Health condition monitoring device based on intelligent sensing technology and safety emergency system

Abstract

The invention relates to the technical field of monitoring devices, in particular to a health condition monitoring device and safety emergency system based on an intelligent sensing technology, comprising a wearable terminal which comprises a wearable waistcoat, a composite heating module and a multi-mode sensor, the wearable terminal is in communication connection with the multi-mode sensor through the composite heating module, and a closed-loop temperature control system is formed. The central processing unit is fixedly arranged on the wearable terminal and establishes communication connection with the environment sensing base station in a wireless mode; physiological data such as heart rate, blood oxygen, body temperature and motion posture are collected through the wearable terminal, wind speed, temperature and air pressure are monitored in real time through the environment base station, meanwhile, dynamic health risk indexes are calculated through the LSTM neural network through the central processing unit, physiological and environment risks are comprehensively evaluated, industrial pain points of construction monitoring in the high-oxygen and high-cold areas are solved, and the construction safety of the high-oxygen and high-cold areas is improved. The method has reliability, accuracy and high efficiency, and is a revolutionary breakthrough of safety management of plateau operation.

Description

Technical Field

[0001] This invention relates to a health status monitoring device and emergency system, and more particularly to a health status monitoring device and safety emergency system based on intelligent sensing technology, belonging to the field of monitoring device technology. Background Technology

[0002] Challenges of working on high-altitude terrain: Frequent health risks such as abnormal heart rate and decreased blood oxygen levels due to low oxygen and low temperature; existing monitoring equipment has the following deficiencies: 1. Monitoring a single parameter (such as blood oxygen or heart rate only) cannot comprehensively assess health status; 2. Battery life drops sharply in low-temperature environments (battery life of conventional devices <8 hours); 3. Severe weather conditions cause a wireless signal transmission failure rate greater than 40%; 4. Lack of an emergency rescue mechanism linked to the positioning system; However, the error problem of multi-sensor data fusion algorithms in low signal-to-noise ratio environments has not yet been solved, and the system warning response delay proposed in related papers is 5-8 minutes, which cannot meet the golden time requirement for emergency rescue.

[0003] Therefore, it is urgent to improve the monitoring devices and emergency systems to solve the aforementioned problems. Summary of the Invention

[0004] The purpose of this invention is to provide a health status monitoring device and safety emergency system based on intelligent sensing technology. It collects physiological data such as heart rate, blood oxygen, body temperature, and movement posture through wearable terminals, monitors wind speed, temperature, and air pressure in real time through environmental base stations, and calculates a dynamic health risk index through a central processing unit using an LSTM neural network to comprehensively assess physiological and environmental risks. This invention solves the industry pain point of construction monitoring in high-oxygen and high-altitude areas, and has the advantages of reliability, accuracy, and efficiency. It is a revolutionary breakthrough in safety management of high-altitude operations.

[0005] To achieve the above objectives, the main technical solutions adopted by the present invention include: A health status monitoring device and safety emergency system based on intelligent sensing technology, comprising: A wearable terminal, comprising a wearable vest and a composite heating module and a multimodal sensor disposed on the wearable vest, wherein the wearable terminal establishes a communication connection with the multimodal sensor through the composite heating module and forms a closed-loop temperature control system; Environmental sensing base stations, which are deployed in the area surrounding the operation; and Central processing unit, which is used for data analysis and emergency response; The central processing unit is fixedly mounted on the wearable terminal and establishes a communication connection with the environmental sensing base station wirelessly.

[0006] Preferably, the vest includes a carrying strap, and the composite heating module includes a rear heating module and a front heating module. The rear heating module is fixedly mounted on the carrying strap, and the front heating module is connected to the carrying strap via a quick-release buckle. The vest is connected to a wristband, which is fixed to the wrist with Velcro. The wristband is equipped with a temperature sensor for real-time monitoring of the skin temperature on the wrist. The temperature sensor establishes a communication connection with the composite heating module.

[0007] Preferably, an electrical box is fixedly installed at the bottom of the front heating module, and both the composite heating module and the multimodal sensor are fixedly installed inside the electrical box.

[0008] Preferably, the composite heating module includes a graphene heating element, which is integrated into the inner layer of the wristband; The three-level gradient heating controller automatically activates stepped heating when the skin temperature is below 28°C.

[0009] Preferably, the multimodal sensor includes an optical sensor module, employing a dual-wavelength LED light source of 850nm and 940nm, and configured with a dynamic calibration algorithm; A three-axis accelerometer with a sampling rate of ≥500Hz is used for attitude recognition and fall detection. The skin conductance sensor has an impedance measurement range of 1kΩ-10MΩ and supports stress state monitoring.

