Method and device for evaluating quality of photoplethysmographic signal and computer device

Abstract

The present application relates to the technical field of signal processing, and particularly relates to a photoelectric plethysmogram signal quality evaluation method and device, computer equipment and storage medium, template construction is carried out based on the photoelectric plethysmogram signals of multiple wavelengths of a user to be detected, and a photoelectric plethysmogram template signal is obtained; signal division and quality detection index extraction are carried out by using the photoelectric plethysmogram template signal, multi-level information mining is carried out on the photoelectric plethysmogram signal, more sufficient and rich feature information is obtained, more comprehensive and sufficient signal quality evaluation is realized, the extracted quality detection index is used to extract target signal extraction results from the photoelectric plethysmogram signals of multiple wavelengths, the accuracy of photoelectric plethysmogram signal extraction is improved, and comprehensive and sufficient quality control is effectively carried out on the photoelectric plethysmogram signal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of signal processing, and particularly relates to a photoplethysmogram signal quality evaluation method and device, a computer device and a storage medium. BACKGROUND

[0002] With the development and popularity of intelligent wearable and home devices, the use of photoplethysmogram (PPG) signals for heart rate and blood oxygen measurement is becoming more and more popular. The PPG signal is an important biological signal for non-invasive physiological monitoring. It measures the change in light reflection on the skin surface through a photoelectric sensor, capturing the fluctuation of blood through the skin blood vessels when the heart beats. In the process of using the PPG signal to monitor heart rate and blood oxygen, the quality of the signal directly determines the accuracy of the heart rate and blood oxygen value. Therefore, it is necessary to detect the usability of the signal.

[0003] The current technical solution for PPG signal usability detection mainly uses PPG time domain, frequency domain and other features to construct indicators, and performs usability detection based on the constructed indicators. The features are calculated based on statistical quantities, and the indicators constructed based on the features may not be sensitive enough to specific application scenarios, cannot fully reflect the quality of the signal, have limited generalization ability, and are difficult to fully and comprehensively control the quality of the PPG signal. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a photoplethysmogram signal quality evaluation method, device, equipment and storage medium. A template is constructed based on the photoplethysmogram signals of multiple wavelengths of a user to be detected, and a photoplethysmogram template signal is obtained. The photoplethysmogram signal is divided and quality detection indicators are extracted using the photoplethysmogram template signal, the photoplethysmogram signal is mined at multiple levels, more sufficient and rich feature information is obtained, more comprehensive and sufficient quality evaluation of the signal is realized, the target signal extraction result is extracted from the photoplethysmogram signals of multiple wavelengths using the extracted quality detection indicators, the accuracy of photoplethysmogram signal extraction is improved, and the photoplethysmogram signal is effectively and comprehensively controlled in quality.

[0005] In a first aspect, an embodiment of the present application provides a photoplethysmogram signal quality evaluation method, including the following steps:

[0006] Obtain the photoplethysmogram signals of multiple wavelengths of a user to be detected;

[0007] Obtain the first peak value positioning data and the valley value positioning data of the photoplethysmogram signal, divide the photoplethysmogram signal according to the first valley value positioning data, and obtain a set of photoplethysmogram cycle signals of multiple wavelengths;

[0008] constructing a template according to the photoplethysmogram cycle signal set of several wavelengths, to obtain a photoplethysmogram template signal;

[0009] performing template matching according to the photoplethysmogram template signal and the photoplethysmogram signals of several wavelengths respectively, to obtain second peak positioning data of the photoplethysmogram signals of several wavelengths;

[0010] dividing the photoplethysmogram signals according to a preset signal unit length, to obtain a photoplethysmogram unit signal set of several wavelengths; and performing quality detection index calculation according to the first peak positioning data, the second peak positioning data and the photoplethysmogram unit signal set of several wavelengths, to obtain quality detection indexes of the photoplethysmogram unit signals of several wavelengths in the photoplethysmogram unit signal set of several wavelengths;

[0011] extracting target photoplethysmogram unit signals from the photoplethysmogram unit signal set of several wavelengths according to the quality detection indexes, and combining the target photoplethysmogram unit signals as a photoplethysmogram signal extraction result of the user to be detected.

[0012] In a second aspect, an embodiment of the present application provides a quality evaluation device of a photoplethysmogram signal, comprising:

[0013] a signal acquisition module, configured to obtain photoplethysmogram signals of several wavelengths of a user to be detected;

[0014] a signal division module, configured to obtain first peak positioning data and valley positioning data of the photoplethysmogram signals, and divide the photoplethysmogram signals according to the first valley positioning data, to obtain a photoplethysmogram cycle signal set of several wavelengths;

[0015] a signal template construction module, configured to construct a template according to the photoplethysmogram cycle signal set of several wavelengths, to obtain a photoplethysmogram template signal;

[0016] a template matching module, configured to perform template matching according to the photoplethysmogram template signal and the photoplethysmogram signals of several wavelengths respectively, to obtain second peak positioning data of the photoplethysmogram signals of several wavelengths;

[0017] The quality detection index calculation module is configured to perform signal division on the photoplethysmogram signal according to a preset signal unit length to obtain a set of photoplethysmogram unit signals of a plurality of wavelengths; and perform quality detection index calculation on the first peak value positioning data, the second peak value positioning data, and the set of photoplethysmogram unit signals of the plurality of wavelengths to obtain quality detection indexes of a plurality of photoplethysmogram unit signals in the set of photoplethysmogram unit signals of the plurality of wavelengths.

[0018] The signal extraction module is configured to extract a plurality of target photoplethysmogram unit signals from the set of photoplethysmogram unit signals of the plurality of wavelengths according to the quality detection indexes, and combine the plurality of target photoplethysmogram unit signals as a photoplethysmogram signal extraction result of the user to be detected.

[0019] In a third aspect, an embodiment of the present application provides a computer device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor; when the computer program is executed by the processor, the steps of the quality evaluation method of the photoplethysmogram signal are implemented.

[0020] In a fourth aspect, an embodiment of the present application provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the quality evaluation method of the photoplethysmogram signal are implemented.

[0021] In the embodiments of the present application, a quality evaluation method, device, equipment, and storage medium of a photoplethysmogram signal are provided, a template is constructed based on a plurality of photoplethysmogram signals of a user to be detected, and a photoplethysmogram template signal is obtained; signal division and quality detection index extraction are performed by using the photoplethysmogram template signal, a plurality of levels of information mining are performed on the photoplethysmogram signal, more sufficient and rich feature information is obtained, more comprehensive and sufficient quality evaluation of the signal is implemented, a target signal extraction result is extracted from the plurality of photoplethysmogram signals by using the extracted quality detection indexes, the accuracy of photoplethysmogram signal extraction is improved, and comprehensive and sufficient quality control of the photoplethysmogram signal is effectively performed.

[0022] For better understanding and implementation, the present application is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A flowchart of a quality evaluation method of a photoplethysmogram signal provided by an embodiment of the present application is shown in the figure;

[0024] Figure 2A flowchart of S2 in a method for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 2;

[0025] Figure 3 A flowchart of S3 in a method for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 3;

[0026] Figure 4 A flowchart of S4 in a method for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 4;

[0027] Figure 5 A flowchart of S5 in a method for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 5;

[0028] Figure 6 A flowchart of S5 in a method for evaluating quality of a photoplethysmogram signal according to another embodiment of the present application is shown in FIG. 6;

[0029] Figure 7 A flowchart of S6 in a method for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 7;

[0030] Figure 8 A structural diagram of a device for evaluating quality of a photoplethysmogram signal according to an embodiment of the present application is shown in FIG. 8;

[0031] Figure 9 A structural diagram of a computer device according to an embodiment of the present application is shown in FIG. 9. DETAILED DESCRIPTION

[0032] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is merely representative of all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims.

