Pulse oximeter equipment and blood oxygen saturation detection method and device

Abstract

The invention relates to pulse oximeter equipment and a blood oxygen saturation degree detection method and device.The method comprises the steps that red light electric signals, infrared light electric signals and acceleration data corresponding to body movement of a wearing object collected by the pulse oximeter equipment are obtained; extracting light intensity corresponding to the current sampling data point according to the red light electric signal and the infrared light electric signal, and obtaining a body motion interference coefficient corresponding to the current sampling data point according to the acceleration data; performing dynamic compensation on the AC components of the red light electric signal and the infrared light electric signal based on the light intensity and the body motion interference coefficient to obtain a compensated AC component; extracting DC components of the red light electric signal and the infrared light electric signal; and calculating the oxyhemoglobin saturation according to the compensated AC component and DC component. In the whole process, the photoelectric signals are dynamically compensated based on the collected acceleration data and light intensity data, the blood oxygen saturation degree detection precision can be remarkably improved, and high-precision blood oxygen saturation degree detection is achieved.

Description

Technical Field

[0001] The present application relates to the field of pulse oximeter technology, and in particular to a pulse oximeter device, as well as a blood oxygen saturation detection method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] Pulse oximeters monitor blood oxygen saturation (SpO2) and pulse rate parameters in a non-invasive way. Its core principle is based on photoplethysmography (PPG) technology. After red light (about 660nm) and infrared light (about 940nm) penetrate human tissue, the intensity changes of the transmitted or reflected light signal are received by the photoelectric sensor, and the ratio of oxygenated hemoglobin to reduced hemoglobin in the blood is calculated in combination with the Lambert-Beer law.

[0003] Although this technology has been widely used in clinical and home health monitoring, the detection accuracy of existing equipment is still highly dependent on the quality of signal acquisition, and the signal strength is easily affected by the following multi-dimensional factors: 1) the difference in user physiological characteristics; 2) the constraints of wearing status on signal stability; 3) the signal attenuation effect of complex environmental factors.

[0004] It can be seen that the blood oxygen signal intensity of the pulse oximeter in Antong technology is easily interfered by multiple and multi-dimensional factors. Currently, there is an urgent need for an accurate blood oxygen saturation detection method. Summary of the Invention

[0005] Based on this, it is necessary to provide a pulse oximeter device with accurate detection, as well as a blood oxygen saturation detection method, device, computer equipment, storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a method for detecting blood oxygen saturation. The method comprises:

[0007] Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device;

[0008] Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data;

[0009] Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0010] extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0011] The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

[0012] In one embodiment, calculating the blood oxygen saturation based on the compensated AC component and the DC component includes:

[0013] noise suppression is performed on the DC components of the red photoelectric signal and the infrared photoelectric signal by using an adjacent point difference average method to obtain a noise-suppressed DC component;

[0014] The blood oxygen saturation is calculated according to the compensated AC component and the noise-suppressed DC component.

[0015] In one embodiment, the noise suppression of the DC components of the red photoelectric signal and the infrared photoelectric signal by averaging the adjacent point differences is performed to obtain the DC components after noise suppression, including:

[0016] Obtain the DC components of two adjacent sampling points of the red photoelectric signal and the DC components of two adjacent sampling points of the infrared photoelectric signal within a unit time;

[0017] Calculate the DC component mean value of the red photoelectric signal and the DC component mean value of the infrared photoelectric signal.

[0018] In one embodiment, calculating the blood oxygen saturation based on the compensated AC component and the noise-suppressed DC component includes:

[0019] Calculating a blood pulsation characteristic ratio based on the compensated AC component and the noise-suppressed DC component;

[0020] Obtaining a preset calibration curve, wherein the preset calibration curve is obtained by fitting a quadratic equation based on clinical blood oxygen saturation data;

[0021] The blood oxygen saturation is obtained according to the blood pulsation characteristic ratio and the preset calibration curve.

[0022] In one embodiment, dynamically compensating the AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain the compensated AC components includes:

[0023] Get the dynamic scale factor;

[0024] Dynamically compensate the AC components of the red photoelectric signal and the infrared photoelectric signal based on the dynamic proportional coefficient, the light intensity, and the body motion interference coefficient to obtain compensated AC components.

