Method, device, electronic device, and storage medium for quality assessment of physical sign signals

Abstract

The present invention relates to the technical field of signal analysis, and provides a method, device, electronic device, and storage medium for quality assessment of physiological sign signals. The method for quality assessment of physiological sign signals includes: intercepting the physiological sign signals of the current time window from the self-collected physiological sign signal stream based on a time window; performing point-by-point forward difference calculation on the physiological sign signals of the current time window according to sampling points to obtain the current set of forward difference values; performing histogram statistics on the current set of difference values, and calculating the standard deviation of the frequency distribution of each group of the histogram; and obtaining the quality assessment result of the physiological sign signals of the current time window according to the standard deviation and the quality threshold. The signal quality assessment of the present invention does not depend on feature extraction and does not require the use of a machine learning training algorithm model. Instead, through forward difference calculation and histogram statistics, the quality assessment result can be obtained conveniently and accurately. The overall operation complexity is low, it is applicable to wearable devices, and the algorithm delay is small, enabling real-time quality assessment of physiological sign signals.

Description

Technical Field

[0001] The present invention relates to the technical field of signal analysis, and more particularly, to a method, apparatus, electronic device, and storage medium for evaluating the quality of physiological sign signals. Background Art

[0002] With the development of social economy and the change of national lifestyle, especially the acceleration of population aging and urbanization, the unhealthy lifestyle of residents has become increasingly prominent. The impact of cardiovascular disease risk factors on residents' health has become more significant, and the incidence of cardiovascular disease has been continuously increasing.

[0003] Collecting physiological sign data such as electrocardiogram, blood pressure, and blood oxygen is helpful for observing the condition of cardiovascular patients and further diagnosis and treatment. With the development of remote medical science and technology, the technology of continuously monitoring physiological sign signals through wearable devices has become more and more common. However, the physiological sign signals collected by wearable devices are easily affected by baseline drift, electromyogram interference, electrode contact noise, motion artifacts, etc., which will cause inaccurate monitoring results of physiological sign data such as electrocardiogram, blood pressure, and blood oxygen, and further affect the evaluation of the condition of cardiovascular patients.

[0004] Therefore, it is particularly important to evaluate the quality of physiological sign signals collected by wearable devices.

[0005] Currently, for signal quality evaluation, a neural network model is usually used. First, features are extracted from physiological sign signals, and then the quality score is obtained by inputting them into the neural network model. The following problems generally exist:

[0006] First, it is necessary to extract features from the originally collected physiological sign signals, and then evaluate the signal quality based on the extracted features. In the case of interference in physiological sign signals, it is difficult to extract accurate features, which will further affect the accuracy of signal quality evaluation;

[0007] Second, the neural network model belongs to a supervised machine learning model and needs to be trained based on a labeled training set, which is prone to overfitting problems, resulting in poor actual application effects;

[0008] Third, the neural network model has a high operation complexity and a large amount of calculation, and cannot be used for real-time evaluation of signal quality, nor is it suitable for running on wearable devices.

[0009] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present invention, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0010] In view of this, the present invention provides a method, apparatus, electronic device, and storage medium for evaluating the quality of physiological sign signals, which can overcome the problems of existing methods.

[0011] According to one aspect of the present invention, there is provided a method for evaluating the quality of a physiological sign signal, including: intercepting the physiological sign signal of the current time window from the collected physiological sign signal stream based on a time window; performing point-by-point forward difference calculation on the physiological sign signal of the current time window according to sampling points to obtain the current set of forward difference values; performing histogram statistics on the current set of difference values and calculating the standard deviation of the frequency distribution of each group of the histogram; and obtaining the quality evaluation result of the physiological sign signal of the current time window according to the standard deviation and a quality threshold.

[0012] In some embodiments, before intercepting the physiological sign signal of the current time window from the collected physiological sign signal stream based on the time window, it further includes: performing noise reduction processing on the collected physiological sign signal stream including power frequency filtering and band-pass filtering.

[0013] In some embodiments, after performing point-by-point forward difference calculation on the physiological sign signal of the current time window according to sampling points, it further includes: taking the absolute value of each forward difference value.

[0014] In some embodiments, the horizontal axis of the histogram is the distribution of the current set of forward difference values, and the vertical axis of the histogram is the frequency.

