Medical-level VSM dynamic monitoring system and method

Abstract

The invention discloses a medical-level VSM dynamic monitoring system and method, and relates to the technical field of vital sign monitoring, and the system is characterized in that a data processing module is connected with an inertial measurement module and a display and interaction module; the power management module is respectively connected with the inertial measurement module, the data processing module and the display and interaction module; the display and interaction module is used for acquiring basic information of a to-be-monitored user; the sensing module is used for measuring vital sign signals and sending the vital sign signals to the data processing module; the inertia measurement module is used for measuring inertia signals and sending the inertia signals to the data processing module; the data processing module is used for acquiring vital sign parameters of the to-be-monitored user according to the inertial signal and the vital sign signal, acquiring vital sign standard parameters according to the basic information and the inertial signal, and comparing the vital sign parameters with the vital sign standard parameters to generate a monitoring report; and sending the monitoring report to the display and interaction module to output the monitoring report. The security of the personal information of the user can be protected.

Description

Technical Field

[0001] The present application relates to the technical field of vital sign monitoring, and particularly to a medical-grade VSM dynamic monitoring system and method. Background Art

[0002] With the development of society and the continuous improvement of people's health awareness, the demand for medical and health services is increasing and becoming more diversified.

[0003] Traditional vital sign monitoring mainly relies on patients going to medical institutions for manual measurement by professional medical staff at specific times and locations. However, for patients with chronic diseases who need long-term vital sign monitoring, frequent trips to the hospital not only consume time and energy but may also affect the timeliness and continuity of monitoring due to factors such as transportation and queuing.

[0004] With the advent of various miniaturized, high-precision and wearable sensors and the development of communication technologies, remote vital sign monitoring technology has emerged. It enables patients to continuously monitor their vital signs in daily life scenarios and then send them to the medical information management system set up in the hospital through the network. Medical staff can remotely and real-time obtain the vital sign data of patients through the medical information management system, thereby realizing services such as remote diagnosis, treatment plan adjustment, and health guidance.

[0005] However, in the remote vital sign monitoring technology, the vital sign data of users faces the risk of being hacked and leaked during the transmission process. Once a data leakage event occurs, it will cause great damage to the privacy of patients. Summary of the Invention

[0006] The purpose of the present application is to provide a medical-grade VSM dynamic monitoring system and method that can protect the security of user personal information.

[0007] To achieve the above purpose, the present application provides the following solutions:

[0008] In the first aspect, the present application provides a medical-grade VSM dynamic monitoring system, and the medical-grade VSM dynamic monitoring system includes: a sensing module, an inertial measurement module, a data processing module, a display and interaction module, an early warning and prompt module, and a power management module;

[0009] The data processing module is respectively connected to the inertial measurement module and the display and interaction module; the power management module is respectively connected to the inertial measurement module, the data processing module, and the display and interaction module;

[0010] The display and interaction module is used to obtain the basic information of the user to be monitored, and the basic information includes: age, gender, height, weight, altitude, and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring;

[0011] The sensing module is used to measure the vital sign signals and send the vital sign signals to the data processing module;

[0012] The inertial measurement module is used to measure the inertial signals and send the inertial signals to the data processing module;

[0013] The data processing module is used to obtain the vital sign parameters of the user to be monitored according to the inertial signals and the vital sign signals, obtain the vital sign standard parameters according to the basic information and the inertial signals, compare the vital sign parameters with the vital sign standard parameters, generate a monitoring report according to the comparison result, and send the monitoring report to the display and interaction module;

[0014] The display and interaction module is further used to output the monitoring report.

[0015] In a second aspect, the present application provides a medical-grade VSM dynamic monitoring method, which is applied to the medical-grade VSM dynamic monitoring system as described in the first aspect. The medical-grade VSM dynamic monitoring system includes: a sensing module, an inertial measurement module, a data processing module, a display and interaction module, an early warning prompt module, and a power management module. The data processing module is respectively connected to the inertial measurement module and the display and interaction module; the power management module is respectively connected to the inertial measurement module, the data processing module, and the display and interaction module. The method includes:

[0016] The display and interaction module obtains the basic information of the user to be monitored, and the basic information includes: age, gender, height, weight, altitude, and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring;

[0017] The sensing module measures the vital sign signals and sends the vital sign signals to the data processing module;

[0018] The inertial measurement module measures the inertial signals and sends the inertial signals to the data processing module;

[0019] The data processing module obtains the vital sign parameters of the user to be monitored according to the inertial signal and the vital sign signal, obtains the standard vital sign parameters according to the basic information and the inertial signal, compares the vital sign parameters with the standard vital sign parameters, generates a monitoring report according to the comparison result, and sends the monitoring report to the display and interaction module;

[0020] The display and interaction module outputs the monitoring report.

[0021] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0022] The present application provides a medical-grade VSM dynamic monitoring system and method. The medical-grade VSM dynamic monitoring system includes: a sensing module, an inertial measurement module, a data processing module, a display and interaction module, and a power management module; the data processing module is respectively connected to the sensing module, the inertial measurement module, and the display and interaction module; the power management module is respectively connected to the inertial measurement module, the data processing module, and the display and interaction module; the display and interaction module is used to obtain the basic information of the user to be monitored, and the basic information includes: age, gender, height, weight, altitude, and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring; the sensing module is used to measure the vital sign signal and send the vital sign signal to the data processing module; the inertial measurement module is used to measure the inertial signal and send the inertial signal to the data processing module; the data processing module is used to obtain the vital sign parameters of the user to be monitored according to the inertial signal and the vital sign signal, obtain the standard vital sign parameters according to the basic information and the inertial signal, compare the vital sign parameters with the standard vital sign parameters, generate a monitoring report according to the comparison result, and send the monitoring report to the display and interaction module; the display and interaction module is further used to output the monitoring report. Since the vital sign signal can be obtained through the local sensing module and the inertial signal can be obtained through the local inertial measurement module, and the obtained vital sign signal and inertial signal are sent to the local data acquisition module, in this way, the data acquisition module can complete the acquisition of the vital sign parameters of the user to be monitored based on the vital sign signal and the inertial signal, and compare them with the standard vital sign parameters, and generate a monitoring report output to the user locally. Since there is no need to send relevant signals to the remote end through the network to generate the monitoring report, the risk of the information of the user to be monitored being hacked and leaked during the network transmission process is avoided, the privacy of the patient is protected, and thus the security of the user's personal information is improved. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0024] Figure 1 It is a schematic diagram of a medical-grade VSM dynamic monitoring system shown according to an exemplary embodiment;

[0025] Figure 2 It is a schematic diagram of a medical-grade VSM dynamic monitoring system shown according to an exemplary embodiment;

[0026] Figure 3 It is a schematic diagram of a medical-grade VSM dynamic monitoring system shown according to an exemplary embodiment.

[0027] Explanation of reference numerals:

[0028] 1 - Sensing module; 11 - Wearable sensor; 12 - Analog front end; 2 - Inertial measurement module; 3 - Data processing module; 4 - Display and interaction module; 5 - Power management module; 6 - SOS rescue module; 7 - Early warning prompt module. Specific embodiments

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0030] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Current healthcare or monitoring systems typically rely on external networks or cloud-based solutions to collect and analyze vital signs, such as heart rate, respiratory rate, and blood oxygen saturation.

[0032] However, this solution has the following defects:

[0033] 1. These systems usually rely on solutions connected through networks such as Wi-Fi, Bluetooth, or cellular, thus potentially causing problems in terms of data privacy, security, and dependence on Internet access. For example:

[0034] Reliability issues: Network interruptions or transmission delays may affect the real-time performance and reliability of the system.

[0035] Data security risk: During network transmission, data may be stolen, resulting in the risk of unauthorized access, leakage, and tampering of data.

[0036] Limited applicability: It cannot work properly in a network-free environment (such as remote areas, the wild, or the battlefield).

[0037] 2. In many cases, such as mountain climbing, ambulance services, or home care, being restricted by the network environment, lack of reliable Internet access, or cloud infrastructure may limit the effectiveness of health monitoring systems.

[0038] 3. High cost: These systems rely on network infrastructure and associated software systems, increasing the overall cost of use.

[0039] 4. Defects in remote monitoring: These systems require external intervention and their timeliness is limited by network efficiency. In particular, early warning or emergency measures are not in the hands of the wearer himself, but in the hands of third-party services, and problems with the efficiency and quality of third-party services may delay the treatment of patients.

[0040] 5. The early warning information of these systems is often directly transmitted to medical staff, and the patient himself cannot see the monitoring data.

[0041] 6. These systems often rely on non-standard lead wearable medical solutions, such as watches. Although they can be called medical solutions, they are not medical-grade monitoring solutions. Medical-grade vital sign monitoring solutions, such as electrocardiogram monitors, are based on internationally recognized AHA and IEC lead standards.

[0042] In summary, it is of great significance to develop a completely local solution (without connecting to an external network) for a vital sign monitoring device that operates completely independently of the network, which can not only meet medical-grade monitoring but also adapt to the needs of various scenarios.

[0043] Figure 1 is a schematic diagram of a medical-grade VSM dynamic monitoring system shown according to an exemplary embodiment, as Figure 1 shown, the medical-grade VSM dynamic monitoring system includes: a sensing module 1, an inertial measurement module 2, a data processing module 3, a display and interaction module 4, and a power management module 5;

[0044] The data processing module 3 is respectively connected to the sensing module 1, the inertial measurement module 2, and the display and interaction module 4;

[0045] The power management module 5 is respectively connected to the inertial measurement module 2, the data processing module 3, and the display and interaction module 4; the power management module 5 in the present disclosure supports a long battery life, for example, meeting the monitoring of vital sign signals for 24 hours to 15 days, or even 30 days or longer. For example, it can be equipped with cochlear batteries, rechargeable high-energy batteries, micro nuclear batteries, etc. In order to further extend the working time, the power management module 5 of the present disclosure also incorporates a low-power circuit design.

[0046] The display and interaction module 4 is used to obtain the basic information of the user to be monitored. The basic information includes: age, gender, height, weight, altitude, and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring.

[0047] The sensing module 1 is used to measure the vital sign signals of the user to be monitored and send the vital sign signals to the data processing module 3; among them, the vital sign signals include at least one of the following signals: ECG signal, PPG signal, BIOZ signal, and temperature signal.

[0048] The inertial measurement module 2 is used to measure the inertial signals of the user to be monitored and send the inertial signals to the data processing module 3; among them, the inertial measurement module 2 may include: a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer. These three devices can be independent (such as only selecting the three-axis accelerometer), or they can be used in combination. The present disclosure takes the three-axis accelerometer as an example for illustration.

