Signal screening method and device, storage medium and wearable equipment
By collecting and labeling physiological signals, the problem of signal quality decline in the prior art is solved, and effective screening and quality improvement of PPG, ECG or PCG signals is achieved, ensuring the accuracy of the analysis results.
Patent Information
- Application Number
- CN202411536948.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2025-02-25
AI Technical Summary
The prior art is difficult to effectively screen and improve the interference caused by PPG signals, ECG signals or PCG signals during transmission, resulting in a decrease in signal quality and inaccurate analysis results.
By collecting the user's first physiological signal (such as PPG, ECG, or PCG signal) and the second physiological signal (at least one of the remaining two signals), the parameter values are determined based on these signals for horizontal and vertical marking, and finally the first physiological signal is screened by the marking results.
Quality screening of PPG signals, ECG signals or PCG signals is realized, improving the accuracy and reliability of the signals, so that the subsequent analysis results are more accurate.
Smart Images
Figure CN119513653A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of signal processing technology, and in particular to a signal screening method, device, storage medium and wearable device. Background Art
[0002] Currently, photoplethysmography (PPG) signals, electrocardiogram (ECG) signals, and phonocardiogram (PCG) signals are widely used in clinical medicine.
[0003] However, the three physiological signals are affected by different factors during transmission and suffer losses, which leads to a decrease in signal quality. For example, PPG signals may be interfered by movement and ambient light, ECG signals may be affected by poor electrode contact and electromagnetic interference, and PCG signals are susceptible to external noise interference. These losses greatly reduce the accuracy and reliability of the signals, and thus the accuracy of subsequent analysis results.
[0004] Therefore, how to perform quality screening on PPG signals, ECG signals or PCG signals so as to make subsequent analysis results more accurate is an urgent problem to be solved. Summary of the invention
[0005] The main purpose of this application is to provide a signal screening method, device, storage medium and wearable device, aiming to solve the existing technical problem of how to screen the interference received by PPG signals, ECG signals or PCG signals during transmission.
[0006] To achieve the above object, the present application provides a signal screening method, the method comprising:
[0007] Collecting a first physiological signal and a second physiological signal of a user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals;
[0008] determining a first parameter value based on the first physiological signal, and transversely marking the first physiological signal by the first parameter value;
[0009] determining a second parameter value based on the first physiological signal and the second physiological signal, and longitudinally marking the first physiological signal by the second parameter value;
[0010] The first physiological signal is screened by using the horizontal marking result and the vertical marking result to obtain a screening result.
[0011] In one embodiment, the step of determining a first parameter value based on the first physiological signal and transversely marking the first physiological signal by the first parameter value comprises:
[0012] Dividing the first physiological signal according to a preset division window to obtain a first divided signal;
[0013] Determine a first parameter value corresponding to each of the first division signals, and horizontally mark the corresponding first division signal by each of the first parameter values;
[0014] The step of determining a second parameter value based on the first physiological signal and the second physiological signal, and longitudinally marking the first physiological signal by the second parameter value comprises:
[0015] Dividing the second physiological signal according to the preset division window to obtain a second divided signal;
[0016] A second parameter value is determined based on each of the first division signals and the corresponding second division signal, and the first division signals are vertically marked by the second parameter value.
[0017] In one embodiment, the step of determining the first parameter value corresponding to each of the first division signals and horizontally marking the corresponding first division signal by each of the first parameter values includes:
[0018] Determine a first single waveform heart rate value of each waveform in each of the first divided signals, and determine a first average heart rate value corresponding to each of the first divided signals;
[0019] The corresponding first divided signals are horizontally marked by each of the first average heart rate values and each of the first single-waveform heart rate values.
[0020] In one embodiment, the step of horizontally marking the corresponding first divided signals by each of the first average heart rate values and each of the first single waveform heart rate values comprises:
[0021] determining a first difference between each of the first single waveform heart rate values and the corresponding first average heart rate value;
[0022] Each of the first differences is compared with a first preset difference threshold, and the corresponding first division signal is horizontally marked according to the comparison result.
[0023] In one embodiment, the step of determining a second parameter value based on each of the first division signals and the corresponding second division signal, and vertically marking the first division signals by the second parameter value includes:
[0024] Determine a first single waveform heart rate value of each waveform in each of the first divided signals, and determine a second single waveform heart rate value of each of the waveforms in each of the second divided signals;
[0025] The corresponding first divided signals are vertically marked by each of the first single-waveform heart rate values and each of the second single-waveform heart rate values.
