Personalized intelligent rope skipping and real-time exercise health data management and analysis system

Abstract

The invention provides a personalized intelligent rope skipping and real-time exercise health data management and analysis system, and relates to the technical field of health management. The system comprises a microcontroller, a data acquisition module, a communication module, a rope skipping adjustment module, an energy collection module and an auxiliary function module which are integrated in a rope skipping handle, and a data analysis module, a user data management module, a personalized exercise scheme generation module and a mobile terminal which are integrated in a remote server, the data acquisition module, the communication module, the rope skipping adjustment module, the energy supply and recovery module and the auxiliary function module are all connected with the microcontroller; the system can monitor the physical condition of the user in real time so as to predict the exercise risk of the user, can provide individualized training guidance for the user according to historical data and other input data of the user, and can recover kinetic energy and convert the kinetic energy into electric energy.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to a personalized intelligent rope skipping and real-time sports health data management and analysis system. Background Art

[0002] With the acceleration of the pace of modern life, people's demand for fitness equipment is increasing. Rope skipping, as a simple and efficient way of fitness, is very popular among the general public. However, traditional rope skipping can hardly meet users' needs for personalized and scientific fitness, such as training difficulty adjustment and accurate fitness data tracking. Existing smart rope skipping still has shortcomings in some parameter calculation methods and data analysis methods. For example, only using heart rate as a calculation indicator to calculate calorie consumption will lead to inaccurate data and incomplete analysis. At the same time, the lack of monitoring of important sports indicators such as user fatigue status and recovery degree makes the problem of sports safety still unresolved; in addition, the accuracy and stability of continuous and reliable monitoring of long-term exercise and health data and personalized intelligent analysis also need to be improved.

[0003] Chinese patent CN104941109A describes a method for estimating calories consumed using the cumulative count of a counter. This method estimates the energy consumed by the user by monitoring the number of movements the user makes during exercise. In short, it associates each movement with a preset calorie consumption value, and then makes a cumulative estimate of calories based on this. However, this simple counter-based method has some obvious disadvantages. Due to individual differences in metabolism and energy consumption. Estimating calorie consumption based solely on the number of movements may not accurately reflect the individual's actual energy consumption. Due to differences in weight, age, gender and physical condition, different users may consume different calories when doing the same number of movements.

[0004] Chinese patent CN112657117B discloses a method and device for recommending rope skipping courses. The method mainly uses a gyroscope and a Hall sensor to obtain the number of data points [n1, n2, n3, ..., nm] in each of the m circles of continuous rope skipping; the user's rope skipping action, coordination, stability, rhythm, and endurance score are calculated based on the number of data points [n1, n2, n3, ..., nm] in each of the m measured circles of rope skipping; and the training courses that need to be pushed are obtained based on the action, coordination, stability, rhythm, and endurance scores. However, the method mainly relies on gyroscopes and Hall sensors to collect data, the data source is too single, and there is a lack of personalized feedback, such as personalized training suggestions.

[0005] Chinese patent CN116779161A discloses a physical fitness analysis method based on rope skipping exercise, that is, a method for performing physical fitness analysis based on rope skipping exercise data. This method mainly obtains certain physical fitness index data of the user by obtaining the user's rope skipping exercise data, such as rope throwing rate, take-off frequency, first rope skipping time, first rope skipping number, reaction delay time and final score, and performs physical fitness analysis based on this. However, this method lacks a comprehensive health assessment. It only focuses on evaluating physical fitness through rope skipping data, while ignoring other factors that may affect physical fitness, such as personal heart rate, recovery time, etc. This may cause the physical fitness analysis data obtained by the user to be too one-sided.

[0006] Chinese patent CN115414626A discloses an intelligent rope skipping device, which is characterized in that it can detect the user's posture in the air and calculate it through an intelligent algorithm chip in the device. However, the defect of this device is that the detection device used is installed on the rope, that is, it is penetrated by the rope. This will bring multiple problems: First, it is difficult to avoid damage to the device due to the violent collision between the rope and the hard plane (such as a wall). Second, this structure greatly increases the difficulty of daily charging, and does not fully utilize the kinetic energy brought by the rope. Third, this device does not effectively separate and manage the data of different users, and does not provide personalized analysis for each user. Summary of the invention

[0007] The technical problem to be solved by the present invention is to provide a personalized intelligent rope skipping and real-time sports health data management and analysis system in response to the above-mentioned deficiencies in the prior art, so as to realize personalized sports decision support based on rope skipping and real-time sports health data, and enhance the effect and safety of exercise.

[0008] In order to solve the above technical problems, the technical solution adopted by the present invention is: a personalized intelligent rope skipping and real-time sports health data management and analysis system, including a microcontroller integrated in the rope skipping handle, a data acquisition module, a communication module, a rope skipping adjustment module, an energy collection module, an auxiliary function module and a data analysis module integrated in a remote server, a user data management module and a personalized exercise program generation module and a mobile terminal; the data acquisition module, the communication module, the rope skipping adjustment module, the energy collection module, and the auxiliary function module are all connected to the microcontroller;

[0009] The data acquisition module is arranged in the handle of the skipping rope, and is used to collect the user's grip strength, pulling force and vital signs data, and transmit the collected data to the microcontroller for processing, and then transmit it to the remote server responsible for data analysis through the communication module;

[0010] The skipping rope adjustment module is used to generate an adjusted skipping rope training program according to the personalized program generation module, and automatically adjust the rope to adapt to different application scenarios and personal sports hobbies of users, while ensuring safety to avoid sports injuries caused by setting inappropriate length;

[0011] The energy collection module provides or stores electrical energy for other modules by recovering the kinetic energy generated by the user during rope skipping;

[0012] The auxiliary module provides users with prompts including voice, vibration, and display, so as to achieve the functions of posture correction, training guidance, real-time information reminder, and rope skipping retrieval;

[0013] The data analysis module is integrated in the remote server and is used to perform functional analysis and calculation on the data output by the data acquisition module, and transmit the data analysis results to the personalized solution generation module;

[0014] The user data management module is integrated in the remote server, and identifies different users based on the data analysis results of the data analysis module, and separates and manages the data of each different user;

[0015] The personalized program generation module provides the user with personalized program selection based on the analysis results of the data analysis module and the user's input data, and provides the user with a training method suitable for him or her.

[0016] Preferably, the data acquisition module includes a sensor module, a signal preprocessing module and a signal encoding module; the sensor module uses a variety of sensors to collect the user's grip strength, pulling force and vital signs data;

[0017] The signal preprocessing module processes each signal collected by the sensor module through an analog circuit filter and a multi-stage amplifier to perform analog signal processing and AD conversion to obtain a digital signal;

[0018] The signal encoding module encodes the digital signal processed by the signal preprocessing module and transmits it to the mobile terminal and the remote server using a low-power Bluetooth module.

[0019] Preferably, the sensor module includes a grip force sensor, a tension sensor, an ECG sensor, a pulse and blood oxygen sensor, a linear Hall sensor and a three-axis acceleration sensor arranged in the double skipping rope handle, which are used to collect the user's grip force, tension, ECG data, pulse and blood oxygen, user's spatial position, and rope swinging times and speed data.

[0020] Preferably, the ECG sensor uses a flexible ECG sensor to collect ECG data of the user; the flexible ECG sensor includes a highly conductive graphene electrode sheet for collecting ECG signals, a polyurethane flexible substrate that can achieve high adhesion to the rope skipping handle, and a stretchable liquid metal-based conductive path connected to the signal processing unit;

[0021] The method for preparing the flexible electrocardiogram sensor comprises:

[0022] Step 1. Preparation of polyurethane solution: vacuum dehydrate the macromolecular diol, diisocyanate and amino-terminated chain extender, cool to room temperature, drop the macromolecular diol into the diisocyanate, stir at high speed under high temperature and nitrogen environment, move to room temperature, pour the solvent into the diisocyanate and stir evenly, then drop the amino-terminated chain extender at room temperature and stir to obtain a polyurethane solution;

[0023] Step 2. Preparation of graphene electrode sheets: mechanically exfoliating graphite powder in a solvent, filtering and drying to obtain a few-layer graphene nanosheet, and spreading the nanosheet on a mold for pressing to obtain a graphene electrode sheet;

[0024] Step 3. Preparation of a flexible ECG sensor: Pour a polyurethane solution onto a mold with a reserved conductive path and perform a semi-curing treatment to obtain a semi-cured polyurethane flexible substrate, and then place two graphene electrode sheets on the substrate; inject liquid metal into the conductive path, place a signal processing unit, place a skipping rope handle in the mold, obtain an overall device, and continue to perform a curing treatment to finally obtain a flexible ECG sensor with high adhesion to the skipping rope handle;

[0025] In step 1, the mass ratio of macromolecular diol, isocyanate, terminal amino chain extender and solvent is 10-20:3-5:10-15:1-3; the vacuum dehydration conditions are: dehydration at 110-130°C and -0.9-1MPa for 1.5-3h; the rate of dripping the macromolecular diol is 5-10s / drop, and then stirring for 1-2.5h under a nitrogen environment of 75-85°C at a speed of 300-500rpm; after pouring the solvent, stirring is continued for 10-30min; the rate of dripping the terminal amino chain extender is 5-10s / drop, and the stirring time is 5-15min;

[0026] In step 2, the mechanical stripping process is to mechanically strip at a rotation speed of 25000 to 30000 rpm for 25 to 35 minutes; the pressure during the pressing process is 10 to 20 MPa;

[0027] In step 3, the total length of the conductive path is 40-50 mm and the width is 5-10 mm; the semi-curing treatment parameters are: curing at 45-60°C for 1-2 hours; the center distance between the two graphite electrode sheets is 25-30 mm; and the curing parameters are: curing at 45-60°C for 5-10 hours.

