Blood oxygen saturation detection method, device and equipment and readable storage medium

Abstract

The present disclosure relates to a blood oxygen saturation detection method, device, equipment and readable storage medium, through the use of the light source and light sensor of the electronic device itself, the spectral channel reading through the user pressing the light source, the PPG signal and the pressing degree of the user measured part are determined based on the spectral channel reading, and the blood oxygen saturation calculation model conforming to the user pressing degree is adopted to determine the blood oxygen saturation of the user, the configuration hardware and function of the electronic device itself are combined with the appropriate algorithm and model, and non-invasive blood oxygen saturation measurement is realized, which brings convenience to the health management of the user.

Description

Technical Field

[0001] This disclosure relates to the field of terminal equipment technology, and in particular to a method, apparatus, device and readable storage medium for blood oxygen saturation detection. Background Technology

[0002] Based on the different light absorption coefficients of oxyhemoglobin and deoxyhemoglobin in the red and infrared spectral regions of the human body, a sensor with dual light-emitting diodes is used to emit red and infrared light to illuminate specific detection sites of the tested user, respectively. The changes in absorbance of the two types of light are detected separately, and the blood oxygen saturation of the tested user can be predicted by the ratio of the changes in absorbance of the two types of light and a specific blood oxygen saturation calculation model.

[0003] Currently, blood oxygen saturation measurement usually requires the use of dedicated wearable devices, such as smart bracelets and smartwatches, which are costly for users and inconvenient for daily blood oxygen saturation monitoring. Summary of the Invention

[0004] In view of this, in order to solve the above-mentioned technical problems, this disclosure provides a method, apparatus, device and storage medium for detecting blood oxygen saturation.

[0005] According to a first aspect of the present disclosure, a method for detecting blood oxygen saturation is provided. This method is applied to an electronic device, which includes at least a light source and a light sensor; the light source supports providing infrared light; the light sensor includes at least a red light channel and an infrared light channel; the method includes:

[0006] In response to the light source emitting light, the spectral channel reading generated by the photosensitive sensor is acquired when the user's measured part presses the light source;

[0007] Based on the spectral channel readings, the light intensity readings are determined, and the photoelectric pulse map (PPG) signals corresponding to red and infrared light are obtained.

[0008] Based on the pre-established mapping relationship between light intensity readings and pressure, the first pressure generated when the user's tested part presses the light source, corresponding to the light intensity reading;

[0009] Based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model, the target calculation model corresponding to the first pressure level is determined.

[0010] Using the target calculation model, the user's blood oxygen saturation measurement results are obtained based on the PPG signals corresponding to the red and infrared light.

[0011] According to a second aspect of the present disclosure, a blood oxygen saturation detection device is provided, the device being applied to an electronic device, the electronic device including at least a light source and a light sensor; the light source supports providing infrared light; the light sensor includes at least a red light channel and an infrared light channel; the device includes:

[0012] The spectral channel reading acquisition module is used to acquire the spectral channel reading generated by the photosensitive sensor when the user presses the light source in response to the light source emission;

[0013] The light intensity reading and signal component acquisition module is used to determine the light intensity reading based on the spectral channel reading, and to acquire the photoelectric pulse map (PPG) signals corresponding to red light and infrared light.

[0014] The pressure intensity determination module is used to obtain the first pressure intensity generated when the user's tested part presses the light source, corresponding to the light intensity reading, based on a pre-established mapping relationship between light intensity readings and pressure intensity.

[0015] The target calculation model determination module is used to determine the target calculation model corresponding to the first pressure level based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model.

[0016] The blood oxygen measurement result acquisition module is used to acquire the user's blood oxygen saturation measurement result based on the PPG signals corresponding to the red and infrared light using the target calculation model.

[0017] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor and a memory; the memory being used to store a computer program; and the processor being used to invoke the computer program to implement the above-described blood oxygen saturation detection method.

[0018] According to a fourth aspect of the present disclosure, a readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described blood oxygen saturation detection method.

[0019] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0020] The blood oxygen saturation detection method provided in this embodiment utilizes the light source and photosensor of the electronic device itself. The spectral channel is read by the user pressing the light source. Based on the spectral channel reading, the PPG signal and pressure applied to the user's measurement site are determined. A blood oxygen saturation calculation model conforming to the user's pressure is then used to determine the user's blood oxygen saturation. This reduces the influence of ambient light on blood oxygen saturation measurement, eliminates the need for dedicated blood oxygen saturation measurement equipment, and achieves non-invasive blood oxygen saturation measurement by utilizing the electronic device's hardware and functions combined with appropriate algorithms and models. It provides real-time blood oxygen saturation monitoring results, saves users the cost of health management, and brings convenience to users' health management.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Furthermore, no embodiment in this disclosure is required to achieve all the effects described above. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0023] Figure 1 This is a flowchart illustrating a blood oxygen saturation detection method according to an exemplary embodiment;

[0024] Figure 2 This is a flowchart illustrating an exemplary embodiment of acquiring PPG signals corresponding to red and infrared light;

[0025] Figure 3 This is a flowchart illustrating a mapping relationship between light intensity readings and pressure intensity according to an exemplary embodiment;

[0026] Figure 4 This is a flowchart illustrating another method for determining the mapping relationship between light intensity readings and pressure intensity, according to an exemplary embodiment.

[0027] Figure 5 This is a flowchart illustrating a correspondence between pressure level and blood oxygen saturation calculation model according to an exemplary embodiment;

[0028] Figure 6 This is a flowchart illustrating a method for determining a user's blood oxygen saturation based on a blood oxygen calculation model, according to an exemplary embodiment.

[0029] Figure 7 This is a flowchart illustrating a blood oxygen saturation detection method using a mobile phone as an example of an electronic device.

[0030] Figure 8 This is a schematic diagram illustrating a measurement posture where a user presses a light source on the part of the body being measured, using a mobile phone as an example of an electronic device.

[0031] Figure 9 This is a schematic diagram of the structure of a blood oxygen saturation detection device according to an exemplary embodiment;

[0032] Figure 10 This is a block diagram illustrating a terminal device according to an exemplary embodiment. Detailed Implementation

[0033] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0034] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0035] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, a first classification threshold may also be referred to as a second classification threshold, and similarly, a second classification threshold may also be referred to as a first classification threshold. Depending on the context, the word "if" as used herein may be interpreted as "when," "in response to a determination," or "when," or "in the event of a determination."