[0049] The data processing module 3 is used to obtain the vital sign parameters of the user to be monitored according to the inertial signals and vital sign signals, obtain the vital sign standard parameters according to the basic information and inertial signals, compare the vital sign parameters with the vital sign standard parameters, generate a monitoring report according to the comparison result, and send the monitoring report to the display and interaction module 4; the data processing module 3 in the present disclosure uses a high-performance microcontroller unit, including but not limited to an FPU based on floating-point operations, ultra-low-power artificial intelligence (AI), MCU (such as a convolutional neural microprocessor CNN-MCU), a recurrent neural RNN-MCU, etc.). It has the following functions: real-time acquisition, filtering, and data analysis of vital sign signals, feature extraction, optimization, and judgment to output a warning prompt module 7. The AI adaptive learning vital sign analysis function of the CNN-MCU. Data local storage and display. Convolution neural data local diagnosis or auxiliary diagnosis report (without displaying the electrocardiogram, only the result part of the internal electrocardiogram analysis). Among them, the vital sign parameters (Vital Sign Parameters, abbreviated as: VSM) include at least one of the following parameters: heart rate (HR), heart rate variability (HRV), respiratory rate (RR), blood oxygen saturation (SpO 2) Blood pressure (BP), arrhythmia (Rhythm), and body temperature (T). Arrhythmia includes atrial fibrillation (AF), premature ventricular contractions (PVC), and ventricular tachycardia (VT).

[0050] Among them, when obtaining the standard parameters of vital signs based on the basic information and inertial signals, first, the motion state can be obtained based on the inertial signals, and then the HR, RR, SpO 2 in the standard parameters of vital signs can be determined based on the motion state, as well as the age and gender in the basic information. Then, the body temperature reference standard in the standard parameters of vital signs can be obtained based on age.

[0051] Taking the inertial signal as acceleration as an example, after obtaining the acceleration of the user to be monitored, the motion state of the user to be monitored is obtained based on Table 1:

[0052] Table 1

[0053]

[0054] Based on the motion state, as well as the age and gender in the basic information, the HR, RR, SpO 2 in the standard parameters of vital signs are determined, as shown in Table 2:

[0055] Table 2

[0056]

[0057]

[0058]

[0059] It should be noted that when determining the HR, RR, SpO 2 in the standard parameters of vital signs, the current season can also be taken into account. Specifically:

[0060] HR: 5% - 10% higher in winter than in summer;

[0061] HRV: 10% - 15% lower in winter than in summer;

[0062] RR: 5% - 8% higher in winter than in summer;

[0063] SpO 2 : 1% - 2% lower in winter than in summer (cold causes blood vessel constriction).

[0064] The body temperature reference standard in the standard parameters of vital signs is obtained based on age, as shown in Table 3:

[0065] Table 3

[0066]

[0067]

[0068] Clinically, the normal body temperature is generally between 36.5°C and 37.5°C, but the normal body temperature range may vary slightly for each individual. And as people age, body temperature may decrease slightly, especially in the very elderly. Body temperature also varies according to factors such as time (e.g., morning and evening), activity level, and diet.

[0069] Methods of measuring body temperature: Common methods of measuring body temperature include oral, axillary, rectal, ear, and forehead temperature measurements. Different measurement methods will have different normal ranges. For example, the body temperature measured axillary is usually slightly lower than that measured rectally.

[0070] Generally, a body temperature above 38°C is considered a fever, and a body temperature above 39°C may indicate a more serious infection or other diseases.

[0071] The display and interaction module 4 is also used to output a monitoring report. In the present disclosure, the display and interaction module 4 may integrate a high-resolution screen (including but not limited to LCD, OLED, TFT, etc.) to display the monitoring report. Alternatively, it may also inherit touch screen or physical button operations to facilitate user input. The display and interaction module 4 may also provide a human-machine interface (Human-Machine Interface, abbreviated as: HMI), and this HMI may be connected to a human-machine voice interaction device, etc., to facilitate user operation.

[0072] Since the medical-grade VSM dynamic monitoring system in the present disclosure can complete monitoring and display of the monitoring report locally without transmitting it to other device terminals through the network, it avoids the problems of network interruption or transmission delay affecting the real-time performance and reliability of the system, and can also avoid the risks of unauthorized access, leakage, and tampering of data during transmission. It can operate normally even in a network-free environment, expanding the scope of use.

[0073] The medical-grade VSM dynamic monitoring system in the present disclosure does not rely on network infrastructure and associated software systems, reducing the usage cost.

[0074] By using the medical-grade VSM dynamic monitoring system in the present disclosure, the patient himself can directly view the monitoring data.

[0075] The medical-grade VSM dynamic monitoring system in this disclosure provides a reliable, private, and autonomous continuous health monitoring method for a completely local medical-grade VSM dynamic monitoring solution without the need for an external network or device. This design focuses on real-time data analysis, alerts, privacy, and local storage to ensure accurate health information and instant feedback regardless of the user's environment. By addressing key challenges in remote monitoring, patient data privacy, and healthcare, this disclosure fills a key gap in the current offline vital signs monitoring system market. Compliance with medical standards (e.g., IEC, ISO, FDA) further consolidates its applicability in various healthcare environments. With its flexibility, future scalability, and compliance, this medical-grade VSM dynamic monitoring system will become an important tool for personal health management, emergency care, and remote patient monitoring.

[0076] In one embodiment, as Figure 2 shown, the sensing module 1 includes: a wearable sensor 11 and an analog front-end 12;

[0077] The analog front-end 12 is respectively connected to the wearable sensor 11, the data processing module 3, and the power management module 5;

[0078] The wearable sensor 11 is used to collect raw vital signs signals and send the collected raw vital signs signals to the analog front-end 12;

[0079] The analog front-end 12 is used to preprocess the received raw vital signs signals to obtain vital signs signals.

[0080] The sensing module 1 is composed of a wearable sensor 11 and an analog front-end 12 (Analog Front-End, abbreviated as: AFE).

[0081] The wearable sensor 11 may include: a wearable garment, patch lead electrodes, an optical sensor, a digital temperature sensor, or other temperature sensors, etc.

[0082] The analog front-end 12 AFE, preferably an advanced clinical medical-grade AFE, is used for analog-to-digital conversion of vital signs parameters, etc. Such as integrating ECG, BIOZ, PPG sensors, it can easily obtain ECG, PPG, BIOZ signals for extracting vital signs parameters (VSM).

[0083] Among them, the AC dynamic input range of the amplifier built by the AFE is ±50mVP-p to ±200mVP-p.

[0084] In this disclosure, a medical-grade AFE is adopted, which can achieve medical-grade monitoring.

[0085] In one embodiment, as Figure 3As shown, the medical-grade VSM dynamic monitoring system in the present disclosure further includes: an SOS rescue module 6;

[0086] The SOS rescue module 6 is respectively connected to the data processing module 3 and the power management module 5;

[0087] The data processing module 3 is further configured to generate a distress signal when it determines that there are abnormal vital sign parameters based on the comparison result, and send the distress signal to the SOS rescue module 6;

[0088] The SOS rescue module 6 is configured to execute a preset rescue measure after receiving the distress signal. The preset rescue measure includes: sending a distress message to a preset emergency contact person, and / or sending a distress message to a rescue agency.

[0089] When the SOS rescue module 6 sends a distress message, it can also carry key information such as the location of the patient and vital sign data.

[0090] By setting the SOS rescue module 6, when the patient has abnormal vital signs or encounters an emergency, a distress signal can be quickly sent through the SOS rescue module 6. This enables medical staff or relevant rescue personnel to learn about the critical condition of the patient in the first place, greatly shortening the distress time and winning more rescue opportunities for the patient.

[0091] In one embodiment, the data processing module 3 is further configured to:

[0092] Obtain medical advice based on the abnormal vital sign parameters, and the medical advice provides measures for the user to be monitored to deal with the abnormal vital sign parameters.

[0093] The monitoring report in the present disclosure includes:

[0094] Vital sign parameters, abnormal vital sign parameters, and doctor's advice.

[0095] Exemplarily, the monitoring report usually includes the following contents:

[0096] Vital sign parameter statistics: Statistical data of parameters such as HR, RR, SpO 2 , BP, HRV, T, etc., for example: average value, maximum value, minimum value, predicted change trend, etc.

[0097] The fluctuation range of each index.

[0098] Abnormal detection: Record abnormal events, indicating the occurrence time and specific abnormal conditions. For example: identifying atrial fibrillation (AF), premature ventricular contractions (PVC), or ventricular tachycardia (VT).

[0099] Provide early warning information, marking the triggered early warning threshold.

[0100] Medical advice: Generate corresponding medical advice based on the monitoring results (such as advice to go to the hospital for treatment, stop strenuous exercise, etc.).

[0101] The warning methods of the monitoring and warning in the present disclosure may include: visual, auditory, tactile and other methods.

[0102] The reporting methods of the monitoring report in the present disclosure may include: visual and auditory methods, wherein, the visual may include display through a display screen, and the auditory method may include voice, etc.

[0103] a) The statistical basis of vital sign parameters is shown in Table 2.

[0104] b) Abnormality detection:

[0105] · No atrial fibrillation (AF) occurs.

[0106] · No premature ventricular contractions (PVC) occur.

[0107] · No ventricular tachycardia (VT) occurs.

[0108] c) Medical advice:

[0109] · The results of this monitoring are good, without abnormalities. Continue to maintain a healthy lifestyle.

[0110] · If the symptoms change, please contact a doctor in time.

[0111] In this way, you can ensure that in the VSM system, the real-time monitoring and warning system can effectively detect potential health risks, generate monitoring reports in a timely manner, and provide necessary medical intervention advice.

[0112] In one embodiment, the data processing module 3 is specifically configured to perform the following steps A1 - A4:

[0113] A1. Obtain the Body Mass Index (BMI) of the user to be monitored according to the height and weight. The BMI can be obtained through the following formula:

[0114]

[0115] Where, the weight unit is Kg and the height unit is m.

[0116] Table 4 shows the BMI and health risk classification:

[0117] Table 4

[0118] Classification <![CDATA[BMI range (kg / m 2 )]]> Health risk Underweight <18.5 Increased risk of malnutrition-related diseases Normal weight 18.5–24.9 Lowest health risk Overweight class I (pre-obese) 25.0–29.9 Slightly increased health risk Overweight class II (obese class I) 30.0–34.9 Moderately increased health risk Overweight class III (obese class II) 35.0–39.9 Severely increased health risk Overweight class IV (morbidly obese class III) ≥40.0 Extremely high health risk

[0119] A2. Obtain the BMI coefficient and altitude coefficient according to the target basic parameters; the target basic parameters include: BMI, or, altitude.

[0120] The body mass index coefficient and the altitude coefficient can be obtained based on Table 5:

[0121] Table 5

[0122] Classification <![CDATA[Body mass index coefficient C bmi > <![CDATA[Altitude coefficient C altitud > Low body weight (BMI < 18.5) Approximately 0.5 Approximately 1.0 Normal weight (18.5 ≤ BMI ≤ 24.9) Approximately 1.0 Approximately 1.0 Overweight (25 ≤ BMI ≤ 29.9) Approximately 1.5 - 2.0 Approximately 1.1 - 1.3 Obese (BMI ≥ 30) Approximately 2.0 - 3.0 Approximately 1.3 - 2.0 Low altitude (0 - 1000 m) Approximately 1.0 Approximately 1.0 Medium altitude (1000 m - 3000 m) Approximately 1.0 Approximately 1.1 - 1.3 High altitude (3000 m and above) Approximately 1.0 Approximately 1.3 - 2.0

[0123] When obtaining the body mass index coefficient and the altitude coefficient, the low altitude can be used as the demarcation line. When the altitude is low altitude, the body mass index coefficient and the altitude coefficient corresponding to the BMI classification are used; when the altitude is medium altitude or high altitude, the body mass index coefficient and the altitude coefficient corresponding to the altitude classification are used.

