Method and apparatus for detecting health signals

Abstract

The embodiment of the present application provides a health signal detection method and device, wherein the health signal detection method comprises the following steps: obtaining a health signal, the health signal comprising a peak value and an interval value; in the case that the peak value and the interval value of a first signal in the health signal satisfy a first condition, taking a valley value or an average value in the first signal as a detection result, wherein the average value is an average value of the peak value and the valley value of the first signal; in the case that the peak value and the interval value of the first signal in the health signal satisfy a second condition, performing reconstruction fitting or waveform repair on the first signal to obtain the detection result.

Description

Technical Field

[0001] This application belongs to the field of electronic equipment technology, and specifically relates to a method and device for detecting health signals. Background Technology

[0002] Currently, smartwatches and other electronic devices typically have the function of detecting pulse waves or other physiological indicators. Taking pulse waves as an example, pulse waves are usually detected using infrared light. However, the signal quality of infrared light is unstable during detection, resulting in poor detection accuracy. Summary of the Invention

[0003] The purpose of this application is to provide a method, device, electronic device, and readable storage medium for detecting health signals, which can effectively solve the technical problem of poor accuracy in the detection of physiological indicators.

[0004] In a first aspect, embodiments of this application provide a method for detecting health signals, including:

[0005] Acquire health signals, which include peak and interval values;

[0006] If the peak value and interval value of the first signal in the health signal meet the first condition, the trough value or mean value in the first signal is taken as the detection result, where the mean value is the average of the peak value and the trough value of the first signal.

[0007] If the peak value and interval value of the first signal in the health signal meet the second condition, the first signal is reconstructed and fitted or the waveform is repaired to obtain the detection result.

[0008] Secondly, embodiments of this application provide a health signal detection device, comprising:

[0009] The acquisition module is used to acquire health signals, which include peak values ​​and interval values.

[0010] The first determining module is used to take the valley value or mean value in the first signal as the detection result when the peak value and interval value of the first signal in the health signal meet the first condition, wherein the mean value is the average value of the peak value and the valley value of the first signal.

[0011] The second determining module is used to reconstruct and fit or repair the waveform of the first signal in the health signal if the peak value and interval value of the first signal in the health signal meet the second condition, so as to obtain the detection result.

[0012] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the health signal detection method provided in the first aspect.

[0013] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the health signal detection method provided in the first aspect.

[0014] Fifthly, embodiments of this application provide a chip including a processor and a communication interface coupled to the processor, the processor being used to run programs or instructions to implement the steps of the health signal detection method provided in the first aspect.

[0015] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the steps of the health signal detection method provided in the first aspect.

[0016] In this embodiment of the application, when the electronic device detects the pulse wave, it emits infrared light, acquires the reflected health signal, and determines the peak value and duration of the health signal. When checking the first signal in the health signal, if the peak value and duration of the first signal meet the first condition, the valley value or average value of the first signal is used as the detection result, wherein the average value is the average of the peak value and valley value of the first signal.

[0017] If the peak value and interval value of the first signal meet the second condition, then the first signal is reconstructed and fitted or the waveform is repaired to obtain the detection result.

[0018] In other words, this application ensures that the detection results of the entire health signal can be obtained by processing signals in different situations, thereby improving the accuracy of pulse wave detection. Attached Figure Description

[0019] Figure 1 A flowchart of one of the methods for detecting health signals according to an embodiment of this application is shown;

[0020] Figure 2 A flowchart is shown in the method for detecting health signals according to an embodiment of this application, in which the conditions for satisfying a first signal are determined;

[0021] Figure 3 A second flowchart of a health signal detection method according to an embodiment of this application is shown;

[0022] Figure 4 A waveform diagram of a health signal with a first signal quality determined in the health signal detection method according to an embodiment of this application is shown.

[0023] Figure 5One of the waveforms of a health signal with a second signal quality determined in the health signal detection method according to an embodiment of this application is shown;

[0024] Figure 6 A second waveform of a health signal with a second signal quality determined in the health signal detection method according to an embodiment of this application is shown.

[0025] Figure 7 One of the waveforms of a health signal of third signal quality determined in the health signal detection method according to an embodiment of this application is shown;

[0026] Figure 8 A second waveform diagram of a health signal of third signal quality determined in the health signal detection method according to an embodiment of this application is shown.

[0027] Figure 9 A schematic diagram illustrating the difference between a health signal of first signal quality and a partial health signal of third signal quality in a health signal detection method according to an embodiment of this application is shown.

[0028] Figure 10 The peak detection of the first waveform in the health signal detection method according to an embodiment of this application is shown;

[0029] Figure 11 The diagram shows waveforms of health signals from multiple channels in a health signal detection method according to an embodiment of this application.

[0030] Figure 12 A schematic diagram of channel switching in a health signal detection method according to an embodiment of this application is shown;

[0031] Figure 13 A structural block diagram of a health signal detection device according to an embodiment of this application is shown;

[0032] Figure 14 A structural block diagram of an electronic device according to an embodiment of this application is shown;

[0033] Figure 15 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of this application is shown. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0035] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0036] The following describes, with reference to the accompanying drawings, a method and apparatus for detecting health signals provided in this application, through specific embodiments and application scenarios.

[0037] Pulse wave detection is usually performed using photoplethysmography (PPG). This application takes the use of infrared light for detection as an example. Specifically, when detecting pulse waves, the electronic device emits infrared light, receives the health signal reflected by the human body, processes the signal, and determines the human pulse wave.

[0038] Figure 1 One of the flowcharts for a health signal detection method according to an embodiment of this application is shown, such as... Figure 1 As shown, the method includes:

[0039] Step 102: Obtain health signals, which include peak values ​​and interval values.

[0040] Specifically, electronic devices acquire health signals when performing pulse wave checks. These devices can be smartwatches or fitness trackers, among others.

[0041] Step 104: If the peak value and interval value of the first signal in the health signal meet the first condition, take the valley value or mean value in the first signal as the detection result, where the mean value is the average of the peak value and the valley value of the first signal.

