Heart rate detection method, device, equipment, readable storage medium and program product

Abstract

The invention relates to a heart rate detection method, device and equipment, a readable storage medium and a program product, and relates to the technical field of heart rate detection. The method comprises the following steps: acquiring a to-be-analyzed heart rate signal of a to-be-detected object according to a first sampling rate; based on the to-be-analyzed heart rate signal, analyzing to obtain a first heart rate value; based on the first heart rate value, determining a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate greater than the first sampling rate and a plurality of first sampling points in the first signal sliding range; and using a preset triangular window weighting coefficient to perform weighted statistics on the autocorrelation degree of each first sampling point, selecting a first target sampling point from each first sampling point according to a weighted statistics result, and determining a second heart rate value according to the signal sliding distance corresponding to the first target sampling point and a second sampling rate. By adopting the method, the sampling rate can be reduced while the heart rate detection precision is improved, so that the computing power is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heart rate detection, and in particular to a heart rate detection method, device, equipment, readable storage medium and program product. BACKGROUND

[0002] People pay more and more attention to health, and sleep quality, as one of the important indicators to measure health status, has attracted widespread attention. Sleep monitoring can help people understand their own sleep state and timely find sleep disorders and other health problems. Heart rate variability (HRV) as a key parameter to evaluate the autonomic nervous function of the cardiovascular system can not only reflect the physiological changes in the sleep process, but also be closely related to the occurrence and development of many diseases. For example, lower heart rate variability is associated with an increased risk of cardiovascular disease, mental illness, etc. The detection of heart rate variability needs to capture the subtle time difference between adjacent heartbeats, so it is necessary to accurately record the subtle changes between adjacent heartbeats through high-precision heart rate monitoring to achieve accurate heart rate variability detection. Therefore, accurate detection of heart rate is of great significance for sleep monitoring and health assessment.

[0003] At present, non-contact piezoelectric materials have been applied to the field of sleep monitoring to some extent. This monitoring method has the advantages of not needing to be worn and not affecting the user's sleep experience. However, the existing non-contact piezoelectric material sleep monitoring products have obvious limitations. When the product uses a lower sampling rate, its function is often limited to measuring heart rate data at a low sampling rate, making it difficult to capture the subtle differences between adjacent heartbeats, and the heart rate detection accuracy is low. In order to achieve high-precision heart rate detection, it is usually necessary to use high-frequency sampling and perform filtering and envelope extraction operations on the data obtained by high-frequency sampling to obtain more detailed heartbeat information. The above operations involve a large number of complex calculations, which require a processor with extremely strong computing power to complete. However, the use of high-performance processors will significantly increase the cost and power consumption of the product, which will cause problems such as short product battery life. In addition, in order to deal with the problem of high power consumption, additional heat dissipation and power management design is needed, which further increases the design difficulty and cost of the product. SUMMARY

[0004] Therefore, it is necessary to provide a heart rate detection method, device, equipment, readable storage medium and program product that can improve heart rate detection accuracy while reducing sampling rate to reduce the hardware computing power requirement.

[0005] In a first aspect, the present application provides a heart rate detection method, comprising:

[0006] acquiring a heart rate signal to be analyzed of a to-be-detected object according to a first sampling rate;

[0007] a first heart rate value is analyzed based on the heart rate signal to be analyzed;

[0008] a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate is determined based on the first heart rate value, and a plurality of first sampling points in the first signal sliding range are determined based on the first heart rate value; the second sampling rate is greater than the first sampling rate;

[0009] a weighted statistical result is obtained by using a preset triangular window weighting coefficient to statistically weight the autocorrelation degrees of the first sampling points, a first target sampling point is selected from the first sampling points according to the weighted statistical result, and a second heart rate value of the heart rate signal to be analyzed is analyzed according to a signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0010] In one of the embodiments, the first heart rate value is analyzed based on the heart rate signal to be analyzed, including:

[0011] the heart rate signal to be analyzed is denoised to obtain a corresponding ballistocardiogram;

[0012] autocorrelation degrees of a plurality of second sampling points of the ballistocardiogram at the first sampling rate are analyzed and calculated based on signal sliding distances corresponding to the second sampling points;

[0013] the second sampling points are respectively weighted and counted by using a triangular window based on the autocorrelation degrees of the second sampling points, to obtain weighted probabilities corresponding to the second sampling points;

[0014] a second target sampling point is obtained from the second sampling points; the second target sampling point is the second sampling point corresponding to the maximum weighted probability;

[0015] the first heart rate value is analyzed according to a signal sliding distance corresponding to the second target sampling point and the first sampling rate.