[0124] A3. Optimize the inertial signal according to the body mass index coefficient and the altitude coefficient.

[0125] Continuing to take the inertial signal as the acceleration signal as an example:

[0126] The acceleration signal is collected by a three-axis accelerometer (such as ADXL367). The three-axis accelerometer usually provides the acceleration components in the X, Y, and Z directions, with the unit g or m / s 2 , for example, the three-axis accelerometer provides: a x (t), a y (t), a z (t), where a x (t) is the acceleration component on the X axis, a y (t) is the acceleration component on the Y axis, a z (t) is the acceleration component on the Z axis, and these values change with time t.

[0127] Calculate the total acceleration a(t) of the device through the three-axis acceleration components:

[0128]

[0129] where the unit of a(t) is g or m / s 2 , indicating the motion intensity or motion state of the three-axis accelerometer in three-dimensional space. Optimize the acceleration using the body mass index coefficient and the altitude coefficient, and the formula is as follows:

[0130] A(t) = C bmi ·C altiud ·a(t);

[0131] where: C bmi is the body mass index coefficient, C altitud is the altitude coefficient.

[0132] A4. Determine the vital sign parameters of the user to be monitored according to the optimized inertial signal and the vital sign signal.

[0133] In one embodiment, in terms of determining the vital sign parameters of the user to be monitored based on the optimized inertial signal and vital sign signal, the data processing module 3 is specifically configured to perform the following steps A41 - A42:

[0134] A41. Obtain filter parameters according to the optimized inertial signal, and process the vital sign signal according to the filter parameters to obtain a target vital sign signal.

[0135] Exemplarily, filter parameters can be obtained according to the optimized inertial signal, and the vital sign signal can be filtered according to the filter parameters. At this time, the filtered vital sign signal is the target vital sign signal.

[0136] Alternatively, filter parameters can be obtained according to the optimized inertial signal, and the vital sign signal can be filtered according to the filter parameters; then, the filtered vital sign signal is smoothed. At this time, the smoothed vital sign signal is the target vital sign signal.

[0137] In one embodiment, in terms of obtaining filter parameters according to the optimized inertial signal, the data processing module 3 is specifically configured to:

[0138] Obtain the dynamic gain of the high - pass filter and the cut - off frequency of the high - pass filter according to the optimized inertial signal, filter the vital sign signal according to the dynamic gain of the high - pass filter and the cut - off frequency of the high - pass filter to obtain the high - pass filtered signal of the vital sign signal;

[0139] Specifically: According to the optimized acceleration A(t), through a preset threshold or motion threshold A thresh (unit g or m / s 2 ) and the gain adjustment coefficient β, dynamically calculate the gain G highpass (t) of the high - pass filter and the cut - off frequency f highpass .

[0140] The calculation formula for the optimized acceleration A(t) and the gain of the high - pass filter is:

[0141]

[0142] Among them, the gain G 0 of the high - pass filter represents the initial gain of the high - pass filter, usually set to 1, A thresh represents the threshold of the motion intensity when calculating the gain of the high - pass filter, which determines the division of the motion state, and β represents the adjustment coefficient of the gain of the high - pass filter, which controls the influence intensity of the optimized acceleration on the gain of the high - pass filter. Usually, β > 1.

[0143] Specifically, in addition to gain adjustment, the cut-off frequency of the high-pass filter can also be dynamically adjusted according to the acceleration. Usually, when the exercise intensity increases, the cut-off frequency of the high-pass filter can be increased to better remove motion artifacts. For example, assuming that the cut-off frequency of the high-pass filter is f highpass It is dynamically adjusted according to the optimized acceleration A(t):

[0144]

[0145] where f highpass represents the cut-off frequency of the high-pass filter, f 0 represents the initial cut-off frequency of the high-pass filter, which is set to an appropriate value (such as 10 HZ), δ represents the adjustment coefficient of the cut-off frequency of the high-pass filter, A(t) represents the degree of influence of the increase in the optimized acceleration on the cut-off frequency of the high-pass filter, and A thresh represents the threshold of the exercise intensity.

[0146] Among them, when the exercise intensity increases, the cut-off frequency f highpass of the high-pass filter will increase, making it more effective in removing low-frequency interference.

[0147] And / or, obtain the dynamic gain of the low-pass filter and the cut-off frequency f lowpass of the low-pass filter according to the optimized inertial signal, and filter the vital sign signal according to the dynamic gain of the low-pass filter and the cut-off frequency of the low-pass filter to obtain the low-pass filtered signal of the vital sign signal.

[0148] Specifically: according to the optimized acceleration A(t), through a preset threshold or motion threshold A t ′ hresh (unit g or m / s 2 ) and the adjustment coefficient, dynamically calculate the gain G lowpass (t) of the low-pass filter and the cut-off frequency f lowpass of the low-pass filter.

[0149] The calculation formula for obtaining the low-pass filter gain through the optimized acceleration A(t) is as follows:

[0150]

[0151] where G lowpass (t) represents the gain of the low-pass filter, represents the initial gain of the low-pass filter, usually set to 1, It represents the threshold of the motion intensity when calculating the gain of the low-pass filter, which determines the division of the motion state. α represents the gain adjustment coefficient of the low-pass filter, controlling the influence degree of the motion state on the gain of the low-pass filter. Usually, 0 ≤ α ≥ 1 is set. γ represents the adjustment coefficient of the gain of the low-pass filter, controlling the influence intensity of the optimized acceleration on the gain of the high-pass filter. Usually, γ > 0.

[0152] Specifically, in addition to gain adjustment, the cut-off frequency of the low-pass filter can also be dynamically adjusted according to the acceleration. Usually, when the motion intensity decreases, the cut-off frequency of the low-pass filter can be reduced to better remove motion artifacts. For example, assume that the cut-off frequency f of the low-pass filter lowpass is dynamically adjusted with the change of the optimized acceleration A(t):

[0153]

[0154] where f lowpass represents the cut-off frequency of the low-pass filter, f' 0 represents the initial cut-off frequency of the low-pass filter, which is set to an appropriate value (such as 10 Hz), δ' represents the adjustment coefficient of the cut-off frequency of the low-pass filter, A(t) represents the influence degree of the increase of the optimized acceleration on the cut-off frequency of the low-pass filter, and A' thresh represents the threshold of the motion intensity when calculating the gain of the low-pass filter.

[0155] Among them, when the motion intensity decreases, the cut-off frequency f of the low-pass filter lowpass will decrease, making it more effective in removing high-frequency interference.

[0156] And / or, obtain the dynamic gain of the band-pass filter and the cut-off frequency of the band-pass filter according to the optimized inertial signal, and filter the vital sign signal according to the dynamic gain of the band-pass filter and the cut-off frequency of the band-pass filter to obtain the band-pass filtered signal of the vital sign signal.

[0157] Specifically: The calculation formula for obtaining the dynamic gain of the band-pass filter through the optimized inertial signal is:

[0158] G bandpass (t) = Inverse FFT(A filtered (f));

[0159] A filtered (f) = A(f) · H(f);

[0160]

[0161] A(f) = FFT(A(t));

[0162] where Gbandpass (t) is the dynamic gain of the band - pass filter, A filtered (f) is the output function of the acceleration signal passing through the band - pass filter; A(f) is the spectrum obtained by performing FFT on the optimized acceleration A(t), H(f) represents the transfer function of the band - pass filter, f high is the high - frequency cut - off point of the band - pass filter, f low is the low - frequency cut - off point of the band - pass filter.

[0163] In one embodiment, in terms of processing the vital sign signal according to the filter parameters to obtain the target vital sign signal, the data processing module 3 is specifically configured to:

[0164] The high - pass filter allows signals with frequencies higher than the cut - off frequency f highpass (t) to pass through. For the vital sign signal X(t), the output X highpass (t) after high - pass filtering can be expressed as:

[0165] X highpass (t) = G highpass (t)·X(t)·H highpass (f, f highpass (t));

[0166] Among them, G highpass (t) represents the gain of the high - pass filter, H highpass (f, f highpass (t)) is the frequency response function of the high - pass filter, usually expressed as the filter characteristics related to the cut - off frequency f highpass (t) of the high - pass filter.

[0167] The low - pass filter allows signals with frequencies lower than the cut - off frequency f lowpass (t) to pass through. For the vital sign signal X(t), the output X lowpass (t) after low - pass filtering can be expressed as:

[0168] X lowpass (t) = G lowpass (t)·X(t)·H lowpass (f, f lowpass (t));

[0169] Among them, G lowpass (t) represents the gain of the low - pass filter, H lowpass (f, f lowpass (t)) is the frequency response function of the low - pass filter, usually expressed as the filter characteristics related to the cut - off frequency f lowpass (t) of the low - pass filter.

[0170] A band - pass filter allows signals within a certain frequency range (determined by a low - frequency cut - off f low (t) and a high - frequency cut - off f high (t)) to pass through. The output X bandpass (t) after filtering by the band - pass filter can be expressed as:

[0171] X bandpass (t) = G bandpass (t)*X(t)*H bandpass (f, f low (t), f high (t));

[0172] Wherein, G bandpass (t) is the dynamic gain of the band - pass filter, and H bandpass (f, f low (t), f high (t)) is the frequency - response function of the band - pass filter, which is usually expressed as a filter characteristic related to the low - frequency cut - off f low (t) and the high - frequency cut - off f high (t).

[0173] That is to say, the main function of a high - pass filter is to filter out signals below a certain cut - off frequency and retain high - frequency components; the main function of a low - pass filter is to filter out signals above a certain cut - off frequency and retain low - frequency components; a band - pass filter allows signals in a specific frequency band to pass through, removing components below the lowest cut - off frequency and above the highest cut - off frequency, and the above - mentioned frequency - response function is usually determined by the specific way of filter design.

[0174] Wherein, the output X highpass (t) after high - pass filtering, and / or, the output X lowpass (t) after low - pass filtering, and / or, the output X bandpass (t) after filtering by the band - pass filter characterizes the target vital - sign signal.

[0175] Furthermore, in step A41, the filtered vital - sign signal can be further processed by a smoothing algorithm (such as Moving Average, Weighted Moving Average, Exponential Smoothing) to further remove small fluctuations.

[0176] Taking the exponential - smoothing algorithm as an example:

[0177] S(t)=ξ×m(t)+(1 - ξ)×S(t - 1);

[0178] Among them, S(t) represents the smoothed signal value at time point t, m(t) represents the original value of the vital sign signal after filtering at time t, S(t - 1) represents the smoothed signal value at time point (t - 1), and ξ represents the smoothing coefficient, which is between 0 and 1 and is used to control the balance between new data and historical data.

[0179] A42. Determine the vital sign parameters of the user to be monitored according to the target vital sign signal.

[0180] The following details the acquisition process of each vital sign parameter.

[0181] I. Heart rate (HR) feature.

[0182] The target vital sign signal can be input into the trained target heart rate feature extraction convolutional neural network to obtain the predicted heart rate feature in the target vital sign signal through the trained target heart rate feature extraction convolutional neural network.