[0033] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0034] It should be understood that, although the terms first, second, third, etc. can be employed in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another type of information. For example, without departing from the scope of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0035] Please refer to Figure 1 , Figure 1 The flowchart of the quality evaluation method of the photoplethysmogram signal provided by an embodiment of the present application, the method comprises the following steps:

[0036] S1: Obtain the photoplethysmogram signals of several wavelengths of the user to be detected.

[0037] The execution subject of the quality evaluation method of the photoplethysmogram signal is the extraction device of the quality evaluation method of the photoplethysmogram signal (hereinafter referred to as the extraction device). In an optional embodiment, the extraction device can be a computer device, which can be a server, or a server cluster formed by a plurality of computer devices.

[0038] In the present embodiment, the extraction device can obtain the photoplethysmogram signals of several wavelengths of the user to be detected by querying in a preset database, or can realize non-perception collection by reflecting the photoplethysmogram signals of several wavelengths of the user to be detected through a plurality of preset PPG signal detection probes, such as a red light detection probe and an infrared light detection probe. In the application scenario of the present embodiment, the initial photoplethysmogram signals of the buttocks of the user to be detected are collected by setting corresponding PPG signal detection probes on the intelligent toilet pad during the process of the user to be detected defecating.

[0039] Since the baseline of the collected initial photoplethysmogram signals of the buttocks usually contains a large amount of glitches, it is necessary to filter out power frequency noise and baseline drift. The extraction device performs filtering processing on the initial photoplethysmogram signals of the several wavelengths to obtain the initial photoplethysmogram signals of the several wavelengths after filtering processing, as the photoplethysmogram signals of the several wavelengths of the user to be detected.

[0040] Specifically, after the signal acquisition is completed, the extraction device filters out the baseline by using a 200-order cutoff frequency 0.3Hz low-pass filter, then smoothes the signal by using a median filter, and finally filters out the power frequency interference and high-frequency noise by using a 1-5Hz band-pass filter to obtain the filtered photoelectric plethysmogram signals of several wavelengths, which can effectively identify the low-quality fragments formed by motion artifacts and noise interference in the data acquisition process, filter them, improve the accuracy of signal extraction, and facilitate effective quality control of the photoelectric plethysmogram signals.

[0041] S2: Obtain first peak value positioning data and valley value positioning data of the photoelectric plethysmogram signal, divide the photoelectric plethysmogram signal according to the first valley value positioning data to obtain a set of photoelectric plethysmogram cycle signals of several wavelengths.

[0042] In this embodiment, the extraction device obtains first peak value positioning data and valley value positioning data of the photoelectric plethysmogram signal, wherein the first peak value positioning data includes a plurality of first peak points.

[0043] The extraction device divides the photoelectric plethysmogram signal according to a plurality of valley points in the first valley value positioning data to obtain a set of photoelectric plethysmogram cycle signals of several wavelengths, wherein the set of photoelectric plethysmogram cycle signals includes a plurality of photoelectric plethysmogram cycle signals.

[0044] Specifically, the first peak value positioning data is fast peak value positioning data obtained by using a fast peak searching method, please refer to Figure 2 , Figure 2 The flowchart of S2 in the quality evaluation method of the photoelectric plethysmogram signal provided by an embodiment of the present application is shown in the figure, which includes steps S21-S23, and the details are as follows:

[0045] S21: Obtain fast peak value positioning data and fast valley value positioning data of the photoelectric plethysmogram signal by using a fast peak searching method.

[0046] In order to reduce the interference of PPG double waves on peak and valley value positioning, in this embodiment, the extraction device performs median filtering on the photoelectric plethysmogram signal by using a median filter, performs peak value positioning and valley value positioning on the photoelectric plethysmogram signal after median filtering by using a fast peak searching method, and obtains fast peak value positioning data and fast valley value positioning data of the photoelectric plethysmogram signal.

[0047] In an optional embodiment, the extraction device corrects the peak points in the fast peak value positioning data, specifically, the extraction device finds the local maximum value in the step length interval around the above-mentioned peak points according to the step length of the median filter, and determines the point as the corrected peak point.

[0048] S22: According to the peak values of the plurality of fast peak points in the fast peak positioning data and the valley values of the plurality of fast valley points in the fast valley positioning data, average screening processing is performed to obtain a plurality of screening peak points and a plurality of screening valley points. The screening peak points are combined with the previous screening valley points to construct a plurality of initial screening peak-valley point combinations.

[0049] In this embodiment, the extraction device performs average screening processing according to the peak values of the plurality of fast peak points in the fast peak positioning data and the valley values of the plurality of fast valley points in the fast valley positioning data, to obtain a plurality of screening peak points and a plurality of screening valley points. The screening peak points are combined with the previous screening valley points to construct a plurality of initial screening peak-valley point combinations.

[0050] Specifically, the extraction device calculates a first fast average peak value and a first fast average valley value according to the peak values of the plurality of fast peak points in the fast peak positioning data and the valley values of the plurality of fast valley points in the fast valley positioning data, respectively. According to the first fast average peak value and the first fast average valley value, the peak points less than twice the first fast average peak value are screened out from the fast peak positioning data to obtain a plurality of screening peak points, and the valley points less than twice the first fast average valley value are screened out from the fast valley positioning data to obtain a plurality of candidate valley points. This is to exclude the fragments caused by motion artifacts or sensor shedding on the signal.

[0051] S23: Obtain the peak-valley values of the plurality of initial screening peak-valley point combinations, and obtain a plurality of target screening peak-valley point combinations according to the peak-valley values and a preset peak-valley depth threshold. The valley points in the target screening peak-valley point combinations are confirmed to construct the valley positioning data of the photoplethysmogram signal.

[0052] In this embodiment, the extraction device obtains the peak-valley values of the plurality of initial screening peak-valley point combinations, and obtains a plurality of target screening peak-valley point combinations according to the peak-valley values and a preset peak-valley depth threshold. The valley points in the target screening peak-valley point combinations are confirmed to construct the valley positioning data of the photoplethysmogram signal.

[0053] Specifically, the extraction device calculates a second fast average peak value and a second fast average valley value according to the peak values of the candidate peak points and the valley values of the candidate valley points, calculates an average peak-valley depth according to the second fast average peak value and the second fast average valley value, obtains peak-valley values of a plurality of initial screening peak-valley point combinations, compares the plurality of initial screening peak-valley point combinations one by one according to the peak-valley values and a preset peak-valley depth threshold, if the peak-valley value of the currently compared initial screening peak-valley point combination meets, i.e., is greater than or equal to the peak-valley depth threshold, the initial screening peak-valley point combination is taken as a target screening peak-valley point combination, and the peak-valley value of the initial screening peak-valley point combination is updated to a preset dynamic peak-valley depth threshold.

[0054] If the peak-valley value of the next compared initial screening peak-valley point combination is less than the peak-valley depth threshold, the peak-valley value of the initial screening peak-valley point combination is compared with the dynamic peak-valley depth threshold of the last initial screening peak-valley point combination that meets the peak-valley depth threshold, if the peak-valley value meets, i.e., is greater than or equal to the dynamic peak-valley depth threshold, the initial screening peak-valley point combination is taken as a target screening peak-valley point combination, and a plurality of target screening peak-valley point combinations are obtained, the valley points in the target screening peak-valley point combinations are confirmed, and valley positioning data of the photoplethysmogram signal is constructed.

[0055] In an optional embodiment, the extraction device corrects the valley points in the valley positioning data of the photoplethysmogram signal, specifically, the extraction device finds a local maximum value in a step length interval around the valley point according to a step length of a median filter, and determines the local maximum value as a corrected valley point.