[0028] Preferably, the specific method by which the data analysis module performs functional analysis and calculation on the data output by the data acquisition module is:

[0029] a. Use the grip force data collected by the grip force sensor to evaluate the user's fatigue status in real time and calculate and generate a fatigue curve;

[0030] a-1: Data collection:

[0031] User grip force data G obtained in real time from a grip force sensor;

[0032] a-2: Grip strength baseline establishment:

[0033] Before the user starts training, obtain the user's maximum grip strength G max and baseline grip strength G min ;

[0034] a-3: Grip force attenuation calculation:

[0035] According to the user's real-time grip strength and baseline grip strength, the grip force decay rate ΔG is calculated:

[0036]

[0037] a-4: Fatigue index determination:

[0038] The fatigue index F is determined from the grip force decay rate using the following formula:

[0039] F=K2·ΔG

[0040] Among them, K2 is the empirical coefficient, which describes the relationship between the grip strength decay rate and fatigue level;

[0041] a-5: Generate fatigue curve:

[0042] As the training time progresses, the fatigue index F value is continuously collected and plotted into a time-fatigue index curve, namely the fatigue curve;

[0043] a-6: Real-time fatigue status display:

[0044] Provide users with real-time fatigue assessment based on the fatigue index value F; when the fatigue index F exceeds the set threshold, the user is prompted that they are seriously fatigued and is advised to take a rest;

[0045] b. Calculate the user's real-time energy consumption by combining the rope's tension, rotation speed, and the user's heart rate;

[0046] b-1. Data Collection:

[0047] The average tension L of the skipping rope is measured by the tension sensor;

[0048] The rotation speed V of the skipping rope is measured by a linear Hall sensor;

[0049] Get the user's real-time heart rate HR through the heart rate sensor;

[0050] Obtain the strength of the user's ECG signal through an ECG sensor;

[0051] b-2. Establish a basic energy consumption model:

[0052] Use the following formula to calculate the user's basic calorie consumption C base :

[0053] C base =a·C HR +b·C V +c·C L +d ECG

[0054] Where: C HR , C V , C L is the user's calorie consumption per minute estimated based on the parameters HR, V, and L, a, b, c, and d are all weight coefficients; C HR , C V , C L Calculated by the following formula:

[0055]

[0056] Where HR0 is the resting heart rate; m is the user's weight; f1 is the conversion factor for calories; f2 is the conversion factor for converting joules to kilocalories;

[0057] C V =MET·m·f3

[0058] Where MET is metabolic equivalent, and f3 is a constant that relates MET to calorie consumption;

[0059]

[0060] Among them, r is the rope skipping radius calculated based on the user's physical data, and f4 is the conversion factor from joules to kilocalories;

[0061] Then the basic calorie consumption calculation formula of the user is obtained as follows:

[0062]

[0063] b-3. Adjustment of individual differences:

[0064] Calculate the individual difference adjustment coefficient K1 based on the height h, weight m, age o and gender g entered by the user:

[0065] K1=f SVM (h,m,o,g)

[0066] Among them, f SVM It is a function obtained by fitting using support vector machine SVM and combining with the actual energy consumption of the user;

[0067] For a given input feature x = (h, m, o, g), the output of SVM is expressed as:

[0068]

[0069] Among them, α i is the weight coefficient of the support vector, b is the bias term; K(x i ,x) is the radial basis kernel of the kernel function, x i The feature vector representing the i-th sample in the training set;

[0070] Based on the naive regression SVM, the hyperparameters of SVM are tuned through Bayesian optimization, specifically:

[0071] The Bayesian optimization goal is to minimize the prediction error of SVM, and the objective function is:

[0072]

[0073] Among them, C and γ are the regularization parameters and the parameters of the RBF kernel as the kernel function, respectively, and their purpose is to find the optimal hyperparameter combination; is the individual difference adjustment coefficient predicted by the support vector machine SVM;

[0074] b-4. Calculate the final energy consumption:

[0075] Combine the user's basic energy consumption and individual differences to calculate the total energy consumption C total :

[0076] C total =K1·C

[0077] c. Evaluate the user's physical condition through the user's heart rate and ECG data to measure exercise recovery time and efficiency;

[0078] c-1. Data Collection:

[0079] Get the user's heart rate data HR in real time t ;

[0080] c-2. Training end sign detection:

[0081] When the user's heart rate drops close to the resting heart rate or the user actively marks the end of training, the recovery time measurement mode begins;

[0082] c-3. Baseline data acquisition:

[0083] Before the user starts training, obtain a resting ECG base , and calculate the resting heart rate HR base For reference;

[0084] c-4. Recovery time starts:

[0085] The moment when the training end mark is detected is marked as the starting point of the recovery time t start ;

[0086] c-5. Calculation of recovery degree:

[0087]

[0088] Among them, HR max is the maximum heart rate recorded during the user's training; R represents the user's current recovery level;

[0089] c-6. Determine the time when recovery is completed:

[0090] When the R value is lower than the preset threshold R0, it is marked as the end point of the recovery time t end ;

[0091] c-7. Calculate the recovery time T recovery :

[0092] T recovery =t end -t start

[0093] c-8. Historical recovery data analysis:

[0094] After each recovery time assessment, save and collect all historical recovery time data, and conduct comprehensive analysis to determine the average recovery time of users;

[0095]

[0096] Where N is the number of training times of user history, Indicates the average recovery time of users;

[0097] d. Based on the existing user height and weight data, combined with the skipping history data and information in the biometric database, the user's arm length is calculated, so as to further deduce the skipping rope length suitable for the user;

[0098] d-1. Data Collection:

[0099] Obtain the user's height h, leg length l, and jumping height n when skipping rope; and calculate the user's shoulder width, arm length, and arm length after removing the shoulder width based on the user's height;

[0100] d-2. Establish the rope skipping curve equation:

[0101] The rope skipping curve is set to a parabola, and the curve equation is y=f(x). The horizontal coordinates of the hand from the hip when skipping rope are obtained from the user's arm length as a and b, respectively. The length L of the curve from a to b is:

[0102]

[0103] d-3. Solve the skipping rope curve equation to obtain the optimal skipping rope length suitable for the user.

[0104] Preferably, the user data management module compares the biometric features obtained from the ECG and pulse data by the data analysis module with the user biometric data stored in the database;

[0105] If the obtained biometric features match the biometric data in the database, the user's identity will be verified and the user's relevant information will be displayed; if they do not match, the user will be prompted to re-authenticate or register their identity;

[0106] The data from different users are classified according to the user's login status or data entry information, and the data are grouped according to certain content and attributes, and then transmitted to the personalized solution generation module in batches;

[0107] Register, add, delete or manage user identity information through the management system.

[0108] Preferably, the personalized program generation module adopts a decision tree algorithm to generate a customized rope skipping training program based on the user's personal information and the sports goal selected by the user;

[0109] According to the analysis results of the data analysis module, the skipping rope training program is adjusted to meet the needs of individual differences.

[0110] Preferably, the skipping rope adjustment module includes a magnetic adjustment component, a motor and an optical sensor connected to a microcontroller and a skipping rope; the microcontroller monitors changes in rope length through the optical sensor; adjusts the rope swinging force by controlling the magnetic adjustment component; and automatically adjusts the skipping rope length by controlling the motor.

[0111] Preferably, the energy collection module includes a lithium battery, a small magnet, an oscillating generator, a rectifier, a current regulator and a power management chip; the small magnet and the oscillating generator are both connected to the skipping rope to convert the kinetic energy generated by the rope into storable and usable electrical energy to generate current; the rectifier and the current regulator are used to convert the generated alternating current into direct current and control the flow direction, charging and discharging process of the current to ensure stable current output; the power management chip is selected to realize safe charging and discharging of the lithium battery, and also provide safe power supply for other modules.

[0112] Preferably, the auxiliary module comprises a vibration motor, a speaker and a small screen with buttons connected to the microcontroller;

[0113] The vibration motor provides physical feedback to the user to help him adjust the skipping frequency;

[0114] The speaker is built into the handle of the skipping rope to provide the user with voice prompts and skipping rope retrieval functions;

[0115] The small screen with buttons is integrated on the handle of the skipping rope, providing a user interactive interface and displaying the user's exercise status in real time, including heart rate, number of skipping times, and calories consumed; the buttons enable the user to quickly browse data indicators and adjust various settings.