[0025] In one embodiment, obtaining the dynamic scaling coefficient includes:

[0026] Identify the wearing method of the wearer;

[0027] According to the wearing manner of the wearing object, a current dynamic proportional coefficient is obtained from a preset dynamic proportional coefficient-posture correspondence relationship.

[0028] In one embodiment, dynamically compensating the AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain the compensated AC components includes:

[0029] determining an exercise intensity level according to the acceleration data, and adaptively adjusting a compensation weight according to the exercise intensity level;

[0030] Obtaining a dynamic proportional coefficient corresponding to the light intensity and a preset baseline offset correction constant;

[0031] constructing a forward compensation term and a reverse interference term based on the light intensity, the body motion interference coefficient, the adjusted compensation weight, the dynamic proportional coefficient, and the baseline offset correction constant;

[0032] Combining the forward compensation term and the reverse interference term to generate an AC component compensation calculation formula;

[0033] The compensated AC component is calculated according to the AC component compensation calculation formula.

[0034] In a second aspect, the present application further provides a blood oxygen saturation detection device. The device comprises:

[0035] A data acquisition module is used to obtain red photoelectric signals, infrared photoelectric signals and acceleration data corresponding to the wearer's body movement collected by the pulse oximeter device;

[0036] a motion interference module, configured to extract the light intensity corresponding to the current sampling data point based on the red photoelectric signal and the infrared photoelectric signal, and obtain the body motion interference coefficient corresponding to the current sampling data point based on the acceleration data;

[0037] an AC processing module, configured to dynamically compensate AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0038] A DC processing module, used for extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0039] The blood oxygen saturation calculation module is used to calculate the blood oxygen saturation according to the compensated AC component and the DC component.

[0040] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0041] Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device;

[0042] Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data;

[0043] Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0044] extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0045] The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

[0046] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0047] Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device;

[0048] Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data;

[0049] Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0050] extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0051] The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

[0052] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0053] Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device;

[0054] Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data;

[0055] Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0056] extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0057] The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

[0058] In a sixth aspect, the present application further provides a pulse oximeter device, wherein the pulse oximeter device performs blood oxygen saturation detection using the following steps:

[0059] Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device;

[0060] Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data;

[0061] Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0062] extracting DC components of the red photoelectric signal and the infrared photoelectric signal;

[0063] The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

[0064] The pulse oximeter device, as well as the blood oxygen saturation detection method, apparatus, computer equipment, storage medium, and computer program product described above, acquires the red photoelectric signal, infrared photoelectric signal, and acceleration data corresponding to the wearer's body motion collected by the pulse oximeter device; extracts the light intensity corresponding to the current sampling data point based on the red photoelectric signal and infrared photoelectric signal, and acquires the body motion interference coefficient corresponding to the current sampling data point based on the acceleration data; dynamically compensates the AC component of the red photoelectric signal and infrared photoelectric signal based on the light intensity and body motion interference coefficient to obtain the compensated AC component; extracts the DC component of the red photoelectric signal and infrared photoelectric signal; and calculates the blood oxygen saturation based on the compensated AC component and DC component. Throughout the entire process, the photoelectric signal is dynamically compensated based on the collected acceleration data and light intensity data, suppressing the noise impact of body motion and light intensity on the AC component extraction, which can significantly improve the accuracy of blood oxygen saturation detection and achieve high-precision blood oxygen saturation detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A diagram showing an application environment of a method for detecting blood oxygen saturation in one embodiment;

[0066] Figure 2 1 is a flow chart of a method for detecting blood oxygen saturation in one embodiment;

[0067] Figure 3 1 is a flow chart of a method for detecting blood oxygen saturation in another embodiment;

[0068] Figure 4 is a structural block diagram of a blood oxygen saturation detection device in one embodiment;

[0069] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0071] The blood oxygen saturation detection method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the calculation module is set in the pulse oximeter device, and the pulse oximeter device is turned on and started. The calculation module receives the data collected by other components of the pulse oximeter device and starts to calculate blood oxygen. Specifically, the calculation module obtains the red photoelectric signal, infrared photoelectric signal and acceleration data corresponding to the body movement of the wearer collected by the pulse oximeter device; extracts the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtains the body movement interference coefficient corresponding to the current sampling data point according to the acceleration data; dynamically compensates the AC component of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body movement interference coefficient to obtain the compensated AC component; extracts the DC component of the red photoelectric signal and the infrared photoelectric signal; and calculates the blood oxygen saturation based on the compensated AC component and DC component. Furthermore, the calculation module can feed back the calculated blood oxygen saturation to the display module in the pulse oximeter device for display.

