Exercise monitoring device capable of preventing exercise falling

Abstract

The invention discloses an anti-falling exercise monitoring device, and aims to solve the problems that existing exercise monitoring equipment is unstable in fixation, easy to fall, insufficient in early warning and poor in data collaboration. The system is composed of a wearable monitoring terminal, a user terminal and a cloud data platform. The wearable monitoring terminal is stably worn through an anti-falling fixing assembly of an elastic band and a buckle, integrates data acquisition modules of heart rate, motion state, fitting pressure and the like, and is matched with vibration, light and buzzing early warning modules and a power supply module. The user terminal interacts with the wearable terminal through Bluetooth / Wi-Fi, displays the motion data and receives a prompt; the cloud data platform is responsible for data storage and analysis, graded early warning decision making and personalized exercise plan generation.

Description

Technical Field

[0001] This invention relates to the field of motion monitoring technology, and specifically to a motion monitoring device to prevent objects from falling during exercise. Background Technology

[0002] With increasing health awareness, fitness tracking devices (such as smart bracelets and sports watches) have become widely used, but existing devices have the following shortcomings: Poor stability: Traditional devices often rely on simple straps for fixation, which are prone to loosening and falling off during high-intensity exercise, leading to monitoring interruption or even device damage; The system lacks a warning function: it can only passively collect data and cannot actively identify movement imbalances (such as the risk of tripping while running) or abnormal device fit, making it difficult to remind users in a timely manner. Weak data collaboration: Local storage data is limited, and the interaction with user terminals and cloud platforms is poor, making it impossible to achieve real-time data synchronization, intelligent analysis, and personalized exercise guidance; Insufficient environmental adaptability: It has weak waterproof and shockproof performance and is prone to failure due to environmental factors in complex outdoor sports scenarios.

[0003] Therefore, there is an urgent need for a motion monitoring system that combines stable fixation, intelligent early warning, data collaboration, and strong environmental adaptability to address the pain points of existing technologies. Summary of the Invention

[0004] The present invention aims to at least partially solve one of the technical problems in the above-mentioned technologies.

[0005] To achieve the above objectives, the first aspect of this invention provides a motion monitoring device to prevent it from falling during exercise, comprising a wearable monitoring terminal, a cloud data platform, and a user terminal; the wearable monitoring terminal includes a monitoring body, an anti-fall fixing component, a motion data acquisition unit, a local processor, and a first wireless communication module; the anti-fall fixing component is connected to the monitoring body to fix the monitoring terminal to the human body; the motion data acquisition unit is electrically connected to the local processor to collect physiological parameters, motion state parameters, and terminal fit data during user exercise and transmit them to the local processor; the first wireless communication module is electrically connected to the local processor for data transmission; the cloud data platform includes a data receiving module, a data storage module, an intelligent analysis module, and an early warning decision module; the data receiving module... The system establishes a connection with the first wireless communication module via a network, receives and transmits data to the data storage module, and the intelligent analysis module performs feature extraction and anomaly identification on the stored motion data. The early warning decision module generates an early warning command based on the analysis results. The user terminal includes a second wireless communication module, a display module, and an alert module. The second wireless communication module establishes communication with the cloud data platform or the wearable monitoring terminal, receives data and early warning commands, the display module displays motion data, and the alert module triggers an alert action based on the early warning command. When the intelligent analysis module identifies a risk of user imbalance or an abnormal fit of the wearable monitoring terminal, the early warning decision module generates an early warning command and synchronizes it to the wearable monitoring terminal and the user terminal to achieve an anti-fall warning.

[0006] As an improvement, the anti-fall fixing component of the wearable monitoring terminal includes an elastic restraint strap, an adjustable buckle, and an anti-slip buffer layer. The two ends of the elastic restraint strap are detachably connected to the monitoring body. The adjustable buckle adjusts the tightness of the restraint strap. The anti-slip buffer layer fits the side of the monitoring body that contacts the human body and has anti-slip texture. The edge of the monitoring body is provided with an elastic silicone anti-fall protective sleeve, and there are thickened buffer protrusions at the corners.

[0007] As an improvement, the motion data acquisition unit includes a photoelectric heart rate sensor, a three-axis accelerometer, a six-axis gyroscope, a GPS positioning module, and a pressure sensor; the heart rate sensor collects heart rate, the accelerometer and gyroscope collect the number of steps, posture, and trajectory, the GPS locates the motion position, and the pressure sensor detects the pressure value between the monitoring terminal and the human body.

