A blood pressure monitoring method, system, electronic device and storage medium

Abstract

The embodiments of the present invention provide a blood pressure monitoring method, system, electronic device and storage medium. The method collects PPG signals through PPG photoplethysmography, transmits them to the host for analysis, controls the electric pulse module to perform blood pressure treatment according to the results, and collects PPG signals again to confirm the treatment effect. The invention also involves steps such as preprocessing, time domain analysis, frequency domain analysis and feature extraction to improve the accuracy of blood pressure monitoring. In addition, the treatment pulse is dynamically adjusted according to the blood pressure parameters, and the changes in the PPG signal are monitored in real time. The present invention also provides a blood pressure monitoring system, electronic device and computer-readable storage medium for implementing the method. Through the technical solution of the present invention, accurate and dynamic blood pressure monitoring and treatment can be achieved, improving user experience and treatment effects.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of medical data processing technology, and in particular, to a blood pressure monitoring method, system, electronic device, and storage medium. Background Art

[0002] Blood pressure monitoring is an important diagnostic method in the field of healthcare, and is particularly critical for the prevention and treatment of cardiovascular diseases such as hypertension. Traditional blood pressure measurement methods mainly rely on cuff-type sphygmomanometers, which measure blood pressure by intermittently applying and releasing pressure on blood vessels.

[0003] In existing blood pressure monitoring technologies, cuff-type sphygmomanometers are usually used for intermittent measurements. Although this method is accurate, it cannot achieve continuous monitoring and may cause discomfort to users during the measurement process. With the popularity of wearable devices, non-invasive and continuous blood pressure monitoring using photoplethysmography (PPG) has gradually become a research hotspot. PPG technology monitors physiological parameters by detecting changes in light intensity caused by changes in blood volume, but its application in blood pressure monitoring still faces challenges in signal acquisition and processing.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure provide a blood pressure monitoring method, system, and electronic

[0007] Devices and storage media are used to solve the technical problems of difficult signal acquisition and processing faced by blood pressure monitoring applications mentioned in the background technology section above.

[0008] In a first aspect, some embodiments of the present disclosure provide a blood pressure monitoring method, the method comprising:

[0009] PPG photoplethysmography is used to collect PPG signals by contacting the skin with a preset sensor;

[0010] Through closed-loop control, the PPG signal collected by the preset sensor is transmitted to the host for analysis;

[0011] According to the analysis results, corresponding current pulses are generated and act on the skin through electrodes to perform blood pressure treatment;

[0012] After the treatment, the PPG signal is collected again by the preset sensor using PPG photoplethysmography to confirm the treatment effect.

[0013] As a further improvement of the present application, using PPG photoplethysmography to contact the skin with a preset sensor, collecting PPG signals includes:

[0014] Arranging the preset sensor at a preset body position of the user, ensuring that the contact between the preset sensor and the skin meets the monitoring condition;

[0015] A PPG signal is formed by emitting a light beam of a specific wavelength, which penetrates the skin and is modulated by changes in blood volume in the blood vessels;

[0016] Receiving a reflected or transmitted PPG signal modulated by a change in blood vessel volume, wherein the PPG signal changes in intensity corresponding to a periodic change in blood vessel volume;

[0017] Using detection of intensity changes of the modulated PPG signal and converting these changes into corresponding electrical signals;

[0018] The converted electrical signal is converted into a processable digital signal form through an analog-to-digital converter;

[0019] The converted digital signal is analyzed by digital signal processing algorithm to extract characteristic parameters related to blood pressure changes.

[0020] As a further improvement of the present application, the digital signal after conversion is analyzed by a digital signal processing algorithm to extract characteristic parameters related to blood pressure changes, including:

[0021] Preprocessing the PPG signal includes filtering out baseline drift and high-frequency noise to improve the signal-to-noise ratio of the signal;

[0022] Performing time domain analysis on the preprocessed PPG signal to calculate the statistical characteristics of the signal, wherein the statistical characteristics include the mean value, standard deviation and peak value of the signal;

[0023] Apply frequency domain analysis technology to convert the PPG signal after time domain analysis from time domain to frequency domain to identify the frequency components related to cardiac activity;

[0024] Through the frequency domain filter, the specific frequency band related to blood pressure changes is selected to exclude the interference of other irrelevant frequency components;

[0025] Perform envelope detection on the PPG signal in the selected frequency band to extract the signal envelope related to the periodic change of vascular volume;

[0026] Performing feature recognition on the signal envelope to extract feature points reflecting blood pressure changes in the PPG signal, wherein the feature points include peaks and troughs;

[0027] Using a machine learning model, a relationship model between PPG signal features and blood pressure parameters is established based on the extracted feature points reflecting blood pressure changes;

[0028] According to the relationship model, blood pressure parameters are calculated from the PPG signal characteristics, the blood pressure parameters being systolic pressure and diastolic pressure;

[0029] The calculated blood pressure parameters are verified and calibrated.

[0030] As a further improvement of the present application, the method further includes:

[0031] Dynamically adjusting the frequency and amplitude of the current pulses generated by the electric pulse module according to the change trend of the blood pressure parameters;

[0032] Real-time monitoring of PPG signal changes during treatment to evaluate the effectiveness of current blood pressure parameters;

[0033] Through user feedback or automatic threshold judgment, the adjustment of blood pressure parameters is triggered to optimize the treatment effect.

[0034] As a further improvement of the present application, the preprocessing of the PPG signal further includes:

[0035] Apply a Gaussian filter or a median filter to remove high-frequency noise from the PPG signal;

[0036] Use a low-pass filter to remove low-frequency trends below the heart's pumping frequency;

[0037] Perform DC offset correction on the PPG signal to ensure the baseline stability of the signal.

[0038] As a further improvement of the present application, the time domain analysis of the preprocessed PPG signal further includes:

[0039] Calculate the maximum and minimum values ​​of the PPG signal within a time interval to determine the amplitude of the vascular volume change;

[0040] Measure the rise time and fall time of the PPG signal waveform to evaluate the vascular response speed;

[0041] Through time series analysis, periodic patterns in PPG signals are identified and compared with preset heart activity cycles.

[0042] As a further improvement of the present application, the application of frequency domain analysis technology to convert the PPG signal after time domain analysis from the time domain to the frequency domain to identify the frequency components related to cardiac activity includes:

[0043] Perform fast Fourier transform on the PPG signal to obtain a PPG signal spectrum diagram;

[0044] identifying a peak frequency in the PPG signal spectrogram, the peak frequency corresponding to the pumping frequency of the heart;

[0045] Apply a bandpass filter to extract the signal components corresponding to the frequency of cardiac activity;

[0046] By calculating the power of signals in different frequency ranges in the PPG signal spectrum diagram, the energy of different frequency components in the PPG signal is quantified.

[0047] In a second aspect, some embodiments of the present disclosure provide a blood pressure monitoring system, comprising:

[0048] A receiving module, used for contacting the skin with at least two electrodes using PPG photoplethysmography, emitting a light beam and receiving a reflected or transmitted PPG signal;

[0049] A control module, used to transmit the collected PPG signal to the host for analysis through closed-loop control;

[0050] The treatment module is used to control the electric pulse module to generate corresponding current pulses according to the analysis results, and act on the skin through electrodes to perform blood pressure treatment;

[0051] The confirmation module is used to collect PPG signals again using PPG photoplethysmography after treatment to confirm the treatment effect.

[0052] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation method in the above-mentioned first aspect.

