Blood component detection method and related equipment

Through the analysis of photovoltaic pulse wave signal at different wavelengths and light intensity, the characteristic parameters and proportional functions are extracted, and the problem of poor detection accuracy of non-invasive blood components is solved, achieving higher detection accuracy.

CN114943249BActive Publication Date: 2024-12-03FUZHOU JIUHOUSHENGYI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210522702.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-13
Publication Date
2024-12-03
Estimated Expiration
2042-05-13

AI Technical Summary

Technical Problem

The existing non-invasive blood component detection methods are difficult to accurately calibrate when the concentration in the blood changes greatly, resulting in poor detection accuracy.

Method used

By obtaining the photovoltaic pulse wave signals at different wavelengths and different light intensities, performing time-domain and frequency-domain analysis, extracting characteristic parameters, and calculating feature proportional functions, thereby performing blood component detection.

Benefits of technology

It improves the accuracy of blood component detection and can more accurately reflect the concentration changes of blood components.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114943249B_ABST
    Figure CN114943249B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides a blood component detection method, including: obtaining photoplethysmogram signals collected from a designated target at different wavelengths and different light intensities; analyzing and processing the photoplethysmogram signals in the time domain and frequency domain to obtain characteristic parameters corresponding to the photoplethysmogram signals; calculating characteristic proportion functions corresponding to the photoplethysmogram signals at different wavelengths according to the characteristic parameters corresponding to the photoplethysmogram signals at different light intensities; using the characteristic proportion functions corresponding to the photoplethysmogram signals as independent variables and the target blood component value as a dependent variable to calculate the blood component results of the designated target. By obtaining the photoplethysmogram signals of the designated target at different wavelengths and different light intensities and extracting the corresponding characteristic parameters from the information, obtaining the characteristic proportion functions corresponding to each wavelength through the characteristic parameters, and then performing blood component detection according to the characteristic proportion functions, the accuracy of blood component detection can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of non-invasive blood analysis, and in particular to a blood component detection method and related equipment. Background Art

[0002] The concentration changes of blood components and components are closely related to the human cardiovascular system, digestive system, endocrine system, etc. It is integrated into the routine clinical examinations of various departments, including cardiology, gastroenterology, urology, obstetrics and gynecology, endocrinology, nephrology and other departments. The diagnosis and routine health examinations have important clinical significance and value. In chronic diseases, it is a must-check item for follow-up visits, and the trend changes of long-term blood components play a pivotal role in the clinical physician's prediction, subtype classification, diagnosis, and medication of the disease. However, for areas where the supply and demand of medical supplies and clinical infrastructure are relatively tight, especially in relatively remote areas with relatively scattered populations, when well-equipped blood test centers are insufficient, low-cost, non-invasive blood test analysis tools are needed as useful tools for preliminary blood examinations and screening in regional or local health centers. In addition, the changing trend or concentration fluctuation of specific blood components over a period of time can reflect the metabolism of substances in the body to a certain extent, which is particularly helpful for the diagnosis of chronic diseases and geriatric diseases, as well as the judgment and analysis of the prevention of complications. Therefore, non-invasive optical blood test analysis technology and systems can be used in home environments and community health centers, and can provide timely feedback and real-time monitoring for early screening and follow-up of chronic diseases.

[0003] At present, the most common non-invasive real-time monitoring products for physiological and biochemical signs on the market mainly use photoplethysmography (PPG) and electrical impedance method as the main detection methods. Among them, the quantitative signal obtained by the electrical impedance method has limited changes and can only become a regression parameter for blood test modeling. Although photoplethysmography can effectively calibrate the changes in the absorption spectrum caused by the volume change of blood with the beating of the heart, most of the blood test components contain complex absorption spectra (absorption peaks). Therefore, when there are large changes in the concentration of blood, it is difficult to accurately calibrate it by non-invasive means, resulting in poor accuracy of blood component detection. Summary of the invention

[0004] The embodiments of the present invention are intended to provide a blood component detection method, which aims to solve the problem that when a large amount of concentration changes in the blood are difficult to be accurately calibrated by non-invasive means, the accuracy of blood component detection is poor. Since light sources of different wavelengths and different light intensities scatter and penetrate at different depths between skin tissues, and the distribution density of large arteries, small arteries and microcirculation in tissues at different depths is different, there is a gradient relationship between the concentrations of various components in the tissue. Therefore, the photoelectric volumetric pulse wave signals of different wavelengths and different light intensities contain information about the concentration gradient in the blood system. The corresponding characteristic parameters are extracted by obtaining the photoelectric volumetric pulse wave signals of the specified target at different wavelengths and different light intensities, and the characteristic ratio functions corresponding to each wavelength are obtained through the characteristic parameters. Then, blood component detection is performed according to the characteristic ratio functions, which can improve the accuracy of blood component detection.