[0042] Specifically, when the peak value and interval value of the first signal in the health signal meet the first condition, the valley value or mean value of the first signal is used as the detection result. For example, when the peak value of the first signal is unclear or cannot accurately reflect the state of the first signal, the valley value or mean value of the first signal is used as the detection result, thereby improving the accuracy of health signal detection.

[0043] Step 106: If the peak value and interval value of the first signal in the health signal meet the second condition, reconstruct and fit or repair the waveform of the first signal to obtain the detection result.

[0044] Specifically, when the peak and interval values ​​of the first signal in the health signal meet the second condition, the first signal is reconstructed and fitted or its waveform is repaired. For example, when the peak and valley values ​​of the first signal are not clear or cannot accurately reflect the state of the first signal, the first signal can be reconstructed and fitted or its waveform repaired to improve the accuracy of health signal detection.

[0045] As mentioned above, by improving the accuracy of health signal detection, infrared light can be used to detect pulse waves on electronic devices, thereby improving the battery life of electronic devices. In addition, infrared light is invisible light, which improves the experience of detecting pulse waves at night.

[0046] As one possible implementation, the step of taking the valley value or mean value of the first signal as the detection result when the peak value and interval value of the first signal in the health signal meet a first condition includes: determining the average peak value of N consecutive peak values ​​and the average interval value of M consecutive interval values ​​in the first signal; and taking the valley value or mean value of the first signal as the detection result when the average peak value is in a first interval and the average interval value is in a second interval.

[0047] Specifically, the step of taking the valley value or mean value of the first signal as the detection result when the peak value and interval value of the first signal in the health signal meet the first condition includes: determining N consecutive peak values ​​in the first signal, calculating the average peak value of the N peak values, determining M consecutive interval values, calculating the average interval value of the M interval values, and taking the valley value or mean value of the first signal as the detection result when the average peak value is in a first interval and the average interval value is in a second interval.

[0048] Where N is an integer greater than or equal to 1, and M is an integer greater than or equal to 1. N and M can be the same or different.

[0049] Specifically, the initial average values ​​of the peak and interval values ​​of the health signal can be preset, denoted as AMP0 and PPI0 respectively. The initial average values ​​of the peak and interval values ​​can be set based on experience, for example, based on the balanced pulse wave of a healthy human body. Alternatively, the initial average values ​​of the peak and interval values ​​can be customized by the user, for example, by pre-extracting the user's pulse wave and customizing the average values ​​of the peak and interval values ​​based on the user's pulse wave.

[0050] The local maxima of the health signal are recursively detected and used as the peak value. The method for determining the local maxima is: Peak... i ≥Peak i+1 And Peak i ≥Peak i-1 Peak i Peak is the amplitude of the i-th signal point. i+1Peak is the amplitude of the (i+1)th signal point. i-1 Let be the amplitude of the (i-1)th signal point. That is, if the amplitude of the i-th signal point is greater than the amplitude of the previous signal point, then the amplitude of the i-th signal point is considered to be the peak value.

[0051] For each peak point detected, the amplitude at that point is peaked. i The inter-period values ​​of the forward difference are stored in a buffer of length N. This forms a peak buffer of length N [Peak0, Peak1, ..., Peak]. i ], and an interval value buffer of length M [PPI0, PPI1, ..., PPI] i ], among which, PPI i This represents the value of the i-th interval.

[0052] Calculate the peak buffer [Peak0, Peak1, ..., Peak] i The average peak value N_AMP is used to calculate the interval values ​​buffer[PPI0, PPI1, ..., PPI]. i The average interval value M_PPI is used to determine the signal quality of the healthy signal based on N_AMP, M_PPI, AMP0 and PPI0, thereby realizing the evaluation of the signal quality of the healthy signal.

[0053] Optionally, such as Figure 4 As shown, if PPI0÷th1≤M_PPI≤PPI0×th2 and N_AMP<AMP0÷th3 or N_AMP>AMP0×th4, then the period of the current first signal is considered to have good consistency, but its amplitude is unstable and fluctuates, which is a signal of medium signal quality. In this case, the valley value or mean value in the first signal can be used as the detection result.

[0054] As one possible implementation, when the average peak value is in a first interval and the average interval is in a second interval, the step of taking the valley value or mean value in the first signal as the detection result includes: when the average peak value is in the first interval and the average interval is in the second interval, determining that the sum of the kurtosis of V valley values ​​in the first signal is greater than the sum of the kurtosis of W peak values; when the sum of the kurtosis of V valley values ​​is greater than the sum of the kurtosis of W peak values, determining that the valley value of the first signal is the detection result; when the sum of the kurtosis of V valley values ​​is less than or equal to the sum of the kurtosis of W peak values, determining that the average value of adjacent peak values ​​and valley values ​​of the first signal is the detection result; wherein W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1.

[0055] Specifically, the step of using the valley value or mean value of the first signal as the detection result when the average peak value is in the first interval and the average interval is in the second interval includes: determining the kurtosis of W consecutive peak values ​​and V consecutive valley values ​​of the first signal when the average peak value is in the first interval and the average interval is in the second interval; if the sum of the kurtosis of the V valley values ​​is greater than the sum of the kurtosis of the W peak values, it indicates that the valley value is clearer and more obvious than the peak value, and therefore, the valley value of the first signal can be used as the detection result. Here, W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1; W and V can be the same or different.

[0056] Optionally, when detecting the peak value, the kurtosis of the peak value is also calculated.

[0057] Where Kurt represents kurtosis, X represents the peak value of the Xth signal point, μ represents the average value of the signal points, and E represents the mean operation. The kurtosis of the peak value and the kurtosis of the valley value are calculated in the same way.

[0058] Construct a kurtosis buffer of length W for the peak values, denoted as Peak_Kurt. Calculate the kurtosis of the valley values, constructing a kurtosis buffer of length V for the valley values, denoted as Valley_Kurt. Compare the cumulative sizes of Peak_Kurt and Valley_Kurt.