[0116] The beneficial effects of adopting the above technical solution are: the personalized intelligent rope skipping and real-time sports health data management and analysis system provided by the present invention,

[0117] (1) Provide a rope skipping tool that can autonomously adjust training intensity;

[0118] With the popularization of fitness concepts, the needs and physical differences of different fitness people make it difficult for a single fitness tool to meet the needs of everyone. Traditional rope skipping tools are difficult to adjust the strength of the rope, which may not be the best choice for both beginners and advanced users. Beginners may feel that the initial strength is too great and difficult to persist; while experienced fitness people may feel that the intensity is not enough and it is difficult to achieve exercise effects, which cannot meet the needs that change with the training process. Therefore, in the smart rope skipping health system provided by the present invention, a function that can adjust the rope swinging strength is specially designed. Through simple operations, fitness people can adjust the rope swinging difficulty according to their own needs and physical condition, so that fitness is more in line with personal conditions and improves fitness efficiency and experience. It can give early warnings and reminders to users' unreasonable settings and training intensity through information such as the user's heart rate, pulse, blood oxygen, etc., to ensure the safety of exercise.

[0119] (2) Achieve more reliable and comprehensive analysis of user fitness data, and even process tracking and comparative analysis, to help users perform fitness in a more personalized manner.

[0120] In contemporary times, data-driven has become the core concept in many fields. Many fields have developed a trend of multi-sensor fusion and intelligent algorithm fusion. In the field of fitness, accurate data analysis can help users better understand their physical condition and exercise effects, so as to develop a more suitable fitness plan. The intelligent skipping rope health system of the present invention can not only monitor the various physical data of the user during exercise in real time, such as heart rate, fatigue, etc., but also conduct in-depth analysis based on the user's historical data and other input data, provide users with detailed fitness reports and suggestions, and provide users with personalized training guidance. This data-driven method enables users to no longer exercise blindly, but to exercise scientifically according to their physical condition and needs, greatly improving the fitness effect and experience.

[0121] (3) Improve users’ fitness effects and safety and prevent sports injuries.

[0122] Safety is always the primary consideration for fitness. Excessive exercise or improper exercise methods may lead to sports injuries, which will not only affect the user's fitness results, but may also cause long-term damage to the body. Therefore, preventing sports injuries is one of the important goals of the present invention. By combining a variety of sensors, such as grip sensors, electrocardiogram sensors, etc., the system can monitor the user's physical condition in real time, such as fatigue, heart rate changes, etc., so as to predict the user's exercise risks. Once a possible risk is found, the system will immediately remind the user and give suggestions, such as taking a break for a period of time, adjusting the exercise method, etc., thereby greatly reducing the risk of sports injuries and ensuring that users can ensure their physical safety while enjoying fitness.

[0123] (4) Based on environmental protection and energy efficiency considerations.

[0124] As environmental protection and energy issues are increasingly receiving global attention, the design of smart devices should also actively respond to this trend and better utilize and preserve energy. The rope skipping system presented in the present invention came into being in this context. When users perform rope skipping exercises, a large amount of kinetic energy will be generated. Traditional rope skipping tools do not effectively utilize this energy, resulting in precious energy being wasted. However, the smart rope skipping health system of the present invention cleverly recycles this kinetic energy and converts it into electrical energy, further powering other modules of the system or storing it for future use. This not only greatly extends the use time of the equipment, but also reduces dependence on external power sources, making rope skipping tools more environmentally friendly and energy-efficient. This innovative design not only meets the user's demand for long-lasting battery life, but also gives traditional fitness tools a new environmental significance, reflecting the perfect combination of technology and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0125] Figure 1A structural block diagram of a personalized intelligent rope skipping and real-time sports health data management and analysis system provided by an embodiment of the present invention;

[0126] Figure 2 A workflow diagram of a personalized smart rope skipping and real-time sports health data management and analysis system provided by an embodiment of the present invention;

[0127] Figure 3 A block diagram of the implementation of the personalized smart rope skipping and real-time sports health data management and analysis system provided by an embodiment of the present invention;

[0128] Figure 4 A functional schematic diagram of a data analysis module provided by an embodiment of the present invention;

[0129] Figure 5 A schematic diagram of a rope skipping curve provided by an embodiment of the present invention;

[0130] Figure 6 A schematic diagram of a personalized solution generation module provided in an embodiment of the present invention generating a personalized solution;

[0131] Figure 7 A flow chart of a biometric feature comparison algorithm provided in an embodiment of the present invention;

[0132] Figure 8 User interaction interface preview provided by the embodiment of the present invention Figure 1 ;

[0133] Fig. 9 User interaction interface preview provided by the embodiment of the present invention Figure 2 ;

[0134] Fig.10 User interaction interface preview provided by the embodiment of the present invention Figure 3 . DETAILED DESCRIPTION

[0135] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0136] In this embodiment, a personalized intelligent rope skipping and real-time sports health data management and analysis system is provided. Figure 1-3 As shown, it includes a microcontroller integrated in the rope skipping handle, a data acquisition module, a communication module, a rope skipping adjustment module, an energy collection module, an auxiliary function module, a data analysis module integrated in a remote server, a user data management module, and a personalized exercise program generation module, as well as a mobile terminal;

[0137] The data acquisition module is arranged in the handle of the skipping rope, and is used to collect the user's grip strength, pulling force and vital signs data, and transmit the collected data to the microcontroller for processing, and then transmit it to the remote server responsible for data analysis through the communication module;

[0138] The skipping rope adjustment module is used to generate an adjusted skipping rope training program according to the personalized program generation module, and automatically adjust the rope to adapt to different application scenarios and corresponding needs of users;

[0139] The energy collection module provides or stores electrical energy for other modules by recovering the kinetic energy generated by the user during rope skipping;

[0140] The auxiliary module provides users with prompts including voice, vibration, and display, so as to achieve the functions of posture correction, training guidance, real-time information reminder, and rope skipping retrieval;

[0141] The data analysis module is integrated in the remote server and is used to perform functional analysis and calculation on the data output by the data acquisition module, and transmit the data analysis results to the personalized solution generation module;

[0142] The user data management module is integrated in the remote server, and identifies different users based on the data analysis results of the data analysis module, and separates and manages the data of each different user;

[0143] The personalized program generation module provides the user with personalized program selection based on the analysis results of the data analysis module and the user's input data, and provides the user with a training method suitable for him or her.

[0144] The data acquisition module includes a sensor module, a signal preprocessing module and a signal encoding module; the sensor module uses a variety of sensors to collect the user's grip strength, pulling force and vital signs data;

[0145] The signal preprocessing module processes and converts each signal collected by the sensor module through an analog circuit filter and a multi-stage amplifier to obtain a high-quality digital signal.

[0146] The signal encoding module encodes the digital signal processed by the signal preprocessing module and transmits it to the mobile terminal and the remote server using a low-power Bluetooth module.

[0147] The sensor module includes a grip sensor, a tension sensor, an ECG sensor, a pulse and blood oxygen sensor, a linear Hall sensor and a three-axis acceleration sensor arranged in the handle of the double skipping rope, and is used to collect the user's grip, tension, ECG data, pulse and blood oxygen, user's spatial position, and rope swing times and speed data;

[0148] In this embodiment, the function of the sensor module is to collect multiple data at the end of the skipping rope and transmit the data to the server responsible for data analysis. The various sensors in the sensor module are located in the front, middle and bottom of the skipping rope handle, connected to the microprocessor in the middle and upper part of the skipping rope handle, and also connected to the energy collection module. The sensor module is divided into six parts: grip force sensor, tension sensor, electrocardiogram sensor, speed and counting sensor, pulse and blood oxygen sensor, and skipping rope handle relative position sensor. The implementation schemes of the six parts will be introduced below:

[0149] A1. Grip force sensing implementation solution:

[0150] A1.1 uses a grip force sensor for data collection; this sensor uses the piezoresistive effect. When subjected to pressure, its resistance value changes, thereby generating a voltage signal related to the pressure.

[0151] A1.2 performs analog-to-digital conversion on the collected voltage signal to obtain a digital representation of the grip force.

[0152] A1.3 transmits the digitized grip force data to the server for further analysis and processing.

[0153] A2. Tension sensor implementation solution:

[0154] A2.1 uses a tension sensor to detect the tension of the rope. This sensor is based on metal strain gauge technology and can accurately measure tension as small as micronewton.

[0155] A2.2 Convert the analog voltage signal output by the tension sensor into a digital signal.

[0156] A2.3 transmits the converted tension data to the server for analysis.

[0157] A3. ECG sensing implementation solution:

[0158] A3.1 Use a flexible ECG sensor to detect the user's ECG signal;

[0159] In this embodiment, the flexible ECG sensor includes a highly conductive graphene electrode sheet for collecting ECG signals, a polyurethane flexible substrate that can achieve high adhesion to the handle of a skipping rope, and a stretchable liquid metal-based conductive path connected to a signal processing unit.

