Physiological parameter determination method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a physiological parameter determination method and device, equipment and a storage medium, and the method comprises the steps: obtaining a first volume wave signal of a target user, the volume wave signal being used for reflecting the physiological condition of the target user; performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal; performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a respiration signal of the target user; physiological parameter calculation is carried out according to the signal features of the breathing signals, physiological parameters of the target user are determined, and the physiological parameters at least comprise breathing parameters. Through the mode, the volume wave signals can be processed for the first time in a filtering mode to filter out interference noise as much as possible, then the volume wave signals are processed for the second time through a wavelet decomposition method to further decompose the signals, the accuracy of respiratory signal extraction is improved, and the calculated respiratory parameters are more accurate.

Description

Technical Field

[0001] The present invention relates to the field of physiological monitoring technology, and in particular to a method and device for determining physiological parameters, equipment and storage medium. Background Art

[0002] As one of the most important parameters of human physiology, the monitoring of respiratory parameters such as respiratory rate is of great significance in the prevention and control of acute respiratory dysfunction. With the continuous development of current science and technology, more and more advanced technologies are used in the monitoring of respiratory parameters. Currently, the more mature applications include chest impedance monitoring, varistor monitoring, temperature monitoring and gas flow monitoring. Although these methods can well realize the monitoring of respiratory parameters, they usually require electrodes to be attached to the body separately, which is troublesome to operate and easily causes psychological and physiological burdens to patients. In addition, the cost is relatively high.

[0003] Therefore, extracting the breathing-related waveform from the collected volume wave signal is not only very economical, but also does not require a separate electrode patch for monitoring breathing, and the operation is more convenient. However, since the volume wave signal is often mixed with various types of physiological signals generated by the user's physiological movement behavior, and there is frequency overlap between various types of signals, it is difficult to extract the breathing-related waveform from the volume wave signal, and the accuracy is not high, which will adversely affect the accuracy of the respiratory parameters finally monitored. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and device for determining physiological parameters, equipment and storage medium, which can solve the problem of high difficulty and low accuracy in extracting respiratory waveforms from volume wave signals in the prior art.

[0005] To achieve the above object, the present invention provides a method for determining a physiological parameter in a first aspect, the method comprising:

[0006] Acquire a first volume wave signal of a target user, where the volume wave signal is used to reflect the physiological condition of the target user;

[0007] performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal;

[0008] performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user;

[0009] Physiological parameters are calculated using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, where the physiological parameters at least include breathing parameters.

[0010] In a feasible implementation, the second volume wave signal includes a first AC component and a second AC component of an optical signal of at least two wavelengths, and the signal decomposition algorithm includes a wavelet decomposition algorithm. Then, performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain the breathing signal of the target user includes:

[0011] Acquire wavelet decomposition parameters, wherein the wavelet decomposition parameters at least include a mother wavelet function and a decomposition scale of the wavelet decomposition algorithm;

[0012] Using the mother wavelet function and the decomposition scale to perform wavelet decomposition on the first AC component and the second AC component respectively, to obtain wavelet decomposition results of the first AC component and the second AC component respectively, wherein the wavelet decomposition results at least include a corresponding relationship between wavelet coefficients and frequency ranges;

[0013] Filtering the wavelet coefficients according to a preset frequency threshold to obtain target wavelet coefficients, wherein the frequency threshold is used to reflect the standard frequency range of the respiratory wave;

[0014] The target wavelet coefficients are reconstructed to obtain the breathing signal of the target user.

[0015] To achieve the above object, the second aspect of the present invention provides a device for determining a physiological parameter, the device comprising:

[0016] A data acquisition module is used to acquire a first volume wave signal of a target user, wherein the volume wave signal is used to reflect the physiological condition of the target user;

[0017] A signal filtering module: used for performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal;

[0018] A signal decomposition module: used for performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user;

[0019] Parameter determination module: used to calculate physiological parameters using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, wherein the physiological parameters at least include breathing parameters.

[0020] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the method described in the first aspect.

[0021] To achieve the above-mentioned purpose, the fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in the first aspect.