[0059] If SUM(Valley_Kurt)>SUM(Peak_Kurt), where SUM represents summation, it indicates that the valley value of the first signal in the current segment is relatively obvious. The first signal of medium signal quality in the current segment is determined to be the first signal of medium signal quality with obvious valley value, and the valley value is used as the detection result of the first signal.

[0060] Among them, the peak value is the local maximum value, and the valley value is the local minimum value.

[0061] like Figure 6 As shown, if the sum of the kurtosis of the V troughs is less than or equal to the sum of the kurtosis of the W peaks, it indicates that the troughs and peaks of the current health signal are not clear or obvious. Therefore, the average of adjacent peaks and troughs is used as the detection result. Here, W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1. W and V can be the same or different.

[0062] If SUM(Valley_Kurt) ≤ SUM(Peak_Kurt), where SUM represents summation, it indicates that the peak and trough values ​​of the current segment's health signal are not significant. In this case, the peak index is set to Peak. i and the nearest valley index i mean beat between _ i =(Peak)i +Valley i ) ÷ 2, which is used as the detection result of the health signal.

[0063] That is, by dividing the first signal satisfying the first condition into two categories: Figure 5 as shown, one is the first signal with inconspicuous peak but obvious valley, such as Figure 6 as shown, the first signal with an obvious difference between the peak and the valley. Different detection methods are adopted for the two types to improve the accuracy of health signal detection.

[0064] As a possible implementation, when the peak and interval value of the first signal in the health signal satisfy the second condition, the step of performing reconstruction fitting or waveform repair on the first signal to obtain the detection result comprises: determining the average peak of N consecutive peaks in the first signal and the average interval value of M consecutive interval values; when the average peak is in the third interval and the average interval value is in the fourth interval, performing reconstruction fitting or waveform repair on the first signal to obtain the detection result.

[0065] Specifically, when the peak and interval value of the first signal in the health signal satisfy the second condition, the step of performing reconstruction fitting or waveform repair on the first signal to obtain the detection result comprises: determining N consecutive peaks in the first signal, calculating the average peak of the N peaks, determining M consecutive interval values, calculating the average interval value of the M interval values, and when the average peak is in the third interval and the average interval value is in the fourth interval, performing reconstruction fitting or waveform repair on the first signal to obtain the detection result.

[0066] Wherein, N is an integer greater than or equal to 1, M is an integer greater than or equal to 1, and N and M may be the same or different.

[0067] Optionally, as Figure 4 shown, if N_AMP < AMP0 ÷ th3 or N_AMP > AMP0 × th4, and M_PPI > PPI0 × th2 or M_PPI < PPI0 ÷ th1, then the current health signal is considered to have poor periodicity and large amplitude fluctuation, and belongs to a signal with low signal quality.

[0068] As a possible implementation, when the average peak is in the third interval and the average interval value is in the fourth interval, the step of performing reconstruction fitting or waveform repair on the first signal to obtain the detection result comprises: when the average peak is in the third interval and the average interval value is in the fourth interval, determining the envelope of the first signal; when the envelope of the first signal has an abrupt amplitude change, performing reconstruction fitting on the first signal; when the envelope of the first signal has no abrupt amplitude change, performing waveform repair on the first signal.

[0069] Specifically, the step of reconstructing and fitting or repairing the waveform of the first signal to obtain the detection result when the average peak value is in the third interval and the average interval value is in the fourth interval includes: determining the envelope of the first signal when the average peak value is in the third interval and the average interval value is in the fourth interval; reconstructing and fitting the first signal when there is an amplitude change in the envelope of the first signal; and repairing the waveform of the first signal when there is no amplitude change in the envelope of the first signal.

[0070] In other words, when the average peak value is in the third interval and the average interval value is in the fourth interval, the processing method for the first signal is determined by the envelope of the first signal, thereby improving the accuracy of health signal detection.

[0071] As one possible implementation, the step of reconstructing and fitting the first signal when there is an amplitude abrupt change in the envelope of the first signal includes: determining the motion artifact signal in the first signal when there is an amplitude abrupt change in the envelope; acquiring a second signal adjacent to the motion artifact signal; estimating the average heart rate based on the second signal; determining the number of peaks in the motion artifact signal based on the average heart rate; reconstructing each peak in the motion artifact signal based on the second signal to reconstruct the first signal; and re-determining the detection result of the reconstructed first signal.

[0072] Specifically, in the case of a sudden amplitude change in the envelope of the first signal, the step of reconstructing and fitting the first signal includes: if the envelope of the first signal has a sudden amplitude change, it is considered that the current first signal includes a motion artifact signal; a second signal adjacent to the motion artifact signal is obtained; and the average heart rate is estimated based on the second signal. Then, based on the average heart rate, the number of peaks in the motion artifact signal is determined; each peak in the motion artifact signal is reset based on the second signal; and the detection result of the current first signal is re-determined. If the first signal becomes a condition that satisfies the first condition, the result is determined according to the detection method corresponding to the first signal that satisfies the first condition. Or, if the first signal becomes a condition that satisfies the third condition, the result is determined according to the detection method corresponding to the first signal that satisfies the third condition. Thus, by reconstructing the first signal with the second signal adjacent to the motion artifact signal, the influence of the motion artifact signal on the first signal is eliminated. Furthermore, the second signal is an adjacent signal to the motion artifact signal, which can roughly reflect the actual waveform of the motion artifact signal at that moment, thereby improving the accuracy of the health signal detection result.

[0073] Optionally, for the first signal containing motion artifacts, to ensure the continuity of the first signal, it is necessary to reconstruct and fit the first signal containing the interference from motion artifacts to restore the waveform of the original first signal. Specifically, this involves first identifying the time of the motion artifact, i.e., determining the motion artifact signal. This can be done by identifying motion artifacts using a triaxial accelerometer, or by constructing an envelope using morphological filtering and then identifying motion artifacts using a threshold method.

[0074] like Figure 9 As shown, the waveform within the box is a motion artifact waveform with a length of L. The waveform of the first signal is reconstructed and fitted using the second signal C seconds before and after the box. Here, C can be a positive integer, such as 2, 3, 4, 5, or 6.

