Heart rate extraction method and device, electronic equipment, piezoelectric sensor and medium

Abstract

The embodiment of the present application provides a heart rate extraction method and device, electronic equipment, piezoelectric sensor and medium, the method comprising: obtaining a vital sign signal of a target object; detecting whether the vital sign signal contains respiratory harmonics to obtain a detection result; performing a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object. By detecting whether the vital sign signal of the target object contains respiratory harmonics, and then performing a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object, the heart rate can be flexibly and accurately extracted, and the utilization rate of computing resources can be improved.

Description

Technical Field

[0001] The present application relates to the field of heart rate measurement technology, and in particular to a heart rate extraction method and device, electronic equipment, a piezoelectric sensor, and a computer-readable storage medium. Background Art

[0002] At present, people are paying more and more attention to their health status, and heart rate as an important vital sign indicator has been paid attention to accordingly. The vital sign signal of the human body can be detected by piezoelectric sensors, and then the respiratory rate and heart rate of the human body can be separated from the vital sign signal. In practical applications, the heartbeat signal is relatively weak and easily affected by respiratory harmonics, resulting in low accuracy in heart rate extraction, which is common in clinical cardiovascular patients or people with uneven breathing.

[0003] However, the known heart rate extraction methods have the following main problems: either they do not consider the influence of respiratory harmonics on heartbeat signals, resulting in low accuracy of heart rate extraction; or they perform respiratory harmonic cancellation processing on any signal, occupying more computing resources. Summary of the invention

[0004] In order to solve the existing technical problems, the present application provides a heart rate extraction method and device, electronic equipment, piezoelectric sensor and computer-readable storage medium that can flexibly and accurately extract heart rate and have high computing resource utilization.

[0005] To achieve the above purpose, the technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a heart rate extraction method, the method comprising:

[0007] Acquire vital sign signals of the target object;

[0008] Detecting whether the vital sign signal contains respiratory harmonics to obtain a detection result;

[0009] A corresponding heart rate extraction operation is performed on the vital sign signal according to the detection result to obtain the heart rate of the target object.

[0010] In a second aspect, an embodiment of the present application provides a heart rate extraction device, the device comprising:

[0011] An acquisition module, used to acquire vital sign signals of a target object;

[0012] A respiratory harmonic detection module, used to detect whether the vital sign signal contains respiratory harmonics and obtain a detection result;

[0013] A heart rate extraction module is used to perform a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the heart rate extraction method described in any embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides a piezoelectric sensor, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the heart rate extraction method described in any embodiment of the present application.

[0016] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the heart rate extraction method described in any embodiment of the present application is implemented.

[0017] The heart rate extraction method and device, electronic device and computer-readable storage medium provided in the above embodiments of the present application obtain the vital sign signal of the target object, detect whether the vital sign signal contains respiratory harmonics, obtain the detection result, and perform corresponding heart rate extraction operations on the vital sign signal according to the detection result to obtain the heart rate of the target object. In this way, by detecting whether the vital sign signal of the target object contains respiratory harmonics, and then performing corresponding heart rate extraction operations on the vital sign signal according to the detection result to obtain the heart rate of the target object, the heart rate can be extracted flexibly and accurately, and the utilization rate of computing resources can be improved. In addition, it can provide a more accurate reference for life and health detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of an application environment applicable to an embodiment of the present application;

[0019] Figure 2 This is a flow chart of the heart rate extraction method in an embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of a heart rate extraction device in one embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of a heart rate extraction device in another embodiment of the present application;

[0022] Figure 5 This is a schematic diagram of adaptive filtering in an embodiment of the present application;

[0023] Figure 6 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0024] Figure 7 This is a schematic diagram of the structure of a piezoelectric sensor in one embodiment of the present application;

[0025] Figure 8 This is a schematic diagram of the structure of an electronic device in another embodiment of the present application;

[0026] Fig. 9 Schematic diagram of a computer-readable storage medium in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The technical solution of the present application is further elaborated in detail below in conjunction with the accompanying drawings and specific embodiments of the specification.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the implementation of this application. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0029] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as a limitation on the present application. In the description of the present application, unless otherwise specified, "multiple" means two or more.

[0030] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0031] See also Figure 1 , Figure 1 The heart rate extraction method provided in the embodiment of the present application can be applied to the following: Figure 1In the smart home system shown, the smart home system includes a piezoelectric sensor 101 and a computer device 102 .

[0032] Among them, the piezoelectric sensor 101 can be used to collect the vital sign signals of the target object when attached to the skin surface of the target object. The computer device 102 refers to a device with the function of processing and storing data, which can be a personal computer (PC), a mobile phone, a tablet computer, a wearable electronic device, a server or other electronic device with computing capabilities, which is not limited in the embodiments of the present application. The computer device 102 and the piezoelectric sensor 101 can be separate hardware devices, and the computer device 102 can receive the vital sign signals of the target object collected by the piezoelectric sensor 101, and then perform subsequent processing, such as extracting the heart rate of the vital sign signals. In the embodiments of the present application, the target object refers to a person or animal with a heart rate.

[0033] The piezoelectric sensor 101 and the computer device 102 can communicate with each other via wired or wireless means. For example, data transmission between the piezoelectric sensor 101 and the computer device 102 can be carried out in a device-to-device (Ad-Hoc) manner, or can be carried out under the coordination of a base station or a wireless access point (Access Point, AP), which is not limited in the embodiments of the present application.

[0034] In some embodiments, the piezoelectric sensor 101 is independent, and the piezoelectric sensor 101 can be set on other electronic devices. For example, the piezoelectric sensor 101 can be set on the computer device 102, and can also be set on other devices other than the computer device 102, such as a ventilator, etc., which is not limited in the embodiments of the present application. In other embodiments, the piezoelectric sensor 101 and the computer device 102 are integrated into one hardware device, and the heart rate extraction method provided in the embodiments of the present application is implemented through the integrated piezoelectric sensor 101. It can be understood that the above application environment is only an exemplary description made to facilitate the understanding of the following embodiments, and does not constitute any limitation on the application environment in which the embodiments of the present application can actually be implemented.

