Quality evaluation method and device for photoelectric volume pulse wave signals and computer equipment

Abstract

The invention relates to the technical field of signal processing, in particular to a photoelectric volume pulse wave signal quality evaluation method and device, computer equipment and a storage medium, template construction is performed based on photoelectric volume pulse wave signals of multiple wavelengths of a to-be-detected user, and photoelectric volume pulse wave template signals are obtained; signal division and quality detection index extraction are carried out by utilizing a photoelectric volume pulse wave template signal, multi-level information mining is carried out on the photoelectric volume pulse wave signal, more sufficient and abundant feature information is obtained, more comprehensive and sufficient signal quality evaluation is realized, and the quality detection accuracy is improved by utilizing the extracted quality detection index. The target signal extraction result is extracted from the photoelectric volume pulse wave signals with the multiple wavelengths, the photoelectric volume pulse wave signal extraction precision is improved, and comprehensive and sufficient quality control is effectively carried out on the photoelectric volume pulse wave signals.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and in particular to a quality assessment method, device, computer equipment and storage medium for a photoplethysmogram signal. Background Art

[0002] With the development and popularization of smart wearable and home devices, the use of photoplethysmography (PPG) signals for heart rate and blood oxygen measurement is becoming more and more popular. PPG signal is an important biological signal for non-invasive physiological monitoring. It measures the changes in light reflection on the skin surface through a photoelectric sensor and captures the fluctuations of blood passing through the skin blood vessels when the heart beats. In the process of using PPG signals to monitor heart rate and blood oxygen, the quality of the signal directly determines the accuracy of the heart rate and blood oxygen values. Therefore, it is very necessary to detect the availability of the signal.

[0003] The current technical solution for PPG signal availability detection is to mainly use PPG time domain, frequency domain and other characteristics to construct indicators, and perform availability detection based on the constructed indicators. These characteristics are all calculated through statistics. The indicators constructed based on these characteristics may not be sensitive enough for specific application scenarios, and cannot fully reflect the quality of the signal. The generalization ability is limited, and it is difficult to conduct comprehensive and sufficient quality control of PPG signals. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a quality assessment method, device, equipment and storage medium for a photoplethysmogram signal, to construct a template based on photoplethysmogram signals of multiple wavelengths of a user to be detected, and to obtain a photoplethysmogram template signal; to use the photoplethysmogram template signal to perform signal division and quality detection index extraction, to perform multi-level information mining on the photoplethysmogram signal, to obtain more sufficient and rich feature information, to achieve a more comprehensive and sufficient signal quality assessment, to use the extracted quality detection index to extract a target signal extraction result from the photoplethysmogram signals of multiple wavelengths, to improve the accuracy of photoplethysmogram signal extraction, and to effectively perform comprehensive and sufficient quality control on the photoplethysmogram signal.

[0005] In a first aspect, an embodiment of the present application provides a method for evaluating the quality of a photoplethysmography signal, comprising the following steps:

[0006] Obtaining photoplethysmographic signals of several wavelengths of the user to be detected;

[0007] Obtaining first peak location data and valley location data of the photoplethysmogram signal, and dividing the photoplethysmogram signal according to the first valley location data to obtain a photoplethysmogram periodic signal set of several wavelengths;

[0008] A template is constructed according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal;

[0009] According to the photoplethysmography template signal, template matching is performed with photoplethysmography signals of several wavelengths respectively to obtain second peak location data of the photoplethysmography signals of several wavelengths;

[0010] According to a preset signal unit length, the photoplethysmogram signal is divided to obtain a photoplethysmogram unit signal set of several wavelengths; according to the first peak location data, the second peak location data and the photoplethysmogram unit signal set of several wavelengths, a quality detection index is calculated to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths;

[0011] According to the quality detection index, a plurality of target photoplethysmogram unit signals are extracted from the photoplethysmogram unit signals of a plurality of wavelengths, and the plurality of target photoplethysmogram unit signals are combined as the photoplethysmogram signal extraction result of the user to be detected.

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

[0013] A signal acquisition module, used to obtain photoplethysmographic signals of several wavelengths of the user to be detected;

[0014] A signal division module, used to obtain first peak location data and valley location data of the photoplethysmogram signal, and divide the photoplethysmogram signal according to the first valley location data to obtain a photoplethysmogram periodic signal set of several wavelengths;

[0015] A signal template building module, used to build a template according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal;

[0016] A template matching module, used to perform template matching with photoplethysmography signals of several wavelengths according to the photoplethysmography template signal, to obtain second peak location data of the photoplethysmography signals of several wavelengths;

[0017] A quality detection index calculation module is used to divide the photoplethysmogram signal according to a preset signal unit length to obtain a photoplethysmogram unit signal set of several wavelengths; perform quality detection index calculation according to the first peak location data, the second peak location data and the photoplethysmogram unit signal set of several wavelengths to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths;

[0018] The signal extraction module is used to extract a plurality of target photoplethysmogram unit signals from the photoplethysmogram unit signals of a plurality of wavelengths according to the quality detection index, and combine the plurality of target photoplethysmogram unit signals as the 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, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for evaluating the quality of the photoplethysmography signal as described in the first aspect are implemented.

[0020] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for quality assessment of a photoplethysmographic signal as described in the first aspect.

[0021] In an embodiment of the present application, a method, device, equipment and storage medium for evaluating the quality of a photoplethysmogram signal are provided. A template is constructed based on photoplethysmogram signals of multiple wavelengths of a user to be detected to obtain a photoplethysmogram template signal. The photoplethysmogram template signal is used to perform signal division and quality detection index extraction, and multi-level information mining is performed on the photoplethysmogram signal to obtain more sufficient and rich feature information, thereby achieving a more comprehensive and sufficient signal quality evaluation. The extracted quality detection index is used to extract a target signal extraction result from the photoplethysmogram signals of multiple wavelengths, thereby improving the accuracy of photoplethysmogram signal extraction and effectively performing comprehensive and sufficient quality control on the photoplethysmogram signal.