[0075] Locate the signal peaks C seconds before and after the bounding box, and count the number D of peaks. Figure 10 In the process, a total of 24 peaks were located. The number of peaks D can be used to estimate the current average heart rate HR as 60÷(10÷N). Furthermore, it can be estimated that there should be L÷[60÷(10÷N)] waveforms of the first signal within the motion artifact signal.

[0076] Since the waveform of the first signal being reconstructed and fitted needs to retain a certain degree of variability, a random function `randint` is used to randomly select N÷2 peaks, such as... Figure 10 As shown, randomly select numbers 2, 6, 8, 10, 12, 14, 16, and 18, and extract the 15 sample points before and after each peak index to obtain the set Peak. i ={num0,num1,…,num 14}, where num represents a sample, and its subscript is the sample requirement. The average of the samples is taken as the waveform of the reconstructed L÷[60÷(10÷N)] first signals.

[0077] in,

[0078]

[0079] Where a, c, and i represent the index of the peak selected by the random function randint.

[0080] Repeat the waveform reconstruction steps until all L÷[60÷(10÷N)] waveforms of the first signal are completely reconstructed.

[0081] After reconstruction, the estimated first signal without motion artifact interference can be obtained, and the first signal can be detected again.

[0082] As one possible implementation, the step of waveform repair of the first signal when there is no amplitude abrupt change in the envelope of the first signal includes: acquiring a third signal from another channel when there is no amplitude abrupt change in the envelope, wherein the third signal and the first signal are signals from the same period; repairing the first signal based on the third signal; and re-determining the detection result of the repaired first signal.

[0083] Specifically, such as Figure 9 As shown, the steps for waveform repair of the first signal when there is no amplitude abrupt change in the envelope of the first signal include: acquiring a third signal from another channel when there is no amplitude abrupt change in the envelope, wherein the third signal is a signal in the same time period as the first signal, repairing the first signal based on the third signal, and re-detecting the repaired first signal.

[0084] The first signal, which does not contain motion artifacts, is mostly due to the tester wearing the device too loosely. Therefore, the first signal can no longer accurately represent the user's pulse wave. Thus, the accuracy of pulse wave detection can be improved by using the third signal from other channels.

[0085] After acquiring the third signal from other channels, channels can be switched or channel fusion can be performed.

[0086] Optionally, for the first signal without motion artifacts, channel switching or channel fusion can be performed to repair the waveform of the first signal. Generally, the first signal is acquired using multiple channels of light source; if the signal quality of one channel is poor, the signal quality of another channel may be good. Therefore, channel fusion or channel switching can be used for waveform repair. The following explanation uses channel switching as an example.

[0087] like Figure 11 As shown, there are currently four channels: combin01, combin03, combin12, and combin23, and the currently used channel is combin01. Combin01 has been detected as the third signal without motion artifact interference, and switching to this channel is necessary.

[0088] For the four-channel health signal spanning F seconds historically, the morphological envelopes are calculated as up0, up1, up2, and up3, and the upper envelopes are calculated as down0, down1, down2, and down3. Here, F is a positive integer, such as 4, 5, 6, 7, 8, or 9.

[0089] The sum of the standard deviations of the upper and lower envelope amplitudes is calculated as std(up0) + std(down0), std(up1) + std(down1), std(up2) + std(down2), and std(up3) + std(down3), where std is a function of standard deviation. The smaller the sum of the standard deviations of the upper and lower envelopes, the better the consistency between the peaks and troughs of the healthy signal, indicating better quality. Specifically, channel combin01 corresponds to std(up0) + std(down0), channel combin03 corresponds to std(up1) + std(down1), channel combin12 corresponds to std(up3) + std(down3), and channel combin23 corresponds to std(up3) + std(down3).

[0090] Therefore, the following decision is made:

[0091] If std(up0) + std(down0) is the smallest, then the current combin01 channel is retained;

[0092] If std(up1) + std(down1) is the smallest, then switch to the combin03 channel;

[0093] If std(up2) + std(down2) is the smallest, then switch to the combin12 channel;

[0094] If std(up3) + std(down3) is the smallest, then switch to the combin23 channel;

[0095] Subsequent health signals will be detected using the switched channel.

[0096] like Figure 12 As shown, the arrows indicate the selected channels. Before the switch, the combin01 channel was used, which is the first signal without significant motion artifact interference. After the switch, the combin23 channel was used. Compared to before the switch, the signal quality of the switched channel is significantly improved.

[0097] The first signals that satisfy the second condition can be broadly divided into two categories: such as Figure 10 As shown, the first signal, which does not contain motion artifacts, is as follows: Figure 9 As shown, the first signal exhibits significant motion artifact interference, with the former mostly due to the tester wearing the device too loosely. The method for distinguishing between the two is simple: the upper and lower envelopes of the first signal can be extracted using morphological filtering. By judging the amplitude of the envelope, if there is a sudden change in amplitude, the segment of the first signal is determined to contain motion artifact signals; otherwise, it is determined to be a first signal without motion artifact signals.

[0098] As a possible implementation, when the peak value and the inter-peak interval value of the first signal in the health signal satisfy a third condition, the peak value of the first signal is taken as the detection result.

[0099] Specifically, when the peak value and the inter-peak interval value of the first signal in the health signal satisfy the third condition, the peak value of the first signal is taken as the detection result, that is, when the peak value of the first signal is accurate and clear, the peak value of the first signal is taken as the detection result.

[0100] If AMP0÷th3≤N_AMP≤AMP0×th4 and PPI0÷th1≤M_PPI≤PPI0×th2 are satisfied, it is considered that the amplitude and period of the current first signal have good consistency, the signal quality is high, and the signal is a high-quality signal.