[0026] In one embodiment, the step of vertically marking the corresponding first divided signal by each of the first single waveform heart rate values and each of the second single waveform heart rate values comprises:
[0027] determining a second average heart rate value based on each of the first single-waveform heart rate values and each of the second single-waveform heart rate values;
[0028] The corresponding first divided signals are vertically marked by each of the first single waveform heart rate values and the corresponding second average heart rate value.
[0029] In one embodiment, the step of longitudinally marking the corresponding first divided signal by each of the first single waveform heart rate values and the corresponding second average heart rate value comprises:
[0030] Determine a second difference between each of the first single waveform heart rate values and the corresponding second average heart rate value;
[0031] Each of the second differences is compared with a second preset difference threshold, and the corresponding first division signal is vertically marked according to the comparison result.
[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a signal screening device, the device comprising:
[0033] a signal acquisition module, configured to acquire a first physiological signal and a second physiological signal of a user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals;
[0034] a first marking module, configured to determine a first parameter value based on the first physiological signal, and to perform horizontal marking on the first physiological signal by using the first parameter value;
[0035] a second marking module, configured to determine a second parameter value based on the first physiological signal and the second physiological signal, and to vertically mark the first physiological signal by the second parameter value;
[0036] The signal screening module is used to screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain a screening result.
[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a signal filtering program is stored, and when the signal filtering program is executed by a processor, the steps of the signal filtering method described above are implemented.
[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a wearable device, which includes: a memory, a processor, and a signal filtering program stored in the memory and executable on the processor, and when the signal filtering program is executed by the processor, the steps of the signal filtering method described above are implemented.
[0039] The present application provides a signal screening method, device, storage medium and wearable device, the method comprising: collecting a first physiological signal and a second physiological signal of a user, the first physiological signal being a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal being at least one of the remaining two signals; determining a first parameter value based on the first physiological signal, and marking the first physiological signal horizontally by the first parameter value; determining a second parameter value based on the first physiological signal and the second physiological signal, and marking the first physiological signal vertically by the second parameter value; screening the first physiological signal by the horizontal marking result and the vertical marking result to obtain a screening result. Since the present application can use the photoplethysmography signal, electrocardiogram signal or heart sound signal of the user as the first physiological signal, and at least one of the remaining two signals as the second physiological signal, the first physiological signal is horizontally marked, and the first physiological signal is vertically marked by the second physiological signal, and then the first physiological signal is screened according to the horizontal marking result and the vertical marking result to obtain a screening result. Therefore, quality screening of PPG signals, ECG signals or PCG signals can be achieved, so that subsequent analysis results are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0042] Figure 1 A schematic diagram of the structure of a wearable device in the hardware operating environment involved in the embodiment of the present application;
[0043] Figure 2This is a flow chart of the first embodiment of the signal screening method of the present application;
[0044] Figure 3 This is a flow chart of the second embodiment of the signal screening method of the present application;
[0045] Figure 4 This is a schematic diagram of the process of horizontal marking in the second embodiment of the signal screening method of the present application;
[0046] Figure 5 This is a flow chart of the third embodiment of the signal screening method of the present application;
[0047] Figure 6 This is a schematic diagram of the vertical marking process in the third embodiment of the signal screening method of the present application;
[0048] Figure 7 This is a structural block diagram of the first embodiment of the signal screening device of the present application.
[0049] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0051] Reference Figure 1 , Figure 1 A schematic diagram of the wearable device structure of the hardware operating environment involved in the embodiment of the present application.
[0052] like Figure 1 As shown, the wearable device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in this application. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable memory (Non-volatile Memory, NVM), such as a disk storage. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.
[0053] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the wearable device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.
[0054] like Figure 1 As shown, the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a signal screening program.
[0055] exist Figure 1 In the wearable device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the user device; the wearable device calls the signal screening program stored in the memory 1005 through the processor 1001, and executes the signal screening method provided in the embodiment of the present application.
[0056] It should be noted that, currently, photoplethysmography (PPG) signals, electrocardiogram (ECG) signals and phonocardiogram (PCG) signals are widely used in clinical medicine.
[0057] The PPG signal can be a signal obtained by measuring the change in blood volume through an optical sensor, which reflects the change in blood vessel volume caused by the periodic activity of the heart; the ECG signal can be a signal that records the electrical activity of the heart and can be obtained by collecting it through electrodes on the skin surface; the PCG signal can be a signal that records the sound generated by the opening and closing of the heart valves and the flow of blood, which can be obtained by collecting it through an acoustic sensor.
[0058] However, the three physiological signals are affected by different factors during transmission and suffer losses, which leads to a decrease in signal quality. For example, PPG signals may be interfered by movement and ambient light, ECG signals may be affected by poor electrode contact and electromagnetic interference, and PCG signals are susceptible to external noise interference. These losses greatly reduce the accuracy and reliability of the signals, and thus the accuracy of subsequent analysis results.