[0015] In some embodiments, after calculating the standard deviation of the frequency distribution of each group of the histogram, it further includes: performing normalization processing on the standard deviation by dividing it by the average value of the histogram.

[0016] In some embodiments, the quality threshold at least includes a target quality threshold for distinguishing whether a physiological sign signal is valid; obtaining the quality evaluation result of the physiological sign signal of the current time window includes: when the standard deviation is greater than or equal to the target quality threshold, obtaining a quality evaluation result that the physiological sign signal of the current time window is valid; and when the standard deviation is less than the target quality threshold, obtaining a quality evaluation result that the physiological sign signal of the current time window is invalid.

[0017] In some embodiments, the physiological sign signal is collected by a wearable device; after obtaining the quality evaluation result of the physiological sign signal of the current time window, it further includes: when the physiological sign signal of the current time window is valid, transmitting the physiological sign signal of the current time window to a physiological sign monitoring module, where the physiological sign monitoring module is deployed in or independent of the wearable device; and when the quality evaluation results of the physiological sign signals in a continuous preset period are all invalid, determining the invalid factors of the physiological sign signals in the continuous preset period and sending an adjustment reminder corresponding to the invalid factors through the wearable device.

[0018] In some embodiments, the invalid factors include device - type invalid factors and non - device - type invalid factors. Sending an adjustment reminder corresponding to the invalid factor through the wearable device includes: when the invalid factor is a device - type invalid factor, sending an adjustment reminder for device restart through the wearable device; when the invalid factor is a non - device - type invalid factor, sending an adjustment reminder for device position adjustment through the wearable device.

[0019] In some embodiments, after sending the adjustment reminder corresponding to the invalid factor through the wearable device, it further includes: if the quality assessment results of the physiological sign signals in the next consecutive preset time period are all invalid, sending an alarm notification to the remote monitoring device of the wearable device.

[0020] According to another aspect of the present invention, there is provided a quality assessment device for physiological sign signals, including: a time - window module for intercepting the physiological sign signals of the current time window from the collected physiological sign signal stream based on the time window; a differential - calculation module for performing point - by - point forward - difference calculation on the physiological sign signals of the current time window according to the sampling points to obtain the current - group forward - difference values; a histogram - statistics module for performing histogram statistics on the current - group difference values and calculating the standard deviation of the frequency distribution of each group of the histogram; a threshold - comparison module for obtaining the quality assessment result of the physiological sign signals of the current time window according to the standard deviation and the quality threshold.

[0021] According to yet another aspect of the present invention, there is provided an electronic device, including: a processor; a memory in which executable instructions are stored; wherein, when the executable instructions are executed by the processor, the quality assessment method for physiological sign signals as described in any of the above embodiments is implemented.

[0022] According to still another aspect of the present invention, there is provided a computer - readable storage medium for storing a program, and when the program is executed by a processor, the quality assessment method for physiological sign signals as described in any of the above embodiments is implemented.

[0023] The beneficial effects of the present invention compared with the prior art at least include:

[0024] The present invention does not rely on feature extraction, but directly performs quality assessment based on the originally collected physiological sign signals, and the accuracy of the quality assessment is not affected by the accuracy of feature extraction;

[0025] The present invention does not adopt an algorithm model trained by supervised machine learning, there is no over - fitting phenomenon, the actual application effect is good, and there is no obvious difference from the prior data;

[0026] The present invention has a low operation complexity and is suitable for running on wearable devices;

[0027] The algorithm of the present invention has a small time delay, and the time window can be set as needed, with the minimum being set to 1 s, enabling real-time evaluation of the signal quality.

[0028] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present invention, and together with the specification are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0030] Figure 1 A schematic diagram showing the steps of a method for evaluating the quality of a physiological sign signal in an embodiment of the present invention;

[0031] Figure 2 A specific flowchart showing the method for evaluating the quality of a physiological sign signal in an embodiment of the present invention;

[0032] Figure 3 A graph showing the waveform of an electrocardiogram signal without interference and the corresponding signal quality evaluation value in an embodiment of the present invention;

[0033] Figure 4 A graph showing the waveform of an electrocardiogram signal with interference but with visible QRS waves and the corresponding signal quality evaluation value in an embodiment of the present invention;

[0034] Figure 5 A graph showing the waveform of an electrocardiogram signal with interference coverage and no visible QRS waves and the corresponding signal quality evaluation value in an embodiment of the present invention;

[0035] Figure 6 A schematic diagram showing the modules of a device for evaluating the quality of a physiological sign signal in an embodiment of the present invention;

[0036] Figure 7 A schematic diagram showing the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the present invention thorough and complete, and to fully convey the concept of the example embodiments to those skilled in the art.