[0183] Before obtaining the predicted heart rate feature, it is also necessary to train the initial heart rate feature extraction convolutional neural network to obtain the target heart rate feature extraction convolutional neural network. The specific training process includes the following steps B1 - B6:

[0184] B1. Obtain a heart rate training sample set, which includes: training sample signals and labeled tags. Among them, the labeled tags can be understood as the labeled true heart rates.

[0185] B2. Input the training sample signals into the initial heart rate feature extraction convolutional neural network to obtain the training heart rate prediction result;

[0186] Specifically, step B2 includes the following sub - steps B21 - B24:

[0187] B21. Input the training sample signals into the convolutional layer for convolution processing;

[0188] Among them, the convolution operation is the core part of extracting signal features in a convolutional neural network (CNN). It performs a convolution operation on the training sample signal X′(t) and the convolution kernel W. The specific formula is:

[0189] F(t) = (X′(t) * W) + b;

[0190] Among them, F(t) represents the feature map after convolution, which is the signal feature obtained after the convolution operation; W represents the convolution kernel, which is a small filter, and usually there are multiple different convolution kernels for extracting different types of features; * represents the convolution operator, indicating the convolution operation; b represents the bias term of the convolutional layer, and X′(t) represents the time - domain data of the training sample signal, usually the signal within a time window.

[0191] B22. Input the training sample signal after convolution processing into the pooling layer for pooling processing;

[0192] The pooling operation is used to reduce the dimension of the feature map and retain important features. Max pooling is a commonly used pooling method, which selects the maximum value in the local window. The specific formula is:

[0193] F pool (t) = max(F(t));

[0194] where F pool (t) represents the feature map after pooling, and max() represents the max pooling operation, that is, selecting the maximum value in the pooling window.

[0195] B23. Perform frequency domain analysis on the training sample signal after pooling processing.

[0196] In order to extract the frequency features related to heart rate from the signal, fast Fourier transform (FFT) is often used for frequency domain analysis. The specific formula is:

[0197] S(f) = FFT(F(t));

[0198] where S(f) represents the frequency domain features of the signal F(t) after Fourier transform, indicating the intensity of the signal at different frequencies; f HR represents the main frequency related to heart rate, indicating the frequency component corresponding to the heartbeat in the spectrum.

[0199] B24. Input the training sample signal after frequency domain processing into the fully connected layer to obtain the training heart rate prediction result.

[0200] The fully connected layer integrates the features extracted through frequency domain analysis to output the final prediction result. The specific formula is:

[0201] HR = FC(S(f), W FC ) + b FC ;

[0202] where W FC represents the weight matrix of the fully connected layer, b FC represents the bias term of the fully connected layer, and HR represents the initial training heart rate prediction result.

[0203] B25. Output the final training heart rate prediction result through the output layer.

[0204] The output layer gives the final training heart rate prediction result. The specific formula is as follows:

[0205]

[0206] where, Shows the final training heart rate prediction result, where f(HR) is a non-linear activation function (such as ReLU, sigmoid, etc.) used to map the output of the model to the final training heart rate prediction result.

[0207] B3. Input the training heart rate prediction result and the corresponding label into the loss function to obtain the loss function value.

[0208] To train the CNN model, it is necessary to define a loss function to measure the difference between the predicted value and the true value. The commonly used loss function is the mean square error (MSE), especially in regression tasks. The formula is as follows:

[0209]

[0210] Where, represents the final training heart rate prediction result corresponding to the i-th training sample signal, HR i represents the true heart rate corresponding to the i-th training sample signal, and N represents the number of training sample signals.

[0211] B4. Adjust the parameters of the convolutional neural network for initial heart rate feature extraction according to the loss function value to obtain a convolutional neural network for heart rate feature extraction with adjusted parameters.

[0212] B5. Perform quantization processing on the convolutional neural network for heart rate feature extraction with adjusted parameters.

[0213] Quantization mainly converts high-precision data (such as 32-bit floating-point numbers) into low-precision integer values. The quantization formula can be:

[0214]

[0215] Where, χ represents the weight, activation value, or input value of a certain layer in the convolutional neural network for heart rate feature extraction with adjusted parameters; Δ represents the quantization step, usually determined by the quantization precision range. For example, when it is 8 bits, the step is 2 8 ; round(·) represents rounding the value to the nearest integer.

[0216] This means that x will be scaled and rounded to the nearest low-precision representation. After quantization, the model will become more efficient, reducing storage requirements and accelerating calculations.

[0217] B6. Perform pruning processing on the convolutional neural network for heart rate feature extraction after quantization processing to obtain a trained target convolutional neural network for heart rate feature extraction.

[0218] Pruning usually reduces the computational amount by removing unimportant neurons or connections in the network. Suppose we have a neural network where the weight matrix of each layer is W. The pruning process can be defined as:

[0219] W pruned = W·L where |w| > τ;

[0220] where W pruned represents the weight matrix after pruning; |w| represents the absolute value of each element in the weight matrix w; τ represents the pruning threshold, and connections with weight values less than τ will be removed; L represents the indicator function, and only when the absolute value of the weight is greater than the threshold τ will the connection be retained.

[0221] Pruning reduces computational complexity and storage requirements by removing connections with smaller absolute weights.

[0222] It should be noted that in the optimization method combining quantization and pruning, quantization and pruning are usually performed sequentially, or in some cases, alternately. The goal of this method is to reduce storage requirements, computational complexity, and maintain model performance simultaneously.

[0223] First, the pruning operation obtains the weight matrix W pruned ;

[0224] Then, the quantization operation:

[0225]

[0226] where Q(W pruned ) represents the pruned weight after quantization.

[0227] The combined operation can first perform pruning to reduce unnecessary connections, and then reduce computational precision through quantization, thereby further improving efficiency.

[0228] Quantization reduces storage requirements and computational volume by mapping high-precision values to lower-precision integers.

[0229] Pruning reduces computational complexity and storage requirements by removing unimportant connections or neurons.

[0230] Combining quantization and pruning first reduces the network scale through pruning, and then reduces the precision through quantization, thereby achieving maximum optimization of resources.

[0231] The final HR value is the predicted value obtained from the output layer of the neural network. After steps such as filtering, convolution, pooling, frequency domain analysis, and fully connected layers, the model outputs a predicted heart rate (HR). Through the loss function (such as MSE) during the training process, the model gradually adjusts its parameters to make the predicted HR value as close as possible to the true value. After quantization and pruning optimization, the inference efficiency and accuracy of the model will be improved, enabling better prediction of heart rate in practical applications.

[0232] When calculating heart rate-related features, the ECG signal or PPG signal in the target vital sign signal is used.

[0233] II. Heart Rate Variability (HRV) features.

[0234] The extraction of heart rate variability (HRV) features is based on the analysis of the r-r interval (also known as the rr interval) in the target vital sign signal, mainly including time domain, frequency domain, and non-linear analysis methods, specifically including the following steps C1-C3:

[0235] C1. Obtain the R-wave position in the target vital sign signal;

[0236] The R-wave position in the target vital sign signal can be obtained through the R-wave detection algorithm. Commonly used ones include differentiation, squaring, and moving window integration methods, and the R-wave position is detected by setting the R-wave threshold.

[0237] (1) Differentiation operation.

[0238] The differentiation operation can enhance the slope change of the signal and highlight the slope of the QRS complex. The specific formula is:

[0239] Y diff [n]=X[n]-X[n - 1];

[0240] Among them, X[n] and X[n - 1] represent the input target vital sign signal, and Y dif [n] represents the differentiated target vital sign signal, highlighting the slope change.

[0241] (2) Squaring.

[0242] The squaring operation changes the signal to a positive value and at the same time enhances the amplitude of the QRS wave. The specific formula is:

[0243] Y square [n]=(T diff [n]) 2 ;

[0244] Among them, Y Square [n] represents the squared target vital sign signal, which is used to enhance the detection of sharp waveforms.

[0245] (3) Moving Window Integration.

[0246] The moving window integration smooths the signal and emphasizes the overall characteristics of the QRS waveform. The specific formula is:

[0247]

[0248] Among them, Y int [n] represents the target vital sign signal after sliding window integration, N represents the length of the sliding window, usually taking 150 ms - 200 ms. k represents the offset of n to the past N time points (from k = 0 to k = N - k = N - 1).

[0249] After obtaining the processed target vital sign signal through the above three methods, then set the dynamic or static R-wave threshold to detect the R-wave position. The position where the signal value in the processed target vital sign signal is greater than the R-wave threshold is the R-wave position.

[0250] The R-wave position can also be determined by the QRS detection algorithm.

[0251] The detection purpose of the QRS detection algorithm is to identify the complete QRS waveform (including Q wave, R wave, S wave), and its algorithm is based on the extraction of signal characteristics in a specific frequency range.

[0252] a) R-wave calibration.

[0253] Determine the position of the R wave by finding the maximum value of the local signal:

[0254] R peak = max(x[n]) for n ∈ [t start , t end ;

[0255] Among them, x[n] represents the input filtered target vital sign signal, R peak represents the position of the R-wave peak (time point n), [t start , t end represents the time range of the sliding window, usually covering one cardiac cycle.

[0256] b) Q-wave calibration.

[0257] Calibrate the Q wave by finding the minimum value of the signal before the R wave:

[0258] Q wave = min(x[n]) for n ∈ [t start , R peak ;

[0259] Among them, Q wave represents the position of the Q wave (time point n); [t start , R peak represents the time range from the starting point of the sliding window to the R-wave peak position.

[0260] c) S-wave calibration.

[0261] Calibrate the S wave by finding the minimum value of the signal after the R wave:

[0262] S wave = min(x[n]) for n ∈ [R peak , t end ;

[0263] Wherein, S wave represents the position of the S wave (time point n), [Rpeak, t end represents the time range from the R wave peak position to the end point of the sliding window.

[0264] C2. Obtain all rr intervals in the target vital sign signal according to the R wave position.

[0265] All R wave positions are obtained through C1, and all rr intervals can be obtained based on all R wave positions.

[0266] C3. Obtain the heart rate variability characteristic values according to the rr intervals. The heart rate variability characteristic values include: average heart rate interval, heart rate, standard deviation of all rr intervals, root mean square of the difference between adjacent rr intervals, proportion of rr interval differences greater than 50 ms, power spectral density within the frequency band corresponding to each rr interval, short-term HRV component, and long-term HRV component.

[0267] Specifically, HRV time-domain feature extraction can adopt the time-domain method, and calculate the characteristic values of heart rate variability by statistically analyzing the rr intervals.

[0268] (1) Average heart rate interval.

[0269]

[0270] Wherein, M ean_rr represents the average rr interval, with the unit of second; rr i represents the i-th rr interval, and M represents the total number of rr intervals.

[0271] (2) Heart rate.

[0272]

[0273] Wherein, HR represents the heart rate, with the unit of bpm (times per minute).

[0274] (3) Standard deviation.

[0275]

[0276] Wherein, SDNN represents the standard deviation of all rr intervals, reflecting the overall level of heart rate variability.

[0277] (4) Root mean square of the difference between adjacent rr intervals.

[0278]

[0279] Among them, RMSSD represents the root mean square of the differences between adjacent rr intervals, mainly reflecting parasympathetic nerve activity; (rr i+1 -rr i ) represents the difference between adjacent rr intervals.

