Physiological characteristic signal processing method, electronic device, chip and readable storage medium

Abstract

The embodiment of the application provides a physiological characteristic signal processing method, and relates to the field of electronic equipment. The original physiological characteristic signal collected is filtered to obtain a physiological characteristic optimization signal, a preset peak extraction algorithm is used to extract peak points in the physiological characteristic optimization signal to obtain a first peak point set, and the first peak point set is subjected to secondary peak extraction optimization processing based on the original physiological characteristic signal to obtain a second peak point set. The physiological characteristics of a target individual are analyzed based on the second peak point set and the physiological characteristic optimization signal. The embodiment of the application also provides an electronic device, a chip and a computer readable storage medium. The secondary peak extraction mechanism is introduced in the application, physiological characteristic data can be collected when a user is in an active state, the user experience is improved, and the physiological characteristics of the user are monitored in real time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal, and in particular, to a physiological characteristic signal processing method, an electronic device, a chip and a computer readable storage medium. BACKGROUND

[0002] With the increasing attention to personal health, electronic devices with physiological characteristic function measurement are increasingly popular, for example, a wearable device can measure heart rate, blood oxygen, motion, sleep and other signs by collecting photoplethysmography (PPG) of the human body. In order to ensure the accuracy of each measurement, as shown in the prior art, the signal collected by the wearable device will go through signal filtering, signal peak picking, signal quality detection, sign measurement and other processing procedures. In this process, the signal quality can be evaluated. Once it is evaluated as poor signal quality, the signal collected by the wearable device will not be used for subsequent sign measurement. Figure 1

[0003] The functions implemented based on the wearable device are becoming more and more complex, such as detecting and even predicting heart problems such as atrial fibrillation and premature beat. These functions have more stringent requirements for the signal quality collected by the wearable device. Sometimes the user needs to maintain a stationary state for a period of time to measure successfully. When the user is in an active state (for example, in a walking state), the signal quality collected by the wearable device is often poor, and the requirements for software and hardware signal processing capabilities are relatively high, resulting in that the measurement function of the wearable device cannot be normally used in most active states. Since the interference generated by the user in the active state is dynamically changing, the interference generated by different users for the same action is different, and even the interference generated by the same user for the same action can be different. The interference in the active state does not follow a fixed change rule. In order to improve the signal quality, the existing methods generally improve the hardware such as sensors or optimize the algorithm in the signal filtering and signal peak picking stages, but the interference elimination effect of these methods is not obvious. SUMMARY

[0004] Therefore, it is necessary to provide a physiological characteristic signal processing method which can overcome the above problems, collect data and perform sign measurement when the user is in an active state, and improve the user experience.

[0005] ​The first aspect of the embodiment of the present application discloses a physiological characteristic signal processing method, comprising: performing filtering processing on a physiological characteristic signal of a target individual collected to obtain a physiological characteristic optimized signal; extracting a peak point in the physiological characteristic optimized signal by using a preset peak value extraction algorithm, and constructing a first peak point set based on the extracted peak point; performing optimization processing on the first peak point set based on the physiological characteristic signal to obtain a second peak point set, wherein the optimization processing comprises one or more of new peak point processing, peak point deletion processing, and peak point updating processing; and analyzing the target individual's physiological characteristics based on the second peak point set and the physiological characteristic optimized signal.

[0006] By adopting the technical scheme, physiological characteristic data can be collected and processed when a user is in an active state, the measurement accuracy is high, the user experience is improved, and real-time monitoring of the user's physiological characteristics is realized.

[0007] In a possible implementation manner, the extracting a peak point in the physiological characteristic optimized signal by using a preset peak value extraction algorithm, and constructing a first peak point set based on the extracted peak point comprises: extracting a wave peak point in the physiological characteristic optimized signal by using the preset peak value extraction algorithm, and constructing the first peak point set based on the extracted wave peak point; or extracting a wave valley point in the physiological characteristic optimized signal by using the preset peak value extraction algorithm, and constructing the first peak point set based on the extracted wave valley point.

[0008] By adopting the technical scheme, only wave peak points or wave valley points can be used to construct a peak point set, and the signal processing operation amount is reduced.

[0009] In a possible implementation manner, the performing optimization processing on the first peak point set based on the physiological characteristic signal comprises: modeling the physiological characteristic signal to obtain a physiological characteristic waveform corresponding to the physiological characteristic signal; splitting the physiological characteristic waveform into an up-slope waveform segment and a down-slope waveform segment, and selecting the up-slope waveform segment or the down-slope waveform segment as a target waveform; marking each peak point in the first peak point set on the target waveform; dividing the target waveform into a plurality of waveform windows, and calculating an initial interference degree of each waveform window according to a preset interference degree calculation algorithm; performing optimization processing on the peak points of the waveform window, and recalculating the interference degree of the waveform window after the optimization processing by using the preset interference degree calculation algorithm until the interference degree of the waveform window reaches a minimum value, and the optimization processing on the waveform window is completed; and collecting the peak points contained in each waveform window after the optimization processing to obtain the second peak point set.