[0010] Preferably, the optical sensor module includes: Photodiode array, signal-to-noise ratio > 60dB; Adaptive filter circuit, operating temperature range -40℃~+50℃; Blood oxygen saturation calculation unit, error range ±1.5%.

[0011] Preferably, both the composite heating module and the multimodal sensor establish a communication connection with the central processing unit, and the central processing unit is equipped with a dual-mode communication module, an anti-interference antenna, and an encrypted transmission unit. The dual-mode communication module simultaneously supports Bluetooth 5.2 and LoRa protocols, and establishes a communication connection with the environmental sensing base station wirelessly. The anti-interference antenna adopts a ceramic substrate design; The encrypted transmission unit implements hardware encryption using the SM4 national cryptographic algorithm.

[0012] Preferably, the environmental sensing base station includes a micro-meteorological monitoring unit, a BeiDou / GPS dual-mode positioning module, and an emergency broadcasting unit; The micro-meteorological monitoring unit integrates sensors for wind speed of 0-60m / s, temperature of -50℃ to +50℃, and air pressure of 300-1100hPa. The horizontal positioning accuracy of the BeiDou / GPS dual-mode positioning module is 1.5m CEP. The emergency broadcast unit includes a 120dB directional sound wave transmitter and an LED strobe light.

[0013] Preferably, the central processing unit is configured with an LSTM neural network acceleration unit, a multi-source data fusion algorithm, a hierarchical early warning decision tree, and a network security module. The network security module is used to monitor equipment anomalies and shut down the equipment in an emergency. The LSTM neural network acceleration unit includes physiological sensors, environmental sensors, and motion sensors, and is dedicated to calculating the HRI index. The sampling window time of the multi-source data fusion algorithm is ≤5 seconds, and the response delay of the hierarchical early warning decision tree is <100ms.

[0014] Preferably, the LSTM neural network acceleration unit uses an LSTM neural network to establish a dynamic risk index (HRI) and collects physiological and environmental parameters in real time. The risk parameters are calculated using the following formula: ; = HR - HR0; in, , as well as These are the weighting coefficients. =0.35, =0.5, =0.15; It represents the change in heart rate, that is, the difference between the current heart rate and the reference heart rate; HR is the real-time measured heart rate, and HR0 represents the baseline heart rate or initial heart rate; SpO 20 Indicates baseline or initial blood oxygen saturation; SpO2 represents the currently measured blood oxygen saturation; T represents the temperature in a specific environment or inside the body; It is an exponential term that describes the effect of temperature on HRI, and e is the base of the natural logarithm; A graded response mechanism is triggered based on the HRI threshold.

[0015] Preferably, the hierarchical response mechanism includes: When 0.7 ≤ HRI < 1.0, activate near-field rescue within a 500m range; When 1.0 ≤ HRI < 1.5, dispatch the medical station and activate emergency oxygen supply; When HRI ≥ 1.5, activate the helicopter rescue channel.

[0016] Preferably, the specific algorithm of the multi-source data fusion algorithm is as follows: Information is pushed to the time alignment module through the physiological sensor, the environmental sensor, and the motion sensor; The time alignment module performs feature-level fusion; Then, decision-level fusion is performed; Finally, a risk warning will be issued.

[0017] Preferably, the environmental sensing base station and the central processing unit communicate using the following method: Redundant communication links, including 4G / 5G backup channels; Time synchronization protocol, error <1ms; Distributed data storage architecture.

[0018] Preferably, the composite heating module is electrically connected to a storage battery, and the composite heating module has an energy efficiency ratio of ≥85% and a temperature control accuracy of ±0.5℃.

[0019] The present invention has at least the following beneficial effects: 1. It collects physiological data such as heart rate, blood oxygen, body temperature, and movement posture through wearable terminals, and monitors wind speed, temperature, and air pressure in real time through environmental base stations. At the same time, it calculates a dynamic health risk index through an LSTM neural network via a central processor, comprehensively assessing physiological and environmental risks. This solves the industry pain point of construction monitoring in high-oxygen and high-altitude areas, and has the advantages of reliability, accuracy, and efficiency. It is a revolutionary breakthrough in safety management of high-altitude operations.