[0008] As an improvement, the intelligent analysis module includes a data preprocessing unit, a feature extraction unit, and an anomaly detection unit. The data preprocessing unit performs noise reduction and filtering on the collected data. The feature extraction unit extracts features such as motion amplitude, heart rate fluctuation, and rate of change of contact pressure. The anomaly detection unit compares the extracted features with preset thresholds to identify motion imbalance or contact abnormalities.

[0009] As an improvement, the preset thresholds include a heart rate threshold (resting heart rate ± 30%) and an exercise acceleration threshold (5-10 m / s²). 2 The fitting pressure threshold (5-15 kPa) is used to determine an abnormal state when any parameter exceeds the threshold and the duration is ≥3 seconds.

[0010] As an improvement, the warning command includes a first-level warning and a second-level warning; when the detected contact pressure value is below the threshold but there is no risk of motion imbalance, a first-level warning is generated, triggering a pop-up reminder on the user terminal and vibration of the wearable monitoring terminal; when a risk of motion imbalance is detected (such as a sudden acceleration ≥8m / s²), a second-level warning is generated. 2 When a Level 2 warning is generated, in addition to the actions of a Level 1 warning, a buzzer reminder is triggered on the user terminal, and the warning information is pushed to the preset emergency contact terminal through the cloud data platform.

[0011] As an improvement, the first wireless communication module supports Bluetooth 5.0 and Wi-Fi 6 standards, the second wireless communication module supports 5G / 4G networks and Bluetooth communication, and the cloud data platform uses an encrypted transmission protocol (such as TLS 1.3) to ensure data security between the wearable monitoring terminal and the user terminal.

[0012] As an improvement, the cloud data platform also includes an exercise plan generation module. The exercise plan generation module generates a personalized exercise plan based on the user's historical exercise data, physiological parameters and exercise goals, and displays it through the user terminal. When the user's exercise trajectory deviates from the plan, the reminder module triggers a trajectory correction reminder.

[0013] As an improvement, the wearable monitoring terminal also includes a power supply unit, which includes a 500-1500mAh lithium battery and a wireless charging coil, supporting Qi wireless charging. The surface of the monitoring body is equipped with a power indicator light. When the power is below 20%, the local processor generates a low power reminder command and synchronizes it to the user terminal.

[0014] As an improvement, the user terminal includes a smartphone, tablet, or smartwatch, the display module displays real-time heart rate, exercise distance, calorie consumption, and other data in the form of charts, and the reminder module includes at least two reminder methods among screen pop-ups, vibration, and buzzers, and supports user-defined reminder modes.

[0015] Beneficial effects The system's anti-fall fixing components provide multiple safeguards from three aspects: material, structure, and fit design. The elastic restraint band, a blend of spandex, nylon, and polyester fibers, boasts a 98% tensile elastic recovery rate and a breaking strength exceeding 600N. It adapts to different body sizes and maintains stable restraint during high-intensity exercise, preventing loosening. A high-density polyurethane anti-slip cushioning layer, combined with a medical-grade anti-slip silicone coating, has a static friction coefficient ≥0.6. This, along with a 4-point pressure sensor array, monitors the fit in real time, accurately identifying abnormal fits and eliminating the limitations of single-point pressure detection. Quick-release buckle connectors and elastic silicone anti-drop protective sleeves not only facilitate device disassembly but also reduce impact damage in case of accidental drops. The device's drop damage rate is reduced by over 90% compared to traditional monitoring devices, while also preventing monitoring interruptions due to drops, ensuring continuous motion data acquisition.

[0016] The wearable monitoring terminal's multi-dimensional motion data acquisition unit breaks through the limitations of traditional single-data acquisition devices: the physiological parameter acquisition subunit uses dual-light source photoelectric sensors to achieve real-time monitoring of heart rate and blood oxygen, while the sweat composition sensor can also detect lactic acid concentration, accurately assessing the degree of exercise fatigue; the motion state acquisition subunit combines a three-axis accelerometer, a six-axis gyroscope, and GPS + Beidou dual-mode positioning to accurately acquire cadence, stride length, movement trajectory, and altitude, reducing data error by 40% compared to traditional devices; the environmental parameter acquisition subunit is in close contact with the device's state acquisition subunit, further enriching the data dimensions and providing comprehensive and accurate raw data for cloud-based intelligent analysis, helping users to deeply understand the influence of exercise state and environment.