[0022] The embodiments of the present invention have the following beneficial effects:

[0023] The present invention provides a method for determining physiological parameters, the method comprising: obtaining a first volume wave signal of a target user, the volume wave signal is used to reflect the physiological condition of the target user; performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal; performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a respiratory signal of the target user; using the signal characteristics of the respiratory signal to calculate physiological parameters to determine the physiological parameters of the target user, the physiological parameters at least including respiratory parameters. Through the above method, the volume wave signal can be processed once by filtering to filter out interference noise as much as possible, and then the volume wave signal can be processed twice by wavelet decomposition to further decompose the signal, which not only improves the accuracy of respiratory signal extraction, but also makes the calculated respiratory parameters more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] in:

[0026] Figure 1 is a flow chart of a method for determining a physiological parameter in an embodiment of the present invention;

[0027] Figure 2 is another flow chart of a method for determining a physiological parameter in an embodiment of the present invention;

[0028] Figure 3 is a structural block diagram of a device for determining a physiological parameter in an embodiment of the present invention;

[0029] Figure 4 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for determining a physiological parameter in an embodiment of the present invention. Figure 1 The method shown can be applied to both a terminal and a server. The terminal can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers. This embodiment is described by applying to a terminal as an example. Figure 1 The method shown specifically includes the following steps:

[0032] 101. Acquire a first volume wave signal of a target user, where the volume wave signal is used to reflect the physiological condition of the target user;

[0033] It should be noted that the terminal can obtain the first volume wave signal of the target user to realize the detection of physiological parameters, wherein the terminal can be a monitor or other electronic device with data acquisition and processing capabilities. This embodiment takes the monitor as an example for explanation without specific limitation; the target user is a user who needs to perform physiological parameter detection, such as a user who is performing physiological parameter detection; the volume wave signal can be used to reflect the physiological condition of the target user, such as breathing condition, pulse condition, blood oxygen condition, etc. The volume wave signal can also be called photoplethysmography (PPG), which is a non-invasive physiological signal acquisition technology to obtain a photoelectric signal, which can be used to detect heart rate, heart rate variability, respiratory rate, blood oxygen and other cardiovascular physiological parameters; the first volume wave signal can be a real-time volume wave signal of the target user collected in real time, so the first volume wave signal can be obtained in a way that the terminal receives the real-time volume wave signal collected by the volume wave acquisition device in real time. It is understandable that the volume wave acquisition device can be a finger sleeve type or a finger clip type. The volume wave acquisition device is composed of a light source and a photodetector (PD). The light source includes but is not limited to light-emitting diodes (LEDs). The photodetector is used to collect the light intensity signal of the LED. According to the acquisition method, the volume wave acquisition device can also be divided into two types: transmission type and reflection type. The transmission type volume wave acquisition device is placed at the end of the limb, such as the tip of the nose, the fingertips, the earlobe, etc. The LED light can penetrate from one side of the end of the limb to the other side, and the photoelectric sensor on the other side receives and detects the light intensity of the light. The light source and the photoelectric sensor of the reflection type volume wave acquisition device are placed on the same side, and the sensor detects the light source signal reflected back by tissues such as bones, skin and blood vessels. Compared with the traditional method of obtaining physiological signals by sticking electrodes, the physiological signal acquisition method using the volume wave acquisition device is easier to operate and improves the user experience.

[0034] The principle of physiological condition detection for target users is that after light enters the skin, bones, muscles, veins, arteries and other tissues will absorb part of the light. Since the absorption of light by bones, muscles and other tissues is basically unchanged, and the blood flow in the arteries changes periodically with the contraction and relaxation of the heart, the absorption of light also changes periodically. Therefore, the light signal received by the photoelectric sensor can detect changes in blood flow volume.

[0035] In a feasible implementation, the first volume wave signal may be subjected to signal filtering to obtain the second volume wave signal, and the signal may be subjected to signal normalization, that is, before step 102, the process may include: performing normalization on the first volume wave signal to obtain a normalized first volume wave signal, and then filtering using the normalized first volume wave signal to execute step 102.

[0036] 102. Perform signal filtering processing on the first volume wave signal to obtain a second volume wave signal;

[0037] Furthermore, the first volume wave signal can be subjected to signal filtering processing to filter out noise data that is an interference signal and a noise signal for the physiological signal, so as to obtain a second volume wave signal with better physiological condition performance, wherein the volume wave signal includes at least a noise signal, a pulse signal, and a respiratory signal.