[0056] S3: Template construction is performed according to the plurality of sets of photoplethysmogram cycle signals of different wavelengths, and a photoplethysmogram template signal is obtained.

[0057] In this embodiment, the extraction device performs template construction according to the plurality of sets of photoplethysmogram cycle signals of different wavelengths, and obtains a photoplethysmogram template signal.

[0058] Please refer to Figure 3 , Figure 3 The flowchart of S3 in the quality evaluation method of the photoplethysmogram signal provided by an embodiment of the present application is shown in FIG. 3, which includes steps S31-S33, and specifically as follows:

[0059] S31: Obtain the correlation coefficients of several photoplethysmography (PPG) periodic signals in the PPG periodic signal set. Based on the correlation coefficients and a preset first correlation coefficient threshold, extract several candidate PPG periodic signals from the PPG periodic signal set of several wavelengths respectively to obtain several candidate PPG periodic signals of several wavelengths.

[0060] In this embodiment, the extraction device obtains correlation coefficients of several photoplethysmography (PPG) cycle signals from the PPG cycle signal set. These correlation coefficients include forward correlation coefficients and backward correlation coefficients, as detailed below:

[0061] r l =corrcoef[x ppg (n-1),x ppg (n)]

[0062] r r =corrcoef[x ppg (n),x ppg (n+1)]

[0063] In the formula, r l R is the forward correlation coefficient. r x is the backward correlation coefficient. ppg (n-1) represents the (n-1)th photoplethysmography (PPG) cycle signal, x ppg (n) represents the nth photoplethysmography (PPG) periodic signal, and (n+1) represents the (n+1)th PPG periodic signal. corrcoef[·] is the correlation coefficient calculation function.

[0064] The extraction device, based on the correlation coefficient and a preset first correlation coefficient threshold, if both the forward correlation coefficient and the backward correlation coefficient of the photoplethysmography (PPG) periodic signal are greater than the first correlation coefficient threshold, selects the PPG periodic signal as a candidate PPG periodic signal, and extracts several candidate PPG periodic signals from a set of PPG periodic signals of several wavelengths to obtain several candidate PPG periodic signals of several wavelengths.

[0065] S32: Obtain the cross-correlation coefficient between several candidate photoplethysmography (PPG) periodic signals of different wavelengths. Based on the cross-correlation coefficient and a preset cross-correlation coefficient threshold, obtain several candidate PPG periodic signals that satisfy the cross-correlation coefficient threshold, and use them as sample PPG template signals to construct a template signal fragment set.

[0066] In the embodiment, the extraction device obtains cross-correlation coefficients between a plurality of candidate photoplethysmogram cycle signals of different wavelengths, obtains a plurality of candidate photoplethysmogram cycle signals satisfying a preset cross-correlation coefficient threshold as sample photoplethysmogram template signals according to the cross-correlation coefficients and the preset cross-correlation coefficient threshold, and constructs a template signal segment set.

[0067] S33: constructing an average photoplethysmogram template signal of the template signal segment set, performing standard deviation calculation according to a plurality of sample photoplethysmogram template signals in the template signal segment set and the average photoplethysmogram template signal, obtaining standard deviations of the plurality of sample photoplethysmogram template signals, obtaining a plurality of sample photoplethysmogram template signals with maximum standard deviations corresponding to a preset signal number as candidate photoplethysmogram template signals according to the preset signal number, and constructing a photoplethysmogram template signal according to the plurality of candidate photoplethysmogram template signals.

[0068] In the embodiment, the extraction device constructs an average photoplethysmogram template signal of the template signal segment set, wherein the average photoplethysmogram template signal is:

[0069]

[0070] In the formula, mean ppg is an average photoplethysmogram template signal, n is a number of sample photoplethysmogram template signals in the template signal segment set, X m (i) is an i-th sample photoplethysmogram template signal in the template signal segment set, peak is a peak point in the sample photoplethysmogram template signal, L model is a template signal length.

[0071] The extraction device performs standard deviation calculation according to a plurality of sample photoplethysmogram template signals in the template signal segment set and the average photoplethysmogram template signal, and obtains standard deviations of the plurality of sample photoplethysmogram template signals, wherein the standard deviation is:

[0072]

[0073] In the formula, σ is a standard deviation.

[0074] The extraction device obtains a plurality of sample photoplethysmogram template signals with maximum standard deviations corresponding to a preset signal number as candidate photoplethysmogram template signals according to the preset signal number, and constructs a photoplethysmogram template signal according to the plurality of candidate photoplethysmogram template signals.

[0075] S4: According to the photoplethysmogram template signal, template matching is respectively performed on the photoplethysmogram signals of the plurality of wavelengths to obtain second peak positioning data of the photoplethysmogram signals of the plurality of wavelengths.

[0076] In this embodiment, the extraction device performs template matching on the photoplethysmogram signals of the plurality of wavelengths according to the photoplethysmogram template signal to obtain second peak positioning data of the photoplethysmogram signals of the plurality of wavelengths.

[0077] Referring to Figure 4 , Figure 4 The flowchart of S4 in the quality evaluation method of the photoplethysmogram signal provided by an embodiment of the present application includes steps S41-S43, and the details are as follows:

[0078] S41: Cross-correlation processing is performed on the photoplethysmogram template signal and the photoplethysmogram signals of the plurality of wavelengths to obtain photoplethysmogram cross-correlation function signals of the plurality of wavelengths.

[0079] In this embodiment, the extraction device performs cross-correlation processing on the photoplethysmogram template signal and the photoplethysmogram signals of the plurality of wavelengths according to the preset step length to obtain photoplethysmogram cross-correlation function signals of the plurality of wavelengths.

[0080] S42: According to a preset peak threshold and a peak searching function, a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signals are obtained, and correlation coefficient calculation is performed on the initial cross-correlation peak points to obtain correlation coefficients of the plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signals.

[0081] In this embodiment, the extraction device obtains a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signals according to a preset peak threshold and a peak searching function, and correlation coefficient calculation is performed on the initial cross-correlation peak points to obtain correlation coefficients of the plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signals.

[0082] S43: According to the correlation coefficients of the plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signals and a preset second correlation coefficient threshold, a plurality of target cross-correlation function peak points of the photoplethysmogram cross-correlation function signals are obtained; the plurality of target cross-correlation function peak points of the photoplethysmogram cross-correlation function signals are mapped to the photoplethysmogram signals of the corresponding wavelengths to obtain second peak positioning data of the photoplethysmogram signals of the plurality of wavelengths.

[0083] In the embodiment, the extraction device maps the plurality of target cross-correlation function peak points of the photoelectric plethysmogram cross-correlation function signal to the photoelectric plethysmogram signals of the corresponding wavelengths to obtain second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths. Since the length of the obtained photoelectric plethysmogram cross-correlation function signal is one photoelectric plethysmogram template signal length less than the photoelectric plethysmogram signal, and the correlation coefficient is recorded from the start position of the signal period, preferably, the extraction device corrects the second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths, specifically as follows.

[0084] In the embodiment, the extraction device maps the plurality of target cross-correlation function peak points of the photoelectric plethysmogram cross-correlation function signal to the photoelectric plethysmogram signals of the corresponding wavelengths to obtain second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths. Since the length of the obtained photoelectric plethysmogram cross-correlation function signal is one photoelectric plethysmogram template signal length less than the photoelectric plethysmogram signal, and the correlation coefficient is recorded from the start position of the signal period, preferably, the extraction device corrects the second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths, specifically as follows.

