embodiments, the power module 170 may be a battery or other portable power element. In other embodiments, the wearable device 100 may also be connected to a charging device (e.g., via a wireless or wired connection), and the power module 170 may receive power input from the charging device for storage by a battery.

The audio device 180 may include a microphone, a speaker, or an earpiece, etc. that may receive or output sound signals.

A horn, also called a "loudspeaker", is used to convert an audio electrical signal into a sound signal. The wearable device 100 may listen to music through a speaker or to hands-free conversation.

Headphones, also known as "receivers," are used to convert the audio electrical signals into sound signals. When the wearable device 100 is answering a phone call or voice message, the voice can be heard by placing the earpiece close to the human ear.

Microphones, also known as "microphones" and "microphones", are used to convert sound signals into electrical signals. When making a call or transmitting voice information, a user can sound near the microphone through the mouth, inputting a sound signal to the microphone. The wearable device 100 may be provided with at least one microphone. In other embodiments, the wearable device 100 may be provided with two microphones, and may implement a noise reduction function in addition to collecting sound signals. In other embodiments, the wearable device 100 may also be provided with three, four, or more microphones to enable collection of sound signals, noise reduction, identification of sound sources, directional recording functions, etc.

In addition, the wearable device 100 may have a wireless communication function. With continued reference to fig. 2B, the wearable device 100 may also include a wireless communication module 191, a mobile communication module 192, one or more antennas 1, and one or more antennas 2. The wearable device 100 may implement wireless communication functions through the antenna 1, the antenna 2, the wireless communication module 191, and the mobile communication module 192.

In some embodiments, the wireless communication module 191 may provide a solution for wireless communication that is applied on the wearable device 100 that conforms to various types of network communication protocols or communication technologies. By way of example, the network communication protocol may include a wireless local area network (wireless local area networks, WLAN) (e.g., wireless fidelity (wireless fidelity, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), and the like. For example, the wearable device 100 may establish a bluetooth connection with other electronic devices, such as a cell phone, through a bluetooth protocol. In other embodiments, the wireless communication module 191 may be one or more devices that integrate at least one communication processing module.

The wireless communication module 191 receives electromagnetic waves via the antenna 1, modulates the electromagnetic wave signals, filters the electromagnetic wave signals, and transmits the processed signals to the processor 110. The wireless communication module 191 may also receive a signal to be transmitted from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves to radiate through the antenna 1. In some embodiments, the wireless communication module 191 may be coupled to one or more antennas 1 such that the wearable device 100 may communicate with a network and other devices through wireless communication techniques.

In some embodiments, the mobile communication module 192 may provide a solution for wireless communication conforming to various types of network communication protocols or communication technologies for use on the wearable device 100. Illustratively, the network communication protocol may be various wired or wireless communication protocols, such as Ethernet, global System for Mobile communications (global system for mobile communications, GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (wideband code division multiple access, WCDMA), time division code division multiple access (time-division code division multiple access, TD-SCDMA), long term evolution (long term evolution, LTE), voice over Internet protocol (voice over Internet protocol, voIP), communication protocols supporting a network slice architecture, or any other suitable communication protocol. For example, the wearable device 100 may establish a wireless communication connection with other electronic devices, such as a cell phone, through a WCDMA communication protocol.

In other embodiments, the mobile communication module 192 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), or the like. In other embodiments, at least some of the functional modules of the mobile communication module 192 may be disposed in the processor 110. In other embodiments, at least some of the functional modules of the mobile communication module 192 may be disposed in the same device as at least some of the modules of the processor 110.

The mobile communication module 192 may receive electromagnetic waves from the antenna 2, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation. The mobile communication module 192 may also amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 2 to radiate. In some embodiments, the mobile communication module 192 may be coupled with one or more antennas 2 such that the wearable device 100 may communicate with a network and other devices through wireless communication technology.

As shown in fig. 3, fig. 3 is a method for detecting a physiological characteristic index of a user provided in an embodiment of the present application, where the following embodiment describes an implementation body of the method as a wearable device, and of course, the method provided in the embodiment of the present application may also be implemented by a device applied to the wearable device, such as a chip, or the method provided in the embodiment of the present application may also be implemented by a device such as a mobile phone, a server, a tablet computer, or a chip applied to the devices, which is not limited in this embodiment of the present application, and the method includes:

step 301, the wearable device acquires multiple paths of PPG signals and a motion signal acquired by a motion sensor of the wearable device.

