Heart rate determination method and apparatus, device, storage medium

Abstract

Embodiments of the present application disclose a heart rate determination method and device, equipment and storage medium, comprising: determining red light physiological signals and green light physiological signals corresponding to a target object in a preset time period. Filtering the green light physiological signals based on the red light physiological signals to obtain target physiological signals in which noise information in the green light physiological signals is removed. Determining the heart rate of the target object based on the target physiological signals. Embodiments of the present application can filter only two signals of red light physiological signals and green light physiological signals, remove motion artifacts in real time and efficiently, obtain target physiological signals clearly representing physiological information of the target object, and further improve the accuracy of the finally determined heart rate of the target object. Moreover, the filtering process is simple and has small calculation amount, and the heart rate can be determined in real time in the process of detecting physiological signals.

Description

Technical Field

[0001] This application relates to the field of computer technology, and to, but is not limited to, a method, apparatus, device, and storage medium for determining heart rate. Background Technology

[0002] Currently, most wristband heart rate monitoring devices obtain heart rate data using algorithms based on photoplethysmography (PPG). During exercise, in addition to the effective pulse signal, the PPG signal contains a significant amount of motion noise, making accurate heart rate calculations impossible through spectral analysis. To address this issue, numerous PPG signal preprocessing methods for removing motion noise have been proposed: such as using independent variable analysis (ICA) to remove motion artifacts; using adaptive noise cancellation (ANC) to remove motion artifacts; and employing the Troika model for signal decomposition, sparse signal reconstruction, and spectral peak tracking of the original PPG signal; wavelet denoising; and empirical mode decomposition. However, these methods for addressing motion noise in PPG signals suffer from drawbacks: excessive computational load hindering real-time calculations, or poor noise removal effectiveness leading to significant errors in heart rate calculations. Summary of the Invention

[0003] In view of this, the heart rate determination method, apparatus, device, and storage medium provided in the embodiments of this application can remove noise from biological signals through simple filtering methods and improve the accuracy of the filtering results. The heart rate determination method, apparatus, device, and storage medium provided in the embodiments of this application are implemented as follows:

[0004] A first aspect of this application provides a method for determining heart rate, including:

[0005] Determine the red and green physiological signals of the target object within a preset time period;

[0006] The green light physiological signal is filtered based on the red light physiological signal to obtain a target physiological signal with noise removed from the green light physiological signal.

[0007] The heart rate of the target object is determined based on the target physiological signals.

[0008] A second aspect of this application also provides a heart rate determination device, comprising:

[0009] The signal acquisition module is used to determine the red light physiological signal and green light physiological signal of the target object within a preset time period;

[0010] The signal filtering module is used to filter the green light physiological signal based on the red light physiological signal to obtain a target physiological signal with noise information removed from the green light physiological signal.

[0011] A heart rate determination module is used to determine the heart rate of the target object based on the target physiological signal.

[0012] The electronic device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.

[0013] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method provided in this application embodiment.

[0014] The heart rate determination method, apparatus, electronic device, and computer-readable storage medium provided in this application determine the red and green physiological signals of a target object within a preset time period. The green physiological signal is filtered based on the red physiological signal to obtain a target physiological signal with noise removed. The heart rate of the target object is then determined based on this target physiological signal. Thus, this application embodiment can filter only the red and green physiological signals, efficiently removing motion artifacts in real time and obtaining a target physiological signal that clearly represents the physiological information of the target object, thereby improving the accuracy of the final determined heart rate. Furthermore, this filtering process is simple and computationally inefficient, enabling real-time heart rate determination during physiological signal detection, thus solving the technical problems mentioned in the background art. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram of an application scenario according to an embodiment of this application is shown;

[0017] Figure 2 A flowchart of a heart rate determination method according to an embodiment of this application is shown;

[0018] Figure 3 A schematic diagram of an adaptive neural network according to an embodiment of this application is shown;

[0019] Figure 4 A schematic diagram of an adaptive filtering module in an adaptive neural network according to an embodiment of this application is shown;

[0020] Figure 5A flowchart of another heart rate determination method according to an embodiment of this application is shown;

[0021] Figure 6 A schematic diagram of a heart rate determination device according to an embodiment of this application is shown;

[0022] Figure 7 A schematic diagram of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0025] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0026] It should be noted that the terms "first, second, third" used in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order of objects. It can be understood that "first, second, third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0027] The heart rate determination method of this application embodiment can be executed by an electronic device, which may include, but is not limited to, mobile phones, wearable devices (such as smartwatches, smart bracelets, smart glasses, etc.), tablet computers, laptops, vehicle terminals, PCs (Personal Computers), etc. The function implemented by this method can be achieved by a processor in the electronic device calling program code. Of course, the program code can be stored in a computer storage medium. Therefore, the electronic device includes at least a processor and a storage medium.