[0017] The cloud-based data platform's AI intelligent analysis module, based on a deep learning model, can quickly identify three types of risks: abnormal fit, movement imbalance, and physiological abnormalities. The tiered early warning decision-making module formulates targeted response strategies: Level 1 (low risk) alerts users promptly via multi-color LEDs and pop-up windows on the device to prevent it from falling; Level 2 (medium risk) combines vibration and buzzer alerts to help users adjust their posture or heart rate; Level 3 (high risk) not only triggers comprehensive alerts but also links emergency contacts and third-party rescue platforms, automatically reporting the user's location and emergency data, improving rescue response efficiency by over 60%. This end-to-end "prevention-alert-rescue" early warning mechanism effectively avoids safety hazards caused by device detachment, postural imbalance, or exceeding physiological limits during exercise, making it particularly suitable for high-risk scenarios such as outdoor hiking and high-intensity running.

[0018] The system fully considers user needs in power consumption control and interaction design: the wearable terminal uses a low-power MCU and multi-mode communication chip, paired with a high-capacity lithium battery of 800-2000mAh, which can work continuously for 8-12 hours on a full charge, improving battery life by 50% compared to traditional devices; it supports Qi wireless charging and Type-C fast charging, with a charging efficiency of ≥75%, solving the problem of outdoor charging. The user terminal uses a high-definition OLED screen and an APP visual interface to intuitively display real-time heart rate curves, exercise trajectory maps, and other data in chart form, supporting touch operation and customized reminders; quick-release buckles and breathable mesh straps not only facilitate device disassembly but also improve breathability during long-term wear, reducing skin stuffiness and discomfort, and greatly optimizing the user experience.

[0019] The cloud-based personalized exercise plan generation module is based on user profiles. For example, it automatically recommends heart rate control zones based on the user's real-time heart rate and triggers correction reminders when the user deviates from the planned trajectory by ≥100 meters, helping users exercise scientifically and improving exercise effectiveness by more than 30%. Meanwhile, the system provides end-to-end security from data transmission and storage to data destruction, complying with data security regulations and eliminating the risk of user privacy leaks. This allows users to enjoy intelligent services without worrying about data security issues. Attached Figure Description

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a control system diagram of a non-contact respiratory monitoring method based on Doppler radar according to an embodiment of the present invention. Detailed Implementation

[0021] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0022] The following describes a non-contact respiratory monitoring method based on Doppler radar according to an embodiment of the present invention, with reference to the accompanying drawings.

[0023] like Figure 1As shown in the figure, an embodiment of the present invention provides a motion monitoring device to prevent falling during exercise, comprising a wearable monitoring terminal, a cloud data platform, and a user terminal. These three components achieve bidirectional data interaction and functional collaboration through a wireless communication network. The wearable monitoring terminal, serving as the core for motion data acquisition and local early warning execution, includes a monitoring body, an anti-fall fixing component, a multi-dimensional motion data acquisition unit, a low-power local processor, a first wireless communication module, a power supply unit, and a local early warning execution module. The anti-fall fixing component is detachably connected to the monitoring body and is used to stably fix the wearable monitoring terminal to a moving part of the human body (wrist, upper arm, ankle). The multi-dimensional motion data acquisition unit and the low-power local processor... The processor is electrically connected to collect physiological parameters, motion state parameters, device fit state parameters, and environmental parameters of the user during exercise in real time and transmit them to the low-power local processor. The first wireless communication module is electrically connected to the low-power local processor and is used to synchronize the processed collected data to the cloud data platform and the user terminal. The power supply unit supplies power to the various components of the wearable monitoring terminal. The local early warning execution module is electrically connected to the low-power local processor, receives early warning commands, and executes local reminder actions. The cloud data platform, as the core of data storage, intelligent analysis, and decision-making, is deployed on a distributed cloud server cluster and includes an encrypted data receiving module, a high-capacity data storage module, an AI intelligent analysis module, a graded early warning decision-making module, a personalized exercise plan generation module, and an emergency rescue linkage module. The encrypted data receiving module establishes a secure connection with the first wireless communication module through a wide area network, receives and verifies the collected data, and then transmits it to the high-capacity data storage module. The AI... The intelligent analysis module performs multi-dimensional feature extraction, anomaly identification, and exercise risk assessment on stored data. The hierarchical early warning decision module generates corresponding level early warning instructions and execution strategies based on the analysis results. The personalized exercise plan generation module generates dynamically adjusted exercise plans based on user physiological baseline data, historical exercise data, and exercise goals. The emergency rescue linkage module establishes communication with preset emergency contact terminals and third-party rescue platforms when a high-risk early warning is triggered. The user terminal, as the core of human-computer interaction and data display, includes smartphones, tablets, smartwatches, and dedicated sports bracelets, integrating a second wireless communication module, a high-definition display module, a customizable reminder module, and a user interaction module. The second wireless communication module establishes bidirectional communication with the cloud data platform and wearable monitoring terminal to receive data, early warning instructions, and exercise plans. The high-definition display module displays real-time exercise data, historical data trends, and exercise plans in a visual form. The customizable reminder module executes multi-mode reminder actions based on early warning instructions. The user interaction module supports users in completing device binding, parameter settings, data queries, and instruction feedback operations.When the AI ​​intelligent analysis module identifies abnormal fit of the wearable monitoring terminal (fitting pressure consistently below a preset threshold), risk of user imbalance (motion posture parameters exceeding safe range), or abnormal physiological parameters (physiological indicators exceeding health thresholds), the graded early warning decision module generates a corresponding level of early warning instruction, which is simultaneously pushed to the local early warning execution module of the wearable monitoring terminal and the user terminal's customizable reminder module. This also triggers relevant linkage functions on the cloud data platform, achieving the dual functions of preventing the device from falling during exercise and ensuring exercise safety.