[0036] This disclosure provides a method for detecting blood oxygen saturation, which can be applied to electronic devices such as mobile phones and tablets. The electronic device includes at least a light source and a light sensor. The light source is used to illuminate the user's test area and supports providing red light and infrared light. The light sensor can contain multiple different color channels, each color channel corresponding to a certain wavelength range or a specific color, used to record the channel readings corresponding to different wavelengths of light intensity or energy in the reflected light from the user's test area when the test area is placed on the light source, such as red light channel, infrared light channel, green light channel, etc.

[0037] Figure 1This is a flowchart illustrating a blood oxygen saturation detection method according to an exemplary embodiment, such as... Figure 1 As shown, the blood oxygen saturation detection method may include the following steps:

[0038] S101, in response to the electronic device being in a vital sign monitoring state, when the light source is emitting light, the spectral channel reading generated by the photosensitive sensor when the user's measured part presses the light source is acquired;

[0039] Spectral channel readings represent the intensity of light signals within different wavelength ranges, including different frequency bands such as visible light and infrared light. Each spectral channel corresponds to a certain wavelength range, such as red, green, and blue. By simultaneously recording the readings of multiple channels, information about light within different wavelength ranges can be obtained.

[0040] The light source is used to illuminate the user's test area. When the light source is turned on and the user's test area is covered by the light source, the user's test area will reflect and absorb the light emitted by the light source. At this time, different channels in the photosensitive sensor can capture the channel reading sequence of light intensity corresponding to different wavelengths of light in the reflected light from the test area as a function of time. The photosensitive sensor can be a spectral sensor.

[0041] The user's test area can include, but is not limited to, fingers, wrists, arms, forehead, cheeks, and other areas that can be placed on a light source.

[0042] For example, electronic devices are equipped with health monitoring programs or software. When a user activates the health monitoring program to measure blood oxygen saturation, they can cover the light source with their finger when the light source is emitting light. At this time, the light sensor can collect the light intensity of different wavelengths reflected by the user's finger from the light source and convert it into corresponding spectral channel readings.

[0043] S102, Based on the spectral channel readings, determine the light intensity readings and acquire the PPG signals corresponding to red light and infrared light;

[0044] Illuminance reading refers to the energy or power density of light, specifically the light energy transmitted per second over a given area. Different wavelengths of light contribute differently to illuminance. Based on pre-set weight values ​​for different channel readings, the readings from each channel are weighted and combined to obtain a comprehensive overall illuminance reading. This illuminance reading can be converted to the appropriate unit, lux or candela per square meter, depending on the specific application requirements. The weight values ​​for different channel readings are determined based on the wavelength range represented by that channel and the light intensity response characteristics; different channels typically have different weight values.

[0045] PPG (Positive Pressure Gauge) signal is a non-invasive technique for monitoring blood flow and pulse waveforms. Based on the principle of light transmission and reflection through the skin when illuminated, it uses a photosensitive sensor to detect changes in the intensity of light absorbed and reflected by the skin, converting this into an electrical signal. This allows for the processing and analysis of PPG signals to predict physiological indicators such as blood oxygen saturation and heart rate. In calculating blood oxygen saturation, both red and infrared light wavelengths are typically used for measurement.

[0046] Hemoglobin exhibits different absorption characteristics at red and infrared light wavelengths. Red light is absorbed more by oxyhemoglobin (oxygenated hemoglobin), while infrared light is absorbed more by deoxyhemoglobin (deoxygenated hemoglobin). When blood oxygen saturation is high, more red light is absorbed by oxyhemoglobin and less infrared light by deoxyhemoglobin, resulting in a relatively strong red light signal and a relatively weak infrared signal. Conversely, when blood oxygen saturation is low, the red light signal is relatively weak and the infrared signal is relatively strong. Therefore, based on red and infrared PPG signals, the absorption characteristics of hemoglobin at different wavelengths can be used to infer the ratio of oxygenated to deoxyhemoglobin in the blood, thereby predicting blood oxygen saturation.

[0047] Based on the above principle, since the spectral channel readings characterize the intensity changes of light after reflection and absorption by the user's measured part in different wavelength ranges, the first PPG signal corresponding to red light and the second PPG signal corresponding to infrared light can be obtained based on the red light channel readings and infrared light channel readings in the spectral channel readings.

[0048] S103, based on the pre-established mapping relationship between light intensity reading and pressure intensity, obtain the first pressure intensity generated when the user's tested part presses the light source corresponding to the light intensity reading;

[0049] When a user presses the light source with varying pressure on the tested area, the contact area between the tested area and the light source differs. This affects the absorption and reflection of light by the tissue in the tested area, resulting in varying light intensities entering the photosensor and consequently changing the spectral channel readings. Based on the correlation between these spectral channel readings and light intensity, sample data can be collected by collecting the pressure level and the corresponding spectral channel readings. Statistical analysis of this sample data can then be performed to determine the relationship between light intensity readings and pressure level.

[0050] The mapping relationship between light intensity readings and pressure pressure is used to determine the initial pressure pressure applied by the user's body part to the light source, based on the light intensity reading obtained from the currently acquired spectral channel readings. This mapping relationship can be determined through data fitting or machine learning based on pre-acquired first sample data. The first sample data includes different pressure pressures applied by the sample population to the light source, and the light intensity reading determined based on the spectral channel readings at that pressure pressure. The electronic device that acquires the first sample data is the same device configured as the current electronic device for detecting blood oxygen saturation.

[0051] S104, Based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model, determine the target calculation model corresponding to the first pressure level;

[0052] When a user presses the light source with varying degrees of pressure on the test site, the resulting tissue compression affects the light's ability to pass through and its absorption, thus influencing the acquired spectral channel readings and consequently impacting blood oxygen saturation measurement. To more accurately predict blood oxygen saturation, a calculation model for blood oxygen saturation under different pressure levels was established to improve the accuracy of the calculation results.

[0053] The blood oxygen saturation calculation model is used to determine the user's blood oxygen saturation based on the PPG signal of the set wavelength determined in the aforementioned step S102. This calculation model can be established by performing data analysis on a large amount of pre-collected sample data and using methods such as machine learning and data fitting. The sample data includes relevant sample data collected from sample groups with different blood oxygen saturations when pressing the light source with different pressure.