[0028] The heart rate determination method of this application embodiment can be used to detect the heart rate of living objects such as people and pets. Heart rate detection refers to measuring the number of times the heart of the measured object beats per minute through various methods. The detection result can be used to assess the heart function and physical condition of the measured object.

[0029] Currently, heart rate measurement methods in related technologies can include various methods such as heart rate measurement via electrocardiogram, heart rate measurement via auscultation, heart rate measurement via Doppler ultrasound, heart rate measurement via pressure sensing, heart rate measurement via magnetic induction, heart rate measurement via bioelectrical impedance analysis, and heart rate measurement via photoplethysmography.

[0030] In the aforementioned heart rate measurement methods, electrocardiography (ECG) measures heart rate based on the principle that the heart generates weak bioelectrical activity during contraction and relaxation. ECG captures these bioelectrical signals by placing electrodes on the body surface, amplifying and recording them. The R wave in the ECG waveform is generated by ventricular depolarization, and its frequency is closely related to heart rate. The heart rate can be calculated by measuring the RR interval (the time interval between two adjacent R waves). This method has the advantages of high accuracy, providing detailed information on cardiac electrical activity, and can be used to diagnose cardiac diseases such as arrhythmias and myocardial ischemia. However, this heart rate measurement method requires specialized equipment and operators, and usually needs to be performed in specific locations such as hospitals or clinics.

[0031] Among the aforementioned heart rate measurement methods, the auscultatory method involves listening to the heartbeat through a stethoscope. Normally, a heartbeat produces a regular "thump-thump" sound, namely the first and second heart sounds. Doctors can estimate the heart rate by counting the number of heartbeats with a stethoscope. The advantages of this method are that it requires no complex equipment and is simple and non-invasive. The disadvantages are that it is greatly affected by environmental noise and the operator's experience, resulting in unstable measurement results and making it unsuitable for accurate heart rate detection.

[0032] In the aforementioned heart rate measurement methods, Doppler ultrasound heart rate detection utilizes the Doppler effect of ultrasound waves. When an ultrasound beam irradiates moving blood, the frequency of the reflected ultrasound waves changes. By analyzing this frequency change, the blood flow velocity and direction can be measured, thereby calculating the heart rate. The advantages of this heart rate detection method are that it is non-invasive and safe, can be used for echocardiography, and can provide detailed information on heart structure and function. The disadvantages are similar to those of electrocardiogram (ECG) monitoring methods: it requires specialized measuring equipment and operators, and typically needs to be performed in specific locations such as hospitals or clinics.

[0033] In the aforementioned heart rate measurement methods, the principle of pressure sensing for heart rate detection involves placing a pressure sensor on a part of the body, such as the finger or wrist, to capture pulse signals by detecting changes in pressure on the blood vessel walls. When the heart beats, the pressure within the arteries changes periodically, and this change is synchronized with the heart rate. By analyzing the frequency of the pressure waveform, the heart rate can be calculated. The advantage of this heart rate detection method is the simplicity of the detection device, making it suitable for users to carry and use flexibly. However, this method is significantly affected by the device's wearing position and pressure changes, resulting in lower accuracy.

[0034] Among the aforementioned heart rate measurement methods, the magnetic induction method detects heart rate based on the principle of magnetic field induction. When the heart beats, the flow of blood generates weak magnetic field changes. These magnetic field changes can be detected by a highly sensitive magnetic induction sensor and converted into electrical signals, which are then used to calculate the heart rate. The advantage of this heart rate detection method is that it can be performed without contact with the subject's skin, making it suitable for some special applications. However, the technology is relatively complex and costly, limiting its application scope and lacking universality.

[0035] Among the aforementioned heart rate measurement methods, the bioelectrical impedance method detects heart rate by applying a weak alternating current to the body and measuring the change in resistance as the current passes through. During a heartbeat, the periodic changes in blood volume within the chest cavity cause changes in resistance. By analyzing the frequency of these resistance changes, the heart rate can be calculated. The advantage of this method is its simple and portable equipment, making it suitable for flexible monitoring. However, it is also significantly affected by factors such as breathing, resulting in lower accuracy.

