Ice and snow sports equipment intelligent monitoring system based on Internet of Things

Abstract

The invention discloses an ice and snow sports equipment intelligent monitoring system based on Internet of Things, and relates to the technical field of Internet of Things and multi-cross fusion, the ice and snow sports equipment intelligent monitoring system comprises a sensor, a data processing module, a communication module, a storage module and a user terminal interaction module, data processing adopts edge and cloud computing combination, an algorithm is used to optimize an evaluation and prediction formula, a communication module introduces an SDN and a wireless energy collection technology, a storage module uses a block chain and a smart contract, a user terminal interacts with a gesture and voice dual mode and an AR technology, immersive experience is provided, and interaction between a user and the system is facilitated to obtain information. The system has obvious advantages, the multi-mode sensor accurately monitors the equipment performance and the motion posture, and motion safety is guaranteed; providing an adaptation suggestion in combination with the environment information; data is deeply analyzed through a layered architecture and an algorithm, and support is provided for training; gesture, voice and AR interaction improves experience and promotes scientific development of ice and snow sports.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things and multi-cross integration technologies, and particularly to an intelligent monitoring system for ice and snow sports equipment based on the Internet of Things. Background Art

[0002] With the popularization and development of ice and snow sports globally, more and more people are engaged in ice and snow projects such as skiing and skating. Ice and snow sports can not only bring excitement and fun, but also have relatively high requirements for an individual's physical fitness and sports skills. However, current ice and snow sports equipment faces many problems during use, seriously affecting the safety and experience of the sports.

[0003] In terms of equipment performance monitoring, traditional ice and snow sports equipment lacks effective real-time monitoring means. Athletes and enthusiasts are difficult to accurately understand the wear condition, performance status of the equipment, and its adaptability in different environments. For example, the edge wear of skis, the change in the sole hardness of ice skates, etc. These subtle changes may have a significant impact on sports performance, but it is very difficult to directly detect them with the naked eye. The lack of timely and accurate equipment performance information makes athletes blind when choosing equipment and adjusting sports strategies. They not only can hardly perform at their best level, but may also cause safety accidents due to equipment failures.

[0004] From the perspective of sports safety, ice and snow sports have certain risks, such as falling and colliding, which occur frequently. Most of the equipment on the current market is not equipped with a complete safety monitoring and emergency response system. When an athlete has an accident on a remote ski slope or ice rink, it is very difficult to obtain rescue in a timely manner. Moreover, during the sports process, there are also no effective monitoring means for the athlete's physical state (such as heart rate, blood oxygen saturation, etc.), and potential health risks cannot be warned in advance.

[0005] Environmental adaptability is also an important issue. The environment of ice and snow sports is complex and changeable, and different snow qualities, temperatures, and humidity conditions have different requirements for the performance of the equipment. For example, in a wet snow environment, the sliding performance of skis will be affected; in a low-temperature environment, the rubber parts of ice skates may become hard, affecting flexibility. However, existing equipment cannot automatically adjust its performance according to environmental changes, nor can it provide accurate environmental adaptability suggestions for athletes.

[0006] In addition, there are also deficiencies in data management and analysis. With the development of Internet of Things technology, a large amount of sports data is generated, but these data are often not effectively integrated and analyzed. Athletes and coaches are difficult to extract valuable information from the vast amount of data and cannot provide a scientific basis for training and competitions.

[0007] In summary, existing ice and snow sports equipment has many deficiencies in aspects such as performance monitoring, safety guarantee, environmental adaptability, and data management. Developing an intelligent monitoring system for ice and snow sports equipment based on the Internet of Things has important practical significance. It can monitor the equipment status in real time, ensure sports safety, improve the environmental adaptability of the equipment, and provide scientific data support for athletes and coaches, promoting the healthy development of ice and snow sports. Summary of the Invention

[0008] The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things proposed by the present invention aims to solve the problems mentioned in the above-mentioned prior art.

[0009] To achieve the above object, the present invention adopts the following technical solutions: An intelligent monitoring system for ice and snow sports equipment based on the Internet of Things, comprising:

[0010] Sensor module: Integrates multi-modal fusion sensors, including traditional pressure, acceleration, temperature, and humidity sensors, as well as optical sensors and strain sensors; The optical sensor uses a miniaturized quantum dot photodetector to sense the change in the reflectivity of the ice and snow surface under extremely low light conditions, and the strain sensor measures the small deformation ε of the equipment. The composite motion state judgment formula is S = f(P, a, T, H, R, ε), where S is the user's motion posture, P is pressure, a is acceleration, T is temperature, H is humidity, R is reflectivity;