[0160] The polyurethane flexible substrate in the flexible ECG sensor is 450 μm thick, 80 mm long and 30 mm wide, the total length of the liquid metal conductive path is 40 mm and 5 mm wide, the radius of the two circular graphene electrode sheets is 5 mm, the center distance is 30 mm, and the thickness is 250 μm.

[0161] The specific preparation method of the flexible electrocardiogram sensor includes:

[0162] Step 1. Preparation of polyurethane solution: vacuum dehydrate the macromolecular diol, diisocyanate and amino-terminated chain extender, cool to room temperature, drop the macromolecular diol into the diisocyanate, stir at high speed under high temperature and nitrogen environment, move to room temperature, pour the solvent into the diisocyanate and stir evenly, then drop the amino-terminated chain extender at room temperature and stir to obtain a polyurethane solution;

[0163] Step 2. Preparation of graphene electrode sheets: mechanically exfoliating graphite powder in a solvent, filtering and drying to obtain a few-layer graphene nanosheet, and spreading the nanosheet on a mold for pressing to obtain a graphene electrode sheet;

[0164] Step 3. Preparation of a flexible ECG sensor: Pour a polyurethane solution onto a mold with a reserved conductive path and perform a semi-curing treatment to obtain a semi-cured polyurethane flexible substrate, and then place two graphene electrode sheets on the substrate; inject liquid metal into the conductive path, place a signal processing unit, place a skipping rope handle in the mold, obtain an overall device, and continue to perform a curing treatment to finally obtain a flexible ECG sensor with high adhesion to the skipping rope handle;

[0165] In step 1, the macromolecular diol includes one or more of polyether polyols, polyester polyols, polyolefin polyols and terminal hydroxyl block copolymers of the above materials with a molecular weight Mn=200-5000, preferably polyether polyols, polyester polyols and terminal hydroxyl block copolymers, and the most preferred terminal hydroxyl block copolymers. Macromolecular polyols with different molecular weights act as soft segments of polyurethane molecular chains, which will determine the deformation ability of the prepared resin.

[0166] In step 1, the diisocyanate includes, but is not limited to, one or more of diphenylmethane-4,4'-diisocyanate (MDI), isophorone diisocyanate (IPDI), hexamethylene diisocyanate (HDI) and toluene diisocyanate (TDI), preferably IPDI and HDI.

[0167] In step 1, the terminal amino chain extender includes but is not limited to diaminodimethylthiotoluene, 4,4'-bis-sec-butylaminodiphenylmethane, diethyltoluenediamine, isophoronediamine and adipic acid dihydrazide, ethylenediamine, 1,2-propylenediamine, 2,5-dimethyl-2,5-hexanediamine, 1,11-undecyldiamine, 1,12-dodecyldiamine, 2,4'-diamino-dicyclohexylmethane, 1-amino-3,3,5-trimethyl-5-aminomethylcyclohexane, 2,4-toluenediamine or 2,6-toluenediamine, 2,4'-diaminodiphenylmethane or 4,4'-diaminodiphenylmethane and mixtures thereof. The above-mentioned amino-terminated chain extender also includes but is not limited to 1,4-butanediamine, 1,6-hexanediamine, 2,4,4-trimethyl-1,6-hexanediamine, 1-amino-3,3,5-trimethyl-5-aminomethylcyclohexane, 4,4,-diamino-dicyclohexylmethane, 3,3,-dimethyl-4,4,-diamino-dicyclohexylmethane and mixtures thereof. Preferably, 4,4'-bis-sec-butylaminodiphenylmethane, diethyltoluenediamine, isophoronediamine and adipic acid dihydrazide are used. The urea bond synthesized by different chain extenders and isocyanate acts as the hard segment of the polyurethane molecular chain, and hydrogen bonds are formed between the hard segments of different molecular chains, which will give the prepared resin good tensile strength.

[0168] In step 1, the solvent includes but is not limited to one or more of N,N-dimethylformamide (DMF), N,N-dimethylacetamide (DMAc), toluene, tetrahydrofuran, preferably DMF and DMAc.

[0169] In step 1, the mass ratio of macromolecular diol, isocyanate, terminal amino chain extender and solvent is 10-20:3-5:10-15:1-3; the vacuum dehydration conditions are: dehydration at 110-130°C and -0.9-1MPa for 1.5-3h; the rate of dripping the macromolecular diol is 5-10s / drop, and then stirring for 1-2.5h under a nitrogen environment of 75-85°C at a speed of 300-500rpm; after pouring the solvent, stirring is continued for 10-30min; the rate of dripping the terminal amino chain extender is 5-10s / drop, and the stirring time is 5-15min;

[0170] In step 2, the mechanical stripping process is to mechanically strip at a rotation speed of 25000 to 30000 rpm for 25 to 35 minutes; the pressure during the pressing process is 10 to 20 MPa;

[0171] In step 3, the total length of the conductive path is 40-50 mm and the width is 5-10 mm; the semi-curing treatment parameters are: curing at 45-60°C for 1-2 hours; the center distance between the two graphite electrode sheets is 25-30 mm; and the curing parameters are: curing at 45-60°C for 5-10 hours.

[0172] Finally, a flexible ECG sensor with high adhesion to the handle of the skipping rope was obtained.

[0173] The electrical conductivity of the graphene electrode sheet can reach 1000-1400 S / cm (the electrical conductivity test is carried out on the thermoelectric test platform MRS-3RT using the classic four-terminal sensing method).

[0174] The polyurethane flexible substrate has good flexibility, and the elongation at break can reach more than 300%.

[0175] The flexible ECG sensor prepared by the present invention can realize real-time collection of ECG signals during rope skipping by being attached to the handle of rope skipping, and uses liquid metal as a conductive path to connect the signal processing unit, which can realize arbitrary bending and twisting of the circuit, and become a stable signal collection unit during exercise.

[0176] A3.2 Preprocess the collected ECG signals: first pass through the first-stage amplifier and perform high-pass filtering; then enter the second-stage amplifier and perform low-pass filtering; finally, remove the power frequency interference through notch filtering to obtain an amplified ECG signal with good signal quality.

[0177] A3.3 digitizes the preprocessed ECG signal and transmits it to the server.

[0178] A4. Speed ​​and counting sensor implementation solution

[0179] A4.1 uses a linear Hall sensor to detect the speed and count of rope skipping. The Hall sensor uses the Hall effect. When current passes through a magnetic field, a voltage is generated in a direction perpendicular to the current and magnetic field, thereby detecting the rotation and number of rope skipping.

[0180] A4.2 performs analog-to-digital conversion on the signal output by the Hall sensor.

[0181] A4.3 transmits the digitized speed and count data to the server for analysis.

[0182] A5. Pulse and blood oxygen sensing implementation solution

[0183] A5.1 uses an optical sensor to measure the user's pulse and blood oxygen. The sensor uses infrared absorption technology to calculate the blood oxygen concentration by detecting the oxygen saturation in the blood.

[0184] A5.2 Convert the analog signal output by the sensor into a digital signal.

[0185] A5.3 transmits the digitized pulse and blood oxygen data to the software for further analysis.

[0186] A6. Rope skipping handle relative position sensing implementation solution

[0187] A6.1 Use a microcontroller to periodically read the data from the three-axis accelerometer.

[0188] A6.2 De-noises and amplifies the signal in the analog circuit.

[0189] A6.3 converts the output analog signal into a digital signal.

[0190] A6.4 transmits the digital signal to a server responsible for data analysis for further processing.

[0191] In this embodiment, the communication module uses a low-power Bluetooth module to communicate with the mobile terminal. All digital data collected by the sensor is pre-processed by the microcontroller, transmitted to the Bluetooth module through the serial port, and then sent to the mobile terminal by the Bluetooth module for real-time display or data analysis.

[0192] The specific method by which the data analysis module performs functional analysis and calculation on the data output by the data acquisition module is:

[0193] a. Use the grip force data collected by the grip force sensor to evaluate the user's fatigue status in real time and calculate and generate a fatigue curve;

[0194] b. Calculate the user's real-time energy consumption by combining the rope's tension, rotation speed, and the user's heart rate;

[0195] c. Evaluate the user's physical condition through the user's heart rate and ECG data to measure exercise recovery time and efficiency;

[0196] d. Based on the existing user height and weight data, combined with previous rope skipping history data and information in the biometric database, the user's arm length is calculated, thereby further calculating the rope skipping length suitable for the user;

[0197] In this embodiment, from the functional point of view, Figure 4 As shown, the functions of the data analysis module can be divided into: accurate energy consumption calculation, real-time fatigue state assessment, recovery time measurement, rope skipping length estimation, rope skipping handle spatial relative coordinate calculation, rope skipping posture correction and biometric feature extraction. This embodiment will be introduced according to different functions.