[0053] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any one of the implementations in the first aspect above is implemented.

[0054] The above-mentioned embodiments of the present disclosure have the following beneficial effects: Continuous blood pressure monitoring is achieved, overcoming the limitation that traditional cuff-type blood pressure monitors can only measure intermittently, and a more comprehensive understanding of the user's blood pressure changes can be obtained. A non-invasive blood pressure monitoring solution is provided, which avoids user discomfort caused by the use of a cuff and improves the comfort of measurement. Advanced PPG signal processing technology and closed-loop control systems are used to improve the accuracy and stability of blood pressure monitoring. The relationship between PPG signal features and blood pressure parameters is established through a machine learning model, which improves the accuracy of blood pressure parameter extraction, and can adapt to individual differences to meet the needs of personalized monitoring. A real-time feedback mechanism is designed, which can dynamically adjust treatment parameters according to real-time PPG signal changes to optimize treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0056] Figure 1 is a flow chart of a blood pressure monitoring method according to an embodiment of the present invention;

[0057] Figure 2 4 is a principle block diagram of a blood pressure monitoring system according to an embodiment of the present invention.

[0058] Figure 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

[0059] Figure 4 is a schematic diagram of the structure of a mobile blood pressure monitoring terminal (smart watch or wristband device) according to an embodiment of the present invention.

[0060] Figure 5 1 is a schematic diagram of the structure of a mobile blood pressure monitoring terminal (smart watch or wristband device) in a decomposed state according to an embodiment of the present invention.

[0061] Figure 6 yes Figure 5 A schematic diagram of the enlarged structure in the middle.

[0062] Figure 7 It is a schematic diagram of the pin structure used in the mobile blood pressure monitoring terminal (smart watch or wristband device) of an embodiment of the present invention.

[0063] Figure 8 It is a schematic structural diagram of an electrode mounting base and a watch strap used in a mobile blood pressure monitoring terminal (smart watch or wristband device) according to an embodiment of the present invention.

[0064] Fig. 9 yes Figure 8 Enlarged schematic diagram of the structure at point B in the middle.

[0065] Fig.10 yes Figure 8 A magnified schematic diagram of the structure in (a schematic diagram of the structure of the pin used in a smart watch or wristband device when it is inserted into the connection hole.)

[0066] Fig.11 yes Figure 8 The enlarged schematic diagram of the structure at B in the middle (smart watch or wristband device) shows the structure of the pin body after it is inserted into the connection hole and rotated. ) DETAILED DESCRIPTION

[0067] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0068] In some embodiments, the treatment process may use a mobile blood pressure monitoring terminal, which may integrate a preset sensor, an electric pulse module, a host, and electrodes. The user may receive treatment based on medical advice or automatic prompts from the device.

[0069] Preferably, the preset sensor integrates the photoelectric sensor required for PPG photoplethysmography, which is used to monitor and collect PPG signals caused by changes in vascular volume. The preset sensor is arranged on the user's wrist, and the vascular activity in these parts is closely related to changes in blood pressure. The electric pulse module is responsible for generating current pulses according to the instructions of the host. The electric pulse module contacts the user's skin through electrodes to transmit the current or voltage required for treatment. The host is responsible for receiving the PPG signal from the preset sensor, analyzing and processing it, and sending corresponding control signals to the electric pulse module based on the analysis results. The electrodes are arranged at the user's treatment area, such as the wrist or neck, to transmit the current pulses generated by the electric pulse module. The number and arrangement position of the electrodes can be adjusted according to the specific needs of the treatment.

[0070] Furthermore, the preset sensor can be connected to the host by wireless or wired means, and the collected PPG signal can be transmitted to the host for analysis. The electric pulse module is also connected to the host by wireless or wired means, and receives the control signal of the host to generate corresponding current pulses. The electrodes are directly connected to the electric pulse module to ensure that the current pulse can be accurately transmitted to the user's skin.

[0071] Figure 2 The process 100 of some embodiments of the blood pressure monitoring method according to the present disclosure is shown. The blood pressure monitoring method comprises the following steps:

[0072] Step 201, using PPG photoplethysmography to collect PPG signals by contacting a preset sensor with the skin;

[0073] In an embodiment, a blood pressure monitoring method applied to a mobile blood pressure monitoring terminal is provided, which mainly utilizes PPG (photoplethysmography) technology to continuously monitor the user's blood pressure non-invasively through a dedicated sensor module, and when necessary, transmits electrical pulses through electrodes to perform blood pressure treatment. This treatment method can be regarded as an electrical stimulation treatment, which is based on the principle that electric current can affect the bioelectric activity of the human body and induce vasodilation.

[0074] It should be clear that PPG photoplethysmography is a technology that monitors physiological parameters by detecting changes in light intensity caused by changes in blood volume. The PPG sensor can measure changes in light absorption caused by periodic changes in blood volume, which are closely related to the heart's pumping activity.

[0075] Specifically, the preset sensor can collect PPG signals by contacting the user's skin through a dedicated PPG sensor module. The preset sensor is placed on the user's wrist, finger, or other suitable monitoring site. One part of the preset sensor is responsible for emitting a light beam of a specific wavelength, while the other part is responsible for receiving the light signal reflected or transmitted back through the skin and blood vessels. Due to the periodic changes in the blood volume in the blood vessels, the light signal is modulated, so that physiological information related to heart activity can be obtained.

[0076] Furthermore, the electric pulse module generates current pulses with specific frequency, amplitude and duration according to preset treatment parameters or control instructions from the host. The therapeutic electrodes are placed in specific locations on the human body, such as the wrist, neck or feet, close to major blood vessels, to ensure that the current can be transmitted more effectively. These current pulses can stimulate vascular smooth muscle cells, causing the blood vessel walls to relax, thereby increasing the diameter of the blood vessels and reducing peripheral resistance. Due to vasodilation, the resistance encountered by the heart when pumping blood is reduced, which helps to lower blood pressure.

[0077] During the treatment, the system will continuously monitor the PPG signal or other relevant physiological parameters to evaluate the effect of the treatment and adjust the parameters of the current pulse according to the actual situation.

[0078] Preferably, PPG technology is a non-invasive method to monitor cardiovascular activity by detecting changes in light intensity caused by changes in blood volume. The electrodes mainly play a role in the treatment process, delivering current pulses to the skin to achieve the purpose of lowering blood pressure.

[0079] Step 202, transmitting the PPG signal collected by the preset sensor to the host for analysis through closed-loop control;

[0080] Preferably, closed-loop control is a control method based on a feedback mechanism, which adjusts the behavior of the system by comparing the difference between the input signal and the output signal, aiming to make the output signal as close to the expected value as possible. This control method not only generates a control signal based on the input signal, but also uses the feedback of the output signal to adjust the control strategy. The PPG signal is collected by contacting the skin with the preset sensor, and these signals are transmitted to the host for analysis through closed-loop control. This real-time signal feedback mechanism ensures the accuracy and timeliness of the data.

[0081] Preferably, the collected PPG signal can be transmitted to the host computer wirelessly or wiredly. The host computer is equipped with a high-performance microprocessor, which is responsible for preprocessing and analyzing the PPG signal. The preprocessing step includes filtering out noise, baseline correction, etc. to improve the signal-to-noise ratio of the signal. The analysis step involves time domain analysis and frequency domain analysis, and characteristic parameters related to blood pressure changes are extracted by calculating the statistical characteristics of the signal and applying methods such as fast Fourier transform (FFT).