[0011] Data processing module: Adopts a hierarchical processing architecture combining edge computing and cloud computing. Edge computing nodes are deployed at the equipment end to preliminarily screen sensor data; In the cloud computing center, the deep reinforcement learning algorithm is used to deeply mine and analyze the data; Build a collaborative learning model based on multi-agent to optimize the wear evaluation formula as W = α×D history +β×D current +γ×ε, where γ is the weight coefficient of strain data, and the performance prediction formula is P performance = g(T, H, P, a, R, ε);

[0012] Communication module: Introduces software-defined network technology to realize the configuration and management of the communication network. Through the SDN controller, according to the signal strength judgment formula and network congestion conditions, adjust the communication protocol and transmission path, P t represents the signal transmission power; At the same time, wireless energy harvesting technology is used to power the communication module;

[0013] Storage module: Adopts distributed ledger technology to store and manage data. The data is stored in multiple nodes in an encrypted form. At the same time, using smart contract technology, realizes automatic authorized access and sharing of data. Through the data retrieval formula R = search(type, time, accessk ey), where access k ey is the authorized access key;

[0014] User terminal interaction module: Developed a dual-mode interaction interface based on gesture recognition and voice interaction. Combining with augmented reality (AR) technology, using the perspective transformation formula View = transform(position, orientation), it displays equipment information and motion data in the form of holographic projection on the user's smart glasses or head-mounted display.

[0015] Furthermore, it also includes a battery management module. This module adopts intelligent thermal management technology and adjusts the battery temperature through a micro thermoelectric cooler to keep it within the optimal operating temperature range T optimal , and uses the heat balance formula Q in -Q out = C × ΔT to monitor and control the battery temperature in real time. Among them, Q in is the heat generated by the battery, Q out is the heat dissipation, C is the battery heat capacity, ΔT is the temperature change. At the same time, it combines wireless charging technology and energy recovery technology, and recovers part of the energy through electromagnetic induction and piezoelectric effect during exercise to charge the battery. The battery life evaluation formula is optimized to L = h(N, T charge , T discharge , T average ), where T average is the average operating temperature of the battery.

[0016] Furthermore, it also includes a safety monitoring and emergency module. This module introduces a biometric monitoring sensor to monitor the user's physiological state in real time. Combining with the motion state judgment formula S = f(P, a, T, H, R, ε) and physiological state data, the safety risk assessment formula is Risk = m(S, HR, SpO 2 ), where HR is the heart rate, SpO 2 is the blood oxygen saturation, m is the risk assessment function. When a risk situation is detected, it automatically sends a rescue request containing the user's location, motion state, and physiological state to the nearby rescue base station.

[0017] Furthermore, the pressure sensor in the sensor module adopts a fiber Bragg grating pressure sensor, which has the advantages of anti-electromagnetic interference and corrosion resistance. Its pressure-wavelength drift characteristic is quantified by the calibration formula Δλ = k FBG × P, where Δλ is the wavelength drift amount, k FBG is the FBG pressure sensing coefficient.

[0018] Furthermore, the deep reinforcement learning algorithm in the data processing module adopts a deep Q-network based on the attention mechanism. This algorithm automatically focuses on the key features in the sensor data, and the attention weight allocation formula where Q, K, and V are data matrices, and d k is the feature dimension, and σ is the activation function. Through this formula, the wear evaluation formula W = α×D history +β×D current +γ×ε and the performance prediction formula P performance = g(T, H, P, a, R, ε) are optimized for their parameters.

[0019] Furthermore, the wireless energy harvesting technology of the communication module adopts a new type of triboelectric nanogenerator TENG. TENG generates electrical energy using the frictional and vibrational energy in ice and snow sports. Its output power is related to the friction frequency f and the contact area A, and is quantified through the power output formula P TENG = k TENG ×f×A, where k TENG is the TENG energy conversion coefficient. Combining with software-defined network SDN technology, according to the energy harvesting situation and communication requirements, the working mode and transmission power of the communication module are dynamically adjusted.

[0020] Furthermore, the gesture recognition function of the user terminal interaction module adopts a gesture perception technology based on millimeter-wave radar. The millimeter-wave radar recognizes the user's gesture actions in complex environments, and extracts gesture features through the gesture feature extraction formula Gesture = extract(radar s ignal), where radar s ignal is the millimeter-wave radar signal, and extract is the feature extraction function. At the same time, the voice interaction function adopts an adaptive speech recognition algorithm, which automatically adjusts the recognition parameters according to the environmental noise level.