[0085] In the embodiment, the extraction device maps the plurality of target cross-correlation function peak points of the photoelectric plethysmogram cross-correlation function signal to the photoelectric plethysmogram signals of the corresponding wavelengths to obtain second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths. Since the length of the obtained photoelectric plethysmogram cross-correlation function signal is one photoelectric plethysmogram template signal length less than the photoelectric plethysmogram signal, and the correlation coefficient is recorded from the start position of the signal period, preferably, the extraction device corrects the second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths, specifically as follows.

[0086] S5: performing signal division on the photoelectric plethysmogram signals according to a preset signal unit length to obtain a plurality of photoelectric plethysmogram unit signal sets of the plurality of wavelengths; and performing quality detection index calculation according to the first peak positioning data, the second peak positioning data, and the plurality of photoelectric plethysmogram unit signal sets of the plurality of wavelengths to obtain quality detection indexes of a plurality of photoelectric plethysmogram unit signals in the plurality of photoelectric plethysmogram unit signal sets of the plurality of wavelengths.

[0087] In the embodiment, the extraction device maps the plurality of target cross-correlation function peak points of the photoelectric plethysmogram cross-correlation function signal to the photoelectric plethysmogram signals of the corresponding wavelengths to obtain second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths. Since the length of the obtained photoelectric plethysmogram cross-correlation function signal is one photoelectric plethysmogram template signal length less than the photoelectric plethysmogram signal, and the correlation coefficient is recorded from the start position of the signal period, preferably, the extraction device corrects the second peak positioning data of the photoelectric plethysmogram signals of the plurality of wavelengths, specifically as follows.

[0088] Specifically, the extraction device adopts a 5s window as a signal unit length, cuts through a 1s sliding (80% overlapping window) mode to obtain a plurality of photoplethysmogram unit signals of the plurality of wavelengths, combines the plurality of photoplethysmogram unit signals of the same wavelength to construct the plurality of wavelength photoplethysmogram unit signal sets.

[0089] The extraction device calculates quality detection indexes according to the first peak positioning data, the second peak positioning data and the plurality of wavelength photoplethysmogram unit signal sets, obtains the quality detection indexes of the plurality of photoplethysmogram unit signals in the plurality of wavelength photoplethysmogram unit signal sets, and uses the quality detection indexes to perform signal extraction, thereby enhancing the time sequence characteristics of the signals and improving the low-quality detection capability, wherein the quality detection indexes include a positioning consistency quality index, an interval consistency quality index and a correlation fluctuation quality index.

[0090] Referring to Figure 5 , Figure 5 The flowchart of S5 in the quality evaluation method of the photoplethysmogram signal provided by an embodiment of the present application includes steps S51-S55, and specifically as follows:

[0091] S51: According to the first peak positioning data and the second peak positioning data, the first peak point and the second peak point under the same position index in the photoplethysmogram unit signal are subjected to consistency judgment, and consistent peak positioning data and inconsistent peak positioning data of the photoplethysmogram unit signal are obtained.

[0092] In the embodiment, the extraction device subjects the first peak point and the second peak point under the same position index in the photoplethysmogram unit signal to consistency judgment according to the first peak positioning data and the second peak positioning data, and obtains consistent peak positioning data and inconsistent peak positioning data of the photoplethysmogram unit signal.

[0093] Specifically, the extraction device subjects the position parameters of the first peak point and the second peak point under the same position index of the same photoplethysmogram unit signal to consistency judgment, obtains a plurality of consistent peak points and inconsistent peak points of the photoplethysmogram unit signal, combines the plurality of consistent peak points, combines the plurality of inconsistent peak points, and constructs the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmogram unit signal.

[0094] S52: obtaining the positioning consistency quality index of the photoplethysmographic unit signal according to the first peak positioning data, the second peak positioning data, the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmographic unit signal and a preset first index calculation algorithm.

[0095] The first index calculation algorithm is:

[0096]

[0097] In the formula, bSQI is the positioning consistency quality index, Rpeakslices_HE is the consistent peak positioning data, Rpeakslices_H is the first peak positioning data, Rpeakslices_E is the second peak positioning data, and len(·) is a length function indicating the number of peak points.

[0098] In this embodiment, the extraction device obtains the positioning consistency quality index of the photoplethysmographic unit signal according to the first peak positioning data, the second peak positioning data, the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmographic unit signal and a preset first index calculation algorithm.

[0099] S53: fusing the first peak positioning data and the second peak positioning data of the photoplethysmographic unit signal according to the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmographic unit signal to construct fusion peak positioning data of the photoplethysmographic unit signal.

[0100] In this embodiment, the extraction device fuses the first peak positioning data and the second peak positioning data of the photoplethysmographic unit signal according to the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmographic unit signal to construct fusion peak positioning data of the photoplethysmographic unit signal, wherein the fusion peak positioning data includes a plurality of fusion peak points.

[0101] Specifically, the extraction device determines whether there is an inconsistent peak point within an interval of 0.36s before and after a plurality of consistent peak points according to the consistent peak positioning data and the inconsistent peak positioning data of the same photoplethysmographic unit signal, and if not, the consistent peak point is taken as a fusion peak point.

[0102] If one or more inconsistent peak points exist within 0.36s before and after the consistent peak point, the extraction device respectively calculates the peak point interval and the peak point amplitude of the inconsistent peak point and the consistent peak point, obtains the variance of the peak point interval and the peak point amplitude of the consistent peak point and the variance of the peak point interval and the peak point amplitude of the inconsistent peak point, compares the consistent peak point and the inconsistent peak point based on the variance of the peak point interval and the peak point amplitude, if the consistent peak point is smaller than the inconsistent peak point, the consistent peak point is reserved as the fusion peak point, if there is an inconsistent peak point smaller than the consistent peak point, the inconsistent peak point closest to the consistent peak point and having the variance of the peak point interval and the peak point amplitude smaller than that of the consistent peak point is taken as the fusion peak point.

[0103] The extraction device determines whether a consistent peak point exists within 0.36s before and after the inconsistent peak point according to the consistent peak positioning data and the inconsistent peak positioning data of the same photoplethysmogram unit signal, if not, the inconsistent peak point is taken as the fusion peak point.

[0104] If one or more consistent peak points exist within 0.36s before and after the inconsistent peak point, the extraction device respectively calculates the peak point interval and the peak point amplitude of the inconsistent peak point and the consistent peak point, obtains the variance of the peak point interval and the peak point amplitude of the consistent peak point and the variance of the peak point interval and the peak point amplitude of the inconsistent peak point, compares the consistent peak point and the inconsistent peak point based on the variance of the peak point interval and the peak point amplitude, if the consistent peak point is smaller than the inconsistent peak point, the consistent peak point is reserved as the fusion peak point, if there is an inconsistent peak point smaller than the consistent peak point, the inconsistent peak point closest to the consistent peak point and having the variance of the peak point interval and the peak point amplitude smaller than that of the consistent peak point is taken as the fusion peak point.

[0105] S54: According to the fusion peak positioning data of the photoplethysmogram unit signal, the fusion peak interval data of the photoplethysmogram unit signal is calculated, and according to the fusion peak interval data of the photoplethysmogram unit signal and a preset second index calculation algorithm, the interval consistency quality index of the photoplethysmogram unit signal is obtained.

[0106] The second index calculation algorithm is:

[0107]

[0108] In the formula, iSQI is the interval consistency quality index, is the interval value in the first 15% of the fusion peak interval data, rank the interval values in the fusion peak interval data.

[0109] In this embodiment, the extraction device calculates fusion peak interval data of the photoplethysmographic unit signal according to the fusion peak positioning data of the photoplethysmographic unit signal, and obtains an interval consistency quality index of the photoplethysmographic unit signal according to the fusion peak interval data of the photoplethysmographic unit signal and a preset second index calculation algorithm.

