Human body abdominal respiration monitoring system and waistband thereof

Abstract

The invention discloses a human body abdominal respiration monitoring system and a waistband thereof, and relates to the technical field of health monitoring, the human body abdominal respiration monitoring system comprises a sensor module, a data visualization module, a data processing and analysis module, a cloud platform, a safety module and a respiration training module; the pressure sensor, the inertial sensor and the surface electromyogram signal sensor are integrated in the waistband, and kinematics, dynamics and biological indexes of abdominal respiration can be comprehensively monitored. Modularized design is adopted in the waistband, the sensor modules can be installed or detached according to needs, more flexible monitoring is achieved, the sensors cover the front side, the rear side and the two sides of the waist and abdomen, and the action modes of abdominal respiration, including the expansion and contraction degree of the abdomen, the respiration speed, the movement track and the activity state of muscles of the waist and abdomen, can be monitored more comprehensively.

Description

Technical Field

[0001] The invention relates to the technical field of health monitoring, in particular to a human abdominal breathing monitoring system and a waist belt thereof. Background Art

[0002] Respiratory monitoring refers to the real-time or regular monitoring and analysis of the human respiratory process through various technical means to evaluate the respiratory function status and health status. Human abdominal respiration monitoring refers to the use of various sensors and equipment to collect and analyze the physiological signals generated by the human body during abdominal breathing in real time, so as to evaluate the respiratory status and movement pattern.

[0003] Most of the existing abdominal breathing monitoring devices only monitor the number of breaths and respiratory rate, and cannot provide comprehensive data on kinematic indicators, dynamic indicators, biological indicators of breathing, and exercise-related information. Most of them only monitor the abdominal breathing in the front of the waist and abdomen. The monitoring range is not comprehensive enough and cannot reflect the movement status and muscle activity of different parts of the waist and abdomen, making it difficult to perform refined monitoring and analysis.

[0004] Therefore, we propose a human abdominal breathing monitoring system and a waist belt thereof to solve the above-mentioned problems. Summary of the invention

[0005] The purpose of the present invention is to provide a human abdominal respiration monitoring system and a waist belt thereof, so as to solve the problems of the prior art mentioned in the above background technology, such as single function and limited monitoring range.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A human abdominal breathing monitoring system, comprising: a sensor module, a data visualization module, a data processing and analysis module, a cloud platform, a security module, and a breathing training module;

[0008] Among them, the sensor module collects pressure, inertia, and electromyography data in real time, and performs preliminary processing on the sensor data. The processed data is transmitted wirelessly to the cloud platform;

[0009] The data processing and analysis module receives the data transmitted by the sensor module, processes the data again, analyzes the processed data, identifies the breathing pattern, breathing cycle, respiratory muscle activity pattern, calculates the breathing frequency, depth, efficiency index, evaluates the respiratory health status and establishes a respiratory health model, and finally, predicts the user's respiratory health status and provides a training plan;

[0010] The data visualization module displays the data in the data processing and analysis module and the user's breathing change trend in the form of charts and curves;

[0011] The cloud platform is used to store basic user information, breathing data, and training data. The user data is stored in the cloud, and data is backed up and connected to other health monitoring devices for data sharing and function expansion. Users can view their breathing data and training progress by remotely accessing the cloud platform.

[0012] The security module encrypts user data and verifies user identity;

[0013] The breathing training module provides a breathing training program based on the user's breathing data and learning curve.

[0014] The sensor module includes a pressure sensor, an inertial sensor, and a surface electromyography sensor;

[0015] Among them, the pressure sensor is used to monitor the frequency and depth of abdominal breathing, as well as the degree of breathing completeness; the inertial sensor is used to collect movement posture, speed and trajectory and establish a three-dimensional model of the human body; the surface electromyography signal sensor is used to measure and analyze the electromyography signals emitted during muscle contraction, reflecting the activity status and functional status of the waist and abdominal muscles.