[0059] Therefore, how to perform quality screening on PPG signals, ECG signals or PCG signals so as to make subsequent analysis results more accurate is an urgent problem to be solved.
[0060] In order to solve the above defects, this embodiment provides a signal screening method, which can use the user's photoplethysmography signal, electrocardiogram signal or heart sound signal as the first physiological signal, and use at least one of the remaining two signals as the second physiological signal, mark the first physiological signal horizontally, and mark the first physiological signal vertically through the second physiological signal, and then screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain the screening result. Therefore, it is possible to achieve quality screening of PPG signals, ECG signals or PCG signals, so that the subsequent analysis results are more accurate.
[0061] For ease of understanding, the following combination Figures 2 to 6 The signal screening method provided in the embodiment of the present application is specifically introduced.
[0062] Reference Figure 2 , Figure 2 Schematic diagram of the flow chart of the first embodiment of the signal screening method of the present application, the first embodiment of the signal screening method of the present application is proposed, such as Figure 2 As shown, in this embodiment, the specific method includes:
[0063] Step S10: collecting a first physiological signal and a second physiological signal of the user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals.
[0064] It is understandable that the method of this embodiment can be applied to a wearable device, wherein the wearable device can be an edge device such as a smart wristband or a smart bracelet that can be worn on a user, or other wearable devices, and this embodiment does not limit this. The execution subject of the method of this embodiment can adopt the above-mentioned wearable device (referred to as the device), and this device is used as an example to illustrate this embodiment and the following embodiments.
[0065] It should be noted that the above-mentioned photoplethysmography signal can be a signal reflecting the change in blood vessel volume caused by the periodic activity of the heart, which can be obtained by collecting through an optical sensor; the above-mentioned electrocardiogram signal can be a signal recording the electrical activity of the heart, which can be obtained by collecting through electrodes on the skin surface; the above-mentioned heart sound signal can be a signal recording the sound generated by the opening and closing of the heart valve and the flow of blood, which can be obtained by collecting through an acoustic sensor. Furthermore, in the above-mentioned device of this embodiment, optical sensors, skin surface electrodes and acoustic sensors can be provided to obtain the above-mentioned physiological signals. Of course, other sensors can also be used, which is not limited in this embodiment. In actual use, the user can obtain the above-mentioned physiological signals by wearing the above-mentioned device.
[0066] It should be understood that the first physiological signal may be a physiological signal that needs to be screened, and the second physiological signal may be a physiological signal referenced when screening the first physiological signal. The first physiological signal and the second physiological signal may be specifically determined according to user needs.
[0067] Exemplarily, for example, if the PPG signal needs to be screened, the PPG signal obtained by simultaneous collection can be used as the above-mentioned first physiological signal, and the ECG signal or PCG signal obtained by simultaneous collection can be used as the above-mentioned second physiological signal. Of course, both the ECG signal and the PCG signal can be used as the above-mentioned second physiological signal. It is only necessary to ensure that the collection time of the first physiological signal and the second physiological signal at each time point is the same, that is, both the first physiological signal and the second physiological signal are collected at the same time.
[0068] Furthermore, in order to ensure the accuracy of subsequent processing, the above-mentioned device can also pre-process the first physiological signal and the second physiological signal after collecting the first physiological signal and the second physiological signal. Specifically, filtering and baseline removal can be used. Of course, other pre-processing methods can also be used, and this embodiment does not limit this.
[0069] Step S20: determining a first parameter value based on the first physiological signal, and transversely marking the first physiological signal by the first parameter value.
[0070] It should also be noted that the above-mentioned first parameter value can be a value used to determine the quality of the physiological signal. In the present embodiment, since the above-mentioned three physiological signals are all composed of continuous waveforms, and each waveform corresponds to one heartbeat. By analyzing these waveforms, the heart rate can be calculated, and theoretically, if the three physiological signals are of stable quality and low noise, the heart rate calculated based on these three physiological signals should be very close. Heart rate is the number of heart beats per unit time, usually expressed in beats per minute (bpm). Heart rate is not only an important physiological indicator, but also reflects the stability of the signal. A single stable signal segment can produce a continuous and consistent heart rate calculation result. Therefore, based on this premise, this embodiment can use the heart rate value as the above-mentioned parameter value for quality analysis.
[0071] The horizontal mark can be a mark for quality analysis based on the waveform of the first physiological signal itself. In actual use, the device can obtain the heart rate value corresponding to each waveform in the first physiological signal, and perform quality analysis on one of the waveforms based on the heart rate values of other waveforms of the first physiological signal, distinguish between stable and unstable waveforms, and complete the horizontal mark.