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

[0023] Figure 1 A schematic diagram of a process for evaluating the quality of a photoplethysmography signal provided by an embodiment of the present application;

[0024] Figure 2A schematic diagram of the process of S2 in the quality assessment method of a photoplethysmography signal provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of the process of S3 in the quality assessment method of a photoplethysmography signal provided in one embodiment of the present application;

[0026] Figure 4 A schematic diagram of the process of S4 in the quality assessment method of a photoplethysmography signal provided in one embodiment of the present application;

[0027] Figure 5 A schematic diagram of the process of S5 in the quality assessment method of a photoplethysmography signal provided in one embodiment of the present application;

[0028] Figure 6 A schematic diagram of the flow chart of S5 in the quality assessment method of a photoplethysmography signal provided in another embodiment of the present application;

[0029] Figure 7 A schematic diagram of the process of S6 in the quality assessment method of a photoplethysmography signal provided in one embodiment of the present application;

[0030] Figure 8 A schematic diagram of the structure of a quality assessment device for a photoplethysmography signal provided in one embodiment of the present application;

[0031] Fig. 9 A schematic diagram of the structure of a computer device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0033] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0034] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0035] See also Figure 1 , Figure 1 A flow chart of a method for evaluating the quality of a photoplethysmography signal provided in one embodiment of the present application, the method comprising the following steps:

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

[0037] The execution subject of the photoplethysmography signal quality assessment method is an extraction device of the photoplethysmography signal quality assessment method (hereinafter referred to as extraction device). In an optional embodiment, the extraction device can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0038] In this embodiment, the extraction device can obtain the photoelectric volumetric pulse wave signals of several wavelengths of the user to be detected by querying in a preset database, or it can realize non-perceptible collection by reflectively collecting the photoelectric volumetric pulse wave signals of several wavelengths of the user to be detected through several preset PPG signal detection probes, such as red light detection probes and infrared light detection probes. In the application scenario of this embodiment, by setting the corresponding PPG signal detection probes on the smart toilet mat, the initial photoelectric volumetric pulse wave signal of the buttocks of the user to be detected is collected during the user to be detected using the toilet.

[0039] Since the baseline of the collected initial photoplethysmogram signal of the buttocks usually contains a large number of burrs, it is necessary to filter to remove power frequency noise and baseline drift. The extraction device filters the initial photoplethysmogram signals of the several wavelengths to obtain the initial photoplethysmogram signals of the several wavelengths after filtering as the photoplethysmogram signals of the several wavelengths of the user to be detected.

[0040] Specifically, after the signal acquisition is completed, the extraction equipment uses a 200-order 0.3Hz cutoff frequency low-pass filter to filter out the baseline, then uses a median filter to smooth the signal, and finally uses a 1-5Hz bandpass filter to filter out power frequency interference and high-frequency noise to obtain photoplethysmogram signals of several wavelengths after filtering. It can effectively identify low-quality fragments formed by motion artifacts and noise interference in the data acquisition process, perform filtering, improve the accuracy of signal extraction, and facilitate effective quality control of photoplethysmogram signals.

[0041] S2: Obtain first peak location data and valley location data of the photoplethysmogram signal, and divide the photoplethysmogram signal according to the first valley location data to obtain a set of photoplethysmogram periodic signals of several wavelengths.

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

[0043] The extraction device divides the photoelectric volumetric pulse wave signal according to several valley points in the first valley positioning data to obtain a photoelectric volumetric pulse wave periodic signal set of several wavelengths, wherein the photoelectric volumetric pulse wave periodic signal set includes several photoelectric volumetric pulse wave periodic signals.

[0044] Specifically, the first peak location data is fast peak location data obtained by using a fast peak search method, see Figure 2 , Figure 2 The flowchart of S2 in the quality assessment method of the photoplethysmography signal provided in one embodiment of the present application includes steps S21 to S23, which are as follows:

[0045] S21: using a fast peak finding method to obtain fast peak location data and fast valley location data of the photoplethysmogram signal.

[0046] In order to reduce the interference of PPG dicrotic waves on peak and valley positioning, in this embodiment, the extraction device uses a median filter to perform median filtering on the photoelectric volumetric pulse wave signal, and uses a fast peak finding method to perform peak positioning and valley positioning on the photoelectric volumetric pulse wave signal after median filtering, so as to obtain fast peak positioning data and fast valley positioning data of the photoelectric volumetric pulse wave signal.

[0047] In an optional embodiment, the extraction device corrects the peak point in the fast peak location data. Specifically, the extraction device searches for the local maximum value in the step size interval around the peak point according to the step size of the median filter, and determines that the point is the corrected peak point.

[0048] S22: Perform average screening processing according to the peak values ​​of several fast peak points in the fast peak positioning data and the valley values ​​of several fast valley points in the fast valley positioning data to obtain several screened peak points and several screened valley points, combine the screened peak points with the previous screened valley points, and construct several initial screened peak-valley point combinations.

[0049] In this embodiment, the extraction device performs average screening processing based on the peak values ​​of several fast peak points in the fast peak positioning data and the valley values ​​of several fast valley points in the fast valley positioning data to obtain several screened peak points and several screened valley points, and combines the screened peak points with the previous screened valley points to construct several initial screened peak and valley point combinations.

[0050] Specifically, the extraction device calculates the first fast average peak value and the first fast average valley value respectively according to the peak values ​​of several fast peak points in the fast peak positioning data and the valley values ​​of several fast valley points in the fast valley positioning data, and selects peak points less than twice the first fast average peak value from the fast peak positioning data according to the first fast average peak value and the first fast average valley value to obtain several selected peak points, and selects valley points less than twice the first fast average valley value from the fast valley positioning data to obtain several candidate valley points, so as to exclude the fragments caused by motion artifacts or sensor shedding to the signal.

[0051] S23: Obtain peak-valley values ​​of several initial screening peak-valley value point combinations, obtain several target screening peak-valley value point combinations based on the peak-valley values ​​and a preset peak-valley value depth threshold, confirm the valley points in the target screening peak-valley value point combinations, and construct valley value positioning data of the photoelectric volumetric pulse wave signal.

[0052] In this embodiment, the extraction device obtains the peak and valley values ​​of several initial screening peak and valley value point combinations, obtains several target screening peak and valley value point combinations based on the peak and valley values ​​and the preset peak and valley value depth thresholds, confirms the valley points in the target screening peak and valley value point combinations, and constructs the valley value positioning data of the photoelectric volumetric pulse wave signal.

[0053] Specifically, the extraction device calculates the second fast average peak value and the second fast average valley value according to the peak values ​​of several candidate peak points and the valley values ​​of several candidate valley points, respectively, and calculates the average peak-valley value depth according to the second fast average peak value and the second fast average valley value. The extraction device obtains the peak-valley values ​​of several initial screening peak-valley value point combinations, and compares the several initial screening peak-valley value point combinations one by one according to the peak-valley values ​​and the preset peak-valley value depth threshold. If the peak-valley value of the currently compared initial screening peak-valley value point combination satisfies, that is, is greater than or equal to, the peak-valley value depth threshold, the initial screening peak-valley value point combination is used as the target screening peak-valley value point combination, and the peak-valley value of the initial screening peak-valley value point combination is updated to the preset dynamic peak-valley value depth threshold.