[0110] S55: obtaining an average value and a standard deviation of amplitudes corresponding to the fusion peak positioning data of the photoplethysmographic unit signal as a first amplitude threshold and a second amplitude threshold, obtaining a number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold according to amplitudes of a plurality of fusion peak points in the fusion peak interval data of the photoplethysmographic unit signal, and obtaining a related fluctuation quality index of the photoplethysmographic unit signal according to the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold and a preset third index calculation algorithm.

[0111] In this embodiment, the extraction device obtains an average value and a standard deviation of amplitudes corresponding to the fusion peak positioning data of the photoplethysmographic unit signal as a first amplitude threshold and a second amplitude threshold, obtains a number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold according to amplitudes of a plurality of fusion peak points in the fusion peak interval data of the photoplethysmographic unit signal, and specifically, if the amplitude of the fusion peak point is greater than the first amplitude threshold, and the amplitude of the fusion peak point is greater than 3 times the second amplitude threshold, it is judged that the fusion peak point satisfies the first amplitude threshold and the second amplitude threshold, and the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold is obtained.

[0112] The extraction device obtains a related fluctuation quality index of the photoplethysmographic unit signal according to the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold and a preset third index calculation algorithm, wherein the third index calculation algorithm is:

[0113]

[0114] In the formula, vSQI is the related fluctuation quality index, s is the signal unit length, fs is the signal sampling rate, and H is the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold.

[0115] The quality detection index further includes a wave group morphology consistency quality index; please refer to Figure 6 ,Figure 6 The flowchart of step S5 of the quality evaluation method of the photoplethysmogram signal provided for another embodiment of the present application further includes steps S56-S58, and the details are as follows:

[0116] S56: Obtain the correlation coefficients of the several initial cross-correlation peak points of the photoplethysmogram unit signal, and average the peak values of all the initial cross-correlation peak points of the photoplethysmogram unit signal to obtain a reference wave group form consistency quality index.

[0117] In the present embodiment, the extraction device obtains the correlation coefficients of the several initial cross-correlation peak points of the photoplethysmogram unit signal, and the specific embodiments can refer to step S42, which will not be described here.

[0118] The extraction device averages the peak values of all the initial cross-correlation peak points of the photoplethysmogram unit signal to obtain a reference wave group form consistency quality index.

[0119] S57: According to the correlation coefficients of the correlation coefficients of the several initial cross-correlation peak points and the preset third correlation coefficient threshold, if the correlation coefficients of the correlation coefficients of the initial cross-correlation peak points are all greater than the third correlation coefficient threshold, the reference wave group form consistency quality index is taken as the wave group form consistency quality index of the photoplethysmogram unit signal.

[0120] In the present embodiment, the extraction device obtains the correlation coefficients of the correlation coefficients of the several initial cross-correlation peak points and the preset third correlation coefficient threshold, and if the correlation coefficients of the correlation coefficients of the initial cross-correlation peak points are all greater than the third correlation coefficient threshold, the reference wave group form consistency quality index is taken as the wave group form consistency quality index of the photoplethysmogram unit signal.

[0121] S58: If there is a correlation coefficient of the correlation coefficients of the initial cross-correlation peak points that is less than or equal to the third correlation coefficient threshold, the several initial cross-correlation peak points of the photoplethysmogram unit signal are divided into intervals according to the correlation coefficient, the proportion of the several intervals of the photoplethysmogram unit signal is obtained, the reference wave group form consistency quality index is adjusted according to the proportion of the several intervals of the photoplethysmogram unit signal and the preset product coefficient of the several intervals, and the wave group form consistency quality index of the photoplethysmogram unit signal is obtained.

[0122] If the correlation coefficient of the correlation coefficient of the initial cross-correlation peak point is less than or equal to the third correlation coefficient threshold, in this embodiment, the extraction device divides the plurality of initial cross-correlation peak points of the photoplethysmographic unit signal according to the correlation coefficient, obtains the proportion of a plurality of intervals of the photoplethysmographic unit signal, adjusts the reference wave group form consistency quality index according to the proportion of a plurality of intervals of the photoplethysmographic unit signal and a plurality of interval product coefficients, and obtains the wave group form consistency quality index of the photoplethysmographic unit signal.

[0123] Specifically, the extraction device obtains the product result of a plurality of intervals of the photoplethysmographic unit signal according to the proportion of a plurality of intervals of the photoplethysmographic unit signal and a plurality of interval product coefficients, subtracts the product result of a plurality of intervals of the photoplethysmographic unit signal from the same reference wave group form consistency quality index, and obtains a plurality of wave group form consistency quality indexes of the photoplethysmographic unit signal.

[0124] S6: Extracting a plurality of target photoplethysmographic unit signals from a plurality of wavelength photoplethysmographic unit signals according to the quality detection index, and combining the plurality of target photoplethysmographic unit signals as the photoplethysmographic wave signal extraction result of the user to be detected.

[0125] In this embodiment, the extraction device extracts a plurality of target photoplethysmographic unit signals from a plurality of wavelength photoplethysmographic unit signals according to the quality detection index, and combines the plurality of target photoplethysmographic unit signals as the photoplethysmographic wave signal extraction result of the user to be detected.

[0126] Based on the multiple wavelength photoplethysmographic wave signals of the user to be detected, a template is constructed to obtain a photoplethysmographic wave template signal; the photoplethysmographic wave template signal is used for signal division and quality detection index extraction, and a plurality of levels of information mining of the photoplethysmographic wave signal is performed to obtain more sufficient and rich feature information, so that more comprehensive and sufficient quality evaluation of the signal is realized. The extracted quality detection index is used to extract a target signal extraction result from the multiple wavelength photoplethysmographic wave signals, so that the accuracy of photoplethysmographic wave signal extraction is improved, and the photoplethysmographic wave signal is effectively controlled comprehensively and sufficiently.

[0127] Please refer to Figure 7 , Figure 7 The flowchart of S6 in the quality evaluation method of the photoplethysmographic wave signal provided in an embodiment of the present application includes steps S61-S63, which are as follows:

[0128] S61: Obtain a comprehensive quality detection index of the photoplethysmography unit signal according to the positioning consistency quality index, the interval consistency quality index, the correlation volatility quality index, the wave group form consistency quality index in the quality detection index, and the corresponding weight parameters; perform quality evaluation and division on the photoplethysmography unit signal according to the comprehensive quality detection index and a preset quality detection index threshold, and obtain a photoplethysmography unit signal set of several quality evaluation grades.

[0129] In the embodiment, the extraction device obtains a comprehensive quality detection index of the photoplethysmography unit signal according to the positioning consistency quality index, the interval consistency quality index, the correlation volatility quality index, the wave group form consistency quality index in the quality detection index, and the corresponding weight parameters, wherein the comprehensive quality detection index is:

[0130] SQI = w b · bSQI + w i · iSQI + w s · sSQI + w v · vSQI

[0131]

[0132] σ s = σ bSQI + σ iSQI + σ sSQI + σ vSQI

[0133] In the formula, SQI is the comprehensive quality detection index, w b is the weight parameter corresponding to the positioning consistency quality index, w i is the weight parameter corresponding to the interval consistency quality index, w s is the weight parameter corresponding to the correlation volatility quality index, w v is the weight parameter corresponding to the wave group form consistency quality index, σ bSQI is the standard deviation corresponding to the positioning consistency quality index, σ iSQI is the standard deviation corresponding to the interval consistency quality index, σ sSQI is the standard deviation corresponding to the correlation volatility quality index, σ vSQI is the standard deviation corresponding to the wave group form consistency quality index.