[0054] After determining the first pressure level of the current user's measured part according to step S103, the first pressure level can be matched with the correspondence between the pressure level and the blood oxygen saturation calculation model, and the blood oxygen saturation calculation model that matches the first pressure level can be used as the target calculation model.

[0055] S105, using the target calculation model, obtain the user's blood oxygen saturation measurement results based on the PPG signals corresponding to the red and infrared light.

[0056] The target calculation model determines blood oxygen saturation by relying on light absorption characteristics and signal analysis techniques. It can be a pre-established model relating blood oxygen saturation to the R-value, used to predict blood oxygen saturation based on the ratio (R-value) of red PPG signals to infrared PPG signals. The R-value is calculated from the red and infrared PPG signals. During the R-value calculation, the influence of environmental noise and light intensity can be reduced by dividing by the DC component of the PPC signal.

[0057] When the target calculation model is a model relating blood oxygen saturation to the R value, the R value can be calculated first based on the AC and DC components of the red and infrared PPG signals. Then, the R value is input into the target calculation model to convert it into the corresponding blood oxygen saturation value. Alternatively, when the target calculation model is a model relating blood oxygen saturation to the AC and DC components of the red and infrared PPG signals, the AC and DC components of the acquired red and infrared PPG signals can be directly used as the input to the target model, and the predicted blood oxygen saturation output can be obtained.

[0058] In this embodiment, the electronic device utilizes its own light source and photosensor to read the spectral channel by pressing the light source. Based on the spectral channel reading, the PPG signal and pressure applied to the user's measurement site are determined. Then, a blood oxygen saturation calculation model that matches the user's pressure is used to determine the user's blood oxygen saturation. This reduces the influence of ambient light on blood oxygen saturation measurement. Without requiring additional hardware, the electronic device's own hardware configuration and functions, combined with appropriate algorithms and models, achieve non-invasive blood oxygen saturation measurement, providing real-time blood oxygen saturation monitoring results. This saves users the cost of health management and brings convenience to their health management.

[0059] In some embodiments, the aforementioned electronic device may further include a light intensity sensor, which acquires the light intensity reading generated by the light intensity sensor when the light source of the electronic device emits light, and performs the above-described blood oxygen saturation detection method based on the light intensity reading.

[0060] In some embodiments, such as Figure 2 As shown, the acquisition of photoelectric pulse map (PPG) signals corresponding to red and infrared light in step S102 can include the following implementation steps:

[0061] S201, Based on the spectral channel readings, obtain the curves of the red light channel readings and infrared light channel readings changing with time;

[0062] The spectral channel readings obtained from the photosensor are a sequence of readings for each channel over a period of time when the user's test area is pressed against the light source. Therefore, based on the reading sequence corresponding to the set wavelength of light, a curve showing the channel readings changing over time can be obtained. For blood oxygen saturation measurement, the set wavelength of light includes red light and infrared light, so curve 1 showing the red light channel reading changing over time and curve 2 showing the infrared light channel reading changing over time can be obtained.

[0063] S202, based on the curve of the channel reading changing over time, determine the first PPG signal corresponding to red light and the second PPG signal corresponding to infrared light;

[0064] The AC component of the PPG signal corresponds to changes in blood flow caused by arterial pulsation, typically corresponding to the systolic and diastolic cycles of the heart. The DC component reflects changes in venous blood volume and other non-pulsating blood flow components, with a lower frequency range, usually less than 0.5 Hz. Spectral channel readings represent the absorption and reflection of light at different wavelengths at the user's measured site. The time-varying curves provide information related to blood absorption and scattering, reflecting the AC and DC components of the PPG signal.

[0065] Based on this, the curve showing the change of the spectral channel reading at the set wavelength over time can be directly determined as the PPG signal for that set wavelength; alternatively, further signal processing can be performed on the curve to improve signal quality, such as filtering and baseline drift correction, and the processed curve can be used as the PPG signal for the set wavelength. In blood oxygen saturation measurement, the set wavelength can typically be a combination of 660 nm and 940 nm wavelengths, that is, the first PPG signal and the second PPG signal are determined based on the red light channel reading and the infrared light channel reading of the photosensitive sensor.

[0066] See Figure 3 As shown, in some embodiments, the method may further include a step of pre-obtaining the mapping relationship between light intensity readings and pressure intensity. The mapping relationship between light intensity readings and pressure intensity described in step S103 can be obtained in the following manner:

[0067] S301, Collect spectral channel readings generated by the light sensor when the sample group presses the light source with different pressure levels, count the pressure level samples of the sample group, and determine the light intensity reading samples under different pressure levels based on the spectral channel readings;

[0068] The sample population can include multiple groups of people of different ages and genders. The spectral channel readings generated by the light sensor of the electronic device are counted when each sample group presses the light source of the electronic device with different pressure levels. Alternatively, a pressure sensor can be used to collect the user's pressing pressure, and the pressing pressure and the corresponding light intensity readings can be counted to obtain a sample dataset.

[0069] S302, perform data fitting based on the light intensity reading samples and the corresponding pressing pressure to obtain the mapping relationship between the light intensity readings and the pressing pressure.

[0070] Data fitting refers to selecting an appropriate mathematical or statistical model, such as a defined function or curve, so that the model can describe the correspondence between a set of data. Common data fitting methods include linear regression, multinomial fitting, and nonlinear fitting, which involve adjusting model parameters to minimize the difference between the model's predicted values ​​and the actual observed values.

[0071] For example, polynomial fitting can be used to establish a polynomial function model based on the selected polynomial order, i.e., f(x) = a0 + a1x + a2x 2 +…+a n xn, where a0, a1, a2…a n Here are the polynomial coefficients to be estimated, where x represents the light intensity reading and f(x) represents the corresponding pressure degree. The polynomial order can be determined using methods such as cross-validation. An error function, such as the residual sum of squares function, is defined to measure the goodness of fit of the model. Based on the light intensity reading samples and the corresponding pressure degree sample datasets, the model can be fitted using methods such as least squares, gradient descent, and Newton's method. The estimated polynomial coefficients are determined by minimizing the error function.

[0072] In this embodiment of the disclosure, based on a large number of sample datasets collected, a data fitting method is used to determine the mapping relationship between light intensity readings and the actual pressure applied by the user to the tested area. This allows the model to adapt to new, unseen data and has strong predictive ability. When actually determining light intensity readings, the pressure applied by the user to the tested area can be accurately obtained based on this mapping relationship, providing a data basis for subsequent blood oxygen saturation calculations.