[0024] It should be noted that the main body of the wearable monitoring terminal is made of lightweight reinforced ABS and PC composite material, with an overall weight of ≤30g and a thickness of ≤12mm. The surface is covered with a double-layer nano-waterproof coating, achieving a waterproof rating of IP68 or higher, allowing it to operate normally for more than 30 minutes in a 1.5-meter water depth environment. The monitoring main body is fitted with an integrated, molded elastic silicone shockproof protective sleeve. The elastic silicone material is food-grade medical silicone with a Shore hardness of 55-65HA. The four corners of the shockproof protective sleeve have 4-10mm high thickened cushioning protrusions with a honeycomb-shaped cushioning structure inside. The front of the monitoring main body features a 0.96-inch OLED high-definition display screen, supporting touch operation and automatic brightness adjustment (depending on ambient light intensity between 100-500 cd / m²). 2 (Adaptive adjustment within the range) The back has a sensor window to expose the detection elements of the multi-dimensional motion data acquisition unit.

[0025] It should be noted that the anti-fall fixing component includes an elastic restraint strap, a multi-position adjustable buckle, a detachable connecting connector, and an anti-slip cushioning layer; the elastic restraint strap is made of a blend of spandex, nylon, and polyester fibers in a blend ratio of 35:45:20, with a tensile elastic recovery rate of not less than 98%, a breaking strength of not less than 600N, a width of 15-25mm, a thickness of 1.2-2mm, and a surface with breathable mesh holes (0.5-1mm in diameter, 2-3mm in spacing) to improve breathability; the multi-position adjustable buckle includes a fixed base, a movable latch, a return spring, and a locking button, with the fixed base connected to one end of the elastic restraint strap. The elastic restraint strap is fixed by ultrasonic welding. The movable latch is rotatably connected to the fixed base via a return spring. The other end of the elastic restraint strap has evenly spaced grooves (groove depth 2-3mm, spacing 3-5mm) along its length to fit the movable latch. The locking button is located on the side of the fixed base. Pressing the locking button disengages the movable latch from the groove, allowing for quick adjustment of the restraint strap length. The adjustment range of the adjusting buckle is 150-250mm, adaptable to different body parts. The detachable connector uses a quick-release buckle structure, including female connectors on both sides of the monitoring body and male connectors fixed to both ends of the elastic restraint strap. The male connector can be locked by rotating 90° after insertion into the female connector. Pressing the unlock button allows for quick separation, facilitating device disassembly for charging or strap replacement. The anti-slip buffer layer is made of high-density polyurethane foam, 3-6mm thick, with a density of 0.3-0.5g / cm³. 3 The anti-slip buffer pad has a cross-grid anti-slip pattern on the side away from the monitoring body (pattern width 0.8-1.2mm, protrusion height 0.8-1.8mm, grid spacing 3-5mm), and a medical-grade anti-slip silicone coating is sprayed on the side that fits against the skin. The static friction coefficient is ≥0.6, which effectively prevents the device from sliding during movement.