[0054] If the peak-valley value of the next compared initial screening peak-valley value point combination is less than the peak-valley value depth threshold, the peak-valley value of the initial screening peak-valley value point combination is compared with the previous dynamic peak-valley value depth threshold that meets the peak-valley value depth threshold. If it meets, that is, is greater than or equal to the dynamic peak-valley value depth threshold, the initial screening peak-valley value point combination is used as the target screening peak-valley value point combination, and several target screening peak-valley value point combinations are obtained. The valley points in the target screening peak-valley value point combination are confirmed, and the valley value positioning data of the photoelectric volumetric pulse wave signal is constructed.

[0055] In an optional embodiment, the extraction device corrects the valley point in the valley positioning data of the photoplethysmogram signal. Specifically, the extraction device searches for the local maximum value within the step size interval around the above-mentioned valley point according to the step size of the median filter, and determines that the point is the corrected valley point.

[0056] S3: constructing a template according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal.

[0057] In this embodiment, the extraction device constructs a template based on a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal.

[0058] See also Figure 3 , Figure 3 The flowchart of S3 in the quality assessment method of the photoplethysmography signal provided in one embodiment of the present application includes steps S31 to S33, which are specifically as follows:

[0059] S31: Obtain the correlation coefficient of several photoelectric volumetric pulse wave periodic signals in the photoelectric volumetric pulse wave periodic signal set, and extract several candidate photoelectric volumetric pulse wave periodic signals from the photoelectric volumetric pulse wave periodic signal set of several wavelengths according to the correlation coefficient and a preset first correlation coefficient threshold, to obtain several candidate photoelectric volumetric pulse wave periodic signals of several wavelengths.

[0060] In this embodiment, the extraction device obtains the correlation coefficient of several photoplethysmographic periodic signals in the photoplethysmographic periodic signal set, wherein the correlation coefficient includes a forward correlation coefficient and a backward correlation coefficient, which are specifically as follows:

[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 is the forward correlation coefficient, r r is the backward correlation coefficient, x ppg (n-1) is the n-1th photoplethysmographic cycle signal, x ppg (n) is the nth photoplethysmographic cycle signal, is the n+1th photoplethysmographic cycle signal, and corrcoef[·] is the correlation coefficient calculation function.

[0064] The extraction device uses the correlation coefficient and a preset first correlation coefficient threshold value, and if the forward correlation coefficient and the backward correlation coefficient of the photoplethysmogram periodic signal are both greater than the first correlation coefficient threshold value, the photoplethysmogram periodic signal is used as a candidate photoplethysmogram periodic signal, and several candidate photoplethysmogram periodic signals are extracted from the photoplethysmogram periodic signals of several wavelengths to obtain several candidate photoplethysmogram periodic signals of several wavelengths.

[0065] S32: Obtain a mutual correlation coefficient between several candidate photoplethysmogram periodic signals of different wavelengths, and based on the mutual correlation coefficient and a preset mutual correlation coefficient threshold, obtain several candidate photoplethysmogram periodic signals that meet the mutual correlation coefficient threshold as sample photoplethysmogram template signals to construct a template signal segment set.

[0066] In this embodiment, the extraction device obtains the cross-correlation coefficient between several candidate photoplethysmogram periodic signals of different wavelengths, and based on the cross-correlation coefficient and a preset cross-correlation coefficient threshold, obtains several candidate photoplethysmogram periodic signals that meet the cross-correlation coefficient threshold as sample photoplethysmogram template signals, 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 based on a number of sample photoplethysmogram template signals and an average photoplethysmogram template signal in the template signal segment set, obtaining the standard deviation of the number of sample photoplethysmogram template signals, obtaining a number of sample photoplethysmogram template signals with the largest standard deviation that matches the number of signals based on a preset number of signals as candidate photoplethysmogram template signals, performing averaging processing based on the number of candidate photoplethysmogram template signals, and constructing a photoplethysmogram template signal.

[0068] In this 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 the average photoplethysmogram template signal, n is the number of sample photoplethysmogram template signals in the template signal segment set, X m (i) is the i-th sample photoplethysmogram template signal in the template signal segment set, peak is the peak point in the sample photoplethysmogram template signal, L model is the template signal length.

[0071] The extraction device calculates the standard deviation of the sample photoplethysmogram template signals and the average photoplethysmogram template signal in the template signal segment set to obtain the standard deviation of the sample photoplethysmogram template signals, wherein the standard deviation is:

[0072]

[0073] Where σ is the standard deviation.

[0074] The extraction device obtains several sample photoplethysmogram template signals with the largest standard deviation that match the preset number of signals as candidate photoplethysmogram template signals according to the preset number of signals, and constructs a photoplethysmogram template signal by averaging the several candidate photoplethysmogram template signals.

[0075] S4: performing template matching with photoplethysmography signals of several wavelengths according to the photoplethysmography template signal to obtain second peak location data of the photoplethysmography signals of several wavelengths.

[0076] In this embodiment, the extraction device performs template matching with photoplethysmography signals of several wavelengths according to the photoplethysmography template signal to obtain second peak location data of the photoplethysmography signals of several wavelengths.

[0077] See also Figure 4 , Figure 4 The flowchart of S4 in the quality assessment method of the photoplethysmography signal provided in one embodiment of the present application includes steps S41 to S43, which are specifically as follows:

[0078] S41: performing cross-correlation processing on the photoplethysmography template signal and the photoplethysmography signals of the plurality of wavelengths respectively, to obtain photoplethysmography 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 a preset step length, so as to obtain photoplethysmogram cross-correlation function signals of the plurality of wavelengths.

[0080] S42: According to a preset peak threshold and a peak-finding function, a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal are obtained, and correlation coefficients of the initial cross-correlation peak points are calculated to obtain correlation coefficients of the plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal.

[0081] In this embodiment, the extraction device obtains several initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal according to a preset peak threshold and a peak-finding function, calculates the correlation coefficients of the initial cross-correlation peak points, and obtains the correlation coefficients of the several initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal.

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

[0083] In this embodiment, the extraction device uses the correlation coefficient of several initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal and a preset second correlation coefficient threshold. If the correlation coefficient of the initial cross-correlation peak point is greater than the second correlation coefficient threshold, the initial cross-correlation peak point is used as the target cross-correlation function peak point to obtain several target cross-correlation function peak points of the photoplethysmogram cross-correlation function signal.

