Photoplethysmography signal reconstruction method, device and equipment and storage medium

Abstract

The invention relates to a photoelectric volume pulse wave signal reconstruction method, device and equipment and a storage medium, and the method comprises the steps that the starting point of each pulse wave is determined based on a photoelectric volume pulse wave signal; the duration, duration stability parameters and / or duration mutation parameters of all the pulse waves are determined according to the starting points of all the pulse waves, the duration stability parameters are used for representing the stability of the duration of the corresponding pulse waves relative to the duration of other pulse waves in the whole photoelectric volume pulse wave signal, and / or the duration mutation parameters are used for representing the stability of the duration of the corresponding pulse waves relative to the duration of other pulse waves in the whole photoelectric volume pulse wave signal. The duration mutation parameter is used for representing the mutation degree of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave; according to the duration, the duration stability parameter and / or the duration mutation parameter of each pulse wave, determining an abnormal pulse wave; and removing the abnormal pulse wave from the photoelectric volume pulse wave signal to obtain a reconstructed photoelectric volume pulse wave signal.

Description

Technical Field

[0001] The present disclosure relates to a photoplethysmography signal optimization processing technology, and more specifically, to a photoplethysmography signal reconstruction method, device, equipment, and storage medium. Background Art

[0002] Existing wearable devices are often equipped with sensors to collect photoplethysmography (PPG) signals. Before PPG signals can be used for subsequent processing, such as determining heart rate or predicting blood pressure, they need to be optimized.

[0003] The existing PPG signal optimization processing mainly adopts the following two methods: overall quality assessment method and fixed window segmentation method.

[0004] Based on the holistic quality assessment method, a machine learning model is used to evaluate the quality of the entire PPG signal, generating a score. PPG signal segments with scores below a threshold are discarded entirely. This method results in the inadvertent discarding of a large number of PPG signals containing locally valid information, making it impossible to retain valid signal segments.

[0005] Based on the fixed window segmentation method, the entire PPG signal is divided into signal segments of fixed duration for quality screening. This method has two drawbacks: first, it is difficult to accurately locate the boundary between the effective signal and the noise, resulting in the partial loss of high-quality segments; second, it destroys the original temporal correlation of the signal, affecting the analysis of temporal characteristics such as heart rate variability. Summary of the Invention

[0006] An object of the present invention is to provide a new technical solution for a photoplethysmography signal reconstruction method.

[0007] According to a first aspect of the present invention, a method for reconstructing a photoplethysmography signal is provided, comprising:

[0008] Determine the starting point of each pulse wave based on the photoplethysmography signal;

[0009] Determining, based on the starting point of each pulse wave, a duration, a duration stability parameter, and / or a duration mutation parameter of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave;

[0010] determining an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave;

[0011] The abnormal pulse wave is removed from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

[0012] Optionally, determining the duration of each pulse wave according to the starting point of each pulse wave includes:

[0013] Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves;

[0014] The difference between the sampling times corresponding to the starting points of every two adjacent pulse waves is determined as the duration of the corresponding pulse wave.

[0015] Optionally, determining the duration stability parameter of each pulse wave according to the starting point of each pulse wave includes:

[0016] Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves;

[0017] Determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave;

[0018] According to the duration of each pulse wave, the median duration is determined;

[0019] Determining the difference between the duration of each pulse wave and the median duration;

[0020] Determining a median of the duration differences according to the duration differences between the durations of the pulse waves and the median of the durations;

[0021] Based on each pulse wave, a duration stability parameter is determined according to the corresponding duration difference and the median value of the duration difference.

[0022] Optionally, determining the duration mutation parameter of each pulse wave according to the starting point of each pulse wave includes:

[0023] Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves;

[0024] Determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave;

[0025] Determine the difference between the durations of two adjacent pulse waves;

[0026] The duration mutation parameter of each pulse wave is determined according to the difference between the durations of each two adjacent pulse waves and the duration of the pulse wave with the earlier sampling time in each two adjacent pulse waves.

[0027] Optionally, determining an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave includes:

[0028] Based on each pulse wave, if the duration of the corresponding pulse wave is not within a preset duration range, or the duration stability parameter of the corresponding pulse wave is greater than a first preset threshold, or the duration mutation parameter of the corresponding pulse wave is greater than a second preset threshold, the corresponding pulse wave is determined to be an abnormal pulse wave.

[0029] Optionally, removing the abnormal pulse wave from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal includes:

[0030] The photoplethysmography signal from which the abnormal pulse wave is removed is subjected to time splicing and amplitude normalization processing to obtain the reconstructed photoplethysmography signal.