[0038] 103. Perform signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user;

[0039] Since the volume wave signal can reflect various types of physiological conditions, so that the volume wave signal includes various types of physiological signals, after filtering the signal, the volume wave signal needs to be decomposed to obtain various physiological signals, wherein the volume wave signal at least includes a pulse signal and a respiratory signal, and the various physiological signals are decomposed by a signal decomposition algorithm, and the signals with overlapping frequencies are separated by the signal decomposition algorithm, and the pulse signal and the respiratory signal can be obtained after the signal decomposition. Among them, the signal decomposition algorithm includes but is not limited to wavelet decomposition, etc.

[0040] 104. Calculate physiological parameters using signal characteristics of the breathing signal to determine physiological parameters of the target user, where the physiological parameters at least include breathing parameters.

[0041] It can be understood that after obtaining the breathing signal, physiological parameters can be calculated based on the signal characteristics of the breathing signal to determine the physiological parameters of the target user and realize physiological parameter monitoring, wherein the physiological parameters include but are not limited to breathing parameters, which are used to reflect the breathing condition of the target user. The breathing parameters include but are not limited to the breathing rate, etc. Furthermore, the physiological parameters can also be output to the preset display screen of the terminal for display so that the user can check it in time. The user can be the target user, or a medical staff or experimenter, etc.

[0042] The present invention provides a method for determining physiological parameters, the method comprising: obtaining a first volume wave signal of a target user, the volume wave signal is used to reflect the physiological condition of the target user; performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal; performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a respiratory signal of the target user; using the signal characteristics of the respiratory signal to calculate physiological parameters to determine the physiological parameters of the target user, the physiological parameters at least including respiratory parameters. Through the above method, the volume wave signal can be processed once by filtering to filter out interference noise as much as possible, and then the volume wave signal can be processed twice by wavelet decomposition to further decompose the signal, which not only improves the accuracy of respiratory signal extraction, but also makes the calculated respiratory parameters more accurate.

[0043] See also Figure 2 , Figure 2 FIG. 4 is another flow chart of a method for determining a physiological parameter in an embodiment of the present invention. Figure 2 The method shown comprises the following steps:

[0044] 201. Acquire a first volume wave signal of a target user, where the volume wave signal is used to reflect the physiological condition of the target user;

[0045] 202. Perform signal filtering processing on the first volume wave signal to obtain a second volume wave signal;

[0046] It should be noted that the contents shown in steps 201 and 202 are the same as Figure 1 The contents of steps 101 and 102 are similar, and are not described here to avoid repetition. For details, please refer to Figure 1 The contents of steps 101 and 102 are shown.

[0047] Furthermore, light of different wavelengths has different penetration capabilities on biological tissues, and the PPG waveform of the light signal (light intensity) converted into an electrical signal can be divided into two components: direct current (DC) and alternating current (AC). The DC component mainly depends on the constant absorption of bones, muscles, fat, and respiratory effects. The AC component mainly depends on the changes in arterial blood volume, and its basic frequency mainly reflects the changes in heart rate.

[0048] Wherein, the first volume wave signal can be an analog signal or a digital signal. If it is an analog signal, the analog signal can be converted into a discrete digital signal, and then the first light signal and the second light signal collected by the red light and the infrared light are obtained respectively: the two light signals are subjected to digital signal processing respectively, such as signal normalization, signal filtering processing, etc. Wherein, the second volume wave signal includes light signals of at least two wavelengths, and the two light signals are subjected to signal filtering processing respectively. The signal filtering processing can be digital filtering processing, including low-pass and high-pass filtering. Wherein, the selection of filtering parameters is adaptively selected according to the frequency of the pulse signal and the respiratory signal to be extracted. For example, the frequency of the pulse wave is usually within 5Hz, and the frequency of breathing is lower, usually within 1.5Hz, so the frequency above 5HZ is filtered out during filtering.

[0049] That is, the normalized first volume wave signal is filtered, for example, the red light signal and the infrared light signal are low-pass filtered respectively, and the DC component is extracted; the low-pass filtered signal is high-pass filtered; the red light signal and the infrared light signal are obtained after low-pass and high-pass, and the AC component containing the pulse signal and the respiratory signal is obtained. Therefore, the second volume wave signal can include a first AC component and a second AC component of a light signal of at least two wavelengths, wherein, for example, the two wavelengths can be red light and infrared light, respectively, the first AC component is the AC component of the red light signal, and the second AC component is the AC component of the infrared light signal, or the first AC component is the AC component of the infrared light signal, and the second AC component is the AC component of the red light signal, which is not limited here.

