A multi-wavelength PPG and body temperature cooperative monitoring system integrated in a smart ring

Abstract

The application discloses a multi-wavelength PPG and body temperature cooperative monitoring system integrated in a smart ring, and relates to the technical field of wearable smart devices.The system comprises the following components: a multi-parameter cooperative acquisition module integrated in the inner wall of the smart ring, comprising a multi-wavelength PPG acquisition unit, a body temperature and environmental parameter acquisition unit and a time sequence synchronization unit, and used for acquiring multi-dimensional physiological signals and environmental parameters;the multi-parameter cooperative acquisition module is used for realizing the synchronous acquisition of multi-wavelength PPG, body temperature and environmental temperature data, and the time sequence synchronization unit is used for ensuring the accurate matching of the time dimension, thereby solving the problem of asynchronous data in the traditional technology;on the basis of the above, a data fusion and health parameter calculation module is combined with multi-parameter to deduce the vascular elasticity characteristics, a vascular elasticity-body temperature-blood pressure coupling model is constructed, a deep learning algorithm is used to analyze the influence law of the change of the vascular elasticity under different temperature conditions on blood pressure, and the 24-hour blood pressure trend prediction in the future is realized.

Description

Technical Field

[0001] This invention relates to the field of wearable smart device technology, specifically to a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring. Background Technology

[0002] As people pay increasing attention to health management, wearable smart devices have been widely used in the field of physiological parameter monitoring. As a portable and comfortable wearable device, smart rings have become a popular choice for physiological parameter monitoring devices due to their advantages such as ease of wearing and no impact on daily activities. Photoplethysmography (PPG) technology and body temperature monitoring technology are commonly used technical means in physiological parameter monitoring. PPG technology can obtain important physiological parameters such as heart rate and blood oxygen by detecting changes in blood volume, while body temperature monitoring can reflect the basic physiological state of the human body.

[0003] Current smart ring-type wearable devices have many technical limitations in the field of physiological parameter monitoring. Most devices can only collect PPG signals or body temperature data separately. The two types of data lack precise matching in the time dimension, which makes it impossible to establish correlation analysis and the health assessment dimension is limited. Secondly, PPG signals are easily affected by motion interference, power frequency interference and outdoor strong light fluctuations. The original signal-to-noise ratio is low, which affects the accuracy of subsequent parameter calculations. Furthermore, in traditional technologies, parameters such as blood oxygen and heart rate are calculated based on PPG signals alone without combining body temperature data for co-correction. When body temperature changes cause vasodilation / vasoconstriction, parameter deviations are likely to occur. At the same time, most existing devices can only estimate instantaneous blood pressure and do not consider the coupling effect of vascular elasticity and temperature, making it impossible to predict blood pressure trends and meet the needs of early intervention for hypertensive patients. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring. This system can simultaneously acquire multi-wavelength PPG signals, body temperature, and ambient temperature data through a multi-parameter co-acquisition module, and ensure precise time-dimension matching through a timing synchronization unit. A signal preprocessing and conditioning module performs combined filtering, gain adjustment, and feature enhancement on the raw signals to improve signal quality. A main control and data transmission module coordinates the operation of each module, balancing low power consumption and data continuity. A data fusion and health parameter calculation module, based on multi-parameter co-analysis and combined with temperature data to correct PPG signals, calculates basic health parameters and constructs a vascular elasticity-body temperature-blood pressure coupling model to predict blood pressure trends for the next 24 hours. An anomaly warning and user interaction module supports default and custom configurations of health thresholds, identifies anomalies through multi-parameter co-analysis and issues warnings, and automatically generates anomaly reports including waveforms, vascular elasticity characteristics, and blood pressure prediction curves.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring, the system comprising: Multi-parameter collaborative acquisition module: integrated into the inner wall of the smart ring, including a multi-wavelength PPG acquisition unit, a body temperature and environmental parameter acquisition unit, and a timing synchronization unit, used to acquire multi-dimensional physiological signals and environmental parameters; Signal preprocessing and conditioning module: performs combined filtering, gain adjustment and vascular elasticity enhancement on PPG signals, and synchronously converts PPG and temperature analog signals into digital signals through a high-precision analog-to-digital converter; Main control and data transmission module: It realizes data interaction with the terminal through low-power wireless communication, and sets three working states and automatically switches to low-power / sleep mode when idle; Data fusion and health parameter calculation module: Based on timestamp aligned data, PPG baseline drift is corrected with temperature as the benchmark, blood oxygen, heart rate and vascular elasticity characteristics are calculated, a coupled model is constructed and deep learning algorithms are used to predict blood pressure trends for the next 24 hours. Anomaly warning and user interaction module: It has a built-in default health threshold and supports customization. It compares parameters and blood pressure trend prediction results with the threshold in real time, and provides warnings and generates anomaly reports through local prompts and terminal push.