The multi-path PPG signals are determined by one path of PPG signals respectively acquired by each channel of a PPG sensor of the wearable equipment.

As one example, a PPG sensor and a motion sensor (e.g., an acceleration ACC sensor) are provided in the wearable device. The PPG sensor has a plurality of channels (hereinafter, M-1 channels are taken as an example), and each channel can detect and obtain a PPG signal. Therefore, the multiple paths of PPG signals in the embodiments of the present application may include one path of PPG signal acquired by each of the M-1 paths, that is, the multiple paths of PPG signals include the M-1 path of PPG signal, or the multiple paths of PPG signals may include the M-1 path of PPG signal and a PPG average signal obtained according to the M-1 path of PPG signal. The PPG signal may reflect heart rate data/blood pressure data/blood oxygen saturation etc. data of the user. The PPG average signal is used for reflecting the average value of one path of PPG signal acquired by each channel.

As an example, an acceleration sensor may detect an Acceleration (ACC) signal, which may reflect movement data of a user.

As an example, the execution body of the embodiment of the present application may be an electronic device such as a mobile phone, for example, wearable devices such as smart bracelets may send PPG signals (possibly including noise) collected by using PPG sensors of the wearable devices and motion signals collected by the motion sensors to the mobile phone, and then the electronic device such as the mobile phone executes the method provided by the embodiment of the present application to obtain the target value of the user physiological characteristic index of the user.

As another example, the execution body in the embodiment of the present application may be a wearable device, for example, the smart band uses a PPG sensor of the smart band to collect a PPG signal (possibly including noise) and a motion signal collected by the motion sensor to execute the method provided in the embodiment of the present application to obtain the target value of the user physiological characteristic index of the user.

For example, taking the heart rate of the user as an example, when the preset heart rate detection triggering condition is met, the wearable device can be triggered to perform heart rate detection. For example, the wearable device receives a heart rate detection command and, in response to the heart rate detection command, triggers the PPG sensor to detect or collect a PPG signal and triggers the acceleration sensor to detect or collect an ACC signal, such that the wearable device acquires the PPG signal and the ACC signal.

As an example, the wearable device has a first control, for example, the first control may be a heart rate detection control, a blood pressure detection control, or an oxygen blood detection control, which is not limited in the embodiment of the present application. The first control may be a button on the wearable device, or the first control may be a virtual control on an operable interface of the wearable device, which is not limited in this embodiment of the present application.

Taking a scenario that the wearable device measures the heart rate of the user as an example, when the wearable device detects that the user triggers a control for heart rate measurement, the wearable device can collect the PPG signal by using the PPG sensor. The ACC sensor also synchronously captures motion signals, such as ACC signals.

In addition to the wearable device collecting the PPG signal with the PPG sensor under the triggering of the user, the wearable device may also collect the PPG signal of the user periodically through the PPG sensor. For example, if the user sets to measure the heart rate every 30 minutes in the wearable device, the wearable device can collect the heart rate of the user by using the PPG sensor every 30 minutes, and calculate the heart rate by the method provided by the embodiment of the application.

Step 302, the wearable device determines a plurality of signal combinations according to the plurality of PPG signals and the plurality of reference signals.

Each signal combination comprises a path of PPG signal and a reference signal, and the PPG signal and the reference signal included in different signal combinations are different. For instance, as an example, the number of reference signals is denoted as N, where the N reference signals may include an infrared signal collected by a sensor module of the wearable device, a motion signal, and a green signal collected by the sensor module. In other words, one signal combination includes: one of the motion signal, the infrared channel signal and the green channel signal, and one of the M PPG signals.

In summary, the M PPG signals and the N reference signals are combined to obtain m×n signal combinations.

For example, taking M equal to 5,N =3 as an example, i.e., taking a PPG sensor as a four-channel sensor as an example, the PPG signals collected by the PPG sensor include four paths of PPG signals, the N reference signals include 3 reference signals, i.e., an ACC signal, an infrared signal, and a green signal as examples, and the four paths of PPG signals include: PPG signal 1, PPG signal 2, PPG signal 3 and PPG signal 4, and the PPG average signal of the four paths of PPG signals is a GAvg signal, for example, the signals obtained by combining PPG signal 1, PPG signal 2, PPG signal 3, PPG signal 4, GAvg signal and various reference signals are combined as follows:

signal combination 1: PPG signal 1 and infrared signal;

signal combination 2: PPG signal 2 and infrared signal;

signal combination 3: PPG signal 3 and infrared signal;

signal combination 4: PPG signal 4 and infrared signal;

signal combination 5: GAvg signals and infrared signals;

signal combination 6: PPG signal 1 and ACC signal;

signal combination 7: PPG signal 2 and ACC signal;

signal combination 8: PPG signal 3 and ACC signal;

signal combination 9: PPG signal 4 and ACC signal;

signal combination 10: GAvg signals and ACC signals;