[0072] Step S30: determining a second parameter value based on the first physiological signal and the second physiological signal, and vertically marking the first physiological signal by the second parameter value.
[0073] It is understandable that the second parameter value may also be a value used to determine the quality of the physiological signal. Similarly, the heart rate value may be used as the parameter value for quality analysis.
[0074] However, it should be emphasized that when performing longitudinal marking, the above-mentioned device can be combined with the second physiological signal for analysis, that is, the first physiological signal and the second physiological signal are combined for quality analysis, and the stable and unstable parts of the first physiological signal are distinguished and marked, thereby completing the longitudinal marking.
[0075] Exemplarily, if the first physiological signal is a PPG signal, and the second physiological signal is an ECG signal and a PCG signal, then when performing vertical marking, the above-mentioned device can determine the second parameter value based on the PPG signal, the ECG signal and the PCG signal, and then perform vertical marking on the PPG signal based on the parameter value.
[0076] Step S40: Screening the first physiological signal according to the horizontal marking result and the vertical marking result to obtain a screening result.
[0077] After the first physiological signal is horizontally marked to obtain stable and unstable signals, and vertically marked to obtain stable and unstable signals, the unstable signal can be eliminated, so as to obtain the signal marked as stable in the first physiological signal, and the signal screening can be completed, and then the subsequent analysis operation can be performed based on the stable signal, so that the subsequent analysis results are more accurate.
[0078] Specifically, the subsequent analysis operation may be used for heart rate monitoring, health analysis, etc., which is not limited in this embodiment.
[0079] Furthermore, considering that the above method can only be judged as having high quality when the entire first physiological signal is stable, but it can also be used if some signals have high quality, in this embodiment, the above step S20 includes:
[0080] Step S21: dividing the first physiological signal according to a preset division window to obtain a first divided signal.
[0081] It should be understood that the above-mentioned preset division window can be a window for signal division, and its window length can be set according to actual conditions. This embodiment uses 5s for illustration. It should be emphasized that when the above-mentioned device in this embodiment divides, in order to improve accuracy, it can be divided according to a certain step length, which can be greater than the window length, and of course can be less than or equal to the window length. This embodiment uses 3s for illustration.
[0082] Exemplarily, if the above-mentioned first physiological signal is a PPG signal of 0s to 20s, after the division operation is performed through the above-mentioned preset division window, the first divided signal that can be obtained includes: a signal of 0s to 5s, a signal of 3s to 8s, a signal of 6s to 11s, a signal of 9s to 14s, a signal of 12s to 17s and a signal of 15s to 20s.
[0083] It should also be emphasized that when the length of the signal in the last preset division window does not reach 5s, all remaining signals will be divided into this window.
[0084] Step S22: determining a first parameter value corresponding to each of the first division signals, and horizontally marking the corresponding first division signals by using each of the first parameter values.
[0085] After obtaining each first division signal, the above-mentioned device can obtain the first parameter value corresponding to each first division signal, and then compare the corresponding first division signals based on each first parameter value, and mark each first division signal as stable or unstable, thereby completing the horizontal marking.
[0086] Correspondingly, the second physiological signal may also be divided using the preset division window. Specifically, the step S30 includes:
[0087] Step S31: dividing the second physiological signal according to the preset division window to obtain a second division signal;
[0088] Step S32: determining a second parameter value based on each of the first division signals and the corresponding second division signal, and vertically marking the first division signals by the second parameter value.
[0089] It should be noted that when dividing the second physiological signal, the preset division window used is consistent with the window used to divide the first physiological signal to facilitate subsequent comparison. Therefore, the specific division process can refer to the above content and will not be repeated here.
[0090] After obtaining each second division signal corresponding to the second physiological signal, each second parameter value can be determined according to the first division signal and the second division signal, and then based on the comparison of each second parameter value with the corresponding first division signal, each first division signal can be marked as stable or unstable to complete the vertical marking.
[0091] Furthermore, after completing the horizontal marking and the vertical marking, the above-mentioned device can eliminate the first division signal that is marked as unstable or both are marked as unstable, and retain the first division signal that is marked as stable twice for subsequent analysis, thereby improving the accuracy of subsequent analysis.
[0092] In this embodiment, the above-mentioned device can use the user's photoplethysmography signal, electrocardiogram signal or heart sound signal as the first physiological signal, and use at least one of the remaining two signals as the second physiological signal, mark the first physiological signal horizontally, and mark the first physiological signal vertically through the second physiological signal, and then screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain the screening result. Therefore, the quality screening of PPG signal, ECG signal or PCG signal can be realized, so that the subsequent analysis results are more accurate.