[0198] B1. Accurate energy consumption calculation:

[0199] In order to more accurately estimate the energy consumption of users during rope skipping training, the following steps were adopted:

[0200] B1.1. Data Collection:

[0201] The following data are obtained from each sensor in real time:

[0202] L- The average tension of the skipping rope, measured by a tension sensor, in Newton (N).

[0203] V-Rotation speed of the skipping rope, measured by a linear Hall sensor, in revolutions per second.

[0204] HR - user's real-time heart rate, obtained through a heart rate sensor, in beats per minute.

[0205] ECG - The strength of the ECG signal, obtained by the ECG sensor, in millivolts (mV).

[0206] B1.2. Establish a basic energy consumption model:

[0207] Use the following formula to calculate basic calorie expenditure C base :

[0208] C base =a·C HR +b·C V +c·C L +d ECG

[0209] Where: C HR , C V , C L is the estimated calorie consumption per minute based on HR, V, L and other parameters, a, b, c, d are weight coefficients obtained based on a large amount of experimental data and references. HR , C V , C L The data can be obtained by calculating the following formula:

[0210]

[0211] HR0 is the resting heart rate, usually 60-100 beats / minute; m is the user's weight, in kg; f1 is the calorie conversion factor based on experience, which indicates the approximate conversion factor of the energy consumed by the human body after the heart rate exceeds the resting heart rate during exercise, and its value is usually 0.6309;

[0212] 1kcal=4184

[0213] f2 is the conversion factor for converting joules (J) to kilocalories (kcal), and its value here is usually 4.184.

[0214] C V =MET·m·f3(kcal / min)

[0215] Speed ​​V reflects the intensity of exercise. Calorie consumption can be estimated by MET (Metabolic Equivalent of Task, which indicates how many times the energy consumed during exercise is compared to that at rest. 1 MET is usually defined as the energy consumed per kilogram of body weight per minute at rest, which is about 3.5 ml of oxygen, equivalent to 1 kcal / kg / hour). Different speeds V correspond to different MET values:

[0216] Rope skipping speed V (r / s) Rope skipping speed (times / minute) MET value 1.0-1.33 rpm 60-80 times / minute 8-10 1.33-2.0 rpm 80-120 times / minute 10-12 2.0-2.67 rpm 120-160 times / minute 12-14 2.67-3.33 rpm 160-200 times / minute 14-16 >3.33 rpm >200 times / minute >16

[0217] f3 is a constant that relates MET to calorie expenditure and its value is:

[0218]

[0219] The calories consumed can be estimated based on the force L applied to the rope measured by the tension sensor during rope skipping:

[0220]

[0221] r is the skipping rope movement radius calculated based on the user's arm length and other body data, and its unit is m. f4 is the conversion coefficient from joule (J) to kilocalorie (kcal), and its value here is 4184.

[0222] The total calorie consumption formula is:

[0223]

[0224] B1.3. Adjustment of individual differences:

[0225] Since each user's metabolic rate and health status are different, an adjustment factor K1 is introduced to take these differences into account. This factor is calculated based on the height h, weight w, age o and gender g entered by the user.

[0226] K1=f SVM (h,w,o,g)

[0227] Among them, f SVM It is a function obtained by fitting using a support vector machine (SVM) by collecting a large amount of user data and combining it with their actual energy consumption.

[0228] This embodiment uses regression SVM to predict K1. For a given input feature x = (h, w, o, g), the output of SVM can be expressed as:

[0229]

[0230] Among them, α iis the weight coefficient of the support vector, which is obtained through training optimization together with the bias term b; K(x i ,x) is the radial basis kernel (RBF kernel), x i The feature vector representing the i-th sample in the training set.

[0231] Based on the naive regression SVM, Bayesian optimization is added for SVM hyperparameter tuning. The process is as follows:

[0232] Bayesian optimization approximates the objective function by constructing a Gaussian process regression surrogate model, and gradually optimizes the objective function by updating the surrogate model. Here, our goal is to minimize the prediction error of SVM, and its objective function can be expressed as:

[0233]

[0234] Among them, C and γ are the regularization parameters and the parameters of the RBF kernel as the kernel function, respectively, and their purpose is to find the optimal hyperparameter combination. K1 is the individual difference adjustment coefficient obtained from the actual energy consumption data; is the adjustment coefficient predicted by SVM.

[0235] B1.4. Calculate the final energy consumption:

[0236] Combine the basic energy expenditure with individual differences to calculate the total energy expenditure C total :

[0237] C total =K1·C

[0238] B2. Real-time fatigue status assessment:

[0239] In order to evaluate the fatigue status of users during rope skipping training in real time, the following steps were adopted:

[0240] B 2.1. Data Collection:

[0241] G-User grip force data obtained in real time from the grip force sensor, in Newton (N).

[0242] B2.2. Grip strength baseline establishment:

[0243] Before the user starts training, the user is required to perform a maximum grip strength test to obtain the maximum grip strength value G. max Similarly, users are also required to maintain their grip strength in a natural state to obtain their baseline grip strength G min .

[0244] B2.3. Grip force attenuation calculation:

[0245] According to the user's real-time grip strength and baseline grip strength, the grip force decay rate ΔG is calculated:

[0246]

[0247] B2.4. Determination of fatigue index:

[0248] The fatigue index F is determined from the grip force decay rate using the following formula:

[0249] F=K2·ΔG

[0250] Among them, K2 is an empirical coefficient that describes the relationship between grip strength decay rate and fatigue level.

[0251] B2.5. Generate fatigue curve:

[0252] As the training time progresses, the fatigue index F value is continuously collected and plotted into a time-fatigue index curve, namely the fatigue curve.

[0253] B2.6. Real-time fatigue status display:

[0254] Provide users with real-time fatigue assessment based on the fatigue index value F. When the fatigue index F exceeds the set threshold, the user is prompted that they are seriously fatigued and is advised to take a rest.

[0255] B 3. Recovery time measurement:

[0256] To accurately measure and evaluate your recovery time and exercise effectiveness, follow these steps:

[0257] B3.1. Data collection:

[0258] HR t -Get the user's heart rate data in real time, in beats per minute.

[0259] B3.2. Training end sign detection:

[0260] When the user's heart rate drops close to resting heart rate or the user actively marks the end of training, the recovery time measurement mode begins.

[0261] B3.3. Baseline data acquisition:

[0262] Before the user starts training, obtain a resting ECG base , and calculate the resting heart rate HR base For reference.

[0263] B3.4. Recovery time starts:

[0264] The moment when the training end mark is detected is marked as the starting point of the recovery time t start .

[0265] B3.5. Calculation of recovery degree:

[0266]

[0267] Among them, HR max It is the maximum heart rate recorded during the user's training. R represents the user's current recovery level. The smaller the value, the better the recovery.

[0268] B3.6. Determine the time when recovery is completed:

[0269] When the R value is lower than the preset threshold R0, it is marked as the end point of the recovery time t end ;

[0270] B3.7. Calculate the recovery time T recovery :

[0271] T recovery =t end -t start

[0272] B3.8. Historical recovery data analysis:

[0273] After each recovery time assessment, save and collect all historical recovery time data, and conduct comprehensive analysis to determine the average recovery time of users;

[0274]

[0275] Where N is the number of training times of user history, Indicates the average recovery time for users.

[0276] B4. Rope skipping length calculation:

[0277] B4.1. Data collection:

[0278] h-user height, unit, meter;

[0279] B4.2. Data calculation:

[0280] Shoulder width ≈ 0.5 × height

[0281] Arm length ≈ 0.5 × height;

[0282] The arm length after removing the shoulder width ≈ arm length - (0.5 × height);

[0283] Assume the user's leg length is m and the jumping height when skipping rope is n.

[0284] B4.3.Based on Figure 5 Establish the equation of the skipping rope curve:

[0285] The curve equation of the shape of the rope affected by centrifugal force when skipping is roughly a parabola. Let its equation be y=f(x). From the user's arm length (forearm), we can get the horizontal coordinates of the hand's distance from the hip when skipping, which are a and b (the vertical coordinates of a and b are the same). Then we need to calculate the length of the curve from a to b.

[0286]

[0287] B5. Rope skipping posture correction:

[0288] B5.1 Tips for correct rope skipping posture:

[0289] (1) Skipping with both feet at the same time

[0290] Jumping rope with both feet at the same time is the most basic way. When jumping, put the center of gravity of the body on the front of the feet, tilt the overall center of gravity slightly forward, keep the upper arms close to the body, use the wrists to drive the forearms to shake the rope, bend the knees slightly, and lightly jump up with the front of the feet until the rope can pass quickly under your feet.

[0291] (2) Double-foot interactive rope skipping mode

[0292] Jumping rope with both feet alternately can be said to be the fastest way to jump rope, but this method of jumping has high requirements on cardiopulmonary capacity and can instantly increase a person's heart rate to 70-80% of the maximum heart rate. Beginners should be cautious when trying this.