[0101] Optionally, Figure 2 shows a flow chart of determining that a first signal satisfies conditions in the health signal detection method according to an embodiment of the present application, as Figure 2 shown, the method comprises:

[0102] Step 202: Acquire a first signal;

[0103] Step 204: Determine an initialized average value of peak values and an initialized average value of inter-peak interval values;

[0104] Step 206: Detect peak values;

[0105] Step 208: Determine N peak values;

[0106] Step 210: Calculate an average value N_AMP of cumulative peak values;

[0107] Step 212: Calculate an average value M_PPI of cumulative inter-peak interval values;

[0108] Step 214: Determine the signal quality of the first signal according to conditions;

[0109] When AMP0÷th1≤N_AMP≤AMP0×th2 and PPI0÷th3≤M_PPI≤PPI0×th4, step 216 is performed;

[0110] When only PPI0÷th1≤M_PPI≤PPI0×th is satisfied, step 218 is performed;

[0111] When N_AMP>AMP0×th2 or N_AMP<AMP0÷th1, and M_PPI>PPI0×th4 or M_PPI<PPI0÷th3, step 220 is performed;

[0112] Step 216: High signal quality;

[0113] Step 218: Signal quality;

[0114] Step 220: Low signal quality;

[0115] Step 222: Update AMP0 and PPI0.

[0116] Specifically, the average values ​​of the peak and interval values ​​of the health signal can be preset, denoted as AMP0 and PPI0 respectively. Specifically, the initial average values ​​of the peak and interval values ​​can be set based on experience, for example, based on the balanced pulse wave of a healthy human body. Alternatively, the average values ​​of the peak and interval values ​​can be customized by the user, for example, by pre-extracting the user's pulse wave and customizing the average values ​​of the peak and interval values ​​based on the user's pulse wave.

[0117] The local maximum value of the first signal is recursively detected and used as the peak value. The method for determining the local maximum value is as follows: Peak i ≥Peak i+1 And Peak i ≥Peak i-1 Peak i Peak is the amplitude of the i-th signal point. i+1 Peak is the amplitude of the (i+1)th signal point. i-1 Let be the amplitude of the (i-1)th signal point. That is, if the amplitude of the i-th signal point is greater than the amplitude of the previous signal point, then the amplitude of the i-th signal point is considered to be the peak value.

[0118] For each detected peak, the amplitude Peak and the interval value of the forward difference are stored in a buffer of length N. This forms a peak buffer of length N [Peak0, Peak1, ..., Peak]. i ], and an interval value buffer of length M [PPI0, PPI1, ..., PPI] i ], among which, PPI i This represents the value of the i-th interval.

[0119] Calculate the peak buffer [Peak0, Peak1, ..., Peak] i The average peak value N_AMP is used to calculate the interval values ​​buffer[PPI0, PPI1, ..., PPI]. i The average interval value M_PPI is used to determine the signal quality of the healthy signal based on N_AMP, M_PPI, AMP0 and PPI0, thereby realizing the evaluation of the signal quality of the healthy signal.

[0120] After the buffer is full of a predetermined number of points, the magnitude and interval of the subsequently located local maximum values ​​are stored in the buffer using a first-in-first-out (FIFO) method.

[0121] For example: PPI0<--[PPI1, PPI2, ..., PPI i <--PPI i+1 , PPI0<--[Peak1, Peak2, ..., Peak i <--Peak i+1 .

[0122] After determining the signal quality of the first signal, the signal quality of the subsequent A seconds is all considered to be the same as the already determined signal quality, and the signal quality of the health signal is re-determined after the A seconds end.

[0123] After the signal quality assessment is completed, the input first signal is divided into as Figure 4 high-quality signal waveforms shown, as shown in Figure 5 and Figure 6 medium-quality signal waveforms shown, as shown in Figure 7 and Figure 8 low-quality signal waveforms shown.

[0124] Optionally, as shown in Figure 5 and Figure 6 if PPI0÷th2≤M_PPI≤PPI0×th4 is only satisfied, it is considered that the period of the current health signal has good consistency, but its amplitude is unstable and fluctuates, which belongs to a signal of the second signal quality.

[0125] As shown in Figure 7 and Figure 8 if N_AMP>AMP0×th2 or N_AMP<AMP0÷th1, M_PPI>PPI0×th4 or M_PPI<PPI0÷th3, it is considered that the current health signal has poor periodicity and large amplitude fluctuation, which belongs to a signal of the third signal quality.

[0126] As shown in Figure 4 , the method for determining high signal quality may be: if AMP0÷th9≤N_AMP≤AMP0×th10 and PPI0÷th11≤M_PPI≤PPI0×th12 are satisfied, it is considered that both the amplitude and period of the current first signal have good consistency, the signal quality is high, and it belongs to a high signal quality signal.

[0127] wherein th1, th2, th3 and th4 are empirical values. For example, the value range of th1 can be 1.5 to 2.5, the value range of th2 can be 1.5 to 2.5, th1 and th2 can be the same or different; the value range of th3 can be 1.5 to 2.5, the value range of th4 can be 1.5 to 2.5, and at least any two of th1, th2, th3 and th4 can be the same or different.

[0128] The quality of the first signal is better than the quality of the second signal, and the quality of the second signal is better than the quality of the third signal. Understandably, the quality of the first signal is high, the quality of the second signal is medium, and the quality of the third signal is low.

[0129] Specifically, Figure 3 A second flowchart of a health signal detection method according to an embodiment of this application is shown, such as... Figure 3 As shown, the method includes:

[0130] Step 302: Obtain health signals;

[0131] Step 304: Determine the signal quality of the first signal (-1 = low quality, 0 = medium quality, 1 = high quality);

[0132] Step 306: Peak detection;

[0133] Step 308: Determine whether the peak and valley are obvious; if the result is yes, proceed to step 310; if the result is no, proceed to step 312.

[0134] Step 310: Use the valley value as the detection result;

[0135] Step 312: Use the average of the peak and trough values ​​as the detection result;

[0136] Step 314: Determine whether motion artifact signals are present; if the result is yes, proceed to step 316; if the result is no, proceed to step 318.

[0137] Step 316: Reconstruct and fit the motion artifact signal; then repeat step 304.

[0138] Step 318: Determine whether the third signal of other channels is available; if the result is yes, proceed to step 320; if the result is no, proceed to step 322.

[0139] Step 320: Channel switching; then repeat step 304.