[0016] In one of the embodiments, the heart rate signal to be analyzed is denoised to obtain a corresponding ballistocardiogram, including:

[0017] the heart rate signal to be analyzed is decomposed by using a Haar wavelet for three layers, a direct current component of a third layer of the heart rate signal to be analyzed is removed, and a first signal component corresponding to the heart rate signal to be analyzed is obtained;

[0018] the first signal component corresponding to the heart rate signal to be analyzed is reconstructed to obtain a corresponding ballistocardiogram.

[0019] In one embodiment, the step of using a preset triangular window weighting coefficient to perform weighted statistics on the autocorrelation of each of the first sampling points to obtain a weighted statistical result, selecting a first target sampling point from each of the first sampling points based on the weighted statistical result, and analyzing and obtaining a second heart rate value of the heart rate signal to be analyzed based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, includes:

[0020] Using a preset triangular window weighting coefficient, combined with the autocorrelation of each first sampling point, weighted statistics are performed with the signal sliding distance corresponding to each first sampling point as the center, to obtain the weighted probability corresponding to each first sampling point;

[0021] A first target sampling point is obtained from each of the first sampling points; the first target sampling point is the first sampling point corresponding to the largest weighted probability.

[0022] Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

[0023] In one embodiment, before using a preset triangular window weighting coefficient, combined with the autocorrelation of each of the first sampling points, and performing weighted statistics centered on the signal sliding distance corresponding to each of the first sampling points to obtain the weighted probability corresponding to each of the first sampling points, the method further includes:

[0024] Using Haar wavelet, the heart rate signal to be analyzed is decomposed into six layers. The DC component of the sixth layer of the heart rate signal to be analyzed is removed to obtain the second signal component corresponding to the heart rate signal to be analyzed.

[0025] The second signal component corresponding to the heart rate signal to be analyzed is reconstructed to obtain the reconstructed heart rate signal to be analyzed;

[0026] Based on the signal sliding distance corresponding to the first heart rate value, the signal sliding distance corresponding to each of the first sampling points of the reconstructed heart rate signal to be analyzed within the first signal sliding range is determined, and the autocorrelation of each of the first sampling points is analyzed and calculated based on the signal sliding distance corresponding to each of the first sampling points.

[0027] In one embodiment, the method further includes:

[0028] Based on the ratio of the first sampling rate to the second sampling rate, and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate, the signal sliding distance corresponding to the first target sampling point is determined.

[0029] Secondly, this application also provides a heart rate detection device, comprising:

[0030] The acquisition module is used to acquire the heart rate signal of the object to be analyzed according to the first sampling rate;

[0031] The analysis module is used to analyze the heart rate signal to be analyzed and obtain a first heart rate value.

[0032] The determining module is configured to determine, based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate, and a plurality of first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate;

[0033] The weighted statistics module is used to perform weighted statistics on the autocorrelation of each of the first sampling points using a preset triangular window weighting coefficient to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points, and a second heart rate value of the heart rate signal to be analyzed is obtained based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0035] According to the first sampling rate, the heart rate signal of the subject to be analyzed is acquired;

[0036] Based on the heart rate signal to be analyzed, a first heart rate value is obtained;

[0037] Based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate is determined, as well as multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0038] Using a preset triangular window weighting coefficient, the autocorrelation of each of the first sampling points is weighted and statistically analyzed to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] According to the first sampling rate, the heart rate signal of the subject to be analyzed is acquired;

[0041] Based on the heart rate signal to be analyzed, a first heart rate value is obtained;

[0042] Based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate is determined, as well as multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0043] Using a preset triangular window weighting coefficient, the autocorrelation of each of the first sampling points is weighted and statistically analyzed to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] According to the first sampling rate, the heart rate signal of the subject to be analyzed is acquired;

[0046] Based on the heart rate signal to be analyzed, a first heart rate value is obtained;

[0047] Based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate is determined, as well as multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0048] Using a preset triangular window weighting coefficient, the autocorrelation of each of the first sampling points is weighted and statistically analyzed to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

[0049] The aforementioned heart rate detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire the heart rate signal to be analyzed of the target object according to a first sampling rate, analyze the heart rate signal to be analyzed to obtain a first heart rate value, then determine a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate, and multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range, wherein the second sampling rate is greater than the first sampling rate, then use a preset triangular window weighting coefficient to perform weighted statistics on the autocorrelation of each first sampling point to obtain a weighted statistical result, select a first target sampling point from each first sampling point according to the weighted statistical result, and analyze the second heart rate value of the heart rate signal to be analyzed according to the signal sliding distance corresponding to the first target sampling point and the second sampling rate. Therefore, this scheme first determines the heart rate value using low sampling rate data, and then, based on the initially determined heart rate value, determines the first signal sliding range under high sampling rate and multiple first sampling points within this first signal sliding range. The heart rate value is then further corrected within this first signal sliding range, eliminating the need to detect high-precision heart rate values ​​from a large amount of data at high sampling rates. This means that the accuracy of the heart rate value is improved while reducing the signal sampling rate, facilitating subsequent heart rate variability detection or other research based on high-precision heart rate values. Furthermore, it reduces the overall data processing volume and the computational requirements of processors and other hardware, thereby reducing product power consumption. In addition, by using preset triangular window weighting coefficients to perform weighted statistics on the autocorrelation of each first sampling point, the weighting characteristics of the triangular window can be utilized to focus the autocorrelation statistics on core effective information and suppress edge sampling points affected by noise or non-periodic interference, thus improving the anti-interference capability and result stability of heart rate value detection. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a heart rate detection method in one embodiment;