[0020] 2. The multimodal sensor includes an optical sensor module employing dual-wavelength LED light sources of 850nm and 940nm. The optical sensor module includes: a photodiode array with a signal-to-noise ratio >60dB, an adaptive filtering circuit, an operating temperature range of -40℃ to +50℃, a blood oxygen saturation calculation unit with an error range of ±1.5%, configured with a dynamic calibration algorithm, a triaxial accelerometer with a sampling rate ≥500Hz for posture recognition and fall detection, and a skin conductance sensor with an impedance measurement range of 1kΩ-10MΩ, supporting stress state monitoring. Through innovative hardware design, intelligent algorithms, and system integration, it solves key technical challenges such as the reliability, data accuracy, and timeliness of emergency response of monitoring equipment in high-altitude and cold environments. Compared with existing technologies, it represents a significant improvement, thereby enhancing user safety. Attached Figure Description

[0021] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a system schematic diagram of the present invention; Figure 2 This is the electrical schematic diagram of the present invention; Figure 3 This is a flowchart of the multi-source data fusion algorithm of the present invention.

[0022] In the diagram, 1. Wearable terminal; 101. Wearable vest; 102. Composite heating module; 1021. Rear heating module; 1022. Front heating module; 103. Multimodal sensor; 104. Wearable strap; 105. Quick-release clip; 106. Wristband; 107. Temperature sensor; 108. Electrical box; 109. Graphene heating element; 110. Three-level gradient heating controller; 2. Environmental sensing base station; 201. Micro-meteorological monitoring unit; 202. Beidou / GPS dual-mode positioning module; 203. Emergency broadcasting unit; 3. Central processing unit; 301. Dual-mode communication module; 302. Anti-interference antenna; 303. Encrypted transmission unit; 304. LSTM neural network acceleration unit; 305. Multi-source data fusion algorithm; 306. Hierarchical early warning decision tree; 4. Battery. Detailed Implementation

[0023] The following will describe in detail the implementation of this application with reference to the accompanying drawings and embodiments, so that the implementation process of how this application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0024] like Figures 1-3 As shown, the health status monitoring device and emergency system based on intelligent sensing technology provided in this embodiment include: Wearable terminal 1 includes a wearable vest 101, a composite heating module 102 and a multimodal sensor 103 mounted on the wearable vest 101. Wearable terminal 1 establishes a communication connection with multimodal sensor 103 through composite heating module 102 and forms a closed-loop temperature control system. Composite heating module 102 includes a graphene heating element 109 integrated into the inner layer of wristband 106 and a three-level gradient heating controller 110. When the skin temperature is <28℃, it automatically starts stepped heating. The heating element is only 0.2mm thick and the heating rate reaches 3.2℃ / W. In an environment of -40℃, it can raise the wrist temperature from 28℃ to 35℃ in 30 seconds. Compared with the traditional resistance wire solution, the energy consumption is reduced by 40% and the weight is reduced by 57% (only 18g). Three-level gradient heating, dynamically adjusting power (1.5W / 3W / 5W) according to skin temperature to avoid burns or energy waste; Environmental sensing base station 2 is deployed in the area surrounding the operation site; and Central Processing Unit 3 (CPU 3) is used for data analysis and emergency response; The central processing unit 3 is fixedly mounted on the wearable terminal 1 and establishes a wireless communication connection with the environmental sensing base station 2. The environmental sensing base station 2 and the central processing unit 3 adopt a redundant communication link, including a 4G / 5G backup channel, a time synchronization protocol, an error of <1ms, and a distributed data storage architecture. The composite heating module 102 is electrically connected to a battery 4. The energy efficiency ratio of the composite heating module 102 is ≥85%, and the temperature control accuracy is ±0.5℃. The wearable terminal 1 collects physiological data such as heart rate, blood oxygen, body temperature, and movement posture (500Hz sampling rate). The environmental base station 2 monitors wind speed (0-60m / s), temperature (-50℃~+50℃), and air pressure (300-1100hPa) in real time. At the same time, the central processing unit 3 calculates the dynamic health risk index (HRI) through an LSTM neural network to comprehensively assess physiological and environmental risks. This system solves the industry pain points of construction monitoring in high-oxygen and high-altitude areas through three core technologies: intelligent sensing, extreme environment adaptation, and real-time response. It has the advantages of reliability, accuracy, and efficiency, and is a revolutionary breakthrough in the safety management of high-altitude operations.