Signal combination 11: PPG signal 1 and green signal;

signal combination 12: PPG signal 2 and green signal;

signal combination 13: PPG signal 3 and green signal;

signal combination 14: PPG signal 4 and green signal;

signal combination 15: GAvg signal and green signal.

In one possible implementation of the present application, when performing signal combining, in the case that the reference signal is only a green signal, the reference signal may be regarded as 0, so that 5 signal combinations obtained when the PPG signal 1, the PPG signal 2, the PPG signal 3, the PPG signal 4, and the GAvg signal are respectively green signals include only the PPG signal 1, the PPG signal 2, the PPG signal 3, the PPG signal 4, and the GAvg signal. That is, in the case where the green signal is regarded as a 0 reference signal, the signal combination 11 may be replaced with: PPG signal 1; signal combination 12: PPG signal 2; signal combination 13: PPG signal 3; signal combination 14: PPG signal 4; signal combination 15: GAvg signal.

Step 303, the wearable device calculates the energy duty ratio of each of the plurality of signal combinations according to the physiological characteristic index predicted value and the dominant frequency of each reference signal.

For example, the wearable device may calculate the energy duty cycle of each of the plurality of signal combinations based on the physiological characteristic index prediction value, the dominant frequency of each reference signal, and the spectral subtraction. For example, the wearable device may calculate the energy duty cycle of each of the signal combinations 1 to 15.

In a specific implementation process, the wearable device can calculate the energy duty ratio of each signal combination by itself. Of course, the wearable device may also send the physiological characteristic index predicted value, the main frequency of the motion signal (i.e. the ACC signal) and other terminal devices in communication with the wearable device to calculate the energy ratio of each signal combination through the server or other terminal devices, and feed back the energy ratio to the wearable device, so that the calculation amount of the wearable device may be reduced.

Spectral subtraction is by subtracting the noise spectrum from the spectrum of the noisy signal, which in the embodiment of the invention is calculated jointly by the noise dominant frequency (i.e. ACC dominant frequency) and the frequency bandwidth (empirically determined). The method comprises the following steps: firstly, calculating the frequency spectrums of a PPG signal and an ACC signal through short-time Fourier transform, identifying a corresponding frequency band of an ACC main frequency according to the energy of the frequency spectrums, and finally subtracting the frequency spectrum with the ACC main frequency as a center and a certain frequency spectrum bandwidth from the PPG frequency spectrum.

Optionally, the wearable device calculates the energy duty ratio of each of the plurality of signal combinations according to the physiological characteristic index predicted value and the dominant frequency of each reference signal by a notch method. In actual operation, in the case of selecting ACC as a reference signal, a notch method is used; in the case of selecting infrared as a reference signal, spectral subtraction is used. The specific process of the notch method is as follows: dominant frequency identification (as in spectral subtraction), the dominant frequency band is filtered from the PPG signal using a notch filter.

It will be appreciated that by calculating the energy duty cycle of each signal combination it can be derived whether each signal combination is concentrated within the predicted range of heart rate/blood pressure/blood oxygen saturation, i.e. relatively close to heart rate/blood pressure/blood oxygen saturation. Of course, the higher the energy duty cycle of the signal combination, the closer to the actual value the prediction of heart rate/blood pressure/blood oxygen saturation using the signal combination.

Because PPG signals of different channels may also differ, the energy duty cycle of the signal combination obtained by combining PPG signals of different channels with the same reference signal also differs. Fig. 4a illustrates the energy ratio of 3 signal combinations obtained by combining the PPG signal 4 and three reference signals, and it can be seen from fig. 4a that the energy ratio of the PPG signal 4 and the signal combination obtained by the ACC signal is 0.287, the energy ratio of the PPG signal 4 and the signal combination obtained by the infrared signal is 0.123, and in the case that the PPG signal 4 is a single signal combination, the energy ratio of the PPG signal 4 is 0.220. Fig. 4b illustrates the energy ratio of 3 signal combinations obtained by combining the PPG signal 1 and three reference signals, and it can be seen from fig. 4b that the energy ratio of the signal combination obtained by the PPG signal 1 and the ACC signal is 0.198, the energy ratio of the signal combination obtained by the PPG signal 1 and the infrared signal is 0.343, and the energy ratio of the PPG signal 1 is 0.221 in the case that the PPG signal 1 is a single signal combination.