[0026] It should be noted that the multi-dimensional motion data acquisition unit includes a physiological parameter acquisition subunit, a motion state acquisition subunit, a device contact state acquisition subunit, and an environmental parameter acquisition subunit. The physiological parameter acquisition subunit includes a photoelectric heart rate and oxygenation sensor, a skin temperature sensor, and a sweat composition sensor. The photoelectric heart rate and oxygenation sensor uses a green light + infrared dual-light source design, with a sampling rate of 1-10Hz, a heart rate measurement range of 30-250 beats / minute, an accuracy of ±2 beats / minute, and an oxygen saturation measurement range of 70%-100%, with an accuracy of ±2%. The photoelectric heart rate and oxygenation sensor is fitted to an anti-slip buffer layer and contacts the human skin through the sensor window. The skin temperature sensor uses an NTC sensor. The thermistor has a measurement range of 0-50℃ and an accuracy of ±0.3℃. The sweat composition sensor is an electrochemical sensor that can detect the concentrations of sodium and potassium ions in sweat (detection range 10-1000 mmol / L, accuracy ±5%) and lactic acid concentration (detection range 0.5-20 mmol / L, accuracy ±0.1 mmol / L) to assess the user's level of exercise fatigue. The motion state acquisition subunit includes a triaxial accelerometer, a six-axis gyroscope, a triaxial magnetometer, and a GPS positioning module. The triaxial accelerometer has a measurement range of ±2 / ±4 / ±8 / ±16g and a resolution of 16 bits. The six-axis gyroscope has a measurement range of ±250 / ±500 / ±1000 / ±2000° / s and a resolution of 16 bits. The two work together with a sampling rate of 10-100Hz to collect the user's step count (accuracy ±1%) and cadence (range 20-240 steps / minute, accuracy ±1 step / minute). The measurement range of the three-axis magnetometer is ±4800μT, with a resolution of 16 bits, used to assist the gyroscope in correcting attitude drift. The GPS positioning module supports GPS + Beidou dual-mode positioning, with a positioning accuracy of ≤5 meters (open environment), a positioning update rate of 1Hz, and supports A-GPS assisted positioning. The cold start time is ≤30 seconds, and the hot start time is ≤10 seconds. It can collect the user's real-time movement position, movement speed (range 0-100km / h, accuracy ±0.1km / h), and movement distance (accuracy ±0.05m).The device contact status acquisition subunit includes a pressure sensor array and a capacitive proximity sensor. The pressure sensor array consists of four miniature piezoresistive pressure sensors, evenly distributed between the anti-slip buffer layer and the monitoring body. Each pressure sensor has a measurement range of 0-100 kPa, an accuracy of ±2 kPa, and a sampling rate of 1 Hz. It is used to detect the contact pressure between the device and different parts of the human body, avoiding the limitations of single-point pressure detection. The capacitive proximity sensor has a detection distance of 0-10 mm and a resolution of 0.1 mm, used to assist in determining whether the device has detached from the human body. The environmental parameter acquisition subunit includes an ambient light sensor, a barometric pressure sensor, and a temperature and humidity sensor. The ambient light sensor has a measurement range of 0-100,000 lux and a resolution of 1 lux, used to adjust the brightness of the OLED display. The barometric pressure sensor has a measurement range of 300-1100 hPa and an accuracy of ±0.1 hPa, used to calculate the altitude of the movement (accuracy ±1 meter). The temperature and humidity sensor has a temperature measurement range of -40-85℃ (accuracy ±0.2℃) and a humidity measurement range of 0-100%. RH (accuracy ±2% RH) is used to collect ambient temperature and humidity data during exercise to assess the impact of the environment on exercise.