[0006] Furthermore, the multi-wavelength PPG acquisition unit includes LED light emitting components and photodiode receiving components with wavelengths of 532nm, 660nm, and 940nm. The 660nm and 940nm wavelengths are used for calculating blood oxygen-related parameters, while the 532nm wavelength is used to extract vascular elasticity characteristics and suppress motion interference. The LED light emitting components operate in a time-division multiplexing manner, and the photodiode receiving components receive light signals reflected / transmitted through finger tissue and convert them into PPG analog signals. The body temperature and environmental parameter acquisition unit uses a temperature sensor to synchronously acquire body temperature and environmental temperature data. It is arranged in the same area as the PPG acquisition unit on the inner wall of the smart ring and supports dynamic sampling frequency adjustment. The timing synchronization unit provides a unified timestamp for the PPG acquisition unit and the body temperature and environmental parameter acquisition unit, binding each frame of PPG signal to the corresponding body temperature and environmental temperature data.

[0007] Furthermore, the signal preprocessing and conditioning module performs combined filtering on the original PPG analog signal. Through the synergistic effect of power frequency notch filtering, dynamic noise suppression filtering, and environmental interference suppression filtering, it suppresses motion, power frequency, and strong light interference. It also adjusts the gain of weak PPG analog signals by amplifying the signal to a stable processing range through a programmable gain amplifier, avoiding accuracy loss caused by signal attenuation. At the same time, it enhances the features of PPG signals related to vascular elasticity, highlighting the pulse wave rise slope and reflected wave intensity. A high-precision analog-to-digital converter is used to convert the processed PPG analog signal and body temperature and ambient temperature analog signals into digital signals. The sampling rate is synchronized with the sampling frequency of the multi-parameter collaborative acquisition module to preserve signal detail features.

[0008] Furthermore, the main control and data transmission module adopts a low-power microcontroller unit, which coordinates the sampling time of the multi-parameter acquisition module and the filtering / gain parameter configuration of the signal preprocessing module through preset logic; at the same time, it performs temporary storage management of digital signals, and the built-in storage unit is used for offline storage of historical data for multiple days; it also adopts a low-power wireless communication protocol to realize data interaction with terminal devices, and supports manual / automatic switching between real-time transmission and timed batch transmission modes; and it is set with three working states: monitoring mode, low-power mode and sleep mode. In monitoring mode, all modules work; in low-power mode, some LED channels are turned off; in sleep mode, only the clock and wake-up trigger are retained; and it automatically switches to low-power / sleep mode when idle.

[0009] Furthermore, the data fusion and health parameter calculation module, based on the timestamp of the multi-parameter collaborative acquisition module, aligns the analog-to-digital converted PPG digital signal with the body temperature and ambient temperature digital signals on the time axis. Using body temperature and ambient temperature data as reference benchmarks, it employs an adaptive correction algorithm to correct the PPG signal baseline drift. Based on the law of light absorption, it calculates blood oxygen saturation using the absorbance ratio of the PPG signal. It calculates the pulse cycle through peak detection of the PPG signal and converts it into a heart rate value. Based on the 532nm wavelength PPG signal, it extracts the pulse wave rise slope and reflected wave intensity parameters to characterize vascular elasticity. It then constructs a vascular elasticity-body temperature-blood pressure coupling model, using deep learning algorithms to analyze the impact of vascular elasticity changes on blood pressure under different temperature conditions, dynamically correcting the prediction results. Based on historical data and real-time characteristics, it achieves 24-hour trend prediction of systolic and diastolic blood pressure.