[0005] In a first aspect, an embodiment of the present invention provides a blood component detection method, the blood component detection method comprising:

[0006] Acquire the photoplethysmographic signals of the designated target collected at different wavelengths and different light intensities;

[0007] Performing time domain and frequency domain analysis on the photoplethysmography signal to obtain characteristic parameters corresponding to the photoplethysmography signal;

[0008] Calculating characteristic proportional functions corresponding to the photoplethysmographic signals at different wavelengths according to characteristic parameters corresponding to the photoplethysmographic signals at different light intensities;

[0009] The characteristic proportional function corresponding to the photoplethysmographic signal is used as an independent variable, and the target blood component value is used as a dependent variable to calculate the blood component result of the designated target.

[0010] Optionally, the performing time domain and frequency domain analysis and processing on the photoplethysmography signal to obtain characteristic parameters corresponding to the photoplethysmography signal includes:

[0011] Dividing the photoplethysmography signal according to the signal period to obtain a segmentation sequence of the photoplethysmography signal, each segmentation sequence including segmentation signals having the same number of periods as the photoplethysmography signal;

[0012] Processing each segmented signal in the segmented sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmography signal;

[0013] Processing each segmented signal in the segmented sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmographic signal;

[0014] A joint calculation is performed based on the frequency domain characteristic data and the time domain characteristic data to obtain characteristic parameters corresponding to the photoplethysmography signal.

[0015] Optionally, the processing of each segmented signal in the segmented sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmographic signal includes:

[0016] Compound series conversion is performed on each segmentation signal in the segmentation sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal.

[0017] Optionally, the processing of each segmented signal in the segmented sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmographic signal includes:

[0018] The peak-to-peak value and the average value in the time domain are calculated for each segmentation signal in the segmentation sequence to obtain the time domain characteristic data corresponding to the photoplethysmogram signal.

[0019] Optionally, calculating the characteristic proportional function corresponding to the photoplethysmography signal at different wavelengths according to the characteristic parameters corresponding to the photoplethysmography signal at different light intensities includes:

[0020] According to the characteristic parameters corresponding to the photoplethysmographic signal, the characteristic function corresponding to the photoplethysmographic signal at different light intensities at the same wavelength is calculated to obtain the characteristic proportional function corresponding to the photoplethysmographic signal at each wavelength.

[0021] Optionally, the method of calculating the blood component result of the designated target by taking the characteristic proportional function corresponding to the photoplethysmography signal as the independent variable and the target blood component value as the dependent variable includes:

[0022] A multi-parameter regression analysis model is constructed using the characteristic proportional function corresponding to the photoplethysmographic signal as an independent variable and the target blood component value as a dependent variable;

[0023] The blood component results of the designated target are calculated through the multi-parameter regression analysis model.

[0024] Optionally, the multi-parameter regression analysis model includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is:

[0025]

[0026] Wherein, Y is the dependent variable, Tn is the independent variable, βn is the regression coefficient of the independent variable, and N is the number of the independent variables.

[0027] In a second aspect, an embodiment of the present invention provides a blood component detection device, the device comprising:

[0028] An acquisition module is used to acquire photoplethysmographic signals collected from a designated target at different wavelengths and different light intensities;

[0029] A processing module, used for analyzing and processing the photoplethysmography signal in the time domain and the frequency domain to obtain characteristic parameters corresponding to the photoplethysmography signal;

[0030] A first calculation module, used to calculate a characteristic proportional function corresponding to the photoplethysmography signal at different wavelengths according to characteristic parameters corresponding to the photoplethysmography signal at different light intensities;

[0031] The second calculation module is used to calculate the blood component result of the designated target by taking the characteristic proportional function corresponding to the photoplethysmography signal as the independent variable and the target blood component value as the dependent variable.

[0032] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the blood component detection method provided in the embodiment of the present invention when executing the computer program.

[0033] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the blood component detection method provided in the embodiment of the invention are implemented.

[0034] In an embodiment of the present invention, the photoplethysmogram signals collected by the designated target at different wavelengths and different light intensities are obtained; the photoplethysmogram signals are analyzed and processed in the time domain and frequency domain to obtain characteristic parameters corresponding to the photoplethysmogram signals; characteristic proportion functions corresponding to the photoplethysmogram signals at different wavelengths are calculated according to the characteristic parameters corresponding to the photoplethysmogram signals at different light intensities; the blood component results of the designated target are calculated using the characteristic proportion functions corresponding to the photoplethysmogram signals as independent variables and the target blood component values ​​as dependent variables. By obtaining the photoplethysmogram signals of the designated target at different wavelengths and different light intensities and extracting the corresponding characteristic parameters from the information, obtaining the characteristic proportion functions corresponding to each wavelength through the characteristic parameters, and then performing blood component detection according to the characteristic proportion functions, the accuracy of blood component detection can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 is an architecture diagram of a blood component detection system provided by an embodiment of the present invention;

[0037] Figure 2 is a flow chart of a blood component detection method provided by an embodiment of the present invention;

[0038] Figure 3 is a schematic diagram of a photoplethysmography signal segmentation method provided by an embodiment of the present invention;

[0039] Figure 4 is a schematic diagram of the principle of multi-wavelength measurement provided by an embodiment of the present invention;

[0040] Figure 5 is a structural schematic diagram of a blood component detection device provided by an embodiment of the present invention;

[0041] Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] See also Figure 1 , Figure 1 is an architecture diagram of a blood component detection system provided by an embodiment of the present invention, such as Figure 1 As shown, the blood component detection system includes: a multi-wavelength photosensitivity transceiver module, a photoplethysmography signal module and a computing terminal. The multi-wavelength photosensitivity transceiver module is signal-connected to the photoplethysmography signal module, and the photoplethysmography signal module is signal-connected to the computing terminal.