[0010] By adopting the technical scheme, the first peak point set can be optimized by adding, deleting or modifying, so that the interference degree of each waveform window is minimized, and a more accurate peak point set is finally obtained.

[0011] In a possible implementation, after the up-slope waveform or the down-slope waveform is selected as the target waveform, the method further includes: simplifying a curve segment in the target waveform into a straight line segment including only start and end points.

[0012] By adopting the technical scheme, the curve segment in the target waveform can be simplified into a straight line segment, and the calculation amount of subsequent interference degree calculation is reduced.

[0013] In a possible implementation, the preset interference degree calculation algorithm includes: calculating a slope distance between any two straight line segments marked with the peak points in the waveform window, and performing normalization processing on the calculated slope distance; calculating a length ratio between any two straight line segments marked with the peak points in the waveform window, and performing normalization processing on the calculated length ratio; calculating an absolute value of a lateral distance difference between any two straight line segments marked with the peak points in the waveform window, and performing normalization processing on the calculated absolute value of the lateral distance difference; calculating an absolute value of a longitudinal distance difference between any two straight line segments marked with the peak points in the waveform window, and performing normalization processing on the calculated absolute value of the longitudinal distance difference; and obtaining the interference degree of the waveform window based on the normalization result of the slope distance, the normalization result of the length ratio, the normalization result of the absolute value of the lateral distance difference, and the normalization result of the absolute value of the longitudinal distance difference.

[0014] By adopting the technical scheme, the interference degree of the waveform window can be calculated based on the slope distance, the length ratio, the lateral distance difference, and the longitudinal distance difference.

[0015] In a possible implementation, the normalization processing on the calculated slope distance includes: performing normalization processing on each of the calculated slope distances, and collecting the normalization result of each slope distance; or accumulating the calculated slope distances to obtain a total slope distance, and performing normalization processing on the total slope distance.

[0016] By adopting the technical scheme, the slope distance can be normalized to be converted into the interference degree.

[0017] In a possible implementation, the longer straight line segment of the two straight line segments is the denominator of the length ratio, and the normalization of the calculated length ratio comprises: performing normalization on each of the calculated length ratios and collecting the normalization results of each of the length ratios, or accumulating the calculated length ratios to obtain a total length ratio and performing normalization on the total length ratio.

[0018] By adopting the technical scheme, the length ratio can be normalized to convert the length ratio into the interference degree.

[0019] In a possible implementation, the normalization of the absolute value of the calculated transverse distance difference comprises: performing average value operation on the absolute values of the calculated transverse distance differences to obtain an average transverse distance difference, and performing normalization on the absolute value of each of the calculated transverse distance differences based on the average transverse distance difference and collecting the normalization results of the absolute values of each of the transverse distance differences.

[0020] By adopting the technical scheme, the absolute value of the transverse distance difference can be normalized to convert the absolute value of the transverse distance difference into the interference degree.

[0021] In a possible implementation, the normalization of the absolute value of the calculated longitudinal distance difference comprises: performing average value operation on the absolute values of the calculated longitudinal distance differences to obtain an average longitudinal distance difference, and performing normalization on the absolute value of each of the calculated longitudinal distance differences based on the average longitudinal distance difference and collecting the normalization results of the absolute values of each of the longitudinal distance differences.

[0022] By adopting the technical scheme, the absolute value of the longitudinal distance difference can be normalized to convert the absolute value of the longitudinal distance difference into the interference degree.

[0023] In a possible implementation, the optimization of the peak point of the waveform window comprises: finding a region with abnormal slope distance change, abnormal length ratio change, abnormal transverse distance difference change, or abnormal longitudinal distance difference change in the waveform window, and optimizing the peak point in the region.

[0024] By adopting the technical scheme, the region that may need to be optimized can be quickly located, and the optimization time is saved.

[0025] In a possible implementation, the optimization of the peak point of the waveform window comprises: when the initial interference degree of the waveform window is less than a preset interference degree, optimizing the peak point of the waveform window.

[0026] By adopting the technical scheme, optimization attempts can be made on the waveform window with room for improvement in signal quality, and optimization efficiency is improved.

[0027] In a possible implementation manner, the method further includes: when the initial interference degree of the waveform window is greater than the preset interference degree, giving up optimization processing on the peak point of the waveform window.

[0028] By adopting the technical scheme, invalid optimization attempts on the waveform window with poor signal quality can be avoided, and optimization time is saved.