[0052] Figure 2 This is a framework diagram of a non-contact heart rate module in one embodiment;

[0053] Figure 3 This is a flowchart illustrating the heart rate sampling step in one embodiment;

[0054] Figure 4This is a flowchart illustrating the heart rate value fine-tuning steps in one embodiment;

[0055] Figure 5 This is a flowchart illustrating the autocorrelation calculation steps in one embodiment;

[0056] Figure 6 This is a flowchart illustrating the heart rate detection method in another embodiment;

[0057] Figure 7 This is a structural block diagram of a heart rate detection device in one embodiment;

[0058] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish the first object from the second object. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the solutions, or any combination of multiple solutions.

[0061] In one exemplary embodiment, such as Figure 1 As shown, a heart rate detection method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes steps 101 to 104. Wherein:

[0062] Step 101: Obtain the heart rate signal of the subject to be analyzed according to the first sampling rate.

[0063] For example, a non-contact heart rate module responds to the input of the subject and acquires the heart rate signal of the subject to be analyzed according to a first sampling rate.

[0064] The non-contact heart rate module can be placed on the inner surface of objects such as pillows, nap pillows, and mattresses. When the object being tested comes into contact with the outer surface of these objects, the non-contact heart rate module can acquire the heart rate signal of the object to be analyzed, thereby achieving non-contact detection of heart rate variability. Furthermore, the input from the object can be signals input by the object through buttons or gesture sensors on the non-contact heart rate module, or pressure signals applied by the object when it comes into contact with the outer surface of the object.

[0065] In this embodiment, as Figure 2 As shown, the non-contact heart rate module may include a main processor, a single / multi-channel piezoelectric module, an input module, an output module, and a power supply module. The main processor performs corresponding ADC (Analog-to-Digital Conversion) processing on the signals output from the single / multi-channel piezoelectric module and the input module. The single / multi-channel piezoelectric module consists of a piezoelectric material sensor and a modulation circuit. This module uses the modulation circuit to convert the charge migration changes of the piezoelectric material sensor into voltage / current changes or PWM (Pulse Width Modulation) signals that the main processor can recognize, and then sends these signals to the main processor. The input module can be a button, a light sensor, a gesture sensor, a wired / wireless communication component, or a touchscreen, and is used to receive user input signals. The output module can be an indicator light, a wired / wireless communication component, a display screen, a sound component, or a vibration component, and is used to output the signals output by the main processor. The power supply module supplies power to the main processor, single / multi-channel piezoelectric modules, and other electronic components within the non-contact heart rate module. Among them, piezoelectric material sensors can be directly bonded or nailed to a single-sided elastic material with a certain structural strength (such as plastic, thin metal, etc.), or sandwiched between two sides. When the object under test is pressed down, whether laterally or longitudinally, micro-vibrations will be transmitted to the piezoelectric material sensor, causing charge migration in the piezoelectric material sensor.

[0066] Step 102: Based on the heart rate signal to be analyzed, the first heart rate value is obtained.

[0067] For example, based on the heart rate signal to be analyzed, the autocorrelation of each second sampling point under the first sampling rate is analyzed. According to the autocorrelation of each second sampling point, a second target sampling point is selected from each second sampling point. Then, the signal sliding distance corresponding to the second target sampling point is used as the heart rate time length, and the first heart rate value is calculated.

[0068] Step 103: Based on the first heart rate value, determine the first signal sliding range of the heart rate signal to be analyzed at the second sampling rate, and the multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0069] For example, if the second sampling rate is set to 500Hz, the signal sliding distance of the heart rate signal to be analyzed at the second sampling rate is: The first signal sliding range of the heart rate signal to be analyzed at the second sampling rate is: .in, This indicates the length of the heart rate time corresponding to the first heart rate value obtained from steps 101 to 102 when the heart rate signal to be analyzed is at the first sampling rate of 50Hz, which is also the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate.