[0031] Optionally, the method further includes:

[0032] The heart rate and / or blood pressure value is determined based on the reconstructed photoplethysmography signal.

[0033] According to a second aspect of the present invention, there is provided a device for reconstructing a photoplethysmography signal, comprising:

[0034] A pulse wave starting point determination module, configured to determine the starting point of each pulse wave based on the photoplethysmography signal;

[0035] a duration parameter determination module, configured to determine the duration, a duration stability parameter, and / or a duration mutation parameter of each pulse wave based on the starting point of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave;

[0036] an abnormal pulse wave determination module, configured to determine an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave;

[0037] The signal reconstruction module is used to remove the abnormal pulse wave from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

[0038] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program for controlling the processor to operate so as to execute the photoplethysmography signal reconstruction method according to any one of the first aspects.

[0039] According to a fourth aspect of the present invention, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the photoplethysmography signal reconstruction method described in any one of the first aspects is implemented.

[0040] The present disclosure provides a method for reconstructing photoplethysmography signals, which avoids the problem of discarding an entire signal segment due to local signal anomalies, and maximizes the retention of valid data in the entire signal segment. At the same time, the abnormal part of the entire signal segment is determined from multiple dimensions such as the duration of each pulse wave, the duration stability parameter, and the duration mutation parameter, thereby improving the accuracy of locating the abnormal part.

[0041] Features and advantages of the embodiments of the present specification will become apparent from the following detailed description of exemplary embodiments of the present specification with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and, together with the description, serve to explain the principles of the embodiments of the specification.

[0043] Figure 1 FIG. 4 is a flow chart of a method for reconstructing a photoplethysmography signal according to an embodiment of the present invention.

[0044] Figure 2 FIG. 1 is a schematic diagram of a PPG signal according to an embodiment of the present invention.

[0045] Figure 3 FIG. 4 is a flow chart of a method for reconstructing a photoplethysmography signal according to an embodiment of the present invention.

[0046] Figure 4 FIG. 4 is a schematic diagram of reconstructing a photoplethysmography signal according to an embodiment of the present invention.

[0047] Figure 5 FIG. 1 is a schematic structural diagram of a device for reconstructing a photoplethysmography signal according to an embodiment of the present invention.

[0048] Figure 6 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] Various exemplary embodiments of the present specification will now be described in detail with reference to the accompanying drawings.

[0050] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the embodiments of this specification, its application, or uses.

[0051] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0052] To solve the above technical problems, the embodiments of the present disclosure provide a method for reconstructing photoplethysmography signals, which avoids the problem of discarding the entire signal due to local signal abnormalities, and maximizes the retention of valid data in the entire signal. At the same time, the abnormal part of the entire signal is determined from multiple dimensions such as the duration of each pulse wave, the duration stability parameter, and the duration mutation parameter, thereby improving the accuracy of locating the abnormal part.

[0053] In one embodiment of the present invention, a method for reconstructing a photoplethysmography signal is provided. Figure 1 As shown, the photoplethysmography signal reconstruction method of this embodiment includes the following steps S110 to S140.

[0054] Step S110 : determining the starting point of each pulse wave based on the photoplethysmography signal.

[0055] Photoplethysmography (PPG) signals are collected by corresponding sensors.

[0056] Based on a pulse wave, the starting point is the feature point onset. The feature point onset is the moment when the heart begins to contract and blood is ejected from the heart into the arterial system, that is, the moment when the heartbeat begins.

[0057] Figure 2 FIG. 1 shows a waveform diagram of a PPG signal according to an embodiment of the present invention. Figure 2 As shown in , based on each pulse wave cycle, the valley point is the feature point onset. Figure 2 It can be seen that the position of the feature point onset is relatively obvious and easy to extract from the PPG signal. In addition, the position of the extracted feature point onset is relatively accurate, providing an accurate data basis for subsequent processing.

[0058] Step S120, determining the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave based on the starting point of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave.

[0059] In some embodiments, determining the duration of each pulse wave based on the starting point of each pulse wave specifically includes: obtaining the sampling time corresponding to the starting points of every two adjacent pulse waves; and determining the difference between the sampling times corresponding to the starting points of every two adjacent pulse waves as the duration of the corresponding pulse wave.

[0060] according to Figure 2 As shown, taking starting points a, b, and c as examples, starting points a and b correspond to two adjacent pulse waves, and starting points b and c correspond to two adjacent pulse waves. The sampling time corresponding to starting point a is obtained, and the difference between the sampling time corresponding to starting point a and the sampling time corresponding to starting point b is determined as the duration of pulse wave A. The sampling time corresponding to starting point b is obtained, and the difference between the sampling time corresponding to starting point b and the sampling time corresponding to starting point c is determined as the duration of pulse wave B. Similarly, the duration of any pulse wave in the PPG signal can be determined.