[0084] The extraction device maps several target cross-correlation function peak points of the photoplethysmogram cross-correlation function signal to the photoplethysmogram signal of the corresponding wavelength to obtain the second peak location data of the photoplethysmogram signal of the several wavelengths. Since the length of the obtained photoplethysmogram cross-correlation function signal is less than the photoplethysmogram signal by one photoplethysmogram template signal length, and the calculated correlation coefficient is recorded at the starting position of the signal cycle, preferably, the extraction device corrects the second peak location data of the photoplethysmogram signal of the several wavelengths, specifically as follows:

[0085] The extraction device performs offset correction by shifting each peak point in the second peak positioning data rightward by half the template length according to the length of the photoplethysmogram template signal. Since the peak point of the systolic period of the PPG signal is located in the left half cycle of the entire PPG signal, after the offset correction, a local maximum peak point is searched to the left of each offset-corrected peak point, and the local maximum peak point is locally corrected again to obtain the second peak positioning data of the corrected photoplethysmogram signal of several wavelengths, wherein the second peak positioning data includes several second peak points.

[0086] S5: According to a preset signal unit length, the photoplethysmogram signal is divided to obtain a photoplethysmogram unit signal set of several wavelengths; according to the first peak positioning data, the second peak positioning data and the photoplethysmogram unit signal set of several wavelengths, quality detection index calculation is performed to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths.

[0087] In this embodiment, the extraction device divides the photoplethysmography signal according to a preset signal unit length to obtain a photoplethysmography unit signal set of several wavelengths.

[0088] Specifically, the extraction device uses a 5s window as the signal unit length, and cuts it by 1s sliding (80% overlapping window) to obtain several photoplethysmogram unit signals of several wavelengths, and combines several photoplethysmogram unit signals of the same wavelength to construct a set of photoplethysmogram unit signals of several wavelengths.

[0089] The extraction device calculates quality detection indicators based on the first peak positioning data, the second peak positioning data and a photoplethysmogram unit signal set of several wavelengths, and obtains quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths for signal extraction, thereby enhancing the timing characteristics of the signal and improving the low-quality detection capability, wherein the quality detection indicators include a positioning consistency quality indicator, an interval consistency quality indicator and a related volatility quality indicator.

[0090] See also Figure 5 , Figure 5 The flowchart of S5 in the quality assessment method of the photoplethysmography signal provided in one embodiment of the present application includes steps S51 to S55, which are specifically as follows:

[0091] S51: Based on the first peak positioning data and the second peak positioning data, consistency judgment is performed on the first peak point and the second peak point under the same position index in the photoplethysmography unit signal to obtain consistent peak positioning data and inconsistent peak positioning data of the photoplethysmography unit signal.

[0092] In this embodiment, the extraction device performs consistency judgment on the first peak point and the second peak point under the same position index in the photoplethysmogram unit signal based on 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 makes a consistency judgment on the position parameters of the first peak point and the second peak point under the same position index of the same photoplethysmogram unit signal, obtains a number of consistent peak points and inconsistent peak points of the photoplethysmogram unit signal, combines a number of consistent peak points, combines a number of inconsistent peak points, and constructs consistent peak positioning data and inconsistent peak positioning data of the photoplethysmogram unit signal.

[0094] S52: Obtain the positioning consistency quality index of the photoplethysmography 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 photoplethysmography unit signal and a preset first index calculation algorithm.

[0095] The first indicator calculation algorithm is:

[0096]

[0097] Wherein, 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 the length function to indicate the number of peak points.

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

[0099] S53: According to the consistent peak positioning data and the inconsistent peak positioning data of the photoplethysmography unit signal, the first peak positioning data and the second peak positioning data of the photoplethysmography unit signal are fused to construct the fused peak positioning data of the photoplethysmography unit signal.

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

[0101] Specifically, the extraction device determines whether there are inconsistent peak points 0.36s before and after a number of consistent peak points based on the consistent peak positioning data and inconsistent peak positioning data of the same photoplethysmogram unit signal. If not, the consistent peak point is used as the fusion peak point.

[0102] If there are one or more inconsistent peak points within an interval of 0.36s before and after the consistent peak point, the extraction device calculates the peak point interval and peak point amplitude of the consistent peak point and the inconsistent peak point respectively, 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, and compares the consistent peak point with the inconsistent peak point based on the variance of the peak point interval and the peak point amplitude; if the consistent peak points are all smaller than the inconsistent peak points, the consistent peak point is retained as a fused peak point; if there is an inconsistent peak point smaller than the consistent peak point, the inconsistent peak point that is closest to the consistent peak point and whose variance of the peak point interval and the peak point amplitude is smaller than the consistent peak point is taken as the fused peak point.

[0103] The extraction device determines whether there is a consistent peak point with an interval of 0.36s before and after a number of inconsistent peak points based on the consistent peak positioning data and the inconsistent peak positioning data of the same photoplethysmogram unit signal. If not, the inconsistent peak point is used as the fusion peak point.

[0104] If there are one or more consistent peak points within an interval of 0.36s before and after the inconsistent peak point, the extraction device calculates the peak point interval and peak point amplitude of the inconsistent peak point and the consistent peak point respectively, obtains the variance of the peak point interval and the peak point amplitude of the inconsistent peak point and the variance of the peak point interval and the peak point amplitude of the consistent peak point, and compares the inconsistent peak point with the consistent peak point based on the variance of the peak point interval and the peak point amplitude. If the inconsistent peak points are all smaller than the consistent peak point, the inconsistent peak point is retained as a fused peak point. If there is a consistent peak point that is smaller than the inconsistent peak point, the consistent peak point that is closest to the inconsistent peak point and whose variance of the peak point interval and the peak point amplitude is smaller than the inconsistent peak point is used as the fused peak point.

[0105] S54: Calculate the fused peak interval data of the photoplethysmogram unit signal based on the fused peak positioning data of the photoplethysmogram unit signal, and obtain the interval consistency quality index of the photoplethysmogram unit signal based on the fused peak interval data of the photoplethysmogram unit signal and a preset second index calculation algorithm.

[0106] The second indicator calculation algorithm is:

[0107]

[0108] Wherein, iSQI is the interval consistency quality index, is the interval value of the top 15% in the fused peak interval data, The interval values ​​are the top 85% of the fused peak interval data.

[0109] In this embodiment, the extraction device calculates the fused peak interval data of the photoplethysmogram unit signal based on the fused peak positioning data of the photoplethysmogram unit signal, and obtains the interval consistency quality index of the photoplethysmogram unit signal based on the fused peak interval data of the photoplethysmogram unit signal and a preset second index calculation algorithm.

[0110] S55: Obtain the amplitude mean value and amplitude standard deviation corresponding to the fused peak positioning data of the photoplethysmogram unit signal as the first amplitude threshold and the second amplitude threshold, and obtain the number of fused peak points that meet the first amplitude threshold and the second amplitude threshold according to the amplitudes of several fused peak points in the fused peak interval data of the photoplethysmogram unit signal; and obtain the relevant volatility quality index of the photoplethysmogram unit signal according to the number of fused peak points that meet the first amplitude threshold and the second amplitude threshold and a preset third index calculation algorithm.