[0093] Reference Figure 3 , Figure 3 This is a flow chart of the second embodiment of the signal screening method of the present application. Based on the above-mentioned first embodiment, the second embodiment of the signal screening method of the present application is proposed.
[0094] like Figure 3 As shown, in this embodiment, in order to achieve horizontal marking, the above step S22 includes:
[0095] Step S221: determining a first single waveform heart rate value of each waveform in each of the first divided signals, and determining a first average heart rate value corresponding to each of the first divided signals.
[0096] It should be noted that the first single waveform heart rate value may be the heart rate value corresponding to each waveform in the first divided signal. The first average heart rate value may be the average heart rate value of all waveforms in the first divided signal.
[0097] Step S222: horizontally mark the corresponding first divided signals by each of the first average heart rate values and each of the first single waveform heart rate values.
[0098] For ease of understanding, refer to Figure 4 , Figure 4 This is a schematic diagram of the horizontal marking process in the second embodiment of the signal screening method of this application. Figure 4As shown, in actual use, since there may be multiple waveforms in the first divided signal, the above device can calculate the heart rate value corresponding to each waveform according to each waveform, as the above first single waveform heart rate value; and calculate the heart rate average value of all waveforms according to the first single waveform heart rate value of each waveform in the first divided signal, as the first average heart rate value corresponding to the above first divided signal (i.e. Figure 4 Calculate the overall average heart rate of a single window signal).
[0099] Then, the first average heart rate value can be compared with the first single waveform heart rate values corresponding to all the waveforms in the first divided signal. The specific comparison process is the above step S222 including:
[0100] Determine a first difference between each of the first single waveform heart rate values and the corresponding first average heart rate value; compare each of the first difference values with a first preset difference threshold, and horizontally mark the corresponding first division signal according to the comparison result.
[0101] It is understandable that the first preset difference threshold may be a threshold for determining whether the waveform is stable, and may be set according to actual conditions. This embodiment uses ±5bpm for illustration.
[0102] Continue based on Figure 4 After obtaining the first average heart rate value corresponding to the first divided signal, the waveforms can be selected in turn for comparison (i.e. Figure 4 The first waveform is selected in the above method), that is, the first single waveform heart rate value corresponding to the current waveform is subtracted from the first average heart rate value of the entire first divided signal to obtain the above first difference value.
[0103] Then determine whether the first difference is between -5bpm and +5bpm (i.e. Figure 4 Is the difference between the waveform heart rate and the average heart rate greater than the threshold?); if so, it can be explained that the difference between the first single waveform heart rate value and the first average heart rate value of the waveform is large, and the waveform is relatively unstable and marked as unstable (i.e. Figure 4 If not, it means that the difference between the first single waveform heart rate value and the first average heart rate value of the waveform is small, and the waveform is relatively stable, which is marked as stable (i.e. Figure 4 The waveform signal segment is marked as stable).
[0104] After the waveform is marked in the above manner, the next waveform is marked (i.e. Figure 4 The above process is repeated until all waveforms in the first divided signal are marked (i.e. Figure 4Is it the last waveform in the first divided signal? ), then it can be determined according to the marking result whether all waveforms in the current first divided signal are marked as stable (i.e. Figure 4 If so, the first divided signal can be marked as stable (i.e. Figure 4 If not, as long as at least one waveform is marked as unstable, the first divided signal is marked as unstable (i.e. Figure 4 Then continue to mark the next first divided signal, and follow the above process until all the first divided signals are marked, and obtain the horizontal marking result.
[0105] Reference Figure 5 , Figure 5 This is a flow chart of the third embodiment of the signal screening method of the present application. Based on the above embodiments, the third embodiment of the signal screening method of the present application is proposed.
[0106] like Figure 5 As shown, in this embodiment, in order to achieve vertical marking, the above step S32 includes:
[0107] Step S321: determining a first single waveform heart rate value of each waveform in each of the first divided signals, and determining a second single waveform heart rate value of each of the waveforms in each of the second divided signals.
[0108] It should be noted that the first single waveform heart rate value is consistent with the second embodiment, and can be the heart rate value corresponding to each waveform in the first divided signal. The second single waveform heart rate value can be the heart rate value corresponding to each waveform in the second divided signal.
[0109] Step S322: vertically mark the corresponding first divided signal by each of the first single-waveform heart rate values and each of the second single-waveform heart rate values.