[0044] Among them, the multi-wavelength photosensor transceiver module includes a multi-wavelength light source array, a photosensor and a light intensity control unit. The light intensity control unit is connected to the multi-wavelength light source array signal. The light intensity control unit is used to control the luminous intensity of the multi-wavelength light source array so that the multi-wavelength light source array emits light with different luminous intensities. The multi-wavelength light source array includes light sources of multiple wavelengths, and each light source corresponds to a wavelength. The photosensor is used to receive light signals scattered and penetrated through the skin tissue of the designated target. Specifically, the light intensity control unit controls the multi-wavelength light source array to illuminate the designated target with different luminous intensities. The light is scattered and penetrated through the skin tissue of the designated target, and is received by the photosensor and converted into corresponding light signals. The light signal corresponding to the multi-wavelength light source array received by the photosensor is an array signal.

[0045] The photoelectric volumetric pulse wave signal module includes an array signal gain filter unit, an array signal acquisition unit, an array signal storage unit, a data transmission unit and a microprocessor unit. The microprocessor unit is respectively connected to the array signal gain filter unit, the array signal acquisition unit, the array signal storage unit and the data transmission unit, and the microprocessor unit controls the array signal gain filter unit, the array signal acquisition unit, the array signal storage unit and the data transmission unit to perform their respective corresponding functions. The array signal acquisition unit is connected to the photosensitive sensor signal, and is used to receive the array signal collected by the photosensitive sensor and store it in the array signal storage unit. The array signal gain filter unit is used to gain and filter the received array signal to obtain photoelectric volumetric pulse wave signals under different wavelengths and different light intensities. The data transmission unit is used to transmit the photoelectric volumetric pulse wave signal to the computing terminal.

[0046] The computing terminal is used to perform pulse wave analysis, characteristic proportion function analysis and multi-parameter regression modeling analysis on the photoplethysmogram signal. By performing pulse wave analysis on the photoplethysmogram signal, the frequency domain characteristic parameters and time domain characteristic parameters of the photoplethysmogram signal are obtained; by performing characteristic proportion function analysis on the frequency domain characteristic parameters and the time domain characteristic parameters, the multi-channel signal differential characteristics, multi-channel signal proportion characteristics and multi-channel signal linear combination proportion characteristics of the photoplethysmogram signal are obtained; and by multi-parameter regression modeling analysis, model regression coefficient analysis and blood component concentration calculation are performed.

[0047] In an embodiment of the present invention, the photoelectric volume pulse wave signal of a specified target at different wavelengths and different light intensities is obtained and the corresponding characteristic parameters are extracted using this information. The characteristic proportion function corresponding to each wavelength is obtained through the characteristic parameters, and blood component detection is performed based on the characteristic proportion function, thereby improving the accuracy of blood component detection.

[0048] The above-mentioned signal connection can be a wired connection or a wireless connection. The above-mentioned wireless connection method can include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultrawideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0049] See also Figure 2 , Figure 2 is a flow chart of a blood component detection method provided by an embodiment of the present invention, such as Figure 2 As shown, the blood component detection method is applied to a computing terminal, and specifically includes the following steps:

[0050] 201. Acquire photoplethysmographic signals of a designated target collected under different wavelengths and different light intensities.

[0051] In an embodiment of the present invention, the light intensity control unit in the multi-wavelength photosensor transceiver module controls the multi-wavelength light source array to illuminate the designated target with different luminous intensities. The light is scattered and penetrated through the skin tissue of the designated target, and is received by the photosensor and converted into a corresponding light signal. The light signal corresponding to the multi-wavelength light source array received by the photosensor is an array signal.

[0052] The photoplethysmography signal module receives the array signal collected by the photosensor and stores it in the array signal storage unit. The array signal gain filter unit is used to gain and filter the received array signal to obtain photoplethysmography signals under different wavelengths and different light intensities. The data transmission unit is used to transmit the photoplethysmography signal to the computing terminal.

[0053] There are multiple photoplethysmographic signals corresponding to different light intensities at each wavelength.

[0054] The above-mentioned designated target may be a designated human body part, such as a human finger part.

[0055] 202. Analyze and process the photoplethysmogram signal in the time domain and the frequency domain to obtain characteristic parameters corresponding to the photoplethysmogram signal.