[0035] See also Figure 2 , is a heart rate extraction method provided in an embodiment of the present application, which can be applied to the above-mentioned computer device. The heart rate extraction method includes but is not limited to S101, S103 and S105, which are specifically described as follows:

[0036] S101, acquiring a vital sign signal of a target object.

[0037] The target object may be an object with a heart rate such as a human body. The computer device may obtain the vital sign signal of the target object by receiving the vital sign signal of the target object collected by the piezoelectric sensor itself, or may receive the vital sign signal of the target object collected by the piezoelectric sensor sent by other terminal devices such as smart phones. It should be noted that in this embodiment, the vital sign signal is taken as a discrete time signal as an example, that is, it is obtained by interval sampling of the original vital sign signal. In addition, the vital sign signal may be one frame or multiple frames, and in this embodiment, obtaining one frame of vital sign signal is taken as an example.

[0038] S103, detecting whether the vital sign signal contains respiratory harmonics, and obtaining a detection result.

[0039] It is understandable that due to the presence of respiratory harmonics, there will be some difference features between the vital sign signal containing respiratory harmonics and the vital sign signal not containing respiratory harmonics, and based on these difference features, it can be detected whether the acquired vital sign signal contains respiratory harmonics. In this embodiment, the computer device can detect whether the vital sign signal contains respiratory harmonics based on the characteristics of the peaks and troughs in the vital sign signal to obtain a detection result.

[0040] S105: Perform a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object.

[0041] Among them, according to different detection results, the heart rate extraction operation performed on the vital sign signal is also different accordingly. Specifically, when it is determined according to the detection results that the vital sign signal does not contain respiratory harmonics, the heart rate extraction can be directly performed on the vital sign signal to obtain the heart rate of the target object; when it is determined according to the detection results that the vital sign signal contains respiratory harmonics, it is necessary to first eliminate the respiratory harmonics contained in the vital sign signal, and then perform heart rate extraction on the vital sign signal after eliminating the respiratory harmonics to obtain the heart rate of the target object.

[0042] In the above embodiment of the present application, the vital sign signal of the target object is obtained, and it is detected whether the vital sign signal contains respiratory harmonics to obtain a detection result. According to the detection result, a corresponding heart rate extraction operation is performed on the vital sign signal to obtain the heart rate of the target object. In this way, by detecting whether the vital sign signal of the target object contains respiratory harmonics, and then performing a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object, it is possible to flexibly and accurately extract the heart rate and improve the utilization rate of computing resources.

[0043] In some embodiments, the detecting whether the vital sign signal contains respiratory harmonics to obtain a detection result includes:

[0044] Performing a first filtering process on the vital sign signal to obtain a breathing signal;

[0045] Detect whether the respiratory signal contains respiratory harmonics to obtain a detection result.

[0046] The computer device first performs a first filtering process on the vital sign signal, obtains a respiratory signal from the vital sign signal, and then detects whether the respiratory signal contains respiratory harmonics to obtain a detection result. Among them, the first filtering process can be performed by bandpass filtering and the like, and when the first filtering process is bandpass filtering, the corresponding cutoff frequency can be determined according to the frequency of the respiratory signal. It can be understood that since respiratory harmonics are usually included in the respiratory signal, the vital sign signal can be first filtered to obtain the respiratory signal, and then the respiratory signal can be detected to detect whether the respiratory harmonics are included in the vital sign signal. Compared with the method of directly detecting whether the vital sign signal contains respiratory harmonics, it not only reduces the amount of calculation and improves the processing speed, but also further improves the accuracy of heart rate extraction.

[0047] In some embodiments, performing a first filtering process on the vital sign signal to obtain a respiratory signal includes:

[0048] Performing a first bandpass filtering process on the acquired vital sign signal of the target object based on a preset first frequency interval to obtain a vital sign signal with baseline and high-frequency interference removed;

[0049] The vital sign signal after the baseline and high-frequency interference are removed is subjected to a second band-pass filtering process based on a preset second frequency interval to obtain a respiratory signal.

[0050] It can be understood that, due to interference from factors such as the measurement environment, the vital sign signal of the target object collected by the piezoelectric sensor may include other non-essential signals such as high-frequency interference in addition to the breathing signal, and the presence of other non-essential signals such as high-frequency interference will affect the processing of the breathing signal. Therefore, the computer device can first perform a first bandpass filtering process on the acquired vital sign signal of the target object based on a preset first frequency interval to obtain a vital sign signal with the baseline and high-frequency interference removed, and then perform a second bandpass filtering process on the vital sign signal with the baseline and high-frequency interference removed based on a preset second frequency interval to obtain a breathing signal. The first frequency interval can be set according to the frequency range of non-essential signals such as the baseline and high-frequency interference, for example, the first frequency interval can be set to 0.1 to 4 Hz. The second frequency interval can be set according to the frequency range of the breathing signal, for example, the second frequency interval can be set to 0.1 to 0.5 Hz. In practical applications, it is also possible to obtain a breathing signal by performing a bandpass filtering operation on the vital sign signal. In this way, by performing two different bandpass filtering processes on the vital sign signal of the target object in sequence, the breathing signal of the target object is obtained, thereby further improving the accuracy of heart rate extraction.

[0051] In some embodiments, the detecting whether the respiratory signal contains respiratory harmonics to obtain a detection result includes:

[0052] Performing peak detection on the respiratory signal to obtain a first peak sequence and a first trough sequence;

[0053] Processing the first peak sequence and the first trough sequence respectively according to a preset rule to obtain a second peak sequence and a second trough sequence;

[0054] It is determined whether the waveform determined based on the second wave peak sequence and the second wave trough sequence satisfies a preset symmetry condition, and a detection result of whether the respiratory signal contains respiratory harmonics is obtained.

