A heartbeat interval measurement method and apparatus

Abstract

The application discloses a heartbeat interval measurement method and device, electronic equipment and a storage medium, and belongs to the technical field of non-contact physiological signal detection and analysis. In the application, a plurality of heartbeat signals are acquired through a heterogeneous sensor; a high-quality frequency interval corresponding to each heartbeat signal is acquired; each heartbeat signal is filtered based on the corresponding high-quality frequency interval to obtain a plurality of target heartbeat signals; the quality of each heartbeat signal in the plurality of target heartbeat signals is acquired; and the heartbeat signals are selected beat by beat based on the quality of the heartbeat signals to be fused to obtain a heartbeat interval sequence. The heartbeat interval sequence can be extracted and fused beat by beat by using a heterogeneous non-contact sensor, the accuracy of heartbeat interval extraction is improved, the heartbeat fusion is performed based on the periodicity of heartbeats, the heartbeat signal morphology feature is not relied on, the method is especially suitable for processing heart impact signals with high change degree and different signal features of different sensors, and the method has better robustness and applicability.

Description

Technical Field

[0001] This application belongs to the field of non-contact physiological signal detection and analysis technology, specifically relating to a method, device, electronic device and storage medium for measuring heartbeat interval. Background Technology

[0002] In recent years, non-contact and non-intrusive physiological signal detection methods (such as cardiometry, BCG) have attracted widespread attention for the continuous monitoring of heart rate and heart rate variability. These methods do not require skin contact and measure physiological signals by detecting body vibrations or reflected electromagnetic waves, eliminating the need for electrode attachments and long electrode wires required by traditional biomedical sensors (such as electrocardiograms, ECGs, and photoplethysmography, PPGs). Non-contact monitoring methods have broad potential applications in the medical and healthcare fields, such as improving patient compliance, reducing infection risks, and assessing severity and prognosis.

[0003] However, the poor accuracy and robustness of these monitoring methods limit their widespread application. BCG methods are susceptible to motion artifacts, and the sensor's position relative to the body or heart significantly affects the signal-to-noise ratio of cardiac vibration signals. This leads to decreased accuracy and coverage of inter-heart cycle (IBI) detection, which is unacceptable for reliable clinical applications relying on heart rate variability, such as cardiovascular event risk analysis and sleep staging. In summary, the limited reliability of non-contact monitoring methods in detecting IBI greatly restricts their application in various monitoring scenarios. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, electronic device, and storage medium for measuring heart interval to solve the problem of the difficulty in measuring heart interval.

[0005] According to a first aspect of the embodiments of this application, a method for measuring heart rate interval is provided, the method including:

[0006] Multiple heartbeat signals were acquired using heterogeneous sensors;

[0007] Obtain the high-quality frequency range corresponding to each heartbeat signal;

[0008] Multiple target heartbeat signals are obtained by filtering each heartbeat signal based on the corresponding high-quality frequency range;

[0009] Obtain the heartbeat quality of each heartbeat signal from the plurality of target heartbeat signals;

[0010] Based on the heartbeat quality, the heartbeat signals are selected one by one and fused to obtain the heartbeat interval sequence.

[0011] In some optional embodiments of this application, obtaining the high-quality frequency range corresponding to each heartbeat signal includes:

[0012] Obtain multiple candidate frequency ranges;

[0013] Perform the following steps for each of the heartbeat signals:

[0014] Obtain the filtered signal of the current heartbeat signal in each of the candidate frequency intervals;

[0015] The signal quality of the filtered signal is calculated using the harmonic addition method.

[0016] The candidate frequency range with the highest corresponding signal quality is taken as the high-quality frequency range.

[0017] In some optional embodiments of this application, the signal quality of the filtered signal is calculated using the harmonic addition method, including:

[0018] Obtain the average peak-to-valley distance of the filtered signal;

[0019] Candidate frequency points are extracted from the filtered signal based on the average peak-to-valley distance.

[0020] The HarSum spectrum value of the corresponding frequency is obtained by convolving the FFT spectrum with the kernel function corresponding to the candidate frequency point.

[0021] The spectral amplitude corresponding to the candidate frequency point in the HarSum spectrum is taken as the signal quality.