[0038] The accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0039] In addition, the processes shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all steps. For example, some steps can be decomposed, some steps can be combined or partially combined, and the actual execution order may be changed according to the actual situation. The terms "first", "second" and similar terms used in the specific description do not denote any order, quantity or importance, but are only used to distinguish different components. It should be noted that, without conflict, the embodiments of the present invention and the features in different embodiments can be combined with each other.

[0040] Figure 1 Illustrate the main steps of the method for evaluating the quality of a vital sign signal in an embodiment. Refer to Figure 1 As shown, the method for evaluating the quality of the vital sign signal in this embodiment includes:

[0041] Step S110, intercept the vital sign signal of the current time window from the acquired vital sign signal stream based on a time window.

[0042] The window width of the time window can be set as needed. For example, it can be set to 1 - 10 seconds. The window width affects the real-time performance of signal quality evaluation. The smaller the window width, the higher the real-time performance of signal quality evaluation. In this embodiment, for the sake of balancing real-time performance and efficiency, the window width of the time window is set to 2s.

[0043] The time window is used to divide the vital sign signal stream. Each time, the vital sign signal of the current time window is intercepted for analysis and processing; the analysis and processing of the vital sign signals in different time windows do not need to be carried out in a streaming manner. In the case where the vital sign signal stream is continuously output, each time a vital sign signal of a time window is intercepted, it can enter the analysis and processing process.

[0044] In this embodiment, the vital sign signal stream is continuously acquired and output by a wearable device. Of course, the quality evaluation method of the present invention is not limited to being applied to wearable devices, but can evaluate the quality of vital sign signals acquired in any suitable manner. In addition, the vital sign signals referred to in this embodiment specifically refer to quasi-periodic signals of vital signs, including but not limited to electrocardiogram, blood pressure and blood oxygen signals. In other embodiments, the vital sign signals can also refer to any other signals that can characterize vital signs.

[0045] In one embodiment, before step S110, that is, before dividing the vital sign signal stream based on a time window, it may further include: performing noise reduction processing on the collected vital sign signal stream including power frequency filtering and band-pass filtering. Power frequency filtering can filter out power frequency interference in the vital sign signal, and band-pass filtering can filter out clutter and harmonics in the vital sign signal in the range of 0.5 - 45 Hz. Through power frequency filtering and band-pass filtering, noise reduction processing of the vital sign signal can be achieved.

[0046] Step S120: Perform point-by-point forward difference calculation on the vital sign signals in the current time window according to sampling points to obtain the current group of forward difference values.

[0047] Point-by-point forward difference calculation refers to performing forward difference calculation on the parameter values of the vital sign signals corresponding to each sampling point in the current time window. Taking the window width as 2 seconds and each second containing 250 sampling points as an example, performing point-by-point forward difference calculation on the vital sign signals in the current time window includes: subtracting the parameter value of the vital sign signal corresponding to the first sampling point from the parameter value of the vital sign signal corresponding to the second sampling point to obtain the first forward difference value, subtracting the parameter value of the vital sign signal corresponding to the second sampling point from the parameter value of the vital sign signal corresponding to the third sampling point to obtain the second forward difference value, and so on, subtracting the parameter value of the vital sign signal corresponding to the penultimate sampling point from the parameter value of the vital sign signal corresponding to the last sampling point to obtain the last forward difference value. The calculation of each forward difference value can be processed in parallel, and finally a current group of forward difference values containing 499 forward difference values is obtained.

[0048] Through forward difference calculation, interference fluctuations of the vital sign signal can be further filtered out, making the vital sign signal tend to be stable.

[0049] Further, after point-by-point forward difference calculation, it may further include: taking the absolute value of each forward difference value so that each forward difference value in the current group of forward difference values is non-negative.