[0056] In an embodiment of the present invention, the wavelength and light intensity are combined, and each combination of a small wavelength and light intensity corresponds to a photoplethysmogram signal. For example, by combining wavelength A, wavelength B, light intensity I1, and light intensity I2, a photoplethysmogram signal corresponding to wavelength A light intensity I1 and a photoplethysmogram signal corresponding to wavelength A light intensity I2 can be obtained. A photoplethysmogram signal corresponding to wavelength B light intensity I1 and a photoplethysmogram signal corresponding to wavelength B light intensity I2 can be obtained.

[0057] Each photoplethysmogram signal is analyzed and processed in the time domain and the frequency domain to obtain characteristic parameters corresponding to each photoplethysmogram signal.

[0058] The above characteristic parameters may be parameters corresponding to characteristics such as amplitude, phase, peak-to-peak value, average value, etc.

[0059] Optionally, in the step of performing time domain and frequency domain analysis and processing on the photoplethysmogram signal to obtain characteristic parameters corresponding to the photoplethysmogram signal, the photoplethysmogram signal can be segmented according to the signal period to obtain a segmented sequence of the photoplethysmogram signal, each segmented sequence including segmented signals having the same number of periods as the photoplethysmogram signal; each segmented signal in the segmented sequence is processed in the frequency domain to obtain frequency domain characteristic data corresponding to the photoplethysmogram signal; each segmented signal in the segmented sequence is processed in the time domain to obtain time domain characteristic data corresponding to the photoplethysmogram signal; and the characteristic parameters corresponding to the photoplethysmogram signal are obtained by performing joint calculation based on the frequency domain characteristic data and the time domain characteristic data.

[0060] Specifically, the continuous photoplethysmogram signal can be segmented into pulse waves one by one according to the lowest point, so as to obtain a segmentation sequence of the photoplethysmogram signal, each segmentation signal corresponding to a pulse wave, such as Figure 3 As shown, Figure 3 It is a schematic diagram of a photoplethysmography signal segmentation method provided by an embodiment of the present invention.

[0061] After the continuous pulse wave is divided into individual pulse waves according to the lowest point, the pulse waves between two low points can be subtracted in equal proportion to complete the pulse wave flattening action, thereby obtaining the segmented signal after the pulse wave is flattened.

[0062] The frequency domain feature data may include frequency domain features such as amplitude and phase, and the frequency domain feature data may also be called harmonic frequency feature data. The time domain feature data may include time domain features such as peak-to-peak value and average value.

[0063] The above-mentioned characteristic parameters corresponding to the photoplethysmogram signal are obtained by jointly calculating the frequency domain characteristic data and the time domain characteristic data. It can be that the characteristics such as amplitude, phase, peak-to-peak value, and average value are jointly calculated to obtain the characteristic parameters corresponding to the photoplethysmogram signal. For example, the amplitude, phase, peak-to-peak value, and average value corresponding to each photoplethysmogram signal can be linearly combined, and the combined characteristics can be proportionally calculated to obtain the characteristic parameters corresponding to the photoplethysmogram signal.

[0064] Optionally, in the step of performing frequency domain processing on each segmented signal in the segmented sequence to obtain frequency domain characteristic data corresponding to the photoplethysmogram signal, each segmented signal in the segmented sequence may be subjected to compound series conversion processing to obtain frequency domain characteristic data corresponding to the photoplethysmogram signal.

[0065] Specifically, the segmentation signal is shown in the following formula:

[0066]

[0067] In the above formula, Y(k) is the segmented signal, which can also be understood as the discrete digitized value of a single pulse wave. The above N represents the total number of segmented signals, and A n represents the amplitude of the nth segmentation signal, P n It represents the phase of the nth segmented signal, and f0 is the frequency of the pulse heartbeat.

[0068] It should be noted that A n It can also be called the amplitude of the nth harmonic frequency, P n It can also be called the phase of the nth harmonic frequency. n = 0, 1, 2, 3, ..., ∞. However, in the embodiment of the present invention, more than 99% of the energy of the pulse wave can be covered by calculating A0-A10. Y(k) is a pulse wave of a signal cycle that has been cut and leveled.

[0069] The above amplitude A n As shown in the following formula:

[0070]

[0071] By processing the segmented signal through compound series conversion, the frequency domain characteristic data corresponding to the photoplethysmogram signal can be accurately obtained.

[0072] Optionally, in the step of performing time domain processing on each segmented signal in the segmented sequence to obtain time domain characteristic data corresponding to the photoplethysmogram signal, the peak-to-peak value and the average value in the time domain of each segmented signal in the segmented sequence can be calculated respectively to obtain the time domain characteristic data corresponding to the photoplethysmogram signal.