[0022] In some optional embodiments of this application, the plurality of candidate frequency intervals include a first frequency interval, a second frequency interval, a third frequency interval, and a fourth frequency interval, wherein the high cutoff frequencies of the first frequency interval, the second frequency interval, the third frequency interval, and the fourth frequency interval are the same, and the low cutoff frequencies are different.

[0023] Calculating the signal quality of the filtered signal using the harmonic addition method also includes:

[0024] The filtered signal is then normalized.

[0025] The normalized filtered signal is then exponentially filtered based on the fifth frequency range.

[0026] In some optional embodiments of this application, the first frequency range is 1Hz to 40Hz, the second frequency range is 3Hz to 40Hz, the third frequency range is 5Hz to 40Hz, the fourth frequency range is 7Hz to 40Hz, and the fifth frequency range is 1Hz to 10Hz.

[0027] In some optional embodiments of this application, the heart rate at which the maximum value in the HarSum spectrum is located is obtained as the average heart rate;

[0028] Obtaining the heartbeat quality of each heartbeat signal from the plurality of target heartbeat signals includes:

[0029] Perform the following steps for each of the target heartbeat signals:

[0030] The current target heartbeat signal is divided into sample signal and matching signal based on a preset time period;

[0031] Based on the average heart rate, a sample heartbeat signal with a maximum value point as the midpoint and a length equal to the average cardiac cycle is extracted from the sample signal.

[0032] The sample heartbeat signals are clustered to obtain multiple clusters;

[0033] Select one or more clusters from the plurality of clusters as templates;

[0034] Based on the average heart rate, the heartbeat signal with the maximum value point as the midpoint and the length of the average cardiac cycle is extracted from the matched signal.

[0035] The heartbeat quality is generated based on the matching degree between the heartbeat signal and the template.

[0036] In some optional embodiments of this application, the sample heartbeat signals are clustered to obtain multiple clusters, including:

[0037] Obtain the Pearson correlation coefficient between any two of the sample heartbeat signals;

[0038] Based on the Pearson correlation, the sample heartbeat signals were clustered using BSAS to obtain multiple clusters;

[0039] The cluster with the highest mean of the heartbeat signal center point is selected as the first template, and the cluster with the largest sum of the Pearson correlation coefficients is selected as the second template from the other clusters.

[0040] In some optional embodiments of this application, generating the heartbeat quality based on the matching degree between the heartbeat signal and the template includes:

[0041] Obtain the correlation coefficient between the heartbeat signal and the template;

[0042] The heartbeat quality is obtained by multiplying the largest correlation coefficient by the corresponding weighting coefficient.

[0043] The higher the low cutoff frequency of the high-quality frequency range, the larger the weighting coefficient.

[0044] In some optional embodiments of this application, the heartbeat signals are selected beat by beat based on the heartbeat quality and fused to obtain a heartbeat interval sequence, including:

[0045] The heartbeat signals with a heartbeat quality greater than a preset value are selected and fused to obtain the heartbeat interval sequence.

[0046] According to a second aspect of the embodiments of this application, a heart rate interval measurement device is provided, comprising:

[0047] The first acquisition module is used to acquire multiple heartbeat signals through a heterogeneous sensor;

[0048] The second acquisition module is used to acquire the high-quality frequency range corresponding to each heartbeat signal;

[0049] A filtering module is used to filter each heartbeat signal based on a corresponding high-quality frequency range to obtain multiple target heartbeat signals;

[0050] The matching module is used to obtain the heartbeat quality of each heartbeat signal among the multiple target heartbeat signals;

[0051] The fusion module is used to select the heartbeat signals one by one based on the heartbeat quality and fuse them to obtain the heartbeat interval sequence.

[0052] According to a third aspect of the embodiments of this application, an electronic device is provided, which may include:

[0053] processor;

[0054] Memory used to store processor-executable instructions;

[0055] The processor is configured to execute instructions to implement the heartbeat interval measurement method as shown in any embodiment of the first aspect.

[0056] According to a fifth aspect of the embodiments of this application, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the heartbeat interval measurement method as shown in any embodiment of the first aspect.