Step 304, the wearable device selects a target signal combination which periodically meets requirements from a plurality of signal combinations according to the energy ratio of each signal combination.

Step 305, the wearable device predicts a target value of the physiological characteristic index of the user according to the target signal combination.

As an example, the wearable device has a neural network model therein, and the neural network model is used for predicting a physiological characteristic index value of the user according to an input target signal combination, that is, one path of PPG and one reference signal included in the target signal combination input into the neural network model.

The neural network model in the embodiment of the application is a model obtained by training a deep Attention mechanism (Attention) network by taking ACC sample data and PPG sample data as input, and heart rate/blood pressure/blood oxygen saturation and other labels and motion scene labels as target variables, and has heart rate/blood pressure/blood oxygen saturation detection capability.

As another example, the neural network model may be deployed in a server or in an electronic device such as a mobile phone, in order to reduce the calculation amount of the wearable device, the wearable device may send the target signal combination to the electronic device such as the server or the mobile phone, then the electronic device such as the server or the mobile phone inputs a path of PPG and a reference signal included in the target signal combination into the neural network model to obtain a target value of the physiological characteristic index of the user, and then the electronic device such as the server or the mobile phone feeds back the target value of the physiological characteristic index of the user to the wearable device.

For example, taking the target signal combination as the signal combination 8, the wearable device may input the PPG signal 3 and the ACC signal into the neural network model to obtain the target value of the physiological characteristic index of the user.

It is worth to say that, in the scenario of measuring the heart rate of the user, the neural network model is a neural network model for measuring the heart rate of the user, and correspondingly, the target value of the physiological characteristic index of the user obtained by the wearable device is the target value of the heart rate of the user. In the scene of measuring the blood pressure of the user, the neural network model is used for measuring the blood pressure of the user, and correspondingly, the target value of the physiological characteristic index of the user obtained by the wearable device is the target value of the blood pressure of the user.

In any scenario, the neural network model may be an existing neural network model for predicting heart rate, or a neural network model for predicting blood pressure, or a neural network model for predicting blood oxygen saturation, which is not limited in the embodiments of the present application.

In one possible embodiment of the present application, the target value of the physiological characteristic index of the user may be output after the target value of the physiological characteristic index is obtained by the wearable device, for example, as shown in (d) diagram in fig. 1, the target value of the physiological characteristic index is displayed on a display interface of the wearable device. Or the wearable device may send the target value of the physiological characteristic index of the user to the electronic device such as the mobile phone for displaying, so that the user can view the target value on the terminal device. For example, in the case where an exercise health APP is installed in an electronic device such as a mobile phone, the electronic device such as a mobile phone may display a heart rate in an interface of the exercise health APP.

Optionally, in the method provided by the embodiment of the present application, the wearable device may further store a time corresponding to the target value of the physiological characteristic index of the user, so as to draw a change curve of the physiological characteristic index of the user according to the target values of the physiological characteristic indexes of the user measured by the user at different times of the same day in a later period. Or drawing a change curve of physiological characteristic indexes of the user on different dates, which is not limited in the embodiment of the application.

In one possible embodiment of the present application, the method provided in the embodiment of the present application may be circularly performed by the wearable device, for example, the wearable device may perform at least three iterative computations to obtain the target value of the physiological characteristic index of the user. This can improve the accuracy of the target value of the finally obtained physiological characteristic index.

When the first iteration is performed (i.e. the first iteration), the wearable device may use a preset value or a value of a physiological characteristic index predicted by one path of target PPG signals and motion signals in multiple paths of PPG signals as a physiological characteristic index prediction value, so as to calculate the energy duty ratio of each group of signal combination. And when the iteration of the P (P is more than or equal to 2) round is carried out, the wearable device can take the target value of the physiological characteristic index calculated in the previous round (namely P-1 round) as the predicted value of the physiological characteristic index so as to calculate the energy ratio of each group of signal combination. For example, p=any one of 2, 3, 4, … …. For example, assuming that the value of the physiological characteristic index obtained by predicting one path of target PPG signal and the motion signal in the multiple paths of PPG signals is used as the physiological characteristic index predicted value and the target value 1 of one physiological characteristic index is obtained by predicting through the steps 303 to 305 in the first iteration, the target value 1 of the physiological characteristic index is used as the physiological characteristic index predicted value and the target value 2 of one physiological characteristic index is obtained by predicting through the steps 303 to 305 in the second iteration, and the target value 2 of the physiological characteristic index is the value of the physiological characteristic index of the user predicted in the second iteration.