[0280] (5) Proportion pNN50 of rr interval differences greater than 50 ms:

[0281]

[0282] Among them, pNN50 represents the proportion of rr interval differences greater than 50 ms, reflecting the short-term fluctuations of heart rate variability.

[0283] Specifically, the method for extracting HRV frequency domain features performs spectral analysis on the rr interval sequence and calculates the power density of different frequency bands.

[0284] (1) Frequency band division.

[0285] ULF (ultra-low frequency): <0.003 Hz;

[0286] VLF (very low frequency): 0.003 Hz ≤ f < 0.04 Hz;

[0287] LF (low frequency): 0.04 Hz ≤ f < 0.15 HzH;

[0288] HF (high frequency): 0.15 Hz ≤ f < 0.4 Hz;

[0289] (2) Spectrum power calculation

[0290] Use the fast Fourier transform (FFT) or Lomb-Scargle spectral analysis method to calculate the power of each frequency band:

[0291]

[0292] Among them, P Band represents the power density within the frequency band, PSD(f) represents the power spectral density, f 1 , f 2 represents the start and end frequencies of the frequency band.

[0293] (3) Frequency domain features.

[0294] By comparing the relationship between P Band and each frequency band, it is obtained which frequency band the current power density belongs to. When P Band belongs to the low-frequency band, the obtained P Band is P LF, which represents the low-frequency power and reflects the sympathetic and parasympathetic nerve activities. When P Band belongs to the high-frequency band, the obtained P Band is P HF , which represents the high-frequency power and reflects the parasympathetic nerve activity. When P Band belongs to the very low-frequency band, the obtained P Band is P VLF , which represents the very low-frequency power and is related to the long-term regulation mechanism (such as body temperature), and P LF / P HF represents the sympathetic and parasympathetic nerve balance.

[0295] Specifically, the extraction of HRV non-linear features can adopt Poincaré plot analysis. Specifically:

[0296]

[0297] Among them, SD1 represents the short-term HRV component, which is related to the parasympathetic nerve activity, and SD2 represents the long-term HRV component, which is related to the sympathetic nerve activity.

[0298] When calculating the features related to heart rate variability, the ECG signal in the target vital sign signal is used.

[0299] III. Respiratory rate (RR).

[0300] When calculating the features related to the respiratory rate, the BIOZ-filtered signal in the target vital sign signal is used. The respiratory rate in the BIOZ signal of the target vital sign signal is mainly extracted through the impedance change of the chest cavity, and can be based on time-domain and frequency-domain methods.

[0301] (a) Time-domain method.

[0302] Using the periodic change of the chest cavity impedance waveform, calculate the average respiratory cycle. The specific formula is:

[0303]

[0304] Among them, RR represents the respiratory rate, with the unit of breaths per minute (bpm), and T breath represents the average cycle of a single breath, with the unit of seconds.

[0305] Feature extraction steps:

[0306] 1. Detect the peak or zero-crossing point of the respiratory waveform from the BIOZ-filtered signal in the target vital sign signal.

[0307] 2. Calculate the time interval T breath .

[0308] 3. Take multiple Tbreath The average value is substituted into the formula (RR = 60 / T breath ) for calculation.

[0309] (b) Frequency domain method.

[0310] Based on the Fast Fourier Transform (FFT), analyze the spectrum of the BIOZ filtered signal in the target vital sign signal to extract the respiratory rate. The specific formula is:

[0311] RR = f peak · 60;

[0312] where f peak represents the main peak frequency of the respiratory rate in the BIOZ signal of the target vital sign signal, with the unit of Hz.

[0313] Feature extraction steps:

[0314] 1. Perform FFT on the BIOZ signal in the target vital sign signal.

[0315] 2. Find the spectrum main peak f in the low frequency band (usually 0.1 Hz - 0.5 Hz) peak .

[0316] 3. Substitute into the formula to calculate the respiratory rate RR = f peak · 60.

[0317] IV. Blood oxygen (SpO 2 ).

[0318] When calculating the relevant features of blood oxygen (SpO 2 ), the signal used is the signal after filtering the photoplethysmogram (PPG) in the target vital sign signal. The feature extraction algorithm for blood oxygen saturation (SpO 2 ) is usually based on the ratio of red light (R) and infrared light (IR) signals, including the following steps:

[0319] a) Signal decomposition:

[0320] Separate the alternating current (AC) and direct current (DC) components from the PPG signal in the target vital sign signal.

[0321] Usually, a high-pass filter is used to extract the AC component, and a low-pass filter is used to extract the DC component.

[0322] b) Calculate the ratio:

[0323] Calculate the AC / DC of the red light and infrared signals respectively.

[0324] c) Calculate Rratio:

[0325] The calculation formula for Rratio:

[0326]

[0327] Among them, AC R represents the alternating current (AC) component of the red light signal (the part reflecting the dynamic changes of the pulse wave). DC R represents the direct current (DC) component of the red light signal (the part reflecting the average value or the base part of the signal). AC IR represents the alternating current (AC) component of the infrared signal. DCIR represents the direct current (DC) component of the infrared signal.

[0328] d) Calculate SpO 2 .

[0329] SpO 2 Calculation formula:

[0330] SpO 2 = 100 - R ratio ;

[0331] Among them: C represents a proportionality constant, related to the calibration curve, usually determined based on experimental data. This value needs to be determined by experimental methods, usually by fitting with the true SpO 2 value measured by a standard oxygen analyzer and the measured value of the device. This value may vary due to factors such as population, skin color, and environmental light interference, and multi-dimensional calibration needs to be considered in actual applications.

[0332] V. Body temperature (T).

[0333] In wearable devices, the algorithm of a high-precision and ultra-low-power digital temperature sensor usually obtains the temperature value T based on the digital output value of the temperature sensor through calibration and formula calculation.

[0334] For digital temperature sensors, the body temperature calculation formula is usually:

[0335] T = a·Output_Code + b;

[0336] Or (when non-linearly calibrated):

[0337]

[0338] Among them, T represents the body temperature value, Output_Code represents the digital output value of the temperature sensor, usually the value after ADC conversion or the direct digital register value; a and b represent calibration coefficients, provided by the sensor manufacturer or obtained through calibration tests, C i represents the calibration coefficient for polynomial fitting, used for higher-precision non-linear calibration, and n represents the order of the polynomial, usually 2 or 3.

[0339] VI. Blood pressure.

[0340] Blood pressure includes systolic blood pressure (SBP) and diastolic blood pressure (DBP). Among them, systolic blood pressure represents the blood pressure value when the heart contracts, and diastolic blood pressure represents the blood pressure value when the heart relaxes.

[0341] 1) Pulse wave transit time (PTT) extraction.

[0342] The pulse wave transit time (PTT) refers to the time when the pulse wave emitted from the heart propagates to the peripheral blood vessels, and it has a certain correlation with blood pressure. PTT is calculated based on the time difference between the ECG and PPG signals in the target vital sign signal and is commonly used for blood pressure estimation. The PTT extraction is as follows:

[0343] PTT = t PPG_peak - t R ;

[0344] Among them, t R represents the R-wave peak time in the ECG signal in the target vital sign signal, which represents the time when the R wave in the electrocardiogram occurs; t PPG_peak represents the pulse wave peak time in the PPG signal in the target vital sign signal, which represents the time when the maximum amplitude of the pulse wave occurs; PTT represents the time difference from the R-wave peak of the ECG signal to the peak of the PPG signal.

[0345] 2) Blood pressure estimation.

[0346] The regression model can be used for blood pressure estimation. Specifically:

[0347] The estimation formula for SBP:

[0348] SBP = a 1 ·PTT + a 2 ·HR + a 3 ·PPG features + b 1 ;

[0349] The estimation formula for DPB:

[0350] DBP = a 4 ·PTT + a 5 ·HR + a 6 ·PPG features + b 2 ;

[0351] Among them, a 1 , a 2， a 3， a 4， a 5， a 6 represents the coefficient of the regression model, which represents the contribution degree of different input features to blood pressure and is obtained through training data; b1 , b 2 represents the constant bias term, the constant value in the regression model, and PPG features represent other features in the PPG signal, such as the rise time, peak amplitude, fall time, etc. of the pulse wave; HR represents the heart rate, which represents the number of heartbeats per unit time, usually in the unit of BPM (beats per minute).

[0352] After obtaining the estimated blood pressure value, the estimated blood pressure value can also be smoothed to reduce the noise in the estimated blood pressure value. It performs a moving window average operation on the signal, replacing each data point with the average value of the data in its neighborhood, thereby achieving the smoothing of the estimated blood pressure value. The smoothing algorithm can include: Moving Average Filter, Exponential Moving Average (EMA), and Kalman Filter.

[0353] a) Moving Average Filter.

[0354] The Moving Average Filter is based on the principle of mean filtering and performs an average calculation on continuous sampled data. It sums and averages the sample values of the input signal within a sliding time window. As the window moves along the time axis, new average values are continuously calculated to obtain the filtered output signal. This can effectively suppress high-frequency noise in the signal and make the signal smoother. The specific formula is as follows:

[0355]

[0356] where represents the smoothed systolic blood pressure value at the i-th time, N represents the window size, and SBP j represents the j-th estimated systolic blood pressure; represents the smoothed diastolic blood pressure at the i-th time, and DBP j represents the j-th estimated diastolic blood pressure.

[0357] b) Exponential Moving Average (EMA).

[0358] The Exponential Moving Average assigns exponentially decreasing weights to past observations, with higher weights for more recent data and lower weights for more distant data. This enables it to respond more quickly to new data and track the changing trend of the data more timely. The specific formula is as follows:

[0359]

[0360] Among them, α represents the smoothing factor, usually between 0 and 1, which controls the weight of smoothing.

[0361] c) Kalman Filter.

[0362] The Kalman filter is a recursive filter commonly used to estimate the state of a linear dynamic system from noisy and incomplete data. It is an optimal estimation method that optimizes the estimation by combining the system model and measurement values, including:

[0363] Prediction stage: Based on the current state estimate and the known system model, predict the state at the next moment.

[0364] Update stage: Use the new measurement value to correct the predicted value to obtain a more accurate estimate.

[0365] The formula of the Kalman filter is:

[0366]

[0367] Among them, represents represents or z k represents the current measured value of SBP i or DBP i ; K k represents the Kalman gain, which is used to weigh and the accuracy of SBP i or, used to weigh and the accuracy of DBP i ; A represents the state transition matrix, which describes the change of the system, B represents the control matrix, which controls the influence of the control input on the state, H is the measurement matrix, which represents the relationship between the state and the estimated blood pressure value, and u k is the control input, which is used to describe the external influence on the system.

[0368] VII. Arrhythmia (Rhythm).

[0369] When extracting arrhythmia features, the ECG signal in the target vital sign signal is used.

[0370] The arrhythmia feature extraction algorithm mainly includes QRS detection, HR and HRV extraction, and feature analysis for different types of arrhythmias. The goal is to identify and analyze abnormal rhythms or heartbeat patterns in ECG signals. Using these features, classification and detection of normal and abnormal heart rhythms can be achieved through methods such as machine learning. Arrhythmia detection can be targeted for independent monitoring, so it includes QRS monitoring, extraction of HR heart rate, extraction of HRV heart rate variability, and feature extraction and classification of arrhythmia (Rhythm) monitoring.