[0029] In a possible implementation manner, the physiological characteristic of the target individual is obtained based on the second peak point set and the physiological characteristic optimization signal, including: performing signal quality evaluation on the second peak point set and the physiological characteristic optimization signal; and when the signal quality evaluation result is good signal quality, obtaining the physiological characteristic of the target individual based on the second peak point set and the physiological characteristic optimization signal.

[0030] By adopting the technical scheme, signal quality can be evaluated, and only the signal with good signal quality is used for subsequent vital sign measurement.

[0031] In a second aspect, an embodiment of the present application provides a computer readable storage medium, including computer instructions, when the computer instructions run on an electronic device, the electronic device executes the physiological characteristic signal processing method as described in the first aspect.

[0032] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the physiological characteristic signal processing method as described in the first aspect.

[0033] In a fourth aspect, an embodiment of the present application provides a computer program product, when the computer program product runs on a computer, the computer executes the physiological characteristic signal processing method as described in the first aspect.

[0034] In a fifth aspect, an embodiment of the present application provides a device, which has the function of realizing the electronic device behavior in the method provided in the first aspect. The function can be realized by hardware, or realized by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0035] It can be understood that the computer readable storage medium provided in the second aspect, the electronic device provided in the third aspect, the computer program product provided in the fourth aspect, and the apparatus provided in the fifth aspect all correspond to the method in the first aspect, and thus the beneficial effects achieved thereby can refer to the beneficial effects provided in the corresponding method, which will not be described here again. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 A flowchart of a physiological characteristic signal processing procedure for an existing wearable device;

[0037] Figure 2 A flowchart of a physiological characteristic signal processing method provided by an embodiment of the present application;

[0038] Figure 3 A waveform diagram of a PPG signal detected by an electronic device provided by an embodiment of the present application;

[0039] Figure 4 A waveform diagram of a PPG signal of Figure 3 A waveform diagram of a PPG signal of

[0040] Figure 5 A waveform diagram of a PPG signal of Figure 4 A waveform diagram of a PPG signal of

[0041] Figure 6 A flowchart of a physiological characteristic signal processing method provided by another embodiment of the present application;

[0042] Figure 7 A structural diagram of a possible electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0043] It should be noted that “at least one” in the present application means one or more, and “multiple” means two or more than two. “And / or” describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The terms “first”, “second”, “third”, “fourth” and the like (if any) in the specification and claims of the present application and the drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0044] For the convenience of understanding, exemplary descriptions of some concepts related to the embodiments of the present application are given for reference.

[0045] Reference is made to Figure 2As shown, the physiological characteristic signal processing method provided in the embodiment of the present application is applied to an electronic device 100, which can be a smart watch, a smart bracelet, a body sign measuring instrument, or the like, and has a physiological characteristic measuring function. In the embodiment, the physiological characteristic signal processing method can include:

[0046] 21. Filtering the collected physiological characteristic signal of the target individual to obtain a physiological characteristic optimized signal.

[0047] In some embodiments, by filtering the collected physiological characteristic signal by using a preset filtering method, some noise contained in the physiological characteristic signal can be filtered out to obtain a physiological characteristic optimized signal. The preset filtering method can select an existing body sign filtering algorithm according to actual needs, which can be a wavelet decomposition algorithm, a frequency domain analysis algorithm, a modal decomposition algorithm (such as empirical modal decomposition), an independent component analysis algorithm, an adaptive filtering algorithm, and the like.

[0048] For example, the physiological characteristic signal is a PPG signal, and the target individual is a user wearing the electronic device 100. The PPG signal of the target individual collected by the electronic device 100 can be filtered to obtain a filtered and optimized PPG signal.

[0049] 22. Extracting a peak point in the physiological characteristic optimized signal, and constructing a first peak point set based on the extracted peak point.

[0050] In some embodiments, a preset peak extraction algorithm can also be used to extract the peak point in the physiological characteristic optimized signal. The peak point can be a peak point or a trough point, and the extracted peak point can be placed in a set to obtain a first peak point set. That is, a preset peak extraction algorithm can be used to extract the peak point in the physiological characteristic optimized signal, and a first peak point set can be constructed based on the extracted peak point, or a preset peak extraction algorithm can be used to extract the trough point in the physiological characteristic optimized signal, and a first peak point set can be constructed based on the extracted trough point. The following takes the peak point as an example to illustrate.

[0051] The preset peak extraction algorithm can also select an existing body sign peak extraction algorithm according to actual needs, which can be a Bayesian decision classification algorithm, a machine learning classification algorithm, a heuristic algorithm, and the like.

[0052] 23. Optimizing the first peak point set based on the physiological characteristic signal to obtain a second peak point set.