[0055] Among them, the purpose of performing peak detection on the respiratory signal is to find out all the peaks and troughs in the respiratory signal to obtain a first peak sequence and a first trough sequence. Specifically, in the respiratory signal, points whose amplitudes are greater than both the left and right sides are sequentially searched for as peaks, and points whose amplitudes are less than both the left and right sides are troughs. It should be noted that the first peak sequence includes not only the amplitude of each peak, but also the corresponding position, i.e., the time sequence number, and the first trough sequence includes not only the amplitude of each trough, but also the corresponding position, i.e., the time sequence number. Here, based on the difference characteristics between the respiratory signal containing respiratory harmonics and the respiratory signal not containing respiratory harmonics, the first peak sequence and the first trough sequence can be processed separately according to preset rules, such as deleting the peaks and troughs that are obviously not respiratory harmonics, etc., to obtain the second peak sequence and the second trough sequence. Preferably, the processing of the first peak sequence and the first trough sequence according to a preset rule to obtain a second peak sequence and a second trough sequence includes: deleting peaks whose ratio of amplitude to maximum peak amplitude in the first peak sequence is less than a preset first ratio threshold, and peaks with small amplitudes among adjacent peaks whose position interval is less than a preset first distance threshold, and inserting a target peak among adjacent peaks whose position interval is greater than a preset second distance threshold to obtain a second peak sequence; wherein the second distance threshold is greater than the first distance threshold, and the amplitude of the target peak is equal to the amplitude of the adjacent peaks. The target peak is the average value of the values, and the position of the target peak is the average value of the adjacent peak positions; the troughs whose ratio of amplitude to the maximum trough amplitude in the first trough sequence is less than the preset second ratio threshold, and the troughs with small amplitudes in the adjacent troughs whose position interval is less than the preset third distance threshold are deleted, and a target trough is inserted in the adjacent troughs whose position interval is greater than the preset fourth distance threshold, to obtain a second trough sequence; wherein the fourth distance threshold is greater than the third distance threshold, the amplitude of the target trough is the average value of the adjacent trough amplitudes, and the position of the target trough is the average value of the adjacent trough positions. Here, the first ratio threshold and the second ratio threshold can be set according to actual needs, for example, the first ratio threshold and the second ratio threshold can be set to 0.5, so as to delete the peaks whose ratio of amplitude to the maximum peak amplitude in the first peak sequence is less than 0.5, and delete the troughs whose ratio of amplitude to the maximum trough amplitude in the first trough sequence is less than 0.5.The first distance threshold, the second distance threshold, the third distance threshold and the fourth distance threshold can be set according to actual needs. For example, the first distance threshold and the second distance threshold can be set according to the average value of the position interval between adjacent peaks in the first peak sequence, and the third distance threshold and the fourth distance threshold can be set according to the average value of the position interval between adjacent troughs in the first trough sequence. Of course, the first distance threshold and the second distance threshold can also be set according to the position interval between adjacent peaks in a normal vital sign signal, and the third distance threshold and the fourth distance threshold can be set according to the position interval between adjacent troughs in a normal vital sign signal. It should be noted that the adjacent peaks refer to the two peaks with the smallest position interval, and the adjacent troughs refer to the two troughs with the smallest position interval, wherein the position interval refers to the difference in time sequence numbers corresponding to the peak points or trough points. In this way, by deleting and filling the peak sequence and the trough sequence in the respiratory signal of the target object, a new peak sequence and a new trough sequence that can be used to determine whether the waveform is symmetrical are obtained, which is simple to operate and improves the speed of heart rate extraction.

[0056] In some embodiments, the determining whether the waveform determined based on the second peak sequence and the second trough sequence satisfies a preset symmetry condition to obtain a detection result of whether the respiratory signal contains respiratory harmonics includes:

[0057] Obtaining a first ratio of a peak amplitude to a trough amplitude in each cycle of a waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle;

[0058] According to a first ratio of the peak amplitude to the trough amplitude in each period, obtaining an average value of the first ratio;

[0059] When the average value of the first ratio does not satisfy a preset first symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

[0060] Among them, since the second wave peak sequence includes not only the amplitude of each wave peak, but also the corresponding position, i.e., the time serial number, and the second wave trough sequence includes not only the amplitude of each wave trough, but also the corresponding position, i.e., the time serial number, therefore, according to the corresponding position of each wave peak and the corresponding position of each wave trough, the adjacent wave peaks and wave troughs in the waveform determined based on the second wave peak sequence and the second wave trough sequence can be known, and the wave peak amplitude and wave trough amplitude in each cycle can be known. After obtaining the first ratio of the wave peak amplitude to the wave trough amplitude in each cycle, the average value of the first ratio can be obtained in combination with the number of cycles contained in the waveform determined by the second wave peak sequence and the second wave trough sequence. Among them, the first symmetry condition can be set according to the actual situation. For example, the first symmetry condition can be set to the average value of the first ratio being greater than 1-a1 and less than a1, wherein a1 can be 1.3 or 1.35, etc. When the average value of the first ratio satisfies the preset first symmetry condition, it indicates that the waveform determined based on the second peak sequence and the second trough sequence is symmetrical up and down; otherwise, it indicates that the waveform determined based on the second peak sequence and the second trough sequence is asymmetrical up and down. When the average value of the first ratio does not satisfy the preset first symmetry condition, that is, the waveform determined based on the second peak sequence and the second trough sequence is asymmetrical up and down, it indicates that respiratory harmonics are detected, that is, the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics. In this way, the detection result of whether the respiratory signal contains respiratory harmonics is determined by detecting whether the waveform determined based on the second peak sequence and the second trough sequence is symmetrical. The operation is simple and fast, which further improves the accuracy and speed of heart rate extraction.