In one possible embodiment of the present application, the predicted value of the physiological characteristic index is a preset value, or the predicted value of the physiological characteristic index is a target value of the physiological characteristic index of the user predicted in the P-1 th round, or the predicted value of the physiological characteristic index is predicted by one path of target PPG signal and the motion signal in the M paths of PPG signals, where P is greater than or equal to 2.

As an example, the heart rate value of the user at different times/under different exercise conditions may be obtained and then used as a preset value in calculating the energy duty cycle of each of the mxn signal combinations.

In order to improve the accuracy of the predicted heart rate, the wearable device can execute the method for multiple times in an iterative mode to obtain the target value of the physiological characteristic index of the user. And when each iteration is executed, the target value of the physiological characteristic index of the user obtained by the previous calculation is used as the predicted value of the physiological characteristic index, and the next calculation is carried out to obtain the target value of the physiological characteristic index of the user.

In one possible implementation of the present application, the above step 304 may be implemented in the following manner: the wearable device selects k signal combinations with the energy duty ratio being higher than or equal to 2 and smaller than or equal to MXN from the MXN signal combinations according to the energy duty ratio of the MXN signal combinations. The wearable device selects a signal combination which meets the requirement periodically from k signal combinations as a target signal combination. For example, the wearable device may select the signal combination with the strongest periodicity from the k signal combinations as the target signal combination.

For example, the wearable device may calculate the periodic intensity of each of the k signal combinations, and then select, as the target signal combination, a signal combination with the strongest periodicity from the k signal combinations according to the periodic intensity of the k signal combinations.

For each signal in the signal combination, its period strength can be derived by calculating the autocorrelation coefficients of the signal. The method comprises the following steps: the first step is to find out the corresponding delay value when the autocorrelation coefficient is highest by drawing the autocorrelation function diagram of the signal. And step two, calculating the maximum periodic intensity of the signal according to the delay value calculated in the step one.

Of course, the wearable device may also select a set of signal combinations from k signal combinations that are periodically satisfactory (e.g., greater than or equal to the period intensity threshold) as the target signal combination.

The accuracy of the predicted target value of the physiological characteristic index of the user may be improved by selecting the most periodic set of signal combinations as the target signal combination for subsequent calculation of the target value of the physiological characteristic index of the user.

For example, the wearable device may select 5 signal combinations with a front energy ratio from the signal combinations 1 to 15 according to the energy ratio of each of the signal combinations 1 to 15, for example, the signal combination 1, the signal combination 2, the signal combination 5, the signal combination 7, and the signal combination 9. The wearable device then determines the periodic intensities corresponding to signal combination 1, signal combination 2, signal combination 5, signal combination 7, signal combination 9, respectively. The wearable device then selects a group of signal combinations (such as the signal combination 5) with the strongest periodicity from the signal combinations according to the periodic intensities respectively corresponding to the signal combinations 1, 2, 5, 7 and 9 as target signal combinations.

In one possible implementation of the present application, the above step 304 may be implemented in the following manner: the wearable device calculates a periodic strength for each of the mxn signal combinations. The wearable device determines a target signal combination from the mxn signal combinations according to the periodic intensity of each of the mxn signal combinations and the energy duty ratio of each of the signal combinations.

For example, the wearable device may determine, as the target signal combination, a set of signal combinations whose period intensity is satisfactory and whose duty ratio is satisfactory among the mxn signal combinations.

In one possible embodiment of the present application, before the wearable device calculates the energy duty ratio of each of the mxn signal combinations according to the physiological characteristic index prediction value and the dominant frequency of the ACC signal, the method provided in the embodiment of the present application further includes: the wearable device selects a target PPG signal from the multiple PPG signals. The wearable device determines a physiological characteristic index predicted value according to the target PPG signal and the motion signal.

In one possible implementation of the present application, the wearable device determining the physiological characteristic index prediction value according to the target PPG signal and the motion signal may include: the wearable device inputs the target PPG signal and the motion signal into the neural network model to obtain the physiological characteristic index predicted value.