[0036] Based on the advantages and disadvantages of the aforementioned heart rate measurement methods, photoplethysmography (PPG) is currently one of the most widely used methods. PPG is a non-invasive physiological monitoring technology based on optical principles, widely used for measuring physiological parameters such as heart rate, blood oxygen saturation, and blood pressure. This PPG technology uses a light source (usually a green LED) and a photodetector placed on the skin surface, utilizing the absorption and reflection characteristics of light by blood to detect vascular pulsation. When the heart beats, the flow of blood in the arteries causes periodic changes in blood volume, which in turn alters the amount of light absorbed. By analyzing the attenuation of the light signal, the pulse waveform can be extracted, and physiological parameters such as heart rate can be calculated. This heart rate detection method has the advantages of simple equipment, portability, and low cost, making it suitable for daily use and wearable devices (such as smartwatches and fitness trackers).

[0037] Figure 1 A schematic diagram illustrating an application scenario according to an embodiment of this application is shown. For example... Figure 1As shown, the heart rate determination method of this application is applicable to everyday life, allowing for heart rate detection at any time regardless of location or operator. This heart rate detection method can be used in wearable devices such as smartwatches or bracelets, enabling real-time or user-instructed heart rate detection using photoplethysmography (PPG) while the user is wearing the device.

[0038] In applications using photoplethysmography (PPG) to detect heart rate, the biosignals acquired by electronic devices are significantly affected by external factors (such as light interference, skin condition, and motion artifacts), resulting in low accuracy. To improve the accuracy of heart rate detection results, current technologies employ techniques such as Independent Component Analysis (ICA), Adaptive Noise Control (ANC), the Troika model (which performs signal decomposition, sparse signal reconstruction, and peak tracking on the original PPG signal), and wavelet denoising to remove motion artifacts from the PPG signal. These methods aim to eliminate noise interference in the biosignal and obtain more accurate heart rate detection results.

[0039] However, the aforementioned methods for removing motion noise in related technologies typically involve large computational loads, making real-time calculations difficult. Alternatively, some of these technologies are ineffective at removing motion noise and cannot accurately remove noise from biosignals caused by light interference, skin condition, motion artifacts, etc., resulting in inaccurate heart rate detection results. Therefore, the technical problem that this application's embodiments essentially need to solve is: how to improve the accuracy and real-time performance of heart rate detection results when using photoplethysmography (PPG) to detect a user's heart rate.

[0040] To address the aforementioned technical issues, the heart rate determination method in this application, based on the characteristics of biological signals acquired through photoplethysmography, filters both red and green physiological signals to efficiently remove motion artifacts, obtaining a clear target physiological signal that characterizes the physiological information of the target object, thereby improving the accuracy of the final determined heart rate. Furthermore, because the biological signal filtering process in this application is simple and computationally inexpensive, it enables real-time heart rate determination during physiological signal detection, improving the real-time performance of the heart rate determination process.

[0041] Figure 2 A flowchart of a heart rate determination method according to an embodiment of this application is shown. Figure 2 As shown, the heart rate determination method in this application embodiment may include the following steps S10-S30.

[0042] For ease of description, the heart rate determination method of this application embodiment is described using an electronic device as the execution subject. It should be understood that the execution subject of this application embodiment can also be a processor or chip in an electronic device, and this application embodiment does not impose any limitations.

[0043] Step S10: The electronic device determines the red light physiological signal and green light physiological signal of the target object within a preset time period.

[0044] In some possible implementations, embodiments of this application acquire red and green physiological signals of a target object within a preset time period using an electronic device. The target object can be a living being such as a person or animal. The preset time period is a pre-defined time interval set by the electronic device; it can be a time period preset with a start and end time, a time period preset with a duration, or a cycle in a periodic signal acquisition process.

[0045] Optionally, in this embodiment, the electronic device can automatically collect PPG physiological signals from the target user within a preset time period to obtain red and green physiological signals. Alternatively, the electronic device can also receive red and green physiological signals obtained by other devices collecting PPG physiological signals from the target user within a preset time period. The red physiological signal can be an electrical signal converted from the light signal generated after red light irradiates the target skin, and the green physiological signal can be an electrical signal converted from the light signal generated after green light irradiates the target skin.