[0072] In one embodiment, Figure 2 As shown, a blood oxygen saturation detection method is provided, which is applied to Figure 1 The calculation module in the example is used to illustrate the following steps:

[0073] S100: Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to body movements of the wearer collected by the pulse oximeter device.

[0074] The pulse oximeter uses a photoelectric sensor to collect electrical signals from red light (typically with a wavelength of around 660nm) and infrared light (typically with a wavelength of around 940nm) passing through human tissue. Simultaneously, an accelerometer is used to collect body motion data from the wearer (such as a finger). Specifically, the pulse oximeter incorporates a photoelectric sensor and an accelerometer. The photoelectric sensor is used to emit red and infrared light, receive reflected or transmitted light after passing through tissue, and convert it into corresponding electrical signals. The accelerometer is used to monitor the wearer's minute body movements and output acceleration data. In actual applications, the photoelectric sensor periodically emits red and infrared light and collects the reflected or transmitted light signals in real time, converting them into analog electrical signals. After pre-processing such as amplification and filtering, the analog electrical signals are converted into digital signals and received by the computing module. The accelerometer simultaneously collects the wearer's acceleration data and also converts it into digital signals for processing by the computing module.

[0075] S200: extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data.

[0076] According to the collected red photoelectric signal and infrared light signal, the light intensity value corresponding to the current sampling data point is extracted. At the same time, the acceleration data is used to calculate the body motion interference coefficient. Specifically, light intensity extraction refers to extracting a numerical value representing light intensity from the photoelectric signal through signal processing techniques such as peak detection and average filtering. The body motion interference coefficient is calculated by an algorithm based on the amplitude, frequency and other characteristics of the acceleration data, and is used to quantify the degree of influence of body motion on the photoelectric signal. Specifically, the red light and infrared photoelectric signals of each sampling point can be preprocessed, such as denoising and smoothing, to improve the accuracy of light intensity extraction. A specific algorithm or model is applied to calculate the body motion interference coefficient based on the characteristics of the acceleration data. For example, a threshold can be set according to the amplitude of the acceleration. If the threshold is exceeded, it is considered that there is body motion interference, and the interference coefficient is adjusted accordingly. Furthermore, the acceleration signal can be averaged to obtain the body motion interference coefficient. The specific formula is as follows:

[0077]

[0078] Where a i is the acceleration data corresponding to the i-th sampling point.

[0079] S300: Dynamically compensate AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components.

[0080] Based on the extracted light intensity and the calculated body motion interference coefficient, the alternating current (AC) component of the red and infrared photoelectric signals is dynamically compensated to reduce the impact of body motion interference. Here, the AC component refers to the portion of the photoelectric signal that changes periodically with the heartbeat and contains the critical information required for blood oxygen saturation detection. Dynamic compensation specifically adjusts the amplitude or phase of the AC component based on the body motion interference coefficient to restore its true value. Specifically, the AC component can be extracted from the photoelectric signal through Fourier transform or other time-frequency analysis methods. Based on the body motion interference coefficient, the AC component is compensated point by point or segment by segment. Compensation strategies may include adjusting the amplitude, phase, or applying filters.

[0081] S400: extracting DC components of the red photoelectric signal and the infrared photoelectric signal.

[0082] Extract the direct current (DC) component of the red and infrared photoelectric signals. This component represents the average level of the photoelectric signal and is an important reference for calculating blood oxygen saturation. The DC component represents the stable portion of the photoelectric signal that does not change with the heartbeat and reflects the average light absorption by the tissue. This component can be extracted by performing long-term averaging or low-pass filtering on the preprocessed photoelectric signal.

[0083] S500: Calculate the blood oxygen saturation based on the compensated AC component and DC component.

[0084] The blood oxygen saturation value is calculated using the compensated AC component and the extracted DC component using the blood oxygen saturation formula. Specifically, blood oxygen saturation can be calculated using a ratio method or algorithmic model based on the differences in the absorption characteristics of red and infrared light in blood. The blood oxygen absorption ratio is calculated based on the compensated red and infrared AC components and the DC component. The blood oxygen saturation value is converted into the blood oxygen saturation value using the blood oxygen saturation formula or algorithmic model. The calculation results are output for user review or further analysis.