[0140] Step 322: Channel fusion; then re-execute step 304.

[0141] This application achieves real-time detection of pulse waves with low signal-to-noise ratio, capable of distinguishing different quality levels of pulse wave health signals and using different detection methods for each quality level. Specifically, it further subdivides the methods for detecting health signals of medium- and low-quality pulse waves: medium-quality signals are distinguished into signals with obvious troughs and signals with obvious peak-to-trough amplitude differences, and detection methods based on signal inversion and amplitude difference are used respectively; low-quality signals are distinguished into those with obvious motion artifact interference and those without, and detection methods based on waveform fitting reconstruction and channel switching / channel fusion are used respectively. The health signal detection method provided in this application can effectively detect health signals of different forms in real time while maintaining signal continuity.

[0142] Health signals include physiological signals such as infrared signals, electrocardiogram (ECG) signals, or cardiac impact (BCG) signals.

[0143] The health signal detection method provided in this application can be executed by a health signal detection device. This application uses an example of a health signal detection device executing the health signal detection method to illustrate the apparatus of the health signal detection method provided in this application.

[0144] like Figure 13 As shown, in some embodiments of this application, this application provides a health signal detection device 1300, including: an acquisition module 1302, used to acquire a health signal, the health signal including peak value and interval value; a first determination module 1304, used to take the valley value or mean value in the first signal as the detection result when the peak value and interval value of the first signal in the health signal meet a first condition, wherein the mean value is the average value of the peak value and the valley value of the first signal; and a second determination module 1306, used to reconstruct and fit or repair the first signal to obtain the detection result when the peak value and interval value of the first signal in the health signal meet a second condition.

[0145] In this embodiment of the application, when the electronic device detects the pulse wave, it emits infrared light, acquires the reflected health signal, and determines the peak value and duration of the health signal. When checking the first signal in the health signal, if the peak value and duration of the first signal meet the first condition, the valley value or average value of the first signal is used as the detection result, wherein the average value is the average of the peak value and valley value of the first signal.

[0146] If the peak value and interval value of the first signal meet the second condition, then the first signal is reconstructed and fitted or the waveform is repaired to obtain the detection result.

[0147] In other words, this application ensures that the detection results of the entire health signal can be obtained by processing signals in different situations, thereby improving the accuracy of pulse wave detection.

[0148] As one possible implementation, the first determining module includes: a first determining submodule, used to determine the average peak value of N consecutive peak values ​​and the average interval value of M consecutive interval values ​​in the first signal; and a second determining submodule, used to take the valley value or mean value in the first signal as the detection result when the average peak value is in a first interval and the average interval value is in a second interval.

[0149] As one possible implementation, the second determining submodule includes: a first determining unit, configured to determine that the sum of the kurtosis of V valley values ​​in the first signal is greater than the sum of the kurtosis of W peak values ​​when the average peak value is in a first interval and the average interval is in a second interval; a second determining unit, configured to determine that the valley value of the first signal is a detection result when the sum of the kurtosis of V valley values ​​is greater than the sum of the kurtosis of W peak values; and a third determining unit, configured to determine that the average value of adjacent peak values ​​and valley values ​​of the first signal is a detection result when the sum of the kurtosis of V valley values ​​is less than or equal to the sum of the kurtosis of W peak values; wherein W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1.

[0150] As one possible implementation, the second determining module includes: a third determining submodule, used to determine the average peak value of N consecutive peak values ​​and the average interval value of M consecutive interval values ​​in the first signal; and a fourth determining submodule, used to reconstruct and fit or repair the waveform of the first signal to obtain the detection result when the average peak value is in the third interval and the average interval value is in the fourth interval.

[0151] As one possible implementation, the fourth determining submodule includes: a fourth determining unit, used to determine the envelope of the first signal when the average peak value is in the third interval and the average interval value is in the fourth interval; a fifth determining unit, used to reconstruct and fit the first signal when there is an amplitude abrupt change in the envelope of the first signal; and a sixth determining unit, used to perform waveform repair on the first signal when there is no amplitude abrupt change in the envelope of the first signal.

[0152] In one possible implementation, the fifth determining unit includes: a first determining subunit, configured to determine the motion artifact signal in the first signal when there is an amplitude abrupt change in the envelope; a first acquiring subunit, configured to acquire a second signal adjacent to the motion artifact signal; a predicting subunit, configured to predict the average heart rate based on the second signal; a second determining subunit, configured to determine the number of peaks in the motion artifact signal based on the average heart rate; a reconstructing subunit, configured to reconstruct each peak in the motion artifact signal based on the second signal to reconstruct the first signal; and a third determining subunit, configured to re-determine the detection result of the reconstructed first signal.

[0153] As one possible implementation, the sixth determining unit includes: a second acquisition subunit, used to acquire a third signal from other channels when there is no amplitude abrupt change in the envelope, wherein the third signal and the first signal are signals from the same period; a repair subunit, used to repair the first signal based on the third signal; and a fourth determining subunit, used to re-determine the detection result of the repaired first signal.

[0154] The health signal detection device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be an electronic device or other devices besides electronic devices. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, private network communication terminal equipment (such as a walkie-talkie), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0155] The health signal detection device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0156] The health signal detection device provided in this application embodiment can implement the various processes implemented in the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0157] This application also provides an electronic device. Figure 14 A structural block diagram of an electronic device according to an embodiment of this application is shown, such as... Figure 14 As shown, the electronic device 1400 includes a processor 1402 and a memory 1404. The program or instructions stored in the memory 1404 and executable on the processor 1402 implement the various processes of the above method embodiments when executed by the processor 1402, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0158] It should be noted that the electronic devices in the embodiments of this application include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0159] Figure 15 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0160] The electronic device 1500 includes, but is not limited to, components such as: a radio frequency unit 1501, a network module 1502, an audio output unit 1503, an input unit 1504, a sensor 1505, a display unit 1506, a user input unit 1507, an interface unit 1508, a memory 1509, and a processor 1510. The electronic device also includes optical elements and detection elements.

[0161] Those skilled in the art will understand that the electronic device 1500 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 1510 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 15 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.