[0053] In some embodiments, the optimization process may include a combination of one or more of the following: adding a peak point, deleting a peak point, and updating a peak point. Adding a peak point may refer to adding a new peak point to the first set of peak points; deleting a peak point may refer to deleting a peak point from the first set of peak points; and updating a peak point may refer to deleting a peak point from the first set of peak points while simultaneously adding a new peak point to the first set of peak points.

[0054] In some embodiments, the PPG signal is used as an example to illustrate the concept. The PPG signal acquired by the electronic device 100 can be modeled to convert the PPG signal into... Figure 3 The physiological characteristic waveform S1 shown (the horizontal axis of the physiological characteristic waveform S1 can be time-based, and the vertical axis can be the light intensity detected by the optical heart rate sensor of the electronic device 100) is then divided into an uphill waveform segment S11 and a downhill waveform segment S12. Either waveform segment can be arbitrarily selected as the target waveform for subsequent analysis. The following example illustrates the selection of the downhill waveform segment S12 as the target waveform.

[0055] choose Figure 3 The downslope waveform segment S12 in the physiological characteristic waveform S1 shown is obtained as follows: Figure 4 The waveform diagram is shown. Furthermore, each peak in the first peak set can be... Figure 4 The target waveform is marked. Since the target waveform contains many waveform segments, in order to speed up signal analysis, the target waveform can be divided into multiple waveform windows, and then the interference degree of each waveform window can be calculated using a preset interference degree calculation algorithm.

[0056] In some embodiments, the target waveform can be divided into multiple waveform windows based on time, with each waveform window containing the same time scale, such as each waveform window containing a 1-second downhill waveform segment. Alternatively, the target waveform can be divided into multiple waveform windows based on the number of waveform segments, with each waveform window containing the same number of waveform segments, such as each waveform window containing 30 downhill waveform segments.

[0057] In some embodiments, to reduce the computational burden of interference, the curve segments in each waveform window can be simplified to straight line segments including only the beginning and end points before calculating the interference. For example... Figure 5 As shown, it is about to Figure 4The curved segment is simplified to a straight segment including only the start and end points. The calculation of the interference degree of the waveform window using the preset interference degree calculation algorithm can include: a. calculating the slope distance (i.e., the included angle between any two straight segments marked with the peak points) between any two straight segments marked with the peak points in the waveform window, and normalizing the calculated slope distance; b. calculating the length ratio (the length value of the longer straight segment is the denominator of the length ratio) between any two straight segments marked with the peak points in the waveform window, and normalizing the calculated length ratio; c. calculating the absolute value of the lateral distance difference between any two straight segments marked with the peak points in the waveform window, and normalizing the calculated absolute value of the lateral distance difference; d. calculating the absolute value of the longitudinal distance difference between any two straight segments marked with the peak points in the waveform window, and normalizing the calculated absolute value of the longitudinal distance difference; e. calculating the interference degree of the waveform window based on the normalized results of the slope distance, the normalized results of the length ratio, the normalized results of the absolute value of the lateral distance difference, and the normalized results of the absolute value of the longitudinal distance difference.

[0058] In some embodiments, the greater the value of the slope distance, the greater the result obtained by normalization processing. The normalization processing of the calculated slope distance can mean that the calculated multiple slope distances are normalized respectively (the closer the value of the slope distance to 0°, the smaller the result obtained by normalization processing, and the closer the value of the slope distance to 90°, the greater the result obtained by normalization processing), the corresponding interference degrees are converted, and the normalized results are summarized, or the calculated multiple slope distances are accumulated to obtain a total slope distance, and the total slope distance is normalized to convert the corresponding interference degrees.

[0059] In some embodiments, the smaller the value of the length ratio, the greater the result obtained by normalization processing. The normalization processing of the calculated length ratio can mean that the calculated multiple length ratios are normalized respectively (the closer the value of the length ratio to 0, the greater the result obtained by normalization processing, and the closer the value of the length ratio to 1, the smaller the result obtained by normalization processing), the corresponding interference degrees are converted, and the normalized results are summarized, or the calculated multiple slope distances are accumulated to obtain a total slope distance, and the total slope distance is normalized to convert the corresponding interference degrees.

[0060] In some embodiments, the normalization of the absolute value of the calculated transverse distance difference can include: first averaging the absolute values of the calculated multiple transverse distance differences to obtain an average transverse distance difference of the waveform window, and then respectively normalizing the absolute values of the calculated multiple transverse distance differences (the closer the absolute value of the transverse distance difference to the average transverse distance difference, the smaller the result obtained by normalization, and the farther the absolute value of the transverse distance difference from the average transverse distance difference, the larger the result obtained by normalization), to convert the corresponding interference degree, and then to summarize the normalized results.