[0021] Furthermore, it includes the following steps:

[0022] Data acquisition step: The multi-modal fusion sensor of the sensor module continuously acquires data such as pressure, acceleration, temperature, humidity, reflectivity, and strain P, a, T, H, R, ε, and determines the user's motion posture using the composite motion state judgment formula S = f(P, a, T, H, R, ε);

[0023] Data processing step: The edge computing node performs preliminary screening and preprocessing on the sensor data. The cloud computing center uses the deep Q-network algorithm based on the attention mechanism, combines with the multi-agent collaborative learning model, and applies the wear evaluation formula W = α×D history +β×D current +γ×ε and the performance prediction formula P performance= g(T, H, P, a, R, ε) evaluates equipment wear and predicts performance changes;

[0024] Data transmission step: The SDN controller of the communication module selects a communication protocol and a transmission path according to the signal strength judgment formula and network congestion conditions, and at the same time uses wireless energy harvesting technology to power the communication;

[0025] Data display and interaction step: The user terminal interaction module uses gesture recognition and voice interaction functions, combines augmented reality technology, displays equipment status data on the holographic projection interface, receives user instructions, and when the data exceeds the threshold, sends a reminder message according to the push formula Push = send(message, user).

[0026] Furthermore, during the operation of the system, the battery management module adopts intelligent thermal management technology, and adjusts the battery temperature according to the heat balance formula Q in -Q out = C × ΔT, charges the battery using wireless charging and energy recovery technology. At the same time, according to the optimized battery life evaluation formula L = h(N, T charge , T discharge , T average ), predicts the remaining battery life. When the battery power is lower than the threshold, the system working mode is adjusted according to the energy-saving strategy formula S save = {reduce(P load1 )}, switch(protocol1)}.

[0027] Furthermore, the safety monitoring and emergency module uses biometric monitoring sensors to continuously monitor the user's physiological state, combines the motion state judgment formula S = f(P, a, T, H, R, ε) and the safety risk assessment formula Risk = m(S, HR, SpO 2 ), evaluates the safety risk level. When a risk situation is detected, an emergency response is triggered through the emergency trigger formula Trigger = condition(Risk high ), and a distress message is sent to emergency contacts and rescue base stations and a local alarm is activated.

[0028] Compared with the existing technologies, the beneficial effects of the present invention are:

[0029] The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things of this patent has remarkable beneficial effects. In terms of equipment performance monitoring, the system can collect various data of the equipment, such as pressure, acceleration, strain, etc., in real time and accurately through the integration of multi-modal fusion sensors. Using advanced compound motion state judgment formulas and wear assessment formulas, the performance state and wear degree of the equipment can be comprehensively and accurately evaluated. This enables athletes and enthusiasts to timely understand the condition of the equipment, perform maintenance and replacement in advance, and avoid affecting sports performance and safety due to equipment failures.

[0030] In terms of sports safety guarantee, the system introduces biometric monitoring sensors to monitor the user's physiological state in real time and combines the motion state data for safety risk assessment. When a high-risk situation is detected, it can quickly trigger an emergency response, send distress messages to emergency contacts and rescue base stations, and activate the local alarm. This greatly improves the safety in ice and snow sports and provides reliable safety guarantee for athletes.

[0031] In terms of environmental adaptability, the optical sensors and temperature and humidity sensors in the system can sense environmental information such as the reflectivity, temperature, and humidity of the ice and snow surface in real time. Through the performance prediction formula, it provides performance prediction and adaptability suggestions for the equipment under different environments for users, helping users adjust sports strategies and equipment selection according to environmental changes and improving the sports experience.

[0032] In terms of data management and analysis, the system adopts a hierarchical processing architecture combining edge computing and cloud computing and distributed ledger technology to achieve efficient data processing, secure storage, and authorized access. Based on the collaborative learning model of multi-agent and deep reinforcement learning algorithms, the data is deeply mined and analyzed, providing scientific data support for athletes and coaches, and helping to formulate personalized training plans and improve sports performance.

[0033] In addition, the user terminal interaction module of the system adopts gesture recognition, voice interaction, and augmented reality (AR) technologies to provide an immersive interaction experience, enabling users to obtain equipment information and sports data more conveniently and intuitively, and further enhancing the user experience and the practicality of the system. Brief Description of the Drawings

[0034] Figure 1 It is a schematic block diagram of an intelligent monitoring system for ice and snow sports equipment based on the Internet of Things proposed by the present invention;

[0035] Figure 2 It is a schematic block diagram of an intelligent monitoring method for ice and snow sports equipment based on the Internet of Things proposed by the present invention. Detailed Embodiments

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0037] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0038] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined. In addition, the terms "mounted", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations. The present invention will be further described in detail below with reference to the accompanying drawings.