[0025] Furthermore, such as Figure 1 and Figure 2 As shown, the vest 101 includes a wearing strap 104, and the composite heating module 102 includes a rear heating module 1021 and a front heating module 1022. The rear heating module 1021 is fixedly mounted on the wearing strap 104, and the front heating module 1022 is connected to the wearing strap 104 by a quick-release clip 105. After the user finishes wearing the vest 101, the rear heating module 1021 is positioned on the user's back, and the front heating module 1022 is worn on the user's chest. The front heating module 1022 is fixed to the vest 101 by the quick-release clip 105, thus making it easy to wear and improving the convenience of use. It can also monitor the user's physiological data such as heart rate, blood oxygen, body temperature, and exercise posture in real time. The vest 101 is connected to a wristband 106, which is fixed to the wrist with Velcro. The wristband 106 is equipped with a temperature sensor 107, which is used to monitor the skin temperature of the wrist in real time. The temperature sensor 107 establishes a communication connection with the composite heating module 102. The wristband 106 is fixed to the vest 101 and fixed to the user's wrist with Velcro. The temperature sensor 107 collects the temperature of the user's wrist. The whole structure is simple and has high timeliness. When the temperature sensor 107 detects a low temperature, it transmits the temperature information to the central processing unit 3 and generates heat through the composite heating module 102 to restore the user's body temperature. An electrical box 108 is fixedly installed at the bottom of the front heating module 1022. The composite heating module 102 and the multimodal sensor 103 are both fixedly installed inside the electrical box 108. The multimodal sensor 103 includes an optical sensor module, which uses 850nm and 940nm dual-wavelength LED light sources. The optical sensor module includes: a photodiode array with a signal-to-noise ratio of >60dB, an adaptive filter circuit, an operating temperature range of -40℃ to +50℃, a blood oxygen saturation calculation unit with an error range of ±1.5%, and a dynamic calibration algorithm; a triaxial accelerometer with a sampling rate of ≥500Hz for posture recognition and fall detection; and a skin conductance sensor with an impedance measurement range of 1kΩ-10MΩ, supporting stress state monitoring. Through innovative hardware design, intelligent algorithms, and system integration, key technical challenges such as the reliability, data accuracy, and emergency response timeliness of monitoring equipment in high-altitude and cold environments have been solved. Compared with existing technologies, this represents a significant improvement, thereby enhancing user safety.

[0026] Furthermore, both the composite heating module 102 and the multimodal sensor 103 establish a communication connection with the central processing unit 3. The central processing unit 3 is connected to a dual-mode communication module 301, an anti-interference antenna 302, and an encrypted transmission unit 303. The dual-mode communication module 301 simultaneously supports Bluetooth 5.2 and LoRa protocols and establishes a communication connection with the environmental sensing base station 2 wirelessly. The anti-interference antenna 302 adopts a ceramic substrate design to improve the stability of signal transmission; The encrypted transmission unit 303 implements hardware encryption of the SM4 national cryptographic algorithm. Hardware encryption devices typically use dedicated security chips or modules with physical isolation and anti-tampering design, which can effectively resist physical attacks, side-channel attacks (such as power consumption analysis, electromagnetic analysis, etc.) and software-level attacks. Hardware encryption devices can process data in parallel, reduce the delay caused by encryption / decryption, and improve the timeliness of emergency response. In addition, the environmental sensing base station 2 includes a micro-meteorological monitoring unit 201, a Beidou / GPS dual-mode positioning module 202, and an emergency broadcasting unit 203; The micro-meteorological monitoring unit 201 integrates sensors for wind speed (0-60 m / s), temperature (-50℃~+50℃), and air pressure (300-1100 hPa), improving detection accuracy. The Beidou / GPS dual-mode positioning module 202 has a horizontal positioning accuracy of 1.5m CEP. By simultaneously receiving signals from Beidou and GPS satellites, the dual-mode module can make full use of the advantages of the two systems to improve positioning accuracy and reliability. Redundancy design: when the signal of one system is weak or unavailable, the other system can provide supplementation to ensure uninterrupted positioning and improve the stability of network transmission. The emergency broadcast unit 203 includes a 120dB directional sound wave transmitter and an LED strobe light, which pushes information to users through the sound wave transmitter and LED strobe light to further improve the timeliness of information.