[0061] In some embodiments, the normalization of the absolute value of the calculated longitudinal distance difference can include: first averaging the absolute values of the calculated multiple longitudinal distance differences to obtain an average longitudinal distance difference of the waveform window, and then respectively normalizing the absolute values of the calculated multiple longitudinal distance differences (the closer the absolute value of the longitudinal distance difference to the average longitudinal distance difference, the smaller the result obtained by normalization, and the farther the absolute value of the longitudinal distance difference from the average longitudinal distance difference, the larger the result obtained by normalization), to convert the corresponding interference degree, and then to summarize the normalized results.

[0062] By dividing the interference degree of the waveform window into four dimensions of slope distance, length ratio, transverse distance difference, and longitudinal distance difference for calculation and normalization in the process of calculating the interference degree of the waveform window, the interference degree of each dimension is converted, and the normalized results of the slope distance, the length ratio, the absolute value of the transverse distance difference, and the absolute value of the longitudinal distance difference are added up, so as to obtain the interference degree of the waveform window.

[0063] In some embodiments, when the initial interference degree of each waveform window is calculated, it can be judged whether the initial interference degree is greater than a preset interference degree to determine whether it is necessary to adjust the peak points in the waveform window. When the initial interference degree of the waveform window is greater than the preset interference degree, it indicates that the quality of the peak points in the waveform window is poor, and even through subsequent optimization processing, it cannot pass the existing signal quality verification. When the initial interference degree of the waveform window is less than the preset interference degree, it indicates that the quality of the peak points in the waveform window has adjustable space, and through the subsequent optimization processing of the present application, it can pass the existing signal quality check. The size of the preset interference degree can be set according to actual needs.

[0064] In some embodiments, when the peak points of the waveform window are optimized, the preset interference degree calculation algorithm can be used to recalculate the interference degree of the optimized waveform window. By continuously adjusting and repeatedly calculating the interference degree, the optimization of the waveform window is stopped until the interference degree of the waveform window reaches the minimum value. After each waveform window is optimized, the peak points currently included in each optimized waveform window can be summarized to obtain a second peak point set.

[0065] As shown in Figure 5 , the optimization of the peak points of the waveform window can be adding a peak point to a straight line segment (which has not previously marked a peak point), deleting a peak point marked by a straight line segment, or deleting a peak point marked by a straight line segment and adding a peak point to another straight line segment (which has not previously marked a peak point).

[0066] In some embodiments, since the human body characteristics generally follow the principle of approximate linear change, they generally do not change suddenly and greatly. For example, the slope distance, length ratio, lateral distance difference, and longitudinal distance difference of several adjacent straight line segments marked with peak points are analyzed. If it is found that a value suddenly changes greatly, the peak points in this region need to be optimized, the peak points are added and / or deleted, and the interference degree is recalculated to minimize the interference degree of the waveform window and save optimization time.

[0067] In some embodiments, the number of optimization attempts can also be limited. After a preset number of optimization attempts are completed, the waveform state with the minimum interference degree is selected.

[0068] In some embodiments, a polling adjustment method can be used to add and / or delete peak points of each straight line segment in the waveform window, and the interference degree of the waveform window is recalculated until the interference degree of the waveform window reaches the minimum value. Compared with the above-described optimization method, the processing time is relatively long.

[0069] 24. The physiological characteristics of the target individual are obtained based on the second peak point set and the physiological characteristic optimization signal.

[0070] In some embodiments, when the second peak point set is obtained, the existing physical measurement analysis method (such as the signal quality detection and physical measurement steps of Figure 1 ) can be used to analyze the second peak point set and the physiological characteristic optimization signal to obtain the physiological characteristics of the target individual. For example, the physiological characteristics are heart rate, blood pressure, etc.

[0071] For example, for heart rate measurement, the heart rate value is converted based on the number of peak points within a certain time. For example, if the analysis obtains the number of peak points of the 5s physiological characteristic optimization signal as N, then the heart rate is N*12.

[0072] In some embodiments, the second peak point set and the physiological characteristic optimization signal can be subjected to signal quality evaluation. If the evaluation result is poor signal quality, the signal will not be used for subsequent vital sign measurement, and the signal processing will be directly ended. If the evaluation result is good signal quality, the signal will be used for vital sign measurement. The existing vital sign analysis method can be used to analyze the second peak point set and the physiological characteristic optimization signal to obtain the physiological characteristics of the target individual.

[0073] The above physiological characteristic signal processing method first obtains an initial peak point set using existing filtering and peak extraction technology, and then optimizes the initial peak point set using a secondary peak extraction mechanism to obtain a final peak point set. This can collect data when the user is in an active state without deliberately keeping the user in a stationary state for a long time, increase the application scenarios of vital sign measurement, improve the user experience, and truly realize real-time monitoring of the physiological characteristics of the user. This can improve the application scenarios of wearable devices.