[0039] Refer to Figure 1-2 : An intelligent monitoring system for ice and snow sports equipment based on the Internet of Things, comprising a sensor module, a data processing module, a communication module, a storage module and a user terminal interaction module.

[0040] Sensor Module: It integrates various types of sensors to construct a multi-modal perception system. Among traditional sensor types, pressure sensors can acutely capture external pressure changes. Whether it is a slight touch or a large load, they can accurately measure and feedback data. Acceleration sensors focus on monitoring the acceleration of the device during movement. Whether it is a rapid sprint or a slow movement, they can track the dynamic changes of the movement in real time. Temperature sensors and humidity sensors are responsible for monitoring the temperature and humidity in the environment, providing important information about the surrounding environmental state for the system, which is crucial for applications in different climate conditions.

[0041] In addition to these traditional sensors, the module also introduces two new types of sensors, namely optical sensors and strain sensors. Optical sensors adopt advanced miniaturized quantum dot photodetectors, which endow them with the ability to work under extremely low light conditions. In snow-covered scenarios, it can precisely sense the subtle changes in the reflectivity of the snow surface. This sensing ability is of great significance for judging the snow quality. For example, through the reflectivity data, information such as the freshness and compactness of the snow can be analyzed, providing important references for skiing and other related activities. Strain sensors use flexible and stretchable graphene materials, which have good flexibility and ductility. It can be accurately attached to the parts of the equipment that are prone to deformation, and precisely measure the minute deformations of the equipment during use. These minute deformation data can reflect the stress conditions and usage status of the equipment, which are of great value for ensuring the safety and performance optimization of the equipment. Using the composite motion state judgment formula S = f(P, a, T, H, R, ε) (where S is the user's motion posture, P is pressure, a is acceleration, T is temperature, H is humidity, and R is the reflectivity measured by the optical sensor) can more comprehensively and accurately determine the user's motion posture, such as accurately distinguishing different types of skiing techniques in complex snow track environments.

[0042] Data Processing Module: It uses an advanced and unique hierarchical processing architecture, which cleverly combines the advantages of edge computing and cloud computing. In terms of edge computing, edge computing nodes are deployed at the equipment end. These nodes undertake crucial preliminary data processing tasks. When sensors continuously collect data, edge computing nodes will conduct preliminary screening and preprocessing on this data. Specifically, it can identify and remove a large amount of redundant information. For example, in some continuous monitoring scenarios, there may be repetitive and worthless data, and edge computing nodes can efficiently filter it out, thus reducing the subsequent data transmission pressure. This process is like opening a smoother channel for data transmission, avoiding congestion problems that may be caused by the transmission of a large amount of invalid data.

[0043] In the cloud computing part, the cloud computing center plays a powerful role in in-depth analysis. Here, deep reinforcement learning algorithms are used to deeply mine and analyze the data that has been preliminarily processed by edge computing. Deep reinforcement learning algorithms can find potential rules and patterns from a large amount of data. By constructing a collaborative learning model based on multi-agent, the equipment data of different users can cooperate and learn from each other. For example, the data collected by the skiing equipment of many skiing enthusiasts can be referenced and analyzed together under this model. In this process, the system can continuously optimize the wear assessment formula W = α×D history +β×D current +γ×ε (γ is the weight coefficient of strain data). This formula comprehensively considers the historical wear data D of the equipment history and the current wear data D current . By optimizing the parameters in the formula through multi-agent collaborative learning, the assessment of the equipment wear condition becomes more accurate. At the same time, the performance prediction formula P performance = g(T, H, P, a, R, ε) is also optimized in this process. This formula combines multiple factors such as temperature T, humidity H, pressure P, acceleration a, and the reflectivity R of the optical sensor, so as to be able to predict the performance of the equipment more comprehensively and accurately. In this way, the accuracy and generalization ability of the assessment and prediction are greatly improved, that is, it can not only accurately assess and predict in the current data environment, but also maintain good performance under different scenarios and data conditions.

[0044] Communication module: The software-defined network (SDN) technology is introduced to achieve flexible configuration and management of the communication network. With the help of the SDN controller, according to the signal strength judgment formula (where I represents the signal strength, k is a constant, P t is the transmission power, d is the transmission distance, and n is the path loss exponent) and the network congestion condition, the communication protocol and transmission path are adjusted in real time. This measure can effectively cope with the complex and changeable communication environment and ensure the high efficiency and stability of data transmission.

[0045] At the same time, this module adopts wireless energy harvesting technology to fully utilize the vibration and temperature difference energy generated in ice and snow sports to power the communication module. This innovative power supply method significantly reduces the dependence on batteries, thereby extending the communication battery life and providing a strong guarantee for the equipment to communicate stably for a long time in the ice and snow sports scenario.