[0010] Furthermore, the data fusion and health parameter calculation module employs an adaptive correction algorithm to correct the PPG signal baseline drift. The algorithm formula is as follows: ,in, It is the corrected PPG signal baseline. It is the original PPG signal baseline. It is the skin temperature obtained by the body temperature acquisition unit; This is the baseline body temperature, which is the average normal human body temperature. It is the ambient temperature, which is simultaneously acquired by the body temperature and environmental parameter acquisition unit. This is the baseline ambient temperature, taken as the average value of a normal ambient temperature. This is the body temperature influence coefficient, obtained through sample training, which characterizes the weight of the effect of body temperature changes on vasodilation / vasoconstriction. It is the environmental temperature influence coefficient, obtained through sample training, which characterizes the influence weight of environmental temperature on the state of blood vessels on the body surface.

[0011] Furthermore, the data fusion and health parameter calculation module extracts the pulse wave rising slope and reflected wave intensity parameters based on the 532nm wavelength PPG signal. The formula for calculating the pulse wave rising slope is as follows: ,in, It is the corrected slope of the rising edge of the pulse wave. It is the main peak value of the 532nm wavelength PPG signal. It is the rising edge start value of the 532nm wavelength PPG signal. It is the time point corresponding to the peak value of the main wave. It is the time point corresponding to the start of the rising edge. It is a temperature correction factor that corrects for the effect of body temperature on vascular elasticity measurements; the formula for calculating the intensity of the reflected wave is: ,in, It is the corrected intensity of the reflected wave. It is the peak value of the reflected wave of the 532nm wavelength PPG signal. It is the corrected PPG signal baseline. It is the main peak value of the 532nm wavelength PPG signal. It is the ambient temperature correction factor.

[0012] Furthermore, the data fusion and health parameter calculation module, based on the law of light absorption, calculates blood oxygen saturation using the absorbance ratio of the PPG signal. The calculation formula is as follows: ,in, This is the corrected blood oxygen saturation. It is a wavelength of 660nm. It is a wavelength of 940nm. , These correspond to the AC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , These correspond to the DC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , These are the reference coefficients for PPG signals at wavelengths of 660nm and 940nm, respectively. It is a blood oxygen temperature correction factor that corrects changes in blood light absorption characteristics caused by body temperature.

[0013] Furthermore, the data fusion and health parameter calculation module utilizes deep learning algorithms to analyze the influence of changes in vascular elasticity on blood pressure under different temperature conditions. The algorithm formula is as follows: ,in, It is the future Predicted blood pressure values ​​at any given time. It is the slope of the rising edge of the pulse wave at the current moment; It is the intensity of the reflected wave at the current moment. It is the skin temperature at the current moment. It is the ambient temperature at the current moment. This is an estimated blood pressure value at the current moment, obtained by fusing historical data with real-time features. ~ These are model weight coefficients, obtained by training sample data using a deep learning algorithm, dynamically representing the influence weights of each parameter on the blood pressure trend. It is the model bias term, determined by the distribution characteristics of the training data.

[0014] Compared with existing technologies, this multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring has the following advantages: I. This invention achieves synchronous acquisition of multi-wavelength PPG, body temperature, and ambient temperature data through a multi-parameter collaborative acquisition module, and ensures accurate matching of time dimensions by utilizing a time-series synchronization unit, thus solving the problem of data asynchrony in traditional technologies. On this basis, the data fusion and health parameter calculation module combines multi-parameter derivation of vascular elasticity characteristics to construct a vascular elasticity-body temperature-blood pressure coupling model. Deep learning algorithms are used to analyze the influence of changes in vascular elasticity on blood pressure under different temperature conditions, enabling 24-hour blood pressure trend prediction. This provides a scientific basis for early intervention for hypertensive patients and other groups, improving the accuracy and foresight of health management.

[0015] Second, this invention coordinates the timing of each module through the main control and data transmission module, supports switching between real-time transmission and timed batch transmission modes, and sets three working states: monitoring mode, low power mode, and sleep mode. While ensuring monitoring continuity and prediction accuracy, it effectively extends the battery life to meet the needs of long-term use. At the same time, the abnormal warning and user interaction module triggers warnings based on multi-parameter collaborative abnormalities and blood pressure trend changes, avoiding misjudgment based on a single parameter, and provides abnormal reports including predicted trends, improving the ability to identify and intervene in health risks, enabling users to understand their own health status in a timely manner and take corresponding measures.