[0050] Step S130: Perform histogram statistics on the current group of difference values and calculate the standard deviation of the frequency distribution of each group of the histogram.

[0051] The distribution law of the vital sign signal can be obtained conveniently and accurately through histogram statistics (hist). In one embodiment, the horizontal axis of the histogram is the distribution of the forward difference values of the current group, and the vertical axis of the histogram is the frequency. The number of groups for histogram statistics (hist_num) can be set as needed. For example, it can be set to 8 - 15 groups, and in this embodiment, it is specifically set to 12 groups. Thus, the process of performing histogram statistics in this embodiment includes: first obtaining the maximum and minimum values of the forward difference values of the current group, calculating the difference between the two and then dividing by 12 groups to obtain the value range of each group of the histogram; then counting the value ranges into which each value of the forward difference values of the current group falls to obtain the frequency of each group, and finally counting the histogram.

[0052] After statistically obtaining the histogram corresponding to the forward difference values of the current group, further calculate the standard deviation (hist_std) of the frequency distribution of each group of the histogram to obtain the degree of dispersion of the forward difference values of the current group.

[0053] Further, after calculating the standard deviation of the frequency distribution of each group of the histogram, it may further include: performing a normalization process of dividing the standard deviation by the average value of the histogram. The normalization process can eliminate the difference in the numerical range of the calculated standard deviation caused by different window widths. The functional expression for normalizing the standard deviation hist_std by dividing it by the average value of the histogram hist is:

[0054] hist_std_nor = hist_std / mean(hist); hist_std_nor is the normalized histogram statistical value.

[0055] Step S140, obtain the quality assessment result of the vital sign signal of the current time window according to the standard deviation and the quality threshold.

[0056] The quality threshold can be set as needed. According to the set quality threshold and the obtained standard deviation (i.e., the above-mentioned normalized histogram statistical value), the quality grading assessment of the vital sign signal of the current time window can be performed.

[0057] In one embodiment, the quality threshold at least includes a target quality threshold (which can be set to 2.0) for distinguishing whether the vital sign signal is valid; obtaining the quality assessment result of the vital sign signal of the current time window specifically includes: when the standard deviation is greater than or equal to the target quality threshold, obtaining the quality assessment result that the vital sign signal of the current time window is valid; when the standard deviation is less than the target quality threshold, obtaining the quality assessment result that the vital sign signal of the current time window is invalid.

[0058] In yet another embodiment, multiple quality thresholds may be set to perform multi-level grading evaluation on the vital sign signals. Specifically, a first quality threshold (thr1, thr1 = 2.5 or other appropriate value) and a second quality threshold (thr2, thr2 = 2.0 or other appropriate value) may be set. The multi-level grading evaluation of the vital sign signals in the current time window includes:

[0059] When hist_std_nor >= thr1, it indicates that the signal quality is good and not affected by interference, and an effective quality evaluation result of the vital sign signal in the current time window is obtained;

[0060] When hist_std_nor >= thr2 and hist_std_nor < thr1, it indicates that the signal is affected by interference, but the useful signal is not submerged by noise. Based on this signal, accurate vital sign parameters can still be calculated, so an effective quality evaluation result of the vital sign signal in the current time window can also be obtained;

[0061] When hist_std_nor < thr2, it indicates that the signal is severely affected by interference and the useful signal is submerged by noise. The accuracy of the vital sign parameters calculated based on this signal is relatively low, and the calculation result cannot be used as the basis for observing and diagnosing the condition of the subject being measured. Therefore, an invalid quality evaluation result of the vital sign signal in the current time window is obtained.

[0062] In other embodiments, the number and specific values of the quality thresholds can be adjusted as needed, and are not limited to the above examples.

[0063] Furthermore, in one embodiment, after obtaining the quality evaluation result of the vital sign signal in the current time window, it may further include: when the vital sign signal in the current time window is effective, transmitting the vital sign signal in the current time window to the vital sign monitoring module, where the vital sign monitoring module is deployed in or independently of the wearable device; when the vital sign signals in a continuous preset period are invalid, determining the invalid factors of the vital sign signals in the continuous preset period, and sending an adjustment reminder corresponding to the invalid factors through the wearable device.