[0046] Storage Module: The distributed ledger technology, i.e., blockchain, is used to carry out data storage and management. Data is stored in an encrypted form on multiple nodes. This method greatly ensures data security because encryption makes it difficult for data to be illegally obtained and cracked. At the same time, multi-node storage also avoids data loss caused by a single node failure and fundamentally eliminates the possibility of data tampering because the characteristics of blockchain make it almost impossible to modify the information on the entire chain with the computing power required for tampering.

[0047] Using smart contract technology, automatic authorized access and sharing of data are realized. A smart contract is an automatically executed contract. When the preset conditions are met, the contract will automatically execute relevant operations. In the data storage scenario, it can automatically grant access and sharing permissions to eligible users or systems according to the set rules. Through the data retrieval formula R = search(type, time, access k ey) (access k ey is the authorized access key), only authorized users or systems can query and call relevant data by virtue of the correct authorized access key and specifying retrieval conditions such as data type and time, further ensuring the security and controllability of data access.

[0048] User Terminal Interaction Module: A dual-mode interaction interface has been developed, including two methods: gesture recognition and voice interaction. In terms of gesture recognition, users can interact with the system through simple gesture actions such as waving and making a fist. These common and easy-to-operate gestures provide users with an intuitive interaction way and can convey instructions without complex operation processes. In terms of voice interaction, users can issue voice commands such as "query the wear condition of the equipment", and the system can recognize and execute corresponding operations. This method is particularly convenient when users' hands are busy or inconvenient for manual operations. Combining with augmented reality (AR) technology, using the viewing angle transformation formula View = transform(position, orientation), equipment information and motion data are displayed in the form of holographic projection on the user's smart glasses or helmet display. This technology can real-time transform the display viewing angle according to the user's position (position) and orientation (orientation), allowing users to obtain information as if they were on the spot, realizing an immersive interaction experience and enhancing the interestingness and convenience of the interaction between users and the system.

[0049] In the present invention, a battery management module is also included. This module adopts intelligent thermal management technology and adjusts the battery temperature through a micro thermoelectric cooler (TEC) to keep it always within the optimal working temperature range T optimal . Using the heat balance formula Q in -Q out= C × ΔT (Q in is the heat generation of the battery, Q out is the heat dissipation, C is the heat capacity of the battery, and ΔT is the temperature change), and the battery temperature is monitored and controlled in real time. At the same time, a combination of wireless charging technology and energy recovery technology is adopted to recover part of the energy through electromagnetic induction and piezoelectric effect during exercise to charge the battery. The battery life evaluation formula is optimized to L = h(N, T charge , T discharge , T average )(T average is the average working temperature of the battery), to more accurately predict the remaining battery life.

[0050] In the present invention, a safety monitoring and emergency module is further included. This module introduces biometric monitoring sensors, such as a heart rate sensor and a blood oxygen sensor, to monitor the user's physiological state in real time. Combining the motion state judgment formula S = f(P, a, T, H, R, ε) and the physiological state data, the safety risk level of the user is evaluated through the safety risk assessment formula Risk = m(S, HR, SpO 2 )(HR is the heart rate, SpO 2 is the blood oxygen saturation, and m is the risk assessment function). When a high-risk situation is detected, in addition to sending a distress message to the emergency contact and activating the local alarm, it can also automatically send a rescue request containing the user's precise location, motion state, and physiological state to the nearby rescue base station to improve the rescue response speed.

[0051] In the present invention, the pressure sensor in the sensor module adopts a new type of fiber Bragg grating (FBG) pressure sensor, which has the advantages of high sensitivity, anti-electromagnetic interference, and corrosion resistance. Its pressure-wavelength drift characteristic is quantified through the precise calibration formula Δλ = k FBG × P (Δλ is the wavelength drift amount, k FBG is the FBG pressure sensing coefficient), which can collect the pressure data P more accurately and further improve the accuracy of the composite motion state judgment formula S = f(P, a, T, H, R, ε).

[0052] In the present invention, the deep reinforcement learning algorithm in the data processing module adopts a deep Q-network (DQN) based on the attention mechanism. This algorithm can automatically focus on the key features in the sensor data, and through the attention weight allocation formula (Q, K, V are data matrices, d k is the feature dimension, and σ is the activation function), optimize the parameters of the wear evaluation formula W = α × D history + β × D current + γ × ε and the performance prediction formula P performaxnce = g(T, H, P, a, R, ε) to improve the accuracy and efficiency of evaluation and prediction.