[0085] The above-mentioned blood oxygen saturation detection method obtains the red photoelectric signal, infrared photoelectric signal and acceleration data corresponding to the wearer's body movement collected by the pulse oximeter device; extracts the light intensity corresponding to the current sampling data point based on the red photoelectric signal and infrared photoelectric signal, and obtains the body movement interference coefficient corresponding to the current sampling data point based on the acceleration data; dynamically compensates the AC component of the red photoelectric signal and infrared photoelectric signal based on the light intensity and body movement interference coefficient to obtain the compensated AC component; extracts the DC component of the red photoelectric signal and infrared photoelectric signal; and calculates the blood oxygen saturation based on the compensated AC component and DC component. Throughout the entire process, the photoelectric signal is dynamically compensated based on the collected acceleration data and light intensity data, suppressing the noise impact of body movement and light intensity on the AC component extraction, which can significantly improve the accuracy of blood oxygen saturation detection and achieve high-precision blood oxygen saturation detection.

[0086] In one embodiment, Figure 3 As shown, S500 includes:

[0087] S520: Suppressing noise on the DC components of the red photoelectric signal and the infrared photoelectric signal by averaging adjacent point differences to obtain a noise-suppressed DC component.

[0088] After extracting the direct current (DC) component of the red and infrared photoelectric signals, the DC component is noise-suppressed using the adjacent point difference mean method to further reduce the impact of noise on blood oxygen saturation calculations. This method is a simple and effective signal smoothing method that calculates the differences between adjacent data points, takes the mean of these differences, and then adjusts the original data points to smooth out the noise. The noise-suppressed DC component is a more stable and accurate DC component value after noise suppression, providing a reliable foundation for subsequent blood oxygen saturation calculations.

[0089] Specifically, the extracted DC component is preprocessed, such as removing outliers and performing preliminary smoothing. The adjacent point difference mean method is applied to calculate the differences between adjacent DC component data points and average these differences. Based on the calculated mean difference, the original DC component is adjusted to obtain the noise-suppressed DC component.

[0090] S540: Calculate the blood oxygen saturation according to the compensated AC component and the noise-suppressed DC component.

[0091] The Lambert-Beer Law and the blood oxygen saturation formula are applied to calculate the blood oxygen saturation value based on the compensated AC component and the noise-suppressed DC component. The blood oxygen saturation formula is used to calculate blood oxygen saturation using a ratio method or an algorithm model based on the difference in the absorption characteristics of red and infrared light in blood.

[0092] In one embodiment, the DC components of the red photoelectric signal and the infrared photoelectric signal are noise-suppressed by averaging the adjacent point differences, and the DC components after noise suppression include:

[0093] Step 1: Obtain the DC components of two adjacent sampling points of the red photoelectric signal and the DC components of two adjacent sampling points of the infrared photoelectric signal within a unit time.

[0094] Step 2: Calculate the DC component mean value of the red photoelectric signal and the DC component mean value of the infrared photoelectric signal.

[0095] After extracting the direct current (DC) components of the red and infrared photoelectric signals, noise suppression is performed on these DC components using the mean of adjacent point differences. Specifically, the DC components of two adjacent sampling points of the red and infrared photoelectric signals within a unit time are first obtained, and then the mean of these DC components is calculated as the basis for noise suppression.

[0096] Specifically, here, the unit time refers to the time interval used to calculate the difference between adjacent points, which can be a fixed sampling period or a time period dynamically determined according to signal characteristics, such as 1 second, 0.5 seconds, etc.

[0097] The DC component of two adjacent sampling points refers to the DC component values ​​at two adjacent time points during continuous sampling. The DC component mean is the average of the DC components of adjacent sampling points, reflecting the stability of the signal over a short period of time. Noise suppression reduces the impact of random noise on the signal by comparing and adjusting the differences between adjacent DC components, thereby improving signal stability and accuracy.

[0098] In practical applications, the DC component of the red and infrared photoelectric signals is extracted at each sampling point. The DC component values ​​of two adjacent sampling points are recorded within a unit of time. The DC component of each sampling point is averaged with the DC component of the previous sampling point to obtain the mean DC component of the red and infrared photoelectric signals. This mean can be a simple arithmetic mean or a weighted average based on signal characteristics.