[0073] The peak-to-peak value is the difference between the highest point and the lowest point of a segmented signal, that is, the peak-to-peak value is the difference between the highest point and the lowest point in a pulse wave. Specifically, the peak-to-peak value is as shown in the following formula:

[0074] Peak-to-peak value = Max(Y(k))-Min(Y(k))

[0075] The above average value is the average value of all segmented signals in a photoplethysmogram signal. Specifically, the above average value is as shown in the following formula:

[0076]

[0077] By calculating the peak-to-peak value and the average value, the time domain characteristic data corresponding to the photoplethysmographic signal is obtained.

[0078] 203. Calculate characteristic proportional functions corresponding to the photoplethysmographic signals at different wavelengths according to characteristic parameters corresponding to the photoplethysmographic signals at different light intensities.

[0079] In an embodiment of the present invention, a characteristic function corresponding to each photoplethysmogram signal can be calculated based on the characteristic parameters corresponding to each photoplethysmogram signal, and a characteristic proportional function corresponding to the photoplethysmogram signal at different wavelengths can be calculated based on the characteristic function corresponding to the photoplethysmogram signal.

[0080] Specifically, the characteristic function may be a ratio, and the ratio may be a ratio of a peak-to-peak value to an average value, which may be expressed as f(wavelength i, light intensity j) = peak-to-peak value / average value, indicating a characteristic function corresponding to a photoplethysmogram signal having a wavelength i and a light intensity j; or an amplitude A n The ratio to the average value can be expressed as f(wavelength i, light intensity j) = amplitude A n / average value; can also be phase P n The ratio to the average value can be expressed as f(wavelength i, light intensity j) = phase P n / average value.

[0081] The characteristic proportional function corresponding to the photoplethysmographic signal can be calculated for each light source, one light source corresponding to one wavelength.

[0082] Optionally, in the step of calculating the characteristic proportional function corresponding to the photoelectric volumetric ...

[0083] Specifically, the characteristic function corresponding to each photoplethysmogram signal can be calculated to obtain the characteristic function corresponding to each photoplethysmogram signal at different wavelengths and different light intensities, thereby sorting out the characteristic functions corresponding to the photoplethysmogram signals at different light intensities at the same wavelength, and performing proportional calculations on the characteristic functions corresponding to the photoplethysmogram signals at different light intensities at the same wavelength to obtain the characteristic proportional functions corresponding to the photoplethysmogram signals at each wavelength.

[0084] The above characteristic ratio function can be understood as the ratio of the characteristic function.

[0085] For example, if Figure 4 As shown, Figure 4 FIG. 1 is a schematic diagram showing the principle of a multi-wavelength measurement provided by an embodiment of the present invention. Figure 4 In the figure, different wavelengths are wavelength A and wavelength B, and different light intensities are light intensity I1 and light intensity I2. Wavelength A corresponds to wavelength A light source, and wavelength B corresponds to wavelength B light source. The wavelength A light source and the wavelength B light source irradiate the measuring part of the human body with light intensity I1 to obtain a photoplethysmogram signal corresponding to the light intensity I1 of wavelength A and a photoplethysmogram signal corresponding to the light intensity I1 of wavelength B. The characteristic function is calculated for the photoplethysmogram signal corresponding to the light intensity I1 of wavelength A to obtain the characteristic function f(wavelength A, I1) of the photoplethysmogram signal corresponding to the light intensity I1 of wavelength A. The characteristic function is calculated for the photoplethysmogram signal corresponding to the light intensity I1 of wavelength B to obtain the characteristic function f(wavelength B, I1) of the photoplethysmogram signal corresponding to the light intensity I1 of wavelength A. After obtaining the characteristic function f(wavelength A, I1) and the characteristic function f(wavelength B, I1), the wavelength A light source and the wavelength B light source are controlled to irradiate the measured part of the human body with the light intensity I2, and the photoplethysmogram signal corresponding to the wavelength A light intensity I2 and the photoplethysmogram signal corresponding to the wavelength B light intensity I2 are obtained. The characteristic function is calculated for the photoplethysmogram signal corresponding to the wavelength A light intensity I2, and the characteristic function f(wavelength A, I2) of the photoplethysmogram signal corresponding to the wavelength A light intensity I2 is obtained. The characteristic function is calculated for the photoplethysmogram signal corresponding to the wavelength B light intensity I2, and the characteristic function f(wavelength B, I2) of the photoplethysmogram signal corresponding to the wavelength A light intensity I2 is obtained. Then the characteristic functions are f(wavelength A, I1), f(wavelength B, I1), f(wavelength A, I2), and f(wavelength B, I2). The ratio between the characteristic functions at the same wavelength is calculated to obtain the characteristic ratio function TA (f (wavelength A, I1), f (wavelength A, I2)). The characteristic ratio function corresponding to the wavelength A is shown in the following formula:

[0086]

[0087] Similarly, the characteristic proportional function corresponding to the wavelength B is shown in the following formula:

[0088]

[0089] In a possible embodiment, multiple light intensity results such as I1, I2, I3, ... can be collected to enhance the stability of the calculated characteristic ratio function. When multiple light intensity results such as I1, I2, I3, ... are collected, the characteristic ratio function corresponding to wavelength A is the linear combination ratio of the characteristic functions.