[0050] The second volume wave signal is decomposed according to a preset signal decomposition algorithm to obtain the breathing signal of the target user. The first AC component and the second AC component may be decomposed by wavelet to obtain the final breathing signal, as described below.

[0051] 203. Acquire wavelet decomposition parameters, wherein the wavelet decomposition parameters at least include a mother wavelet function and a decomposition scale of the wavelet decomposition algorithm;

[0052] It should be noted that the signal decomposition algorithm can be a wavelet decomposition algorithm. Wavelet decomposition is used to split the frequency overlapping signal. First, the wavelet decomposition parameters of the wavelet decomposition algorithm need to be obtained. The wavelet decomposition parameters can be pre-set or determined based on the frequency range of the input signal and the correspondence between the preset wavelet decomposition parameters and the frequency range. The pre-setting is only used as an example here and is not limited here.

[0053] 204. Perform wavelet decomposition on the first AC component and the second AC component respectively using the mother wavelet function and the decomposition scale to obtain wavelet decomposition results of the first AC component and the second AC component, respectively, wherein the wavelet decomposition results at least include a correspondence between wavelet coefficients and frequency ranges;

[0054] After obtaining the wavelet decomposition parameters, the parameters of the wavelet decomposition algorithm can be assigned according to the parameters, and the wavelet decomposition process can be started. Specifically, the first AC component of the red light and the second AC component of the infrared light are respectively subjected to wavelet decomposition using the mother wavelet function and the decomposition scale to obtain the wavelet decomposition results of the two AC components. The wavelet decomposition results include the wavelet coefficients obtained by decomposition and the frequency ranges corresponding to the wavelet coefficients, that is, the wavelet decomposition results at least include the corresponding relationship between the wavelet coefficients and the frequency ranges.

[0055] It can be understood that wavelet decomposition includes multiple layers,

[0056] 205. Filter the wavelet coefficients according to a preset frequency threshold to obtain target wavelet coefficients, wherein the frequency threshold is used to reflect a standard frequency range of a respiratory wave;

[0057] 206. Reconstruct the target wavelet coefficients to obtain a breathing signal of the target user;

[0058] Further, the wavelet coefficients are filtered according to a preset frequency threshold to obtain target wavelet coefficients. The frequency threshold can be a standard frequency range corresponding to the respiratory wave, such as 0.5Hz to 1.5Hz. In this way, the wavelet coefficients below 0.5Hz or above 1.5Hz will be filtered out, and the remaining wavelet coefficients in the frequency range of 0.5Hz-1.5Hz are considered to be the target wavelet coefficients, that is, the target wavelet coefficients are the wavelet coefficients whose frequency range is within the standard frequency range of the respiratory wave. Then, the target wavelet coefficients are reconstructed to obtain the respiratory signal of the target user. The reconstruction method can be wavelet decomposition inverse transform.

[0059] Among them, since the frequency of the pulse wave is usually within 5Hz, and the frequency of breathing is lower, usually within 1.5Hz, there is a frequency overlap between the two. In order to better extract the breathing-related signal from the volume wave, it is necessary to perform wavelet decomposition on the signal after traditional filtering, so as to extract the breathing-related signal for calculating the breathing rate; select a suitable mother wavelet function for the wavelet decomposition of the signal; select a reasonable decomposition scale according to the current signal characteristics (such as signal-to-noise ratio, signal quality, pulse rate and other parameters); decompose the signal into high-frequency and low-frequency wavelet coefficients according to the selected mother wavelet function and decomposition scale; mainly filter the low-frequency wavelet coefficients and high-frequency wavelet coefficients. Since the frequency of the breathing signal itself is relatively low, the low-frequency coefficients below 0.05Hz are directly filtered out for the low-frequency filter coefficients; and the high-frequency coefficients above 1.5Hz of the high-frequency filter coefficients are also directly filtered out, and the coefficients of other frequencies are adaptively filtered; the retained filter coefficients are reconstructed to extract the breathing signal.

[0060] 207. Calculate physiological parameters using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, where the physiological parameters at least include breathing parameters.