[0099] The original DC component is smoothed using the calculated DC component mean. Specifically, for each sampling point, the difference between the DC component mean and the previous sampling point is calculated, and the original DC component value is adjusted based on this difference. After this noise suppression process, more stable and accurate DC component values ​​are obtained. These values ​​will serve as the basis for subsequent blood oxygen saturation calculations.

[0100] In one embodiment, calculating the blood oxygen saturation based on the compensated AC component and the noise-suppressed DC component includes:

[0101] Step 1: Calculate the blood pulsation characteristic ratio based on the compensated AC component and the noise-suppressed DC component.

[0102] Before calculating blood oxygen saturation, the blood pulsation characteristic ratio must first be calculated based on the compensated AC component and the noise-suppressed DC component. The blood pulsation characteristic ratio is the specific proportional relationship between the red and infrared light signals during blood pulsation. It reflects the difference in absorption of different wavelengths of light by oxygenated and reduced hemoglobin in the blood.

[0103] Step 2: Obtain a preset calibration curve, which is obtained by fitting a quadratic equation based on clinical blood oxygen saturation data.

[0104] After obtaining the blood pulsation characteristic ratio, a preset calibration curve is used to calculate blood oxygen saturation. This calibration curve is constructed based on clinical blood oxygen saturation data and reflects the corresponding relationship between the blood pulsation characteristic ratio and blood oxygen saturation. To obtain more accurate blood oxygen saturation values, the calibration curve can be fitted using a quadratic equation. Specifically, a preset calibration curve is a curve constructed based on a large amount of clinical data, which is used to convert the blood pulsation characteristic ratio into blood oxygen saturation values. This curve is typically obtained through statistical analysis methods and can reflect the changes in the blood pulsation characteristic ratio at different blood oxygen saturation levels. Quadratic equation fitting is a mathematical method used to find the quadratic polynomial equation that is closest to the preset calibration curve using the least squares method or other optimization algorithm. This equation can be used to predict blood oxygen saturation values ​​based on the blood pulsation characteristic ratio. Furthermore, this preset calibration curve can be stored in a database file within the device or retrieved from a remote server via a network connection.

[0105] Step 3: Obtain blood oxygen saturation based on the blood pulsation characteristic ratio and the preset calibration curve.

[0106] Substitute the calculated blood pulsation characteristic ratio into the fitted quadratic equation to solve the blood oxygen saturation value. Output the blood oxygen saturation value for the user to view or further analyze. Specifically, the quadratic equation corresponding to the preset calibration curve is as follows:

[0107] SpO2=xR 2 +yR+z

[0108] Where SpO2 is the blood oxygen saturation; x, y, and z are the coefficients of the quadratic equation, which can be obtained based on clinical data fitting and calibration; and R is the blood pulsation characteristic ratio. The calculation formula for R is as follows:

[0109]

[0110] In this embodiment, the blood pulsation characteristic ratio is calculated using the compensated AC component and the noise-suppressed DC component. Accurate blood oxygen saturation values ​​are obtained by fitting a pre-set calibration curve using a quadratic equation. This method not only improves blood oxygen saturation measurement accuracy but also enhances the stability and reliability of the device.

[0111] In one embodiment, the AC components of the red photoelectric signal and the infrared photoelectric signal are dynamically compensated based on the light intensity and the body motion interference coefficient, and the compensated AC components include:

[0112] Step 1: Get the dynamic scale factor.

[0113] Here, a dynamic proportional coefficient can be calculated or determined, which will be used in the subsequent signal compensation process. This coefficient may be based on experimental data, theoretical calculations or real-time measurements, and is used to reflect the degree of influence of light signals and body motion interference on the AC component in the current environment. Furthermore, the dynamic proportional coefficient can be optimized by machine learning. Specifically, these dynamic proportional coefficients can be determined based on the photoelectric signals collected in a large number of body motion environments, and based on the calibration and optimization of these photoelectric signals and the corresponding body motion data (acceleration data) through machine learning.

[0114] Step 2: Dynamically compensate the AC components of the red photoelectric signal and the infrared photoelectric signal based on the dynamic proportional coefficient, light intensity, and body motion interference coefficient to obtain the compensated AC components.