[0061] In some embodiments, the determining whether the waveform determined based on the second peak sequence and the second trough sequence satisfies a preset symmetry condition to obtain a detection result of whether the respiratory signal contains respiratory harmonics includes:

[0062] Obtaining a second ratio of the first amplitude to the second amplitude in each cycle of the waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle, the first amplitude is an amplitude corresponding to a position difference between a peak position and a trough position, and the second amplitude is an amplitude corresponding to a position difference between a trough position and a peak position;

[0063] According to a second ratio of the first amplitude to the second amplitude in each period, obtaining an average value of the second ratio;

[0064] When the average value of the second ratio does not satisfy a preset second symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

[0065] Among them, since the second wave peak sequence includes not only the amplitude of each wave peak, but also the corresponding position, i.e., the time serial number, and the second wave trough sequence includes not only the amplitude of each wave trough, but also the corresponding position, i.e., the time serial number, therefore, according to the corresponding position of each wave peak and the corresponding position of each wave trough, the adjacent wave peaks and wave troughs in the waveform determined based on the second wave peak sequence and the second wave trough sequence can be known, and the wave peak amplitude and wave trough amplitude as well as the wave peak position and wave trough position in each cycle can be known. After obtaining the second ratio of the first amplitude to the second amplitude in each cycle, the average value of the second ratio can be obtained in combination with the number of cycles contained in the waveform determined by the second wave peak sequence and the second wave trough sequence. Among them, the second symmetry condition can be set according to the actual situation. For example, the second symmetry condition can be set to the average value of the second ratio being greater than 1-a2 and less than a2, wherein a2 can be 1.3 or 1.4, etc. When the average value of the second ratio meets the preset second symmetry condition, it means that the waveform determined based on the second peak sequence and the second trough sequence is symmetrical on the left and right; otherwise, it means that the waveform determined based on the second peak sequence and the second trough sequence is asymmetrical on the left and right. When the average value of the second ratio does not meet the preset second symmetry condition, that is, the waveform determined based on the second peak sequence and the second trough sequence is asymmetrical on the left and right, it means that respiratory harmonics are detected, that is, the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics. In this way, the detection result of whether the respiratory signal contains respiratory harmonics is determined by detecting whether the waveform determined based on the second peak sequence and the second trough sequence is symmetrical, and the operation is simple and fast, which further improves the accuracy and speed of heart rate extraction.

[0066] In some embodiments, performing a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object includes:

[0067] When it is determined according to the detection result that the respiratory signal contains respiratory harmonics, respiratory harmonic cancellation processing is performed on the respiratory signal, and heart rate extraction is performed on the first heartbeat signal obtained after the respiratory harmonic cancellation processing to obtain the heart rate of the target object.

[0068] When it is determined according to the detection result that the respiratory signal does not contain respiratory harmonics, a second filtering process is performed on the vital sign signal, and a heart rate extraction is performed on the second heartbeat signal obtained after the second filtering process to obtain the heart rate of the target object.

[0069] Specifically, when it is determined according to the detection result that the respiratory signal contains respiratory harmonics, it means that the respiratory harmonics need to be eliminated to improve the accuracy of heart rate extraction. At this time, the respiratory signal is subjected to respiratory harmonic cancellation processing to obtain a first heartbeat signal after the respiratory harmonic cancellation processing, and the first heartbeat signal obtained after the respiratory harmonic cancellation processing is subjected to heart rate extraction to obtain the heart rate of the target object. When it is determined according to the detection result that the respiratory signal does not contain respiratory harmonics, it means that there is no need to perform respiratory harmonic elimination processing. At this time, the vital sign signal can be directly subjected to a second filtering processing to obtain a second heartbeat signal, and the second heartbeat signal obtained after the second filtering processing is subjected to heart rate extraction to obtain the heart rate of the target object. Among them, the second filtering processing can adopt a bandpass filtering processing and the like, and when the second filtering processing is a bandpass filtering processing, the corresponding cutoff frequency can be determined according to the frequency of the heartbeat signal. It should be noted that the above-mentioned method for extracting the heart rate of the first heartbeat signal or the second heartbeat signal can adopt an existing heart rate extraction method, such as an autocorrelation function method or a spectrum estimation method, which will not be described in detail here. In this way, when the target object's vital sign signal does not contain respiratory harmonics, there is no need to perform respiratory harmonic cancellation processing, saving computing resources; and when the target object's vital sign signal contains respiratory harmonics, respiratory harmonic cancellation processing is performed to improve the accuracy of heart rate extraction.

[0070] In some embodiments, performing respiratory harmonic cancellation processing on the respiratory signal includes:

[0071] The respiratory signal is used as the input signal of the adaptive filter, and the vital sign signal with baseline and high-frequency interference removed is used as the expected signal of the adaptive filter. The parameters of the adaptive filter are continuously adjusted and updated through an adaptive filtering algorithm to obtain the first heartbeat signal after respiratory harmonics are offset.

[0072] The computer device can obtain the power spectrum function of the respiratory signal by estimating the power spectrum of the autocorrelation function of the respiratory signal, and the maximum peak of the power spectrum function is the fundamental frequency of the respiratory signal. Based on the fundamental frequency of the respiratory signal, a mathematical model of the respiratory harmonic signal can be established to obtain the respiratory harmonic signal. Then, the respiratory signal is used as the main input of the adaptive filter, the vital sign signal with baseline and high-frequency interference removed is used as the expected reference input of the adaptive filter, and the respiratory harmonic signal is used as the output of the adaptive filter, wherein the adaptive filter can continuously iterate and update the adaptive filter parameters using algorithms such as the least mean square, when the square of the difference between the vital sign signal with baseline and high-frequency interference removed and the respiratory harmonic signal is the smallest, the difference between the vital sign signal with baseline and high-frequency interference removed and the respiratory harmonic signal is the first heartbeat signal. In this way, the respiratory signal is subjected to respiratory harmonic cancellation processing through adaptive filtering to obtain the heartbeat signal after respiratory harmonic cancellation, and then the heart rate of the target object is extracted based on the heartbeat signal, further improving the accuracy of heart rate extraction.