[0046] In some possible embodiments, when red and green physiological signals are collected by an electronic device, the electronic device can emit light (including red and green light) onto the skin of the target object through its installed light source (e.g., LED), and then the photoelectric detection device receives the red and green light signals emitted or transmitted through the skin of the target object, converts the red light signal into an electrical signal corresponding to red light, and converts the green light signal into an electrical signal corresponding to green light.

[0047] Optionally, the wavelength of the red light physiological signal acquired by the electronic device is approximately 600-750 nm. Due to the deep penetration of red light, it can detect blood flow in deep tissues and veins of the target object. However, based on the optical characteristics of red light, the signal intensity is relatively weak, especially in areas with darker skin or thicker tissues, and it is easily affected by ambient light and other noise. Therefore, in this embodiment, the acquired red light physiological signal can be recorded within a preset time period of PPG signal noise.

[0048] Optionally, the wavelength of the green light physiological signal acquired by the electronic device is approximately 500-570 nm, as it has good absorption of oxyhemoglobin and deoxyhemoglobin, resulting in a high signal-to-noise ratio. Furthermore, compared to other wavelengths, green light is less affected by skin pigmentation and moisture absorption, making it more suitable for measurements of different skin colors and conditions. In other words, the green light physiological signal has a stronger signal intensity, is more sensitive to motion artifacts, has higher measurement accuracy, and can record the physiological characteristics of the target subject within a preset time period.

[0049] Step S20: The electronic device filters the green light physiological signal based on the red light physiological signal to obtain the target physiological signal with noise removed from the green light physiological signal.

[0050] In one possible implementation, after acquiring the red and green physiological signals of the target object within a preset time period, the electronic device can filter the red physiological signal as a noise source and the green physiological signal as the desired physiological signal to remove motion artifacts and other noise. This is because the infrared channel is more sensitive to noise, while the green channel is more sensitive to signal. In other words, the electronic device can filter the green physiological signal based on the red physiological signal to obtain the target physiological signal with noise removed.

[0051] In some embodiments, after acquiring red and green physiological signals from a target object within a preset time period, the electronic device can first detect whether the electronic device is worn by the target object within that time period to verify the validity of the acquired red and green physiological signals. If the electronic device is detected to be worn by the target object within the preset time period, the electronic device determines that the acquired red and green physiological signals are valid, and then filters the green physiological signal based on the red physiological signal to obtain the target physiological signal with noise removed. In other words, if the electronic device is not worn by the target object within the preset time period, the electronic device determines that the acquired red and green physiological signals are invalid and does not execute the subsequent heart rate detection algorithm. This detection method avoids performing heart rate detection when invalid red and green physiological signals are acquired, thus avoiding unnecessary computational power and inaccurate detection results.

[0052] For example, the electronic device can detect whether the electronic device is worn by the target object within a preset time period based on red and green physiological signals, or it can detect whether the electronic device is worn by the target object within a preset time period in other ways. If it is not necessary to detect whether the electronic device is worn by the target object within a preset time period based on red and green physiological signals, the electronic device can actually perform wearing detection before step S10 begins, and then acquire the red and green physiological signals of the target object within the preset time period only after detecting that the electronic device is worn by the target object.

[0053] Optionally, based on the optical characteristics of the infrared and green light channels, the green physiological signal acquired under green light illumination has higher signal quality than the red physiological signal acquired under red light illumination. Furthermore, since the red and green physiological signals are acquired simultaneously from the target object, the gain and phase consistency of the two signals are superior. Based on the principle of motion artifact generation in PPG signals, the electronic device can use the red physiological signal as a noise source and the green physiological signal as the desired physiological signal for signal filtering to remove motion artifacts and other noise, thus obtaining a signal that accurately records the biometrics of the target object within a preset time period.

[0054] In some embodiments of this application, the electronic device can preprocess the red and green physiological signals before performing signal filtering. To ensure consistent gain and phase for both signals, the electronic device can use the same preprocessing method for both signals. This preprocessing method can be a bidirectional IIR (Infinite Impulse Response) filtering technique. Bidirectional IIR filtering is a signal processing method based on an infinite impulse response (IIR) filter, which reduces phase delay and improves filtering effectiveness through two filtering operations (forward and reverse). Compared to FIR (Finite Impulse Response) filters, this filtering method has lower delay, smaller budget, and better initial noise filtering, enabling the acquisition of red and green physiological signals within the target frequency band.