[0110] After obtaining the first single waveform heart rate value and the second single waveform heart rate value corresponding to the waveforms at the same time, the first divided signal can be vertically marked. The specific process is that the above step S322 includes:
[0111] A second average heart rate value is determined based on each of the first single waveform heart rate values and each of the second single waveform heart rate values; and the corresponding first divided signal is vertically marked by each of the first single waveform heart rate values and the corresponding second average heart rate value.
[0112] It is understandable that the second average heart rate value may be an average of a heart rate value of a certain waveform in the first divided signal and a heart rate value of a corresponding waveform in the second divided signal at the same time.
[0113] For ease of understanding, refer to Figure 6 , Figure 6 This is a schematic diagram of the vertical marking process in the third embodiment of the signal screening method of this application. Figure 6 As shown, in actual use, the above device can first select the first partition window (i.e. Figure 4 The same time window is selected in the above examples), and then the first first division signal corresponding to the first physiological signal is selected, and the first second division signal corresponding to the second physiological signal is selected. The time of the first division signal is the same as the time of the second division signal. Then, the first single waveform heart rate value corresponding to each waveform in the first division signal is calculated, and the second single waveform heart rate value corresponding to each waveform in the second division signal is calculated (i.e. Figure 6 Calculate the heart rate value of each waveform of PPG, ECG and PCG). Since the first physiological signal in this embodiment is a PPG signal, and the second physiological signal is an ECG signal and a PCG signal, it is necessary to calculate the single waveform heart rate values of the three signals respectively;
[0114] Then select the first waveform in the first divided signal and the first waveform in the second divided signal. Since the acquisition time is consistent, the time points corresponding to the two waveforms are also consistent. Sum the first single waveform heart rate value of the first waveform in the first divided signal and the second single waveform heart rate value of the first waveform in the second divided signal, and then divide by the number of physiological signals (3 physiological signals in this embodiment), then the average heart rate of the three waveforms at that time point can be obtained, and used as the above-mentioned second average heart rate value (i.e. Figure 6 The heart rate average values corresponding to the three signals at each time point are calculated). Then, the corresponding first divided signal can be vertically marked according to the first single waveform heart rate value and the corresponding second average heart rate value.
[0115] Furthermore, the step of vertically marking the corresponding first divided signal by each of the first single waveform heart rate values and the corresponding second average heart rate value comprises:
[0116] Determine a second difference between each of the first single waveform heart rate values and the corresponding second average heart rate value; compare each of the second difference values with a second preset difference threshold, and vertically mark the corresponding first division signal according to the comparison result.
[0117] It should be understood that the second preset difference threshold may be a threshold for determining whether the waveform is stable, and may be set according to actual conditions. The present embodiment may be set to be consistent with the first preset difference, that is, ±5bpm is used for illustration.
[0118] Continue based on Figure 6, similar to the above-mentioned horizontal mark, after obtaining the second average heart rate value corresponding to the first waveform, the above-mentioned device can subtract the first single waveform heart rate value corresponding to the first waveform in the first divided signal from the second average heart rate value to obtain the above-mentioned second difference.
[0119] Then determine whether the second difference is between -5bpm and +5bpm (i.e. Figure 6 Is the difference between the waveform heart rate and the average heart rate in the comparison greater than the threshold?); If so, it can be explained that the difference between the first single waveform heart rate value and the second average heart rate value of the waveform is large, that is, the difference between the heart rate of the waveform in the first physiological signal and the average heart rate of the waveform in the three signals is large, then the waveform is relatively unstable and is marked as unstable (i.e. Figure 6 If not, it means that the difference between the first single waveform heart rate value and the second average heart rate value of the waveform is small, that is, the difference between the heart rate average value of the waveform in the first physiological signal and the waveform in the three signals is small, then the waveform is relatively stable and marked as stable (i.e. Figure 6 The waveform signal segment is marked as stable).
[0120] After the waveform is marked in the above manner, the next waveform is marked (i.e. Figure 6 The above process is repeated until all waveforms in the first divided signal are marked (i.e. Figure 6 Is it the last waveform in the first divided signal? ), then it can be determined according to the marking result whether all waveforms in the current first divided signal are marked as stable (i.e. Figure 6 If so, the first divided signal can be marked as stable; if not, as long as there is at least one waveform marked as unstable (i.e. Figure 6 If the signal segment of the window in the first partition is stable), the first partition signal is marked as unstable (i.e. Figure 6 Then continue to mark the next first divided signal, and follow the above process until all the first divided signals are marked, and obtain the vertical marking result.