[0073] On the other hand, please refer to Figure 3 , a heart rate extraction device is also provided, the device comprising: an acquisition module 11, used to acquire the vital sign signal of the target object; a respiratory harmonic detection module 12, used to detect whether the vital sign signal contains respiratory harmonics and obtain a detection result; a heart rate extraction module 13, used to perform a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object.

[0074] In some embodiments, the respiratory harmonic detection module 12 includes: a filtering submodule 120, which is used to perform a first filtering process on the vital sign signal to obtain a respiratory signal; and a detection submodule 121, which is used to detect whether the respiratory signal contains respiratory harmonics to obtain a detection result.

[0075] In some embodiments, the filtering submodule 120 is specifically used to: perform a first bandpass filtering process on the acquired vital sign signal of the target object based on a preset first frequency interval to obtain a vital sign signal with the baseline and high-frequency interference removed; perform a second bandpass filtering process on the vital sign signal with the baseline and high-frequency interference removed based on a preset second frequency interval to obtain a breathing signal.

[0076] In some embodiments, the detection submodule 121 is specifically used to:

[0077] Performing peak detection on the respiratory signal to obtain a first peak sequence and a first trough sequence;

[0078] Processing the first peak sequence and the first trough sequence respectively according to a preset rule to obtain a second peak sequence and a second trough sequence;

[0079] It is determined whether the waveform determined based on the second wave peak sequence and the second wave trough sequence satisfies a preset symmetry condition, and a detection result of whether the respiratory signal contains respiratory harmonics is obtained.

[0080] In some embodiments, the detection submodule 121 is specifically used to:

[0081] Delete the peaks whose ratio of amplitude to maximum peak amplitude is less than a preset first ratio threshold in the first peak sequence, and the peaks with small amplitudes among adjacent peaks whose position interval is less than a preset first distance threshold, and insert a target peak among adjacent peaks whose position interval is greater than a preset second distance threshold, to obtain a second peak sequence; wherein the second distance threshold is greater than the first distance threshold, the amplitude of the target peak is the average of the amplitudes of adjacent peaks, and the position of the target peak is the average of the positions of adjacent peaks;

[0082] Delete the troughs in the first trough sequence whose ratio of amplitude to maximum trough amplitude is less than a preset second ratio threshold and the troughs with small amplitudes in adjacent troughs whose position interval is less than a preset third distance threshold, and insert a target trough in adjacent troughs whose position interval is greater than a preset fourth distance threshold to obtain a second trough sequence; wherein the fourth distance threshold is greater than the third distance threshold, the amplitude of the target trough is the average of the amplitudes of adjacent troughs, and the position of the target trough is the average of the positions of adjacent troughs.

[0083] In some embodiments, the detection submodule 121 is specifically used to:

[0084] Obtaining a first ratio of a peak amplitude to a trough amplitude in each cycle of a waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle;

[0085] According to a first ratio of the peak amplitude to the trough amplitude in each period, obtaining an average value of the first ratio;

[0086] When the average value of the first ratio does not satisfy a preset first symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

[0087] In some embodiments, the detection submodule 121 is specifically used to:

[0088] Obtaining a second ratio of the first amplitude to the second amplitude in each cycle of the waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle, the first amplitude is an amplitude corresponding to a position difference between a peak position and a trough position, and the second amplitude is an amplitude corresponding to a position difference between a trough position and a peak position;

[0089] According to a second ratio of the first amplitude to the second amplitude in each period, obtaining an average value of the second ratio;

[0090] When the average value of the second ratio does not satisfy a preset second symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

[0091] In some embodiments, the heart rate extraction module 13 is specifically used to:

[0092] When it is determined according to the detection result that the respiratory signal contains respiratory harmonics, respiratory harmonic cancellation processing is performed on the respiratory signal, and heart rate extraction is performed on the first heartbeat signal obtained after the respiratory harmonic cancellation processing to obtain the heart rate of the target object.

[0093] When it is determined according to the detection result that the respiratory signal does not contain respiratory harmonics, a second filtering process is performed on the vital sign signal, and a heart rate extraction is performed on the second heartbeat signal obtained after the second filtering process to obtain the heart rate of the target object.

[0094] In some embodiments, the heart rate extraction module 13 is specifically used to:

[0095] The respiratory signal is used as the input signal of the adaptive filter, and the vital sign signal with baseline and high-frequency interference removed is used as the expected signal of the adaptive filter. The parameters of the adaptive filter are continuously adjusted and updated through an adaptive filtering algorithm to obtain the first heartbeat signal after respiratory harmonics are offset.

[0096] In some embodiments, the heart rate extraction module 13 is specifically used to:

[0097] Performing autocorrelation function power spectrum estimation on the respiratory signal, and determining the maximum peak value of the power spectrum function of the respiratory signal obtained as the fundamental frequency of the respiratory signal;

[0098] Based on the fundamental frequency of the respiratory signal, a respiratory harmonic signal mathematical model is established to obtain the respiratory harmonic signal;

[0099] The respiratory signal is used as the main input of the adaptive filter, the vital sign signal with the baseline and high-frequency interference removed is used as the expected reference input of the adaptive filter, and the respiratory harmonic signal is used as the output of the adaptive filter. The least mean square algorithm is used to continuously iterate and update the adaptive filter parameters until the square of the difference between the vital sign signal with the baseline and high-frequency interference removed and the respiratory harmonic signal is minimized, and the difference between the vital sign signal with the baseline and high-frequency interference removed and the respiratory harmonic signal is determined as the first heartbeat signal.