[0073] In some embodiments, such as Figure 4 As shown, the mapping relationship between the light intensity reading and the pressure intensity described in step S103 above can also be obtained in the following way:

[0074] S401, Collect the spectral channel readings generated by the light sensor when the sample group presses the light source with different pressure levels, count the pressure level samples of the sample group, and determine the light intensity reading samples under different pressure levels based on the spectral channel readings;

[0075] S402, the pressure value is divided into M discrete value intervals, and a mapping relationship between the light intensity reading and the discrete value intervals is established based on the light intensity reading samples. This mapping relationship is determined as the mapping relationship between the light intensity reading and the pressure value; M is greater than or equal to 2.

[0076] In other words, the pressure intensity samples of the sample population pressing the light source are divided into at least two value intervals. Based on the light intensity readings and the corresponding pressure intensity samples, a mapping relationship between the light intensity readings and the pressure intensity value intervals is established. Furthermore, these pressure intensity value intervals can serve as the division intervals for different pressure intensity values ​​corresponding to the blood oxygen saturation calculation model, and the number of pressure intensity value intervals is the same as the number of blood oxygen saturation calculation models.

[0077] For example, the pressure P is divided into three value ranges: (0, N1], (N1, N2], and (N2, N3]. Based on the light intensity reading and the corresponding pressure sample, the mapping relationship between the light sensor reading and these three value ranges is determined, so that the pressure value range can be determined based on this mapping relationship when determining the light sensor reading.

[0078] In this embodiment of the disclosure, the pressure data is divided into discrete value ranges, which reduces the complexity of the problem. The changes in the light sensor reading caused by the change in pressure are limited to the range, which reduces the propagation of errors and makes it easier to process and implement the determination of the pressure value based on the light sensor reading.

[0079] In some embodiments, see Figure 5 As shown, the method may further include a step of pre-obtaining the correspondence between the pressure applied and the blood oxygen saturation calculation model. The correspondence between the pressure applied and the blood oxygen saturation calculation model mentioned in step S103 can be obtained in the following way:

[0080] S501, when the sample group presses the light source with different pressure levels, collect the spectral channel reading samples generated by the light sensor under the pressure level, and record the blood oxygen saturation of the sample group to obtain the sample dataset;

[0081] The sample dataset collected in this embodiment can be the same batch of data collected using the same device as the sample data required to determine the mapping relationship between light intensity readings and pressure intensity. When the sample group presses the light source with different pressure intensities, the pressure intensity, the corresponding spectral channel reading, and the blood oxygen saturation of the sample group are recorded. This recorded data is used as the sample dataset for determining the blood oxygen saturation calculation model. Furthermore, this sample dataset can be preprocessed, including data cleaning and outlier removal, to improve the quality of the sample data.

[0082] S502, perform data fitting based on the sample dataset to obtain a blood oxygen saturation calculation model with respect to parameter R value under different pressure levels; the R value is determined based on spectral channel reading samples; the R value is used to represent the absorption ratio of red light and infrared light.

[0083] The compression pressure is categorized into different ranges. Based on the spectral channel readings and corresponding blood oxygen saturation within each range, a calculation model is established for the blood oxygen saturation and the R-value determined from the spectral channel readings within that range. This calculation model can be determined through data fitting methods such as linear regression, support vector regression, multinomial fitting, or machine learning and neural networks. In this embodiment, the least squares method can be used for linear regression data fitting to determine the calculation model. Specific implementation can employ techniques from related technologies, which will not be elaborated upon here.

[0084] In this embodiment of the disclosure, a blood oxygen saturation calculation model under different pressure levels is determined based on a large number of sample datasets collected. Blood oxygen saturation is predicted by spectral channel readings, achieving non-invasive and non-surgical measurement. This reduces the influence of pressure level on blood oxygen saturation measurement, reduces interference from ambient light, and improves measurement accuracy.

[0085] like Figure 6 As shown, in some embodiments, the step S105 described above, which utilizes the target calculation model to obtain the user's blood oxygen saturation measurement result based on the PPG signals corresponding to the red and infrared light, can be achieved in the following way:

[0086] S601, acquire the AC and DC components of the PPG signals corresponding to the red light and infrared light;

[0087] Since the PPG signal is a composite signal of DC and AC components, these two components can be separated from the PPG signal by utilizing the spectral characteristics or the overall waveform characteristics of the signal, such as time-domain waveform method, frequency-domain waveform method, machine learning method, wavelet transform method, etc. The specific component extraction method can be determined according to the signal characteristics of the PPG signal, such as the signal-to-noise ratio, signal characteristics, real-time requirements, etc.

[0088] S602, determine the parameter R value based on the AC component and the DC component; the R value is used to represent the absorption ratio of red light and infrared light;

[0089] The R value, as an indicator of blood oxygen saturation, reflects the difference between red and infrared light channel readings, and is thus used to estimate the level of blood oxygen saturation. The R value can be calculated as follows: the ratio of the AC component to the DC component of the red light is determined as the first component ratio; the ratio of the AC component to the DC component of the infrared light is determined as the second component ratio; and the ratio R is determined based on the first component ratio and the second component ratio.

[0090] S603, based on the R value and the target calculation model about the R value, determine the user's blood oxygen saturation measurement result.

[0091] In this embodiment, the target calculation model is a model relating blood oxygen saturation and R value. By inputting the R value, the corresponding blood oxygen saturation can be obtained.

[0092] In this embodiment of the disclosure, the blood oxygen saturation assessment index R value is determined by acquiring the AC and DC components of red and infrared light, which reduces the influence of environmental noise and light intensity. Based on the established relationship model between blood oxygen saturation and R value, the user's blood oxygen saturation measurement is determined, meeting the real-time requirements of blood oxygen saturation monitoring and providing convenience for the user's health monitoring.

[0093] In some embodiments, the acquisition of the AC and DC components of the PPG signals corresponding to the red and infrared light in step S601 above can be achieved in the following way:

[0094] Each of the PPG signals is resampled; wherein the same sampling frequency is used for each signal resampling.

[0095] Based on the component extraction method of the resampled PPG signal, the AC component and DC component of the resampled PPG signal are obtained.