[0121] Finally, after obtaining the horizontal marking results and the vertical marking results, the above device can select the signal with unstable horizontal marking and unstable vertical marking from the first physiological signal for elimination, that is, the first divided signal with unstable horizontal marking and unstable vertical marking is eliminated, and the first divided signal with stable horizontal marking and stable vertical marking is retained for subsequent analysis, thereby ensuring the accuracy of subsequent analysis.
[0122] It should also be emphasized that when it is necessary to screen the PPG signal, ECG signal and PCG signal separately, the PPG signal, ECG signal and PCG signal can be used as the above-mentioned first physiological signal, and the remaining two signals can be used as the above-mentioned second physiological signals, and then the above-mentioned schemes can be executed separately. Since the process is the same, this embodiment will not elaborate on this.
[0123] At the same time, since the present embodiment adopts multiple signals for combined analysis, the reliability of signal screening is improved, and the error that may be caused by a single signal can be effectively reduced. For example, the ECG signal may tend to be stable in a motion state, but this section of the signal can be successfully filtered out through the PPG signal that fluctuates due to motion, thereby avoiding some result deviations caused by missing the real fluctuating signals due to the need for multi-signal calculation but filtering and screening with only a single signal.
[0124] Furthermore, since this embodiment uses comparisons in both horizontal and vertical dimensions to comprehensively evaluate the signal quality, it not only considers the internal consistency of a single signal, but also focuses on the synergy between multiple signals, which greatly improves the reliability of screening.
[0125] In addition, an embodiment of the present application further proposes a storage medium, on which a signal screening program is stored. When the signal screening program is executed by a processor, the signal screening method described above is implemented.
[0126] In addition, refer to Figure 7 , Figure 7 1 is a structural block diagram of the first embodiment of the signal screening device of the present application; Figure 7 As shown, the embodiment of the present application also provides a signal screening device, which includes:
[0127] A signal acquisition module 701 is used to acquire a first physiological signal and a second physiological signal of a user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals;
[0128] A first marking module 702, configured to determine a first parameter value based on the first physiological signal, and to perform a transverse marking on the first physiological signal by using the first parameter value;
[0129] A second marking module 703, configured to determine a second parameter value based on the first physiological signal and the second physiological signal, and to vertically mark the first physiological signal by the second parameter value;
[0130] The signal screening module 704 is used to screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain a screening result.
[0131] In this embodiment, the above-mentioned device can use the user's photoplethysmography signal, electrocardiogram signal or heart sound signal as the first physiological signal, and use at least one of the remaining two signals as the second physiological signal, mark the first physiological signal horizontally, and mark the first physiological signal vertically through the second physiological signal, and then screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain the screening result. Therefore, the quality screening of PPG signal, ECG signal or PCG signal can be realized, so that the subsequent analysis results are more accurate.
[0132] As an embodiment, the first marking module 702 is also used to divide the first physiological signal according to a preset division window to obtain a first divided signal; determine the first parameter value corresponding to each of the first divided signals, and horizontally mark the corresponding first divided signal through each of the first parameter values.
[0133] The second marking module 703 is also used to divide the second physiological signal according to the preset division window to obtain a second divided signal; determine a second parameter value based on each of the first divided signals and the corresponding second divided signal, and vertically mark the first divided signal by the second parameter value.
[0134] Based on the above-mentioned first embodiment of the signal screening device of the present application, a second embodiment of the signal screening device of the present application is proposed.
[0135] In this embodiment, the first marking module 702 is also used to determine the first single waveform heart rate value of each waveform in each of the first divided signals, and determine the first average heart rate value corresponding to each of the first divided signals; and horizontally mark the corresponding first divided signals by each of the first average heart rate values and each of the first single waveform heart rate values.
[0136] As an embodiment, the first marking module 702 is also used to determine the first difference between each of the first single waveform heart rate values and the corresponding first average heart rate value; compare each of the first difference values with the first preset difference threshold, and horizontally mark the corresponding first division signal according to the comparison result.
[0137] Based on the above-mentioned embodiments of the signal filtering device of the present application, a third embodiment of the signal filtering device of the present application is proposed.
[0138] In this embodiment, the second marking module 703 is also used to determine the first single waveform heart rate value of each waveform in each of the first divided signals, and to determine the second single waveform heart rate value of each of the waveforms in each of the second divided signals; and to vertically mark the corresponding first divided signals by each of the first single waveform heart rate values and each of the second single waveform heart rate values.
[0139] As an embodiment, the second marking module 703 is also used to determine the second average heart rate value based on each of the first single waveform heart rate values and each of the second single waveform heart rate values; and to vertically mark the corresponding first divided signal by each of the first single waveform heart rate values and the corresponding second average heart rate value.