[0371] 1) QRS detection.

[0372] The QRS complex is used to identify the starting point of the heartbeat. Accurate detection of the QRS complex is the first step in arrhythmia analysis. The formula is as follows:

[0373]

[0374] Among them, ECG[t] represents the ECG signal in the target vital sign signal, represents the derivative of ECG[t], highlighting the sharp change of the QRS complex, represents the integral of , which helps to identify the width and position of the QRS complex. Thresholding is the set threshold, and QRS(t) represents the position of the QRS complex. It can be specifically achieved through the following steps:

[0375] 1. Signal filtering: First, digitally filter the ECG signal in the target vital sign signal to remove high-frequency noise and baseline drift.

[0376] 2. Derivative and integral: Calculate the derivative and integral of the ECG signal in the target vital sign signal to highlight the characteristics of the QRS complex.

[0377] 3. QRS detection: Detect the QRS complex by setting a threshold.

[0378] 2) Heart rate (HR) extraction.

[0379] Heart rate refers to the number of heartbeats per unit time, usually determined by calculating the rr interval (the time difference between two adjacent R-wave peaks).

[0380] HR calculation can be achieved through the following steps:

[0381] 1. rr interval calculation:

[0382] R - R interval=t R(i+1) -t R(i) ;

[0383] Among them, t R(i)represents the time point of the i-th R wave peak, R-R interval represents the time difference between two adjacent R wave peaks.

[0384] 2. Heart rate (HR) calculation:

[0385] Heart rate is the number of heartbeats per unit time, usually expressed in BPM, and the calculation formula is:

[0386]

[0387] 3) Extraction of heart rate variability (HRV), see "II. Heart rate variability (HRV) characteristics" in the above-mentioned embodiments for details.

[0388] 4) Feature extraction and classification for arrhythmia detection.

[0389] For arrhythmia detection, it is usually necessary to extract abnormal features different from normal heart rhythm (such as PVC, AF, Ventricular Tachycardia, etc.).

[0390] a) Arrhythmia features.

[0391] · Premature Contractions: Refer to QRS waves earlier than expected, which may be PVC (premature ventricular contraction) or PAC (premature atrial contraction).

[0392] · Atrial Fibrillation (AF): AF usually shows irregular QRS waves and an ECG lacking P waves.

[0393] · Ventricular Tachycardia (VT): Usually shows wide and uniformly shaped QRS complexes.

[0394] b) Feature extraction:

[0395] 1. R wave morphology analysis:

[0396] Compare the morphology of the R wave with the typical normal R wave morphology to detect abnormalities.

[0397] R wave morphology: Identify whether there are premature contractions, etc. by comparing the amplitude, width, and shape of the R wave.

[0398] 2. QRS complexity analysis:

[0399] Calculate the width and amplitude of the QRS complex.

[0400] RS complexity: Judge whether there are abnormalities such as ventricular tachycardia by analyzing the complexity of the QRS wave.

[0401] 5) Classification algorithms (such as SVM or neural networks):

[0402] By using machine learning methods (such as support vector machine SVM or CNN neural network), combined with the extracted features (HR, HRV, R-wave morphology, etc.), normal heart rhythms can be classified from various arrhythmias. The formula is as follows:

[0403]

[0404] Wherein, represents the predicted heart rhythm category (normal, atrial fibrillation, premature beats, etc.), and f ML represents the machine learning model obtained through training, which is learned from the process-annotated data for heart rhythm classification.

[0405] The process of comparing vital sign parameters with standard vital sign parameters is introduced in detail below.

[0406] In the VSM (Vital Signs Monitoring) monitoring system, HR (heart rate), RR (respiratory rate), SpO 2 (blood oxygen saturation), BP (blood pressure), HRV (heart rate variability), and temperature are all important physiological signals, which can reflect the health status of an individual. Data analysis and comparison can be achieved through various methods. Next, we will explore how to perform this data analysis and the comparison between different indicators.

[0407] 1. Heart rate (HR) analysis.

[0408] Heart rate is the core indicator for evaluating the health status of the heart and is usually analyzed through the following methods:

[0409] Basic statistical analysis: including the mean, standard deviation, maximum value, and minimum value of the heart rate, etc.

[0410] Time-domain analysis: Based on the RR interval (heartbeat interval), calculate HRV, etc.

[0411] Frequency-domain analysis: Evaluate the change of heart rate through spectral analysis.

[0412] 2. Respiratory rate (RR) analysis.

[0413] Respiratory rate reflects the health status of the respiratory system. The data analysis of RR includes:

[0414] Time-domain analysis: By monitoring the number of breaths per minute, calculate its average value, maximum value, and minimum value.

[0415] Frequency-domain analysis: Use spectral analysis to evaluate the respiratory frequency components and analyze the ratio of low-frequency and high-frequency components.

[0416] 3. Blood oxygen saturation (SpO 2 ) analysis.

[0417] SpO 2 is a key indicator for evaluating oxygenation status. Analysis methods:

[0418] Time-domain analysis: Fluctuations in blood oxygen values are used to calculate their average value.

[0419] Threshold judgment: According to clinical standards, an alarm threshold below 90% or 92% is set.

[0420] 4. Blood pressure (BP) analysis.

[0421] Blood pressure (systolic blood pressure SBP and diastolic blood pressure DBP) reflects the health status of the heart and blood vessel system. Blood pressure analysis includes:

[0422] Time-domain analysis: Calculate the mean, maximum, and minimum values of SBP and DBP.

[0423] Fluctuation analysis: Analyze the blood pressure fluctuations to evaluate cardiovascular health.

[0424] 5. Heart rate variability (HRV) analysis.

[0425] HRV is a key indicator for evaluating the health of the autonomic nervous system and usually adopts:

[0426] Time-domain analysis: Such as SDNN (standard deviation) and RMSSD (root mean square of the differences between adjacent RR intervals), etc.

[0427] Frequency-domain analysis: Evaluate sympathetic and parasympathetic nerve activities by analyzing the ratio of low frequency (LF) to high frequency (HF).

[0428] 6. Body temperature (T) analysis.

[0429] Body temperature is an important physiological indicator for evaluating the body's state and reflects the health status of the immune system and metabolic activities. Body temperature analysis methods:

[0430] Time-domain analysis: Calculate the mean and fluctuations of body temperature.

[0431] Rate of change: Monitor the change of body temperature over time to detect sudden changes in body temperature.

[0432] Data comparison and comprehensive analysis.

[0433] 1) Data correlation analysis.

[0434] Analyze the correlations between HR, RR, SpO 2 , BP, HRV, and T data through Pearson correlation coefficient or Spearman correlation coefficient, etc. For example:

[0435] HR and HRV: High heart rate is usually accompanied by low HRV, indicating strong sympathetic nerve activity.

[0436] HR and BP: High heart rate may be accompanied by elevated blood pressure, especially systolic blood pressure.

[0437] HR and SpO 2 : When the blood oxygen saturation drops, the heart rate usually increases to compensate for insufficient oxygen supply.

[0438] T and HR / SpO 2 : Changes in body temperature may affect heart rate and blood oxygen saturation, especially in febrile or cold environments.

[0439] 2) Multidimensional data analysis and trend comparison.

[0440] Long-term trend analysis: Analyze the long-term trends of HR, RR, SpO 2 , BP, HRV, and T. For example, a gradually increasing heart rate and a gradually decreasing blood oxygen level may indicate certain health problems.

[0441] Short-term fluctuation analysis: By monitoring short-term fluctuations, potential sudden health risks can be detected. For example, a sudden increase in body temperature may indicate fever or infection.

[0442] 3) Risk prediction and health assessment.

[0443] Risk assessment model: Based on multiple physiological indicators (such as HR, RR, SpO 2 , BP, HRV, and T), construct a machine learning model to predict the risk of cardiovascular events, respiratory failure, or infection. For example, high HR, low HRV, low SpO 2 and high T may indicate potential infection.

[0444] Comprehensive health index: Calculate a comprehensive health index using all physiological indicators to detect health problems at an early stage.

[0445] Integrating HR, RR, SpO 2 , BP, HRV, and T data can comprehensively evaluate an individual's physiological status and health risks. Through correlation analysis, trend analysis, and multidimensional data comparison, potential health problems can be more accurately identified and early warnings can be issued.

[0446] The following details the analysis and comparison of arrhythmia Rhythm data.

[0447] 1) Arrhythmia analysis.

[0448] Normal heart rhythm (normal sinus rhythm): Under normal circumstances, the heart rate should be 60 - 100 BPM, and the QRS complex is regular.

[0449] Atrial Fibrillation (AF): An irregular heart rate, commonly in the range of 100 - 175 BPM. At this time, the electrical activity of the atria loses its regularity, and the ventricular beats are irregular.

[0450] Premature Ventricular Contractions (PVC): Premature ventricular contractions usually present with early abnormal QRS complexes, resulting in irregular RR intervals, but generally do not affect the overall heart rate.

[0451] Ventricular Tachycardia (VT): Due to the rapid contraction of the ventricles, the heart rate significantly increases during ventricular tachycardia, usually between 100 - 250 BPM.

[0452] 2) Classification of arrhythmias.

[0453] The classification of arrhythmias can be based on the extracted features. Common classification methods include: Support Vector Machine (SVM), Neural Network, Decision Tree, etc. Feature extraction is as follows:

[0454] Premature Contractions:

[0455] PVC (Premature Ventricular Contractions) or PAC (Premature Atrial Contractions).

[0456] Feature: Abnormal QRS complexes, either narrow or wide, with different morphologies.

[0457] Atrial Fibrillation (AF):

[0458] Feature: Irregular R wave complexes, without obvious P waves.

[0459] During atrial fibrillation, the RR intervals are irregular and fluctuate greatly.

[0460] Ventricular Tachycardia (VT):

[0461] Feature: Wide and uniformly shaped QRS complexes, fast heartbeats.

[0462] 3) Machine learning classification.

[0463] Machine Learning Classification (Heart Rhythm Classification)

[0464] Machine learning classification is used to classify heart rhythms based on the features extracted from ECG signals. Commonly used machine learning algorithms include Support Vector Machine (SVM), Random Forest (RF), Neural Network, etc.

[0465] ① Feature input:

[0466] Features extracted from the ECG signal of the target vital signs are used as input to a machine learning model for classification. Common features include:

[0467] HR (heart rate), HRV (heart rate variability), QRS complex features (such as amplitude, width, etc.), P wave and T wave features, rr interval.

[0468] ② Machine learning model:

[0469] Training phase:

[0470] X train : Training dataset, containing features and corresponding labels (rhythm types).

[0471] Y train : Labels in the training dataset (such as normal, atrial fibrillation, ventricular premature beats, etc.).

[0472] f ML (Xtrain): Trained machine learning model.

[0473] Classification phase:

[0474] Xnew: New input data (extracted features).

[0475] Predicted rhythm type, for example: normal rhythm, atrial fibrillation, ventricular premature beats, etc., the output of the model.

[0476] Formula of the model:

[0477]

[0478] Arrhythmia comparative analysis.