[0090] 204. Taking the characteristic proportional function corresponding to the photoplethysmographic signal as the independent variable and the target blood component value as the dependent variable, the blood component result of the designated target is calculated.

[0091] In an embodiment of the present invention, after obtaining the characteristic proportion function corresponding to the photoplethysmographic signals of different wavelengths, the characteristic proportion function can be used as the independent variable and the target blood component value can be used as the dependent variable to calculate the blood component result of the specified target. The above-mentioned target blood component value can be a blood concentration value, and the blood component result can be a blood concentration.

[0092] Optionally, in the step of calculating the blood composition result of the specified target using the characteristic proportional function corresponding to the photoplethysmogram signal as the independent variable and the target blood component value as the dependent variable, a multi-parameter regression analysis model can be constructed using the characteristic proportional function corresponding to the photoplethysmogram signal as the independent variable and the target blood component value as the dependent variable; the blood composition result of the specified target is calculated using the multi-parameter regression analysis model.

[0093] Specifically, the characteristic proportion function is calculated for the photoplethysmographic signals of different wavelengths, such as wavelength A and wavelength B, to obtain the characteristic proportion function group {TA, TB} as the independent variable, and the specific blood concentration H measured in the population is used as the dependent variable. Multiple linear regression is used to calibrate the regression coefficients β0-βn to complete the population modeling.

[0094] In a possible embodiment, multiple light sources such as wavelength A, wavelength B, wavelength C, etc. can be collected to enhance the fit and statistical credibility of the multi-parameter regression analysis model, thereby improving the reliability of non-invasive detection of specific blood components.

[0095] Optionally, the multi-parameter regression analysis model includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is:

[0096]

[0097] Wherein, Y is the dependent variable, Tn is the independent variable, βn is the regression coefficient of the independent variable, and N is the number of the independent variables.

[0098] Furthermore, the multi-parameter regression analysis model includes the independent variable, the dependent variable, and the first regression coefficient and the second regression coefficient of the independent variable. The multi-parameter regression analysis model is:

[0099]

[0100] Wherein, Y is the dependent variable, Tn is the independent variable, βn is the first regression coefficient of the independent variable, αn is the first regression coefficient of the independent variable, and N is the number of the independent variables.

[0101] In an embodiment of the present invention, the photoplethysmogram signals collected by the designated target at different wavelengths and different light intensities are obtained; the photoplethysmogram signals are analyzed and processed in the time domain and frequency domain to obtain characteristic parameters corresponding to the photoplethysmogram signals; characteristic proportion functions corresponding to the photoplethysmogram signals at different wavelengths are calculated according to the characteristic parameters corresponding to the photoplethysmogram signals at different light intensities; the blood component results of the designated target are calculated using the characteristic proportion functions corresponding to the photoplethysmogram signals as independent variables and the target blood component values ​​as dependent variables. By obtaining the photoplethysmogram signals of the designated target at different wavelengths and different light intensities and extracting the corresponding characteristic parameters from the information, obtaining the characteristic proportion functions corresponding to each wavelength through the characteristic parameters, and then performing blood component detection according to the characteristic proportion functions, the accuracy of blood component detection can be improved.

[0102] To further illustrate the technical effect of the embodiment of the present invention, the embodiment of the present invention uses red light and infrared light to perform non-invasive blood glucose concentration detection, as shown in Table 1 and Table 2:

[0103] Table 1

[0104]

[0105] Table 1 above shows the characteristic functions f and proportional function T obtained by measuring the red light / infrared light source before meals.

[0106] Table 2

[0107]

[0108]

[0109] Table 2 above shows the characteristic functions f and proportional function T obtained by measuring the red light / infrared light source after a meal.

[0110] The results of blood glucose concentration were calculated by multi-parameter regression analysis model as shown in Table 3:

[0111]

[0112] Table 3 shows the results of blood glucose concentration. It can be seen from Table 3 that the embodiment of the present invention is characterized by high scalability, and can calculate any specific component in any blood with a concentration gradient between the systemic circulation and the microcirculation by screening light sources of different wavelengths and light intensities.

[0113] It should be noted that the blood component detection method provided in the embodiment of the present invention can be applied to smart phones, computers, servers and other devices that can perform blood component detection.

[0114] Optional, see Figure 5 , Figure 5 FIG. 1 is a schematic diagram of the structure of a blood component detection device provided by an embodiment of the present invention. Figure 5 As shown, the device comprises:

[0115] An acquisition module 501 is used to acquire photoplethysmographic signals of a designated target collected at different wavelengths and different light intensities;

[0116] A processing module 502 is used to perform time domain and frequency domain analysis on the photoplethysmography signal to obtain characteristic parameters corresponding to the photoplethysmography signal;

[0117] A first calculation module 503 is used to calculate a characteristic proportional function corresponding to the photoplethysmography signal at different wavelengths according to the characteristic parameters corresponding to the photoplethysmography signal at different light intensities;

[0118] The second calculation module 504 is used to calculate the blood component result of the designated target by taking the characteristic proportional function corresponding to the photoplethysmography signal as the independent variable and the target blood component value as the dependent variable.