[0140] As an embodiment, the second marking module 703 is also used to determine the second difference between each of the first single waveform heart rate values and the corresponding second average heart rate value; compare each of the second difference values with a second preset difference threshold, and vertically mark the corresponding first division signal according to the comparison result.
[0141] Other embodiments or specific implementations of the signal screening device described in the present application can refer to the above-mentioned method embodiments and will not be described in detail here.
[0142] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0143] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0144] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0145] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A signal screening method, characterized in that: The method comprises: Collecting a first physiological signal and a second physiological signal of a user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals; determining a first parameter value based on the first physiological signal, and transversely marking the first physiological signal by the first parameter value; determining a second parameter value based on the first physiological signal and the second physiological signal, and longitudinally marking the first physiological signal by the second parameter value; The first physiological signal is screened by using the horizontal marking result and the vertical marking result to obtain a screening result.
2. The method according to claim 1, characterized in that The step of determining a first parameter value based on the first physiological signal and transversely marking the first physiological signal by the first parameter value includes: Dividing the first physiological signal according to a preset division window to obtain a first divided signal; Determine a first parameter value corresponding to each of the first division signals, and horizontally mark the corresponding first division signal by each of the first parameter values; The step of determining a second parameter value based on the first physiological signal and the second physiological signal, and longitudinally marking the first physiological signal by the second parameter value comprises: Dividing the second physiological signal according to the preset division window to obtain a second divided signal; A second parameter value is determined based on each of the first division signals and the corresponding second division signal, and the first division signals are vertically marked by the second parameter value.
3. The method according to claim 2, characterized in that The step of determining the first parameter value corresponding to each of the first division signals, and horizontally marking the corresponding first division signal by each of the first parameter values, comprises: Determine a first single waveform heart rate value of each waveform in each of the first divided signals, and determine a first average heart rate value corresponding to each of the first divided signals; The corresponding first divided signals are horizontally marked by each of the first average heart rate values and each of the first single-waveform heart rate values.
4. The method according to claim 3, characterized in that The step of horizontally marking the corresponding first divided signals by using the first average heart rate values and the first single waveform heart rate values comprises: determining a first difference between each of the first single waveform heart rate values and the corresponding first average heart rate value; Each of the first differences is compared with a first preset difference threshold, and the corresponding first division signal is horizontally marked according to the comparison result.
5. The method according to claim 2, characterized in that The step of determining a second parameter value based on each of the first division signals and the corresponding second division signal, and vertically marking the first division signal by the second parameter value comprises: Determine a first single waveform heart rate value of each waveform in each of the first divided signals, and determine a second single waveform heart rate value of each of the waveforms in each of the second divided signals; The corresponding first divided signals are vertically marked by each of the first single-waveform heart rate values and each of the second single-waveform heart rate values.
6. The method according to claim 5, characterized in that The step of vertically marking the corresponding first divided signal by each of the first single waveform heart rate values and each of the second single waveform heart rate values comprises: determining a second average heart rate value based on each of the first single-waveform heart rate values and each of the second single-waveform heart rate values; The corresponding first divided signals are vertically marked by each of the first single waveform heart rate values and the corresponding second average heart rate value.
7. The method according to claim 6, characterized in that The step of vertically marking the corresponding first divided signal by each of the first single waveform heart rate values and the corresponding second average heart rate value comprises: Determine a second difference between each of the first single waveform heart rate values and the corresponding second average heart rate value; Each of the second differences is compared with a second preset difference threshold, and the corresponding first division signal is vertically marked according to the comparison result.
8. A signal screening device, characterized in that: The device comprises: a signal acquisition module, configured to acquire a first physiological signal and a second physiological signal of a user, wherein the first physiological signal is a photoplethysmography signal, an electrocardiogram signal or a heart sound signal of the user, and the second physiological signal is at least one of the remaining two signals; a first marking module, configured to determine a first parameter value based on the first physiological signal, and to perform horizontal marking on the first physiological signal by using the first parameter value; a second marking module, configured to determine a second parameter value based on the first physiological signal and the second physiological signal, and to vertically mark the first physiological signal by the second parameter value; The signal screening module is used to screen the first physiological signal according to the horizontal marking result and the vertical marking result to obtain a screening result.
9. A storage medium, characterized in that: The storage medium stores a signal screening program, and when the signal screening program is executed by the processor, the steps of the signal screening method according to any one of claims 1 to 7 are implemented.
10. A wearable device, characterized in that: The wearable device comprises: a memory, a processor, and a signal filtering program stored in the memory and executable on the processor, wherein the signal filtering program implements the steps of the signal filtering method according to any one of claims 1 to 7 when executed by the processor.