In one possible implementation of the present application, the wearable device may optionally select one PPG signal from among multiple PPG signals as the target PPG signal. Or the wearable device may take the PPG average signal in the multiple PPG signals as the target PPG signal. The obtained physiological characteristic index predicted value is more similar to the real physiological characteristic index value of the user by taking the PPG average signal in the multipath PPG signals as the target PPG signal to predict the physiological characteristic index predicted value.

In one possible implementation manner of the present application, the physiological characteristic index related to the embodiment of the present application includes: one or more of heart rate, blood pressure, or blood oxygen saturation.

The reference signals due to different motion states are different: periodic regular motion-ACC; slight motion, random noise and on-channel near-IR, so fig. 4c shows the various channel selection scheme duty cycles for different scenarios, as shown in fig. 4 c. As can be seen from fig. 4c, in the signal combination obtained by combining the reference signal acquired in different scenes with the PPG signal in different scenes, the duty cycle of the different signal combinations is different.

As shown in fig. 5, fig. 5 illustrates a detailed flowchart of predicting a heart rate based on a smart watch, which is provided by an embodiment of the present application, by taking a wearable device as the smart watch and taking heart rate prediction of a user performed by the smart watch as an example, the method includes:

Step 501, in response to a triggered heart rate detection command, the smart watch collects PPG signals of a user by using a PPG sensor, collects ACC signals of the user by using an ACC sensor, and collects infrared signals by using a sensor module of the smart watch.

Step 502, the smart watch performs preprocessing on the PPG signal and the ACC signal collected by the smart watch, so as to obtain ACC effective spectrum data and PPG effective spectrum data.

The preprocessing may include fourier transform (fast Fourier transform, FFT) and filtering. The filtering process may be a bandpass filtering process.

For example, the signals collected by the smart watch may include some noise or signals with unsatisfactory frequency bands, so the smart watch may perform bandpass filtering processing on the signals collected in step 501 to filter out unwanted signals in the signals collected by the smart watch, so as to obtain the processed signals. In the embodiment of the application, after the wearable device acquires the ACC signal, the wearable device may perform FFT on the ACC signal to obtain a corresponding ACC spectrum. And then, carrying out band-pass filtering treatment on the ACC frequency spectrum, and filtering noise data to obtain an ACC effective frequency spectrum. Similarly, after acquiring the PPG signal, the wearable device may perform FFT on the PPG signal to obtain a corresponding PPG spectrum. And then, carrying out band-pass filtering treatment on the PPG spectrum to filter noise data, and obtaining a PPG effective spectrum.

Step 503, the smart watch calculates the PSD of the ACC effective spectrum data and the PSD of the PPG effective spectrum data, and performs normalization processing to obtain an ACC signal and five paths of PPG signals. Wherein the five PPG signals include a PPG average signal GAvg of four PPG signals.

It can be appreciated that after the smart watch obtains the ACC signal and the five PPG signals, the smart watch may combine the ACC signal, the infrared signal, the green signal, and the like collected by the smart watch as reference signals with the five PPG signals to obtain 15 signal combinations.

Step 504, the smart watch selects a PPG average signal GAvg from the five channels of PPG signals and selects an ACC signal from the reference signals as a characteristic signal combination.

And 505, the smart watch inputs the characteristic signal combination into the neural network model to obtain the physiological characteristic index predicted value of the user.

Step 506, the smart watch uses the predicted value of the physiological characteristic index of the user as a pseudo-gold mark to calculate the energy duty ratio of 15 signal combinations.

In step 507, the smart watch combines five channels of PPG signals, which are four channels of PPG signals and its PPG average signal GAvg, with three reference signals to obtain 15 signal combinations.

Step 508, the smart watch calculates the dominant frequency of the ACC signal.

Step 509, the smart watch calculates the energy duty ratio of 15 signal combinations by using the predicted value of the physiological characteristic index of the user, the dominant frequency of each reference signal and the spectral subtraction.

Step 510, the smart watch selects k signal combinations with the front energy ratio according to the energy ratio of 15 signal combinations.

For example, the smart watch may sort the 15 signal combinations according to the energy ratios of the 15 signal combinations, and then select k signal combinations with the energy ratios that are the front from the 15 signal combinations after sorting.

Step 511, the smart watch calculates the period intensity of k signal combinations.

Step 512, the smart watch selects a group of signal combinations with strongest periodicity according to the periodical intensities of the k signal combinations.

Step 513, the smart watch determines the target value of the physiological characteristic index of the user according to the most periodic set of signal combinations.