[0057] The above-mentioned technical solution of this application has the following beneficial technical effects:

[0058] The heartbeat interval measurement method provided in this application uses a heterogeneous non-contact sensor to extract and fuse the heartbeat intervals step by step, which improves the accuracy of heartbeat interval extraction. This method is based on the periodicity of the heartbeat to fuse heartbeats, and does not depend on the morphological characteristics of the heartbeat signal. It is especially suitable for processing cardiac impact signals with high degree of change and different signal characteristics of different sensors, and has better robustness and applicability. Attached Figure Description

[0059] Figure 1 This is a flowchart illustrating a method for measuring the interval between heartbeats in an exemplary embodiment of this application;

[0060] Figure 2 This is a flowchart illustrating a method for measuring the interval between heartbeats in another exemplary embodiment of this application;

[0061] Figure 3 This is a schematic diagram of a harmonic addition method in an exemplary embodiment of this application;

[0062] Figure 4 This is a schematic diagram of heartbeat signal fusion in an exemplary embodiment of this application;

[0063] Figure 5 This is a schematic diagram of the structure of a heartbeat interval measurement device according to an exemplary embodiment of this application;

[0064] Figure 6 This is a schematic diagram of the electronic device structure in an exemplary embodiment of this application;

[0065] Figure 7 This is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of this application. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to specific embodiments and accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of this application. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0067] The accompanying drawings illustrate layer structure diagrams according to embodiments of this application. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0068] Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0069] In the description of this application, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0070] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0071] Research has shown that multi-channel sensors can improve the accuracy and coverage of contactless heart monitoring compared to single-channel heartbeat signal detection. However, different types of sensors typically employ different signal processing methods, and fusing heartbeat signals acquired by multiple sensors remains a challenge. Therefore, this invention proposes using heterogeneous contactless sensors (i.e., different types of contactless sensors) to extract beat-by-beat heartbeat intervals and presents an algorithmic framework for extracting beat-by-beat heartbeat intervals from multi-channel contactless heartbeat signals.

[0072] The non-contact heartbeat signals mentioned here include cardiac impulse signals (BCG) measured using piezoelectric sensors, fiber optic sensors, pressure sensors, accelerometers, etc., as well as Doppler cardiac signals (DCG) measured using radar and other signals with similar characteristics. In the following text, "heartbeat signal" refers to non-contact heartbeat signals.

[0073] The following description, in conjunction with the accompanying drawings, details the heartbeat interval measurement method, heartbeat interval measurement device, electronic device, and storage medium provided in this application through specific embodiments and application scenarios.

[0074] like Figure 1 As shown, in a first aspect of this application embodiment, a method for measuring heart rate interval is provided, the method may include:

[0075] Step S101: Acquire multiple heartbeat signals using a heterogeneous sensor;

[0076] Step S102: Obtain the high-quality frequency range corresponding to each heartbeat signal;

[0077] Step S103: Filter each heartbeat signal based on the corresponding high-quality frequency range to obtain multiple target heartbeat signals;

[0078] Step S104: Obtain the heartbeat quality of each heartbeat signal from multiple target heartbeat signals;

[0079] Step S105: Select heartbeat signals one by one based on heartbeat quality and fuse them to obtain the heartbeat interval sequence.

[0080] The heartbeat interval measurement method provided in this embodiment improves the accuracy of heartbeat interval extraction by using heterogeneous non-contact sensors to extract and fuse beat-by-beat heartbeat intervals. This method fuses heartbeats based on the periodicity of the heartbeat, independent of the morphological characteristics of the heartbeat signal, and is particularly suitable for processing highly variable cardiac impact signals and different signal characteristics from different sensors, exhibiting better robustness and applicability.

[0081] In some embodiments, step S102 includes: acquiring a plurality of candidate frequency ranges;

[0082] Perform the following steps for each heartbeat signal:

[0083] Obtain the filtered signal of the current heartbeat signal in each candidate frequency range;

[0084] Normalize the filtered signal;

[0085] The normalized and filtered signal is exponentially multiplied and then filtered based on the fifth frequency range;

[0086] Obtain the average peak-to-valley distance of the filtered signal;

[0087] Candidate frequency points are extracted from the filtered signal based on the average peak-valley distance.