[0111] In this embodiment, the extraction device obtains the amplitude average value and the amplitude standard deviation corresponding to the fused peak positioning data of the photoplethysmogram unit signal as the first amplitude threshold and the second amplitude threshold, and obtains the number of fused peak points that meet the first amplitude threshold and the second amplitude threshold according to the amplitudes of several fused peak points in the fused peak interval data of the photoplethysmogram unit signal. Specifically, if the amplitude of the fused peak point is greater than the first amplitude threshold, and the amplitude of the fused peak point is greater than 3 times the second amplitude threshold, then it is judged that the fused peak point meets the first amplitude threshold and the second amplitude threshold, and the number of fused peak points that meet the first amplitude threshold and the second amplitude threshold is obtained.

[0112] The extraction device obtains the relevant volatility quality index of the photoplethysmogram unit signal according to the number of fusion peak points that meet 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 correlation volatility quality index, s is the signal unit length, fs is the signal sampling rate, and H is the number of fusion peak points that meet the first amplitude threshold and the second amplitude threshold.

[0115] The quality detection index also includes the wave group morphology consistency quality index; please refer to Figure 6 , Figure 6 The flowchart of S5 in the quality assessment method of the photoplethysmography signal provided in another embodiment of the present application further includes steps S56 to S58, which are specifically as follows:

[0116] S56: Obtain correlation coefficients of several initial cross-correlation peak points of the photoplethysmography unit signal, perform average processing on the peak values ​​of all initial cross-correlation peak points of the photoplethysmography unit signal, and obtain a reference wave group morphology consistency quality index.

[0117] In this embodiment, the extraction device obtains the correlation coefficients of several initial cross-correlation peak points of the photoplethysmogram unit signal. For the specific embodiment, reference may be made to step S42 and will not be repeated here.

[0118] The extraction device performs average processing on the peak values ​​of all the initial cross-correlation peak points of the photoplethysmogram unit signal to obtain a reference wave group morphology consistency quality index.

[0119] S57: Based on the correlation coefficients of the correlation coefficients of several initial mutual correlation peak points and a preset third correlation coefficient threshold, if the correlation coefficients of the correlation coefficients of the initial mutual correlation peak points are all greater than the third correlation coefficient threshold, the reference wave group morphology consistency quality index is used as the wave group morphology consistency quality index of the photoplethysmogram unit signal.

[0120] In this embodiment, the extraction device uses the reference wave group morphology consistency quality index as the wave group morphology consistency quality index of the photoplethysmogram unit signal based on the correlation coefficients of the correlation coefficients of several initial cross-correlation peak points and a preset third correlation coefficient threshold value, if the correlation coefficients of the correlation coefficients of the initial cross-correlation peak points are all greater than the third correlation coefficient threshold value.

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

[0122] If there is a correlation coefficient of the correlation coefficient of the initial cross-correlation peak point that is less than or equal to the third correlation coefficient threshold, in this embodiment, the extraction device divides the several initial cross-correlation peak points of the photoplethysmogram unit signal into intervals according to the correlation coefficient, obtains the ratio of several intervals of the photoplethysmogram unit signal, and adjusts the reference wave group morphology consistency quality index according to the ratio of several intervals of the photoplethysmogram unit signal and the product coefficient of several preset intervals to obtain the wave group morphology consistency quality index of the photoplethysmogram unit signal.

[0123] Specifically, the extraction device obtains the product results of several intervals of the photoplethysmogram unit signal according to the ratio of several intervals of the photoplethysmogram unit signal and the product coefficients of several preset intervals, and subtracts the product results of several intervals of the same photoplethysmogram unit signal from the same reference wave group morphology consistency quality index to obtain the wave group morphology consistency quality indicators of several photoplethysmogram unit signals.

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

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

[0126] A template is constructed based on the photoplethysmogram signals of multiple wavelengths of the user to be detected to obtain a photoplethysmogram template signal; the photoplethysmogram template signal is used to perform signal division and quality detection index extraction, and multi-level information mining is performed on the photoplethysmogram signal to obtain more sufficient and rich feature information, thereby achieving a more comprehensive and sufficient signal quality assessment; the extracted quality detection index is used to extract the target signal extraction result from the photoplethysmogram signals of multiple wavelengths, thereby improving the accuracy of photoplethysmogram signal extraction and effectively performing comprehensive and sufficient quality control on the photoplethysmogram signal.

[0127] See also Figure 7 , Figure 7 The flowchart of S6 in the quality assessment method of the photoplethysmography signal provided in one embodiment of the present application includes steps S61 to S63, which are specifically as follows:

[0128] S61: According to the positioning consistency quality index, interval consistency quality index, related volatility quality index, wave group morphology consistency quality index and corresponding weight parameters in the quality detection indicators, the comprehensive quality detection index of the photoplethysmogram unit signal is obtained; according to the comprehensive quality detection index and the preset quality detection index threshold, the photoplethysmogram unit signal is quality evaluated and divided to obtain a set of photoplethysmogram unit signals with several quality evaluation levels.

[0129] In this embodiment, the extraction device obtains the comprehensive quality detection index of the photoplethysmography unit signal according to the positioning consistency quality index, the interval consistency quality index, the related volatility quality index, the wave group morphology consistency quality index and the corresponding weight parameters in the quality detection index, 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] Where SQI is the comprehensive quality inspection index, w b is the weight parameter corresponding to the positioning consistency quality indicator, w i is the weight parameter corresponding to the interval consistency quality index, w s is the weight parameter corresponding to the relevant volatility quality indicator, w v is the weight parameter corresponding to the wave group morphology consistency quality index, σ bSQI is the standard deviation of the positioning consistency quality indicator, σ iSQI is the standard deviation of the interval consistency quality index, σ sSQI is the corresponding standard deviation of the relevant volatility quality indicator, σ vSQI is the corresponding standard deviation of the wave group morphology consistency quality index.

[0134] The extraction device performs quality assessment and classification on the photoplethysmogram unit signal according to the comprehensive quality detection index and the preset quality detection index threshold, and obtains a set of photoplethysmogram unit signals with several quality assessment levels, wherein the quality assessment levels include an excellent level, a pending level, and a poor level.

[0135] Specifically, the quality detection index threshold includes first, second and third quality detection index thresholds which decrease in sequence. If the comprehensive quality detection index is greater than the first quality detection index threshold, the extraction device sets the quality assessment level of the photoelectric volumetric pulse wave unit signal to an excellent level. 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 assessment level of the photoelectric volumetric pulse wave unit signal to a pending level. If the comprehensive quality detection index is less than the third quality detection index threshold, the extraction device sets the quality assessment level of the photoelectric volumetric pulse wave unit signal to a poor level. Several photoelectric volumetric pulse wave unit signals of the same quality assessment level are respectively combined to construct a set of photoelectric volumetric pulse wave unit signals of several quality assessment levels.