[0064] When the quality evaluation result is that the vital sign signal is effective, accurate vital sign parameters can be calculated based on the corresponding vital sign signal, so it is transmitted to the vital sign monitoring module for calculating vital sign parameters. The vital sign monitoring module can be deployed in the wearable device, that is, an in-built module of the wearable device; the vital sign monitoring module can also be independent of the wearable device, for example, deployed in a remote monitoring device.

[0065] When the quality assessment result of the vital sign signal is invalid and accurate vital sign parameters cannot be calculated based on the corresponding vital sign signal, the vital sign signal is not transmitted. In addition, when the quality assessment results of the vital sign signals in a continuous preset period (which can be set as needed, for example, continuously for 10 s, corresponding to 5 consecutive time windows in the embodiment with a window width of 2 s) are all invalid, it indicates that there may be situations such as the wearable device malfunctioning or being worn improperly, resulting in all the vital sign signals collected within a continuous period being invalid. Therefore, first, determine the invalid factors that cause the vital sign signals in this continuous preset period to be invalid. The invalid factors specifically include device - type invalid factors and non - device - type invalid factors. Device - type invalid factors refer to malfunctions of the wearable device itself, and non - device - type invalid factors are not malfunctions of the wearable device itself but reasons such as improper wearing / poor contact of the wearable device. Specifically, existing methods can be used to determine the invalid factors. In the present invention, classifying the invalid factors into device - type invalid factors and non - device - type invalid factors is beneficial for guiding the user to make adjustments for different types of invalid factors.

[0066] Specifically, the wearable device sends out adjustment reminders corresponding to the invalid factors, including: if the invalid factor is a device - type invalid factor, the wearable device sends out an adjustment reminder to restart the device to guide the user of the wearable device to restart the wearable device and overcome the situation where the collected signal is invalid caused by the device - type invalid factor; if the invalid factor is a non - device - type invalid factor, the wearable device sends out an adjustment reminder to adjust the device position to guide the user of the wearable device to adjust the wearing position of the wearable device and overcome the situation where the collected signal is invalid caused by the non - device - type invalid factor. By guiding the user to make timely adjustments when the collected vital sign signals are invalid, it is possible to ensure that effective vital sign signals that can be used to calculate vital sign parameters are collected.

[0067] Further, in an embodiment, after the wearable device sends out an adjustment reminder, it may further include: when the quality assessment results of the vital sign signals in the next continuous preset period are all invalid, sending an alarm notification to the remote monitoring device of the wearable device.

[0068] The quality assessment of the vital sign signal stream is continuously carried out. If it is monitored that the quality assessment results of the vital sign signals in the next continuous preset period (i.e., the next continuous 10 s) are still all invalid, it indicates that the wearable device is very likely to have problems that cannot be overcome by simple device restart / device position adjustment. To ensure the safety of the measured person, an alarm notification is sent to the remote monitoring device of the wearable device to avoid loopholes in vital sign monitoring caused by the inability to collect effective vital sign signals and obtain accurate vital sign parameters.

[0069] In summary, the method for evaluating the quality of physiological sign signals of the present invention has the following advantages: It does not rely on feature extraction, but directly evaluates the quality based on the originally collected physiological sign signals, and the accuracy of quality evaluation is not affected by the accuracy of feature extraction; It does not rely on an algorithm model trained by supervised machine learning, there is no overfitting phenomenon, the actual application effect is good, and there is no obvious difference from prior data; The overall operation complexity is low, which is suitable for wearable devices to run; The algorithm delay is small, the time window can be set as needed, and the minimum can be set to 1 s, realizing real-time evaluation of signal quality; In the case where the acquisition of physiological sign signals in a continuous preset period is invalid, it can guide the user to make adjustments to overcome the problem of invalid signal acquisition, and can send an alarm to the remote monitoring device to ensure the use safety.

[0070] Figure 2 Fig. shows the specific process of the method for evaluating the quality of physiological sign signals in an embodiment. Refer to Figure 2 As shown, in combination with the descriptions of the above embodiments, in a specific example, evaluating the quality of physiological sign signals includes:

[0071] S210, performing power frequency filtering and band-pass filtering of 0.5 - 45 Hz on the collected physiological sign signals in sequence to achieve noise reduction processing on the originally collected physiological sign signals.

[0072] S220, performing window division based on a time window on the filtered physiological sign signals, and the window width can be 1 - 10 seconds, specifically 2 seconds in this example.