[0016] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0018] Figure 1 This is a structural block diagram of a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring; Figure 2 This is a flowchart of a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring. Detailed Implementation

[0019] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0020] This invention provides a multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring, such as... Figure 1 As shown, the system includes a multi-parameter collaborative acquisition module, a signal preprocessing and conditioning module, a main control and data transmission module, a data fusion and health parameter calculation module, and an anomaly warning and user interaction module. The multi-parameter collaborative acquisition module enables synchronous acquisition of multi-wavelength PPG signals, body temperature, and ambient temperature data, and ensures accurate time-dimension matching through a timing synchronization unit. The signal preprocessing and conditioning module performs combined filtering, gain adjustment, and feature enhancement on the raw signals to improve signal quality. The main control and data transmission module coordinates the work of each module, balancing low power consumption and data continuity. The data fusion and health parameter calculation module, based on multi-parameter collaborative analysis and combined with temperature data to correct PPG signals, calculates basic health parameters and constructs a vascular elasticity-body temperature-blood pressure coupling model to predict blood pressure trends for the next 24 hours. The anomaly warning and user interaction module supports default and custom configurations of health thresholds, identifies anomalies through multi-parameter collaborative analysis, issues warnings, and automatically generates anomaly reports containing waveforms, vascular elasticity characteristics, and blood pressure prediction curves.

[0021] Example 1 In this embodiment, the user commutes for one hour every morning during the subway rush hour. During the commute, physiological parameters often fluctuate due to crowds and walking. The user needs to monitor blood oxygen, heart rate, vascular elasticity, and blood pressure trends for the next 24 hours in real time through a smart ring to provide timely warnings of health risks.

[0022] When a user puts on the smart ring after waking up in the morning, the low-power microcontroller unit of the ring's main control and data transmission module automatically detects the wearing action and switches from sleep mode to monitoring mode. In this mode, the multi-parameter collaborative acquisition module, signal preprocessing and conditioning module, and data fusion and health parameter calculation module all work. At the same time, the microcontroller unit presets logic to coordinate the sampling time of the multi-parameter acquisition module and configures the filtering and gain parameters of the signal preprocessing module to ensure that acquisition and processing are synchronized.

[0023] like Figure 2 As shown, the multi-wavelength PPG acquisition unit of the multi-parameter collaborative acquisition module is activated. The LED light emitting components with wavelengths of 532nm, 660nm, and 940nm operate according to a time-division multiplexing mechanism. The 660nm and 940nm wavelengths are used for subsequent calculation of blood oxygen-related parameters, while the 532nm wavelength is used to extract vascular elasticity characteristics and suppress motion interference during commuting. The photodiode receiving component continuously receives light signals reflected / transmitted through finger tissue and converts them into PPG analog signals. At the same time, the body temperature and environmental parameter acquisition unit activates the temperature sensor to synchronously collect the user's finger skin temperature and the ambient temperature inside the subway car. It also supports dynamic adjustment of the sampling frequency based on the density of people inside the car. The timing synchronization unit provides a unified timestamp for the PPG acquisition unit and the body temperature and environmental parameter acquisition unit, binding each frame of PPG analog signal with the corresponding body temperature and ambient temperature data to avoid data misalignment.

[0024] After receiving the raw PPG analog signal, the signal preprocessing and conditioning module first filters out power frequency interference from the subway power supply system, motion interference from finger swaying during walking, and strong light interference inside the carriage through the combined effects of power frequency notch filtering, dynamic noise suppression filtering, and environmental interference suppression filtering. Then, the weak PPG analog signal after filtering is amplified to a stable processing range by a programmable gain amplifier to prevent signal attenuation from causing accuracy loss. At the same time, the features related to vascular elasticity in the PPG signal are enhanced to highlight the two key features of pulse wave rise slope and reflected wave intensity. Finally, a high-precision analog-to-digital converter is used to synchronously convert the processed PPG analog signal and body temperature and ambient temperature analog signals into digital signals. The conversion sampling rate is consistent with the sampling frequency of the multi-parameter collaborative acquisition module to fully preserve the signal details.