[0136] S62: Inputting the photoplethysmography unit signal set of pending level into a preset neural network model for availability judgment, and obtaining availability judgment results of several photoplethysmography unit signals in the photoplethysmography unit signal set of pending level; performing quality assessment and division on several photoplethysmography unit signals in the photoplethysmography unit signal set of pending level according to the availability judgment results, and obtaining photoplethysmography unit signal sets of several quality assessment levels.

[0137] In this embodiment, the extraction device inputs the photoplethysmogram unit signal set of the to-be-determined level into a preset neural network model for availability judgment, and obtains the availability judgment results of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of the to-be-determined level, wherein the availability judgment results include available judgment labels and unavailable judgment labels.

[0138] The extraction device performs quality assessment and classification on a plurality of photoplethysmography unit signals in the photoplethysmography unit signal set of pending level according to the availability determination result and the comprehensive quality detection index, and obtains a plurality of photoplethysmography unit signal sets of quality assessment levels.

[0139] Specifically, if the comprehensive quality detection index of the photoelectric volumetric pulse wave unit signal is greater than a preset fourth quality detection index threshold, and the availability judgment result of the photoelectric volumetric pulse wave unit signal is an available judgment 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 assessment level of the photoelectric volumetric pulse wave unit signal to an excellent level; if the comprehensive quality detection index of the photoelectric volumetric pulse wave unit signal is greater than the fourth quality detection index threshold, and the availability judgment result of the photoelectric volumetric pulse wave unit signal is an unavailable judgment label, the extraction device sets the quality assessment level of the photoelectric volumetric pulse wave unit signal to a good level; if the comprehensive quality detection index of the photoelectric volumetric pulse wave unit signal is less than or equal to the fourth quality detection index threshold, and the availability judgment result of the photoelectric volumetric pulse wave unit signal is an unavailable judgment label, the extraction device sets the quality assessment level of the photoelectric volumetric pulse wave unit signal to a poor level. The extraction device combines a plurality of the photoplethysmography unit signals of the same quality evaluation level to construct a plurality of photoplethysmography unit signal sets of quality evaluation levels.

[0140] S63: taking the photoplethysmogram unit signals in the excellent-grade photoplethysmogram unit signal set and the good-grade photoplethysmogram unit signal set as the target photoplethysmogram unit signals, and extracting a plurality of target photoplethysmogram unit signals from the photoplethysmogram unit signal sets of a plurality of wavelengths.

[0141] In this embodiment, the extraction device uses the photoplethysmogram unit signals in the excellent-grade photoplethysmogram unit signal set and the good-grade photoplethysmogram unit signal set as the target photoplethysmogram unit signal, and extracts several target photoplethysmogram unit signals from the photoplethysmogram unit signal sets of several wavelengths.

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

[0143] Please refer to Figure 8 , Figure 8 A schematic diagram of the structure of a device for evaluating the quality of a photoelectric volumetric pulse wave signal provided in one embodiment of the present application. The device can implement all or part of the device for evaluating the quality of a photoelectric volumetric pulse wave signal through software, hardware, or a combination of both. The device 8 includes:

[0144] A signal acquisition module 81 is used to obtain a photoplethysmogram signal of a user to be detected with a plurality of wavelengths;

[0145] A signal division module 82, used to obtain first peak location data and valley location data of the photoplethysmogram signal, and divide the photoplethysmogram signal according to the first valley location data to obtain a photoplethysmogram periodic signal set of several wavelengths;

[0146] A signal template building module 83 is used to build a template according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal;

[0147] The template matching module 84 is used to perform template matching with the photoplethysmography signals of several wavelengths according to the photoplethysmography template signal, so as to obtain the second peak location data of the photoplethysmography signals of several wavelengths;

[0148] The quality detection index calculation module 85 is used to divide the photoplethysmogram signal according to a preset signal unit length to obtain a photoplethysmogram unit signal set of several wavelengths; perform quality detection index calculation according to the first peak location data, the second peak location data and the photoplethysmogram unit signal set of several wavelengths to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths;

[0149] The signal extraction module 86 is used to extract a plurality of target photoplethysmogram unit signals from the photoplethysmogram unit signals of a plurality of wavelengths according to the quality detection index, and combine the plurality of target photoplethysmogram unit signals as the photoplethysmogram signal extraction result of the user to be detected.

[0150] In an embodiment of the present application, a signal acquisition module is used to obtain a photoelectric volumetric pulse wave signal of several wavelengths of the user to be detected; a signal division module is used to obtain first peak location data and valley location data of the photoelectric volumetric pulse wave signal, and the photoelectric volumetric pulse wave signal is divided according to the first valley location data to obtain a photoelectric volumetric pulse wave periodic signal set of several wavelengths; a signal template construction module is used to construct a template according to the photoelectric volumetric pulse wave periodic signal set of several wavelengths to obtain a photoelectric volumetric pulse wave template signal; a template matching module is used to perform template matching with the photoelectric volumetric pulse wave signals of several wavelengths according to the photoelectric volumetric pulse wave template signal to obtain second peak location data of the photoelectric volumetric pulse wave signals of several wavelengths; The quality detection index calculation module divides the photoelectric volumetric pulse wave signal according to a preset signal unit length to obtain a photoelectric volumetric pulse wave unit signal set of several wavelengths; calculates the quality detection index according to the first peak positioning data, the second peak positioning data and the photoelectric volumetric pulse wave unit signal set of several wavelengths to obtain the quality detection index of several photoelectric volumetric pulse wave unit signals in the photoelectric volumetric pulse wave unit signal set of several wavelengths; and extracts several target photoelectric volumetric pulse wave unit signals from the photoelectric volumetric pulse wave unit signal set of several wavelengths through the signal extraction module according to the quality detection index, and combines the several target photoelectric volumetric pulse wave unit signals as the photoelectric volumetric pulse wave signal extraction result of the user to be detected. A template is constructed based on the photoplethysmogram signals of multiple wavelengths of the user to be detected to obtain a photoplethysmogram template signal; the photoplethysmogram template signal is used to perform signal division and quality detection index extraction, and multi-level information mining is performed on the photoplethysmogram signal to obtain more sufficient and rich feature information, thereby achieving a more comprehensive and sufficient signal quality assessment; the extracted quality detection index is used to extract the target signal extraction result from the photoplethysmogram signals of multiple wavelengths, thereby improving the accuracy of photoplethysmogram signal extraction and effectively performing comprehensive and sufficient quality control on the photoplethysmogram signal.