[0100] It should be noted that: the heart rate extraction device provided in the above embodiment only uses the division of the above program modules as an example to illustrate the process of implementing the heart rate extraction. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the method steps described above. In addition, the heart rate extraction device provided in the above embodiment and the heart rate extraction method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0101] In order to have a more systematic understanding of the heart rate extraction method provided in the embodiment of the present application, the following is a description in conjunction with a specific example. In this example, the heart rate extraction device is a piezoelectric sensor or a cloud server as an example. Figure 4 The heart rate extraction device provided in this example includes the following modules: a filtering module 21, a respiratory harmonic detection module 22, a respiratory harmonic elimination module 23 and a heart rate extraction module 24; wherein,

[0102] First, the filtering module 21 passes a frame of signal x[n] collected by the piezoelectric sensor, where n=1…N (n is a discrete time sequence number and N is the total length of a frame of data), through a Butterworth bandpass filter (not limited to other FIR or IIR bandpass filters) with a cutoff frequency of 0.1 to 4 Hz to obtain a vital sign signal x[n] with baseline and high-frequency interference removed. m [n], and obtain the breathing signal x through a Butterworth bandpass filter with a cutoff frequency of 0.1 to 0.5 Hz (not limited to using other FIR or IIR bandpass filters) b [n].

[0103] It should be noted that the filtering module 21 can also process the original signal x[n] by wavelet decomposition, wavelet denoising and other methods to obtain the vital sign signal x[n] without baseline and high-frequency interference. m [n] and breathing signal x b [n] etc.

[0104] As for the respiratory harmonic detection module 22, the functions of the respiratory harmonic detection module 22 mainly include peak detection, peak deletion and peak filling, and symmetry judgment.

[0105] Regarding peak detection, in the breathing signal x b The point in [n] whose value is greater than both the left and right sides is the peak, and the peak value x is saved. p [n], n = 1ΛN p and the peak position l p [n], n = 1ΛN p , where N p is the number of peaks; and in the respiratory signal x b [n]Sequentially search for points where the value is smaller than both the left and right sides, and save the trough value x v [n], n = 1ΛN v and trough position l v [n], n = 1ΛN v , where N v is the number of troughs.

[0106] Regarding peak deletion and peak filling, first solve the maximum value of the peak modulus, and delete the peaks with modulus less than half of the maximum value in the peak points; solve the maximum value of the trough modulus, and delete the troughs with modulus less than half of the maximum value in the trough points; then, according to the reasonable range of the position difference between two adjacent peaks or troughs, the minimum value l min and the maximum value l max , delete intervals less than l min The peak with smaller modulus value among two adjacent peaks and the interval less than l is deleted min The trough with smaller modulus value in the two adjacent troughs is greater than l max A new peak is inserted between two adjacent peaks. The new peak value is the average value of the two peak values, and the new peak position is the average value of the two peak positions. max A new trough is inserted between two adjacent troughs, and the new trough value is the average of the two trough values, and the new trough position is the average of the two trough positions. After peak deletion and peak filling, the new peak value sequence is X p '[n], n = 1ΛN p ', the corresponding position sequence is l p '[n], n = 1ΛN p ', and the new trough value sequence is X v '[n], n = 1ΛN v ', the corresponding position sequence is l v '[n], n = 1ΛN v '.

[0107] Regarding symmetry judgment, adjacent peaks and troughs form a complete cycle. The ratio of the peak modulus to the trough modulus in each cycle is calculated. The average value of the ratio of all complete cycles in a frame of data is calculated. like If it is greater than α1 or less than 1-α1 (α1 can be 1.3, etc.), it means that the waveform is asymmetrical. If it is greater than 1-α1 and less than α1, it means that the waveform is symmetrical up and down; calculate the ratio τ2 of the difference modulus between the peak and trough position and the difference modulus between the trough and peak position in each cycle, and calculate the average value of the ratio of all complete cycles in a frame of data like If it is greater than α2 or less than 1-α2 (α2 can be 1.3, etc.), it means that the waveform is asymmetrical. If it is greater than 1-α2 and less than α2, it means that the waveform is symmetrical.

[0108] If the waveform is asymmetrical up and down or left and right, it means that respiratory harmonics are detected; otherwise, it means that there are no respiratory harmonics.

[0109] As for the respiratory harmonic elimination module 23, the functions of the respiratory harmonic elimination module 23 mainly include mathematical modeling of respiratory harmonic signals and adaptive filtering harmonic cancellation; wherein,

[0110] The mathematical modeling of respiratory harmonic signals includes the following processes:

[0111] First, the breathing signal x generated by the filtering module 21 is b [n] Estimating the power spectrum of the autocorrelation function to obtain the power spectrum function P(f) of the respiratory signal. The maximum peak value of the power spectrum function is the fundamental frequency f0 of the respiratory signal.

[0112] Next, a mathematical model of respiratory harmonic signals is established

[0113]

[0114] Where m is the order of respiratory harmonics (the respiratory frequency range for adults is 0.1-0.5 Hz, and the heart rate range is 0.8-2 Hz. Considering the influence of respiratory harmonics on the heart rate frequency signal, the order here can be between 2 and 20). i , and φ i are the amplitude, angular frequency and phase of the i-th order harmonic of breathing respectively. Through the transformation of trigonometric formula, the amplitude and phase form of the mathematical model can be converted into the in-phase and orthogonal components s I (n) and s Q (n) and coefficients α(n) and β(n), where s I (n)=[cos(ω1n), cos(ω2n),…, cos(ω mn)],s Q (n)=[sin(ω1n),sin(ω2n),…,sin(ω m n)], α(n)=[α1, α2,…,α m ], β(n)=[β1, β2,…,β m ].

[0115] Regarding adaptive filtering harmonic cancellation, the following process is included:

[0116] See also Figure 5 , which is a schematic diagram of adaptive filtering provided in this example, wherein the vital sign signal x obtained by the filtering module 21 is m [n] is taken as the expected signal, and the breathing signal x obtained by the filter module 21 b [n] is used as the input signal and the respiratory harmonic signal is used as the adaptive filtering output signal. The difference between the expected signal and the filtered output signal is calculated by using the LMS (least mean square) algorithm (other LMS-type or RLS recursive least squares algorithms can also be used instead). The adaptive filter parameters are continuously iterated and updated. When the square of the difference between the two reaches a steady state, the difference between the two signals is the heartbeat signal.