[0053] In the present invention, the wireless energy harvesting technology of the communication module adopts a novel triboelectric nanogenerator (TENG). TENG generates electrical energy by utilizing the frictional and vibrational energy in ice and snow sports. Its output power is related to the friction frequency f and the contact area A, and is quantified through the power output formula P TENG = k TENG × f × A (k TENG is the TENG energy conversion coefficient). This means that during ice and snow sports, the higher the friction frequency and the larger the contact area, the more electrical energy TENG can theoretically generate. For example, when skiing, the friction between the ski board and the snow surface and the vibration generated by the equipment during movement can all be utilized by TENG to generate electricity. At the same time, combined with software-defined network (SDN) technology, the system can dynamically adjust the working mode and transmission power of the communication module according to the energy harvesting situation and communication requirements. When sufficient energy is harvested, the communication module may be allowed to operate in a higher power and more efficient working mode to ensure fast and stable data transmission; when the energy harvesting is insufficient, the transmission power is reduced and the working mode is adjusted to maintain the communication function and save energy, ensuring that the communication module can better meet the communication requirements under different energy conditions.

[0054] In the present invention, the gesture recognition function of the user terminal interaction module adopts a gesture perception technology based on millimeter-wave radar. The millimeter-wave radar can accurately recognize the gesture actions of users in complex environments. The gesture features are extracted through the gesture feature extraction formula Gesture = extrsct(radar s ignal) (radar s ignal is the millimeter-wave radar signal, and extract is the feature extraction function). In this process, the millimeter-wave radar emits signals and receives the reflected signals. The feature extraction function analyzes the feature information related to gestures, such as the shape, movement trajectory, speed, etc. of the gestures from these signals, thereby realizing fast and accurate gesture interaction. The voice interaction function adopts an adaptive speech recognition algorithm, which can automatically adjust the recognition parameters according to the environmental noise level. In a noisy ice and snow sports environment, such as in a ski resort with noisy crowds and whistling wind and snow, the algorithm can increase the gain of the voice signal and improve the sensitivity to voice features; in a quiet environment, the relevant parameters are appropriately reduced to reduce misrecognition. Through this adaptive adjustment, the accuracy of speech recognition is improved, enabling users to interact with the system more smoothly through voice in various environments.

[0055] In the present invention, the following steps are included: Data acquisition step: The pressure sensor can accurately sense the magnitude of the externally applied pressure. Whether it is a slight touch or a large load, it can accurately record the corresponding pressure data P; the acceleration sensor monitors the acceleration changes of the device during movement in real time, providing dynamic information a about the movement state of the system for the system; the temperature sensor and the humidity sensor focus on monitoring environmental parameters, respectively collecting environmental temperature T and humidity H data. These environmental information are crucial for analyzing the movement conditions under different climate conditions; the miniaturized quantum dot photodetector in the optical sensor can accurately sense the change in the reflectivity R of the ice and snow surface under extremely low light conditions, providing data support for judging the snow quality and other conditions; the strain sensor uses a flexible and stretchable graphene material, which can be accurately attached to the easily deformed parts of the equipment to measure the minute deformation ε of the equipment.

[0056] After collecting these data, using the composite motion state judgment formula S = f(P, a, T, H, R, ε), comprehensively analyzing and processing various data can more comprehensively and accurately determine the user's motion posture, providing reliable basic data for subsequent motion analysis, equipment state evaluation, etc.

[0057] Data processing step: In the data processing step, a hierarchical processing mode is adopted. The edge computing node first conducts preliminary screening and preprocessing on the data collected by the sensors. The sensors will collect a large amount of data, among which there are some redundant or invalid information. The edge computing node removes these unnecessary data through specific algorithms, reducing the burden of subsequent data transmission and processing. For example, it removes the abnormal data generated by the sensors due to short-term interference. The cloud computing center undertakes more complex processing tasks. It uses the deep Q-network algorithm based on the attention mechanism. This algorithm can focus on key information in a large amount of data, improving the efficiency and accuracy of data processing. At the same time, combined with the multi-agent collaborative learning model, the data of different user equipment can cooperate and learn from each other. In terms of evaluating equipment wear and predicting performance changes, the wear evaluation formula W = α×D history +β×D current +γ×ε and the performance prediction formula P performaxnce = g(T, H, P, a, R, ε) are used to predict the performance changes of the equipment, providing a reference basis for the maintenance and use of the equipment.

[0058] Data transmission step: The SDN controller of the communication module judges according to the signal strength judgment formula Based on the signal strength and network congestion situation, the optimal communication protocol and transmission path are selected. The purpose of doing this is to ensure the efficiency and stability of data transmission. When the signal strength is weak or the network is congested, by timely adjusting the communication protocol and transmission path, problems such as data transmission delay and packet loss can be avoided. In addition, this communication module also uses wireless energy harvesting technology. In the ice and snow sports scenario, this technology can utilize the vibration energy generated by movement and the temperature difference energy in the environment, convert them into electrical energy, and supply power to the communication module. This measure reduces the dependence of the communication module on traditional batteries, effectively extends the communication endurance time, and ensures continuous and stable power supply during data transmission.