[0162] The processor 1510 is used to acquire health signals, which include peak and interval values.

[0163] The processor 1510 is used to take the valley value or mean value in the first signal as the detection result when the peak value and interval value of the first signal in the health signal meet the first condition, wherein the mean value is the average value of the peak value and the valley value of the first signal.

[0164] The processor 1510 is used to reconstruct and fit or repair the waveform of the first signal in the health signal if the peak value and interval value of the first signal in the health signal meet the second condition, so as to obtain the detection result.

[0165] In some embodiments, the processor 1510 is configured to, when the peak value and interval value of the first signal in the health signal meet a first condition, take the trough value or mean value in the first signal as the detection result, wherein the mean value is the average of the peak value and the trough value of the first signal, including:

[0166] The processor 1510 is used to determine the average peak value of N consecutive peaks in the first signal and the average interval value of M consecutive interval values;

[0167] The processor 1510 is used to take the valley or mean value in the first signal as the detection result when the average peak value is in the first interval and the average interval value is in the second interval.

[0168] In some embodiments, the processor 1510 is configured to use the valley or mean value in the first signal as the detection result when the average peak value is in a first interval and the average interval value is in a second interval, including:

[0169] The processor 1510 is used to determine that the sum of the kurtosis of V valleys in a first signal is greater than the sum of the kurtosis of W peaks when the average peak value is in a first interval and the average interval value is in a second interval.

[0170] The processor 1510 is used to determine the valley value of the first signal as a detection result when the sum of the kurtosis of the V valley values ​​is greater than the sum of the kurtosis of the W peak values.

[0171] The processor 1510 is used to determine the average value of the adjacent peaks and valleys of the first signal as the detection result when the sum of the kurtosis of V valleys is less than or equal to the sum of the kurtosis of W peaks; where W is an integer greater than or equal to 1 and V is an integer greater than or equal to 1.

[0172] In some embodiments, the processor 1510 is configured to reconstruct and fit or repair the first signal to obtain a detection result when the peak value and interval value of the first signal in the health signal meet a second condition, including:

[0173] The processor 1510 is used to determine the average peak value of N consecutive peaks in the first signal and the average interval value of M consecutive interval values;

[0174] The processor 1510 is used to reconstruct and fit or repair the waveform of the first signal to obtain the detection result when the average peak value is in the third interval and the average interval value is in the fourth interval.

[0175] In some embodiments, the processor 1510 is configured to reconstruct and fit or repair the waveform of the first signal to obtain a detection result when the average peak value is in the third interval and the average interval value is in the fourth interval, including:

[0176] The processor 1510 is used to determine the envelope of the first signal when the average peak value is in the third interval and the average interval value is in the fourth interval.

[0177] The processor 1510 is used to reconstruct and fit the first signal when there is a sudden change in amplitude in the envelope of the first signal;

[0178] The processor 1510 is used to perform waveform repair on the first signal when there is no amplitude abrupt change in the envelope of the first signal.

[0179] In some embodiments, the processor 1510 is configured to reconstruct and fit the first signal when there is a sudden change in amplitude in the envelope of the first signal, including:

[0180] The processor 1510 is used to determine the motion artifact signal in the first signal when there is a sudden change in amplitude in the envelope;

[0181] Processor 1510 is used to acquire a second signal adjacent to the motion artifact signal;

[0182] The processor 1510 is used to estimate the average heart rate based on the second signal;

[0183] The processor 1510 is used to determine the number of peaks in the motion artifact signal based on the average heart rate;

[0184] The processor 1510 is used to reconstruct each peak in the motion artifact signal based on the second signal to reconstruct the first signal;

[0185] The processor 1510 is used to redetermine the detection result of the reconstructed first signal.

[0186] In some embodiments, the processor 1510 is configured to perform waveform repair on the first signal when there is no amplitude abrupt change in the envelope of the first signal, including:

[0187] The processor 1510 is used to acquire a third signal from other channels when there is no amplitude change in the envelope. The third signal and the first signal are signals from the same period.

[0188] Processor 1510 is used to repair the first signal based on the third signal;

[0189] Processor 1510 is used to re-determine the detection result of the first signal after repair.

[0190] In this embodiment of the application, when the electronic device detects the pulse wave, it emits infrared light, acquires the reflected health signal, and determines the peak value and duration of the health signal. When checking the first signal in the health signal, if the peak value and duration of the first signal meet the first condition, the valley value or average value of the first signal is used as the detection result, wherein the average value is the average of the peak value and valley value of the first signal.

[0191] If the peak value and interval value of the first signal meet the second condition, then the first signal is reconstructed and fitted or the waveform is repaired to obtain the detection result.

[0192] In other words, this application ensures that the detection results of the entire health signal can be obtained by processing signals in different situations, thereby improving the accuracy of pulse wave detection.

[0193] It should be understood that, in this embodiment, the input unit 1504 may include a graphics processing unit (GPU) 15041 and a microphone 15042. The GPU 15041 processes image files 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 1506 may include a display panel 15061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1507 includes at least one of a touch panel 15071 and other input devices 15072. The touch panel 15071 is also called a touch screen. The touch panel 15071 may include a touch detection device and a touch controller. Other input devices 15072 may include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.

[0194] The memory 1509 can be used to store software programs and various files. The memory 1509 may primarily include a first storage area for storing programs or instructions and a second storage area for storing files. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1509 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM). The memory 1509 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0195] Processor 1510 may include one or more processing units; optionally, processor 1510 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1510.

[0196] 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 health signal detection method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0197] 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.

[0198] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described health signal detection method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0199] 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.

[0200] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the health signal detection method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0201] 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.