[0096] Resampling, in digital signal processing, refers to the process of converting a signal from one sampling rate to another. The sampling rate represents the number of times the signal is sampled per second, also known as the sampling frequency. The basic principle of resampling is to change the sampling rate of the signal through methods such as interpolation or downsampling. Interpolation is a method of estimating new sampling points by using linear or nonlinear interpolation between known sampling points, while downsampling is a method of deleting some sampling points according to certain rules.

[0097] In this embodiment, the first and second PPG signals of red light are resampled at the same sampling rate to obtain signals with uniform time intervals. The PPG signals can be resampled using an interpolation method based on their timestamp information. This results in resampled first and second PPG signals with the same sampling frequency and consistent time intervals between sampling points. For example, with a sampling rate of 150Hz, the first and second PPG signals are resampled using linear interpolation based on the timestamp information of existing sampling points.

[0098] Signal component extraction refers to the methods used to extract the DC and AC components of a PPG signal. These methods may include, but are not limited to, time-domain waveform extraction, frequency-domain waveform extraction, and wavelet transform extraction. For example, using the signal-to-noise ratio (SNR) of the resampled PPG signal as a determining factor, time-domain waveform extraction can be used to extract signal components for PPG signals with an SNR higher than a set threshold, while frequency-domain waveform extraction can be used for PPG signals with an SNR lower than the set threshold.

[0099] The first PPG signal and the second PPG signal can be extracted using appropriate methods based on their characteristics, and these extraction methods can be different. For example, if the signal-to-noise ratio (SNR) of the first PPG signal is higher than a set threshold, and the SNR of the second PPG signal is lower than the set threshold, then the first PPG signal is extracted using the time-domain waveform method, and the second PPG signal is extracted using the frequency-domain waveform method.

[0100] In this embodiment of the disclosure, the red PPG signal and the infrared PPG signal are determined by the reading sequence of the red light channel and the infrared light channel of the photosensitive sensor, and the two sets of signals are resampled using the same sampling rate, which improves the signal quality and data processing efficiency. Furthermore, the signal component extraction method is determined based on the signal characteristics of the resampled PPG signal, which improves the noise resistance of the signal and makes the extracted signal components more accurate.

[0101] In some embodiments, since the component extraction method of the resampled PPG signal is time-domain waveform extraction, the acquisition of the AC and DC components of the resampled PPG signal according to the component extraction method of the resampled PPG signal described in the above embodiments can be achieved in the following way:

[0102] Detect the peak value and peak value of the PPG signal to obtain the peak value set and peak-valley set;

[0103] The DC component and AC component are determined by using the mean value calculation based on the set of peaks and valleys and the set of peak values.

[0104] The peak value refers to the maximum value of the PPG signal. Within a complete heartbeat cycle, the peak value generally corresponds to the systolic phase of the heart. By detecting and extracting the peak values ​​in the PPG signal, these peak values ​​are grouped into a set, which can contain peak values ​​from multiple complete heartbeat cycles. The trough value represents the minimum value of the PPG signal, which usually corresponds to the diastolic phase of the heart. By detecting and extracting the trough values ​​in the PPG signal, these trough values ​​are grouped into a set, which can contain trough values ​​from multiple complete heartbeat cycles.

[0105] Taking the first PPG signal of the resampled red light as an example, after obtaining the peak set and peak-valley set of the PPG signal, the first average value of each peak and valley value in the peak-valley set can be determined as the DC component of the first PPG signal, and the difference between the second average value of each peak value in the peak set and the first average value can be determined as the AC component.

[0106] Alternatively, the average value of corresponding points in the peak set and the valley set can be calculated as the estimate of the DC component. That is, each peak and the nearest valley are taken as corresponding points, the values ​​of the paired points are added together and divided by the number of paired points to obtain the third average value as the DC component of the PPG signal, and the difference between the peak and valley of the paired points is added together and divided by the number of paired points to obtain the fourth average value as the AC component of the PPG signal.

[0107] The AC and DC components of the PPG signal are determined based on the peak-valley set and peak-peak set. A detrending method can also be used to eliminate baseline drift, and then the average value of the remaining signal is extracted as an estimate of the DC component. The average value of the signal after removing the DC component can be used as the AC component. It is understood that this disclosure does not limit the method for extracting PPG signal components based on the peak-valley set and peak-peak set; a calculation method that better suits the signal characteristics can be selected according to the actual situation.

[0108] In this embodiment of the disclosure, the AC and DC components of the PPG signal are determined using the mean calculation method, which meets the real-time requirements of data processing. The mean calculation removes noise and interference, improving the accuracy and stability of the extracted signal components.

[0109] In some embodiments, in response to the component extraction method of the resampled PPG signal being time-domain waveform extraction, the acquisition of the AC and DC components of the resampled PPG signal according to the component extraction method of the resampled PPG signal described in the above embodiments may include the following steps:

[0110] The resampled PPG signal is processed by Fast Fourier Transform (FFT) to obtain the spectral information of the resampled PPG signal.

[0111] Based on the spectrum information, the energy value corresponding to the DC frequency is determined as the DC component, and the energy value corresponding to the set AC frequency range is determined as the AC component.

[0112] Fourier transform is an analysis tool that decomposes a time-domain signal into a frequency-domain signal. It is often used to perform operations such as spectrum analysis, filtering, and noise reduction on signals. After converting the resampled PPG signal into a frequency-domain signal, a spectrum of the PPG signal can be obtained. The horizontal axis represents frequency, and the vertical axis represents the amplitude or power spectral density of the signal. Based on this spectrum, the intensity and relative proportion of different frequency components in the signal can be determined.

[0113] The DC component refers to the constant offset of the signal, usually located at the far left of the frequency axis, corresponding to a frequency of 0Hz. Therefore, the DC frequency can be set to 0Hz, and the energy value corresponding to 0Hz in the frequency spectrum is determined as the DC component. The AC component refers to the changing part of the signal after removing the DC component, representing the alternating changes of the signal in the frequency domain, usually caused by periodic fluctuations. In blood oxygen saturation measurement, the AC frequency range is typically set to 0.5Hz-10Hz. For example, 0.5Hz-3Hz can be used as the set AC frequency range. The AC component within this range can be extracted using methods such as filtering and averaging energy values.

[0114] In this embodiment of the disclosure, the spectrum information of the PPG signal is obtained by performing FFT processing on the signal, and the AC component and DC component of the signal are extracted according to different frequencies based on the spectrum information. Energy in the noise frequency range is filtered out, and efficient calculation is achieved by using a fast algorithm, which saves computing resources, meets the real-time requirements of signal processing, and suppresses noise interference.