[0059] Data display and interaction steps: It has dual functions of gesture recognition and voice interaction. The gesture recognition function can accurately capture the user's actions such as waving and making a fist, and convert them into operation instructions. The voice interaction function can recognize voice instructions such as "query the wear condition of the equipment" from the user. At the same time, this module combines augmented reality (AR) technology to display the equipment status data on the holographic projection interface. These data cover various aspects of information such as the wear degree, performance parameters, and power of the equipment. After the user issues an instruction, the system will respond and process quickly. When it is detected that the equipment status data exceeds the preset threshold, the system will strictly send a reminder message according to the push formula Push = send(message, uset).

[0060] In the present invention, during the operation of the system, the battery management module adopts intelligent thermal management technology, adjusts the battery temperature according to the heat balance formula Q in -Q out = C × ΔT, and uses wireless charging and energy recovery technology to charge the battery. At the same time, according to the optimized battery life evaluation formula L = h(N, T charge , T discharge , T average ), predicts the remaining battery life. When the battery power is low, the system working mode is adjusted according to the energy-saving strategy formula S save = {reduce(P load1 ), switch(protocol1)}.

[0061] In the present invention, the safety monitoring and emergency module uses biometric monitoring sensors to continuously monitor the user's physiological state, and combines the motion state judgment formula S = f(P, a, T, H, R, ε) and the safety risk assessment formula Risk = m(S, HR, SpO 2 ) to evaluate the safety risk level. When a high-risk situation is detected, an emergency response is triggered through the emergency trigger formula Trigger = condition(Risk high ), and a distress message is sent to emergency contacts and rescue base stations and the local alarm is activated.

[0062] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered by the protection scope of the present invention.

Claims

1. An intelligent monitoring system for ice and snow sports equipment based on the Internet of Things, characterized in that: include: Sensor module: Integrates multi-modal fusion sensors, including traditional pressure, acceleration, temperature and humidity sensors as well as optical sensors and strain sensors; The optical sensor uses a miniaturized quantum dot photodetector to sense the reflectivity change of the ice and snow surface under extremely low light conditions. The strain sensor measures the tiny deformation ε of the equipment. The composite motion state judgment formula is S=f(P, a, T, H, R, ε), where S is the user's motion posture, P is pressure, a is acceleration, T is temperature, H is humidity, and R is reflectivity. Data processing module: adopts a layered processing architecture that combines edge computing and cloud computing. Edge computing nodes are deployed at the equipment end to perform preliminary screening of sensor data; deep reinforcement learning algorithms are used in the cloud computing center to conduct in-depth mining and analysis of data; a collaborative learning model based on multi-agents is constructed, and the wear assessment formula is optimized as W = α × D history +β×D current +γ×ε, where γ is the weight coefficient of strain data, and the performance prediction formula is P performance =g(T, H, P, a, R, ε); Communication module: Introduce software-defined network technology to realize the configuration and management of communication network. Through SDN controller, according to the signal strength judgment formula and network congestion, adjust the communication protocol and transmission path, P t Indicates the signal transmission power; wireless energy harvesting technology is used to power the communication module; Storage module: Distributed ledger technology is used to store and manage data. Data is stored in multiple nodes in an encrypted form. At the same time, smart contract technology is used to realize automatic authorized access and sharing of data. The data retrieval formula R = search (type, time, access k ey), where access k ey is the authorized access key; User terminal interaction module: A dual-mode interaction interface based on gesture recognition and voice interaction has been developed. Combined with augmented reality AR technology, the perspective transformation formula View = transform (position, orientation) is used to display equipment information and motion data in a holographic projection manner on the user's smart glasses or helmet display.

2. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: It also includes a battery management module, which uses intelligent thermal management technology to adjust the battery temperature through a micro-thermoelectric cooler to keep it in the optimal operating temperature range T optimal , using the heat balance formula Q in -Q out =C×ΔT real-time monitoring and control of battery temperature, where Q in The battery generates heat, Q out is heat dissipation, C is the battery heat capacity, ΔT is the temperature change, and at the same time, a combination of wireless charging technology and energy recovery technology is used to recover part of the energy to charge the battery through electromagnetic induction and piezoelectric effect during exercise. The battery life evaluation formula is optimized to L = h (N, T charge , T discharge , T average ), where T average is the average operating temperature of the battery.

3. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: It also includes a safety monitoring and emergency response module, which introduces biometric monitoring sensors to monitor the user's physiological state in real time. Combined with the motion state judgment formula S=f(P, a, T, H, R, ε) and physiological state data, the safety risk assessment formula is Risk=m(S, HR, SpO2), where HR is heart rate, SpO2 is blood oxygen saturation, and m is the risk assessment function. When a risk situation is detected, a rescue request containing the user's location, motion state and physiological state is automatically sent to a nearby rescue base station.

4. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: The pressure sensor in the sensor module adopts a fiber Bragg grating pressure sensor, which has the advantages of anti-electromagnetic interference and corrosion resistance. Its pressure-wavelength drift characteristic is calibrated by the formula Δλ=k FBG ×P is quantified, where Δλ is the wavelength drift, k FBG is the FBG pressure sensing coefficient.

5. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: The deep reinforcement learning algorithm in the data processing module adopts a deep Q network based on the attention mechanism, which automatically focuses on the key features in the sensor data. The attention weight allocation formula is Among them, Q, K, V are data matrices, d k is the feature dimension, σ is the activation function, and the wear assessment formula W = α × D is optimized through this formula history +β×D current +γ×ε and performance prediction formula P performance = parameters of g(T, H, P, a, R, ε).

6. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: The wireless energy harvesting technology of the communication module adopts a new type of friction nanogenerator TENG. TENG uses the friction and vibration energy in ice and snow movement to generate electrical energy. Its output power is related to the friction frequency f and the contact area A. The power output formula P TENG =k TENG ×f×A for quantization, where k TENG The energy conversion coefficient of TENG is combined with software-defined network (SDN) technology to dynamically adjust the working mode and transmission power of the communication module according to the energy collection situation and communication requirements.

7. The intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to claim 1 is characterized in that: The gesture recognition function of the user terminal interaction module adopts the gesture perception technology based on millimeter wave radar. The millimeter wave radar recognizes the user's gesture in a complex environment and extracts the gesture feature through the gesture feature extraction formula Gesture = extract (radar s signal) to extract gesture features, among which radar s Signal is the millimeter-wave radar signal, extract is the feature extraction function, and the voice interaction function uses an adaptive speech recognition algorithm to automatically adjust the recognition parameters according to the ambient noise level.

8. A method for applying the intelligent monitoring system for ice and snow sports equipment based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The following steps are involved: Data collection steps: The multimodal fusion sensor of the sensor module collects data such as pressure, acceleration, temperature, humidity, reflectivity and strain in real time, P, a, T, H, R, ε, and uses the composite motion state judgment formula S = f (P, a, T, H, R, ε) to determine the user's motion posture; Data processing steps: The edge computing node performs preliminary screening and preprocessing of sensor data. The cloud computing center uses a deep Q network algorithm based on the attention mechanism, combined with a multi-agent collaborative learning model, and uses the wear assessment formula W = α × D history +β×D current +γ×ε and performance prediction formula P performance = g(T, H, P, a, R, ε) to assess equipment wear and predict performance changes; Data transmission steps: The SDN controller of the communication module judges the formula based on the signal strength and network congestion, select communication protocols and transmission paths, and use wireless energy harvesting technology to power communications; Data display and interaction steps: The user terminal interaction module uses gesture recognition and voice interaction functions, combined with augmented reality technology, to display equipment status data on the holographic projection interface and receive user instructions. When the data exceeds the threshold, a reminder message is sent according to the push formula Push = send (message, user).

9. The ice and snow sports equipment monitoring method according to claim 8, characterized in that: During system operation, the battery management module adopts intelligent thermal management technology and uses the thermal balance formula Q in -Q out =C×ΔT adjusts the battery temperature, uses wireless charging and energy recovery technology to charge the battery, and at the same time, according to the optimized battery life evaluation formula L=h(N, T charge , T discharge , T average ) predicts the remaining battery life. When the battery power is lower than the threshold, the energy saving strategy formula S save ={reduce(P load1 ), switch(protocol1)} to adjust the system working mode.

10. The ice and snow sports equipment monitoring method according to claim 8, characterized in that: The safety monitoring and emergency module uses biometric monitoring sensors to monitor the user's physiological state in real time, and combines the motion state judgment formula S = f (P, a, T, H, R, ε) and the safety risk assessment formula Risk = m (S, HR, SpO2) to assess the safety risk level. When a risk situation is detected, the emergency trigger formula Trigger = condition (Risk) is used to trigger the user's physiological state in real time. high ) triggers an emergency response, sends a distress message to emergency contacts and rescue base stations, and initiates a local alarm.

Images