[0070] Step 104: Using a preset triangular window weighting coefficient, perform weighted statistics on the autocorrelation of each of the first sampling points to obtain a weighted statistical result. Based on the weighted statistical result, select a first target sampling point from each of the first sampling points, and analyze and obtain the second heart rate value of the heart rate signal to be analyzed based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0071] For example, after performing weighted statistics on the autocorrelation of each of the above first sampling points, the weighted statistical results are the weighted probabilities corresponding to each of the above first sampling points. The weighted probabilities corresponding to each of the above first sampling points are compared with a preset threshold, and the first sampling points with weighted probabilities greater than the preset threshold are selected. Then, the first sampling point with the largest weighted probability is selected from the selected first sampling points as the first target sampling point.

[0072] In the aforementioned heart rate detection method, the heart rate signal of the subject to be analyzed is first acquired according to a first sampling rate. A first heart rate value is initially determined using low sampling rate data. Then, based on the initially determined first heart rate value, a first signal sliding range at a second sampling rate greater than the first sampling rate is determined, along with multiple first sampling points within this first signal sliding range. The heart rate value is then further corrected within this first signal sliding range, eliminating the need to detect high-precision heart rate values ​​from a large amount of data at a high sampling rate throughout the process. This means that the accuracy of the heart rate value is improved while reducing the signal sampling rate, facilitating subsequent heart rate variability detection or other research based on high-precision heart rate values. Furthermore, it reduces the overall data processing volume and the computational power requirements of hardware such as processors, thereby reducing the power consumption of the product. This allows for improved heart rate detection accuracy while reducing the sampling rate, thus reducing the computational power requirements of hardware and achieving high-precision heart rate detection with limited computing power. In addition, by using a preset triangular window weighting coefficient to perform weighted statistics on the autocorrelation of each first sampling point, the weighting characteristics of the triangular window can be utilized to focus the autocorrelation statistics on the core effective information and suppress edge sampling points affected by noise or non-periodic interference, thereby improving the anti-interference ability and result stability of heart rate detection.

[0073] In one exemplary embodiment, such as Figure 3 As shown, in step 102 above, based on the heart rate signal to be analyzed, a first heart rate value is obtained, specifically including steps 301 to 305. Wherein:

[0074] Step 301: Denoise the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal.

[0075] A typical complete cardiac shockwave contains 3 to 4 jitters. Taking a limiting assumption, with a heart rate of 3Hz, the fastest fluctuation is 12Hz. According to Shannon's sampling theorem, a frequency more than twice that is sufficient to receive all the contours. Based on this, in this embodiment, the first sampling rate can be set to 50Hz.

[0076] For example, the first sampling rate is 50Hz, while the resting heart rate typically ranges from 30 to 120 beats per minute, or 0.5Hz to 2Hz. Based on this, by decomposing and denoising the heart rate signal to be analyzed, a frequency signal containing frequencies below 2.79Hz is obtained, which serves as the cardiac impulse signal corresponding to the aforementioned heart rate signal to be analyzed.

[0077] Step 302: Based on the signal sliding distance corresponding to multiple second sampling points of the cardiac impact signal at the first sampling rate, analyze and calculate the autocorrelation of each of the second sampling points.

[0078] For example, the sliding range of the second signal of the cardiac impact signal at the first sampling rate can be set to 2 seconds. Referring to equation (1), the sliding autocorrelation of the cardiac impact signal at the first sampling rate for 2 seconds is calculated to obtain the autocorrelation of each of the second sampling points.

[0079] (1)

[0080] In the formula, Indicates the signal sliding distance as The autocorrelation of the second sampling point, This indicates that the above cardiac impact signal was in the first... The sampling signal corresponding to the first sampling point This indicates the signal sliding distance.

[0081] The maximum value of the autocorrelation is 1, and the minimum value is -1. At the first sampling rate of 50Hz, there are 25 to 100 second sampling points.

[0082] Step 303: Based on the autocorrelation of each of the above-mentioned second sampling points, perform triangular window weighting and statistics on each of the above-mentioned second sampling points to obtain the weighted probability corresponding to each of the above-mentioned second sampling points.

[0083] Since human heart rate is variable, it is also necessary to select and calculate the weighted probabilities of several second sampling points around the second sampling point corresponding to the largest autocorrelation.

[0084] For example, referring to equation (2), a series of triangular windows are used to perform weighted and statistical analysis on the second sampling point corresponding to the maximum autocorrelation, as well as on each selected second sampling point, to obtain the weighted probability corresponding to the second sampling point corresponding to the maximum autocorrelation, and the weighted probability corresponding to each selected second sampling point. The series of triangular windows can be set as follows: .

[0085] (2)

[0086] In the formula, Indicates the current second sampling point The corresponding weighted probability, Indicates the first The autocorrelation of the second sampling point Represents a series of triangular windows The coefficient within.