[0027] Furthermore, such as Figure 2 As shown, the central processing unit 3 is equipped with an LSTM neural network acceleration unit 304, a multi-source data fusion algorithm 305, and a hierarchical early warning decision tree 306, as well as a network security module. The network security module is used to monitor equipment anomalies and shut down the equipment in an emergency. The LSTM neural network acceleration unit 304 includes physiological sensors, environmental sensors, and motion sensors, and is dedicated to calculating the HRI index. The sampling window time of the multi-source data fusion algorithm 305 is ≤5 seconds, and the response latency of the hierarchical early warning decision tree 306 is <100ms. The LSTM neural network acceleration unit 304, the multi-source data fusion algorithm 305, and the hierarchical early warning decision tree 306 can quickly process information and improve the timeliness of emergency response. Moreover, the LSTM neural network acceleration unit 304 uses an LSTM neural network to establish a dynamic risk index (HRI) and collect physiological and environmental parameters in real time. The risk parameters are calculated using the following formula: ; = HR - HR0; in, , as well as These are the weighting coefficients. =0.35, =0.5, =0.15; It represents the change in heart rate, that is, the difference between the current heart rate and the reference heart rate; HR is the real-time measured heart rate, and HR0 represents the baseline heart rate or initial heart rate; SpO 20 Indicates baseline or initial blood oxygen saturation; SpO2 represents the currently measured blood oxygen saturation; T represents the temperature in a specific environment or inside the body; It is an exponential term that describes the effect of temperature on HRI, and e is the base of the natural logarithm; A graded response mechanism is triggered based on the HRI threshold; The tiered response mechanism includes: When 0.7 ≤ HRI < 1.0, activate near-field rescue within a 500m range; When 1.0 ≤ HRI < 1.5, dispatch the medical station and activate emergency oxygen supply; When HRI ≥ 1.5, activate the helicopter rescue route; The LSTM neural network acceleration unit 304 uses an LSTM neural network to establish a dynamic risk index (HRI), collects physiological and environmental parameters in real time, calculates them, and finally activates near-field rescue equipment, dispatches medical stations and starts emergency oxygen supply or activates helicopter rescue channels to ensure the safety of users. In addition, the specific algorithm of the multi-source data fusion algorithm 305 is as follows: Information is pushed to the time alignment module through physiological sensors, environmental sensors, and motion sensors; The time alignment module performs feature-level fusion; Then, decision-level fusion is performed; Ultimately, risk warnings are issued. Different data sources may contain their own errors or noise. Multi-source data fusion integrates information from multiple data sources, which can mutually correct each other, reduce errors, and improve data accuracy. Different data sources may cover different information dimensions or time ranges. Fusion algorithms can integrate these data, make up for the shortcomings of a single data source, and provide more comprehensive information. Multi-source data fusion can provide a richer information foundation for decision-making, helping decision-makers to have a more comprehensive understanding of the situation and make more scientific decisions.

[0028] If certain terms are used in the specification and claims to refer to specific components, those skilled in the art will understand that hardware manufacturers may use different names to refer to the same component. This specification and claims do not distinguish components based on differences in name, but rather on differences in function. The term "comprising" as used throughout the specification and claims is an open-ended term and should be interpreted as "comprising but not limited to." "Approximately" means that within an acceptable margin of error, those skilled in the art can solve the technical problem and substantially achieve the technical effect within a certain margin of error.

[0029] It should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes that element.

[0030] The foregoing description illustrates and describes several preferred embodiments of the present invention. However, as previously stated, it should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the inventive concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A health status monitoring device and safety emergency system based on intelligent sensing technology, characterized in that, include: Wearable terminal (1), the wearable terminal (1) includes a wearable vest (101) and a composite heating module (102) and a multimodal sensor (103) disposed on the wearable vest (101). The wearable terminal (1) establishes a communication connection with the multimodal sensor (103) through the composite heating module (102) and forms a closed-loop temperature control system. An environmental sensing base station (2) is deployed in the area surrounding the operation site; and a central processing unit (3) for data analysis and emergency response; The central processing unit (3) is fixedly mounted on the wearable terminal (1) and establishes a communication connection with the environmental sensing base station (2) wirelessly.

2. The health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 1, characterized in that: The vest (101) includes a wearing strap (104), and the composite heating module (102) includes a rear heating module (1021) and a front heating module (1022). The rear heating module (1021) is fixedly mounted on the wearing strap (104), and the front heating module (1022) is connected to the wearing strap (104) by a quick-release clip (105). The vest (101) is connected to a wristband (106), which is fixed to the wrist by Velcro. A temperature sensor (107) is provided on the wristband (106). The temperature sensor (107) is used to monitor the skin temperature of the wrist in real time. The temperature sensor (107) establishes a communication connection with the composite heating module (102). An electrical box (108) is fixedly installed at the bottom of the front heating module (1022), and the composite heating module (102) and the multimodal sensor (103) are both fixedly installed inside the electrical box (108); The composite heating module (102) is electrically connected to a storage battery (4), and the composite heating module (102) has an energy efficiency ratio of ≥85% and a temperature control accuracy of ±0.5℃. The composite heating module (102) includes a graphene heating element (109), which is integrated into the inner layer of the wristband (106); The three-level gradient heating controller (110) automatically starts stepped heating when the skin temperature is <28℃.