[0088] The HarSum spectrum is obtained by performing an FFT transform on the candidate frequency points;

[0089] The spectral amplitude corresponding to the candidate frequency point in the HarSum spectrum is used as the signal quality.

[0090] The candidate frequency range with the highest corresponding signal quality is taken as the high-quality frequency range.

[0091] Among them, the candidate frequency ranges include the first frequency range of 1Hz to 40Hz, the second frequency range of 3Hz to 40Hz, the third frequency range of 5Hz to 40Hz, the fourth frequency range of 7Hz to 40Hz, and the fifth frequency range of 1Hz to 10Hz.

[0092] The heartbeat interval measurement method provided in this embodiment uses a bandpass filter with a variable low cutoff frequency to obtain different components of the heartbeat signal, thereby obtaining the optimal heartbeat signal components and improving the accuracy of the heartbeat interval. It offers higher accuracy and coverage for beat-by-beat heartbeat interval detection. Innovatively, it calculates the average heart rate of the heartbeat signal spectrum using a harmonic addition method, which can adapt to various cardiac impulse signal morphological patterns. Subsequent template calculation and matching do not depend on the morphological characteristics of the heartbeat signal but solely on its quasi-periodic nature.

[0093] In some embodiments, step S104 includes:

[0094] To acquire the heartbeat quality of each heartbeat signal from multiple target heartbeat signals, including:

[0095] Perform the following steps for each target heartbeat signal:

[0096] The current target heartbeat signal is divided into sample signal and matching signal based on a preset time period;

[0097] Based on the average heart rate, sample heartbeat signals with the maximum value point as the midpoint and the length of the average cardiac cycle are extracted from the sample signals.

[0098] Multiple clusters were obtained by clustering the sample heartbeat signals;

[0099] Select one or more clusters from multiple clusters as templates;

[0100] Based on the average heart rate, a heartbeat signal with a maximum value point as the midpoint and a length equal to the average cardiac cycle is extracted from the matched signal.

[0101] Heartbeat quality is generated based on the matching degree between the heartbeat signal and the template.

[0102] Specifically, the sample heartbeat signals are clustered to obtain multiple clusters, including:

[0103] Obtain the Pearson correlation coefficient between any two sample heartbeat signals;

[0104] Based on the Pearson correlation, BSAS clustering was performed on the sample heartbeat signals to obtain multiple clusters;

[0105] The cluster with the highest mean of the heartbeat signal center point was selected as the first template, and the cluster with the largest sum of Pearson correlation coefficients among the other clusters was selected as the second template.

[0106] Heartbeat quality is generated based on the matching degree between the heartbeat signal and the template, including:

[0107] Obtain the correlation coefficient between the heartbeat signal and the template;

[0108] The heartbeat quality is obtained by multiplying the largest correlation coefficient by the corresponding weight coefficient.

[0109] Among them, the higher the low cutoff frequency in the high-quality frequency range, the greater the weighting coefficient.

[0110] The framework proposed in this embodiment for measuring heart rate intervals includes using the Harmonic Sum (HarSum) algorithm for average heart rate estimation, using the Basic Sequential Scheme (BSCS) for template extraction, and using Optimal Filter Selection (OFS) and Signal Quality Index (SQI) for optimal signal selection and fusion. This achieves high-precision and robust IBI measurement on multi-channel heart rate signal data from heterogeneous sensors.

[0111] In some embodiments, step S105 includes:

[0112] Heartbeat signals with a quality greater than a preset value are selected and fused to obtain the inter-heartbeat sequence.

[0113] Figure 2 This is a flowchart illustrating a method for measuring heart rate intervals according to another exemplary embodiment of this application. Figure 2 As shown, in a second aspect of the embodiments of this application, a method for measuring the heart rate interval is provided, the method may include:

[0114] Step 1: Bandpass filtering with variable low cutoff frequency

[0115] Multiple bandpass filters with different filtering parameters are used to process multi-channel cardiac impulse signals to extract different heartbeat components. Generally, due to the presence of heart valve signals, higher signal frequencies can obtain a more accurate heartbeat interval compared to the ECG reference signal. The bandpass filter parameters selected here are based on a high cutoff frequency f. H =40Hz, low cutoff frequency f L ∈{f1=1Hz, f2=3Hz, f3=5Hz, f4=7Hz}. These bandpass filters correspond to weighting coefficients β=1+0.05×(f L -1).