[0061] Taking the PPG signal including n pulse waves as an example, the duration x of the n-1th pulse wave is calculated based on the following formula: n-1 ,

[0062] x n-1 =t n -t n-1

[0063] Among them, t n-1 is the sampling time corresponding to the starting point of the n-1th pulse wave, t n is the sampling time corresponding to the starting point of the nth pulse wave.

[0064] In some embodiments, determining the duration stability parameter of each pulse wave based on the starting point of each pulse wave specifically includes: obtaining the sampling time corresponding to the starting point of each two adjacent pulse waves; determining the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; determining the median duration based on the duration of each pulse wave; determining the duration difference between the duration of each pulse wave and the median duration; determining the median duration difference based on the duration difference between the duration of each pulse wave and the median duration; based on each pulse wave, determining the duration stability parameter according to the corresponding duration difference and the median duration difference.

[0065] The method for determining the duration of each pulse wave can refer to the method based on Figure 2 The three starting points shown are used as examples of a method for determining duration, and will not be described in detail here.

[0066] For example, a PPG signal consisting of n pulse waves can be used to determine a duration for each pulse wave, resulting in n duration values. These n duration values ​​are arranged in order of magnitude, and the duration value in the middle is determined as the median duration value. It should be noted that if there are two duration values ​​in the middle, the median duration value is determined as the average of the two middle duration values.

[0067] For each pulse wave, the duration difference between the pulse wave duration and the median duration is determined, resulting in n duration differences. These n duration differences are arranged in order of magnitude, and the duration difference at the middle position is determined as the median duration difference. It should be noted that if there are two duration differences at the middle position, the average of the two duration differences at the middle position is determined as the median duration difference.

[0068] Based on each pulse wave, a duration stability parameter is determined according to the corresponding duration difference and the median value of the duration difference.

[0069] Specifically, the duration stability parameter Z corresponding to any pulse wave in the PPG signal is calculated based on the following formula:

[0070]

[0071] Where x is the duration of any pulse wave, x median is the median value of the duration of each pulse wave in the PPG signal, Δx median is the median value of the duration difference corresponding to all duration differences corresponding to the PPG signal.

[0072] In some embodiments, determining the duration mutation parameter of each pulse wave based on the starting point of each pulse wave specifically includes: obtaining the sampling time corresponding to the starting point of each two adjacent pulse waves; determining the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; determining the difference between the durations of each two adjacent pulse waves; and determining the duration mutation parameter of each pulse wave based on the difference between the durations of each two adjacent pulse waves and the duration of the pulse wave with the earlier sampling time among the durations of each two adjacent pulse waves.

[0073] The method for determining the duration of each pulse wave can refer to the method based on Figure 2 The three starting points shown are used as examples of a method for determining duration, and will not be described in detail here.

[0074] Taking the PPG signal including n pulse waves as an example, the duration mutation parameter Δ of the nth pulse wave is determined based on the following calculation formula:

[0075]

[0076] Among them, xn-1 is the duration of the n-1th pulse wave, x n is the duration of the nth pulse wave.

[0077] Step S130 , determining abnormal pulse waves based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave.

[0078] In some embodiments, step S130 specifically includes: based on each pulse wave, when the duration of the corresponding pulse wave is not within a preset duration range, or the duration stability parameter of the corresponding pulse wave is greater than a first preset threshold, or the duration mutation parameter of the corresponding pulse wave is greater than a second preset threshold, determining that the corresponding pulse wave is an abnormal pulse wave.

[0079] The first preset threshold can be set according to needs, for example, set to 3.5.

[0080] The second preset threshold can be set according to needs, for example, set to 20%.

[0081] Step S140 , removing abnormal pulse waves from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

[0082] In some embodiments, the photoplethysmography signal after abnormal pulse waves are removed is spliced ​​in time and amplitude normalized to obtain a reconstructed photoplethysmography signal, thereby ensuring seamless splicing in time and amplitude alignment of the reconstructed photoelectric statistical pulse wave signal.

[0083] The following describes the photoplethysmography signal reconstruction method provided by the present invention using a specific embodiment. Figure 3 As shown, the photoplethysmography signal reconstruction method includes the following steps S301 to S309.

[0084] Step S301: Acquire a photoplethysmography signal.

[0085] Step S302: Determine the starting point of each pulse wave based on the photoplethysmography signal.

[0086] Step S303: Determine the duration of each pulse wave according to the starting point of each pulse wave.