[0055] Optionally, the preprocessing of red and green physiological signals by the aforementioned electronic equipment can be used to initially eliminate interference from various noises that are easily induced during PPG signal acquisition, such as skin movement, electromagnetic interference, light variations, power supply noise (50Hz or 60Hz), and electromyographic noise. This preprocessing can include removing high-frequency noise, low-frequency drift, and detrending. Specifically, high-frequency noise removal is used to eliminate high-frequency interference, such as power supply noise and electronic switch noise. Low-frequency drift removal is used to remove baseline drift, which may be caused by respiration, temperature changes, or poor sensor contact. Detrending is used to eliminate slow fluctuations caused by changes in ambient light or device white balance adjustments.

[0056] In one possible implementation, the filtering of green physiological signals based on red physiological signals by the electronic device in this embodiment can be achieved through a pre-trained adaptive neural network. Specifically, after acquiring red and green physiological signals, or after preprocessing them, the electronic device can input the red and green physiological signals into the adaptive neural network for filtering, outputting the target physiological signal. The target physiological signal is the denoised green physiological signal. The red physiological signal input to the adaptive neural network includes a red pulse signal and an infrared noise signal, while the green physiological signal includes a green pulse signal and a green noise signal. Furthermore, the phase and gain of the red and green physiological signals are essentially the same. After passing through the adaptive neural network, some motion interference in the green physiological signal can be removed, resulting in a cleaner green pulse signal. Optionally, an adaptive neural network (ANN) is a neural network that can dynamically adjust its structure and parameters based on the characteristics of the input data or feedback information during training. Compared to traditional fixed-architecture neural networks, adaptive neural networks better adapt to the needs of different tasks by changing the number of layers, neurons, and connections, thereby improving the model's generalization ability and learning efficiency. In some optional embodiments, the electronic device can use red light physiological signals as a noise source and green light physiological signals as initial input signals to the adaptive neural network, performing at least one filtering process to output the target physiological signal in the final filtering process. Optionally, this filtering process can be an iterative filtering process, that is, determining the input information for the next filtering process based on the filtering result output by each filtering process. This filtering method is simple and can improve the accuracy of the filtering results through multiple iterations.

[0057] For example, in this embodiment, each filtering process can involve inputting the noise source and the input signal into an adaptive filter to obtain a corresponding noise mapping signal. In the first filtering process, the input signal is the green light physiological signal. In subsequent filtering processes, the input signal is determined based on the input signal and the output noise mapping signal from the previous filtering process. Until the final filtering process, the electronic device determines the target physiological signal based on the difference between the input signal and the noise mapping signal from the final filtering process; that is, it determines that the difference between the input signal and the noise mapping signal at this point is the green light pulse signal after noise removal. This filtering method, through multiple iterative filtering processes, eliminates noise in the green light physiological signal, resulting in an accurate filtering result.

[0058] Optionally, the noise mapping signal in this embodiment is a noise signal obtained based on noise source mapping. Therefore, after each filtering process, the electronic device can calculate the difference between the current input signal and the noise mapping signal to obtain the filtered physiological signal. In the first filtering process, the electronic device can input the red light physiological signal and the green light physiological signal into the adaptive neural network together to obtain the noise mapping signal of the first filtering. In the i-th filtering process, the electronic device can determine the i-th input signal based on the noise mapping signal obtained in the (i-1)-th filtering process and the input signal of the (i-1)-th filtering process, and input the red light physiological signal and the i-th input signal into the adaptive neural network together to obtain the noise mapping signal of the i-th filtering, where i is a positive integer greater than 1. The electronic device can determine the difference between the input signal of the (i-1)-th filtering process and the noise mapping signal obtained in the (i-1)-th filtering process as the input signal of the i-th filtering process.

[0059] In some embodiments, the noise mapping signal is actually the noise signal obtained based on the noise source mapping. To further improve the accuracy of the filtering results, the electronic device can also update the noise source signal based on the noise mapping signal after each filtering process. For example, the red light physiological signal can be used as the noise source signal in the first filtering process, and the noise mapping signal obtained in the previous filtering process can be used as the noise source signal in the i-th filtering process, where i is a positive integer greater than 1. Alternatively, the difference between the noise source signal (red light physiological signal) and the noise mapping signal obtained in the previous filtering process can be used as the noise source signal for the next filtering process.