[0061] It should be noted that the content shown in step 207 is the same as Figure 1 The contents of step 104 are similar, and are not described here to avoid repetition. Figure 1 The content of step 104 is shown.

[0062] Furthermore, breathing signals at two wavelengths can be obtained through the first AC component and the second AC component, and four sets of breathing parameters can be obtained through the peaks and valleys of the envelopes of the two breathing signals. Comprehensive decisions can be made through the four sets of breathing parameters to obtain more accurate breathing parameters.

[0063] In a feasible implementation, in order to further improve the accuracy of the calculation of the breathing parameters, the effective breathing in the breathing signal can also be judged, and the breathing parameters are calculated according to the signal characteristics of the effective breathing to improve the accuracy of the calculation of the breathing parameters. Then, step 207 can also include steps A01 to A03:

[0064] A01. Determine the signal characteristics of the respiratory signal, wherein the signal characteristics at least include a respiratory peak and a respiratory interval, and the respiratory interval is composed of two adjacent respiratory peaks;

[0065] A02. Determine each target respiratory interval corresponding to effective breathing according to the respiratory peak and the respiratory interval;

[0066] It should be noted that in order to calculate more accurate breathing parameters based on effective breathing, it is first necessary to determine which breathing intervals correspond to effective breathing. A breathing interval is composed of two adjacent breathing peaks. Therefore, it is first necessary to at least determine that the signal feature of the breathing signal is the breathing peak, and obtain all breathing intervals of the breathing signal through the breathing peak, so as to screen out which are the target breathing intervals of effective breathing. In a feasible implementation, the target breathing interval can be confirmed by the breathing peak, and then step A02 can include steps B01 to B04:

[0067] B01. determining a respiratory peak sequence of the respiratory signal, wherein the respiratory peak sequence includes a plurality of respiratory peaks arranged in time sequence;

[0068] It is understandable that the target user's breathing signal may have multiple breathing peaks, and then the breathing peak sequence of the breathing signal may be determined using the multiple breathing peaks. The breathing peak sequence includes a number of breathing peaks arranged in time sequence, and the time sequence may follow the positive time sequence of the peak generation. For example, peak 1 is generated in the first second, peak 2 is generated in the second second, peak 3 is generated in the third second, and so on. Then the breathing peak sequence is: [peak 1, peak 2, peak 3, ...], which is not limited to this example.

[0069] B02, traversing the respiratory peak sequence, for the traversed target respiratory peak, using the preset respiratory rhythm feature and the target respiratory peak to perform peak type judgment, and determine the peak type of the target respiratory peak, wherein the peak type at least includes an interference peak or an effective peak, and the respiratory rhythm feature is used to reflect the respiratory rhythm characteristics of effective breathing;

[0070] Further, the respiratory peaks in the respiratory peak sequence are traversed one by one to determine which is the peak of effective breathing. Specifically, the respiratory peak sequence is traversed, and for the traversed target respiratory peak, the peak type is determined using the preset respiratory rhythm feature and the target respiratory peak to determine the peak type of the target respiratory peak, wherein the peak type at least includes an interference peak or an effective peak, and the respiratory rhythm feature is used to reflect the respiratory rhythm characteristics of effective breathing, wherein the respiratory rhythm feature includes but is not limited to the respiratory peak threshold of effective breathing, and the target respiratory peak is judged by threshold comparison.

[0071] B03. If the peak type is an interference peak, determining that the first respiratory interval corresponding to the target respiratory peak does not belong to the target respiratory interval, the first respiratory interval being the respiratory interval between the target respiratory peak and the previous respiratory peak;

[0072] B04. If the peak type is a valid peak, determine that the first respiratory interval belongs to the target respiratory interval.

[0073] Furthermore, the respiratory rhythm characteristics include a respiratory peak threshold of effective breathing, and the threshold is a minimum value. For example, if the target respiratory peak is greater than the respiratory peak threshold, the type of the target respiratory peak is determined to be a valid peak. Otherwise, the peak type of the target respiratory peak is considered to be an interference peak. The target respiratory peak is judged by threshold comparison.

[0074] When the peak type of the target respiratory peak is an interference peak, it means that the target respiratory peak is not generated by effective breathing, and the corresponding target respiratory peak is not a respiratory interval of effective breathing, and then the target respiratory peak and its corresponding first respiratory interval are eliminated, and the calculation of subsequent respiratory parameters does not use the eliminated data. On the contrary, when the peak type of the target respiratory peak is a valid peak, the relevant data of the target respiratory peak can be retained as a basis for the calculation of subsequent respiratory parameters.