[0087] Step S304: Detect a pulse wave whose duration is not within a preset duration range and regard it as an abnormal pulse wave.

[0088] Step S305: Determine the duration stability parameter of each pulse wave according to the starting point of each pulse wave.

[0089] Step S306: Detect a pulse wave whose duration stability parameter is greater than a first preset threshold value as an abnormal pulse wave.

[0090] Step S307: Determine the duration mutation parameter of each pulse wave according to the starting point of each pulse wave.

[0091] Step S308: Detect a pulse wave whose duration mutation parameter is greater than a second preset threshold value and regard it as an abnormal pulse wave.

[0092] Step S309 , removing abnormal pulse waves from the photoplethysmography signal, performing time splicing and amplitude normalization processing on the photoplethysmography signal from which the abnormal pulse waves are removed, and obtaining a reconstructed photoplethysmography signal.

[0093] Specific can be combined Figure 4 Schematic diagram of the PPG signal reconstruction process shown. Figure 4 As shown in the figure, from top to bottom, the PPG signal shown in the second figure is the PPG signal after removing the abnormal pulse wave. The PPG signal shown in the third figure is the PPG signal obtained after amplitude normalization. The PPG signal shown in the fourth figure is the PPG signal obtained after time splicing.

[0094] It should be noted that the detection order of whether a pulse wave is abnormal based on the duration of each pulse wave, the detection order of whether a pulse wave is abnormal based on the duration stability parameter of each pulse wave, and the detection order of whether a pulse wave is abnormal based on the duration mutation parameter of each pulse wave can be changed arbitrarily and is limited to the detection order performed in this embodiment.

[0095] In addition, for any pulse wave in the PPG signal, as long as at least one of the corresponding duration, duration stability parameter, and duration mutation parameter is abnormal, the corresponding pulse wave can be determined to be an abnormal pulse wave.

[0096] In some embodiments, the method further includes determining a heart rate and / or blood pressure value based on the reconstructed photoplethysmography signal.

[0097] One embodiment of the present invention provides a device for reconstructing a photoplethysmography signal. Figure 5 As shown, the photoplethysmography signal reconstruction device 500 includes a pulse wave starting point determination module 510 , a duration parameter determination module 520 , an abnormal pulse wave determination module 530 and a signal reconstruction module 540 .

[0098] The pulse wave starting point determination module 510 is used to determine the starting point of each pulse wave based on the photoplethysmography signal.

[0099] The duration parameter determination module 520 is used to determine the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave based on the starting point of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave.

[0100] The abnormal pulse wave determination module 530 is configured to determine an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave.

[0101] The signal reconstruction module 540 is used to remove abnormal pulse waves from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

[0102] In some embodiments, the duration parameter determination module 520 is further configured to obtain the sampling time corresponding to the starting points of every two adjacent pulse waves; and determine the difference between the sampling times corresponding to the starting points of every two adjacent pulse waves as the duration of the corresponding pulse wave.

[0103] In some embodiments, the duration parameter determination module 520 is further used to obtain the sampling time corresponding to the starting point of each two adjacent pulse waves; determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; determine the median duration based on the duration of each pulse wave; determine the duration difference between the duration of each pulse wave and the median duration; determine the median duration difference based on the duration difference between the duration of each pulse wave and the median duration; and determine the duration stability parameter based on each pulse wave according to the corresponding duration difference and the median duration difference.

[0104] In some embodiments, the duration parameter determination module 520 is further used to obtain the sampling time corresponding to the starting point of each two adjacent pulse waves; determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; determine the difference between the durations of each two adjacent pulse waves; and determine the duration mutation parameter of each pulse wave based on the difference between the durations of each two adjacent pulse waves and the duration of the pulse wave with the earlier sampling time in each two adjacent pulse waves.

[0105] In some embodiments, the abnormal pulse wave determination module 530 is used to determine, based on each pulse wave, that the corresponding pulse wave is an abnormal pulse wave if the duration of the corresponding pulse wave is not within a preset duration range, or if the duration stability parameter of the corresponding pulse wave is greater than a first preset threshold, or if the duration mutation parameter of the corresponding pulse wave is greater than a second preset threshold.

[0106] In some embodiments, the signal reconstruction module 540 is configured to perform time splicing and amplitude normalization processing on the photoplethysmography signal after removing abnormal pulse waves to obtain a reconstructed photoplethysmography signal.

[0107] In some embodiments, the device further includes a heart rate and / or blood pressure value determination module for determining the heart rate and / or blood pressure value based on the reconstructed photoplethysmography signal.