[0025] The main control and data transmission module transmits the converted digital signal to the user's mobile terminal in real time via a low-power wireless communication protocol (such as Bluetooth Low Energy). If the signal is interrupted in the subway tunnel, the module's built-in storage unit will automatically store the data offline and continue transmitting it after the signal is restored. It also supports storing nearly 7 days of historical monitoring data for easy review by the user.

[0026] After receiving the digital signal, the data fusion and health parameter calculation module first aligns the PPG digital signal with the body temperature and ambient temperature digital signals on the time axis based on the timestamp provided by the multi-parameter collaborative acquisition module. Then, using the body temperature and ambient temperature data as reference benchmarks, it employs an adaptive correction algorithm to correct the PPG signal baseline drift and eliminate the influence of temperature changes on the PPG signal. The algorithm formula is as follows: ,in It is the corrected PPG signal baseline. It is the original PPG signal baseline. It is the skin temperature obtained by the body temperature acquisition unit. It is the baseline body temperature, which is the average normal human body temperature. It is the ambient temperature that is synchronously acquired by the body temperature and environmental parameter acquisition unit. It is the baseline ambient temperature, which is the average value of a normal ambient temperature. It is a body temperature influence coefficient obtained through sample training, which characterizes the weight of the effect of body temperature changes on vasodilation / vasoconstriction. The environmental temperature influence coefficient, obtained through sample training, characterizes the weight of the influence of environmental temperature on the state of blood vessels on the body surface. Subsequently, based on the law of light absorption, blood oxygen saturation is calculated using the absorbance ratio of the PPG signal. The calculation formula is as follows: ,in This is the corrected blood oxygen saturation. It is a wavelength of 660nm. It is a wavelength of 940nm. , These correspond to the AC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , These correspond to the DC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , The reference coefficients for PPG signals at wavelengths of 660nm and 940nm are respectively. It is a blood oxygen temperature correction factor that corrects for changes in blood light absorption characteristics caused by body temperature. Simultaneously, it calculates the pulse cycle through peak detection of the PPG signal and converts the cycle into a heart rate value. Based on the 532nm wavelength PPG signal, it extracts the pulse wave rise slope and reflected wave intensity parameters to characterize the user's vascular elasticity. The formula for calculating the pulse wave rise slope is: It is the corrected slope of the rising edge of the pulse wave. It is the main peak value of the 532nm wavelength PPG signal. It is the rising edge start value of the 532nm wavelength PPG signal. It is the time point corresponding to the peak value of the main wave. It is the time point corresponding to the start of the rising edge. It is a temperature correction factor that corrects for the effect of body temperature on vascular elasticity measurements; the formula for calculating the intensity of reflected waves is: ,in It is the corrected intensity of the reflected wave. It is the peak value of the reflected wave of the 532nm wavelength PPG signal. It is the corrected PPG signal baseline. It is the main peak value of the 532nm wavelength PPG signal. It is the ambient temperature correction factor.

[0027] Finally, a coupled model of vascular elasticity, body temperature, and blood pressure was constructed. A deep learning algorithm was then used to analyze the influence of changes in vascular elasticity under current body temperature and ambient temperature on blood pressure. The formula for this deep learning algorithm is as follows: ,in It is the future Predicted blood pressure values ​​at any given time. It is the slope of the rising edge of the pulse wave at the current moment. It is the intensity of the reflected wave at the current moment. It is the skin temperature at the current moment. It is the ambient temperature at the current moment. It is an estimated blood pressure value for the current moment obtained by fusing historical data with real-time features. These are model weight coefficients obtained by training sample data using deep learning algorithms, dynamically representing the influence of each parameter on blood pressure trends. It is a model bias term determined by the distribution characteristics of the training data; by combining historical monitoring data and real-time features, this algorithm can predict the trend of systolic and diastolic blood pressure in the next 24 hours.

[0028] The abnormal warning and user interaction module calls the built-in default health thresholds and compares the calculated blood oxygen, heart rate, vascular elasticity parameters and 24-hour blood pressure trend prediction results in real time. When a user's heart rate rises to 110 beats per minute and blood oxygen saturation drops to 93% due to running while changing subway lines, the system determines that the parameters exceed the thresholds and immediately sends a local alert through the ring's built-in vibrator. At the same time, it pushes a warning message to the mobile terminal, which includes the abnormal parameter values, the time of the abnormality, and a simple suggestion. It also automatically generates an abnormal report, recording the physiological parameter change curves during the abnormal period, for the user to view later or share with medical staff.