[0119] Optionally, the processing module 502 includes:

[0120] A segmentation submodule, used for segmenting the photoplethysmography signal according to the signal period to obtain a segmentation sequence of the photoplethysmography signal, each segmentation sequence including segmentation signals having the same number of periods as the photoplethysmography signal;

[0121] A first processing submodule is used to process each segmentation signal in the segmentation sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmography signal;

[0122] A second processing submodule is used to process each segmentation signal in the segmentation sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmography signal;

[0123] The first calculation submodule is used to perform joint calculation based on the frequency domain feature data and the time domain feature data to obtain the feature parameters corresponding to the photoplethysmography signal.

[0124] Optionally, the second processing submodule includes:

[0125] The first processing unit is used to perform compound series conversion processing on each segmentation signal in the segmentation sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal.

[0126] Optionally, the first processing submodule includes:

[0127] The first calculation unit is used to calculate the peak-to-peak value and the average value in the time domain of each segmentation signal in the segmentation sequence to obtain the time domain characteristic data corresponding to the photoplethysmography signal.

[0128] Optionally, the first calculation module 503 includes:

[0129] The second calculation submodule is used to calculate the characteristic function corresponding to the photoplethysmogram signal at different light intensities at the same wavelength according to the characteristic parameters corresponding to the photoplethysmogram signal, and obtain the characteristic proportional function corresponding to the photoplethysmogram signal at each wavelength.

[0130] Optionally, the second calculation module 504 includes:

[0131] Constructing a submodule for constructing a multi-parameter regression analysis model using the characteristic proportion function corresponding to the photoplethysmographic signal as an independent variable and the target blood component value as a dependent variable;

[0132] The third calculation submodule is used to calculate the blood component result of the designated target through the multi-parameter regression analysis model.

[0133] Optionally, the multi-parameter regression analysis model includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is:

[0134]

[0135] Wherein, Y is the dependent variable, Tn is the independent variable, βn is the regression coefficient of the independent variable, and N is the number of the independent variables.

[0136] It should be noted that the data center equipment provided in the embodiment of the present invention can be applied to smart phones, computers, servers and other devices that can perform blood component detection.

[0137] The data center equipment provided in the embodiment of the present invention can implement each process implemented by the blood component detection method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0138] See also Figure 6 , Figure 6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, it includes: a memory 602, a processor 601, and a computer program of a blood component detection method stored in the memory 602 and executable on the processor 601, wherein:

[0139] The electronic device is applied to a data center, and the processor 601 is used to call the computer program stored in the memory 602 to perform the following steps:

[0140] Acquire the photoplethysmographic signals of the designated target collected at different wavelengths and different light intensities;

[0141] Performing time domain and frequency domain analysis on the photoplethysmography signal to obtain characteristic parameters corresponding to the photoplethysmography signal;

[0142] Calculating characteristic proportional functions corresponding to the photoplethysmographic signals at different wavelengths according to characteristic parameters corresponding to the photoplethysmographic signals at different light intensities;

[0143] The characteristic proportional function corresponding to the photoplethysmographic signal is used as an independent variable, and the target blood component value is used as a dependent variable to calculate the blood component result of the designated target.

[0144] Optionally, the processor 601 performs time domain and frequency domain analysis and processing on the photoplethysmography signal to obtain characteristic parameters corresponding to the photoplethysmography signal, including:

[0145] Dividing the photoplethysmography signal according to the signal period to obtain a segmentation sequence of the photoplethysmography signal, each segmentation sequence including segmentation signals having the same number of periods as the photoplethysmography signal;

[0146] Processing each segmented signal in the segmented sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmography signal;

[0147] Processing each segmented signal in the segmented sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmographic signal;

[0148] A joint calculation is performed based on the frequency domain characteristic data and the time domain characteristic data to obtain characteristic parameters corresponding to the photoplethysmography signal.

[0149] Optionally, the processor 601 performs frequency domain processing on each segmented signal in the segmented sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal, including:

[0150] Compound series conversion is performed on each segmentation signal in the segmentation sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal.

[0151] Optionally, the processor 601 performs time domain processing on each segmented signal in the segmented sequence to obtain time domain feature data corresponding to the photoplethysmogram signal, including:

[0152] The peak-to-peak value and the average value in the time domain are calculated for each segmentation signal in the segmentation sequence to obtain the time domain characteristic data corresponding to the photoplethysmogram signal.

[0153] Optionally, the processor 601 calculates the characteristic proportional function corresponding to the photoplethysmography signal at different wavelengths according to the characteristic parameters corresponding to the photoplethysmography signal at different light intensities, including:

[0154] According to the characteristic parameters corresponding to the photoplethysmographic signal, the characteristic function corresponding to the photoplethysmographic signal at different light intensities at the same wavelength is calculated to obtain the characteristic proportional function corresponding to the photoplethysmographic signal at each wavelength.