[0060] Figure 4 A schematic diagram of an adaptive neural network according to an embodiment of this application is shown. Figure 4As shown, the adaptive neural network includes an adaptive filtering module. The adaptive neural network has two input terminals: one connected to the adaptive filtering module for inputting the noise source signal X(n), and the other for inputting the input signal s(n) to be filtered. During a single filtering process by the adaptive neural network, the adaptive filtering module maps and transforms the input noise source signal X(n) to obtain the noise mapping signal y(n) determined for this filtering process. Further, if the current filtering process is not the last, the electronic device can calculate the difference e(n) between the input signal s(n) and the noise mapping signal y(n) to obtain the input signal for the next filtering process. If the current filtering process is the last, the electronic device can calculate the difference e(n) between the input signal s(n) and the noise mapping signal y(n) to obtain the final output target physiological signal. Optionally, after each filtering step, the electronic device can further optimize the adaptive filtering module in the adaptive neural network based on the difference e(n) between the input signal s(n) and the noise mapping signal y(n) to improve the filtering effect of the adaptive neural network in real time during the filtering process.

[0061] Based on the principle of adaptive neural networks, when the useful information contained in the initial input signal (green light physiological signal) is very weak or basically unpredictable, the principle of filtering and denoising by the adaptive neural network is as follows: the input red light physiological signal is taken as the original input X(n), and the noisy green light physiological signal is taken as the desired signal s(n). After multiple iterations, the difference between the desired signal and the output noise mapping signal y(n) of the adaptive filtering module is the final output target physiological signal e(n).

[0062] In some possible embodiments, when the adaptive neural network in this application embodiment performs filtering only once, the functions used by the adaptive neural network in the single filtering process include: X(n) = IR_S(n) + IR_N(n), where X(n) is the red light physiological signal, including the red light pulse signal IR_S(n) and the infrared noise signal IR_N(n). s(n) = GREEN_S(n) + GREEN_N(n), where s(n) is the green light physiological signal GREEN_S(n), including the green light pulse signal and the green light noise signal GREEN_N(n). y(n) = f(x(n)), where f(·) is the filtering function of the adaptive filtering module. d(n) = s(n), e(n) = GREEN_S(n) – f(IR_S(n)) + GREEN_N(n) – f(IR_N(n)). After multiple iterations, GREEN_N(n)–f(IR_N(n)) approaches 0. Since the sensitivity of the red light physiological signal to noise and pulse signals is different from that of the green light physiological signal, GREEN_S(n)–f(IR_S(n)) will approach the difference of the pulse signal, and this difference preserves the periodicity of the pulse signal in the frequency domain.

[0063] Figure 4 A schematic diagram of an adaptive filtering module in an adaptive neural network according to an embodiment of this application is shown. Figure 4 As shown, the adaptive filtering module in an adaptive neural network can include N filtering layers, which are sequentially connected to filter the input noise source signal layer by layer, obtaining an accurate noise mapping signal. This cascaded setting of filtering layers can significantly enhance the filtering effect, optimize filter characteristics, and improve the stability and efficiency of the system. In practical applications, electronic devices can achieve complex signal processing tasks and meet the needs of different application scenarios by reasonably designing the structure and parameters of cascaded filters. Step S30: The electronic device determines the heart rate of the target object based on the target physiological signal.

[0064] In one possible implementation, the electronic device of this application, after obtaining the target physiological signal (with noise and motion artifacts removed) through the above-described filtering method, determines the heart rate of the target object based on the target physiological signal. Optionally, the method of determining the heart rate of the target object based on the target physiological signal in this application embodiment can be to first perform frequency domain transformation on the target physiological signal, and then determine the heart rate of the target object based on the frequency domain transformed target physiological signal. According to the above technical features, this application embodiment can first filter the acquired physiological signal of the target object in the time domain, which to a certain extent overcomes the problem of co-frequency interference that cannot be solved in the frequency domain. Then, the filtered physiological signal is transformed from the time domain to the frequency domain for heart rate determination, obtaining an accurate heart rate estimation result.

[0065] Optionally, in the embodiments of this application, the electronic device may perform frequency domain transformation on the target physiological signal using any method such as Fourier transform, short-time Fourier transform, wavelet transform, Hilbert transform, and z-transform, without limitation. After filtering, the original spectral interference peaks in the target physiological signal transformed to the frequency domain are eliminated, enabling a more accurate heart rate to be obtained subsequently.