[0117] Among them, the adaptive filter parameter α is defined as the initialization time n = 0 i and β i is a zero vector, and the steps of iteration and updating using the LMS algorithm are as follows:

[0118] (1) At time n, according to the expected signal x m [n] and respiratory harmonic signal s(n), calculate the error signal e(n): e(n) = x m (n)-s(n).

[0119] (2) Update the coefficients recursively:

[0120]

[0121]

[0122] Among them, μ is the iteration step size.

[0123] (3) Repeat the above steps (1) and (2) until the algorithm reaches a steady state, and the heartbeat signal x after respiratory harmonics are offset can be obtained. h [n].

[0124] For the heart rate extraction module 24, if no respiratory harmonics are detected, the original signal x[n] may be passed through a Butterworth bandpass filter with a cutoff frequency of 0.8 to 2 Hz (not limited to using other FIR or IIR bandpass filters) to obtain a heartbeat signal x h[n]; If respiratory harmonics are detected, the heartbeat signal x after respiratory harmonics are offset can be obtained h [n]. Then, the heartbeat signal x h [n] A more accurate heart rate can be obtained by using the autocorrelation function method or the spectrum estimation method.

[0125] In this way, the heart rate extraction device provided in the above embodiment can eliminate the influence of high-order harmonics of breathing and obtain a more accurate heart rate; and for signals in which no respiratory harmonics are detected, there is no need for harmonic cancellation processing; in addition, whether the respiratory waveform is symmetrical can provide more dimensional references for life and health detection.

[0126] On the other hand, please refer to Figure 6 , an electronic device is also provided, including a processor 211, a memory 212, and a computer program stored in the memory 212 and executable by the processor 211, the computer program when executed by the processor 211 implements the heart rate extraction method provided in any embodiment of the present application, and can achieve the same technical effect, to avoid repetition, it is not repeated here. The electronic device can be a smart phone, a personal computer, etc.

[0127] On the other hand, please refer to Figure 7 , also provides a piezoelectric sensor, including a processor 111, a memory 112, and a computer program stored in the memory 112 and executable by the processor 111, the computer program when executed by the processor 111 implements the heart rate extraction method provided in any embodiment of the present application, and can achieve the same technical effect, to avoid repetition, no further description is given here. The piezoelectric sensor may include Figure 6 The electronic device shown has the same hardware composition, and further includes a collection sensing component for collecting vital sign signals of the target object.

[0128] See also Figure 8 , is an optional hardware structure block diagram of the electronic device provided in the embodiment of the present application. Figure 8As shown, electronic devices may have relatively large differences due to different configurations or performances, and may include one or more processors (Processing Units, CPU) 1110 (the processor 1110 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1130 for storing data, and one or more storage media 1120 (such as one or more mass storage devices) for storing application programs 1123 or data 1122. Among them, the memory 1130 and the storage medium 1120 can be short-term storage or permanent storage. The program stored in the storage medium 1120 may include one or more modules, each of which may include a series of instruction operations in heart rate extraction. Furthermore, the processor 1110 can be configured to communicate with the storage medium 1120 to execute a series of instruction operations in the storage medium 1120 on the electronic device. The electronic device may also include one or more power supplies 1160, one or more wired or wireless network interfaces 1150, one or more input and output interfaces 1140, and / or one or more operating systems 1121, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, FreeBSD TM, etc.

[0129] The input / output interface 1140 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the electronic device. In one example, the input / output interface 1140 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the input / output interface 1140 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0130] It can be understood by those skilled in the art that Figure 8 The structure shown is only for illustration and does not limit the structure of the above terminal device. Figure 8 More or fewer components as shown, or with Figure 8 Different configurations are shown.

[0131] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned heart rate extraction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0132] Fig. 9 800 is a block diagram of a computer-readable storage medium 800 provided in an embodiment of the present application. The computer-readable storage medium 800 stores program code, and the program code can be called by a processor to execute the smart home control method provided in an embodiment of the present application. The computer-readable storage medium 800 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. Optionally, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for program code 810 that executes any method step in the above method. These program codes can be read from one or more computer program products or written to one or more computer program products. The program code 810 can be compressed, for example, in an appropriate form.

[0133] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A heart rate extraction method, characterized in that: The method comprises: Acquire vital sign signals of the target object; Detecting whether the vital sign signal contains respiratory harmonics to obtain a detection result; According to the detection result, if the vital sign signal contains respiratory harmonics, performing a corresponding heart rate extraction operation on the vital sign signal based on the vital sign signal after eliminating the respiratory harmonics to obtain the heart rate of the target object; Wherein, the detecting whether the vital sign signal contains respiratory harmonics to obtain the detection result includes: Performing a first filtering process on the vital sign signal to obtain a breathing signal; Performing peak detection on the respiratory signal to obtain a first peak sequence and a first trough sequence; Processing the first peak sequence and the first trough sequence respectively according to a preset rule to obtain a second peak sequence and a second trough sequence; It is determined whether the waveform determined based on the second wave peak sequence and the second wave trough sequence satisfies a preset symmetry condition, and a detection result of whether the respiratory signal contains respiratory harmonics is obtained.

2. The method according to claim 1, characterized in that The first filtering process is performed on the vital sign signal to obtain a breathing signal, including: Performing a first bandpass filtering process on the acquired vital sign signal of the target object based on a preset first frequency interval to obtain a vital sign signal with baseline and high-frequency interference removed; The vital sign signal after the baseline and high-frequency interference are removed is subjected to a second band-pass filtering process based on a preset second frequency interval to obtain a respiratory signal.