[0155] Optionally, the processor 601 performs the step of taking the characteristic proportion function corresponding to the photoplethysmography signal as an independent variable and the target blood component value as a dependent variable to calculate the blood component result of the designated target, including:

[0156] A multi-parameter regression analysis model is constructed using the characteristic proportional function corresponding to the photoplethysmographic signal as an independent variable and the target blood component value as a dependent variable;

[0157] The blood component results of the designated target are calculated through the multi-parameter regression analysis model.

[0158] Optionally, the multi-parameter regression analysis model executed by the processor 601 includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is:

[0159]

[0160] Wherein, Y is the dependent variable, Tn is the independent variable, βn is the regression coefficient of the independent variable, and N is the number of the independent variables.

[0161] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to smart phones, computers, servers and other devices that can perform blood component detection.

[0162] The electronic device provided in the embodiment of the present invention can implement each process implemented by the blood component detection method in the above method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0163] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the blood component detection method or the application-end blood component detection method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0165] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for detecting blood components, characterized in that: The following steps are involved: Acquire the photoplethysmographic signals of the designated target collected at different wavelengths and different light intensities; Dividing the photoplethysmography signal according to the signal period to obtain a segmentation sequence of the photoplethysmography signal, each segmentation sequence including segmentation signals having the same number of periods as the photoplethysmography signal; Processing each segmented signal in the segmented sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmography signal; Processing each segmented signal in the segmented sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmographic signal; Performing joint calculation based on the frequency domain feature data and the time domain feature data to obtain feature parameters corresponding to the photoplethysmography signal; Calculating characteristic proportional functions corresponding to the photoplethysmographic signals at different wavelengths according to characteristic parameters corresponding to the photoplethysmographic signals at different light intensities; A multi-parameter regression analysis model is constructed using the characteristic proportional function corresponding to the photoplethysmographic signal as an independent variable and the target blood component value as a dependent variable; The blood component result of the designated target is calculated by the multi-parameter regression analysis model; the multi-parameter regression analysis model includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is: Where Y is the dependent variable, T n is the independent variable, β n is the regression coefficient of the independent variable, and N is the number of the independent variables.

2. The blood component detection method according to claim 1, characterized in that: The processing of each segmented signal in the segmented sequence in the frequency domain to obtain frequency domain feature data corresponding to the photoplethysmographic signal includes: Compound series conversion is performed on each segmentation signal in the segmentation sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal.

3. The blood component detection method according to claim 2, characterized in that: The processing of each segmented signal in the segmented sequence in the time domain to obtain time domain feature data corresponding to the photoplethysmographic signal includes: The peak-to-peak value and the average value in the time domain are calculated for each segmentation signal in the segmentation sequence to obtain the time domain characteristic data corresponding to the photoplethysmogram signal.

4. The blood component detection method according to claim 3, characterized in that: The step of calculating the characteristic proportional function corresponding to the photoplethysmogram signal at different wavelengths according to the characteristic parameters corresponding to the photoplethysmogram signal at different light intensities includes: According to the characteristic parameters corresponding to the photoplethysmographic signal, the characteristic function corresponding to the photoplethysmographic signal at different light intensities at the same wavelength is calculated to obtain the characteristic proportional function corresponding to the photoplethysmographic signal at each wavelength.

5. A blood component detection device, characterized in that: The blood component detection device comprises: An acquisition module is used to acquire photoplethysmographic signals collected from a designated target at different wavelengths and different light intensities; A processing module, used for segmenting the photoplethysmography signal according to the signal period to obtain a segmentation sequence of the photoplethysmography signal, each segmentation sequence including segmentation signals having the same number of periods as the photoplethysmography signal; performing frequency domain processing on each segmentation signal in the segmentation sequence to obtain frequency domain feature data corresponding to the photoplethysmography signal; performing time domain processing on each segmentation signal in the segmentation sequence to obtain time domain feature data corresponding to the photoplethysmography signal; and performing joint calculation based on the frequency domain feature data and the time domain feature data to obtain feature parameters corresponding to the photoplethysmography signal; A first calculation module, used to calculate a characteristic proportional function corresponding to the photoplethysmography signal at different wavelengths according to characteristic parameters corresponding to the photoplethysmography signal at different light intensities; The second calculation module is used to construct a multi-parameter regression analysis model with the characteristic proportional function corresponding to the photoplethysmography signal as an independent variable and the target blood component value as a dependent variable; the blood component result of the designated target is calculated by the multi-parameter regression analysis model; the multi-parameter regression analysis model includes the independent variable, the dependent variable and the regression coefficient of the independent variable, and the multi-parameter regression analysis model is: Where Y is the dependent variable, T n is the independent variable, β n is the regression coefficient of the independent variable, and N is the number of the independent variables.

6. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the blood component detection method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the blood component detection method according to any one of claims 1 to 4 are implemented.