[0073] S230, performing forward difference calculation point by point on the physiological sign signals in the current time window, and taking the absolute value of the value after difference to obtain the current set of forward difference values.

[0074] S240, performing histogram statistics (hist) on the current set of forward difference values, and the number of groups hist_num for histogram statistics can be 8 - 15, specifically 12 in this example.

[0075] S250, calculating the standard deviation (hist_std) of the frequency distribution of each group of the histogram.

[0076] S260, normalizing by dividing the standard deviation hist_std by the average value of the histogram hist to eliminate the difference in the numerical range of the calculated standard deviation hist_std caused by different window widths. The function expression for normalization is: hist_std_nor = hist_std / mean(hist).

[0077] S270, performing quality grading on the physiological sign signals in the current time window according to the calculated normalized value hist_std_nor, including:

[0078] S270a. When hist_std_nor >= thr1, the signal quality is good and not affected by interference. The typical value of thr1 is 2.5. Figure 3 shows the electrocardiogram (ECG) signal waveform without interference and the corresponding signal quality evaluation value in one embodiment. Refer to Figure 3 as shown, when the ECG signal waveform 310 is not affected by interference, its waveform is stable and clean, and the corresponding signal quality evaluation value 320 is above the threshold of 2.5.

[0079] S270b. When hist_std_nor >= thr2 && hist_std_nor < thr1, the signal is affected by interference, but the useful signal is not submerged by noise. Based on this signal, accurate vital sign parameters can still be calculated. The typical value of thr2 is 2.0. Figure 4 shows the ECG signal waveform affected by interference but with visible QRS waves and the corresponding signal quality evaluation value in one embodiment. Refer to Figure 4 as shown, when the ECG signal waveform 410 is affected by certain interference but there are visible QRS waves, the corresponding signal quality evaluation value 420 is between the threshold of 2.0 and the threshold of 2.5.

[0080] S270c. When hist_std_nor < thr2, the signal is severely affected by interference and the useful signal is submerged by noise. The accuracy of the vital sign parameters calculated based on this signal is relatively low, and the calculation result cannot be used as the basis for observing and diagnosing the condition of the measured person. Figure 5 shows the ECG signal waveform covered by interference and without visible QRS waves and the corresponding signal quality evaluation value in one embodiment. Refer to Figure 5 as shown, when the ECG signal waveform 510 is severely affected by interference and there are no visible QRS waves, the corresponding signal quality evaluation value 520 is less than the threshold of 2.0.

[0081] The embodiment of the present invention also provides a quality evaluation device for vital sign signals, which can be used to implement the quality evaluation method for vital sign signals described in any of the above embodiments. The features and principles of the quality evaluation method described in any of the above embodiments can be applied to the following embodiments of the quality evaluation device. In the following embodiments of the quality evaluation device, the features and principles regarding the quality evaluation of vital sign signals that have been clarified will not be repeated.

[0082] Figure 6 shows the main modules of the quality evaluation device for vital sign signals in one embodiment. Refer to Figure 6As shown in the figure, the quality evaluation device 600 for physiological sign signals of this embodiment includes: a time window module 610, configured to intercept the physiological sign signals of the current time window from the collected physiological sign signal stream based on the time window; a differential calculation module 620, configured to perform point-by-point forward difference calculation on the physiological sign signals of the current time window according to the sampling points to obtain the current group of forward difference values; a histogram statistics module 630, configured to perform histogram statistics on the current group of difference values and calculate the standard deviation of the frequency distribution of each group of the histogram; and a threshold comparison module 640, configured to obtain the quality evaluation result of the physiological sign signals of the current time window according to the standard deviation and the quality threshold.

[0083] The quality evaluation device 600 for physiological sign signals may be the above-mentioned wearable device or an independent device communicatively connected to the wearable device.

[0084] Furthermore, the quality evaluation device 600 for physiological sign signals may further include modules for implementing other process steps of the above-mentioned embodiments of each quality evaluation method. The specific principles of each module may refer to the descriptions of the above-mentioned embodiments of each quality evaluation method and will not be repeated here.