[0082] Preferably, a photoelectric sensor is used to convert the received light intensity change into an electrical signal, and an analog-to-digital converter (ADC) is used to convert the analog electrical signal into a digital signal. The PPG signal is preprocessed, including filtering out ambient light interference, motion artifacts, and physiological noise (such as electromyographic interference).

[0083] Step 203, according to the analysis result, the host controls the electric pulse module to generate corresponding current pulses, which act on the skin through electrodes to perform blood pressure treatment;

[0084] The electric pulse module can be understood as an electronic device that can generate current pulses of specific frequency and amplitude according to a control signal.

[0085] Preferably, the electric pulse module applies current pulses of specific frequency and amplitude to the skin through electrodes according to the instructions of the host. These current pulses are dynamically adjusted according to the blood pressure condition of the user, aiming to promote blood circulation and thus help lower blood pressure. Electric pulse therapy is a non-drug treatment method that assists in regulating blood pressure through physical means.

[0086] Step 204, after the treatment, PPG signal is collected again using PPG photoplethysmography to confirm the treatment effect.

[0087] Preferably, after the treatment is completed, the PPG sensor is used again to collect PPG signals to confirm the treatment effect. The host compares the characteristic parameters of the PPG signal after treatment with the parameters before treatment to evaluate the treatment effect. If the treatment effect is not obvious, the host can adjust the treatment parameters according to the feedback and optimize the treatment plan.

[0088] Furthermore, in the above step 201, using PPG photoplethysmography to contact the skin through at least two electrodes, emitting a light beam and receiving a reflected or transmitted PPG signal includes:

[0089] Arrange at least two electrodes at preset body positions of the user to ensure that the contact between the electrodes and the skin meets the monitoring conditions;

[0090] During the electrode placement process, the user's wrist can be selected as the site for placing the electrodes because this site is rich in blood vessels and is easy to fix the device.

[0091] Preferably, at least two electrodes are placed on the wrist, one of which is used as a light source emitter and the other as a light intensity detector. The electrodes are in close contact with the skin through medical tape or a special fixing tape to ensure accurate transmission and reception of optical signals.

[0092] Preferably, first, the blood pressure monitoring terminal includes at least two electrodes, which are arranged on the wrist of the user to ensure stable contact with the skin. One electrode is used as a light source transmitter to emit a light beam of a specific wavelength, such as infrared light, and the other one or more electrodes are used as light intensity detectors to receive reflected or transmitted light signals.

[0093] A PPG signal is formed by emitting a light beam of a specific wavelength from the electrode, which penetrates the skin and is modulated by changes in blood volume in the blood vessels;

[0094] Preferably, the light source emitter electrode emits a light beam of a specific wavelength (e.g., green light or infrared light), which can penetrate the surface of the skin and reach the blood vessels. The blood volume in the blood vessels changes periodically as the heart pumps blood, causing the amount of light absorbed and scattered to change accordingly. The light detector electrode receives the reflected or transmitted light signals modulated by the blood vessel volume, and these signals undergo corresponding intensity changes as the blood vessel volume changes periodically.

[0095] The emitted light beam penetrates the surface of the skin. When the blood volume in the blood vessels changes periodically as the heart pumps blood, the amount of light absorbed and scattered by the blood vessels also changes, thereby modulating the emitted light beam. The receiving electrodes detect the light signals modulated by the changes in blood vessel volume. These signals change in intensity accordingly with the periodic changes in blood vessel volume.

[0096] Receiving a reflected or transmitted PPG signal modulated by a change in blood vessel volume, wherein the PPG signal changes in intensity corresponding to a periodic change in blood vessel volume;

[0097] It is understandable that a photoelectric sensor (such as a photodiode) is used to detect the intensity change of the PPG signal after vascular volume modulation. The photoelectric sensor converts the received light intensity change into a corresponding electrical signal, and converts the converted analog electrical signal into a processable digital signal form through an analog-to-digital converter (ADC) to prepare for subsequent digital signal processing. In applications, the received PPG signal may be very weak, so it needs to be detected by a highly sensitive photoelectric sensor. The photoelectric sensor converts the received light intensity change into an electrical signal. Since these electrical signals are in analog form, they need to be converted into digital signals through an analog-to-digital converter (ADC) to facilitate subsequent digital signal processing.

[0098] Using a photoelectric sensor to detect intensity changes of the modulated PPG signal and convert these changes into corresponding electrical signals;

[0099] The converted electrical signal is converted into a processable digital signal form through an analog-to-digital converter;

[0100] Preferably, at the digital signal processing stage, the signal is first preprocessed to improve the signal-to-noise ratio. The preprocessing step may include filtering out high-frequency noise (such as using a Gaussian filter or a median filter), removing baseline drift, and correcting for DC offset. The preprocessed PPG signal will be analyzed in the time domain to calculate its statistical characteristics, such as the mean, standard deviation, and peak value, as well as the rise time and fall time of the waveform. In order to further analyze the frequency components in the PPG signal, the signal is converted from the time domain to the frequency domain. This can be achieved through a fast Fourier transform (FFT), which can reveal the energy distribution of different frequency components in the PPG signal. In the frequency domain, frequency components related to cardiac activity can be identified, such as low-frequency components below 1 Hz, which may be associated with changes in blood pressure.

[0101] The converted digital signal is analyzed by digital signal processing algorithm to extract characteristic parameters related to blood pressure changes.

[0102] Preferably, the signal of a specific frequency band related to cardiac activity can be extracted by a frequency domain filter, eliminating the interference of other irrelevant frequency components. Envelope detection is performed on the PPG signal in the selected frequency band to extract the signal envelope of vascular volume change. In the signal envelope, characteristic points reflecting blood pressure changes, such as peaks and troughs, can be identified.

[0103] Using machine learning or statistical models, a relationship model between PPG signal features and blood pressure parameters can be established based on these feature points. Through this model, blood pressure parameters such as systolic and diastolic pressure can be calculated from the PPG signal features. In order to ensure the accuracy of the measurement results, the calculated blood pressure parameters need to be verified and calibrated. During the treatment stage, according to the blood pressure parameters obtained by analysis, the host controls the electric pulse module to generate corresponding current pulses. These current pulses act on the skin through electrodes, stimulate vascular smooth muscle, promote vasodilation, and thus help lower blood pressure. During the treatment process, the changes in the PPG signal can be monitored in real time to evaluate the treatment effect, and the parameters of the current pulse can be dynamically adjusted as needed. After the treatment is completed, the PPG signal is collected again to confirm the treatment effect. The host compares the characteristic parameters of the PPG signal after treatment with the parameters before treatment to evaluate the treatment effect. If the treatment effect is not obvious, the host can adjust the treatment parameters based on the feedback and optimize the treatment plan.

[0104] This embodiment demonstrates a method for blood pressure monitoring and treatment using PPG photoplethysmography. The method uses signal processing technology and closed-loop control to provide a comprehensive, continuous and non-invasive blood pressure monitoring and treatment solution suitable for mobile blood pressure monitoring terminals such as smart watches or wristband devices.

[0105] Furthermore, the above step of analyzing the converted digital signal by a digital signal processing algorithm to extract characteristic parameters related to blood pressure changes may also include:

[0106] Preprocessing the PPG signal includes filtering out baseline drift and high-frequency noise to improve the signal-to-noise ratio of the signal;

[0107] Preferably, the PPG signal is preprocessed, which is a critical step because it can significantly improve the signal-to-noise ratio of the signal. Preprocessing includes using a bandpass filter to filter out low-frequency and high-frequency components that are not related to physiological signals, for example, removing high-frequency noise caused by ambient light interference, and removing low-frequency baseline drift that is not related to cardiac activity through a high-pass filter.