[0074] Referring to Figure 6 An embodiment of the present application provides a flowchart of a physiological characteristic measurement process of an electronic device 100 on a target individual.

[0075] 61. Wearable device signal acquisition. The target individual wears the electronic device 100, and the electronic device 100 can collect the original physiological characteristic signal.

[0076] 62. Signal filtering processing. The existing filtering algorithm can be used to filter the original physiological characteristic signal to obtain a physiological characteristic optimization signal.

[0077] 63. Signal peak extraction processing. The existing peak extraction algorithm can be used to extract the peak points of the physiological characteristic optimization signal obtained after filtering to obtain a first peak point set. The peak extraction method can be to extract only the peak points or only the trough points.

[0078] 64. Secondary peak extraction processing. The original physiological characteristic signal is modeled, and the waveform obtained by modeling is divided into an uphill waveform segment and a downhill waveform segment. Then, one of the waveform segments is selected as a target waveform for subsequent analysis. The peak points contained in the first peak point set are marked on the target waveform, and the interference degree is calculated. The peak value points are added, deleted, or updated to the target waveform to minimize the interference degree. Then, the second peak point set is constructed based on the peak points in the state of minimum interference degree.

[0079] 65、Signal quality detection. The second peak set and the physiological feature optimized signal are evaluated by using the existing signal quality detection method. If the evaluation result is poor signal quality, the signal will not be used for subsequent physical sign measurement, and the signal processing is directly ended.

[0080] 66、Physical sign measurement. When the second peak set and the physiological feature optimized signal are evaluated by using the existing signal quality detection method, if the evaluation result is good signal quality, the signal will be used for physical sign measurement. The existing physical sign analysis method can be used to analyze the second peak set and the physiological feature optimized signal to obtain the physiological features of the target individual.

[0081] The following compares the experimental data obtained by using the existing physiological feature signal processing method (as shown in the method) Figure 1 with the experimental data obtained by using the physiological feature signal processing method of the present application Figure 6 .

[0082] In order to ensure the accuracy of atrial fibrillation detection, the signal quality screening of the prior art is relatively strict. Many signals collected in an active state cannot pass the signal quality verification. Therefore, the atrial fibrillation detection function generally requires the user to remain stationary for about 1 minute before performing atrial fibrillation detection.

[0083] Experiment 1:

[0084] This experiment no longer requires the collected user to remain stationary. Therefore, some signal data of the user in an active state (such as a walking state) can be collected. Sample 1: 9899 PPG signals without atrial fibrillation attack are collected in a stationary and active state, each signal lasting about 1 minute. Sample 2: 6740 PPG signals with atrial fibrillation attack are collected in a stationary and active state, each signal lasting about 1 minute.

[0085] The existing physiological feature signal processing method is used to process sample 1 and sample 2. Among the 9899 PPG signals without atrial fibrillation collected, 6891 signals pass the existing signal quality check, which can be considered to be mostly collected in a stationary state. The remaining 3008 signals do not pass the existing signal quality check, which can be considered to be mostly collected in an active state. Among the 6740 PPG signals without atrial fibrillation collected, 3031 signals pass the existing signal quality check, which can be considered to be mostly collected in a stationary state. The remaining 3709 signals do not pass the existing signal quality check, which can be considered to be mostly collected in an active state. That is, about 6717 (3008+3709) PPG signal data cannot pass the signal quality verification using the existing physiological feature signal processing method. Among the data that pass the signal quality verification, the accuracy of atrial fibrillation measurement is above 95%.

[0086] While using the physiological characteristic signal processing method shown in the present application Figure 6 When the physiological characteristic signal processing method shown in the present application

[0087] Experiment Two:

[0088] The user is warned of atrial fibrillation in a vehicle (driving or riding) state. The current atrial fibrillation warning function generally cannot be used when the user is in a vehicle state. In this experiment, PPG signal data in a vehicle scene is collected. In order to ensure patient safety, no vehicle data of atrial fibrillation patients is collected, so the actual samples are all negative samples, testing the atrial fibrillation false alarm rate (jolts in a vehicle state will cause signal fluctuations, making it easy to produce false positives in the results measured by current electronic devices). Sample 1: 343 PPGs collected from the driver's left hand in a vehicle scene; sample 2: 343 PPGs collected from the driver's right hand in a vehicle scene; sample 3: 49 PPGs collected from the driver in a stationary scene. That is, a total of 735 (343+343+49) PPGs are collected, each signal lasting about 1 minute.