[0116] This weighting factor will be used in step 6.

[0117] Step 2: Power and Bandpass Filtering

[0118] After normalizing the signals processed in step 1, they are exponentially multiplied and then bandpass filtered. The cutoff frequency of the bandpass filter is 1Hz-10Hz. The purpose of this preprocessing step is to shift the frequency band distribution of the signal to lower harmonic frequencies.

[0119] Step 3: Calculate the average heart rate and signal quality using the harmonic addition method.

[0120] In order to calculate the average heart rate better in various modes of heartbeat signal, the harmonic addition method is used to process the higher harmonics of the heartbeat signal spectrum.

[0121] In the spectrum, a good candidate fundamental frequency should not only have peaks at integer multiples, but also valleys at half-integer multiples. The concept of peak-valley distance is introduced to measure the significance of a peak in its spectrum relative to its two adjacent valleys.

[0122]

[0123] Where d k(f) represents the peak-to-valley distance at frequency f. |X(kf)| represents the FFT frequency response amplitude at frequency kf, where k is a positive integer.

[0124] The average peak-to-valley distance (APVD) of each harmonic can represent the salience of the frequency:

[0125]

[0126] APVD can be represented as the inner product of the amplitude spectrum and the kernel function, with upward impulses at integer multiples and downward impulses at half-integer multiples. Here, we limit the number of harmonics to less than 7. For frequency f′, the following kernel function is applied:

[0127]

[0128] For each candidate frequency point f', the inner product of the FFT amplitude spectrum and the kernel function is calculated to obtain the HarSum spectrum.

[0129] |HS(f')|=<|X(f)|,K(f,f′)>

[0130] like Figure 3 As shown, the heart rate at which the maximum value in the HarSum spectrum is located represents the average heart rate.

[0131] Here, we can obtain the signal quality index based on the HarSum spectrum. Since the signal has been normalized, the HarSum spectral amplitude of the candidate fundamental frequency can, to some extent, represent the energy ratio of the candidate fundamental frequency to its corresponding higher harmonics. We define:

[0132] SQI HarSum =max(HarSum(f))

[0133] Step 4: Selection of the low cutoff frequency of the bandpass filter

[0134] For the signal of each channel, select SQI. HarSum The signal corresponding to the lowest cutoff frequency bandpass filter is used for the next step of template group extraction and beat-by-beat heart rate calculation.

[0135] Step 5: Extract template groups using BSCS

[0136] For each channel of cardiac impact signal that meets the conditions, we first extract a template from the data. To address the morphological differences within each respiratory cycle of certain signals caused by respiratory modulation, we use a set of templates instead of a single template, calculated using the Basic Sequential Algorithm Scheme (BSAS).

[0137] A set of signals with a length of L equal to the average cardiac cycle is selected, with all the maximum points of an initial 10-second signal as the midpoint. They were then clustered using BSAS.

[0138] in:

[0139]

[0140] calculate Correlation matrix:

[0141]

[0142] Where corr(q) x ,q y ) represents q x and q y The Pearson correlation coefficient between them.

[0143] Subsequently, BSAS clustering was performed using the correlation coefficients obtained from the matrix, with the threshold set to θ1 = 0.8, meaning that correlation coefficients greater than 0.8 were grouped into the same class, and signal segments with similar morphology were grouped into the same category.

[0144] The class with the highest mean of the signal segment center point is selected as the first template class, and a sample signal with the largest sum of correlation coefficients with samples in other classes is selected as the template.

[0145] If the signal segments in this class, when connected, have a large gap compared to the original signal segments, there may be an additional heartbeat pattern caused by respiration. In this case, continue calculating another template using the method described above.

[0146] Step 6: Template Matching Stage (Correlation Coefficient Function Calculation)

[0147] For each channel signal, the correlation coefficient between each template in the template group and each peak in the subsequent cardiac impact signal is calculated to obtain the correlation coefficient function.

[0148] CCF α (x)=corr[bcg(x),T α ]×P(x),α∈{1,2}

[0149] P(x) is an indicator function:

[0150]

[0151] At this point, another signal quality index is introduced. This represents the matching degree of the i-th heartbeat.