[0115] Using the previously acquired dynamic scaling factor, combined with light intensity (which generally reflects the strength or brightness of the light signal) and body motion interference coefficient (which reflects the degree of signal interference caused by body movement), the AC components of the red and infrared photoelectric signals are compensated. The purpose of compensation is to reduce or eliminate signal fluctuations caused by light intensity variations and body motion interference, thereby improving signal stability and accuracy. After the above compensation process, the AC components of the red and infrared photoelectric signals are corrected to obtain compensated AC components. These compensated components are closer to the true value, reducing the influence of interference and noise.

[0116] In one embodiment, obtaining the dynamic scaling factor includes:

[0117] Step 1: Identify the wearing method of the wearer.

[0118] This step involves detecting or determining how the subject (e.g., user or patient) is wearing the measurement device, for example, whether it is worn on the wrist, finger, or elsewhere. Identification methods may include using sensors (e.g., accelerometers, gyroscopes, etc.) to detect the device's physical position or motion pattern, or through user input (e.g., selecting a wearing method through the device's user interface). Specifically, the wearing method here includes wrist or handheld wearing.

[0119] Step 2: According to the wearing method of the wearer, obtain the current dynamic scale coefficient from the preset dynamic scale coefficient-posture correspondence.

[0120] Once the wearing style is determined, the system accesses a preset dynamic scale factor-posture correspondence table or database. This correspondence table or database contains information related to the dynamic scale factor for different wearing styles. The dynamic scale factor is derived based on experimental data, theoretical calculations, or empirical rules to reflect changes in signal characteristics under different wearing postures. Based on the currently identified wearing style, the system retrieves the corresponding dynamic scale factor from the correspondence. This factor is used in the subsequent AC component dynamic compensation process to adjust the signal and reduce interference.

[0121] In one embodiment, the AC components of the red photoelectric signal and the infrared photoelectric signal are dynamically compensated based on the light intensity and the body motion interference coefficient, and the compensated AC components include:

[0122] Step 1: Determine the exercise intensity level based on acceleration data and adaptively adjust the compensation weight according to the exercise intensity level.

[0123] Use acceleration data to assess the wearer's exercise intensity. This can be achieved by calculating the acceleration amplitude, frequency, or other relevant indicators. Based on the exercise intensity, the exercise is divided into different levels (such as low intensity, medium intensity, high intensity, etc.). Based on the exercise intensity level, the compensation weight is adaptively adjusted. Generally, the greater the exercise intensity, the more significant the impact of body motion interference on the signal, so a larger compensation weight is required to offset this interference.

[0124] Step 2: Obtain the dynamic scale factor corresponding to the light intensity and the preset baseline offset correction constant.

[0125] The dynamic scaling factor is predetermined based on light intensity and is used to reflect changes in signal characteristics under different conditions. The baseline offset correction constant is a preset value used to correct the baseline offset in the signal, that is, the average offset of the signal in the static state.

[0126] Step 3: Based on the light intensity, body motion interference coefficient, adjusted compensation weight, dynamic scale coefficient, and baseline offset correction constant, construct the forward compensation term and reverse interference term respectively.

[0127] The forward compensation term is constructed based on light intensity, body motion interference coefficient, adjusted compensation weight, and dynamic scale factor, aiming to enhance the useful component (AC component) in the signal. The reverse interference term is constructed based on these parameters and the baseline offset correction constant, aiming to suppress or eliminate the interference component in the signal.

[0128] Step 4: Combine the forward compensation term and the reverse interference term to generate the AC component compensation calculation formula.

[0129] The forward compensation term and the reverse interference term are combined to form a complete AC component compensation calculation formula. This formula will be used to calculate the compensated AC component.

[0130] Step 5: Calculate the compensated AC component according to the AC component compensation calculation formula.

[0131] The AC component compensation calculation formula is used to compensate the AC component of the original red photoelectric signal and the infrared photoelectric signal. The compensated AC component will have a higher signal-to-noise ratio and more accurate physiological information.