[0108] Performing time domain analysis on the preprocessed PPG signal to calculate the statistical characteristics of the signal, wherein the statistical characteristics include the mean value, standard deviation and peak value of the signal;

[0109] Preferably, the preprocessed PPG signal is subjected to time domain analysis to calculate the statistical characteristics of the signal, including the mean value, standard deviation and peak value of the signal. The mean value provides the central trend of the signal, the standard deviation reflects the variability of the signal, and the peak value indicates the maximum amplitude of the vascular volume change.

[0110] Apply frequency domain analysis technology to convert the PPG signal after time domain analysis from time domain to frequency domain to identify the frequency components related to cardiac activity;

[0111] Preferably, a frequency domain analysis technique, such as a Fast Fourier Transform (FFT), is applied to convert the PPG signal from the time domain to the frequency domain. This conversion reveals the frequency content in the signal, which helps to identify periodic changes associated with cardiac activity.

[0112] Through the frequency domain filter, the specific frequency band related to blood pressure changes is selected to exclude the interference of other irrelevant frequency components;

[0113] Preferably, a specific frequency band related to blood pressure changes, such as 0.7-2.0 Hz, which is usually related to heart rate variability, is selected through a frequency domain filter, while interference from other non-related frequency components is excluded to improve the accuracy of blood pressure related information in the signal.

[0114] Perform envelope detection on the PPG signal in the selected frequency band to extract the signal envelope related to the periodic change of vascular volume;

[0115] Preferably, envelope detection is performed on the PPG signal within the selected frequency band, and the signal envelope related to the periodic change of the vascular volume is extracted by detecting the local maximum and minimum values ​​of the signal. Envelope detection helps to extract the signal reflecting the change of vascular volume from the modulated PPG signal.

[0116] Performing feature recognition on the signal envelope to extract feature points reflecting blood pressure changes in the PPG signal, wherein the feature points include peaks and troughs;

[0117] Preferably, feature recognition is performed on the signal envelope to extract characteristic points in the PPG signal that reflect changes in blood pressure, such as peaks and troughs. These characteristic points correspond to periodic changes in vascular volume and are key information for blood pressure monitoring.

[0118] Using a machine learning model, a relationship model between PPG signal features and blood pressure parameters is established based on the extracted feature points reflecting blood pressure changes;

[0119] Preferably, a machine learning model is used to establish a relationship model between PPG signal features and blood pressure parameters based on the extracted feature points. A machine learning model, such as a support vector machine (SVM) or a neural network, can learn the complex relationship between PPG signal features and blood pressure parameters through training.

[0120] According to the relationship model, blood pressure parameters are calculated from the PPG signal characteristics, the blood pressure parameters being systolic pressure and diastolic pressure;

[0121] Preferably, according to the established relationship model, blood pressure parameters, including systolic pressure and diastolic pressure, are calculated from the PPG signal features. These parameters are obtained by analyzing the characteristic points in the PPG signal and predicting the model.

[0122] The calculated blood pressure parameters are verified and calibrated.

[0123] Preferably, finally, the calculated blood pressure parameters are verified and calibrated to ensure the accuracy and reliability of the measurement results. This may involve comparison with the measurement results of a standard blood pressure measurement device (such as a cuff-type blood pressure monitor) and adjustment based on the user's physiological feedback.

[0124] Through the above steps, an accurate blood pressure monitoring method can be realized, which utilizes PPG signal processing technology to extract reliable information related to blood pressure changes from non-invasive sensors through a series of advanced signal processing and machine learning algorithms.

[0125] Furthermore, in combination with specific examples, a wristband device integrating a PPG sensor and an electric pulse therapy module is used to monitor the user's blood pressure in real time and provide treatment when necessary.

[0126] Take a 45-year-old middle-aged user as an example. He wears this wristband device while doing daily activities. The wristband device first collects the PPG signal, which contains information about the changes in blood vessel volume caused by the heart pumping blood. The signal may contain noise due to factors such as user movement and ambient light. The wristband device uses a bandpass filter with a pass frequency range set to 0.5Hz to 5Hz to filter out non-physiological noise components such as motion artifacts and ambient light interference. The pre-processed PPG signal is used to calculate time domain statistical features. For example, during a stable breathing cycle, the wristband device calculates the average intensity, standard deviation, and peak value of the PPG waveform. The average intensity may be 0.5V, the standard deviation is 0.1V, and the peak intensity is 0.7V.

[0127] Next, the wristband device performs a fast Fourier transform (FFT) on the PPG signal to obtain a spectrum. In the spectrum, the wristband device identifies a frequency peak related to the heart rate, assumed to be 1.2Hz, which corresponds to the user's heart rate. In addition, the wristband device also identifies a lower frequency peak of approximately 0.08Hz, which may be related to the periodic changes in blood pressure. The wristband device performs an inverse FFT on the result after FFT to obtain a clear time waveform and performs envelope detection. By identifying the rising and falling edges of the waveform, the wristband device extracts the envelope of the vascular volume change. On the envelope curve, the wristband device detects obvious peaks and troughs, and these feature points are synchronized with the user's heartbeat cycle.

[0128] Using a large amount of user data collected previously, the machine learning model in the wristband device has been trained to predict blood pressure parameters based on the PPG signal feature points. For example, the model may learn that there is a certain mathematical relationship between the PPG peak and the diastolic pressure. Based on the real-time extracted PPG peaks and troughs, the wristband device calculates the current systolic blood pressure to be 120mmHg and the diastolic blood pressure to be 80mmHg. To ensure the accuracy of the measurement results, the wristband device compares these calculated blood pressure parameters with the pre-set calibration values. If there is a deviation, the wristband device adjusts the result according to the built-in calibration algorithm to improve the accuracy of the measurement.

[0129] If the calculated blood pressure value is outside the normal range, the electrical pulse module of the wristband device will be activated. According to the user's blood pressure condition, the wristband device generates a series of current pulses, which act on the user's wrist through electrodes. The frequency and intensity of the current pulses are dynamically adjusted according to the feedback of the closed-loop control system to achieve the best treatment effect. After a period of treatment, the wristband device collects the PPG signal again and repeats the above signal processing steps to evaluate the treatment effect. If the blood pressure value has returned to the normal range, the electrical pulse treatment will be stopped. Otherwise, the wristband device will continue to adjust the treatment parameters until the ideal treatment effect is achieved.

[0130] The above example shows how to use PPG photoplethysmography and electric pulse therapy modules to achieve real-time monitoring and treatment of blood pressure on a mobile blood pressure monitoring terminal. This method combines advanced signal processing technology and machine learning algorithms to provide a non-invasive, high-precision blood pressure monitoring solution.

[0131] Furthermore, the above method further comprises: dynamically adjusting the frequency and amplitude of the current pulse generated by the electric pulse module according to the change trend of the blood pressure parameter;

[0132] Preferably, the monitoring terminal extracts blood pressure characteristic parameters, such as systolic pressure and diastolic pressure, through the PPG signal processing algorithm. By analyzing the changing trend of these parameters over time, the monitoring terminal can determine whether the user's blood pressure is in a stable state or whether there is a risk of hypertension.