[0066] In some optional implementations, after converting the target physiological signal to the frequency domain, the embodiments of this application can use peak tracking technology to calculate the heart rate of the target physiological signal after eliminating interference peaks, obtaining an accurate heart rate calculation result. This heart rate calculation result is the heart rate of the target object within a preset time period in the embodiments of this application. Peak tracking technology is a method for signal processing and analysis, mainly used to accurately identify and track target spectral peaks from complex spectral signals. This technology has wide applications in many fields, such as hyperspectral imaging, biomedical signal processing, and fiber optic sensor demodulation. In the biomedical field, peak tracking technology is used to process and analyze physiological signals. By removing motion artifacts and noise, peak tracking can accurately identify the spectral peaks corresponding to the heart rate, maintaining high accuracy even under conditions of strong motion interference.

[0067] Figure 5 A flowchart of another heart rate determination method according to an embodiment of this application is shown. Figure 4 As shown, in the process of determining heart rate in this embodiment, the electronic device first performs step S50 to acquire red and green physiological signals, and then performs step S51 to determine whether the electronic device is worn by the target object within a preset time period. If the electronic device is worn by the target object within the preset time period, the electronic device further performs step S52 to preprocess the red and green physiological signals. After completing the signal preprocessing, the electronic device performs step S53 to filter the green physiological signal based on the red physiological signal in the time domain to obtain the target physiological signal after noise removal. Further, the electronic device performs step S54 to convert the target physiological signal from the time domain to the frequency domain, and then performs step S55 to calculate the heart rate of the target physiological signal in the frequency domain using spectral peak tracking technology to obtain the target object's heart rate within the preset time period.

[0068] Based on the aforementioned technical features, the heart rate determination method of this application fully considers the principle of PPG motion artifact generation. It filters based on the different sensitivities of infrared and green light channels to noise and pulse signals—infrared light is more sensitive to noise, while green light is more sensitive to pulse signals. The filtering process uses the red light physiological signal as the noise source and the green light physiological signal as the desired signal. This filtering process uses an adaptive network to map the noise and cancel it out from the noise in the green light physiological signal of the green light channel, ensuring that the filtered signal maintains the periodicity of the heart rate and pulse signals. This filtering method uses a simple filtering network with low computational cost, thus ensuring the timeliness of the filtering process and enabling real-time heart rate detection. Furthermore, this filtering process is performed in the time domain, which can overcome the problem of co-frequency interference that cannot be solved in the frequency domain to a certain extent. Compared with simple adaptive filtering, the filtering effect is better, resulting in a more accurate calculated heart rate.

[0069] It should be understood that although the steps in the above flowcharts are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0070] Based on the foregoing embodiments, this application provides a heart rate determination device, which includes various modules and units included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0071] Figure 6 A schematic diagram of a heart rate determining device 606 according to an embodiment of this application is shown. Figure 6 As shown, the heart rate determination device 60 in this embodiment may include:

[0072] Signal acquisition module 61 is used to determine the red light physiological signal and green light physiological signal of the target object within a preset time period;

[0073] Signal filtering module 62 is used to filter the green light physiological signal based on the red light physiological signal to obtain the target physiological signal with noise information removed from the green light physiological signal;

[0074] Heart rate determination module 63 is used to determine the heart rate of the target object based on the target physiological signal.

[0075] In one possible implementation, the signal filtering module 62 is further used for:

[0076] The red light physiological signal and the green light physiological signal are input into the adaptive neural network, and the target physiological signal is output.

[0077] In one possible implementation, the signal filtering module 62 is further used for:

[0078] The red light physiological signal is used as a noise source, and the green light physiological signal is used as the initial input signal to input into the adaptive filtering neural network. At least one filtering process is performed to output the target physiological signal in the last filtering process.

[0079] In one possible implementation, each filtering process includes:

[0080] The noise source and the input signal are input into an adaptive filtering neural network to obtain the corresponding noise mapping signal. In the first filtering process, the input signal is the green light physiological signal. In non-first filtering processes, the input signal is determined based on the input signal and the output noise mapping signal of the previous filtering process.

[0081] In one possible implementation, the target physiological signal is determined based on the difference between the input signal and the noise-mapped signal from the last filtering process.

[0082] In one possible implementation, the heart rate determination module 63 is further used for:

[0083] Frequency domain transformation of the target physiological signal;

[0084] The heart rate of the target object is determined based on the target physiological signal after frequency domain transformation.