[0075] It should be noted that before elimination, more signal features can be further extracted to continue to judge the peak type and improve the accuracy of effective breathing judgment. It can be understood that the richer the types of signal features, the more accurate the judgment of effective breathing. After rich feature judgment, the accuracy of effective breathing judgment can be improved. Signal features include but are not limited to respiratory wave amplitude, respiratory wave amplitude extreme value, respiratory wave interval, respiratory wave interval median and mean, interval mean, peak and trough extreme value, respiratory wave peak width, respiratory wave area, etc. For example, firstly, the extracted respiratory waveform is searched for respiratory peaks and troughs; the extracted respiratory waveform features are calculated, mainly including the amplitude features of the respiratory wave, the extreme values ​​(maximum and minimum values) of all respiratory wave amplitudes, respiratory interval features, the median and mean features of the respiratory intervals, the interval extreme value (maximum and minimum value) features, the peak and trough extreme value features, the respiratory wave peak width features, the respiratory wave area features, etc.; according to the calculated respiratory waveform features, the respiratory peaks found are traversed one by one to determine whether the searched respiratory peaks are valid respiratory peaks. If the current respiratory peak is an interference peak, the current respiratory peak and its calculated respiratory interval are eliminated; step A03 is executed to calculate the average interval of the current respiratory waveform using the calculated effective respiratory interval; finally, the current respiratory rate is calculated using the calculated average interval.

[0076] A03. Determine the breathing parameters of the target user by using the average breathing interval of each target breathing interval and a preset breathing rate algorithm, wherein the breathing parameters at least include the breathing rate.

[0077] It should be noted that after the target breathing interval is obtained, the average breathing interval of the target user can be calculated using all the target breathing intervals, and the breathing parameters, such as the breathing rate RR, can be calculated using the average breathing interval.

[0078] In a feasible implementation, the second volume wave signal is a time domain signal and can be regarded as a pulse wave signal. The pulse parameter and the blood oxygen parameter can be calculated based on the second volume wave signal. That is, step 207 can also include steps C01 to C02:

[0079] C01. performing time-frequency transformation on the second volume wave signal by using a preset time-frequency transformation algorithm to obtain a frequency domain signal corresponding to the second volume wave signal;

[0080] C02. Calculate physiological parameters according to the signal characteristics of the second volume wave signal and the frequency domain signal to determine a target blood oxygen parameter and a target pulse parameter, wherein the physiological parameters also include a target blood oxygen parameter and a target pulse parameter.

[0081] The second volume wave signal may be first converted into a frequency domain signal, and then the final target blood oxygen parameter and target pulse parameter may be calculated using the signal characteristics of the time domain signal and the frequency domain signal. For example, two sets of blood oxygen parameters and two sets of pulse parameters may be calculated using two sets of time domain and frequency domain signals, and then the final physiological parameters may be obtained using the calculation results of multiple sets of physiological parameters. Specifically, step C02 may include D01 to D03:

[0082] D01. Calculating physiological parameters according to the signal characteristics of the second volume wave signal to determine a first blood oxygen parameter and a first pulse parameter corresponding to the time domain signal;

[0083] D02. Calculate physiological parameters according to the signal characteristics of the frequency domain signal to determine a second blood oxygen parameter and a second pulse parameter corresponding to the frequency domain signal;

[0084] D03. Making a comprehensive decision based on the first blood oxygen parameter and the second blood oxygen parameter to determine a target blood oxygen parameter; and making a comprehensive decision based on the first pulse parameter and the second pulse parameter to determine a target pulse parameter.

[0085] For example, the time-frequency transformation algorithm can be Fourier transform (FFT), etc., and the blood oxygen parameters at least include blood oxygen saturation (SpO2 value), the pulse parameters at least include pulse rate (PR value), and perfusion index (PI). Perform FFT transformation on the filtered signal to obtain the frequency domain signal, and then calculate parameters such as f_SpO2 and f_PR by extracting the frequency domain signal features; and perform feature extraction on the time domain signal to calculate parameters such as signal quality, t_PI value, t_SpO2 value, and t_PR value; finally, combine the calculation results of the time domain and frequency domain for comprehensive analysis to obtain the final SpO2 value and PR value. Among them, the perfusion index can be calculated through the time domain.