[0152]

[0153] Here, β is the weighting coefficient from step 1.

[0154] Step 7: Selecting and fusing the heartbeat intervals in each beat

[0155] like Figure 4 As shown, in this step, the IBI from multiple channels will be based on the SQI of each channel. beat Make selections and combinations. For the i-th heartbeat, when... Select the channel for final IBI calculation based on the following formula:

[0156] Figure 5 This is a schematic diagram of a heart rate interval measurement device according to an exemplary embodiment of this application. Figure 5 As shown, in a third aspect of the embodiments of this application, a heart rate interval measurement device is provided, comprising:

[0157] The first acquisition module 11 is used to acquire multiple heartbeat signals through a heterogeneous sensor;

[0158] The second acquisition module 12 is used to acquire the high-quality frequency range corresponding to each heartbeat signal;

[0159] Filtering module 13 is used to filter each heartbeat signal based on the corresponding high-quality frequency range to obtain multiple target heartbeat signals;

[0160] Matching module 14 is used to obtain the heartbeat quality of each heartbeat signal among multiple target heartbeat signals;

[0161] The fusion module 15 is used to select heartbeat signals one by one based on heartbeat quality and fuse them to obtain the heartbeat interval sequence.

[0162] Optionally, such as Figure 6 As shown, this application embodiment also provides an electronic device 1100, including a processor 1101, a memory 1102, and a program or instructions stored in the memory 1102 and executable on the processor 1101. When the program or instructions are executed by the processor 1101, they implement the various processes of the above-described heartbeat interval measurement method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0163] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0164] Figure 7 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0165] The electronic device 1200 includes, but is not limited to, components such as: radio frequency unit 1201, network module 1202, audio output unit 1203, input unit 1204, sensor 1205, display unit 1206, user input unit 1207, interface unit 1208, memory 1209, and processor 1210.

[0166] Those skilled in the art will understand that the electronic device 1200 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1210 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 7 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0167] It should be understood that, in this embodiment, the input unit 1204 may include a graphics processing unit (GPU) 12041 and a microphone 12042. The GPU 12041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1206 may include a display panel 12061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1207 includes a touch panel 12071 and other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 may include a touch detection device and a touch controller. Other input devices 12072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here. The memory 1209 can be used to store software programs and various data, including but not limited to applications and operating systems. Processor 1210 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 1210.

[0168] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described heartbeat interval measurement method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0169] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0170] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described heartbeat interval measurement method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0171] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0172] 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. Without further limitations, 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. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0173] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0174] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for measuring the interval between heartbeats, characterized in that, include: Multiple heartbeat signals are acquired using heterogeneous non-contact sensors; Obtaining a high-quality frequency range corresponding to each heartbeat signal includes: obtaining multiple candidate frequency ranges; performing the following steps on each heartbeat signal: obtaining the filtered signal of the current heartbeat signal in each candidate frequency range; calculating the signal quality of the filtered signal using the harmonic addition method; and selecting the candidate frequency range with the highest corresponding signal quality as the high-quality frequency range. Multiple target heartbeat signals are obtained by filtering each heartbeat signal based on the corresponding high-quality frequency range; Obtain the heartbeat quality of each heartbeat signal from the plurality of target heartbeat signals; Based on the heartbeat quality, the heartbeat signals are selected one by one and fused to obtain the heartbeat interval sequence; The plurality of candidate frequency intervals include a first frequency interval, a second frequency interval, a third frequency interval, and a fourth frequency interval. The first frequency interval, the second frequency interval, the third frequency interval, and the fourth frequency interval have the same high cutoff frequency but different low cutoff frequencies.

2. The method for measuring cardiac interval according to claim 1, characterized in that, The signal quality of the filtered signal is calculated using the harmonic addition method, including: Obtain the average peak-to-valley distance of the filtered signal; Candidate frequency points are extracted from the filtered signal based on the average peak-to-valley distance. The HarSum spectrum value of the corresponding frequency is obtained by convolving the FFT spectrum with the kernel function corresponding to the candidate frequency point. The spectral amplitude corresponding to the candidate frequency point in the HarSum spectrum is taken as the signal quality.