[0133] If the monitored blood pressure parameters show an upward trend, it indicates that the user may need therapeutic intervention. The control unit of the electric pulse module will adjust the frequency and amplitude of the current pulse according to the preset treatment logic. For example, if the systolic blood pressure continues to rise, the control unit may increase the frequency of the current pulse to promote vasodilation.

[0134] The adjustment of treatment parameters is not a single process, but a closed-loop feedback process. After the pulse generated by the current pulse module acts on the skin through the electrode, the monitoring terminal will collect the PPG signal again to monitor the treatment effect in real time.

[0135] Real-time monitoring of PPG signal changes during treatment to evaluate the effectiveness of current blood pressure parameters;

[0136] Preferably, during the treatment process, the monitoring terminal will not stop collecting PPG signals, but will continue to collect PPG signals at certain time intervals (such as every second or every minute). Using the collected PPG signals, the monitoring terminal performs signal processing again to extract blood pressure characteristic parameters. The treatment effect is evaluated by comparing the changes in blood pressure parameters before and after treatment. The monitoring terminal is provided with preset blood pressure thresholds. When the real-time monitored blood pressure parameters reach or exceed these thresholds, the monitoring terminal will automatically trigger the adjustment of the treatment parameters.

[0137] Through user feedback or automatic threshold judgment, the adjustment of blood pressure parameters is triggered to optimize the treatment effect.

[0138] Preferably, in addition to the automatic threshold judgment, the monitoring terminal can also receive direct feedback from the user. The user can report comfort or any discomfort during the treatment process by interacting with the monitoring terminal (such as pressing a button or through a smartphone application). Based on user feedback and automatic threshold judgment, the control software of the monitoring terminal will make a logical judgment to decide whether the treatment parameters need to be adjusted. If the user reports discomfort or the treatment effect is not good, the monitoring terminal may reduce the amplitude of the current pulse or adjust the pulse frequency. The monitoring terminal also has the ability of long-term trend analysis and can store and analyze the user's historical blood pressure data and treatment records. Through machine learning algorithms, the monitoring terminal can learn the user's response pattern to treatment, thereby providing a more personalized treatment plan in future treatments. In some cases, the monitoring terminal may suggest that the user consult a doctor. For example, if the user's blood pressure continues to be high, the monitoring terminal will remind the user to seek professional medical advice.

[0139] Through the above steps, a blood pressure monitoring method is shown that can dynamically adjust treatment parameters according to the user's blood pressure change trend and monitor the treatment effect in real time. This method can not only provide timely treatment, but also automatically optimize the treatment plan according to the user's feedback and blood pressure changes, thereby improving the safety and effectiveness of the treatment.

[0140] Furthermore, preprocessing the PPG signal in the above method may also include:

[0141] Apply a Gaussian filter or a median filter to remove high-frequency noise from the PPG signal;

[0142] Preferably, the application of the Gaussian filter requires applying a Gaussian filter to the original PPG signal to remove high-frequency noise. The Gaussian filter is a smoothing filter that reduces the noise level by reducing the high-frequency components in the signal. The bandwidth of the Gaussian filter is selected based on the main frequency components of the PPG signal, usually excluding high-frequency noise above 1Hz.

[0143] In addition to the Gaussian filter, a median filter can be used to further remove high-frequency noise from the PPG signal. The median filter reduces spike noise and salt noise by replacing the value of each point with the median value within its neighborhood, which is a nonlinear filtering method that is more robust to sudden signal changes.

[0144] In order to remove low-frequency trends in the PPG signal, such as baseline drift caused by the user's body movement, a low-pass filter is used. This filter allows low-frequency signal components to pass while suppressing signals above a certain cutoff frequency. The cutoff frequency of the low-pass filter is usually set below the heart's pumping frequency, for example, below 1Hz.

[0145] Use a low-pass filter to remove low-frequency trends below the heart's pumping frequency;

[0146] Preferably, for the identification of DC offset, in the PPG signal, DC offset manifests itself as non-physiological level changes in the signal, which may be caused by slight changes in the sensor position or changes in ambient light. To correct for DC offset, a baseline correction technique can be used. This technique ensures baseline stability of the PPG signal by calculating the mean or median of the signal and subtracting this value from the entire signal. In some cases, the PPG signal can also be normalized to keep its amplitude within a fixed range, such as between -1 and 1. This helps consistency and repeatability in subsequent signal analysis steps.

[0147] Perform DC offset correction on the PPG signal to ensure the baseline stability of the signal.

[0148] Preferably, the filter parameters in the preprocessing step (such as the standard deviation of the Gaussian filter, the window size of the median filter, and the cutoff frequency of the low-pass filter) can be automatically adjusted according to the characteristics of the PPG signal to adapt to the physiological characteristics and environmental conditions of different users. The preprocessing step needs to be completed in real time or near real time to ensure that the monitoring terminal can respond to the user's blood pressure changes in a timely manner. The preprocessing algorithm is usually implemented in software on the microprocessor of the monitoring terminal, which requires the algorithm to have efficient computing performance and low latency characteristics.

[0149] The above method provides high-quality PPG signals for subsequent signal analysis and feature extraction by removing high-frequency noise, filtering low-frequency trends, and correcting DC offsets. These preprocessing steps are essential to improving the accuracy and reliability of blood pressure monitoring.

[0150] Furthermore, the time domain analysis of the preprocessed PPG signal in the above steps further includes:

[0151] Calculate the maximum and minimum values ​​of the PPG signal within a time interval to determine the amplitude of the vascular volume change;

[0152] Preferably, the preprocessed PPG signal will show fluctuations that vary with the heart's pumping cycle. During each heartbeat cycle, the maximum value (usually corresponding to the maximum point of vascular volume) and the minimum value (corresponding to the minimum point of vascular volume) of the PPG waveform are identified. The magnitude of vascular volume change is quantified by calculating the difference between the maximum and minimum values ​​of the PPG waveform during consecutive heartbeat cycles. This difference reflects the increase or decrease in vascular volume during each heartbeat.

[0153] Measure the rise time and fall time of the PPG signal waveform to evaluate the vascular response speed;

[0154] Preferably, in a PPG waveform, the rise time refers to the duration from the minimum value to the maximum value of the waveform, and the fall time refers to the time from the maximum value back to the minimum value. These time parameters can be measured by determining the location of the inflection point in the waveform. The rise time and fall time are related to how fast the blood vessels respond to the heart pumping blood. Changes in the speed of blood vessel response may indicate the health of the blood vessels and the ability to regulate blood pressure.

[0155] Through time series analysis, periodic patterns in PPG signals are identified and compared with preset heart activity cycles.

[0156] Preferably, identifying a periodic pattern in a PPG signal may specifically include:

[0157] 1. Time series analysis: Perform time series analysis on the PPG signal to identify periodic patterns. This usually involves sliding window processing of the signal and calculating statistics such as the mean and standard deviation within the window.

[0158] 2. Comparison of cardiac activity cycles: The periodic pattern in the PPG signal is compared with a preset cardiac activity cycle, which can be an average heart rate based on demographic data or a historical average heart rate for the user.

[0159] 3. Evaluation of heart rate variability: By analyzing the periodic changes of PPG signals, heart rate variability (HRV) can be evaluated, which is an important indicator of the activity of the cardiac autonomic nervous system.