[0115] To enable those skilled in the art to better understand the blood oxygen saturation measurement method provided in this disclosure, a mobile phone will be used as an example to describe the technical solution of this disclosure. The mobile phone has a light source and a built-in light sensor, supporting the provision of red and infrared light sources. The channels of the light sensor may include channels within the visible light wavelength range, such as red, green, and blue light, as well as an infrared light channel.

[0116] When using this blood oxygen saturation measurement method to predict a user's blood oxygen saturation, sample data can first be collected using the mobile phone or an electronic device with the same configuration. Based on this sample data, the required force model and blood oxygen saturation calculation model for this measurement method can be established. See [link to relevant documentation]. Figure 7 As shown, the steps may include:

[0117] S701 collects the pressure, blood oxygen saturation, spectral channel reading sequence generated by the photosensitive sensor, and light intensity determined based on the spectral channel reading sequence when different groups of people press the light source on the test site with different pressure levels, as sample data;

[0118] The pressure applied can be collected using a pressure sensor. For example, a pressure sensor can be installed on the electronic device that collects sample data, allowing the pressure applied by the user's finger when pressing the light source to be measured. Alternatively, a suitable force sensor can be selected and fixed to the user's body part, such as their finger, and the pressure value applied by the user's finger to the light source of the electronic device can be obtained based on the sensor and the accompanying data acquisition device. Based on the preset weight values ​​of different channel readings, the corresponding light intensity reading is determined according to the collected spectral channel readings.

[0119] like Figure 8 As shown, users can place the part to be measured, such as a finger, on the rear light source of the phone to cover the light source. When different forces are applied to the light source, the spectral channel readings and the user's blood oxygen saturation are recorded at that force.

[0120] S702, Based on the sample data of the light intensity reading and the corresponding pressing pressure, establish the correspondence between the light intensity reading and the pressing pressure.

[0121] S703, based on the pressure applied, blood oxygen saturation, and spectral channel readings at that pressure level, a blood oxygen saturation calculation model is established for different pressure levels. The blood oxygen saturation calculation model is a relationship model between blood oxygen saturation and R value, and the R value is determined based on the spectral channel readings.

[0122] The AC component of the red PPG signal was determined based on the spectral channel reading sequence. red With DC component red And the AC component of the infrared PPG signal. Ir With DC component Ir The value of R can be determined in the following way:

[0123]

[0124] Based on the blood oxygen saturation under different pressure levels and the R value determined based on spectral channel readings, a model for the relationship between blood oxygen saturation and R value under different pressure levels was determined by data fitting.

[0125] For example, the pressure level P is divided into three discrete intervals: (0, n1], (n1, n2], and (n2, n3). Different pressure level intervals correspond to different relational model parameters. An exemplary model for calculating blood oxygen saturation under different pressure levels is as follows:

[0126]

[0127] After establishing the correspondence between light intensity readings and pressure levels, and a calculation model for blood oxygen saturation under different pressure levels, the blood oxygen saturation of the user under test can be predicted using the aforementioned blood oxygen saturation detection method based on this correspondence and the blood oxygen saturation calculation model under different pressure levels. Figure 7 The aforementioned process may include the following detection steps:

[0128] S704, in response to the mobile phone being in blood oxygen saturation monitoring state, when the light source is turned on, acquires the spectral channel reading sequence generated when the user's finger presses on the light source, and the light intensity reading determined based on the spectral channel reading sequence;

[0129] S705, based on the correspondence between the light intensity reading and the pressure intensity determined in step S702, determine the second pressure intensity of the user's finger pressing on the light source;

[0130] S706, Determine the red PPG signal and the infrared PPG signal 2 based on the red and infrared light channel reading sequences in the spectral channel readings;

[0131] For example, the curve of the red light channel reading changing with time is the PPG signal 1 at a wavelength of 660 nm: PPG1={R1,R2,R3….Rn}, and the curve of the infrared light channel reading changing with time is the PPG signal 2 at a wavelength of 9400 nm: PPG2={IR1,IR2,IR3….IRn}.

[0132] S707: Resample PPG signal 1 and PPG signal 2 by interpolation based on the timestamp information of the channel readings, and determine the signal component extraction method based on the signal-to-noise ratio of the two resampled PPG signals.

[0133] In this embodiment, the two PPG signals can be resampled using interpolation based on the timestamp to obtain signals with uniform time intervals, such as a sampling rate of 150Hz. Based on the signal characteristics of the resampled PPG signals, a method for extracting the AC and DC components of the PPG signals at different wavelengths is selected.

[0134] For PPG signals with high signal-to-noise ratios, time-domain waveform methods can be used. For example, peak detection and peak-valley detection can be performed on the PPG signal to obtain peak sets and peak-valley sets, and the AC and DC components can be calculated respectively according to the following methods:

[0135] DC=mean{foot1,foot2,foot3,…,footn};

[0136] AC=mean{peak1,peak2,peak3,…,peakn}-mean{foot1,foot2,foot3,…,footn};

[0137] Where DC represents the direct current component, AC represents the alternating current component, {foot1,foot2,foot3,…,footn} represents the peak-valley set, {peak1,peak2,peak3,…,peakn} represents the peak value set, and mean{} represents the average value.

[0138] For PPG signals with low signal-to-noise ratio, the frequency domain waveform method can be used. By performing FFT on the PPG signal, the energy value corresponding to the frequency of 0Hz can be determined as the DC component, and the maximum value of the energy value corresponding to the frequency range of 0.5-3Hz can be determined as the AC component.

[0139] S708 extracts the AC and DC components of the resampled PPG signals 1 and 2 respectively, and calculates the R value corresponding to the user under test.

[0140] S709, based on the second pressing force determined in step S705, determine the blood oxygen saturation calculation model that satisfies the second pressing force, and determine the blood oxygen saturation of the user under test based on the R value corresponding to the user under test and the blood oxygen saturation calculation model.

[0141] In this embodiment, the light source and light sensor of the mobile phone are used as the detection light source, and the user presses their finger on the light source, reducing the influence of ambient light on the measurement results. The light intensity reading is determined based on the acquired spectral channel reading to obtain the user's pressing pressure. A blood oxygen saturation calculation model that conforms to the user's pressing pressure is adopted. The user's blood oxygen saturation is measured based on the measured PPG signal of the measured area. Without the need for additional hardware, the mobile phone's own hardware configuration and functions, combined with a suitable blood oxygen saturation calculation model, realize non-invasive blood oxygen saturation measurement, provide real-time blood oxygen saturation monitoring results, reduce interference factors on the measurement results, improve the accuracy of blood oxygen saturation measurement, and bring convenience to the user's health management.