[0151] Please refer to Fig. 9 , Fig. 9 The computer device 9 is a schematic diagram of a structure of a computer device provided in an embodiment of the present application. The computer device 9 includes: 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 may store a plurality of instructions, which are suitable for being loaded and executed by the processor 91 Figures 1 to 7 The method steps shown in the figure can be found in the specific execution process. Figures 1 to 7 The specific description shown will not be repeated here.

[0152] Among them, the processor 91 may include one or more processing cores. The processor 91 uses various interfaces and lines to connect various parts in the server, and executes various functions and processes data of the quality assessment device 8 of the photoelectric volume pulse wave signal by running or executing instructions, programs, code sets or instruction sets stored in the memory 92, and calling the data in the memory 92. Optionally, the processor 91 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programble Logic Array, PLA). The processor 91 can integrate one or more combinations of a central processing unit 91 (Central Processing Unit, CPU), a graphics processor 91 (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 91, and it can be implemented by a single chip.

[0153] Among them, the memory 92 may include a random access memory 92 (Random Access Memory, RAM), and may also include a read-only memory 92 (Read-Only Memory). 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 may include a program storage area and a data storage area, wherein the program storage area may 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 may store data involved in the above-mentioned various method embodiments, etc. The memory 92 may also be optionally at least one storage device located away from the aforementioned processor 91.

[0154] The present application also provides a storage medium that can store multiple instructions, which are suitable for the processor to load and execute the above-mentioned Figures 1 to 7 The method steps shown in the figure can be found in the specific execution process. Figures 1 to 7 The specific description shown will not be repeated here.

[0155] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0156] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0158] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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

[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0161] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0162] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications to the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims and equivalent technologies of the present invention, the present invention is also intended to include these changes and modifications.

Claims

1. A method for evaluating the quality of a photoplethysmography signal, characterized in that: The following steps are involved: Obtaining photoplethysmographic signals of several wavelengths of the user to be detected; Obtaining first peak location data and valley location data of the photoplethysmogram signal, and dividing the photoplethysmogram signal according to the first valley location data to obtain a photoplethysmogram periodic signal set of several wavelengths; A template is constructed according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal; According to the photoplethysmography template signal, template matching is performed with photoplethysmography signals of several wavelengths respectively to obtain second peak location data of the photoplethysmography signals of several wavelengths; According to a preset signal unit length, the photoplethysmogram signal is divided to obtain a photoplethysmogram unit signal set of several wavelengths; according to the first peak location data, the second peak location data and the photoplethysmogram unit signal set of several wavelengths, a quality detection index is calculated to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths; According to the quality detection index, a plurality of target photoplethysmogram unit signals are extracted from the photoplethysmogram unit signals of a plurality of wavelengths, and the plurality of target photoplethysmogram unit signals are combined as the photoplethysmogram signal extraction result of the user to be detected.

2. The method for evaluating the quality of a photoplethysmography signal according to claim 1, wherein: The first peak location data is fast peak location data obtained by using a fast peak search method; The method of obtaining the first peak location data and the valley location data of the photoplethysmogram signal comprises the steps of: A fast peak finding method is used to obtain fast peak location data and fast valley location data of the photoplethysmogram signal; According to the peak values ​​of several fast peak points in the fast peak positioning data and the valley values ​​of several fast valley points in the fast valley positioning data, an average screening process is performed to obtain several screening peak points and several screening valley points, and the screening peak points are combined with the previous screening valley point to construct several initial screening peak valley point combinations; Obtain peak-valley values ​​of several initial screening peak-valley value point combinations, obtain several target screening peak-valley value point combinations based on the peak-valley values ​​and a preset peak-valley value depth threshold, confirm the valley points in the target screening peak-valley value point combinations, and construct the valley value positioning data of the photoelectric volumetric pulse wave signal.

3. The method for evaluating the quality of a photoplethysmography signal according to claim 2, wherein: The photoplethysmogram periodic signal set includes a plurality of photoplethysmogram periodic signals; The method of constructing a template based on a set of photoplethysmographic periodic signals of a plurality of wavelengths to obtain a photoplethysmographic template signal comprises the following steps: Obtaining a correlation coefficient of a plurality of photoplethysmogram periodic signals in the photoplethysmogram periodic signal set, and extracting a plurality of candidate photoplethysmogram periodic signals from the photoplethysmogram periodic signal set of a plurality of wavelengths according to the correlation coefficient and a preset first correlation coefficient threshold, to obtain a plurality of candidate photoplethysmogram periodic signals of a plurality of wavelengths; Obtaining a cross-correlation coefficient between a plurality of candidate photoplethysmogram periodic signals of different wavelengths, and obtaining, based on the cross-correlation coefficient and a preset cross-correlation coefficient threshold, a plurality of candidate photoplethysmogram periodic signals that meet the cross-correlation coefficient threshold as sample photoplethysmogram template signals, and constructing a template signal segment set; An average photoplethysmogram template signal of the template signal segment set is constructed, and standard deviation calculation is performed based on a number of sample photoplethysmogram template signals and an average photoplethysmogram template signal in the template signal segment set to obtain the standard deviation of the number of sample photoplethysmogram template signals; based on a preset number of signals, a number of sample photoplethysmogram template signals with the largest standard deviation that matches the number of signals are obtained as candidate photoplethysmogram template signals; average processing is performed based on the number of candidate photoplethysmogram template signals to construct a photoplethysmogram template signal.

4. The method for evaluating the quality of a photoplethysmography signal according to claim 3, wherein: The method of performing template matching on the photoplethysmogram template signal and the photoplethysmogram signals of several wavelengths to obtain second peak location data of the photoplethysmogram signals of several wavelengths comprises the following steps: 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; According to a preset peak threshold and a peak-finding function, a plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal are obtained, and correlation coefficients of the initial cross-correlation peak points are calculated to obtain correlation coefficients of the plurality of initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal; According to the correlation coefficient of several initial cross-correlation peak points of the photoplethysmogram cross-correlation function signal and a preset second correlation coefficient threshold, several target cross-correlation function peak points of the photoplethysmogram cross-correlation function signal are obtained; the several target cross-correlation function peak points of the photoplethysmogram cross-correlation function signal are mapped to the photoplethysmogram signal of the corresponding wavelength to obtain second peak positioning data of the photoplethysmogram signal of several wavelengths.