[0160] 4. Signal quality assessment: When performing time domain analysis, the quality of the PPG signal also needs to be assessed to ensure the accuracy of the analysis results. The assessment of signal quality can be based on criteria such as the signal-to-noise ratio and the clarity of the waveform.

[0161] 5. Real-time and automation: The above time domain analysis steps need to be completed automatically under real-time or near real-time conditions to monitor the user's blood pressure changes in a timely manner and provide accurate data support for subsequent blood pressure parameter calculations and treatments.

[0162] 6. Software implementation and algorithm optimization: The algorithm of time domain analysis is usually implemented in software on the microprocessor of the monitoring terminal, which requires the algorithm to have efficient computing performance and low latency. In addition, the algorithm needs to be optimized for different types of users and environmental conditions to improve its robustness and adaptability.

[0163] Through the above steps, a method for time domain analysis of preprocessed PPG signals is shown, which can accurately evaluate the amplitude of vascular volume changes, vascular response speed, and identify periodic patterns in PPG signals, providing important time domain characteristic parameters for blood pressure monitoring. These parameters are crucial for accurate monitoring and treatment of blood pressure.

[0164] Furthermore, the above-mentioned step of applying frequency domain analysis technology to convert the PPG signal after time domain analysis from the time domain to the frequency domain to identify the frequency components related to cardiac activity includes:

[0165] Perform fast Fourier transform on the PPG signal to obtain a PPG signal spectrum diagram;

[0166] Preferably, the fast Fourier transform (FFT) processing may include the following specific steps:

[0167] Signal segmentation: First, the PPG signal is divided into data blocks of multiple time periods. The length of each data block is usually a fixed value, such as 4 seconds or 8 seconds, to ensure a balance between frequency resolution and time resolution.

[0168] Window function: Before taking the FFT of each data block, apply a window function, such as a Hanning window or a Hamming window, to reduce spectral leakage. The window function helps reduce interference between different frequency bands by gradually reducing the signal amplitude at the beginning and end of the data block.

[0169] FFT calculation: Perform FFT on each windowed data block to convert the time domain signal into a frequency domain signal. The result of FFT is a series of complex numbers of frequency components, each of which contains amplitude and phase information.

[0170] identifying a peak frequency in the PPG signal spectrogram, the peak frequency corresponding to the pumping frequency of the heart;

[0171] Preferably, spectrogram drawing can be understood as drawing the result of FFT into a spectrogram, with the horizontal axis representing frequency and the vertical axis representing the amplitude of each frequency component. The spectrogram can be linear or logarithmic to better show the distribution of frequency components. In the spectrogram, the peak frequency corresponding to the heart's pumping frequency is identified. These peaks are usually in the range of 1-4Hz and are related to heart rate variability (HRV).

[0172] Apply a bandpass filter to extract the signal components corresponding to the frequency of cardiac activity;

[0173] In this embodiment, a bandpass filter may be selected, and its transmission frequency range is set to the main frequency band of cardiac activity, such as 0.7-2.0 Hz. This range covers the main frequency components related to cardiac activity.

[0174] Apply a bandpass filter to the spectrum of the PPG signal to extract the signal components corresponding to the frequency of cardiac activity. Filter out signals in non-target frequency bands, such as high-frequency noise above 2.0 Hz or low-frequency baseline drift below 0.7 Hz.

[0175] By calculating the power of signals in different frequency ranges in the PPG signal spectrum diagram, the energy of different frequency components in the PPG signal is quantified.

[0176] Calculate the power of each frequency component in the PPG signal spectrogram. The power can be obtained by taking the square of the modulus length of the FFT result, integrating the power within the selected frequency band, and quantifying the energy of different frequency components in the PPG signal. This can be achieved by summing the bandpass filtered spectrogram over a specific frequency range. For ease of comparison and analysis, the quantized energy values ​​are normalized so that their sum is 1 or another fixed value. Extract features related to blood pressure changes from the power spectrum, such as peak frequency, energy ratio of frequency bands, slope of the power spectrum, etc. Train a machine learning model using the extracted frequency domain features to establish the relationship between PPG signal features and blood pressure parameters.

[0177] The above steps can be used to convert PPG signals from the time domain to the frequency domain and identify frequency components related to cardiac activity. In addition, it also provides methods for quantifying the energy of these components and further analyzing blood pressure parameters through machine learning models. These steps provide rich frequency domain feature parameters for blood pressure monitoring, which helps to improve the accuracy and reliability of monitoring.

[0178] Further, the blood pressure detection method disclosed in this embodiment is combined with a wristband device for illustration. The user wears a thin wristband device equipped with a PPG sensor. The wristband is comfortably fixed on the user's wrist, and the PPG sensor is located on the inner side of the wristband, close to the skin. The sensor includes a pair of electrodes for transmitting and receiving light signals. The transmitting electrode emits a light beam of a specific wavelength, which penetrates the skin and is modulated by the change in blood volume in the blood vessels. The receiving electrode detects the reflected or transmitted PPG signals, which change with the periodic change of the blood vessel volume. The microprocessor built into the wristband device preprocesses the raw PPG signal. First, a Gaussian filter is used to remove high-frequency noise caused by user movement or ambient light changes. A low-pass filter is applied to filter out low-frequency baseline drift caused by changes in body temperature. Finally, a DC offset correction is performed to ensure the baseline stability of the PPG signal. In the time domain, the wristband device analyzes the maximum and minimum values ​​of the PPG signal within a heartbeat cycle to determine the amplitude of the blood vessel volume change.

[0179] For example, in a calm environment, the device measures the maximum value of the PPG signal to be 1.5V and the minimum value to be 0.3V. At the same time, the device measures the rise time and fall time of the waveform, which are 0.45 seconds and 0.4 seconds respectively, to evaluate the response speed of the blood vessels. Through time series analysis, the device identifies the periodic pattern of the PPG signal and compares it with the preset heart activity cycle of an average heart rate of 60 beats per minute.

[0180] Preferably, the wristband device performs a fast Fourier transform (FFT) on the PPG signal to obtain a spectrum diagram of the PPG signal. In the spectrum diagram, the device identifies the peak frequency corresponding to the heart's pumping frequency, which is assumed to be 1.25Hz. The device then applies a bandpass filter to extract signal components in the frequency range of 0.7Hz to 2.0Hz to exclude interference from other frequency components. Through envelope detection, the wristband device extracts the signal envelope of the periodic change of vascular volume from the bandpass filtered signal and identifies the peaks and troughs in the PPG signal. These feature points are used to train a machine learning model to establish a relationship model between PPG signal features and blood pressure parameters. Using the machine learning model, the wristband device calculates blood pressure parameters such as systolic and diastolic pressure from the PPG signal features. For example, the model may predict that the current systolic pressure is 125mmHg and the diastolic pressure is 85mmHg.

[0181] If the user is in a state of high blood pressure, the wristband device's electrical pulse module will generate current pulses based on the PPG signal characteristics, which will act on the skin through electrodes to lower blood pressure. After treatment, the wristband device will collect PPG signals again and evaluate the treatment effect by comparing the changes in blood pressure parameters before and after treatment. If necessary, the wristband device will dynamically adjust the frequency and amplitude of the electrical pulses based on the user's real-time PPG signal changes or feedback to optimize the treatment effect.

[0182] Through the above examples, a closed-loop blood pressure monitoring method is developed that integrates PPG signal acquisition, preprocessing, time domain and frequency domain analysis, feature extraction, blood pressure parameter calculation, treatment effect evaluation and adjustment. This method can achieve continuous and real-time monitoring and treatment of the user's blood pressure on a wristband device, and is suitable for users who need to monitor their blood pressure for a long time.