[0086] By obtaining two sets of physiological parameters, a comprehensive decision is made. Since the frequency domain signal has a strong anti-interference ability, if the calculation results of two sets of physiological parameters of the same type are different, the decision result focuses on the reference frequency domain calculation results. For example, when the first blood oxygen parameter and the second blood oxygen parameter are different, the second blood oxygen parameter is taken as the target blood oxygen parameter. Similarly, when the first pulse parameter and the second pulse parameter are different, the second pulse parameter is taken as the target pulse parameter; or, the weighted average of the two sets of physiological parameters of the same type is calculated to give a higher weight to the frequency domain; if the calculation results of the two sets of physiological parameters of the same type are the same, you can take any one set, or calculate the average of the two sets of physiological parameters of the same type as the final physiological parameter.

[0087] The present invention provides a method for determining physiological parameters. In the above manner, the volume wave signal can be processed once by filtering to filter out interference noise as much as possible, and then the volume wave signal can be processed twice by wavelet decomposition to further decompose the signal, which not only improves the accuracy of respiratory signal extraction, but also makes the calculated respiratory parameters more accurate. On the basis of monitoring blood oxygen saturation and pulse rate, the photoelectric volume wave can also be used to extract respiratory related signals to calculate the respiratory rate, which can not only effectively reduce costs, but also better avoid human discomfort. At the same time, the acquisition of multiple parameters of blood oxygen saturation, pulse rate and respiratory rate is also conducive to the comprehensive decision-making of medical staff on the patient's condition. The present invention uses a traditional filter to filter out other interference noise as much as possible, and effectively improves the accuracy of blood oxygen saturation and pulse rate by combining time domain technology with frequency domain technology; and for the extraction of respiratory signals, the wavelet decomposition method is used to decompose the mixed signal containing pulse wave signals and respiratory signals, which can effectively realize the extraction of respiratory signals.

[0088] See also Figure 3 , Figure 3 FIG. 1 is a structural block diagram of a device for determining a physiological parameter in an embodiment of the present invention. Figure 3 The device shown comprises:

[0089] Data acquisition module 301: used to acquire a first volume wave signal of a target user, where the volume wave signal is used to reflect the physiological condition of the target user;

[0090] Signal filtering module 302: used for performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal;

[0091] Signal decomposition module 303: used to perform signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user;

[0092] The parameter determination module 304 is used to calculate physiological parameters using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, where the physiological parameters at least include breathing parameters.

[0093] It should be noted that Figure 3 The contents of the device shown are Figure 1 The contents of each step in the method shown are similar, so they are not described here to avoid repetition. For details, please refer to Figure 1 The contents of each step in the method shown.

[0094] The present invention provides a device for determining physiological parameters, the device comprising: a data acquisition module: used to acquire a first volume wave signal of a target user, the volume wave signal is used to reflect the physiological condition of the target user; a signal filtering module: used to perform signal filtering processing on the first volume wave signal to obtain a second volume wave signal; a signal decomposition module: used to perform signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user; a parameter determination module: used to calculate physiological parameters using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, the physiological parameters at least including breathing parameters. Through the above device, the volume wave signal can be processed once by filtering to filter out interference noise as much as possible, and then the volume wave signal can be processed twice by wavelet decomposition to further decompose the signal, which not only improves the accuracy of breathing signal extraction, but also makes the calculated breathing parameters more accurate.

[0095] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps: Figure 1 or Figure 2 Steps shown.

[0097] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps: Figure 1 or Figure 2 Steps shown.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a physiological parameter, characterized in that: The method comprises: Acquire a first volume wave signal of a target user, where the volume wave signal is used to reflect the physiological condition of the target user; performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal; performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user; Physiological parameters are calculated using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, where the physiological parameters at least include breathing parameters.