[0085] In one possible implementation, the device is applied to an electronic device, and the signal filtering module 62 is further used for:

[0086] When it is detected that the electronic device is worn by the target object within a preset time period, the green light physiological signal is filtered based on the red light physiological signal to obtain the target physiological signal with noise information removed from the green light physiological signal.

[0087] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0088] It should be noted that, in the embodiments of this application... Figure 6 The module division of the heart rate determination device shown is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, exist as separate physical units, or be integrated into one unit with two or more units. The integrated units can be implemented in hardware, as software functional units, or a combination of both.

[0089] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0090] Figure 7 A schematic diagram of an electronic device according to an embodiment of this application is shown. For example... Figure 7 As shown in the figure, this application provides an electronic device, which can be a server, and its internal structure diagram can be as follows. Figure 7 As shown, the electronic device includes a processor 720, a memory, and a transceiver 740 connected via a system bus 710. The processor 720 provides computing and control capabilities. The memory includes a non-volatile storage medium 731 and internal memory 77132. The non-volatile storage medium 731 stores an operating system, computer programs, and a database. The internal memory 77132 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium 731. The database stores data. The transceiver 740 communicates with external terminals via a network connection. The computer program is executed by the processor 720 to implement the aforementioned methods.

[0091] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor 720, implements the steps of the method provided in the above embodiments.

[0092] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the method provided in the above-described method embodiments.

[0093] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0094] In one embodiment, the heart rate determining device provided in this application can be implemented as a computer program, which can be implemented in the form of, for example, Figure 7 The device operates on the electronic device shown. The memory of the electronic device can store the various program modules that make up the above-described apparatus. The computer program composed of the various program modules causes the processor 720 to execute the steps of the methods in the various embodiments of this application described in this specification.

[0095] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0096] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0097] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three kinds of relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0098] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or modules can be electrical, mechanical, or other forms.

[0100] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0101] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0102] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0103] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0104] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0105] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0106] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0107] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining heart rate, characterized in that, The method includes: Determine the red and green physiological signals of the target object within a preset time period; The green light physiological signal is filtered based on the red light physiological signal to obtain a target physiological signal with noise removed from the green light physiological signal. The heart rate of the target object is determined based on the target physiological signals.

2. The method according to claim 1, characterized in that, The step of filtering the green light physiological signal based on the red light physiological signal to obtain a target physiological signal with noise removed from the green light physiological signal includes: The red light physiological signal and the green light physiological signal are input into an adaptive neural network, which outputs the target physiological signal.

3. The method according to claim 2, characterized in that, The step of inputting the red light physiological signal and the green light physiological signal into a trained adaptive neural network and outputting the target physiological signal includes: The red light physiological signal is used as a noise source, and the green light physiological signal is used as an initial input signal to input into the adaptive filtering neural network. At least one filtering process is performed to output the target physiological signal in the last filtering process.

4. The method according to claim 3, characterized in that, Each filtering process includes: The noise source and the input signal are input into the adaptive filtering neural network to obtain the corresponding noise mapping signal. In the first filtering process, the input signal is the green light physiological signal. In non-first filtering processes, the input signal is determined based on the input signal and the output noise mapping signal of the previous filtering process.

5. The method according to claim 3, characterized in that, The target physiological signal is determined based on the difference between the input signal and the noise mapping signal from the last filtering process.

6. The method according to claim 1, characterized in that, Determining the heart rate of the target object based on the target physiological signal includes: The target physiological signal is frequency domain converted; The heart rate of the target object is determined based on the target physiological signal after frequency domain transformation.

7. The method according to claim 1, characterized in that, The method is applied to electronic devices, wherein filtering the green light physiological signal based on the red light physiological signal to obtain a target physiological signal with noise removed from the green light physiological signal includes: When it is detected that the electronic device is worn by the target object within the preset time period, the green light physiological signal is filtered based on the red light physiological signal to obtain the target physiological signal with noise information removed from the green light physiological signal.

8. A heart rate determination device, characterized in that, The device includes: The signal acquisition module is used to determine the red light physiological signal and green light physiological signal of the target object within a preset time period; The signal filtering module is used to filter the green light physiological signal based on the red light physiological signal to obtain a target physiological signal with noise information removed from the green light physiological signal. A heart rate determination module is used to determine the heart rate of the target object based on the target physiological signal.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images