[0132] Specifically, the AC component compensation calculation formula is as follows:

[0133] AC 红光 / 红外 =(aK n+m *bP n+m +C)-(dK n+m *eP n+m +F)

[0134] Where, (aK n+m *bP n+m +C) is the positive compensation term; (dK n+m *eP n+m +F) is the reverse compensation term; K n+m The body motion interference coefficient corresponding to the sampling point position (n, m); P n+m is the light intensity corresponding to the sampling point position (n, m); a and d are the adjusted compensation weights; b and e are the dynamic proportional coefficients corresponding to the light intensity; C and F are the baseline offset correction constants corresponding to forward compensation and reverse interference, respectively.

[0135] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0136] Based on the same inventive concept, embodiments of the present application also provide a blood oxygen saturation detection device for implementing the aforementioned blood oxygen saturation detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the blood oxygen saturation detection device provided below can be found in the above-described limitations on the blood oxygen saturation detection method and will not be further elaborated here.

[0137] In one embodiment, Figure 4 As shown, a blood oxygen saturation detection device is provided, comprising:

[0138] The data acquisition module 100 is used to obtain the red photoelectric signal, infrared photoelectric signal and acceleration data corresponding to the wearer's body movement collected by the pulse oximeter device;

[0139] The motion interference module 200 is used to extract the light intensity corresponding to the current sampling data point based on the red photoelectric signal and the infrared photoelectric signal, and obtain the body motion interference coefficient corresponding to the current sampling data point based on the acceleration data;

[0140] An AC processing module 300 is configured to dynamically compensate the AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components;

[0141] A DC processing module 400 is used to extract the DC components of the red photoelectric signal and the infrared photoelectric signal;

[0142] The blood oxygen saturation calculation module 500 is used to calculate the blood oxygen saturation according to the compensated AC component and DC component.

[0143] In one embodiment, the blood oxygen saturation calculation module 500 is further used to suppress the noise of the DC component of the red photoelectric signal and the infrared photoelectric signal by using the average of adjacent point differences to obtain the noise-suppressed DC component; and calculate the blood oxygen saturation based on the compensated AC component and the noise-suppressed DC component.

[0144] In one embodiment, the blood oxygen saturation calculation module 500 is further used to obtain the DC component of two adjacent sampling points of the red photoelectric signal and the DC component of two adjacent sampling points of the infrared photoelectric signal within a unit time; and calculate the average DC component of the red photoelectric signal and the average DC component of the infrared photoelectric signal.

[0145] In one embodiment, the blood oxygen saturation calculation module 500 is further used to calculate the blood pulsation characteristic ratio based on the compensated AC component and the DC component after noise suppression; obtain a preset calibration curve, which is obtained by fitting a quadratic equation based on clinical blood oxygen saturation data; and obtain blood oxygen saturation based on the blood pulsation characteristic ratio and the preset calibration curve.

[0146] In one embodiment, the AC processing module 300 is further used to obtain a dynamic proportional coefficient; dynamically compensate the AC components of the red photoelectric signal and the infrared photoelectric signal based on the dynamic proportional coefficient, light intensity and body motion interference coefficient to obtain a compensated AC component.

[0147] In one embodiment, the AC processing module 300 is further configured to identify a wearing style of the wearer;

[0148] According to the wearing method of the wearer, the current dynamic scale coefficient is obtained from the preset dynamic scale coefficient-posture correspondence relationship.

[0149] In one embodiment, the AC processing module 300 is also used to determine the motion intensity level based on the acceleration data, and adaptively adjust the compensation weight according to the motion intensity level; obtain the dynamic proportional coefficient corresponding to the light intensity, and the preset baseline offset correction constant; construct the forward compensation term and the reverse interference term based on the light intensity, body motion interference coefficient, the adjusted compensation weight, the dynamic proportional coefficient and the baseline offset correction constant respectively; combine the forward compensation term and the reverse interference term to generate an AC component compensation calculation formula; and calculate the compensated AC component according to the AC component compensation calculation formula.

[0150] Each module in the aforementioned blood oxygen saturation detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0151] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, memory, communication interface, display screen and input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a blood oxygen saturation detection method is implemented.

[0152] Those skilled in the art will understand that Figure 5 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0153] In addition, the present application also provides a pulse oximeter device, which specifically uses the above-mentioned blood oxygen saturation detection method to perform blood oxygen saturation detection.

[0154] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned blood oxygen saturation detection method when executing the computer program.

[0155] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned blood oxygen saturation detection method is implemented.