5. The method for evaluating the quality of a photoplethysmography signal according to claim 4, characterized in that: The first peak positioning data includes a plurality of first peak points; the second peak positioning data includes a plurality of second peak points; the quality detection index includes a positioning consistency quality index, an interval consistency quality index and a related volatility quality index; The method of calculating the quality detection index according to the first peak location data, the second peak location data and the photoplethysmography unit signal set of several wavelengths to obtain the quality detection index of several photoplethysmography unit signals in the photoplethysmography unit signal set of several wavelengths comprises the following steps: According to the first peak location data and the second peak location data, consistency judgment is performed on the first peak point and the second peak point under the same position index in the photoplethysmography unit signal to obtain consistent peak location data and inconsistent peak location data of the photoplethysmography unit signal; According to the first peak location data, the second peak location data, the consistent peak location data and the inconsistent peak location data of the photoplethysmography unit signal and a preset first indicator calculation algorithm, the positioning consistency quality index of the photoplethysmography unit signal is obtained, wherein the first indicator calculation algorithm is: Wherein, 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 the length function to indicate the number of peak points; According to the consistent peak location data and the inconsistent peak location data of the photoplethysmogram unit signal, the first peak location data and the second peak location data of the photoplethysmogram unit signal are fused to construct fused peak location data of the photoplethysmogram unit signal, wherein the fused peak location data includes a plurality of fused peak points; According to the fused peak positioning data of the photoplethysmography unit signal, the fused peak interval data of the photoplethysmography unit signal is calculated, and according to the fused peak interval data of the photoplethysmography unit signal and a preset second indicator calculation algorithm, the interval consistency quality index of the photoplethysmography unit signal is obtained, wherein the second indicator calculation algorithm is: Wherein, iSQI is the interval consistency quality index, is the interval value of the top 15% in the fused peak interval data, The interval values ​​of the top 85% of the fused peak interval data; The amplitude average value and the amplitude standard deviation corresponding to the fusion peak positioning data of the photoplethysmography unit signal are obtained as the first amplitude threshold and the second amplitude threshold. According to the amplitudes of several fusion peak points in the fusion peak interval data of the photoplethysmography unit signal, the number of fusion peak points that meet the first amplitude threshold and the second amplitude threshold is obtained. According to the number of fusion peak points that meet the first amplitude threshold and the second amplitude threshold and a preset third indicator calculation algorithm, the relevant volatility quality index of the photoplethysmography unit signal is obtained, wherein the third indicator calculation algorithm is: In the formula, vSQI is the correlation volatility quality index, s is the signal unit length, fs is the signal sampling rate, and H is the number of fusion peak points that meet the first amplitude threshold and the second amplitude threshold.

6. The method for evaluating the quality of a photoplethysmography signal according to claim 5, wherein: The quality detection index also includes a wave group morphology consistency quality index; The method of calculating the quality detection index according to the first peak location data, the second peak location data and the photoplethysmography unit signal set of several wavelengths to obtain the quality detection index of several photoplethysmography unit signals in the photoplethysmography unit signal set of several wavelengths also includes the steps of: Obtaining correlation coefficients of several initial cross-correlation peak points of the photoplethysmography unit signal, performing average processing on the peak values ​​of all initial cross-correlation peak points of the photoplethysmography unit signal, and obtaining a reference wave group morphology consistency quality index; According to the correlation coefficients of the correlation coefficients of the 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 morphology consistency quality index is used as the wave group morphology consistency quality index of the photoplethysmography unit signal; If there is a correlation coefficient of the correlation coefficient of the initial cross-correlation peak point that is less than or equal to the third correlation coefficient threshold, according to the correlation coefficient, several initial cross-correlation peak points of the photoplethysmogram unit signal are divided into intervals to obtain the ratio of several intervals of the photoplethysmogram unit signal, and according to the ratio of several intervals of the photoplethysmogram unit signal and the product coefficient of several preset intervals, the reference wave group morphology consistency quality index is adjusted to obtain the wave group morphology consistency quality index of the photoplethysmogram unit signal.

7. The method for evaluating the quality of a photoplethysmography signal according to claim 6, wherein: The method of extracting a plurality of target photoplethysmogram unit signals from a plurality of photoplethysmogram unit signals of wavelengths according to the quality detection index comprises the steps of: According to the positioning consistency quality index, the interval consistency quality index, the related volatility quality index, the wave group morphology consistency quality index and the corresponding weight parameters in the quality detection index, the comprehensive quality detection index of the photoplethysmography unit signal is obtained; according to the comprehensive quality detection index and the preset quality detection index threshold, the photoplethysmography unit signal is quality evaluated and divided to obtain a set of photoplethysmography unit signals of several quality evaluation levels, wherein the quality evaluation levels include an excellent level, a pending level and a poor level; Inputting a photoplethysmography unit signal set of a pending level into a preset neural network model for availability judgment, and obtaining availability judgment results of a plurality of photoplethysmography unit signals in the photoplethysmography unit signal set of a pending level; performing quality assessment and division on a plurality of photoplethysmography unit signals in the photoplethysmography unit signal set of a pending level according to the availability judgment results and the comprehensive quality detection index, and obtaining a photoplethysmography unit signal set of a plurality of quality assessment levels, wherein the quality assessment level includes a good level; The photoplethysmogram unit signals in the excellent photoplethysmogram unit signal set and the good photoplethysmogram unit signal set are used as the target photoplethysmogram unit signals, and several target photoplethysmogram unit signals are extracted from the photoplethysmogram unit signal sets of several wavelengths.

8. A device for evaluating the quality of a photoplethysmography signal, characterized in that: include: A signal acquisition module, used to obtain photoplethysmographic signals of several wavelengths of the user to be detected; A signal division module, used to obtain first peak location data and valley location data of the photoplethysmogram signal, and divide the photoplethysmogram signal according to the first valley location data to obtain a photoplethysmogram periodic signal set of several wavelengths; A signal template building module, used to build a template according to a set of photoplethysmographic periodic signals of several wavelengths to obtain a photoplethysmographic template signal; A template matching module, used to perform template matching with photoplethysmography signals of several wavelengths according to the photoplethysmography template signal, to obtain second peak location data of the photoplethysmography signals of several wavelengths; A quality detection index calculation module is used to divide the photoplethysmogram signal according to a preset signal unit length to obtain a photoplethysmogram unit signal set of several wavelengths; perform quality detection index calculation according to the first peak location data, the second peak location data and the photoplethysmogram unit signal set of several wavelengths to obtain quality detection indicators of several photoplethysmogram unit signals in the photoplethysmogram unit signal set of several wavelengths; The signal extraction module is used to extract a plurality of target photoplethysmogram unit signals from the photoplethysmogram unit signals of a plurality of wavelengths according to the quality detection index, and combine the plurality of target photoplethysmogram unit signals as the photoplethysmogram signal extraction result of the user to be detected.

9. A computer device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for evaluating the quality of a photoplethysmography signal according to any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for evaluating the quality of a photoplethysmography signal according to any one of claims 1 to 7 are implemented.

Images