[0202] 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 an electronic device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0203] 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 detecting health signals, characterized in that, include: Acquire health signals, which include peak values ​​and interval values; If the peak value and the interval value of the first signal in the health signal meet a first condition, the trough value or the mean value of the first signal is taken as the detection result, wherein the mean value is the average value of the peak value and the trough value of the first signal; If the peak value and the interval value of the first signal in the health signal meet the second condition, the first signal is reconstructed and fitted or its waveform is repaired to obtain the detection result; The step of taking the trough or mean value of the first signal as the detection result when the peak value and the interval value of the first signal in the health signal meet a first condition includes: Determine the average peak value of N consecutive peak values ​​in the first signal, and the average interval value of M consecutive interval values; When the average peak value is in the first interval and the average interval value is in the second interval, it is determined that the sum of the kurtosis of the V valley values ​​in the first signal is greater than the sum of the kurtosis of the W peak values; If the sum of the kurtosis of the V valley values ​​is greater than the sum of the kurtosis of the W peak values, the valley value of the first signal is determined to be the detection result. If the sum of the kurtosis of the V valley values ​​is less than or equal to the sum of the kurtosis of the W peak values, the average of the peak values ​​and valley values ​​adjacent to the first signal is determined as the detection result. Where W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1.

2. The method for detecting health signals according to claim 1, characterized in that, The step of reconstructing and fitting or repairing the first signal to obtain a detection result when the peak value and the interval value of the first signal in the health signal meet the second condition includes: Determine the average peak value of N consecutive peak values ​​in the first signal, and the average interval value of M consecutive interval values; When the average peak value is in the third interval and the average interval value is in the fourth interval, the first signal is reconstructed and fitted or the waveform is repaired to obtain the detection result.

3. The method for detecting health signals according to claim 2, characterized in that, The step of reconstructing and fitting the first signal or repairing the waveform to obtain the detection result when the average peak value is in the third interval and the average interval value is in the fourth interval includes: When the average peak value is in the third interval and the average interval value is in the fourth interval, the envelope of the first signal is determined. When there is a sudden change in amplitude in the envelope of the first signal, the first signal is reconstructed and fitted. If there is no amplitude abrupt change in the envelope of the first signal, waveform repair is performed on the first signal.

4. The method for detecting health signals according to claim 3, characterized in that, The step of reconstructing and fitting the first signal when there is a sudden change in amplitude in the envelope of the first signal includes: In the case where the amplitude abrupt change exists in the envelope, motion artifact signals in the first signal are determined; Acquire a second signal adjacent to the motion artifact signal; Based on the second signal, estimate the average heart rate; The number of peaks in the motion artifact signal is determined based on the average heart rate; Based on the second signal, reconstruct each peak in the motion artifact signal to reconstruct the first signal; The detection result of the first signal after reconstruction is re-determined.

5. The method for detecting health signals according to claim 3, characterized in that, The step of waveform repair of the first signal when there is no amplitude abrupt change in the envelope of the first signal includes: If there is no amplitude abrupt change in the envelope, a third signal from another channel is obtained, wherein the third signal and the first signal are signals from the same time period; Repair the first signal according to the third signal; The detection result of the first signal after repair was reassessed.

6. A health signal detection device, characterized in that, include: The acquisition module is used to acquire health signals, which include peak values ​​and interval values; The first determining module is configured to, when the peak value and the interval value of the first signal in the health signal meet a first condition, take the trough value or the mean value in the first signal as the detection result, wherein the mean value is the average value of the peak value and the trough value of the first signal; The second determining module is used to reconstruct and fit or repair the waveform of the first signal in the health signal when the peak value and the interval value of the first signal in the health signal meet the second condition, so as to obtain the detection result; The first determining module includes: The first determining submodule is used to determine the average peak value of N consecutive peak values ​​in the first signal and the average interval value of M consecutive interval values. The second determining submodule is used to take the valley value or mean value in the first signal as the detection result when the average peak value is in the first interval and the average interval value is in the second interval. The second determining submodule includes: The first determining unit is configured to determine, when the average peak value is in a first interval and the average interval is in a second interval, that the sum of the kurtosis of the V valley values ​​in the first signal is greater than the sum of the kurtosis of the W peak values; The second determining unit is used to determine the valley value of the first signal as a detection result when the sum of the kurtosis of the V valley values ​​is greater than the sum of the kurtosis of the W peak values. The third determining unit is used to determine the average value of the peaks and valleys adjacent to the first signal as the detection result when the sum of the kurtosis of the V valleys is less than or equal to the sum of the kurtosis of the W peaks. Where W is an integer greater than or equal to 1, and V is an integer greater than or equal to 1.

7. The health signal detection device according to claim 6, characterized in that, The second determining module includes: The third determining submodule is used to determine the average peak value of N consecutive peak values ​​in the first signal and the average interval value of M consecutive interval values. The fourth determining submodule is used to reconstruct and fit or repair the waveform of the first signal to obtain the detection result when the average peak value is in the third interval and the average interval value is in the fourth interval.

8. The health signal detection device according to claim 7, characterized in that, The fourth determining submodule includes: The fourth determining unit is used to determine the envelope of the first signal when the average peak value is in the third interval and the average interval value is in the fourth interval. The fifth determining unit is used to reconstruct and fit the first signal when there is a sudden change in amplitude in the envelope of the first signal; The sixth determining unit is used to perform waveform repair on the first signal when there is no amplitude change in the envelope of the first signal.

9. The health signal detection device according to claim 8, characterized in that, The fifth determining unit includes: The first determining subunit is configured to determine the motion artifact signal in the first signal when the amplitude abrupt change exists in the envelope; The first acquisition subunit is used to acquire a second signal adjacent to the motion artifact signal; The estimation subunit is used to estimate the average heart rate based on the second signal; The second determining subunit is used to determine the number of peaks in the motion artifact signal based on the average heart rate; A reconstruction subunit is configured to reconstruct each peak in the motion artifact signal based on the second signal, so as to reconstruct the first signal; The third determining subunit is used to redetermine the detection result of the reconstructed first signal.

10. The health signal detection device according to claim 8, characterized in that, The sixth determining unit includes: The second acquisition subunit is used to acquire a third signal from another channel when there is no amplitude change in the envelope, wherein the third signal and the first signal are signals from the same time period. A repair subunit is configured to repair the first signal based on the third signal; The fourth determining subunit is used to re-determine the detection result of the first signal after repair.

Images