[0087] For example, the time-domain average of the weighted probability can be calculated over a continuous period of T seconds to achieve weighted processing of the weighted probability, which can smooth out instantaneous fluctuations, such as occasional noise, thereby improving the long-term stability of the weighted probability and the accuracy of the heart rate value. Among them, when calculating the weighted probability P of each of the above-mentioned second sampling points over a period of time, equation (2) can be optimized and adjusted to equation (3).

[0088] (3)

[0089] In the formula, This indicates the specified statistical time period. During the statistical process, abnormal heart rate values ​​that are subject to interference can be discarded using a triangular window weighted method.

[0090] Step 304: Obtain the second target sampling point from each of the aforementioned second sampling points; the aforementioned second target sampling point is the second sampling point corresponding to the largest weighted probability.

[0091] For example, when the weighted probability P is greater than the preset threshold A, the second sampling point corresponding to the maximum value max(P) is selected as the second target sampling point.

[0092] Step 305: Based on the signal sliding distance corresponding to the second target sampling point and the first sampling rate, the first heart rate value is obtained by analysis.

[0093] For example, the sliding distance corresponding to the second target sampling point is the heart rate time length, as shown in equation (4), and the first heart rate value is calculated.

[0094] (4)

[0095] In the formula, This represents the heart rate value. Indicates the sampling rate. This indicates the duration of heart rate.

[0096] In this embodiment, the first heart rate value is calculated during the low-sampling phase to achieve coarse localization of the heart rate value, thereby predicting the heart rate range. This coarse localization reduces the computational load from O(n²) to O(m² + s*n), thus reducing CPU load. Here, n is the number of high-precision samples per unit time, m is the number of low-precision samples per unit time, s = n / m, and m and s < 0. <n。

[0097] In an exemplary embodiment, step 301 above, which involves denoising the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal, includes: using Haar wavelet to perform a three-level decomposition on the heart rate signal to be analyzed, removing the DC component of the third level of the heart rate signal to be analyzed, and obtaining the first signal component corresponding to the heart rate signal to be analyzed; and reconstructing the first signal component corresponding to the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal.

[0098] For example, the heart rate signal to be analyzed is decomposed into three layers using Haar wavelets. The frequency of the DC component in the third layer is 0 to 1.39 Hz, while the frequency of the main impact energy in the heart rate signal to be analyzed is less than this frequency. Therefore, the DC component of the third layer of the heart rate signal to be analyzed is removed to obtain the first signal component corresponding to the heart rate signal to be analyzed. The first signal component corresponding to the heart rate signal to be analyzed is then reconstructed to obtain the corresponding cardiac impact signal.

[0099] In one exemplary embodiment, such as Figure 4 As shown, in step 104 above, a weighted statistical result is obtained by using a preset triangular window weighting coefficient to perform weighted statistics on the autocorrelation of each of the first sampling points. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Then, based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained. Specifically, this includes steps 401 to 403. Wherein:

[0100] Step 401: Using preset triangular window weighting coefficients and combining the autocorrelation of each of the first sampling points, weighted statistics are performed with the signal sliding distance corresponding to each of the first sampling points as the center, to obtain the weighted probability corresponding to each of the first sampling points.

[0101] For example, the preset weighting coefficient of the triangular window can be set to The calculation of the weighted probability corresponding to each of the first sampling points can be found in Equation (2), which shows the calculation of the weighted probability corresponding to each of the second sampling points. The calculation of the weighted probability of each of the first sampling points over a period of time can be found in Equation (3), which shows the calculation of the weighted probability of each of the second sampling points over a period of time.

[0102] Step 402: Obtain the first target sampling point from each of the aforementioned first sampling points; the aforementioned first target sampling point is the aforementioned first sampling point corresponding to the largest weighted probability.

[0103] For example, when the weighted probability P is greater than the preset threshold A, the first sampling point corresponding to the maximum value max(P) is selected as the first target sampling point.

[0104] Step 403: Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

[0105] For example, the sliding distance corresponding to the first target sampling point is the heart rate time length. The calculation of the second heart rate value of the heart rate signal to be analyzed can be referred to the calculation of the first heart rate value shown in Equation (4).

[0106] In one exemplary embodiment, such as Figure 5 As shown, the method described above in this application further includes an autocorrelation calculation step before step 401, specifically steps 501 to 503. Wherein:

[0107] Step 501: Using Haar wavelet, the heart rate signal to be analyzed is decomposed into six layers. The DC component of the sixth layer of the heart rate signal to be analyzed is removed to obtain the second signal component corresponding to the heart rate signal to be analyzed.

[0108] Step 502: Reconstruct the second signal component corresponding to the heart rate signal to be analyzed to obtain the reconstructed heart rate signal to be analyzed.