2. The method according to claim 1, characterized in that: The second volume wave signal includes a first AC component and a second AC component of an optical signal of at least two wavelengths, and the signal decomposition algorithm includes a wavelet decomposition algorithm. Then, the second volume wave signal is decomposed according to a preset signal decomposition algorithm to obtain a breathing signal of the target user, including: Acquire wavelet decomposition parameters, wherein the wavelet decomposition parameters at least include a mother wavelet function and a decomposition scale of the wavelet decomposition algorithm; Using the mother wavelet function and the decomposition scale to perform wavelet decomposition on the first AC component and the second AC component respectively, to obtain wavelet decomposition results of the first AC component and the second AC component respectively, wherein the wavelet decomposition results at least include a corresponding relationship between wavelet coefficients and frequency ranges; Filtering the wavelet coefficients according to a preset frequency threshold to obtain target wavelet coefficients, wherein the frequency threshold is used to reflect the standard frequency range of the respiratory wave; The target wavelet coefficients are reconstructed to obtain the breathing signal of the target user.

3. The method according to claim 1, characterized in that: The calculating of physiological parameters by using the signal characteristics of the breathing signal to determine the physiological parameters of the target user includes: Determine signal characteristics of the respiratory signal, wherein the signal characteristics at least include a respiratory peak and a respiratory interval, wherein the respiratory interval is composed of two adjacent respiratory peaks; Determine each target respiratory interval corresponding to effective breathing according to the respiratory peak and the respiratory interval; The breathing parameters of the target user are determined by using the average breathing interval of each target breathing interval and a preset breathing rate algorithm, wherein the breathing parameters at least include the breathing rate.

4. The method according to claim 3, characterized in that: Determining each target respiratory interval corresponding to effective breathing according to the respiratory peak and the respiratory interval includes: Determine a respiratory peak sequence of the respiratory signal, wherein the respiratory peak sequence includes a plurality of respiratory peaks arranged in time sequence; Traversing the respiratory peak sequence, for the traversed target respiratory peak, using the preset respiratory rhythm feature and the target respiratory peak to perform peak type judgment, and determine the peak type of the target respiratory peak, wherein the peak type at least includes an interference peak or a valid peak, and the respiratory rhythm feature is used to reflect the respiratory rhythm characteristics of effective breathing; If the peak type is an interference peak, determining that a first respiratory interval corresponding to the target respiratory peak does not belong to the target respiratory interval, the first respiratory interval being a respiratory interval between the target respiratory peak and a previous respiratory peak; If the peak type is a valid peak, it is determined that the first respiratory interval belongs to the target respiratory interval.

5. The method according to claim 1, characterized in that: The second volume wave signal is a time domain signal, and the physiological parameter calculation is performed using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, and further includes: Performing time-frequency transformation on the second volume wave signal using a preset time-frequency transformation algorithm to obtain a frequency domain signal corresponding to the second volume wave signal; Physiological parameters are calculated according to the signal characteristics of the second volume wave signal and the frequency domain signal to determine a target blood oxygen parameter and a target pulse parameter, wherein the physiological parameters also include a target blood oxygen parameter and a target pulse parameter.

6. The method according to claim 5, characterized in that: The step of calculating physiological parameters according to the signal characteristics of the second volume wave signal and the frequency domain signal to determine a target blood oxygen parameter and a target pulse parameter includes: Calculating physiological parameters according to the signal characteristics of the second volume wave signal to determine a first blood oxygen parameter and a first pulse parameter corresponding to the time domain signal; Calculate physiological parameters according to the signal characteristics of the frequency domain signal to determine a second blood oxygen parameter and a second pulse parameter corresponding to the frequency domain signal; A comprehensive decision is made based on the first blood oxygen parameter and the second blood oxygen parameter to determine a target blood oxygen parameter; and a comprehensive decision is made based on the first pulse parameter and the second pulse parameter to determine a target pulse parameter.

7. The method according to claim 1, characterized in that: Before performing signal filtering on the first volume wave signal to obtain the second volume wave signal, the method further includes: The first volume wave signal is normalized to obtain a normalized first volume wave signal.

8. A device for determining physiological parameters, characterized in that: The device comprises: A data acquisition module is used to acquire a first volume wave signal of a target user, wherein the volume wave signal is used to reflect the physiological condition of the target user; A signal filtering module: used for performing signal filtering processing on the first volume wave signal to obtain a second volume wave signal; A signal decomposition module: used for performing signal decomposition on the second volume wave signal according to a preset signal decomposition algorithm to obtain a breathing signal of the target user; Parameter determination module: used to calculate physiological parameters using the signal characteristics of the breathing signal to determine the physiological parameters of the target user, wherein the physiological parameters at least include breathing parameters.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images