[0479] Arrhythmia comparative analysis is mainly carried out by comparing the feature differences between different arrhythmia types. Common methods include comparing heart rate (HR), rr interval, etc. Common arrhythmia feature comparison:

[0480] ① Normal rhythm:

[0481] · The normal ECG signal shows regular rr intervals and a stable heart rate.

[0482] · HRnormal: Normal heart rate, usually 60 - 100 BPM.

[0483] · Atrial fibrillation (AF):

[0484] · Features: Irregular rr intervals, lack of P waves, unstable heart rate.

[0485] · The rr intervals during atrial fibrillation fluctuate greatly and change frequently.

[0486] · Premature ventricular contraction (PVC):

[0487] · Characteristics: Premature QRS complexes with abnormal morphology.

[0488] · The rr interval during PVC is advanced and irregular.

[0489] · Ventricular tachycardia (VT):

[0490] · Characteristics: Wide QRS complexes and a very fast heart rate.

[0491] · HRVT: When ventricular tachycardia occurs, the heart rate is relatively high, usually above 150 BPM.

[0492] ② Comparative analysis formula:

[0493] rr interval difference:

[0494] By comparing the rr intervals in different cardiac rhythm states, the type of arrhythmia is judged. The formula is as follows:

[0495] ΔR-R = |(R-R current ) - (R-R baseline )|;

[0496] Where, ΔR-R represents the difference between the current rr interval and the baseline interval, used to identify abnormal heart rates; R-R current represents the currently detected rr interval, and R-R baseline represents the rr interval of the baseline normal cardiac rhythm.

[0497] Heart rate difference (HR):

[0498] By comparing the changes in heart rate, especially the fluctuations during abnormal cardiac rhythms, the formula is:

[0499] ΔHR = |HR current - HR baseline |;

[0500] Where, ΔHR represents the difference between the current heart rate and the baseline heart rate, used to identify abnormal cardiac rhythms; HR current represents the currently measured heart rate; HR baseline represents the normal heart rate (usually 60 - 100 BPM).

[0501] Ratio characteristics: The ratio of HR and rr interval is used to further compare different types of arrhythmias.

[0502]

[0503] Where, Ratio represents the ratio characteristic used to distinguish the types of arrhythmias.

[0504] In arrhythmia analysis, machine learning classification methods predict the type of heart rhythm by extracting features of the ECG signal (such as HR, HRV, QRS features, etc.). In arrhythmia comparative analysis, by comparing features (such as r-r interval, heart rate, etc.) under different heart rhythm states, different types of arrhythmias (such as normal, atrial fibrillation, premature ventricular contractions, ventricular tachycardia, etc.) can be further distinguished.

[0505] The arrhythmia Rhythm standard is shown in Table 6:

[0506] Table 6

[0507]

[0508] It should be noted that the hardware design in this disclosure complies with YY9706.102-2021 "Medical Electrical Equipment, Part 1-2: General Requirements for Basic Safety and Basic Performance Collateral Standard: Electromagnetic Compatibility Requirements and Tests"; complies with GB 9706.1-2020 "Medical Electrical Equipment, Part 1: General Requirements for Basic Safety and Basic Performance"; complies with GB 9706.227-2021 "Medical Electrical Equipment, Part 2-27: Applicable Requirements in the Special Requirements for Basic Safety and Basic Performance of Electrocardiogram Monitoring Equipment"; the hardware design complies with YY9706.247-2021 "Medical Electrical Equipment, Part 2-47: Applicable Requirements in the Special Requirements for Basic Safety and Basic Performance of Ambulatory Electrocardiogram Systems".

[0509] Key technical advantages in this disclosure:

[0510] 1. Non-networked design: Real-time data analysis, alerts, privacy, and local storage and monitoring reports, operating completely independently without a network, ensuring data security.

[0511] 2. Vital sign parameters (such as: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO 2 )), T (body temperature), HRV (heart rate variability), Rhythm arrhythmia (AF (atrial fibrillation), PVC (premature ventricular contractions), VT (ventricular tachycardia), etc.) are monitored and warning prompts are given to the wearer or carrier himself.

[0512] 3. Based on age, gender, height, weight, altitude (3000m; or select > 3000m).

[0513] 4. Monitoring type: Automatic monitoring or selective targeted monitoring (such as patients with arrhythmia, myocardial infarction, etc.).

[0514] 5. Portability: The solution is small in size and light in weight, suitable for carrying and adaptable to various environments.

[0515] 6. High energy efficiency: Low-power design and efficient power management support long-term continuous operation.

[0516] Advantages of the present disclosure

[0517] 1. Users can timely grasp their health status, effectively prevent acute diseases, and have broad market application prospects. The system does not rely on an external network or external system and has the ability to operate independently, ensuring the application of the intended use in environments without a network, environments where the network solution fails, and environments where privacy protection is required.

[0518] 2. The embedded algorithm can quickly and effectively diagnose vital signs, reducing misdiagnosis and missed diagnosis problems caused by delays.

[0519] 3. Real-time - When the user's heart rate, blood oxygen saturation, and respiratory rate values are abnormal, timely visual, auditory, and tactile alerts are given, winning life-saving time at critical moments.

[0520] 4. Adopts a low-power design for long battery life, suitable for scenarios of long-term wear.

[0521] 5. The device also has a human-computer interaction function, facilitating human-computer voice interaction settings.

[0522] 6. The device allows users to select the SOS function.

[0523] 7. Suitable for wide application in user groups such as chronic disease patients, the elderly, and sports enthusiasts, applicable to various scenarios such as home, hospital, work, and outdoor sports.

[0524] 1) Emergency rescue: Monitor vital signs in disaster areas, the wild, or on the battlefield.

[0525] 2) Hospital monitoring: As a supplementary device for monitoring the vital signs of hospital patients.

[0526] 3) Home care: Suitable for the health monitoring of chronic disease patients or the elderly.

[0527] 4) Remote areas: Do not rely on a network and can operate independently in remote areas.

[0528] 5) High-altitude areas: Such as areas above 3000m.

[0529] 6) Protected populations: For the vital sign values of individuals, there is no worry about network leakage for national political figures and people who need privacy protection. The monitoring and warning only prompt themselves.

[0530] In one embodiment, as Figure 3 shown, the medical-grade VSM dynamic monitoring system in the present disclosure further includes: an early warning prompt module 7;

[0531] The early warning prompt module 7 is respectively connected to the data processing module 3 and the power management module 5;

[0532] The data processing module 3 is further configured to generate an early warning signal when abnormal vital sign parameters are determined according to the comparison result, and send the early warning signal to the early warning prompt module 7;

[0533] The early warning prompt module 7 outputs an early warning signal.

[0534] In one embodiment, the early warning prompt module 7 may have the function of voice broadcast prompt for vital sign measurement values, such as visual, auditory or tactile early warning prompts.

[0535] At this time, in terms of outputting the early warning signal, the early warning prompt module 7 is specifically configured to:

[0536] Output the early warning signal in a visual form, such as outputting the early warning signal through a three-color LED or a display screen, etc. When outputting the early warning signal through the three-color LED, different early warning levels can be set according to different lights:

[0537] Green (normal): All parameters are within the normal range.

[0538] Yellow (warning): Some parameters are close to the early warning threshold but have not exceeded the threshold (such as HR is slightly higher than the normal range but has not reached the dangerous level).

[0539] Red (emergency): Some parameters exceed the early warning threshold and immediate attention is required (such as SpO 2 drops below 85% and HR is below 50 BPM).

[0540] Or,

[0541] Output the early warning signal in an auditory form, such as outputting the early warning signal through voice (including but not limited to Chinese, English) or a buzzer, a speaker, etc.

[0542] Or,

[0543] Output the early warning signal in a tactile form, such as outputting the early warning signal through a vibration motor.

[0544] In the VSM (Vital Signs Monitoring) system, after data preprocessing and feature extraction, and after completing data analysis and comparison, the generation of the early warning system and the monitoring report are the next key steps. For each monitoring parameter (such as: HR, RR, SpO 2 , BP, HRV, T, AF, PVC, VT), the early warning and the provision of the monitoring report can be designed through the following steps.

[0545] The reference table of the standard parameters of the vital sign VSM is shown in Table 2 and Table 3. The normal physiological value ranges of the standard parameters of the vital sign VSM in the resting state, static rest state, gait state, running state, falling state, and rapid movement state grouped by age are defined as the warning thresholds.

[0546] The following methods can be used to trigger warnings:

[0547] Rule-based warning: Based on predefined threshold rules, an alarm is triggered when a certain parameter exceeds the threshold.

[0548] For example: If HR > 100 BPM, a high heart rate alarm is triggered.

[0549] Machine learning-based warning: By training a machine learning model, patterns in different states are learned from historical data to identify potential danger signals. For example, support vector machine (SVM) or random forest (RandomForest) is used to comprehensively analyze HR, SpO 2 and BP data to determine whether there are abnormal patterns.

[0550] In the present disclosure, warnings can be promptly issued through the warning prompt module 7, so that users can execute corresponding emergency strategies based on the warning signals. In this way, the warnings or emergency measures are in the hands of the wearer himself, avoiding delays in treatment.

[0551] From the above analysis, it can be seen that the present disclosure provides a completely local (without network) solution, which uses biometrics (such as photoplethysmography PPG) and bioimpedance BIOZ, electrocardiogram ECG sensors, and digital temperature sensors to collect data. The data processing module 3 independently performs real-time data analysis, completes real-time collection, processing, and warning or monitoring reports of vital signs to the wearer, taking into account portability and efficient, low-power design of wearables, improving the real-time performance and accuracy of monitoring, ensuring data privacy, and intervening in advance before unexpected health events occur, meeting the data security and high reliability requirements in different application scenarios.

[0552] The core elements of the present disclosure:

[0553] 1. This solution focuses on completely local (without external network) real-time vital sign data analysis, alarms, privacy, and local storage and monitoring reports.

[0554] 2. Vital sign (VSM) monitoring: including but not limited to: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO 2 ), T (body temperature), HRV (heart rate variability), Rhythm arrhythmia (AF (atrial fibrillation), PVC (premature ventricular contraction), VT (ventricular tachycardia)).

[0555] 3. Targeted monitoring and early warning. Implement targeted monitoring and early warning for patients diagnosed with Rhythm arrhythmia, myocardial infarction, etc.

[0556] 4. No need for external analysis graphs, based on internal analysis and model verification technology. It means that non-professionals can directly view the results of the monitoring report.

[0557] 5. Collecting information related to the patient (basic information such as age, gender, height, weight, altitude, arrhythmia patients, etc.) and exercise status, etc., to improve the quality of analysis and processing.

[0558] 6. Based on the current collection, warn of the risk change trend of vital signs (VSM).

[0559] 7. Local paperless monitoring report.

[0560] 8. This solution provides a reliable, private and autonomous continuous (such as 1 - 15 days) health monitoring method, without the need for an external network to protect the privacy of users, a private and autonomous continuous health monitoring method.

[0561] 9. This solution ensures that no matter what environment the user is in, such as: exercise, indoors, outdoors, at work, sleeping, in a nursing home, a medical institution, etc., as well as in environments such as high altitude, war, natural disasters, etc., the user can obtain accurate health information and instant feedback to the wearer himself.