[0109] For example, using Haar wavelet, the heart rate signal to be analyzed is decomposed into six layers. The frequency of the DC component in the sixth layer is less than 3.46 Hz, while the high-frequency signal with a frequency greater than 3.46 Hz is more able to reflect the changes in the signal caused by cardiac impact. Therefore, the DC component of the sixth layer of the heart rate signal to be analyzed is removed to obtain the second signal component corresponding to the heart rate signal to be analyzed. The second signal component corresponding to the heart rate signal to be analyzed is then reconstructed to obtain the reconstructed heart rate signal to be analyzed. This reconstructed heart rate signal can completely filter out respiratory interference, retain detailed information to reconstruct the signal, and avoid spurious peak interference.

[0110] Step 503: Based on the signal sliding distance corresponding to the first heart rate value, determine the signal sliding distance corresponding to each of the first sampling points of the reconstructed heart rate signal to be analyzed within the first signal sliding range, and analyze and calculate the autocorrelation of each of the first sampling points based on the signal sliding distance corresponding to each of the first sampling points.

[0111] For example, since the heart rate range has been locked through the aforementioned steps, the amount of data can be reduced, requiring only 1 second of data for the calculation of the sliding autocorrelation. The calculation of the autocorrelation of each of the aforementioned first sampling points can be found in Equation (1) for the calculation of the autocorrelation of each of the aforementioned second sampling points.

[0112] In an exemplary embodiment, the method of this application further includes: determining the signal sliding distance corresponding to the first target sampling point based on the ratio of the first sampling rate to the second sampling rate and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate.

[0113] For example, if the first sampling rate is set to 50Hz and the second sampling rate is set to 500Hz, the ratio of the first sampling rate to the second sampling rate is 1 / 10, and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate is... Therefore, the signal sliding distance corresponding to the first target sampling point is determined to be... .

[0114] In one exemplary embodiment, such as Figure 6 As shown, a heart rate detection method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes steps 601 to 609. Wherein:

[0115] Step 601: Obtain the heart rate signal of the subject to be analyzed according to the first sampling rate.

[0116] Step 602: Using Haar wavelet, the heart rate signal to be analyzed is decomposed into three layers to remove the DC component of the third layer of the heart rate signal to be analyzed, and the first signal component corresponding to the heart rate signal to be analyzed is obtained; the first signal component corresponding to the heart rate signal to be analyzed is reconstructed to obtain the corresponding cardiac impulse signal.

[0117] Step 603: Based on the signal sliding distance corresponding to multiple second sampling points of the cardiac impact signal at the first sampling rate, analyze and calculate the autocorrelation of each of the second sampling points, and based on the autocorrelation of each of the second sampling points, perform triangular window weighting and statistics on each of the second sampling points to obtain the weighted probability corresponding to each of the second sampling points.

[0118] Step 604: Obtain the second target sampling point from each of the above-mentioned second sampling points; analyze and obtain the first heart rate value based on the signal sliding distance corresponding to the second target sampling point and the first sampling rate; the second target sampling point is the second sampling point corresponding to the largest weighted probability.

[0119] Step 605: Based on the first heart rate value, determine the first signal sliding range of the heart rate signal to be analyzed at the second sampling rate, and a plurality of first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0120] Step 606: Using Haar wavelet, the heart rate signal to be analyzed is decomposed into six layers. The DC component of the sixth layer of the heart rate signal to be analyzed is removed to obtain the second signal component corresponding to the heart rate signal to be analyzed. The second signal component corresponding to the heart rate signal to be analyzed is then reconstructed to obtain the reconstructed heart rate signal to be analyzed.

[0121] Step 607: Based on the signal sliding distance corresponding to the first heart rate value, determine the signal sliding distance corresponding to each of the first sampling points of the reconstructed heart rate signal to be analyzed within the first signal sliding range, and analyze and calculate the autocorrelation of each of the first sampling points based on the signal sliding distance corresponding to each of the first sampling points.

[0122] Step 608: Using a preset triangular window weighting coefficient, combined with the autocorrelation of each of the first sampling points, weighted statistics are performed with the signal sliding distance corresponding to each of the first sampling points as the center to obtain the weighted probability corresponding to each of the first sampling points, and the first target sampling point is obtained from each of the first sampling points; the first target sampling point is the first sampling point corresponding to the largest weighted probability.