[0085] The quality evaluation device for physiological sign signals of the present invention can realize convenient and accurate quality evaluation of physiological sign signals. The accuracy of quality evaluation is not affected by the accuracy of feature extraction, the evaluation effect is good, the overall operation complexity is low, the algorithm delay is small, it is suitable for running on wearable devices, and can realize real-time evaluation of signal quality; in the case where the acquisition of physiological sign signals is invalid for a continuous preset period, it can guide the user to make adjustments to overcome the problem of invalid signal acquisition, and can send an alarm to the remote monitoring device to ensure the use safety.

[0086] An embodiment of the present invention further provides an electronic device, including a processor and a memory. An executable instruction is stored in the memory. When the executable instruction is executed by the processor, the quality evaluation method for physiological sign signals described in any of the above embodiments is realized.

[0087] The electronic device of the present invention may be the above-mentioned wearable device or an independent device communicatively connected to the wearable device. The electronic device of the present invention can realize convenient and accurate quality evaluation of physiological sign signals. The accuracy of quality evaluation is not affected by the accuracy of feature extraction, the evaluation effect is good, the overall operation complexity is low, the algorithm delay is small, it is suitable for running on wearable devices, and can realize real-time evaluation of signal quality; in the case where the acquisition of physiological sign signals is invalid for a continuous preset period, it can guide the user to make adjustments to overcome the problem of invalid signal acquisition, and can send an alarm to the remote monitoring device to ensure the use safety.

[0088] Figure 7 The main structure of the electronic device in an embodiment is shown. It should be understood that Figure 7Only various modules are schematically shown. These modules can be virtual software modules or actual hardware modules. The combination, splitting, and addition of other modules are within the protection scope of the present invention.

[0089] Referring Figure 7 As shown, the electronic device 700 is presented in the form of a general-purpose computing device. The components of the electronic device 700 include but are not limited to: at least one processing unit 710, at least one storage unit 720, a bus 730 connecting different platform components (including the storage unit 720 and the processing unit 710), a display unit 740, etc.

[0090] The storage unit 720 stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 executes the steps of the method for evaluating the quality of the physical sign signals described in any of the above embodiments. For example, the processing unit 710 can execute steps as Figure 1 and Figure 2 shown.

[0091] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7201 and / or a cache storage unit 7202, and may further include a read-only storage unit (ROM) 7203.

[0092] The storage unit 720 may further include a program / utility 7204 having one or more program modules 7205. Such program modules 7205 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0093] The bus 730 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0094] The electronic device 700 can also communicate with one or more external devices, which can be one or more of devices such as a keyboard, a pointing device, a Bluetooth device, etc. These external devices enable users to interact and communicate with the electronic device 700. The electronic device 700 can also communicate with one or more other computing devices, and the shown computer devices include a router and a modem. This communication can be carried out through the input / output (I / O) interface 750. Moreover, the electronic device 700 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 760. The network adapter 760 can communicate with other modules of the electronic device 700 through the bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0095] An embodiment of the present invention also provides a computer-readable storage medium for storing a program, which when executed implements the method for evaluating the quality of the physiological sign signal described in any of the above embodiments. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the method for evaluating the quality of the physiological sign signal described in any of the above embodiments.

[0096] The storage medium of the present invention can be executed by a processor deployed in a wearable device or in an independent device communicatively connected to the wearable device, to implement a convenient and accurate quality evaluation of the physiological sign signal. The accuracy of the quality evaluation is not affected by the accuracy of feature extraction, the evaluation effect is good, the overall operation complexity is low, the algorithm delay is small, and it is suitable for running on a wearable device to implement real-time evaluation of the signal quality; in the case that the acquisition of the physiological sign signal in a continuous preset time period is invalid, it can also guide the user to make adjustments to overcome the problem of invalid signal acquisition, and can send an alarm to a remote monitoring device to ensure the use safety.

[0097] The storage medium can adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the storage medium of the present invention is not limited thereto, and it can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0098] The storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium include, but are not limited to: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0099] The readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable signal medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0100] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device, for example, by connecting through the Internet using an Internet service provider.