[0293] (3) Skipping rope mode with open and closed feet

[0294] Jumping rope with open and close feet is to add the action of jumping rope to the opening and closing jumping. This rope jumping action can better train a person's coordination than the conventional jumping method with two feet.

[0295] (4) Other rope skipping modes

[0296] There are other correct ways to skip rope, such as: single-leg skipping, double-swing skipping, fancy skipping, etc.

[0297] B5.2 Scope of incorrect posture monitoring:

[0298] Mistake 1: Jumping too high

[0299] This way of skipping rope will increase the burden on the knees, and skipping for a long time will damage the knees.

[0300] Mistake 2: Spreading your arms too wide / shaking the rope with your arms

[0301] When skipping rope, if your upper arms are extended too wide and the amplitude is too large, and your arms shake the rope too vigorously, it will injure your arms.

[0302] Mistake 3: Unstable skipping rhythm

[0303] Keeping a steady speed while skipping rope can greatly improve the success rate of the skipping rope action and achieve the best exercise effect.

[0304] B5.3 Correction of Error 1:

[0305] The three-axis acceleration sensor is used to obtain the relative coordinates of the end of the skipping rope held by the user when standing, so as to calculate the height of the handle from the ground. The height h of the end of the skipping rope held by the user at the highest point when jumping is measured max When the height differs from the initial height of the skipping rope end by more than 8cm, a voice prompt will be given at the skipping rope end.

[0306] B5.4 Correction of Error 2:

[0307] The three-axis acceleration sensor is used to obtain the relative coordinates of the end of the skipping rope held by the user when standing, so as to calculate the height of the handle from the ground and compare it with the recommended height of the skipping rope end from the ground calculated by the system. If the difference is greater than 5cm, a voice prompt will be given.

[0308] B5.5 Correction of Error 3:

[0309] The speed of the skipping rope is measured by the Hall sensor and starts 30 seconds after the start of exercise. If the speed of the skipping rope decreases by more than 30 times / min within a 3-second interval or the speed of the skipping rope changes by more than 50 times / min within a 3-second interval, a voice prompt will be issued: A large change in the speed of the skipping rope is detected, and whether it is necessary to pause the exercise and rest.

[0310] B6. Biometric feature extraction:

[0311] B6.1 ECG data acquisition:

[0312] When the user holds the skipping rope handle, a pair of electrodes located in the grip part contacts the user's skin. These electrodes measure the voltage changes of the heart's electrical activity in real time, thereby capturing the user's ECG signals.

[0313] B6.2. Pulse wave data acquisition:

[0314] The optical sensor inside the handle senses the user's pulse waveform in real time through the skin. The data captured by the sensor first passes through a filter to remove possible noise or other interference. The peak value (P_peak) and valley value (P_valley) of the pulse waveform are identified and used to calculate the pulse frequency.

[0315] B6.3. Biometric Data Analysis:

[0316] Using the ECG and pulse wave data captured above, SVM is used to extract biometric features.

[0317] B6.4. Characteristics and parameter transmission:

[0318] The extracted biometric features will be transmitted to the user data management module for comparison and analysis.

[0319] In this embodiment, the user data management module obtains the biometric features from the ECG and pulse data through the data analysis module and compares them with the user biometric data stored in the database. Figure 6 As shown;

[0320] If the obtained biometric features match the biometric data in the database, the user's identity will be verified and the user's relevant information will be displayed: name, age, training goals, height and weight; if they do not match, the user will be prompted to re-authenticate or register their identity;

[0321] The data from different users are classified according to the user's login status or data entry information, and the data are grouped according to certain content and attributes (including height, weight, historical sports evaluation, etc.), and then transmitted to the personalized plan generation module in batches;

[0322] Register, add, delete or manage user identity information through the management system; this module allows users to flexibly manage their identity data to adapt to different usage scenarios.

[0323] In this embodiment, the specific measures for user management by the user data management module are as follows:

[0324] C1. Data matching and user identification:

[0325] C1.1. Use the data analysis module to extract user biometrics.

[0326] C1.2. Compare the extracted biometrics with the user's biometrics stored in the database.

[0327] C1.3. If a matching biometric feature is found, the user is successfully identified and the corresponding user information and service content will be automatically loaded.

[0328] C1.4. If no data matching the biometrics is found, the user will be proactively reminded to authenticate or register a new identity.

[0329] C2. Data separation and batch transmission:

[0330] C2.1. According to the results of biometric matching, different data are marked with 16-bit data labels.

[0331] C2.2. Through data labels, the health data of different identified users can be separated independently.

[0332] C2.3. Segment the separated data according to their specific attributes, and divide the data into data with different contents such as height, weight, and historical sports evaluation.

[0333] C2.4. The segmented data are transmitted one by one to the personalized solution generation module for processing.

[0334] C3. User identity management:

[0335] C3.1. Users can access the user management system through a specially designed interface.

[0336] C3.2. In the user management system, users can register their identities and fill in or update their personal information.

[0337] C3.3. Users can delete existing identities or add new identities as needed.

[0338] C3.4. To ensure data security and integrity, users are supported to back up and restore identity data.

[0339] In this embodiment, the personalized program generation module uses a decision tree algorithm to generate a customized rope skipping training program based on the user's personal information: height, weight, age, combined with the user's selected exercise goals, including muscle gain, fat loss, and body shape maintenance; according to the analysis results of the data analysis module, the rope skipping training program is adjusted to meet the needs of individual differentiation. Figure 7 As shown, the following is the specific implementation method:

[0340] D1. Data collection and preprocessing

[0341] D1.1. User input data: First, collect the data provided by the user, including height, weight, age, health status, and exercise goals (such as muscle gain or fat loss).

[0342] D1.2. Obtain the user's past exercise data from the user data management module.

[0343] D1.3. Data preprocessing: The input data is first cleaned to remove or repair any missing or erroneous data. Subsequently, all numerical data are normalized to the range of [0,1], expressed as

[0344]

[0345] This ensures that the decision tree considers all features equally during training.

[0346] D2. Establishment and training of decision tree model

[0347] D2.1. Feature selection: Select the best splitting features for the decision tree using criteria based on information gain or Gini impurity. Information gain is defined as:

[0348]

[0349] Where S is a given dataset, which contains the collected data of different users, A is a feature, Values(A) is the value of all features, S v is a subset of feature A whose value is v, and Entropy is the calculation of entropy.

[0350] D2.2. Node Splitting: When a node is considered “impure”, it is split into two or more sub-nodes. This process is performed based on the different values ​​of the selected features.

[0351] D2.3. Pruning: To avoid overfitting, pruning techniques are used to simplify the decision tree after training by removing subtrees that do not significantly improve model performance.

[0352] D2.4. Training termination: Training stops when all nodes reach a certain purity level or the tree reaches a preset maximum depth.

[0353] D2.5. Upload model: After the training is completed, the trained decision model will be saved in the remote server and deployed on the mobile terminal.

[0354] D3. Generate personalized training plan

[0355] D3.1. User data input: The user enters his / her height, weight, age and other information.

[0356] D3.2. Decision tree navigation: Based on the input data, navigate through the decision tree until you reach a leaf node.

[0357] D3.3. Output training scheme: Each leaf node is associated with a predefined rope skipping training scheme. When user data navigates to a specific leaf node, the training scheme associated with it is selected as output.

[0358] D4. Update and Iteration

[0359] D4.1. User feedback: After completing the training program, collect user feedback, such as exercise difficulty, satisfaction, etc.

[0360] D4.2. Training effect evaluation: The results obtained through the data analysis module are used to determine the effect of the user's training so as to obtain a reference for the next training plan.

[0361] D4.3. Decision tree update: Regularly update and retrain the decision tree with new user data and feedback information to ensure that it continues to adapt to changing user needs and feedback.

[0362] In this embodiment, the skipping rope adjustment module includes a magnetic force adjustment component, a motor and an optical sensor connected to a microcontroller and a skipping rope; the microcontroller monitors the change in rope length through an optical sensor; adjusts the rope swinging force by controlling the magnetic force adjustment component; and automatically adjusts the skipping rope length by controlling the motor to adapt to different application scenarios and corresponding needs of users. The following is its specific implementation process:

[0363] E1. Magnetic adjustment component design:

[0364] In this embodiment, the magnetic force adjustment component includes a small permanent magnet and an electromagnetic coil. The permanent magnet is fixed at one end of the skipping rope, and the electromagnetic coil is embedded in the other end. By adjusting the current in the electromagnetic coil, the magnetic field strength generated by the coil can be changed, thereby affecting the attraction or repulsion between the permanent magnet and the rope, thereby achieving the purpose of adjusting the rope swinging force.

[0365] E2. Microcontroller control:

[0366] E2.1. Use a microcontroller to control the current in the electromagnetic coil.

[0367] E2.2. The microcontroller adjusts the PWM (pulse width modulation) signal to change the current intensity in the electromagnetic coil according to the user's input or preset program.

[0368] E2.3. The relationship between current intensity and magnetic force can be experimentally determined in advance to ensure that the force input by the user matches the actual performance.