[0027] It should be noted that the low-power local processor uses an ARM Cortex-M4 architecture MCU chip (such as STM32L476RG), with a maximum operating frequency of 80MHz, a sleep current ≤1μA, and an operating current ≤5mA. The low-power local processor has a built-in 12-bit ADC (sampling rate 1Msps), a 16-bit timer, and a hardware encryption module (supporting AES-256 encryption algorithm). The low-power local processor preprocesses the raw data collected by the multi-dimensional motion data acquisition unit, including Kalman filtering (removing noise from heart rate and acceleration data), mean filtering (smoothing temperature and humidity data), outlier removal (removing GPS positioning drift data), and data compression (using LZ77 compression algorithm, compression rate ≥50%). The preprocessed data is transmitted through the first wireless communication module. At the same time, the low-power local processor receives control commands from the cloud data platform or user terminal in real time to perform operations such as parameter configuration, data acquisition frequency adjustment, and warning mode switching.

[0028] It should be noted that the first wireless communication module uses a multi-mode communication chip (such as nRF52840), integrating Bluetooth 5.2, Wi-Fi 6, and LoRa communication functions. The Bluetooth 5.2 module supports BLE Low Power mode, with a communication distance ≤100 meters (open environment) and a transmission rate ≤2Mbps, used for establishing direct connections with user terminals at close range to achieve low-latency data transmission (latency ≤5ms) and device control. The Wi-Fi 6 module supports the IEEE 802.11ax standard, with a communication rate ≤9.6Gbps, a communication distance ≤300 meters (open environment), and supports 2.4GHz / 5GHz dual-band, used for accessing wireless networks to achieve long-distance data transmission with cloud data platforms. The LoRa module supports the LoRaWAN protocol, with a communication distance ≤5 kilometers (open environment) and a transmission rate ≤50kbps, used for low-power long-distance data transmission in outdoor scenarios without Wi-Fi / cellular network coverage (such as mountain climbing in remote mountainous areas). The first wireless communication module has a built-in hardware encryption engine and supports Bluetooth LE Secure. Connections, Wi-Fi WPA3, and LoRa AES-128 encryption ensure secure data transmission.

[0029] It should be noted that the power supply unit includes a high-capacity lithium battery, a wireless charging coil, a wired charging interface, and a power management chip. The high-capacity lithium battery is a lithium polymer battery with a capacity of 800-2000mAh, an energy density ≥600Wh / L, an operating voltage of 3.7-4.2V, supports 1C charging and 0.5C discharging, and a cycle life ≥500 cycles (capacity retention ≥80%). The lithium battery is externally wrapped with a flame-retardant insulating layer to prevent short-circuit fire. The wireless charging coil is made of multi-turn enameled copper wire with a diameter of 15-20mm and a thickness of 2-3mm. It supports the Qi wireless charging standard, has a charging power of 5-10W, and a charging efficiency ≥75%. The wireless charging coil is integrated inside the monitoring body and has a magnetic shielding sheet underneath to reduce electromagnetic interference. The wired charging interface uses a Type-C interface, supports the USB PD fast charging protocol, has a charging power of 10-18W, and has a waterproof sealing ring at the interface, with a waterproof rating consistent with the monitoring body. The power management chip uses a low-power PMIC. The chip (e.g., ADP5350) supports multiple voltage outputs (3.3V, 1.8V, 1.2V) to power different components. It also features overvoltage protection (protection voltage ≥ 4.5V), overcurrent protection (protection current ≥ 2A), overtemperature protection (protection temperature ≥ 85℃), and low-voltage alarm function. When the lithium battery voltage is below 3.3V, a low-battery alarm is triggered, reminding the user to charge via a local warning execution module.

[0030] It should be noted that the local early warning execution module includes a miniature vibration motor, a buzzer, and a multi-color LED indicator. The miniature vibration motor is an eccentric rotor motor with dimensions ≤6×3×2mm, adjustable vibration intensity (3 levels, corresponding to vibration acceleration 0.5-2g), and a response time ≤10ms, used to alert the user through vibration. The buzzer is a piezoelectric buzzer with an operating voltage of 3.3V, adjustable volume (50-80dB, 3 levels), and supports various alarm sound effects (such as short tone, long tone, and intermittent tone), used to alert the user through sound. The multi-color LED indicator consists of 3 LED beads (red, yellow, and green), located on the front of the monitoring body, supporting two working modes: constant light and flashing (flashing frequency 1-5Hz). Different colors and states correspond to different warning levels (e.g., constant green indicates normal operation, flashing yellow indicates a level 1 warning, and flashing red indicates a level 2 warning), and also indicates the device's working status (e.g., constant red when charging, and constant green when fully charged).