3. The method according to claim 1, characterized in that The processing of the first peak sequence and the first trough sequence according to a preset rule to obtain a second peak sequence and a second trough sequence includes: Delete the peaks whose ratio of amplitude to maximum peak amplitude is less than a preset first ratio threshold in the first peak sequence, and the peaks with small amplitudes among adjacent peaks whose position interval is less than a preset first distance threshold, and insert a target peak among adjacent peaks whose position interval is greater than a preset second distance threshold, to obtain a second peak sequence; wherein the second distance threshold is greater than the first distance threshold, the amplitude of the target peak is the average of the amplitudes of adjacent peaks, and the position of the target peak is the average of the positions of adjacent peaks; Delete the troughs in the first trough sequence whose ratio of amplitude to maximum trough amplitude is less than a preset second ratio threshold and the troughs with small amplitudes in adjacent troughs whose position interval is less than a preset third distance threshold, and insert a target trough in adjacent troughs whose position interval is greater than a preset fourth distance threshold to obtain a second trough sequence; wherein the fourth distance threshold is greater than the third distance threshold, the amplitude of the target trough is the average of the amplitudes of adjacent troughs, and the position of the target trough is the average of the positions of adjacent troughs.

4. The method according to claim 1, characterized in that The determining whether the waveform determined based on the second peak sequence and the second trough sequence satisfies a preset symmetry condition to obtain a detection result of whether the respiratory signal contains respiratory harmonics includes: Obtaining a first ratio of a peak amplitude to a trough amplitude in each cycle of a waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle; According to a first ratio of the peak amplitude to the trough amplitude in each period, obtaining an average value of the first ratio; When the average value of the first ratio does not satisfy a preset first symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

5. The method according to claim 1, characterized in that The determining whether the waveform determined based on the second peak sequence and the second trough sequence satisfies a preset symmetry condition to obtain a detection result of whether the respiratory signal contains respiratory harmonics includes: Obtaining a second ratio of the first amplitude to the second amplitude in each cycle of the waveform determined based on the second peak sequence and the second trough sequence; wherein adjacent peaks and troughs form one cycle, the first amplitude is an amplitude corresponding to a position difference between a peak position and a trough position, and the second amplitude is an amplitude corresponding to a position difference between a trough position and a peak position; According to a second ratio of the first amplitude to the second amplitude in each period, obtaining an average value of the second ratio; When the average value of the second ratio does not satisfy a preset second symmetry condition, it is determined that the respiratory signal contains respiratory harmonics; otherwise, it is determined that the respiratory signal does not contain respiratory harmonics.

6. The method according to any one of claims 1 to 5, characterized in that: The performing a corresponding heart rate extraction operation on the vital sign signal according to the detection result to obtain the heart rate of the target object includes: When it is determined according to the detection result that the respiratory signal contains respiratory harmonics, the respiratory signal is subjected to respiratory harmonic cancellation processing, and the heart rate is extracted from the first heartbeat signal obtained after the respiratory harmonic cancellation processing to obtain the heart rate of the target object; When it is determined according to the detection result that the respiratory signal does not contain respiratory harmonics, a second filtering process is performed on the vital sign signal, and a heart rate extraction is performed on the second heartbeat signal obtained after the second filtering process to obtain the heart rate of the target object.

7. The method according to claim 6, characterized in that The performing respiratory harmonic cancellation processing on the respiratory signal comprises: The respiratory signal is used as the input signal of the adaptive filter, and the vital sign signal with the baseline and high-frequency interference removed is used as the expected signal of the adaptive filter. The parameters of the adaptive filter are continuously adjusted and updated through an adaptive filtering algorithm to obtain the first heartbeat signal after the respiratory harmonics are offset; wherein the vital sign signal with the baseline and high-frequency interference removed is obtained by performing a first bandpass filtering process on the acquired vital sign signal of the target object based on a preset first frequency interval.

8. The method according to claim 7, characterized in that The method uses the respiratory signal as the input signal of the adaptive filter, removes the baseline and high-frequency interference of the vital sign signal as the expected signal of the adaptive filter, and continuously adjusts and updates the parameters of the adaptive filter through the adaptive filtering algorithm to obtain the first heartbeat signal after the respiratory harmonics are offset, including: Performing autocorrelation function power spectrum estimation on the respiratory signal, and determining the maximum peak value of the power spectrum function of the respiratory signal obtained as the fundamental frequency of the respiratory signal; Based on the fundamental frequency of the respiratory signal, a respiratory harmonic signal mathematical model is established to obtain the respiratory harmonic signal; The respiratory signal is used as the main input of the adaptive filter, the vital sign signal with the baseline and high-frequency interference removed is used as the expected reference input of the adaptive filter, and the respiratory harmonic signal is used as the output of the adaptive filter. The least mean square algorithm is used to continuously iterate and update the adaptive filter parameters until the square of the difference between the vital sign signal with the baseline and high-frequency interference removed and the respiratory harmonic signal is minimized, and the difference between the vital sign signal with the baseline and high-frequency interference removed and the respiratory harmonic signal is determined as the first heartbeat signal.

9. A heart rate extraction device, characterized in that: The device comprises: An acquisition module, used to acquire vital sign signals of a target object; A respiratory harmonic detection module, used to detect whether the vital sign signal contains respiratory harmonics and obtain a detection result; a heart rate extraction module, configured to, according to the detection result, if the vital sign signal contains respiratory harmonics, perform a corresponding heart rate extraction operation on the vital sign signal based on the vital sign signal after eliminating the respiratory harmonics, so as to obtain the heart rate of the target object; Among them, the respiratory harmonic detection module is specifically used to perform a first filtering process on the vital sign signal to obtain a respiratory signal; perform peak detection on the respiratory signal to obtain a first peak sequence and a first trough sequence; process the first peak sequence and the first trough sequence respectively according to preset rules to obtain a second peak sequence and a second trough sequence; determine whether the waveform determined based on the second peak sequence and the second trough sequence meets a preset symmetry condition, and obtain a detection result of whether the respiratory signal contains respiratory harmonics.

10. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable by the processor, wherein the computer program implements the heart rate extraction method according to any one of claims 1 to 8 when executed by the processor.

11. A piezoelectric sensor, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable by the processor, wherein the computer program implements the heart rate extraction method according to any one of claims 1 to 8 when executed by the processor.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the heart rate extraction method according to any one of claims 1 to 8 is implemented.

Images