[0369] E3. Electronic component protection:

[0370] Ensure that there is sufficient insulation distance between the electromagnetic coil and existing electronic components, and use a protective shell and curing agent to prevent it from being affected by moisture, vibration and impact.

[0371] E4. Automatic adjustment of skipping rope length

[0372] E4.1. Combine the output of the data analysis module to find out the skipping rope length suitable for the user.

[0373] E4.2. Automatically adjust the length of the skipping rope to match the data analysis results through a motor directly connected to the skipping rope.

[0374] E4.3. Use an optical sensor to continuously monitor the change in rope length through the scale drawn on the rope to ensure that the motor adjustment action is accurate and smooth. If there is any deviation or the user needs, fine-tuning can be performed.

[0375] In this embodiment, the energy collection module includes a lithium battery, a small magnet, an oscillating generator, a rectifier, a current regulator and a power management chip; the small magnet and the oscillating generator are connected to the skipping rope to convert the kinetic energy generated by the rope into storable electrical energy to generate current; the rectifier and the current regulator are used to convert the generated alternating current into direct current and control the flow direction, charging and discharging process of the current to ensure a stable output current; the power management chip is selected to realize the safe charging and discharging of the lithium battery, which also provides safe power supply for other hardware modules. The specific implementation process is:

[0376] F1. Kinetic energy converted into electrical energy

[0377] F1.1. Install an oscillating generator inside the rope skipping handle, whose main components are a small magnet and a coil connected to the rope skipping handle.

[0378] F1.2. When the user performs rope skipping exercise, the swing of the rope handle causes the small magnet to move in the coil, generating electromagnetic induction, which in turn converts the user's kinetic energy into electrical energy.

[0379] F2. Current processing and optimization

[0380] F2.2. The alternating current generated by the oscillating generator must first be rectified in order to power or charge electronic devices.

[0381] F2.3. Use a diode with a maximum forward voltage greater than 5V and a maximum forward current greater than 1mA as a rectifier to convert AC power into DC power.

[0382] F2.4. Use a current regulator to further optimize the DC power while measuring the current, ensure the stability of the current, and control the current flow, charging and discharging process.

[0383] F3. Power management and safe power supply

[0384] F3.1. Select a power management chip with a built-in high-voltage power transistor to be responsible for the safe charging and discharging process of the lithium battery and provide high-precision constant voltage and constant current output performance.

[0385] F3.2. The power management chip ensures the safety of the lithium battery during charging and discharging, and provides a stable and reliable power supply for other hardware modules of the system.

[0386] F3.3. Select lithium batteries with a charge and discharge voltage not exceeding 10V and a capacity greater than 1500MAH as energy storage devices, and meet the energy storage requirements of the device within a limited space.

[0387] In this embodiment, the auxiliary module includes a vibration motor, a speaker and a small screen with buttons connected to the microcontroller;

[0388] The vibration motor provides physical feedback to the user to help him adjust the skipping frequency;

[0389] The speaker is built into the handle of the skipping rope to provide the user with voice prompts and skipping rope retrieval functions;

[0390] The small screen with buttons is integrated on the handle of the skipping rope, providing a user interactive interface and displaying the user's exercise status in real time, including heart rate, number of skipping times, and calories consumed; through buttons, the user can quickly browse data indicators and adjust various settings, including program selection, real-time calorie consumption display, and heart rate too fast reminder. The specific implementation process is:

[0391] G1. Vibration reminder function:

[0392] G1.1. A small and efficient vibration motor is installed inside the handle of the skipping rope.

[0393] G1.2. When the system detects that the user's skipping frequency deviates from the set target frequency, the microcontroller controls the vibration motor to provide physical feedback to the user.

[0394] G1.3. Users can judge whether their current skipping rhythm is consistent with the target by the frequency and intensity of the vibration motor, and make corresponding adjustments.

[0395] G2. Voice prompt function:

[0396] G2.1. Integrate a small speaker into the handle of the skipping rope.

[0397] G2.2. A series of voice prompts are pre-stored in the speaker, such as "speed up", "slow down", etc.

[0398] G2.3. According to the user's rope skipping status and data analysis results, the microcontroller controls the speaker to play corresponding voice prompts to guide the user to skip rope.

[0399] G2.4. When the user's rope skipping posture is incorrect, prompt in time to correct the user's mistake.

[0400] G3. Rope skipping retrieval function:

[0401] G3.1. Use the built-in speaker to provide users with a skipping rope retrieval function. When the user needs the system to assist in retrieval of the skipping rope, the skipping rope will play a voice prompt "The skipping rope is here" through the speaker through the user interface operation.

[0402] G3.2. The user can manually trigger the “retrieve” function through the mobile terminal or the buttons on the skipping rope.

[0403] G4. Real-time data display and user interaction:

[0404] G4.1. Integrate a small screen with buttons on the handle of the skipping rope.

[0405] G4.2. The screen displays the user's skipping data in real time, such as current heart rate, number of skipping times, frequency, etc.

[0406] G4.3. Combined with other sensor modules, such as heart rate sensor and frequency / frequency sensor, real-time data collection and display.

[0407] G4.4. Users can quickly adjust various skipping rope settings, such as target skipping frequency, vibration intensity, etc. through a screen with buttons.

[0408] In this embodiment, the user interaction interface is as follows: Figure 8-10 shown.

[0409] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present invention.

Claims

1. A personalized intelligent rope skipping and real-time sports health data management and analysis system, characterized by: It includes a microcontroller integrated in the rope skipping handle, a data acquisition module, a communication module, a rope skipping adjustment module, an energy collection module, an auxiliary function module, a data analysis module integrated in a remote server, a user data management module, a personalized exercise program generation module, and a mobile terminal; the data acquisition module, the communication module, the rope skipping adjustment module, the energy collection module, and the auxiliary function module are all connected to the microcontroller; The data acquisition module is arranged in the handle of the skipping rope, and is used to collect the user's grip strength, pulling force and vital signs data, and transmit the collected data to the microcontroller for processing, and then transmit it to the remote server responsible for data analysis through the communication module; The skipping rope adjustment module is used to generate an adjusted skipping rope training program according to the personalized program generation module, and automatically adjust the rope to adapt to different application scenarios and corresponding needs of users; The energy collection module provides or stores electrical energy for other modules by recovering the kinetic energy generated by the user during rope skipping; The auxiliary module provides users with prompts including voice, vibration, and display, so as to achieve the functions of posture correction, training guidance, real-time information reminder, and rope skipping retrieval; The data analysis module is integrated in the remote server and is used to perform functional analysis and calculation on the data output by the data acquisition module, and transmit the data analysis results to the personalized solution generation module; The user data management module is integrated in the remote server, and identifies different users based on the data analysis results of the data analysis module, and separates and manages the data of each different user; The personalized program generation module provides the user with personalized program selection based on the analysis results of the data analysis module and the user's input data, and provides the user with a training method suitable for him or her.

2. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 1 is characterized by: The data acquisition module includes a sensor module, a signal preprocessing module and a signal encoding module; the sensor module uses a variety of sensors to collect the user's grip strength, pulling force and vital signs data; The signal preprocessing module processes each signal collected by the sensor module through an analog circuit filter and a multi-stage amplifier to perform high-quality signal processing and AD conversion, and finally obtains an amplified digital signal; The signal encoding module encodes the digital signal processed by the signal preprocessing module and transmits it to the mobile terminal and the remote server using a low-power Bluetooth module.

3. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 2 is characterized by: The sensor module includes a grip force sensor, a tension sensor, an electrocardiogram sensor, a pulse and blood oxygen sensor, a linear Hall sensor and a three-axis acceleration sensor arranged in the double skipping rope handle, which are used to collect the user's grip force, tension, electrocardiogram data, pulse and blood oxygen, user's spatial position, and rope swinging times and speed data.

4. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 3 is characterized by: The ECG sensor uses a flexible ECG sensor to collect ECG data of the user; the flexible ECG sensor includes a highly conductive graphene electrode sheet for collecting ECG signals, a polyurethane flexible substrate that can achieve high adhesion to the rope skipping handle, and a stretchable liquid metal-based conductive path connected to a signal processing unit; The method for preparing the flexible electrocardiogram sensor comprises: Step 1. Preparation of polyurethane solution: vacuum dehydrate the macromolecular diol, diisocyanate and amino-terminated chain extender, cool to room temperature, drop the macromolecular diol into the diisocyanate, stir at high speed under high temperature and nitrogen environment, move to room temperature, pour the solvent into the diisocyanate and stir evenly, then drop the amino-terminated chain extender at room temperature and stir to obtain a polyurethane solution; Step 2. Preparation of graphene electrode sheets: mechanically exfoliating graphite powder in a solvent, filtering and drying to obtain a few-layer graphene nanosheet, and spreading the nanosheet on a mold for pressing to obtain a graphene electrode sheet; Step 3. Preparation of a flexible ECG sensor: Pour a polyurethane solution onto a mold with a reserved conductive path and perform a semi-curing treatment to obtain a semi-cured polyurethane flexible substrate, and then place two graphene electrode sheets on the substrate; inject liquid metal into the conductive path, place a signal processing unit, place a skipping rope handle in the mold, obtain an overall device, and continue to perform a curing treatment to finally obtain a flexible ECG sensor with high adhesion to the skipping rope handle; In step 1, the mass ratio of macromolecular diol, isocyanate, terminal amino chain extender and solvent is 10-20:3-5:10-15:1-3; the vacuum dehydration conditions are: dehydration at 110-130°C and -0.9-1MPa for 1.5-3h; the rate of dripping the macromolecular diol is 5-10s / drop, and then stirring for 1-2.5h under a nitrogen environment of 75-85°C at a speed of 300-500rpm; after pouring the solvent, stirring is continued for 10-30min; the rate of dripping the terminal amino chain extender is 5-10s / drop, and the stirring time is 5-15min; In step 2, the mechanical stripping process is to mechanically strip at a rotation speed of 25000 to 30000 rpm for 25 to 35 minutes; the pressure during the pressing process is 10 to 20 MPa; In step 3, the total length of the conductive path is 40-50 mm and the width is 5-10 mm; the semi-curing treatment parameters are: curing at 45-60°C for 1-2 hours; the center distance between the two graphite electrode sheets is 25-30 mm; and the curing parameters are: curing at 45-60°C for 5-10 hours.

5. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 3 is characterized by: The specific method by which the data analysis module performs functional analysis and calculation on the data output by the data acquisition module is: a. Use the grip force data collected by the grip force sensor to evaluate the user's fatigue status in real time and calculate and generate a fatigue curve; a-1: Data collection: User grip force data G obtained in real time from a grip force sensor; a-2: Grip strength baseline establishment: Before the user starts training, obtain the user's maximum grip strength G max and baseline grip strength G min ; a-3: Grip force attenuation calculation: According to the user's real-time grip strength and baseline grip strength, the grip force decay rate ΔG is calculated: a-4: Fatigue index determination: The fatigue index F is determined from the grip force decay rate using the following formula: F=K2·ΔG Among them, K2 is the empirical coefficient, which describes the relationship between the grip strength decay rate and fatigue level; a-5: Generate fatigue curve: As the training time progresses, the fatigue index F value is continuously collected and plotted into a time-fatigue index curve, namely the fatigue curve; a-6: Real-time fatigue status display: Provide users with real-time fatigue assessment based on the fatigue index value F; when the fatigue index F exceeds the set threshold, the user is prompted that they are seriously fatigued and is advised to take a rest; b. Calculate the user's real-time energy consumption by combining the rope's tension, rotation speed, and the user's heart rate; b-1. Data Collection: The average tension L of the skipping rope is measured by the tension sensor; The rotation speed V of the skipping rope is measured by a linear Hall sensor; Get the user's real-time heart rate HR through the heart rate sensor; Obtain the strength of the user's ECG signal through an ECG sensor; b-2. Establish a basic energy consumption model: Use the following formula to calculate the user's basic calorie consumption C base : C base =a·C HR +b·C V +c·C L +d·ECG Where: C HR , C V , C L is the user's calorie consumption per minute estimated based on the parameters HR, V, and L, a, b, c, and d are all weight coefficients; C HR , C V , C L Calculated by the following formula: Where HR0 is the resting heart rate; m is the user's weight; f1 is the conversion factor for calories; f2 is the conversion factor for converting joules to kilocalories; C V =MET·m·f3 Where MET is metabolic equivalent, and f3 is a constant that relates MET to calorie consumption; Among them, r is the rope skipping radius calculated based on the user's physical data, and f4 is the conversion factor from joules to kilocalories; Then the basic calorie consumption calculation formula of the user is obtained as follows: b-3. Adjustment of individual differences: Calculate the individual difference adjustment coefficient K1 based on the height h, weight m, age o and gender g entered by the user: K1=f SVM (h,m,o,g) Among them, F SVM It is a function obtained by fitting using support vector machine SVM and combining with the actual energy consumption of the user; For a given input feature x = (h, m, o, g), the output of SVM is expressed as: Among them, α i is the weight coefficient of the support vector, b is the bias term; K(x i ,x) is the radial basis kernel of the kernel function, x i The feature vector representing the i-th sample in the training set; Based on the naive regression SVM, the hyperparameters of SVM are tuned through Bayesian optimization, specifically: The Bayesian optimization goal is to minimize the prediction error of SVM, and the objective function is: Among them, C and γ are the regularization parameters and the parameters of the RBF kernel as the kernel function, respectively, and their purpose is to find the optimal hyperparameter combination; is the individual difference adjustment coefficient predicted by the support vector machine SVM; b-4. Calculate the final energy consumption: Combine the user's basic energy consumption and individual differences to calculate the total energy consumption C total : C total =K1·C c. Evaluate the user's physical condition through the user's heart rate and ECG data to measure exercise recovery time and efficiency; c-1. Data Collection: Get the user's heart rate data HR in real time t ; c-2. Training end sign detection: When the user's heart rate drops close to the resting heart rate or the user actively marks the end of training, the recovery time measurement mode begins; c-3. Baseline data acquisition: Before the user starts training, obtain a resting ECG base , and calculate the resting heart rate HR base For reference; c-4. Recovery time starts: The moment when the training end mark is detected is marked as the starting point of the recovery time t start ; c-5. Calculation of recovery degree: Among them, HR max is the maximum heart rate recorded during the user's training; R represents the user's current recovery level; c-6. Determine the time when recovery is completed: When the R value is lower than the preset threshold R0, it is marked as the end point of the recovery time t end ; c-7. Calculate the recovery time T recovery : T recovery =t end -t start c-8. Historical recovery data analysis: After each recovery time assessment, save and collect all historical recovery time data, and conduct comprehensive analysis to determine the average recovery time of users; Where N is the number of training times of user history, Indicates the average recovery time of users; d. Based on the existing user height and weight data, combined with the rope skipping history data and information in the biometric database, the user's arm length is calculated, thereby further calculating the rope skipping length suitable for the user; d-1. Data Collection: Obtain the user's height h, leg length l, and jumping height n when skipping rope; and calculate the user's shoulder width, arm length, and arm length after removing the shoulder width based on the user's height; d-2. Establish the rope skipping curve equation: The rope skipping curve is set to a parabola, and the curve equation is y=f(x). The horizontal coordinates of the hand from the hip when skipping rope are obtained from the user's arm length as a and b, respectively. The length L of the curve from a to b is: d-3. Solve the skipping rope curve equation to obtain the optimal skipping rope length suitable for the user.

6. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 1 is characterized by: The user data management module compares the biometric features obtained from the ECG and pulse data by the data analysis module with the user biometric data stored in the database; If the obtained biometric features match the biometric data in the database, the user's identity will be verified and the user's relevant information will be displayed; if they do not match, the user will be prompted to re-authenticate or register their identity; The data from different users are classified according to the user's login status or data entry information, and the data are grouped according to certain content and attributes, and then transmitted to the personalized solution generation module in batches; Register, add, delete or manage user identity information through the management system.

7. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 1 is characterized by: The personalized program generation module uses a decision tree algorithm to generate a customized rope skipping training program based on the user's personal information and the sports goals selected by the user; According to the analysis results of the data analysis module, the skipping rope training program is adjusted to meet the needs of individual differences.

8. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 1 is characterized by: The skipping rope adjustment module includes a magnetic adjustment component, a motor and an optical sensor connected to a microcontroller and a skipping rope; the microcontroller monitors the change in rope length through the optical sensor; adjusts the rope swinging force by controlling the magnetic adjustment component; and automatically adjusts the skipping rope length by controlling the motor.

9. The personalized intelligent rope skipping and real-time sports health data management and analysis system according to claim 1, characterized in that: The energy collection module includes a lithium battery, a small magnet, an oscillating generator, a rectifier, a current regulator and a power management chip; the small magnet and the oscillating generator are both connected to the skipping rope to convert the kinetic energy generated by the rope into storable and usable electrical energy to generate current; the rectifier and the current regulator are used to convert the generated alternating current into direct current and control the flow direction, charging and discharging process of the current to ensure a stable output current; the power management chip is selected to achieve safe charging and discharging of the lithium battery, and also provides safe power supply for other modules.

10. The personalized smart rope skipping and real-time sports health data management and analysis system according to claim 1, characterized in that: The auxiliary module includes a vibration motor, a speaker and a small screen with buttons connected to the microcontroller; The vibration motor provides physical feedback to the user to help him adjust the skipping frequency; The speaker is built into the handle of the skipping rope to provide the user with voice prompts and skipping rope retrieval functions; The small screen with buttons is integrated on the handle of the skipping rope, providing a user interactive interface and displaying the user's exercise status in real time, including heart rate, number of skipping times, and calories consumed; the buttons enable the user to quickly browse data indicators and adjust various settings.

Images