[0031] It should be noted that the encrypted data receiving module of the cloud data platform establishes a connection with the first wireless communication module using the HTTPS protocol, supports the TLS 1.3 encryption algorithm, and employs data verification mechanisms (such as CRC32 checksum and MD5 hash checksum) to ensure the integrity and accuracy of the received data. The concurrent processing capacity of the encrypted data receiving module is ≥10,000 device connections, and the data reception latency is ≤30ms. The high-capacity data storage module adopts a distributed database architecture, including a MySQL cluster (storing structured data, such as user basic information, physiological baseline data, and exercise plan parameters), a MongoDB cluster (storing unstructured data, such as exercise trajectory data and raw sensor data), and a Redis cache (storing frequently accessed data, such as real-time heart rate and device online status). The data storage module supports data backup (daily full backup + incremental backup), data archiving (archiving historical data exceeding one year to low-cost storage), and data destruction (completely deleting data within 30 days after user logout), complying with data security regulations. The AI... The intelligent analysis module is built on deep learning frameworks (such as TensorFlow and PyTorch) and includes a data preprocessing layer, a feature extraction layer, a model inference layer, and a result output layer. The data preprocessing layer normalizes and standardizes the collected data. The feature extraction layer extracts 15 key features (including heart rate coefficient of variation, standard deviation of motion acceleration, rate of change of contact pressure, and rate of change of altitude). The model inference layer uses a pre-trained multi-classification model (such as random forest or CNN-LSTM hybrid model) to classify motion states (such as normal motion, risk of imbalance, and abnormal contact) and assess the motion risk level (low risk, medium risk, and high risk). The model inference accuracy is ≥95%, and the inference time is ≤100ms. The graded warning decision module divides the warning level into three levels: Level 1 warning (low risk, such as contact pressure below the threshold but no motion imbalance, duration ≥3 seconds), the execution strategy is to trigger a pop-up reminder on the user terminal + flashing of the yellow LED on the wearable terminal; Level 2 warning (medium risk, such as slight imbalance in motion posture or heart rate exceeding the safe range, duration ≥2 seconds). The execution strategy is to trigger a pop-up window on the user terminal + a buzzer alert, vibration on the wearable terminal (level 2 intensity) + flashing of a yellow LED, and simultaneously push a warning message to the preset emergency contact terminal (text message only); Level 3 warning (high risk, such as sudden acceleration ≥10m / s²) 2If the heart rate exceeds the safe range by 20% for more than 10 seconds or the device is completely detached from the human body, the execution strategy is to trigger a pop-up window on the user terminal + a buzzer (maximum volume) + vibration reminder, or vibration (level 3 intensity) + a buzzer (maximum volume) + flashing red LED on the wearable terminal, push warning information (including the user's real-time location, movement status, and physiological parameters) to the preset emergency contact terminal, and at the same time connect to a third-party rescue platform (such as the 120 emergency medical platform or outdoor rescue organization) through the emergency rescue linkage module to automatically report the user's location and danger information and request rescue support.

[0032] It should be noted that the personalized exercise plan generation module includes a user profile construction submodule, a goal decomposition submodule, a plan generation submodule, and a dynamic adjustment submodule. The user profile construction submodule constructs a user's exercise ability profile and assesses the user's exercise level (e.g., beginner, intermediate, professional) based on the user's basic information (age, gender, height, weight, health status), physiological baseline data (resting heart rate, maximum heart rate, blood pressure, blood oxygen level), and historical exercise data (exercise frequency, exercise duration, average intensity, and exercise type in the past 3 months). The goal decomposition submodule breaks down the user's long-term exercise goals (e.g., losing 10kg in 3 months, completing a marathon in 6 months) into short-term goals (e.g., losing 0.8kg per week, increasing running mileage by 5km per month). The plan generation submodule is based on the user profile and short-term goals.