It should be noted that, the scheme shown in fig. 5 may perform loop iteration to refer to the accuracy of the target value of the physiological characteristic index of the user, and when determining the target value of the physiological characteristic index of the user for the first time, the wearable device may use the predicted value of the physiological characteristic index of the user determined in steps 504 to 506 as a pseudo-gold standard, so as to determine the energy duty ratio of various signal combinations in step 509. In the subsequent iteration process, the wearable device for each iteration of P rounds may use the target value of the physiological characteristic index of the user obtained in the steps 509 to 513 of P-1 times as the pseudo-gold mark, so as to determine the energy duty ratio of various signal combinations in the step 509. For example, when determining the target value of the physiological characteristic index of the user for the first time, the wearable device may use the predicted value of the physiological characteristic index of the user determined in steps 504 to 506 as the pseudo-gold mark, and after steps 509 to 513, the wearable device may output the target value 1 of the physiological characteristic index of the user. In order to make the final output target value of the physiological characteristic index of the user more accurate, the wearable device may perform a second iteration, and in the second iteration, the wearable device may use the target value 1 of the physiological characteristic index of the user output for the first time as a pseudo-gold mark, and after steps 509 to 513, the wearable device may output the target value 2 of the physiological characteristic index of the user. After the second iteration, the wearable device may use the target value 2 of the physiological characteristic index of the user as a pseudo-gold mark, perform the third iteration, and after steps 509 to 513, the wearable device may output the target value 3 of the physiological characteristic index of the user. And repeating the iterative computation for a plurality of times, and taking the finally obtained target value P of the physiological characteristic index of the user as the target value of the physiological characteristic index of the user and outputting the target value P. As can be seen in fig. 6, the difference between the sample average (i.e., the predicted target value) and the class average (actual value) gradually decreases over multiple rounds of iterative training.

It can be understood that, in order to obtain a more accurate target value of the physiological characteristic index of the user, in the embodiment of the present application, when determining the target value of the physiological characteristic index of the user, the wearable device may perform P iterations, where P is an integer greater than or equal to 1, and when p=1, i.e. perform 1 iteration calculation, at this time, the predicted value of the physiological characteristic index of the user determined in steps 504 to 506 is used as the pseudo-gold mark. For example, P may be equal to 3, i.e., three iterative computations are performed. Of course, the wearable device in the embodiment of the present application may also perform an iterative calculation, that is, P is equal to 1, which is not limited in the embodiment of the present application.

As shown in fig. 7, fig. 7 is a schematic structural diagram of an apparatus for detecting a physiological characteristic index of a user according to an embodiment of the present application, where the apparatus may be an electronic device such as a wearable device or the apparatus may be a chip applied to the wearable device, as shown in fig. 7, the apparatus may include: an acquisition unit 501, a determination unit 502, a processing unit 503, and a prediction unit 504. The acquiring unit 501 is configured to acquire multiple paths of photoplethysmogram PPG signals and motion signals acquired by a motion sensor of a wearable device, where the multiple paths of PPG signals are determined by PPG signals acquired by channels of the PPG sensor of the wearable device respectively;

A determining unit 502, configured to determine a plurality of signal combinations according to the plurality of PPG signals and a plurality of reference signals, where the plurality of reference signals at least includes: an infrared signal acquired by an infrared sensor of the wearable device, the motion signal and a green light signal; wherein one of said signal combinations comprises: one of the reference signals and one of the multiple PPG signals, the reference signals and PPG signals comprised by different combinations of the signals being different;

a processing unit 503, configured to calculate an energy ratio of each of the plurality of signal combinations according to the predicted value of the physiological characteristic index and the dominant frequencies of the plurality of reference signals, and select a target signal combination that is periodically satisfactory from the plurality of signal combinations according to the energy ratio of each of the plurality of signal combinations;

a prediction unit 504, configured to predict a target value of the physiological characteristic index of the user according to the target signal combination.