[0123] Step 609: Based on the ratio of the first sampling rate to the second sampling rate and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate, determine the signal sliding distance corresponding to the first target sampling point, and analyze and obtain the second heart rate value of the heart rate signal to be analyzed according to the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0124] In the aforementioned heart rate detection method, the heart rate signal to be analyzed is first acquired according to the first sampling rate. Then, the heart rate signal to be analyzed is decomposed into three levels using Haar wavelet. After removing the DC component of the third level, the reconstructed signal can initially filter out noise and interference in the signal, highlighting the characteristics of the heart rate signal. Then, the sliding autocorrelation of the reconstructed cardiac impact signal is calculated to obtain the autocorrelation degree of each second sampling point corresponding to the cardiac impact signal. Further, triangular window weighting and statistics are performed based on the autocorrelation degree to obtain the weighted probability of each second sampling point. By selecting the second sampling point corresponding to the maximum weighted probability, the first heart rate value is initially determined, which can more accurately capture the periodic characteristics of the cardiac impact signal and avoid misjudgment of heart rate value caused by factors such as signal fluctuation. Then, based on the first heart rate value, the sliding range of the first signal and multiple first sampling points under a higher second sampling rate are determined. Further correction analysis is then performed within the sliding range of the first signal to obtain the second heart rate value. Through multi-level sampling and analysis, the advantages of different sampling rates can be fully utilized, improving the accuracy of heart rate detection while ensuring computational efficiency. Therefore, this method uses a lower sampling rate in the data acquisition and preliminary analysis stages to reduce the amount of computation and improve the processing speed. After initially determining the first heart rate value, it uses a higher second sampling rate, which can provide more detailed signal information in the subsequent correction analysis, thus helping to detect the heart rate more accurately and solving the problem of balancing heart rate detection accuracy and computational efficiency.

[0125] It should be understood that although the steps in the flowcharts of the embodiments described above 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 flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0126] Based on the same inventive concept, this application also provides a heart rate detection device for implementing the heart rate detection method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more heart rate detection device embodiments provided below can be found in the limitations of the heart rate detection method described above, and will not be repeated here.

[0127] In one exemplary embodiment, such as Figure 7 As shown, a heart rate detection device is provided, including: an acquisition module 701, an analysis module 702, a determination module 703, and a weighted statistics module 704, wherein:

[0128] The acquisition module 701 is used to acquire the heart rate signal of the object to be analyzed according to the first sampling rate.

[0129] Analysis module 702 is used to analyze and obtain a first heart rate value based on the above-mentioned heart rate signal to be analyzed.

[0130] The determining module 703 is used to determine, based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate, and a plurality of first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate.

[0131] The weighted statistics module 704 is used to perform weighted statistics on the autocorrelation of each of the first sampling points using a preset triangular window weighting coefficient to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points, and a second heart rate value of the heart rate signal to be analyzed is obtained based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0132] In an exemplary embodiment, the analysis module 702 is used to denoise the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal; based on the signal sliding distance corresponding to multiple second sampling points of the cardiac impact signal at the first sampling rate, analyze and calculate the autocorrelation of each of the second sampling points; based on the autocorrelation of each of the second sampling points, perform triangular window weighting and statistics on each of the second sampling points to obtain the weighted probability corresponding to each of the second sampling points; obtain a second target sampling point from each of the second sampling points; the second target sampling point is the second sampling point corresponding to the largest weighted probability; and analyze and obtain the first heart rate value according to the signal sliding distance corresponding to the second target sampling point and the first sampling rate.

[0133] In an exemplary embodiment, the analysis module 702 is used to perform a three-level decomposition on the heart rate signal to be analyzed using Haar wavelet, remove the DC component of the third level of the heart rate signal to be analyzed to obtain the first signal component corresponding to the heart rate signal to be analyzed; and reconstruct the first signal component corresponding to the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal.

[0134] In an exemplary embodiment, the weighted statistics module 704 is used to perform weighted statistics with the signal sliding distance corresponding to each of the first sampling points as the center, using a preset triangular window weighting coefficient and the autocorrelation of each of the first sampling points, to obtain the weighted probability corresponding to each of the first sampling points; to obtain a first target sampling point from each of the first sampling points; the first target sampling point is the first sampling point corresponding to the largest weighted probability; and to analyze and obtain the second heart rate value of the heart rate signal to be analyzed based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

[0135] In an exemplary embodiment, the above-described apparatus further includes a decomposition calculation module. The calculation module is configured to use Haar wavelets to perform a six-level decomposition on the heart rate signal to be analyzed, removing the DC component of the sixth level of the heart rate signal to be analyzed to obtain a second signal component corresponding to the heart rate signal to be analyzed; reconstruct the second signal component corresponding to the heart rate signal to be analyzed to obtain a reconstructed heart rate signal to be analyzed; determine the signal sliding distance corresponding to each of the first sampling points of the reconstructed heart rate signal to be analyzed within the first signal sliding range based on the signal sliding distance corresponding to the first heart rate value; and analyze and calculate the autocorrelation of each of the first sampling points based on the signal sliding distance corresponding to each of the first sampling points.

[0136] In an exemplary embodiment, the above-described apparatus further includes a distance determination module. The distance determination module is configured to determine the signal sliding distance corresponding to the first target sampling point based on the ratio of the first sampling rate to the second sampling rate, and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate.