[0033] In the description of this specification, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0034] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0035] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A motion monitoring device for preventing objects from falling during exercise, characterized in that, The system includes a wearable monitoring terminal, a cloud data platform, and a user terminal. The wearable monitoring terminal comprises a monitoring body, an anti-drop fixing component, a motion data acquisition unit, a local processor, and a first wireless communication module. The anti-drop fixing component is connected to the monitoring body to secure the monitoring terminal to the human body. The motion data acquisition unit is electrically connected to the local processor, collecting physiological parameters, motion state parameters, and terminal fit data during user movement and transmitting them to the local processor. The first wireless communication module is electrically connected to the local processor for data transmission. The cloud data platform includes a data receiving module, a data storage module, an intelligent analysis module, and an early warning decision module. The data receiving module establishes a connection with the first wireless communication module via a network, receiving and transmitting data to the data storage module. The intelligent analysis module performs feature extraction and anomaly identification on the stored motion data. The early warning decision module generates early warning commands based on the analysis results. The user terminal includes a second wireless communication module, a display module, and an alert module. The second wireless communication module establishes communication with the cloud data platform or the wearable monitoring terminal, receiving data and early warning commands. The display module displays motion data, and the alert module triggers an alert action based on the early warning command. When the intelligent analysis module detects a risk of user imbalance or an abnormal fit of the wearable monitoring terminal, the early warning decision module generates an early warning command and synchronizes it to the wearable monitoring terminal and the user terminal to achieve an anti-fall warning.

2. The motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The anti-fall fixing component of the wearable monitoring terminal includes an elastic restraint strap, an adjustable buckle, and an anti-slip buffer layer. The two ends of the elastic restraint strap are detachably connected to the monitoring body. The adjustable buckle adjusts the tightness of the restraint strap. The anti-slip buffer layer fits the side of the monitoring body that contacts the human body and has anti-slip texture. The edge of the monitoring body is provided with an elastic silicone anti-fall protective cover, and there are thickened buffer protrusions at the corners.

3. The motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The motion data acquisition unit includes a photoelectric heart rate sensor, a three-axis accelerometer, a six-axis gyroscope, a GPS positioning module, and a pressure sensor. The heart rate sensor collects heart rate data, the accelerometer and gyroscope collect step count, posture, and trajectory data, the GPS locates the motion position, and the pressure sensor detects the pressure value between the monitoring terminal and the human body.

4. The motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The intelligent analysis module includes a data preprocessing unit, a feature extraction unit, and an anomaly detection unit. The data preprocessing unit performs noise reduction and filtering on the collected data. The feature extraction unit extracts features such as motion amplitude, heart rate fluctuation, and rate of change of contact pressure. The anomaly detection unit compares the extracted features with preset thresholds to identify motion imbalance or contact abnormalities.

5. A motion monitoring device for preventing falls during exercise according to claim 4, characterized in that, The preset thresholds include heart rate threshold (resting heart rate ± 30%) and exercise acceleration threshold (5-10 m / s²). 2 The fitting pressure threshold (5-15 kPa) is used to determine an abnormal state when any parameter exceeds the threshold and the duration is ≥3 seconds.

6. The motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The warning commands include a level 1 warning and a level 2 warning. A level 1 warning is generated when the contact pressure is detected to be below a threshold but there is no risk of motion imbalance, triggering a pop-up notification on the user terminal and vibration of the wearable monitoring terminal. A level 2 warning is generated when a risk of motion imbalance is detected (e.g., a sudden acceleration change ≥ 8 m / s²). 2 When a Level 2 warning is generated, in addition to the actions of a Level 1 warning, a buzzer reminder is triggered on the user terminal, and the warning information is pushed to the preset emergency contact terminal through the cloud data platform.

7. A motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The first wireless communication module supports Bluetooth 5.0 and Wi-Fi 6 standards, and the second wireless communication module supports 5G / 4G networks and Bluetooth communication. The cloud data platform, wearable monitoring terminal, and user terminal use an encrypted transmission protocol (such as TLS 1.3) to ensure data security.

8. A motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The cloud data platform also includes an exercise plan generation module, which generates a personalized exercise plan based on the user's historical exercise data, physiological parameters and exercise goals, and displays it through the user terminal. When the user's exercise trajectory deviates from the plan, the reminder module triggers a trajectory correction reminder.

9. A motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The wearable monitoring terminal also includes a power supply unit, which includes a 500-1500mAh lithium battery and a wireless charging coil, supporting Qi wireless charging. The surface of the monitoring body is equipped with a power indicator light. When the power is below 20%, the local processor generates a low power reminder command and synchronizes it to the user terminal.

10. A motion monitoring device for preventing falls during exercise according to claim 1, characterized in that, The user terminal includes a smartphone, tablet, or smartwatch. The display module displays real-time heart rate, exercise distance, calorie consumption, and other data in the form of charts. The reminder module includes at least two reminder methods among screen pop-ups, vibration, and beeping, and supports user-defined reminder modes.

Images