[0134] The extraction device performs quality evaluation division on the photoplethysmogram unit signals according to the comprehensive quality detection index and a preset quality detection index threshold, to obtain a plurality of photoplethysmogram unit signal sets of quality evaluation grades, wherein the quality evaluation grades include an excellent grade, a pending grade and a poor grade.

[0135] Specifically, the quality detection index threshold includes first, second and third quality detection index thresholds that decrease in turn. If the comprehensive quality detection index is greater than the first quality detection index threshold, the extraction device sets the quality evaluation grade of the photoplethysmogram unit signal as the excellent grade. If the comprehensive quality detection index is less than or equal to the first quality detection index threshold and greater than or equal to the second quality detection index threshold, the extraction device sets the quality evaluation grade of the photoplethysmogram unit signal as the pending grade. If the comprehensive quality detection index is less than the third quality detection index threshold, the extraction device sets the quality evaluation grade of the photoplethysmogram unit signal as the poor grade. A plurality of photoplethysmogram unit signals of the same quality evaluation grade are combined to construct a plurality of photoplethysmogram unit signal sets of quality evaluation grades.

[0136] S62: inputting the photoplethysmogram unit signal set of the pending grade into a preset neural network model for availability discrimination, to obtain availability discrimination results of a plurality of photoplethysmogram unit signals in the photoplethysmogram unit signal set of the pending grade; performing quality evaluation division on the plurality of photoplethysmogram unit signals in the photoplethysmogram unit signal set of the pending grade according to the availability discrimination results, to obtain a plurality of photoplethysmogram unit signal sets of quality evaluation grades.

[0137] In this embodiment, the extraction device inputs the photoplethysmogram unit signal set of the pending grade into a preset neural network model for availability discrimination, to obtain availability discrimination results of a plurality of photoplethysmogram unit signals in the photoplethysmogram unit signal set of the pending grade, wherein the availability discrimination results include available discrimination labels and unavailable discrimination labels.

[0138] The extraction device performs quality evaluation division on the plurality of photoplethysmogram unit signals in the photoplethysmogram unit signal set of the pending grade according to the availability discrimination results and the comprehensive quality detection index, to obtain a plurality of photoplethysmogram unit signal sets of quality evaluation grades.

[0139] Specifically, if the comprehensive quality detection index of the photoplethysmographic unit signal is greater than a preset fourth quality detection index threshold, and the availability discrimination result of the photoplethysmographic unit signal is an available discrimination label, the fourth quality detection index threshold is less than the first quality detection index threshold and greater than the second quality detection index threshold, the extraction device sets the quality evaluation level of the photoplethysmographic unit signal as an excellent level; if the comprehensive quality detection index of the photoplethysmographic unit signal is greater than the fourth quality detection index threshold, and the availability discrimination result of the photoplethysmographic unit signal is an unavailable discrimination label, the extraction device sets the quality evaluation level of the photoplethysmographic unit signal as a good level; if the comprehensive quality detection index of the photoplethysmographic unit signal is less than the fourth quality detection index threshold, and the availability discrimination result of the photoplethysmographic unit signal is an unavailable discrimination label, the extraction device sets the quality evaluation level of the photoplethysmographic unit signal as a poor level. The extraction device combines a plurality of photoplethysmographic unit signals of the same quality evaluation level to construct a plurality of photoplethysmographic unit signal sets of different quality evaluation levels.

[0140] S63: The photoplethysmographic unit signals in the excellent level photoplethysmographic unit signal set and the good level photoplethysmographic unit signal set are extracted as the target photoplethysmographic unit signals from the plurality of wavelength photoplethysmographic unit signal sets to obtain a plurality of target photoplethysmographic unit signals.

[0141] In the embodiment, the photoplethysmographic unit signals in the excellent level photoplethysmographic unit signal set and the good level photoplethysmographic unit signal set are extracted as the target photoplethysmographic unit signals from the plurality of wavelength photoplethysmographic unit signal sets to obtain a plurality of target photoplethysmographic unit signals.

[0142] Since the same low-quality PPG signal exists in multiple slice segments during the slicing process, in an optional embodiment, if the number of continuous photoplethysmographic unit signals in the poor level photoplethysmographic unit signal set does not meet the condition, the quality evaluation level of the number of photoplethysmographic unit signals is modified to the good level.

[0143] Please refer to Figure 8 , Figure 8 The structure diagram of the photoplethysmographic wave signal quality evaluation device provided by an embodiment of the present application, which can realize all or part of the photoplethysmographic wave signal quality evaluation device by software, hardware or a combination of both. The device 8 comprises:

[0144] The signal acquisition module 81 is configured to acquire photoelectric plethysmogram signals of several wavelengths of a user to be detected.

[0145] The signal division module 82 is configured to acquire first peak positioning data and valley positioning data of the photoelectric plethysmogram signals, divide the photoelectric plethysmogram signals according to the first valley positioning data, and acquire a set of photoelectric plethysmogram cycle signals of several wavelengths.

[0146] The signal template construction module 83 is configured to construct a template according to the set of photoelectric plethysmogram cycle signals of several wavelengths, and acquire a photoelectric plethysmogram template signal.

[0147] The template matching module 84 is configured to respectively perform template matching between the photoelectric plethysmogram template signal and the photoelectric plethysmogram signals of several wavelengths, and acquire second peak positioning data of the photoelectric plethysmogram signals of several wavelengths.

[0148] The quality detection index calculation module 85 is configured to divide the photoelectric plethysmogram signals according to a preset signal unit length, acquire a set of photoelectric plethysmogram unit signals of several wavelengths, and perform quality detection index calculation according to the first peak positioning data, the second peak positioning data, and the set of photoelectric plethysmogram unit signals of several wavelengths, to acquire quality detection indexes of the photoelectric plethysmogram unit signals of several wavelengths in the set of photoelectric plethysmogram unit signals of several wavelengths.

[0149] The signal extraction module 86 is configured to extract target photoelectric plethysmogram unit signals from the set of photoelectric plethysmogram unit signals of several wavelengths according to the quality detection indexes, and combine the target photoelectric plethysmogram unit signals as an extraction result of the photoelectric plethysmogram signals of the user to be detected.

[0150] In the embodiment of the present application, the signal acquisition module is used to obtain photoelectric plethysmogram signals of several wavelengths of the user to be detected; the signal division module is used to obtain first peak positioning data and valley positioning data of the photoelectric plethysmogram signals, and the photoelectric plethysmogram signals are divided according to the first valley positioning data to obtain a set of photoelectric plethysmogram cycle signals of several wavelengths; the signal template construction module is used to construct a template according to the set of photoelectric plethysmogram cycle signals of several wavelengths to obtain a photoelectric plethysmogram template signal; the template matching module is used to respectively match the photoelectric plethysmogram template signal with the photoelectric plethysmogram signals of several wavelengths to obtain second peak positioning data of the photoelectric plethysmogram signals of several wavelengths; the quality detection index calculation module is used to divide the photoelectric plethysmogram signals according to a preset signal unit length to obtain a set of photoelectric plethysmogram unit signals of several wavelengths; the quality detection index of a plurality of photoelectric plethysmogram unit signals in the set of photoelectric plethysmogram unit signals of several wavelengths is calculated according to the first peak positioning data, the second peak positioning data and the set of photoelectric plethysmogram unit signals of several wavelengths; the signal extraction module is used to extract a plurality of target photoelectric plethysmogram unit signals from the set of photoelectric plethysmogram unit signals of several wavelengths according to the quality detection index, and the plurality of target photoelectric plethysmogram unit signals are combined as a photoelectric plethysmogram signal extraction result of the user to be detected. The template is constructed based on the photoelectric plethysmogram signals of multiple wavelengths of the user to be detected to obtain a photoelectric plethysmogram template signal; the photoelectric plethysmogram signals are divided and the quality detection index is extracted by using the photoelectric plethysmogram template signal, the information of the photoelectric plethysmogram signals is mined in multiple levels to obtain more sufficient and rich feature information, the quality evaluation of the signals is more comprehensive and sufficient, the target signal extraction result is extracted from the photoelectric plethysmogram signals of multiple wavelengths by using the extracted quality detection index, the accuracy of the photoelectric plethysmogram signal extraction is improved, and the quality control of the photoelectric plethysmogram signals is comprehensive and sufficient.