[0108] An embodiment of the present invention provides an electronic device. Figure 6 As shown, the electronic device 600 includes a memory 620 and a processor 610. The memory 620 stores a computer program, which is used to control the processor 610 to operate so as to execute the photoplethysmography signal reconstruction method provided by any of the above embodiments.

[0109] The processor 610 is used to execute computer instructions, which can be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, or SSE. The memory 620 includes, for example, ROM (read-only memory), RAM (random access memory), and non-volatile memory such as a hard disk, etc., which are not limited here.

[0110] The present disclosure further provides a non-volatile computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the photoplethysmography signal reconstruction method provided in any of the above embodiments.

[0111] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0112] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The embodiments of this specification may be systems, methods, and / or computer program products. The computer program product may include a computer-readable storage medium carrying computer instructions for causing a processor to implement various aspects of the embodiments of this specification.

[0114] A computer-readable storage medium can be a tangible device that can hold and store computer instructions for use by a computer instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which computer instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0115] The computer instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer instructions from the network and forwards the computer instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0116] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of this specification. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of a computer instruction, and the module, program segment or part of a computer instruction contains one or more executable computer instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0117] The embodiments of the present specification have been described above. The above description is illustrative and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for reconstructing a photoplethysmography signal, characterized in that: include: Determine the starting point of each pulse wave based on the photoplethysmography signal; Determining, based on the starting point of each pulse wave, a duration, a duration stability parameter, and / or a duration mutation parameter of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave; determining an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave; The abnormal pulse wave is removed from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

2. The method according to claim 1, characterized in that Determining the duration of each pulse wave according to the starting point of each pulse wave includes: Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves; The difference between the sampling times corresponding to the starting points of every two adjacent pulse waves is determined as the duration of the corresponding pulse wave.

3. The method according to claim 1, characterized in that Determining the duration stability parameter of each pulse wave according to the starting point of each pulse wave includes: Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves; Determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; According to the duration of each pulse wave, the median duration is determined; Determining the difference between the duration of each pulse wave and the median duration; Determining a median of the duration differences according to the duration differences between the durations of the pulse waves and the median of the durations; Based on each pulse wave, a duration stability parameter is determined according to the corresponding duration difference and the median value of the duration difference.

4. The method according to claim 1, wherein Determining the duration mutation parameter of each pulse wave according to the starting point of each pulse wave includes: Obtain the sampling time corresponding to the starting points of every two adjacent pulse waves; Determine the difference between the sampling times corresponding to the starting points of each two adjacent pulse waves as the duration of the corresponding pulse wave; Determine the difference between the durations of two adjacent pulse waves; The duration mutation parameter of each pulse wave is determined according to the difference between the durations of each two adjacent pulse waves and the duration of the pulse wave with the earlier sampling time in each two adjacent pulse waves.

5. The method according to claim 1, wherein Determining an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave includes: Based on each pulse wave, if the duration of the corresponding pulse wave is not within a preset duration range, or the duration stability parameter of the corresponding pulse wave is greater than a first preset threshold, or the duration mutation parameter of the corresponding pulse wave is greater than a second preset threshold, the corresponding pulse wave is determined to be an abnormal pulse wave.

6. The method according to claim 1, wherein The step of removing the abnormal pulse wave from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal includes: The photoplethysmography signal from which the abnormal pulse wave is removed is subjected to time splicing and amplitude normalization processing to obtain the reconstructed photoplethysmography signal.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The heart rate and / or blood pressure value is determined based on the reconstructed photoplethysmography signal.

8. A photoplethysmography signal reconstruction device, characterized in that: include: A pulse wave starting point determination module, configured to determine the starting point of each pulse wave based on the photoplethysmography signal; a duration parameter determination module, configured to determine the duration, a duration stability parameter, and / or a duration mutation parameter of each pulse wave based on the starting point of each pulse wave, wherein the duration stability parameter is used to indicate the stability of the duration of the corresponding pulse wave relative to the durations of other pulse waves in the entire photoplethysmography signal, and the duration mutation parameter is used to indicate the degree of mutation of the duration of the corresponding pulse wave relative to the duration of the previous pulse wave; an abnormal pulse wave determination module, configured to determine an abnormal pulse wave based on the duration, duration stability parameter, and / or duration mutation parameter of each pulse wave; The signal reconstruction module is used to remove the abnormal pulse wave from the photoplethysmography signal to obtain a reconstructed photoplethysmography signal.

9. An electronic device, characterized in that: The device comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute the photoplethysmography signal reconstruction method according to any one of claims 1 to 7.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the photoplethysmography signal reconstruction method according to any one of claims 1 to 7 is implemented.

Images