[0562] 10. Combined hardware: Vital sign sensors (i.e., the wearable sensor 11 in the above embodiments), analog front end 12, and data processing module 3 (which can include FPU - MCU or RNN - MCU or CNN - MCU or AI MCU), etc., to build a hardware combination structure. At least one or more FPU - MCUs (or RNN - MCUs or CNN - MCUs or AI MCUs) centrally process or separately process the analysis of vital sign data such as heart rate, respiratory rate, blood oxygen, filtering, sign extraction, motion artifacts, data judgment, etc. The microprocessors involved have ultra - low power consumption, high efficiency, and high reliability (meeting the reliability requirements of medical - grade applications).

[0563] 11. This solution provides a hardware requirement of ±50mVP - p to ±200mVP - p AC dynamic input range to prevent measurement saturation (signal integrity), and implements an acceleration motion artifact processing algorithm.

[0564] 12. The independent use or combined use of accelerometers, gyroscopes, and magnetometers, combined with 5, implements an independent motion artifact processing algorithm - the acceleration VSM signal pre - processing algorithm, which is one of the core algorithms for acceleration to participate in filtering.

[0565] 13. The embedded convolutional neural network vital sign (VSM) eigenvalue extraction algorithm is one of the core algorithms. However, the extraction of single or a small number of vital sign parameter features is not limited to using other methods.

[0566] 14. Automatically and precisely match 6 motion states: stationary state, static rest state, gait state, running state, fall state, fast motion state, without the wearer having to set them.

[0567] 15. The vital sign (VSM) monitoring solution can manufacture single-parameter monitoring devices (such as: respiratory rate (RR)), or can also manufacture devices for multi-parameter monitoring of vital signs (VSM) (such as: including but not limited to: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO 2 )), T (body temperature), HRV (heart rate variability), Rhythm arrhythmia (AF (atrial fibrillation), PVC (ventricular premature beat), VT (ventricular tachycardia)).

[0568] 16. It can be extended to heart sounds, lung breath sounds, etc.

[0569] 17. It can be extended to manufacture local non-wearable vital sign (VSM) early warning monitoring devices to make comprehensive physical examination indicators.

[0570] Based on the same inventive concept, an embodiment of the present application further provides a medical-grade VSM dynamic monitoring method for the medical-grade VSM dynamic monitoring system involved above. The implementation solutions provided by this method for solving problems are similar to the implementation solutions recorded in the above system. Therefore, the specific limitations in one or more embodiments of the medical-grade VSM dynamic monitoring method provided below can refer to the limitations on the medical-grade VSM dynamic monitoring system in the above text, and will not be repeated here. In an exemplary embodiment, the present disclosure further provides a medical-grade VSM dynamic monitoring method, which is applied to a medical-grade VSM dynamic monitoring system. The medical-grade VSM dynamic monitoring system includes: a sensing module, an inertial measurement module, a data processing module, a display and interaction module, a warning and prompt module, and a power management module. The data processing module is respectively connected to the inertial measurement module and the display and interaction module; the power management module is respectively connected to the inertial measurement module, the data processing module, and the display and interaction module. The method includes: the display and interaction module obtains the basic information of the user to be monitored, and the basic information includes: age, gender, height, weight, altitude, and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring; the sensing module measures the vital sign signal and sends the vital sign signal to the data processing module; the inertial measurement module measures the inertial signal and sends the inertial signal to the data processing module; the data processing module obtains the vital sign parameters of the user to be monitored according to the inertial signal and the vital sign signal, obtains the vital sign standard parameters according to the basic information and the inertial signal, compares the vital sign parameters with the vital sign standard parameters, generates a monitoring report according to the comparison result, and sends the monitoring report to the display and interaction module; the display and interaction module outputs the monitoring report.

[0571] In one embodiment, the medical-grade VSM dynamic monitoring system further includes: a warning prompt module; the warning prompt module is respectively connected to the data processing module and the power management module; the method further includes: when the data processing module determines that there are abnormal vital sign parameters according to the comparison result, generating a warning signal and sending the warning signal to the warning prompt module; the warning prompt module outputs the warning signal. In one embodiment, the medical-grade VSM dynamic monitoring system further includes: an SOS rescue module; the SOS rescue module is respectively connected to the data processing module and the power management module; the method further includes: when the data processing module determines that there are abnormal vital sign parameters according to the comparison result, generating a help signal and sending the help signal to the SOS rescue module; after receiving the help signal, the SOS rescue module executes a preset help measure, and the preset help measure includes: sending a distress message to a preset emergency contact person, and / or sending a distress message to a rescue agency.

[0572] In one embodiment, the sensing module includes: a wearable sensor and an analog front end; the analog front end is respectively connected to the wearable sensor, the data processing module and the power management module; the method further includes: the wearable sensor collects raw vital sign signals and sends the collected raw vital sign signals to the analog front end; the analog front end preprocesses the received raw vital sign signals to obtain the vital sign signals.

[0573] In one embodiment, the vital sign signals include at least one of the following signals: ECG signal, PPG signal, BIOZ signal, and temperature signal. In one embodiment, the vital sign parameters include at least one of the following parameters: heart rate, heart rate variability, respiratory rate, blood oxygen saturation, body temperature, blood pressure, and arrhythmia. In one embodiment, the outputting of the warning signal includes: outputting the warning signal in a visual form; or outputting the warning signal in an auditory form; or outputting the warning signal in a tactile form.

[0574] In one embodiment, the method further includes: the data processing module obtains medical advice according to the abnormal vital sign parameters, and the medical advice provides measures for the user to be monitored to cope with the abnormal vital sign parameters; the monitoring report includes: the vital sign parameters, the abnormal vital sign parameters, and the medical advice.

[0575] In one embodiment, the method further includes: the data processing module obtaining the body mass index of the user to be monitored according to the height and the weight; the data processing module obtaining a body mass index coefficient and an altitude coefficient according to the target basic parameter; the target basic parameter including: the body mass index, or, the altitude; the data processing module optimizing the inertial signal according to the body mass index coefficient and the altitude coefficient; the data processing module determining the vital sign parameter of the user to be monitored according to the optimized inertial signal and the vital sign signal.

[0576] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A medical-grade VSM dynamic monitoring system, characterized in that: The medical-grade VSM dynamic monitoring system includes: a sensor module, an inertial measurement module, a data processing module, a display and interaction module, and a power management module; The data processing module is connected to the sensor module, the inertial measurement module and the display and interaction module respectively; the power management module is connected to the inertial measurement module, the data processing module and the display and interaction module respectively; The display and interaction module is used to obtain basic information of the user to be monitored, and the basic information includes: age, gender, height, weight, altitude and monitoring mode; the monitoring mode includes: automatic monitoring or selective targeted monitoring; The sensor module is used to measure the vital sign signal of the user to be monitored and send the vital sign signal to the data processing module; The inertial measurement module is used to measure the inertial signal of the user to be monitored and send the inertial signal to the data processing module; The data processing module is used to obtain the vital sign parameters of the user to be monitored according to the inertial signal and the vital sign signal, obtain the standard vital sign parameters according to the basic information and the inertial signal, compare the vital sign parameters with the standard vital sign parameters, generate a monitoring report according to the comparison result, and send the monitoring report to the display and interaction module; The display and interaction module is used to output the monitoring report.

2. The VSM dynamic monitoring system according to claim 1, characterized in that: Also includes: Early warning module; The early warning prompt module is connected to the data processing module and the power management module respectively; The data processing module is further configured to generate a warning signal when abnormal vital sign parameters are determined according to the comparison result, and send the warning signal to the warning prompt module; The early warning prompt module is used to output the early warning signal.

3. The VSM dynamic monitoring system according to claim 2, characterized in that: Also includes: SOS rescue module; The SOS rescue module is connected to the data processing module and the power management module respectively; The data processing module is further configured to generate a help signal when abnormal vital sign parameters are determined according to the comparison result, and send the help signal to the SOS rescue module; The SOS rescue module is used to execute a preset rescue means after receiving the rescue signal. The preset rescue means include: sending a rescue message to a preset emergency contact, and / or sending a rescue message to a rescue organization.

4. The VSM dynamic monitoring system according to claim 1, characterized in that: The sensing module includes: a wearable sensor and an analog front end; The analog front end is respectively connected to the wearable sensor, the data processing module and the power management module; The wearable sensor is used to collect original vital sign signals and send the collected original vital sign signals to the analog front end; The analog front end is used to preprocess the received original vital sign signal to obtain the vital sign signal.

5. The VSM dynamic monitoring system according to claim 1, characterized in that: The vital sign signal includes at least one of the following signals: an ECG signal, a PPG signal, a BIOZ signal and a temperature signal.

6. The VSM dynamic monitoring system according to claim 1, characterized in that: The vital sign parameters include at least one of the following parameters: heart rate, heart rhythm variability, respiratory rate, blood oxygen saturation, body temperature, blood pressure and arrhythmia.

7. The VSM dynamic monitoring system according to claim 2, characterized in that: In terms of outputting the warning signal, the warning prompt module is specifically used to: Outputting the warning signal in a visual form; or, Outputting the warning signal in an auditory form; or, The warning signal is output in a tactile form.

8. The VSM dynamic monitoring system according to claim 2, characterized in that: The data processing module is further used for: Obtaining medical advice according to the abnormal vital sign parameters, wherein the medical advice provides the monitored user with measures to deal with the abnormal vital sign parameters; The monitoring report includes: The vital sign parameters, the abnormal vital sign parameters and the medical advice.

9. The VSM dynamic monitoring system according to claim 1, characterized in that: The data processing module is specifically used for: Acquire the body mass index of the user to be monitored according to the height and the weight; Obtaining a body mass index coefficient and an altitude coefficient according to target basic parameters; the target basic parameters include: the body mass index, or the altitude; Optimizing the inertial signal according to the body mass index coefficient and the altitude coefficient; The vital sign parameters of the user to be monitored are determined according to the optimized inertial signal and the vital sign signal.

10. A medical-grade VSM dynamic monitoring method, characterized in that: The method is applied to the medical-grade VSM dynamic monitoring system according to any one of claims 1 to 9, wherein the medical-grade VSM dynamic monitoring system comprises: a sensor module, an inertial measurement module, a data processing module, a display and interaction module, an early warning prompt module and a power management module, wherein the data processing module is respectively connected to the inertial measurement module and the display and interaction module; the power management module is respectively connected to the inertial measurement module, the data processing module and the display and interaction module, and the method comprises: The display and interaction module obtains basic information of the user to be monitored, the basic information including age, gender, height, weight, altitude and monitoring mode; the monitoring mode includes automatic monitoring or selective targeted monitoring; The sensing module measures vital sign signals and sends the vital sign signals to the data processing module; The inertial measurement module measures the inertial signal and sends the inertial signal to the data processing module; The data processing module obtains the vital sign parameters of the user to be monitored according to the inertial signal and the vital sign signal, obtains the standard vital sign parameters according to the basic information and the inertial signal, compares the vital sign parameters with the standard vital sign parameters, generates a monitoring report according to the comparison result, and sends the monitoring report to the display and interaction module; The display and interaction module outputs the monitoring report.

Images