[0089] Of the 735 PPG signals collected without atrial fibrillation, most can be considered to have been collected in an active state. When the existing physiological characteristic signal processing method is used to process these PPG signals, 698 PPG signals cannot pass the signal quality verification, and 37 PPG signals pass the signal quality verification. Analysis of the 37 PPG signals (37 / 735=80%) shows that no false positives occurred in the atrial fibrillation warning module.

[0090] When the physiological characteristic signal processing method shown in the present application Figure 6 588 PPG signals (588 / 735≈5%) pass the signal quality verification, the number of PPG signals that cannot pass the signal quality verification is reduced from 698 to 147, and the recall rate of PPG signals collected in an active state is increased by more than a dozen times (signal quality pass rate from 5% to 80%), and analysis of the 588 PPG signals shows that no false alarms occurred in the atrial fibrillation warning module.

[0091] Reference Figure 7A hardware structure schematic diagram of the electronic device 100 is provided for the embodiments of the present application. As shown in Figure 7 The electronic device 100 can include a processor 1001, a memory 1002, and a communication bus 1003. The memory 1002 is configured to store one or more computer programs 1004. The one or more computer programs 1004 are configured to be executed by the processor 1001. The one or more computer programs 1004 include instructions that can be used to implement the above-mentioned physiological characteristic signal processing method in the electronic device 100.

[0092] It can be understood that the structure illustrated in the embodiments does not constitute a specific limitation on the electronic device 100. In other embodiments, the electronic device 100 can include more or fewer components than those illustrated, or combine certain components, or split certain components, or different component arrangements.

[0093] The processor 1001 can include one or more processing units, for example: the processor 1001 can include an application processor (AP), a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a DSP, a CPU, a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units can be independent devices, or can be integrated in one or more processors.

[0094] The processor 1001 can also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 1001 is a cache memory. The memory can save instructions or data that the processor 1001 has just used or repeatedly uses. If the processor 1001 needs to use the instructions or data again, it can directly call from the memory. This avoids repeated access and reduces the waiting time of the processor 1001, thereby improving the efficiency of the system.

[0095] In some embodiments, the processor 1001 can include one or more interfaces. The interfaces can include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.

[0096] In some embodiments, the memory 1002 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0097] The embodiments also provide a computer storage medium, which stores computer instructions, and when the computer instructions are run on an electronic device, the electronic device executes the related method steps to implement the physiological characteristic signal processing method in the above embodiments.

[0098] The embodiments also provide a computer program product, which, when run on a computer, causes the computer to execute the related steps to implement the physiological characteristic signal processing method in the above embodiments.

[0099] In addition, the embodiments of the present application also provide a device, which can be a chip, a component or a module, and the device can include a processor and a memory connected to each other; wherein the memory is used to store computer execution instructions, and when the device is running, the processor can execute the computer execution instructions stored in the memory to enable the chip to execute the physiological characteristic signal processing method in the above method embodiments.

[0100] Among them, the first electronic device, the computer storage medium, the computer program product or the chip provided by the embodiments are used to execute the corresponding method provided above, so the beneficial effects they can achieve can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0101] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0102] In several embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the module or unit is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0103] The unit described as a separate component can or can not be physically separated, and the component shown as a unit can be one physical unit or a plurality of physical units, that is, can be located in one place, or can be distributed to a plurality of different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0104] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0105] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such understanding, the technical scheme of the embodiment of the present application essentially or the part that contributes to the prior art or all or part of the technical scheme can be embodied in the form of a software product, which is stored in a storage medium, includes a plurality of instructions to make a device (which can be a single chip microcomputer, a chip, etc.) or a processor execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various program code storage media.

[0106] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this, any change or replacement within the technical scope disclosed by the present application should be covered in the protection scope of the present application.

Claims

1. A physiological feature signal processing method, characterized by, The method comprises the following steps: filtering a physiological characteristic signal of a target individual to obtain an optimized physiological characteristic signal; extracting peak points in the optimized physiological characteristic signal by using a preset peak extraction algorithm, and constructing a first peak point set based on the extracted peak points; modeling the physiological characteristic signal to obtain a physiological characteristic waveform corresponding to the physiological characteristic signal; splitting the physiological characteristic waveform into an up-slope waveform segment and a down-slope waveform segment, and selecting the up-slope waveform segment or the down-slope waveform segment as a target waveform; marking each peak point in the first peak point set on the target waveform; dividing the target waveform into a plurality of waveform windows, and calculating an initial interference degree of each waveform window according to a preset interference degree calculation algorithm; when the initial interference degree of the waveform window is less than a preset interference degree, optimizing the peak points of the waveform window, and recalculating the interference degree of the waveform window after the optimization by using the preset interference degree calculation algorithm until the interference degree of the waveform window reaches a minimum value, thereby completing the optimization of the waveform window; summarizing the peak points contained in each waveform window after the optimization to obtain a second peak point set, wherein the optimization includes one or more of adding a peak point, deleting a peak point, and updating a peak point; and analyzing the target individual's physiological characteristics based on the second peak point set and the optimized physiological characteristic signal.