3. The health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 2, characterized in that: The multimodal sensor (103) includes an optical sensor module, which uses a dual-wavelength LED light source of 850nm and 940nm and is configured with a dynamic calibration algorithm; A three-axis accelerometer with a sampling rate of ≥500Hz is used for attitude recognition and fall detection. Skin conductance sensor with impedance measurement range of 1kΩ-10MΩ, supporting stress state monitoring; Both the composite heating module (102) and the multimodal sensor (103) establish a communication connection with the central processing unit (3). The central processing unit (3) is connected to a dual-mode communication module (301), an anti-interference antenna (302), and an encrypted transmission unit (303). The dual-mode communication module (301) simultaneously supports Bluetooth 5.2 and LoRa protocols and establishes a communication connection with the environmental sensing base station (2) wirelessly. The anti-interference antenna (302) adopts a ceramic substrate design; The encrypted transmission unit (303) implements hardware encryption using the SM4 national cryptographic algorithm.

4. The health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 3, characterized in that: The optical sensor module includes: Photodiode array, signal-to-noise ratio > 60dB; Adaptive filter circuit, operating temperature range -40℃~+50℃; Blood oxygen saturation calculation unit, error range ±1.5%.

5. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 1, characterized in that: The environmental sensing base station (2) includes a micro-meteorological monitoring unit (201), a Beidou / GPS dual-mode positioning module (202), and an emergency broadcasting unit (203). The micro-meteorological monitoring unit (201) integrates sensors for wind speed of 0-60m / s, temperature of -50℃ to +50℃, and air pressure of 300-1100hPa. The Beidou / GPS dual-mode positioning module (202) has a horizontal positioning accuracy of 1.5m CEP. The emergency broadcast unit (203) includes a 120dB directional sound wave transmitter and an LED strobe light.

6. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 5, characterized in that: The central processing unit (3) is equipped with an LSTM neural network acceleration unit (304), a multi-source data fusion algorithm (305), a hierarchical early warning decision tree (306), and a network security module. The network security module is used to monitor equipment abnormalities and shut down the equipment in an emergency. The LSTM neural network acceleration unit (304) includes physiological sensors, environmental sensors, and motion sensors, and is dedicated to calculating the HRI index. The sampling window time of the multi-source data fusion algorithm (305) is ≤5 seconds, and the response delay of the hierarchical early warning decision tree (306) is <100ms.

7. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 6, characterized in that: The LSTM neural network acceleration unit (304) uses an LSTM neural network to establish a dynamic risk index (HRI) and collect physiological and environmental parameters in real time. The risk parameters are calculated using the following formula: ； = HR - HR0; in, , as well as These are the weighting coefficients. =0.35, =0.5, =0.15; It represents the change in heart rate, that is, the difference between the current heart rate and the reference heart rate; HR is the real-time measured heart rate, and HR0 represents the baseline heart rate or initial heart rate; SpO 20 Indicates baseline or initial blood oxygen saturation; SpO2 represents the currently measured blood oxygen saturation; T represents the temperature in a specific environment or inside the body; It is an exponential term that describes the effect of temperature on HRI, and e is the base of the natural logarithm; A graded response mechanism is triggered based on the HRI threshold.

8. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 7, characterized in that: The graded response mechanism includes: When 0.7 ≤ HRI < 1.0, activate near-field rescue within a 500m range; When 1.0 ≤ HRI < 1.5, dispatch the medical station and activate emergency oxygen supply; When HRI ≥ 1.5, activate the helicopter rescue channel.

9. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 8, characterized in that: The specific algorithm of the multi-source data fusion algorithm (305) is as follows: Information is pushed to the time alignment module through the physiological sensor, the environmental sensor, and the motion sensor; The time alignment module performs feature-level fusion; Then, decision-level fusion is performed; Finally, a risk warning will be issued.

10. A health status monitoring device and safety emergency system based on intelligent sensing technology according to claim 9, characterized in that: The environmental sensing base station (2) and the central processing unit (3) communicate using the following method: Redundant communication links, including 4G / 5G backup channels; Time synchronization protocol, error <1ms; Distributed data storage architecture.

Images