[0137] The modules in the aforementioned heart rate monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0138] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a heart rate detection method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0139] Those skilled in the art will understand that Figure 8 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 computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0140] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the heart rate detection method described above.

[0141] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the heart rate detection method described above.

[0142] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the heart rate detection method described above.

[0143] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0144] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0145] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0146] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A heart rate detection method, characterized in that, The method includes: According to the first sampling rate, the heart rate signal of the subject to be analyzed is acquired; Based on the heart rate signal to be analyzed, a first heart rate value is obtained; Based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate is determined, as well as multiple first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate. Using a preset triangular window weighting coefficient, the autocorrelation of each of the first sampling points is weighted and statistically analyzed to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

2. The method according to claim 1, characterized in that, The step of analyzing the heart rate signal to be analyzed to obtain the first heart rate value includes: The heart rate signal to be analyzed is denoised to obtain the corresponding cardiac impact signal; Based on the signal sliding distance corresponding to multiple second sampling points of the cardiac impact signal at the first sampling rate, the autocorrelation of each second sampling point is analyzed and calculated. Based on the autocorrelation of each second sampling point, triangular window weighting and statistics are performed on each second sampling point to obtain the weighted probability corresponding to each second sampling point; The second target sampling point is obtained from each of the second sampling points; the second target sampling point is the second sampling point corresponding to the largest weighted probability. The first heart rate value is obtained by analyzing the signal sliding distance corresponding to the second target sampling point and the first sampling rate.

3. The method according to claim 2, characterized in that, The denoising process of the heart rate signal to be analyzed to obtain the corresponding cardiac impact signal includes: Using Haar wavelet, the heart rate signal to be analyzed is decomposed into three layers. The DC component of the third layer of the heart rate signal to be analyzed is removed to obtain the first signal component corresponding to the heart rate signal to be analyzed. The first signal component corresponding to the heart rate signal to be analyzed is reconstructed to obtain the corresponding cardiac impact signal.

4. The method according to claim 1, characterized in that, The method involves using preset triangular window weighting coefficients to perform weighted statistical analysis on the autocorrelation of each first sampling point to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points. Then, based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, a second heart rate value of the heart rate signal to be analyzed is obtained, including: Using a preset triangular window weighting coefficient, combined with the autocorrelation of each first sampling point, weighted statistics are performed with the signal sliding distance corresponding to each first sampling point as the center, to obtain the weighted probability corresponding to each first sampling point; A first target sampling point is obtained from each of the first sampling points; the first target sampling point is the first sampling point corresponding to the largest weighted probability. Based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate, the second heart rate value of the heart rate signal to be analyzed is obtained.

5. The method according to claim 4, characterized in that, Before using a preset triangular window weighting coefficient, combined with the autocorrelation of each of the first sampling points, and performing weighted statistics centered on the signal sliding distance corresponding to each of the first sampling points to obtain the weighted probability corresponding to each of the first sampling points, the method further includes: Using Haar wavelet, the heart rate signal to be analyzed is decomposed into six layers. The DC component of the sixth layer of the heart rate signal to be analyzed is removed to obtain the second signal component corresponding to the heart rate signal to be analyzed. The second signal component corresponding to the heart rate signal to be analyzed is reconstructed to obtain the reconstructed heart rate signal to be analyzed; Based on the signal sliding distance corresponding to the first heart rate value, the signal sliding distance corresponding to each of the first sampling points of the reconstructed heart rate signal to be analyzed within the first signal sliding range is determined, and the autocorrelation of each of the first sampling points is analyzed and calculated based on the signal sliding distance corresponding to each of the first sampling points.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Based on the ratio of the first sampling rate to the second sampling rate, and the signal sliding distance of the heart rate signal to be analyzed at the first sampling rate, the signal sliding distance corresponding to the first target sampling point is determined.

7. A heart rate detection device, characterized in that, The device includes: The acquisition module is used to acquire the heart rate signal of the object to be analyzed according to the first sampling rate; The analysis module is used to analyze the heart rate signal to be analyzed and obtain a first heart rate value. The determining module is configured to determine, based on the first heart rate value, a first signal sliding range of the heart rate signal to be analyzed at a second sampling rate, and a plurality of first sampling points of the heart rate signal to be analyzed within the first signal sliding range; the second sampling rate is greater than the first sampling rate; The weighted statistics module is used to perform weighted statistics on the autocorrelation of each of the first sampling points using a preset triangular window weighting coefficient to obtain a weighted statistical result. Based on the weighted statistical result, a first target sampling point is selected from each of the first sampling points, and a second heart rate value of the heart rate signal to be analyzed is obtained based on the signal sliding distance corresponding to the first target sampling point and the second sampling rate.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. 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 steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images