[0029] Example 2 The user in this embodiment has a mild tendency to sleep apnea, and is prone to fluctuations in blood oxygen and slowed heart rate during nighttime sleep. They also need to monitor blood pressure changes over a long period of time. By monitoring physiological parameters during nighttime sleep through a smart ring, the interference of traditional monitoring devices on sleep can be avoided, and risks can be warned in real time and blood pressure trends can be predicted for the next day.

[0030] When a user wears the smart ring 30 minutes before bed, the low-power microcontroller unit of the main control and data transmission module detects a decrease in the user's activity level and automatically switches from monitoring mode to low-power mode: turning off the 660nm wavelength LED channel and keeping only the 532nm and 940nm wavelength LED channels working to reduce energy consumption; if the user is detected to have entered deep sleep, it further switches to hibernation mode, keeping only the clock module and wake-up trigger module working to minimize nighttime power consumption.

[0031] The multi-wavelength PPG acquisition unit of the multi-parameter collaborative acquisition module operates on a time-sharing mechanism. The 532nm wavelength LED is used to extract vascular elasticity characteristics and suppress motion interference from the user turning over at night. The 940nm wavelength LED, in conjunction with the 660nm wavelength LED (intermittently turned on in low-power mode, once every 10 seconds), is used for blood oxygen parameter calculation. The photodiode receiving component receives the light signal reflected by the finger tissue and converts it into a PPG analog signal. The body temperature and environmental parameter acquisition unit synchronously collects the user's finger skin temperature and bedroom ambient temperature, with the sampling frequency dynamically adjusted to once every 10 seconds (reduced to once every 30 seconds during deep sleep). It is also arranged in the same area on the inner wall of the ring as the PPG acquisition unit to ensure the correlation between temperature data and PPG data. The timing synchronization unit provides a unified timestamp for the two types of acquisition units, binding each frame of PPG analog signal with the corresponding body temperature and ambient temperature data to ensure data time consistency.

[0032] The signal preprocessing and conditioning module addresses nighttime scene interference by filtering out interfering signals through the combined effects of power frequency notch filtering, dynamic noise suppression filtering, and environmental interference suppression filtering. For the weaker PPG analog signals at night, gain adjustment is applied using a programmable gain amplifier to amplify the signal to a stable processing range, avoiding accuracy loss. Simultaneously, the module enhances the vascular elasticity-related characteristics in the PPG signal, highlighting the pulse wave rise slope and reflected wave intensity, providing clear features for subsequent vascular elasticity assessment. Finally, a high-precision analog-to-digital converter is used to convert the processed PPG analog signal, body temperature, and ambient temperature analog signals into digital signals, with the sampling rate synchronized with the dynamic sampling frequency of the acquisition module to preserve subtle changes in physiological parameters at night.

[0033] The main control and data transmission module adopts a timed batch transmission mode to reduce the power consumption of wireless communication at night. If the user's mobile phone is in airplane mode, the module's built-in storage unit automatically stores the data, supporting the storage of nearly 14 days of nighttime sleep monitoring data, so that users can easily view the changes in physiological parameters during the complete sleep period the next morning.

[0034] The data fusion and health parameter calculation module first aligns the PPG digital signal, body temperature, and ambient temperature digital signals based on timestamps. Then, using nighttime body temperature and bedroom ambient temperature as benchmarks, it employs an adaptive correction algorithm to correct the PPG signal baseline drift and eliminate the impact of nighttime temperature fluctuations on the PPG signal. Subsequently, it calculates blood oxygen saturation based on the law of light absorption, calculates heart rate through PPG signal peak detection, and evaluates vascular elasticity by extracting pulse wave rise slope and reflected wave intensity parameters based on the 532nm wavelength PPG signal. Finally, it constructs a vascular elasticity-body temperature-blood pressure coupling model, combines nighttime physiological parameters with historical blood pressure data, and uses deep learning algorithms to predict the systolic and diastolic blood pressure trends for the next 24 hours, providing a reference for users' blood pressure management the following day.