[0156] In one embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned blood oxygen saturation detection method when executed by a processor.

[0157] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0158] The technical features of the above embodiments can 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.

[0159] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for detecting blood oxygen saturation, characterized in that: The method comprises: Obtaining red photoelectric signals, infrared photoelectric signals, and acceleration data corresponding to the wearer's body movements collected by the pulse oximeter device; Extracting the light intensity corresponding to the current sampling data point according to the red photoelectric signal and the infrared photoelectric signal, and obtaining the body motion interference coefficient corresponding to the current sampling data point according to the acceleration data; Dynamically compensating AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components; extracting DC components of the red photoelectric signal and the infrared photoelectric signal; The blood oxygen saturation is calculated according to the compensated AC component and the DC component.

2. The method according to claim 1, characterized in that Calculating the blood oxygen saturation according to the compensated AC component and the DC component includes: noise suppression is performed on the DC components of the red photoelectric signal and the infrared photoelectric signal by using an adjacent point difference average method to obtain a noise-suppressed DC component; The blood oxygen saturation is calculated according to the compensated AC component and the noise-suppressed DC component.

3. The method according to claim 2, characterized in that The DC components of the red photoelectric signal and the infrared photoelectric signal are subjected to noise suppression by using the adjacent point difference average method to obtain the DC components after noise suppression, including: Obtain the DC components of two adjacent sampling points of the red photoelectric signal and the DC components of two adjacent sampling points of the infrared photoelectric signal within a unit time; Calculate the DC component mean value of the red photoelectric signal and the DC component mean value of the infrared photoelectric signal.

4. The method according to claim 2, characterized in that Calculating the blood oxygen saturation according to the compensated AC component and the noise-suppressed DC component includes: Calculating a blood pulsation characteristic ratio based on the compensated AC component and the noise-suppressed DC component; Obtaining a preset calibration curve, wherein the preset calibration curve is obtained by fitting a quadratic equation based on clinical blood oxygen saturation data; The blood oxygen saturation is obtained according to the blood pulsation characteristic ratio and the preset calibration curve.

5. The method according to claim 1, wherein The dynamically compensating the AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain the compensated AC components includes: Get the dynamic scale factor; Dynamically compensate the AC components of the red photoelectric signal and the infrared photoelectric signal based on the dynamic proportional coefficient, the light intensity, and the body motion interference coefficient to obtain compensated AC components.

6. The method according to claim 5, characterized in that The obtaining of the dynamic proportional coefficient comprises: Identify the wearing method of the wearer; According to the wearing manner of the wearing object, a current dynamic proportional coefficient is obtained from a preset dynamic proportional coefficient-posture correspondence relationship.

7. The method according to claim 1, characterized in that The dynamically compensating the AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain the compensated AC components includes: determining an exercise intensity level according to the acceleration data, and adaptively adjusting a compensation weight according to the exercise intensity level; Obtaining a dynamic proportional coefficient corresponding to the light intensity and a preset baseline offset correction constant; constructing a forward compensation term and a reverse interference term based on the light intensity, the body motion interference coefficient, the adjusted compensation weight, the dynamic proportional coefficient, and the baseline offset correction constant; Combining the forward compensation term and the reverse interference term to generate an AC component compensation calculation formula; The compensated AC component is calculated according to the AC component compensation calculation formula.

8. A blood oxygen saturation detection device, characterized in that: The device comprises: A data acquisition module is used to obtain red photoelectric signals, infrared photoelectric signals and acceleration data corresponding to the wearer's body movement collected by the pulse oximeter device; a motion interference module, configured to extract the light intensity corresponding to the current sampling data point based on the red photoelectric signal and the infrared photoelectric signal, and obtain the body motion interference coefficient corresponding to the current sampling data point based on the acceleration data; an AC processing module, configured to dynamically compensate AC components of the red photoelectric signal and the infrared photoelectric signal based on the light intensity and the body motion interference coefficient to obtain compensated AC components; A DC processing module, used for extracting DC components of the red photoelectric signal and the infrared photoelectric signal; The blood oxygen saturation calculation module is used to calculate the blood oxygen saturation according to the compensated AC component and the DC component.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A pulse oximeter device, characterized in that: Blood oxygen saturation is detected using the method according to any one of claims 1 to 7.

Images