[0183] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the method allows the mobile blood pressure monitoring terminal to perform continuous blood pressure monitoring instead of traditional intermittent measurement, providing users with more comprehensive blood pressure change information. Through PPG photoplethysmography, the method avoids the discomfort that may be caused by using a cuff-type blood pressure monitor, and provides a non-invasive, user-friendly blood pressure monitoring method. The closed-loop control system can dynamically adjust the electric pulse treatment parameters according to the real-time PPG signal analysis results, providing a personalized and adaptive treatment method, which helps to improve the treatment effect. By adopting pre-processing techniques such as Gaussian filter, median filter, low-pass filter and DC offset correction, the quality of the PPG signal is improved, thereby improving the accuracy of blood pressure parameter extraction. Combined with time domain analysis and frequency domain analysis, the method can extract richer feature parameters from the PPG signal, improving the reliability and accuracy of blood pressure monitoring. Using a machine learning model, a relationship model between PPG signal features and blood pressure parameters can be established based on the user's unique physiological characteristics, further improving the accuracy of blood pressure parameter calculation.

[0184] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a blood pressure monitoring method system. These device embodiments are similar to Figure 2 Corresponding to the method embodiment shown, the blood pressure monitoring system can be specifically applied to various electronic devices. Figure 2 As shown, a blood pressure monitoring system 300 of some embodiments includes:

[0185] A receiving module 301 is used for using PPG photoplethysmography to contact the skin through at least two electrodes, emitting a light beam and receiving a reflected or transmitted PPG signal;

[0186] A control module 302 is used to transmit the collected PPG signal to the host for analysis through closed-loop control;

[0187] The treatment module 303 is used for controlling the electric pulse module to generate corresponding current pulses according to the analysis results, and applying the current pulses to the skin through electrodes to perform blood pressure treatment;

[0188] The confirmation module 304 is used to collect PPG signals again using PPG photoplethysmography after treatment to confirm the treatment effect.

[0189] It is understandable that the modules described in the blood pressure monitoring system 300 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the blood pressure monitoring method are also applicable to the blood pressure monitoring system 300 and the modules included therein, and will not be described in detail here.

[0190] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 400 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0191] like Figure 3 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0192] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0193] It should be noted that when using the mobile blood pressure monitoring terminal of the present invention, since the electrode is a consumable, its service life is limited. As the use time increases, the electrode may be worn, aged, etc., which will directly affect the use effect. Therefore, the electrode can also be configured with a life monitoring module, which can specifically include:

[0194] The electrode impedance monitoring module determines the performance status by regularly measuring the impedance value of the electrode. A significant increase in impedance may mean that the electrode is aging or damaged.

[0195] After an electrode is installed or replaced, its initial impedance value is first recorded as a baseline. Subsequently, a small current is periodically sent through the electrode during use, and the current impedance value is measured. This value is compared with the initial impedance value. If the impedance increases significantly, it may mean that physical changes have occurred on the electrode surface, such as corrosion or oxidation. At this time, the system will issue a warning, prompting the user to check the electrode status and consider replacement.

[0196] Electrode surface status detection module: Use optical sensors to regularly check the electrode surface and identify the degree of wear. The wear of the electrode surface will directly affect its conductivity and treatment effect.

[0197] Optical sensors are used to regularly check the electrode surface to identify the degree of wear. When the electrode is just installed or replaced, the sensor is used to capture the initial state of the electrode surface. After that, before each use or at regular intervals, the image of the electrode surface is captured again and compared using image processing technology to identify any wear, scratches or corrosion. Based on the degree of wear, the system determines whether the electrode needs to be replaced to ensure that its conductivity and treatment effect are not affected.

[0198] Feedback on treatment effect: By comparing blood pressure parameters before and after, the performance of the electrode can be indirectly evaluated. If the treatment effect is significantly reduced, it may be a sign of electrode aging.

[0199] Electrode performance can be indirectly evaluated by comparing blood pressure parameters before and after treatment. The patient's blood pressure is measured and recorded before and after treatment. If the treatment effect is significantly reduced, that is, the blood pressure does not improve significantly after treatment, this may be a sign of reduced electrode performance. At this time, the system will consider the impact of electrode aging on the treatment effect and prompt the user to perform corresponding checks.

[0200] Electrode temperature monitoring: A temperature sensor is installed near the electrode to monitor the working temperature in real time. Abnormal temperature changes can indicate that the electrode performance is degraded or there is a safety hazard.

[0201] By placing a temperature sensor near the electrode, its operating temperature can be monitored in real time. This monitoring continuously collects and records the temperature data of the electrode. If abnormal temperature changes are observed, such as a sudden increase or decrease in temperature, this may indicate that the electrode performance has deteriorated or there is a safety hazard. In this case, the system will immediately issue a warning, prompting the user to check the electrode to ensure safety of use.

[0202] Figure 4-11 A structural schematic diagram of a mobile blood pressure monitoring terminal according to the present disclosure is shown. In this embodiment, a blood pressure monitoring method using PPG photoplethysmography is provided, and the method is applied to a mobile blood pressure monitoring terminal, such as a smart watch or a wristband device.

[0203] The smart watch or wristband device in this example has a detachable / replaceable electrode mounting structure to enable replacement of electrodes.

[0204] The present invention comprises an electrode mounting seat 2 and an electrode 3 arranged on the inner side thereof; wherein the electrode mounting seat 2 is detachably assembled in the receiving groove 1.1 through a connecting assembly, and the electrode mounting seat 2 is made of an elastic material (such as silicone), and after being connected to the strap 1, has the performance of synchronously bending with the strap 1; the electrode 3 which fits the human skin is arranged on the inner side of the electrode mounting seat 2; wherein the four corners of the electrode mounting seat 2 are respectively provided with connecting holes 4, and the corresponding positions on the strap 1 at the bottom of the receiving groove 1.1 are also provided with connecting holes 4 The connecting hole 4 is composed of a first semicircular hole 4.1 and a second semicircular hole 4.2 which are opposite to each other and whose diameters overlap and whose center positions are staggered. A guide groove 4.11 is arranged on the inner wall of the first semicircular hole 4.1 along the hole. An arc groove 4.12 is arranged at the top of the first semicircular hole 4.1 on the electrode mounting seat 2. The arc groove 4.12 is coaxially arranged with the first semicircular hole 4.1. The front end of the arc groove 4.12 is connected with the guide groove 4.11, and the tail end of the arc groove 4.12 is provided with a blind groove 4.13 opened toward the bottom.