[0035] The abnormal warning and user interaction module calls the user-defined health threshold and compares the results of nighttime physiological parameters and blood pressure trend prediction in real time. When a user's blood oxygen saturation drops to 90% for 10 seconds due to sleep apnea at 2 a.m., the system determines that there is an abnormality and first provides a local alert through a weak vibration built into the ring. When the user wakes up the next morning, the mobile terminal pushes detailed abnormal warning information, including the time of the abnormality, the lowest blood oxygen value, heart rate changes and blood pressure trend prediction, and generates a nighttime sleep health report with curves of changes in blood oxygen, heart rate and vascular elasticity parameters to help the user understand their own sleep health status.

[0036] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring, characterized in that, The system includes: Multi-parameter collaborative acquisition module: integrated into the inner wall of the smart ring, including a multi-wavelength PPG acquisition unit, a body temperature and environmental parameter acquisition unit, and a timing synchronization unit, used to acquire multi-dimensional physiological signals and environmental parameters; Signal preprocessing and conditioning module: performs combined filtering, gain adjustment and vascular elasticity enhancement on PPG signals, and synchronously converts PPG and temperature analog signals into digital signals through a high-precision analog-to-digital converter; Main control and data transmission module: It realizes data interaction with the terminal through low-power wireless communication, and sets three working states and automatically switches to low-power / sleep mode when idle; Data fusion and health parameter calculation module: Based on timestamp aligned data, PPG baseline drift is corrected with temperature as the benchmark, blood oxygen, heart rate and vascular elasticity characteristics are calculated, a coupled model is constructed and deep learning algorithms are used to predict blood pressure trends for the next 24 hours. Anomaly warning and user interaction module: It has a built-in default health threshold and supports customization. It compares parameters and blood pressure trend prediction results with the threshold in real time, and provides warnings and generates anomaly reports through local prompts and terminal push.

2. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 1, characterized in that, The multi-wavelength PPG acquisition unit includes LED light emitting components and photodiode receiving components with wavelengths of 532nm, 660nm, and 940nm. The 660nm and 940nm wavelengths are used for calculating blood oxygen-related parameters, while the 532nm wavelength is used to extract vascular elasticity characteristics and suppress motion interference. The LED light emitting components operate in a time-division multiplexing manner, and the photodiode receiving components receive light signals reflected / transmitted through finger tissue and convert them into PPG analog signals. The body temperature and environmental parameter acquisition unit uses a temperature sensor to synchronously acquire body temperature and environmental temperature data. It is arranged in the same area as the PPG acquisition unit on the inner wall of the smart ring and supports dynamic sampling frequency adjustment. The timing synchronization unit provides a unified timestamp for the PPG acquisition unit and the body temperature and environmental parameter acquisition unit, binding each frame of PPG signal to the corresponding body temperature and environmental temperature data.

3. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 1, characterized in that, The signal preprocessing and conditioning module performs combined filtering on the original PPG analog signal. Through the synergistic effect of power frequency notch filtering, dynamic noise suppression filtering, and environmental interference suppression filtering, it suppresses motion, power frequency, and strong light interference. It also adjusts the gain of weak PPG analog signals by amplifying the signal to a stable processing range through a programmable gain amplifier to avoid accuracy loss caused by signal attenuation. At the same time, it enhances the features of PPG signals related to vascular elasticity, highlighting the pulse wave rise slope and reflected wave intensity characteristics. A high-precision analog-to-digital converter is used to convert the processed PPG analog signal and the analog signals of body temperature and ambient temperature into digital signals. The sampling rate is synchronized with the sampling frequency of the multi-parameter collaborative acquisition module to preserve the detailed features of the signal.

4. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 1, characterized in that, The main control and data transmission module adopts a low-power microcontroller unit, which coordinates the sampling time of the multi-parameter acquisition module and the filtering / gain parameter configuration of the signal preprocessing module through preset logic; at the same time, it performs temporary storage management of digital signals, and the built-in storage unit is used for offline storage of historical data for multiple days; it also adopts a low-power wireless communication protocol to realize data interaction with terminal devices, and supports manual / automatic switching between real-time transmission and timed batch transmission modes; and it is set with three working states: monitoring mode, low-power mode and sleep mode. In monitoring mode, all modules work; in low-power mode, some LED channels are turned off; in sleep mode, only the clock and wake-up trigger are retained; and it automatically switches to low-power / sleep mode when idle.

5. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 1, characterized in that, The data fusion and health parameter calculation module aligns the PPG digital signal after analog-to-digital conversion with the body temperature and ambient temperature digital signals on the time axis based on the timestamp of the multi-parameter collaborative acquisition module. Using the body temperature and ambient temperature data as reference benchmarks, it uses an adaptive correction algorithm to correct the baseline drift of the PPG signal. Based on the law of light absorption, blood oxygen saturation is calculated using the absorbance ratio of PPG signals; the pulse cycle is calculated by detecting the peak value of PPG signals and converted into heart rate value. Based on the 532nm wavelength PPG signal, the pulse wave rise slope and reflected wave intensity parameters are extracted to characterize the vascular elasticity state. A vascular elasticity-body temperature-blood pressure coupling model is constructed, and a deep learning algorithm is used to analyze the influence of vascular elasticity changes on blood pressure under different temperature conditions. The prediction results are dynamically corrected, and based on historical data and real-time features, the trend prediction of systolic and diastolic blood pressure for the next 24 hours is achieved.

6. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 5, characterized in that, The data fusion and health parameter calculation module uses an adaptive correction algorithm to correct the PPG signal baseline drift. The algorithm formula is as follows: ,in, It is the corrected PPG signal baseline. It is the original PPG signal baseline. It is the skin temperature obtained by the body temperature acquisition unit; This is the baseline body temperature, which is the average normal human body temperature. It is the ambient temperature, which is simultaneously acquired by the body temperature and environmental parameter acquisition unit. This is the baseline ambient temperature, taken as the average value of a normal ambient temperature. This is the body temperature influence coefficient, obtained through sample training, which characterizes the weight of the effect of body temperature changes on vasodilation / vasoconstriction. It is the environmental temperature influence coefficient, obtained through sample training, which characterizes the influence weight of environmental temperature on the state of blood vessels on the body surface.

7. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 5, characterized in that, The data fusion and health parameter calculation module extracts the pulse wave rising slope and reflected wave intensity parameters based on the 532nm wavelength PPG signal. The formula for calculating the pulse wave rising slope is as follows: ,in, It is the corrected slope of the rising edge of the pulse wave. It is the main peak value of the 532nm wavelength PPG signal. It is the rising edge start value of the 532nm wavelength PPG signal. It is the time point corresponding to the peak value of the main wave. It is the time point corresponding to the start of the rising edge. It is a temperature correction factor that corrects for the effect of body temperature on vascular elasticity measurements; the formula for calculating the intensity of the reflected wave is: ,in, It is the corrected intensity of the reflected wave. It is the peak value of the reflected wave of the 532nm wavelength PPG signal. It is the corrected PPG signal baseline. It is the main peak value of the 532nm wavelength PPG signal. It is the ambient temperature correction factor.

8. The multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 5, characterized in that, The data fusion and health parameter calculation module is based on the law of light absorption and uses the absorbance ratio of PPG signals to calculate blood oxygen saturation. The calculation formula is as follows: ,in, This is the corrected blood oxygen saturation. It is a wavelength of 660nm. It is a wavelength of 940nm. , These correspond to the AC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , These correspond to the DC components of PPG signals at wavelengths of 660nm and 940nm, respectively. , These are the reference coefficients for PPG signals at wavelengths of 660nm and 940nm, respectively. It is a blood oxygen temperature correction factor that corrects changes in blood light absorption characteristics caused by body temperature.

9. A multi-wavelength PPG and body temperature co-monitoring system integrated into a smart ring according to claim 5, characterized in that, The data fusion and health parameter calculation module uses deep learning algorithms to analyze the influence of changes in vascular elasticity on blood pressure under different temperature conditions. The algorithm formula is as follows: ,in, It is the future Predicted blood pressure values ​​at any given time. It is the slope of the rising edge of the pulse wave at the current moment; It is the intensity of the reflected wave at the current moment. It is the skin temperature at the current moment. It is the ambient temperature at the current moment. This is an estimated blood pressure value at the current moment, obtained by fusing historical data with real-time features. ~ These are model weight coefficients, obtained by training sample data using a deep learning algorithm, dynamically representing the influence weights of each parameter on the blood pressure trend. It is the model bias term, determined by the distribution characteristics of the training data.

Images