[0142] Corresponding to the embodiments of the aforementioned blood oxygen saturation detection method, Figure 9 This is a schematic diagram of the structure of a blood oxygen saturation detection device according to an exemplary embodiment, such as... Figure 9 As shown, the device is applied to an electronic device, which includes at least a light source and a light sensor; the light source supports providing infrared light; the light sensor includes at least a red light channel and an infrared light channel; the device includes: a spectral channel reading acquisition module 901, a light intensity reading and signal component acquisition module 902, a pressure degree determination module 903, a target calculation model determination module 904, and a blood oxygen measurement result acquisition module 905;

[0143] The spectral channel reading acquisition module 901 is used to acquire the spectral channel reading generated by the photosensitive sensor when the user presses the light source in response to the light source emission.

[0144] The light intensity reading and signal component acquisition module 902 is used to determine the light intensity reading based on the spectral channel reading, and to acquire the photoelectric pulse map (PPG) signals corresponding to red light and infrared light.

[0145] The pressure intensity determination module 903 is used to obtain the first pressure intensity generated when the user's tested part presses the light source according to the pre-established mapping relationship between the light intensity reading and the pressure intensity.

[0146] The target calculation model determination module 904 is used to determine the target calculation model corresponding to the first pressure level based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model.

[0147] The blood oxygen measurement result acquisition module 905 is used to acquire the user's blood oxygen saturation measurement result based on the PPG signals corresponding to the red light and infrared light using the target calculation model.

[0148] In some embodiments, the light intensity reading and signal component acquisition module is specifically used for:

[0149] Based on the spectral channel readings, obtain the curves of the red light channel readings and infrared light channel readings changing over time;

[0150] Based on the curve of the channel reading changing over time, the first PPG signal corresponding to red light and the second PPG signal corresponding to infrared light are determined.

[0151] In some embodiments, the blood oxygen measurement result acquisition module is specifically used for:

[0152] Obtain the AC and DC components of the PPG signals corresponding to the red and infrared light;

[0153] The parameter R value is determined based on the AC and DC components; the R value is used to represent the absorption ratio of red and infrared light.

[0154] Based on the R value and the target calculation model for the R value, the user's blood oxygen saturation measurement result is determined.

[0155] In some embodiments, the blood oxygen measurement result acquisition module, when acquiring the AC and DC components of the PPG signals corresponding to the red and infrared light, includes:

[0156] Each of the PPG signals is resampled; wherein the same sampling frequency is used for each signal resampling.

[0157] Based on the signal characteristics of the resampled PPG signal, the signal component extraction method is determined, and the AC component and DC component are obtained based on the signal component extraction method.

[0158] In some embodiments, the blood oxygen measurement result acquisition module, in determining the parameter R value based on the AC component and the DC component, includes:

[0159] The ratio of the AC component to the DC component of the red light is determined as the first component ratio.

[0160] The ratio of the AC component to the DC component of the infrared light is determined as the second component ratio.

[0161] The ratio R is determined based on the ratio of the first component to the ratio of the second component.

[0162] In some embodiments, the apparatus further includes:

[0163] The spectral channel readings generated by the photosensitive sensor when the sample population presses the light source with different pressure levels are collected to determine the light intensity reading samples under different pressure levels.

[0164] By fitting the light intensity readings to the corresponding pressure levels, a mapping relationship between the light intensity readings and the pressure levels can be obtained; or,

[0165] The pressure value is divided into M discrete value intervals. Based on the light intensity reading samples, a mapping relationship between the light intensity reading and the discrete value intervals is established. This mapping relationship is determined as the mapping relationship between the light intensity reading and the pressure value; M is greater than or equal to 2.

[0166] In some embodiments, the apparatus further includes:

[0167] When the sample population presses the light source with different pressure levels, the spectral channel readings generated by the light sensor under the pressure level are collected, and the blood oxygen saturation of the sample population is recorded to obtain the sample dataset.

[0168] Based on the sample dataset, a blood oxygen saturation calculation model with respect to parameter R value is obtained to obtain blood oxygen saturation under different pressure levels; the R value is determined based on spectral channel reading samples; the R value is used to represent the absorption ratio of red light and infrared light.

[0169] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0170] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0171] This disclosure also provides a terminal device. The terminal device includes a memory and a processor. The memory stores processor-executable instructions, and the processor is configured to execute the executable instructions in the memory to implement the steps of the blood oxygen saturation detection method provided above. In this disclosure, the terminal device may be a display device with a light source and a light sensor, such as a mobile phone or tablet.

[0172] Figure 10 This is a block diagram of a terminal device provided according to an exemplary embodiment. For example... Figure 10 As shown, the terminal device 1000 may include one or more of the following components: a processing component 1002, a memory 1004, a power supply component 1006, a multimedia component 1008, an audio component 1010, an input / output (I / O) interface 1012, a sensor component 1014, a communication component 1016, and an image acquisition component.

[0173] Processing component 1002 typically handles the overall operation of terminal device 1000, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 1002 may include one or more processors 1020 to execute instructions. Furthermore, processing component 1002 may include one or more units to facilitate interaction between processing component 1002 and other components. For example, processing component 1002 may include a multimedia unit to facilitate interaction between multimedia component 1008 and processing component 1002.

[0174] Memory 1004 is configured to store various types of data to support the operation of terminal device 1000. Examples of this data include instructions for any application or method operating on terminal device 1000, contact data, phonebook data, messages, pictures, videos, etc. Memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0175] The power supply component 1006 provides power to various components of the terminal device 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal device 1000.

[0176] Multimedia component 1008 includes a screen that provides an output interface between terminal device 1000 and target object. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the target object. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of a touch or swipe action but also the duration and pressure associated with the touch or swipe operation.

[0177] Audio component 1010 is configured to output and / or input audio signals. For example, audio component 1010 includes a microphone (MIC) configured to receive external audio signals when terminal device 1000 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 1004 or transmitted via communication component 1016. In some embodiments, audio component 1010 also includes a speaker for outputting audio signals.