[0151] Please refer to Figure 9 , Figure 9 The structural schematic diagram of the computer device provided in an embodiment of the present application, the computer device 9 comprises a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91; the computer device can store a plurality of instructions, the instructions are suitable for being loaded by the processor 91 and executing the method steps shown in the above Figures 1 to 7 , the specific execution process can be referred to the specific description shown in Figures 1 to 7 , which will not be described here.

[0152] The processor 91 can include one or more processing cores. The processor 91 connects various parts within the server by various interfaces and lines, performs various functions and processes data of the photoplethysmographic signal quality assessment device 8 by running or executing instructions, programs, code sets or instruction sets stored in the memory 92, and calling data in the memory 92. Optionally, the processor 91 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programable logic array (PLA). The processor 91 can be integrated with a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content displayed on the touch display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 91, but can be realized by a separate chip.

[0153] The memory 92 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 92 includes a non-transitory computer-readable storage medium. The memory 92 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 92 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 92 can also be at least one storage device located away from the aforementioned processor 91.

[0154] The embodiments of the present application also provide a storage medium, which can store a plurality of instructions. The instructions are suitable for being loaded and executed by a processor to perform the above-mentioned method steps. The specific execution process can refer to the specific description of the above-mentioned method steps, and will not be described here in detail. Figures 1 to 7 The specific execution process can refer to the specific description of the above-mentioned method steps, and will not be described here in detail. Figures 1 to 7 The specific execution process can refer to the specific description of the above-mentioned method steps, and will not be described here in detail.

[0155] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software. In addition, the specific name of each functional unit and module is only for the convenience of mutual distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can be referred to the corresponding process in the foregoing method embodiment, which will not be described here.

[0156] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0157] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the algorithm. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of the present application.

[0158] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented by other ways. For example, the above-mentioned apparatus / terminal device embodiments are only schematic, and the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between each other can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0159] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0160] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, 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 function unit.

[0161] The integrated module / unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form.

[0162] The present application is not limited to the above-described embodiments, and various modifications or changes can be made to the present application without departing from the spirit and scope of the present application. The present application is intended to include such modifications and changes if they fall within the scope of the claims and their equivalents.

Claims

1. A method of quality assessment of a photoplethysmographic pulse wave signal, characterized in that, The method comprises the following steps: Obtaining photoelectric plethysmogram signals of several wavelengths of a user to be detected; Obtaining first peak positioning data and valley positioning data of the photoelectric plethysmogram signals, dividing the photoelectric plethysmogram signals according to the valley positioning data, and obtaining a set of photoelectric plethysmogram cycle signals of several wavelengths; Template construction is performed according to the set of photoelectric plethysmogram cycle signals of several wavelengths, and a photoelectric plethysmogram template signal is obtained; Template matching is performed between the photoelectric plethysmogram template signal and the photoelectric plethysmogram signals of several wavelengths respectively, and second peak positioning data of the photoelectric plethysmogram signals of several wavelengths are obtained; The photoelectric plethysmogram signals are divided according to a preset signal unit length, a set of photoelectric plethysmogram unit signals of several wavelengths is obtained, quality detection indexes are calculated according to the first peak positioning data, the second peak positioning data and the set of photoelectric plethysmogram unit signals of several wavelengths, and quality detection indexes of a plurality of photoelectric plethysmogram unit signals in the set of photoelectric plethysmogram unit signals of several wavelengths are obtained, wherein the quality detection indexes include positioning consistency quality indexes, interval consistency quality indexes, correlation fluctuation quality indexes and wave group form consistency quality indexes; According to the quality detection indexes, a plurality of target photoelectric plethysmogram unit signals are extracted from the set of photoelectric plethysmogram unit signals of several wavelengths, and the plurality of target photoelectric plethysmogram unit signals are combined as a photoelectric plethysmogram signal extraction result of the user to be detected.

2. The method of claim 1, wherein: The first peak positioning data is fast peak positioning data obtained by using a fast peak searching method; The first peak positioning data and the valley positioning data of the photoelectric plethysmogram signals are obtained by comprising the following steps: The fast peak positioning data and the fast valley positioning data of the photoelectric plethysmogram signals are obtained by using a fast peak searching method; According to the peak values of a plurality of fast peak points in the fast peak positioning data and the valley values of a plurality of fast valley points in the fast valley positioning data, average screening processing is performed, a plurality of screening peak points and a plurality of screening valley points are obtained, the screening peak points are combined with a previous screening valley point, and a plurality of initial screening peak-valley point combinations are constructed; The peak-valley values of the plurality of initial screening peak-valley point combinations are obtained, a plurality of target screening peak-valley point combinations are obtained according to the peak-valley values and a preset peak-valley value depth threshold, the valley points in the target screening peak-valley point combinations are confirmed, and the valley positioning data of the photoelectric plethysmogram signals is constructed.

3. The method of claim 2, wherein: The set of photoelectric plethysmogram cycle signals comprises a plurality of photoelectric plethysmogram cycle signals; The template construction is performed according to the set of photoelectric plethysmogram cycle signals of several wavelengths, and a photoelectric plethysmogram template signal is obtained by comprising the following steps: Obtain the correlation coefficient of a plurality of photoplethysmogram cycle signals in the photoplethysmogram cycle signal set, and extract a plurality of candidate photoplethysmogram cycle signals from the photoplethysmogram cycle signal set of a plurality of wavelengths according to the correlation coefficient and a preset first correlation coefficient threshold. Obtain the cross-correlation coefficient between a plurality of candidate photoplethysmogram cycle signals of different wavelengths, and obtain a plurality of candidate photoplethysmogram cycle signals satisfying the cross-correlation coefficient threshold as sample photoplethysmogram template signals according to the cross-correlation coefficient and a preset cross-correlation coefficient threshold, to construct a template signal segment set. Construct an average photoplethysmogram template signal of the template signal segment set, calculate the standard deviation according to a plurality of sample photoplethysmogram template signals and the average photoplethysmogram template signal in the template signal segment set, obtain the standard deviation of a plurality of the sample photoplethysmogram template signals, obtain a plurality of sample photoplethysmogram template signals with the largest standard deviation corresponding to a preset signal number as candidate photoplethysmogram template signals according to the signal number, and perform average processing on a plurality of the candidate photoplethysmogram template signals to construct a photoplethysmogram template signal.

4. The method of claim 3, wherein the step of determining the quality of the PPG signal is performed by using a correlation between the PPG signal and a reference signal. The second peak positioning data of the photoplethysmogram signals of a plurality of wavelengths is obtained by performing template matching on the photoplethysmogram template signal and a plurality of photoplethysmogram signals of a plurality of wavelengths, including the steps of: Perform cross-correlation processing on the photoplethysmogram template signal and the photoplethysmogram signals of a plurality of wavelengths to obtain a plurality of photoplethysmogram cross-correlation function signals; Obtain a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal according to a preset peak threshold and a peak searching function, calculate the correlation coefficient of the initial cross-correlation peak points to obtain the correlation coefficient of a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal; Map the plurality of target cross-correlation function peak points of the photoplethysmogram cross-correlation function signal to the photoplethysmogram signals of the corresponding wavelengths to obtain the second peak positioning data of the photoplethysmogram signals of a plurality of wavelengths.