As an example, the determining unit 502, the processing unit 503, and the predicting unit 504 may be integrated in a processor as shown in fig. 2B, and the acquiring unit 501 may be implemented by a sensor module in fig. 2B, which is not limited in the embodiment of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

It should be appreciated that reference throughout this specification to "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, various embodiments are not necessarily referring to the same embodiments throughout the specification. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described embodiments of the electronic device are merely illustrative, e.g., the division of the modules is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

In addition, the term "and/or" herein is merely an association relation describing an association object, and means that three kinds of relations may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application should be defined by the claims, and the above description is only a preferred embodiment of the technical solution of the present application, and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method of detecting a physiological characteristic index of a user, comprising:

acquiring multiple paths of photoplethysmogram PPG signals and motion signals acquired by a motion sensor of a wearable device, wherein the multiple paths of PPG signals are determined by PPG signals acquired by channels of the PPG sensor of the wearable device respectively;

determining a plurality of signal combinations according to the multipath PPG signals and a plurality of reference signals, wherein the plurality of reference signals at least comprise: infrared signal, green light signal and the motion signal that the sensor module of wearable equipment gathered, wherein, one signal combination includes: one of the reference signals and one of the multiple PPG signals, the reference signals and PPG signals included in different signal combinations being different;

Calculating the energy ratio of each signal combination in a plurality of signal combinations according to the predicted value of the physiological characteristic index and the main frequency of each reference signal, wherein the energy ratio represents the energy ratio of a heart rate frequency band, a blood pressure frequency band or a blood oxygen saturation frequency band,

the predicted value of the physiological characteristic index is a preset value, or,

the physiological characteristic index predicted value is a target value of a physiological characteristic index of the user predicted in the P-1 round, P is more than or equal to 2, and the physiological characteristic index predicted value is used for predicting the target value of the physiological characteristic index of the user in the P round, or,

the physiological characteristic index predicted value is obtained by predicting one path of target PPG signal and the motion signal in the multiple paths of PPG signals;

selecting at least one of said signal combinations having a front energy ratio from a plurality of said signal combinations based on the energy ratio of each of said signal combinations;

selecting the signal combination with the periodicity meeting the requirement from at least one signal combination as a target signal combination, wherein the periodicity is the periodicity of the signal combination, and the requirement indicates that the periodic intensity of one signal combination is greater than or equal to the preset periodic intensity;

And predicting a target value of the physiological characteristic index of the user according to the target signal combination.

2. The method of claim 1, wherein the multiple PPG signals comprise a PPG average signal derived from one PPG signal acquired separately for each of the channels of the PPG sensor and one PPG signal acquired separately for each of the channels.

3. The method of claim 1, wherein said selecting said signal combination from at least one of said signal combinations that periodically meets said requirement as said target signal combination comprises:

calculating a period intensity for each of at least one of said signal combinations;

and selecting the signal combination which periodically meets the requirement from at least one signal combination as the target signal combination according to the periodical intensity of each signal combination.

4. A method according to any one of claims 1 to 3, wherein the periodic intensity of the target signal combination is the signal combination with the strongest periodic intensity among the plurality of signal combinations.

5. A method according to any one of claims 1 to 3, further comprising:

Selecting the target PPG signal from the multiple PPG signals;

and determining the physiological characteristic index predicted value according to the target PPG signal and the motion signal.

6. The method according to any one of claim 1 to 3, wherein,

the target PPG signal is a PPG average signal corresponding to one path of PPG signal respectively collected by each channel of a PPG sensor of the wearable equipment.

7. A method according to any one of claims 1-3, wherein before the acquiring the multiple PPG signals and the motion signal acquired by the motion sensor of the wearable device, the method further comprises:

in the case that a user wears the wearable device, in response to a signal detection command, the wearable device acquires a PPG signal through a PPG sensor of the wearable device, and acquires an acceleration ACC signal as the motion signal through a running sensor of the wearable device;

preprocessing a PPG signal and an acceleration ACC signal obtained by the PPG sensor to obtain ACC effective spectrum data corresponding to the ACC signal and PPG effective spectrum data corresponding to the PPG signal, wherein the preprocessing at least comprises filtering processing;

And respectively calculating the power spectral density PSD of the PPG effective spectral data and the power spectral density PSD of the ACC effective spectral data, and carrying out normalization processing to obtain the multipath PPG signals and the motion signals.

8. A method according to any one of claims 1 to 3, wherein the physiological characteristic index comprises: one or more of heart rate, blood pressure, or blood oxygen saturation.

9. A method according to any one of claims 1 to 3, wherein predicting the target value of the physiological characteristic index of the user according to the target signal combination comprises:

and inputting the target signal combination into a neural network model to obtain a target value of the physiological characteristic index of the user.

10. A wearable device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of any of claims 1 to 9 when executing the computer program.

11. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 9.

12. A chip, comprising a processor;

the processor is configured to read and execute a computer program stored in a memory to perform the method of any one of claims 1 to 9.