[0178] I / O interface 1012 provides an interface between processing component 1002 and peripheral interface unit, which may be a keyboard, click wheel, button, etc.

[0179] Sensor assembly 1014 includes one or more sensors for providing various aspects of status assessment for terminal device 1000. For example, sensor assembly 1014 can detect the on / off state of terminal device 1000, the relative positioning of components such as the display screen and keypad of terminal device 1000, changes in the position of terminal device 1000 or a component, the presence or absence of contact between a target object and terminal device 1000, the orientation or acceleration / deceleration of terminal device 1000, and temperature changes of terminal device 1000. As another example, sensor assembly 1014 also includes a light sensor disposed below the OLED display screen.

[0180] Communication component 1016 is configured to facilitate wired or wireless communication between terminal device 1000 and other devices. Terminal device 1000 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 1016 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 1016 further includes a near-field communication (NFC) unit to facilitate short-range communication. For example, the NFC unit may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0181] In an exemplary embodiment, the terminal device 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components.

[0182] In one exemplary embodiment, this disclosure also provides a readable storage medium storing executable instructions. These executable instructions can be executed by a processor of a terminal device to implement the steps of the blood oxygen saturation detection method provided above. The readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0183] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the foregoing claims.

[0184] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for detecting blood oxygen saturation, characterized in that, This technology is applied to electronic devices, which at least include a light source and a light sensor; the light source supports providing infrared light; the light sensor includes a spectral sensor; and the electronic device includes a mobile phone or a tablet. The method includes: In response to the light source emitting light, the spectral channel reading generated by the photosensitive sensor is acquired when the user's measured part presses the light source; Based on the spectral channel readings, the light intensity reading is determined, and the photoelectric pulse image (PPG) signals corresponding to red and infrared light are obtained; wherein, determining the light intensity reading based on the spectral channel readings includes: weighting and merging the readings of each spectral channel according to the pre-set weight values ​​of different channel readings to obtain the light intensity reading; Based on the pre-established mapping relationship between light intensity readings and pressure, the first pressure generated when the user's tested part presses the light source, corresponding to the light intensity reading; Based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model, the target calculation model corresponding to the first pressure level is determined. Using the target calculation model, the user's blood oxygen saturation measurement results are obtained based on the PPG signals corresponding to the red and infrared light.

2. The method according to claim 1, characterized in that, The acquisition of PPG signals corresponding to red and infrared light includes: Based on the spectral channel readings, obtain the curves of the red light channel readings and infrared light channel readings changing over time; Based on the curve of the channel reading changing over time, the first PPG signal corresponding to red light and the second PPG signal corresponding to infrared light are determined.

3. The method according to claim 1, characterized in that, The step of using the target calculation model to obtain the user's blood oxygen saturation measurement results based on the PPG signals corresponding to the red and infrared light includes: Obtain the AC and DC components of the PPG signals corresponding to the red and infrared light; The parameter R value is determined based on the AC and DC components; the R value is used to represent the absorption ratio of red and infrared light. Based on the R value and the target calculation model for the R value, the user's blood oxygen saturation measurement result is determined.

4. The method according to claim 3, characterized in that, The acquisition of the AC and DC components of the PPG signals corresponding to the red and infrared light includes: Each of the PPG signals is resampled; wherein the same sampling frequency is used for each signal resampling. Based on the signal characteristics of the resampled PPG signal, the signal component extraction method is determined, and the AC component and DC component are obtained based on the signal component extraction method.

5. The method according to claim 3, characterized in that, The step of determining the parameter R value based on the AC component and the DC component includes: The ratio of the AC component to the DC component of the red light is determined as the first component ratio. The ratio of the AC component to the DC component of the infrared light is determined as the second component ratio. The ratio R is determined based on the ratio of the first component to the ratio of the second component.

6. The method according to claim 1, characterized in that, The method further includes: The spectral channel readings generated by the photosensitive sensor when the sample population presses the light source with different pressure levels are collected to determine the light intensity reading samples under different pressure levels. By fitting the light intensity readings to the corresponding pressure levels, a mapping relationship between the light intensity readings and the pressure levels can be obtained; or, The pressure value is divided into M discrete value intervals. Based on the light intensity reading samples, a mapping relationship between the light intensity reading and the discrete value intervals is established. This mapping relationship is determined as the mapping relationship between the light intensity reading and the pressure value; M is greater than or equal to 2.

7. The method according to claim 1, characterized in that, The method further includes: When the sample population presses the light source with different pressure levels, the spectral channel readings generated by the light sensor under the pressure level are collected, and the blood oxygen saturation of the sample population is recorded to obtain the sample dataset. Based on the sample dataset, a blood oxygen saturation calculation model with respect to parameter R value is obtained to obtain blood oxygen saturation under different pressure levels; the R value is determined based on spectral channel reading samples; the R value is used to represent the absorption ratio of red light and infrared light.

8. A blood oxygen saturation detection device, characterized in that, This technology is applied to electronic devices, which at least include a light source and a light sensor; the light source supports providing infrared light; the light sensor includes a spectral sensor; and the electronic device includes a mobile phone or a tablet. The device includes: The spectral channel reading acquisition module is used to acquire the spectral channel reading generated by the photosensitive sensor when the user presses the light source in response to the light source emission; The light intensity reading and signal component acquisition module is used to determine the light intensity reading based on the spectral channel readings and acquire the photoelectric pulse map (PPG) signals corresponding to red light and infrared light; wherein, determining the light intensity reading based on the spectral channel readings includes: weighting and merging the readings of each spectral channel according to the pre-set weight values ​​of different channel readings to obtain the light intensity reading; The pressure intensity determination module is used to obtain the first pressure intensity generated when the user's tested part presses the light source, corresponding to the light intensity reading, based on a pre-established mapping relationship between light intensity readings and pressure intensity. The target calculation model determination module is used to determine the target calculation model corresponding to the first pressure level based on the pre-established correspondence between the pressure level and the blood oxygen saturation calculation model. The blood oxygen measurement result acquisition module is used to acquire the user's blood oxygen saturation measurement result based on the PPG signals corresponding to the red and infrared light using the target calculation model.

9. An electronic device, characterized in that, include: Processor, memory; The memory is used to store computer programs; The processor is used to invoke the computer program to implement the blood oxygen saturation detection method as described in any one of claims 1-7.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the blood oxygen saturation detection method as described in any one of claims 1-7.

Images