5. The method of claim 4, wherein: The first peak positioning data includes a plurality of first peak points, and the second peak positioning data includes a plurality of second peak points. The quality detection index calculation is performed according to the first peak positioning data, the second peak positioning data, and a plurality of photoplethysmogram unit signal sets of a plurality of wavelengths to obtain the quality detection index of a plurality of photoplethysmogram unit signals in a plurality of photoplethysmogram unit signal sets of a plurality of wavelengths, including the steps of: According to the first peak positioning data and the second peak positioning data, consistency of first peak points and second peak points at same position indexes in the photoplethysmographic unit signal is judged, and consistent peak positioning data and inconsistent peak positioning data of the photoplethysmographic unit signal are obtained; According to the first peak positioning data, the second peak positioning data, the consistent peak positioning data, the inconsistent peak positioning data of the photoplethysmographic unit signal and a preset first index calculation algorithm, a positioning consistency quality index of the photoplethysmographic unit signal is obtained, wherein the first index calculation algorithm is: wherein is a positioning consistency quality indicator, is consistent peak positioning data, is first peak positioning data, is second peak positioning data, is a length function to indicate the number of peak points. According to the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmographic unit signal, the first peak positioning data and the second peak positioning data of the photoplethysmographic unit signal are fused, and fusion peak positioning data of the photoplethysmographic unit signal is constructed, wherein the fusion peak positioning data includes several fusion peak points; According to the fusion peak positioning data of the photoplethysmographic unit signal, fusion peak interval data of the photoplethysmographic unit signal is calculated, and according to the fusion peak interval data of the photoplethysmographic unit signal and a preset second index calculation algorithm, an interval consistency quality index of the photoplethysmographic unit signal is obtained, wherein the second index calculation algorithm is: wherein is the inter- interval consistency quality indicator, is the 15th percentile of the fused peak interval data, is the 85th percentile of the fused peak interval data. The average value and the standard deviation of the amplitude corresponding to the fusion peak positioning data of the photoplethysmographic unit signal are obtained as a first amplitude threshold and a second amplitude threshold, the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold is obtained according to the amplitudes of the several fusion peak points in the fusion peak interval data of the photoplethysmographic unit signal, and according to the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold and a preset third index calculation algorithm, a related fluctuation quality index of the photoplethysmographic unit signal is obtained, wherein the third index calculation algorithm is: wherein is the correlation fluctuation quality indicator, s is the signal unit length, is the signal sampling rate, H is the number of fusion peak points satisfying the first amplitude threshold and the second amplitude threshold.

6. The method of claim 5, wherein the step of determining the quality of the PPG signal is performed by using a correlation between the PPG signal and a reference signal. According to the first peak positioning data, the second peak positioning data and the photoplethysmographic unit signal set of several wavelengths, quality detection index calculation is performed, and quality detection indexes of several photoplethysmographic unit signals in the photoplethysmographic unit signal set of several wavelengths are obtained, including the steps of: The correlation coefficients of the several initial cross-correlation peak points of the photoplethysmographic unit signal are obtained, and the peak values of all the initial cross-correlation peak points of the photoplethysmographic unit signal are averaged to obtain a reference wave group form consistency quality index; According to the correlation coefficients of the several initial cross-correlation peak points and a preset third correlation coefficient threshold, if the correlation coefficients of the initial cross-correlation peak points are all greater than the third correlation coefficient threshold, the reference wave group form consistency quality index is taken as a wave group form consistency quality index of the photoplethysmographic unit signal; If the correlation coefficient of the initial cross-correlation peak point is less than or equal to the third correlation coefficient threshold, a plurality of initial cross-correlation peak points of the photoplethysmographic unit signal are divided into intervals according to the correlation coefficient, and a proportion of a plurality of intervals of the photoplethysmographic unit signal is obtained; and the reference wave group shape consistency quality index is adjusted according to the proportion of the plurality of intervals of the photoplethysmographic unit signal and a plurality of interval product coefficients, so as to obtain a wave group shape consistency quality index of the photoplethysmographic unit signal.

7. The method for quality assessment of photoplethysmography (PPG) signals according to claim 6, characterized in that, The extracting a plurality of target photoplethysmographic unit signals from the plurality of wavelength photoplethysmographic unit signal sets according to the quality detection indexes comprises the following steps: According to the positioning consistency quality index, the interval consistency quality index, the correlation fluctuation quality index, the wave group shape consistency quality index and the corresponding weight parameters in the quality detection indexes, a comprehensive quality detection index of the photoplethysmographic unit signal is obtained, and the quality of the photoplethysmographic unit signal is evaluated and divided according to the comprehensive quality detection index and a preset quality detection index threshold, so as to obtain a plurality of quality evaluation level photoplethysmographic unit signal sets, wherein the quality evaluation levels include an excellent level, a pending level and a poor level; The pending level photoplethysmographic unit signal set is input into a preset neural network model for availability discrimination, and an availability discrimination result of a plurality of photoplethysmographic unit signals in the pending level photoplethysmographic unit signal set is obtained; and the plurality of photoplethysmographic unit signals in the pending level photoplethysmographic unit signal set are evaluated and divided according to the availability discrimination result and the comprehensive quality detection index, so as to obtain a plurality of quality evaluation level photoplethysmographic unit signal sets, wherein the quality evaluation levels include a good level; The photoplethysmographic unit signals in the excellent level photoplethysmographic unit signal set and the good level photoplethysmographic unit signal set are taken as the target photoplethysmographic unit signals, and a plurality of target photoplethysmographic unit signals are extracted from the plurality of wavelength photoplethysmographic unit signal sets.

8. A device for quality assessment of a photoplethysmographic pulse wave signal, characterized in that Comprise: A signal acquisition module is configured to obtain a plurality of wavelength photoplethysmographic wave signals of a user to be detected; A signal division module is configured to obtain first peak positioning data and valley positioning data of the photoplethysmographic wave signals, divide the photoplethysmographic wave signals according to the valley positioning data, and obtain a plurality of wavelength photoplethysmographic wave cycle signal sets; A signal template construction module is configured to construct a template according to the plurality of wavelength photoplethysmographic wave cycle signal sets, and obtain a photoplethysmographic wave template signal; A template matching module is configured to respectively match the photoplethysmographic wave template signal with the plurality of wavelength photoplethysmographic wave signals, and obtain second peak positioning data of the plurality of wavelength photoplethysmographic wave signals; The quality detection index calculation module is configured to perform signal division on the photoplethysmogram signal according to a preset signal unit length, to obtain a plurality of wavelength photoplethysmogram unit signal sets; and to perform quality detection index calculation according to the first peak value positioning data, the second peak value positioning data, and the plurality of wavelength photoplethysmogram unit signal sets, to obtain quality detection indexes of a plurality of photoplethysmogram unit signals in the plurality of wavelength photoplethysmogram unit signal sets, wherein the quality detection indexes include positioning consistency quality indexes, interval consistency quality indexes, correlation fluctuation quality indexes, and wave group form consistency quality indexes. The signal extraction module is configured to extract a plurality of target photoplethysmogram unit signals from the plurality of wavelength photoplethysmogram unit signal sets according to the quality detection indexes, and to combine the plurality of target photoplethysmogram unit signals as a photoplethysmogram signal extraction result of the user to be detected.

9. A computer device, comprising: The computer program is executed by the processor to implement the steps of the photoplethysmogram signal quality evaluation method according to any one of claims 1 to 7. The storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the photoplethysmogram signal quality evaluation method according to any one of claims 1 to 7.

10. A storage medium characterized by: ​

Images