[0101] The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention pertains, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for evaluating the quality of a physical sign signal, characterized in that, Including: Intercepting the physiological sign signals of the current time window from the collected physiological sign signal stream based on a time window; Performing point-by-point forward difference calculation on the physiological sign signals of the current time window according to sampling points to obtain the current set of forward difference values; Performing histogram statistics on the current set of difference values and calculating the standard deviation of the frequency distribution of each group of the histogram; Performing normalization processing on the standard deviation to eliminate the numerical range difference caused by different time window widths; Comparing the normalized standard deviation with a quality threshold to obtain the quality assessment result of the physiological sign signals of the current time window; Wherein, the physiological sign signals include any one or more of electrocardiogram signals, blood pressure signals, and blood oxygen signals, and the quality assessment method is applied to a wearable device.

2. The quality assessment method according to claim 1, wherein Before intercepting the physiological sign signals of the current time window from the collected physiological sign signal stream based on a time window, it further includes: Performing noise reduction processing on the collected physiological sign signal stream including power frequency filtering and band-pass filtering.

3. The quality assessment method according to claim 1, wherein After performing point-by-point forward difference calculation on the physiological sign signals of the current time window according to sampling points, it further includes: Taking the absolute value of each forward difference value.

4. The quality assessment method according to claim 1, characterized in that, The horizontal axis of the histogram is the distribution of the current set of forward difference values, and the vertical axis of the histogram is the frequency.

5. The quality assessment method according to claim 1, characterized in that The performing normalization processing on the standard deviation includes: Performing normalization processing on the standard deviation by dividing it by the average value of the histogram.

6. The quality assessment method according to claim 1, characterized in that The quality threshold at least includes a target quality threshold for distinguishing whether the physiological sign signals are valid; The obtaining the quality assessment result of the physiological sign signals of the current time window includes: When the standard deviation is greater than or equal to the target quality threshold, obtaining a quality assessment result that the physiological sign signals of the current time window are valid; When the standard deviation is less than the target quality threshold, obtaining a quality assessment result that the physiological sign signals of the current time window are invalid.

7. The quality assessment method according to claim 6, characterized in that The physiological sign signals are collected by a wearable device; After obtaining the quality assessment result of the physiological sign signals of the current time window, it further includes: When the physiological sign signals of the current time window are valid, transmitting the physiological sign signals of the current time window to a physiological sign monitoring module, and the physiological sign monitoring module is deployed in or independent of the wearable device; When the quality assessment results of the physiological sign signals in a continuous preset period are all invalid, determining the invalid factors of the physiological sign signals in the continuous preset period and sending an adjustment reminder corresponding to the invalid factors through the wearable device.

8. The quality assessment method according to claim 7, wherein The invalid factors include device-type invalid factors and non-device-type invalid factors, and the sending an adjustment reminder corresponding to the invalid factors through the wearable device includes: When the invalid factor is the device-type invalid factor, sending an adjustment reminder for device restart through the wearable device; When the invalid factor is a non-device-type invalid factor, sending an adjustment reminder for device position adjustment through the wearable device.

9. The quality assessment method according to claim 7, characterized in that, After sending an adjustment reminder corresponding to the invalid factors through the wearable device, it further includes: When the quality assessment results of the physiological sign signals in the next continuous preset period are all invalid, sending an alarm notification to the remote monitoring device of the wearable device.

10. A quality assessment device for physical sign signals, characterized in that, Including: A time window module for intercepting the physiological sign signals of the current time window from the collected physiological sign signal stream based on the time window; A differential calculation module for performing point-by-point forward difference calculation on the physiological sign signals of the current time window according to sampling points to obtain the current set of forward difference values; A histogram statistics module for performing histogram statistics on the current set of difference values and calculating the standard deviation of the frequency distribution of each group of the histogram; A normalization processing module for performing normalization processing on the standard deviation to eliminate the numerical range difference caused by different time window widths; A threshold comparison module for comparing the normalized standard deviation with a quality threshold to obtain a quality evaluation result of the physiological sign signals of the current time window; Wherein, the physiological sign signals include any one or more of electrocardiogram signals, blood pressure signals, and blood oxygen signals, and the quality evaluation device is applied to a wearable device.

11. An electronic device, characterized in that, Comprising: A processor; A memory in which executable instructions are stored; Wherein, when the executable instructions are executed by the processor, the quality evaluation method of the physiological sign signals as described in any one of claims 1-9 is implemented.

12. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, the quality evaluation method of the physiological sign signals as described in any one of claims 1-9 is implemented.

Images