2. The physiological characteristic signal processing method of claim 1, wherein, The method of extracting peak points in the optimized physiological characteristic signal by using a preset peak extraction algorithm, and constructing a first peak point set based on the extracted peak points comprises: extracting wave peak points in the optimized physiological characteristic signal by using the preset peak extraction algorithm, and constructing the first peak point set based on the extracted wave peak points; or extracting wave valley points in the optimized physiological characteristic signal by using the preset peak extraction algorithm, and constructing the first peak point set based on the extracted wave valley points.

3. The physiological characteristic signal processing method of claim 1 or 2, wherein, After selecting the up-slope waveform or the down-slope waveform as the target waveform, the method further comprises: simplifying a curve segment in the target waveform into a straight line segment including only the start and end points.

4. The physiological characteristic signal processing method of claim 3, wherein, The preset interference degree calculation algorithm comprises: calculating the slope distance between any two straight line segments marked with the peak points in the waveform window, and normalizing the calculated slope distance; calculating the length ratio between any two straight line segments marked with the peak points in the waveform window, and normalizing the calculated length ratio; calculating the absolute value of the lateral distance difference between any two straight line segments marked with the peak points in the waveform window, and normalizing the calculated absolute value of the lateral distance difference; calculating the absolute value of the longitudinal distance difference between any two straight line segments marked with the peak points in the waveform window, and normalizing the calculated absolute value of the longitudinal distance difference; and obtaining the interference degree of the waveform window based on the normalized results of the slope distance, the length ratio, the absolute value of the lateral distance difference, and the absolute value of the longitudinal distance difference.

5. The physiological characteristic signal processing method of claim 4, wherein, The normalization processing on the calculated slope distance comprises: respectively normalizing a plurality of calculated slope distances, and collecting the normalization results of each of the slope distances; or accumulating a plurality of calculated slope distances to obtain a total slope distance, and normalizing the total slope distance.

6. The physiological characteristic signal processing method of claim 4, wherein, The longer straight line segment of the two straight line segments is the denominator of the length ratio, and the normalization processing on the calculated length ratio comprises: respectively normalizing a plurality of calculated length ratios, and collecting the normalization results of each of the length ratios; or accumulating a plurality of calculated length ratios to obtain a total length ratio, and normalizing the total length ratio.

7. The physiological characteristic signal processing method of claim 4, wherein, The normalization processing on the absolute value of the calculated transverse distance difference comprises: performing an average value operation on the absolute values of a plurality of calculated transverse distance differences to obtain an average transverse distance difference; and respectively normalizing the absolute value of each of the calculated transverse distance differences based on the average transverse distance difference, and collecting the normalization results of the absolute value of each of the transverse distance differences.

8. The physiological characteristic signal processing method of claim 4, wherein, The normalization processing on the absolute value of the calculated longitudinal distance difference comprises: performing an average value operation on the absolute values of a plurality of calculated longitudinal distance differences to obtain an average longitudinal distance difference; and respectively normalizing the absolute value of each of the calculated longitudinal distance differences based on the average longitudinal distance difference, and collecting the normalization results of the absolute value of each of the longitudinal distance differences.

9. The physiological characteristic signal processing method of claim 4, wherein, The optimization processing on the peak points of the waveform window comprises: finding a region with abnormal slope distance change, abnormal length ratio change, abnormal transverse distance difference change, or abnormal longitudinal distance difference change in the waveform window, and optimizing the peak points in the region.

10. The physiological characteristic signal processing method according to any one of claims 1, 2, 4 to 9, characterized in that, The method further comprises: when the initial interference degree of the waveform window is greater than the preset interference degree, giving up the optimization processing on the peak points of the waveform window.

11. The physiologic feature signal processing method according to any one of claims 1, 2, 4 to 9, characterized by, The analysis of the physiological characteristics of the target individual based on the second peak point set and the physiological characteristic optimization signal comprises: performing signal quality evaluation on the second peak point set and the physiological characteristic optimization signal; and when the signal quality evaluation result is that the signal quality is good, analyzing the physiological characteristics of the target individual based on the second peak point set and the physiological characteristic optimization signal.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, which, when executed on an electronic device, cause the electronic device to perform the physiological characteristic signal processing method of any one of claims 1 to 11.

13. An electronic device, comprising: The electronic device comprises a processor and a memory, the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the physiological characteristic signal processing method of any one of claims 1 to 11.

14. A chip coupled with a memory in an electronic device, the chip comprising: The chip is used to control the electronic device to execute the physiological characteristic signal processing method of any one of claims 1 to 11.

Images