3. The method for measuring cardiac interval according to claim 2, characterized in that, Before calculating the signal quality of the filtered signal using the harmonic addition method, the following steps are also included: The filtered signal is then normalized. The normalized filtered signal is then exponentially filtered based on the fifth frequency range.

4. The method for measuring cardiac interval according to claim 3, characterized in that, The first frequency range is 1Hz to 40Hz, the second frequency range is 3Hz to 40Hz, the third frequency range is 5Hz to 40Hz, the fourth frequency range is 7Hz to 40Hz, and the fifth frequency range is 1Hz to 10Hz.

5. The method for measuring cardiac interval according to claim 2, characterized in that, Also includes: The heart rate at which the maximum value in the HarSum spectrum is located is taken as the average heart rate. Obtaining the heartbeat quality of each heartbeat signal from the plurality of target heartbeat signals includes: Perform the following steps for each of the target heartbeat signals: The current target heartbeat signal is divided into sample signal and matching signal based on a preset time period; Based on the average heart rate, a sample heartbeat signal with a maximum value point as the midpoint and a length equal to the average cardiac cycle is extracted from the sample signal. The sample heartbeat signals are clustered to obtain multiple clusters; Select one or more clusters from the plurality of clusters as templates; Based on the average heart rate, the heartbeat signal with the maximum value point as the midpoint and the length of the average cardiac cycle is extracted from the matched signal. The heartbeat quality is generated based on the matching degree between the heartbeat signal and the template.

6. The method for measuring cardiac interval according to claim 5, characterized in that, Clustering the sample heartbeat signals yields multiple clusters, including: Obtain the Pearson correlation coefficient between any two of the sample heartbeat signals; Based on the Pearson correlation, the sample heartbeat signals were clustered using BSAS to obtain multiple clusters; The cluster with the highest mean of the heartbeat signal center point is selected as the first template, and the cluster with the largest sum of the Pearson correlation coefficients is selected as the second template from the other clusters.

7. The method for measuring cardiac interval according to claim 5, characterized in that, The heartbeat quality is generated based on the matching degree between the heartbeat signal and the template, including: Obtain the correlation coefficient between the heartbeat signal and the template; The heartbeat quality is obtained by multiplying the largest correlation coefficient by the corresponding weighting coefficient. The higher the low cutoff frequency of the high-quality frequency range, the larger the weighting coefficient.

8. A method for measuring cardiac interval according to any one of claims 1-7, characterized in that, Based on the heartbeat quality, the heartbeat signals are selected beat by beat and fused to obtain the inter-heartbeat sequence, including: The heartbeat signals with a heartbeat quality greater than a preset value are selected and fused to obtain the heartbeat interval sequence.

9. A device for measuring the interval between heartbeats, characterized in that, include: The first acquisition module is used to acquire multiple heartbeat signals through a heterogeneous non-contact sensor; The second acquisition module is used to acquire the high-quality frequency interval corresponding to each heartbeat signal. The second acquisition module includes: an interval acquisition unit, used to acquire multiple candidate frequency intervals; a signal quality calculation unit, used to acquire the filtered signal of the current heartbeat signal in each candidate frequency interval, and calculate the signal quality of the filtered signal by the harmonic addition method; and an interval determination unit, used to take the candidate frequency interval with the highest corresponding signal quality as the high-quality frequency interval. A filtering module is used to filter each heartbeat signal based on a corresponding high-quality frequency range to obtain multiple target heartbeat signals; The matching module is used to obtain the heartbeat quality of each heartbeat signal among the multiple target heartbeat signals; The fusion module is used to select the heartbeat signals one by one based on the heartbeat quality and fuse them to obtain the heartbeat interval sequence; The plurality of candidate frequency intervals include a first frequency interval, a second frequency interval, a third frequency interval, and a fourth frequency interval. The first frequency interval, the second frequency interval, the third frequency interval, and the fourth frequency interval have the same high cutoff frequency but different low cutoff frequencies.

10. An electronic device, characterized in that, include: A processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement a method for measuring heart intervals as described in any one of claims 1-8.

11. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement a method for measuring heart intervals as described in any one of claims 1-8.

Images