[0205] The connecting assembly includes a pin body 5, the pin body 5 has a first peripheral surface 5.1 adapted to the inner wall of the first semicircular hole 4.1, and a second peripheral surface (similar to the eccentric structure of the cam) adapted to the second semicircular hole 4.2, Figure 7 In the figure, the red line indicates the minimum diameter of the pin body 5, and the green line indicates the maximum diameter of the pin body 5; a positioning block 5.11 is also provided at the front end of the first circumferential surface 5.1; when assembling the electrode mounting seat 2, first place the electrode mounting seat 2 in the accommodating groove 1.1, and align the connecting hole 4 on the electrode mounting seat 2 with the connecting hole 4 on the strap 1 (the inner wall of the first semicircular hole 4.1 on the electrode mounting seat 2 coincides with the wall of the first semicircular hole 4.1 on the strap 1, and the inner wall of the second semicircular hole 4.2 on the electrode mounting seat 2 coincides with the wall of the second semicircular hole 4.2 on the strap 1); place the pin body 5 below the strap 1, and adjust it so that the first circumferential surface 5.1 coincides with the wall of the first semicircular hole 4.1, the second circumferential surface coincides with the wall of the second semicircular hole 4.2, and the positioning block 5.11 coincides with the wall of the guide groove 4.11; pass the head of the pin body 5 through the strap 1 and enter the electrode mounting The pin body 5 is placed in the seat 2, and the pin body 5 continues to move upward, so that the positioning block 5.11 of the head enters the side of the arc groove 4.12; the pin body 5 is rotated, so that the positioning block 5.11 moves along the arc groove 4.12 to the blind groove 4.13. In this process, the first circumferential surface 5.1 and the second circumferential surface 5.2 of the pin body 5 form a cam structure; because the electrode mounting seat 2 has a certain elasticity, when the pin body 5 rotates, the large-diameter circumferential surface gradually contacts the inner wall of the connecting hole 4, which causes the connecting hole 4 to expand, and forms an interference fit with the connecting hole 4 to lock the pin body 5. After the first circumferential surface 5.1 of the pin body 5 rotates, the first semicircular hole 4.1 expands, and the second circumferential surface 5.2 drives the second semicircular hole 4.2 to expand after the rotation, and the first semicircular hole 4.1 is tightly attached to the first circumferential surface 5.1 after expansion, and the second semicircular hole 4.2 is tightly attached to the second circumferential surface 5.2 after expansion, so that the pin body 5 is locked;

[0206] The first circumferential surface 5.1, the second circumferential surface 5.2, the inner wall of the first semicircular hole 4.1, and the inner wall of the second semicircular hole 4.2 may be provided with some structures to increase friction (such as anti-skid patterns, anti-skid materials, etc.), so that the pin body 5 can be locked more reliably; after the positioning block 5.11 enters the blind groove 4.13, it can fit with the blind groove 4.13, further locking the pin body 5 to prevent it from rotating. The electrode mounting seat 2 is firmly connected to the strap 1 through the pin body 5.

[0207] After the pin body 5 is reversed, the first semicircular hole 4.1 and the second semicircular hole 4.2 are reset, and the positioning block 5.11 is located in the guide groove 4.11. The electrode mounting seat 2 can be removed by pulling out the pin body 5 to replace the electrode.

[0208] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0209] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The units described may also be provided in a processor, and the functions described above herein may be performed at least in part by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0210] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A blood pressure monitoring system, characterized in that: include: A receiving module, used for collecting PPG signals by contacting the skin with a preset sensor using PPG photoplethysmography; Arranging the preset sensor at a preset body position of the user, ensuring that the contact between the preset sensor and the skin meets the monitoring condition; A PPG signal is formed by emitting a light beam of a specific wavelength, which penetrates the skin and is modulated by changes in blood volume in the blood vessels; Receiving a reflected or transmitted PPG signal modulated by a change in blood vessel volume, wherein the PPG signal changes in intensity corresponding to a periodic change in blood vessel volume; Using detection of intensity changes of the modulated PPG signal and converting these changes into corresponding electrical signals; The converted electrical signal is converted into a processable digital signal form through an analog-to-digital converter; The converted digital signal is analyzed by a digital signal processing algorithm to extract characteristic parameters related to blood pressure changes; The analysis of the converted digital signal by a digital signal processing algorithm to extract characteristic parameters related to blood pressure changes includes: Preprocessing the PPG signal includes filtering out baseline drift and high-frequency noise to improve the signal-to-noise ratio of the signal; Performing time domain analysis on the preprocessed PPG signal to calculate the statistical characteristics of the signal, wherein the statistical characteristics include the mean value, standard deviation and peak value of the signal; Apply frequency domain analysis technology to convert the PPG signal after time domain analysis from time domain to frequency domain to identify the frequency components related to cardiac activity; Through the frequency domain filter, the specific frequency band related to blood pressure changes is selected to exclude the interference of other irrelevant frequency components; Perform envelope detection on the PPG signal in the selected frequency band to extract the signal envelope related to the periodic change of vascular volume; Performing feature recognition on the signal envelope to extract feature points reflecting blood pressure changes in the PPG signal, wherein the feature points include peaks and troughs; Using a machine learning model, a relationship model between PPG signal features and blood pressure parameters is established based on the extracted feature points reflecting blood pressure changes; According to the relationship model, blood pressure parameters are calculated from the PPG signal characteristics, the blood pressure parameters being systolic pressure and diastolic pressure; Verifying and calibrating the calculated blood pressure parameters; A control module, used for transmitting the PPG signal collected by the preset sensor to the host for analysis through closed-loop control; The treatment module is used to generate corresponding current pulses according to the analysis results, and act on the skin through electrodes to perform blood pressure treatment; The confirmation module is used to collect PPG signals again through the preset sensor using PPG photoplethysmography after treatment to confirm the treatment effect.

2. A blood pressure monitoring system according to claim 1, characterized in that: The system further comprises: Dynamically adjusting the frequency and amplitude of the current pulses generated by the electric pulse module according to the change trend of the blood pressure parameters; Real-time monitoring of PPG signal changes during treatment to evaluate the effectiveness of current blood pressure parameters; Through user feedback or automatic threshold judgment, the adjustment of blood pressure parameters is triggered to optimize the treatment effect.

3. A blood pressure monitoring system according to claim 1, characterized in that: The preprocessing of the PPG signal further comprises: Apply a Gaussian filter or a median filter to remove high-frequency noise from the PPG signal; Use a low-pass filter to remove low-frequency trends below the heart's pumping frequency; Perform DC offset correction on the PPG signal to ensure the baseline stability of the signal.

4. A blood pressure monitoring system according to claim 1, characterized in that: The time domain analysis of the pre-processed PPG signal further comprises: Calculate the maximum and minimum values ​​of the PPG signal within a time interval to determine the amplitude of the vascular volume change; Measure the rise time and fall time of the PPG signal waveform to evaluate the vascular response speed; Through time series analysis, periodic patterns in PPG signals are identified and compared with preset heart activity cycles.

5. A blood pressure monitoring system according to claim 1, characterized in that: The application of frequency domain analysis technology to convert the PPG signal after time domain analysis from the time domain to the frequency domain to identify the frequency components related to cardiac activity includes: Perform fast Fourier transform on the PPG signal to obtain a PPG signal spectrum diagram; identifying a peak frequency in the PPG signal spectrogram, the peak frequency corresponding to the pumping frequency of the heart; Apply a bandpass filter to extract the signal components corresponding to the frequency of cardiac activity; By calculating the power of signals in different frequency ranges in the PPG signal spectrum diagram, the energy of different frequency components in the PPG signal is quantified.

6. A blood pressure monitoring system according to claim 1, characterized in that: include: The electrode impedance monitoring module measures the electrode impedance value regularly and uses the initial impedance value as a benchmark to determine the electrode performance status. The electrode surface status detection module uses optical sensors to regularly check the electrode surface and identify its degree of wear. Based on the degree of wear, the system determines whether the electrode needs to be replaced to ensure that its conductivity and treatment effect are not affected. The electrode temperature monitoring module monitors the working temperature in real time by setting a temperature sensor near the electrode.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the system according to any one of claims 1 to 6.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the system according to any one of claims 1 to 7.

Images