[0016] The data processing and analysis module includes a data preprocessing unit, a signal recognition unit, a feature extraction unit, a respiratory assessment unit, a respiratory health model unit, and a training program generation unit;

[0017] Among them, in the data preprocessing unit, noise and interference are removed through digital signal processing to extract useful signal features;

[0018] The signal recognition unit identifies the characteristics of the breathing signal through pattern recognition and compares it with the known breathing pattern to determine the breathing state;

[0019] The feature extraction unit uses feature extraction to extract feature parameters from the data;

[0020] The respiratory assessment unit calculates the respiratory index and assesses the respiratory health status based on the extracted characteristic parameters using the respiratory physiology model;

[0021] The respiratory health model unit uses machine learning algorithms to build a respiratory health model based on historical data and user characteristics to predict the user's future respiratory health status;

[0022] The training program generating unit generates a breathing training program according to the user's breathing data and training goals.

[0023] The data visualization module includes a chart generation unit, an animation display unit, a three-dimensional model display unit, an electromyography display unit, a real-time feedback unit, an operation interface unit, a setting unit, a data viewing unit, a training guidance unit, a data sharing unit, a networking unit, and a voice interaction unit;

[0024] The cloud platform includes a data storage unit, a data analysis unit, a model training unit, a data sharing unit, a remote access unit, a user management unit, and a service monitoring unit;

[0025] The data storage unit stores and manages the user's breathing data by using a NoSQL database;

[0026] The data analysis unit models and analyzes the user's breathing data through data mining and generates analysis results;

[0027] The model training unit trains the model and optimizes the model performance according to the user's breathing data and learning curve through a support vector machine.

[0028] The data sharing unit uses data encryption and authorization mechanisms to ensure data security and privacy;

[0029] The remote access unit uses RESTful API to provide a remote access interface for the cloud platform;

[0030] The user management unit ensures the security of user accounts through user registration, login, password management, and permission control;

[0031] The service monitoring unit monitors the service status of the cloud platform in real time through the performance monitoring and alarm system.

[0032] The breathing training module includes a training program generation unit, a training guidance unit, a breathing game unit, a training effect evaluation unit, a breathing pattern recognition unit, a respiratory muscle activity monitoring unit, and a respiratory physiology knowledge base;

[0033] The training program generation unit generates a breathing training program according to the user's breathing data and learning curve through reinforcement learning; the training guidance unit provides voice prompts, visual and tactile prompts according to the breathing training program and user feedback to guide the user to perform breathing training; the breathing game unit enables the user to perform breathing training in the game by designing breathing simulation breathing; the training effect evaluation unit evaluates the user's breathing training effect according to the user's breathing data and training progress; the breathing pattern recognition unit identifies the user's breathing pattern through cluster analysis, and adjusts the training program according to the breathing pattern; the respiratory muscle activity monitoring unit uses a surface electromyography signal sensor to monitor the user's respiratory muscle activity, and adjusts the training program according to the muscle activity; the respiratory physiology knowledge base stores basic knowledge of respiratory physiology, breathing training methods, and respiratory health information for users to view.

[0034] A human abdominal respiration monitoring belt comprises a belt, one side of the belt is provided with an L-shaped groove body, the L-shaped groove body is provided with a rubber slide groove, the inside of the rubber slide groove is slidably connected with a plurality of fixed blocks, a sensor module is arranged between the fixed blocks, and the belt is provided with a rectangular through hole for storing a wiring harness.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention integrates the sensor module into the waist belt to realize multi-dimensional data collection, and can comprehensively monitor the kinematics, dynamics and biological indicators of abdominal breathing. The waist belt adopts a modular design, and the sensor module can be installed or removed as needed to achieve more flexible monitoring, that is, the module can be selectively installed according to the location to be monitored, or the module position can be adjusted according to the user's body shape to improve wearing comfort and data collection accuracy. The sensor covers the front, back and both sides of the waist and abdomen, and can more comprehensively monitor the movement pattern of abdominal breathing, including the expansion and contraction degree of the abdomen, breathing speed, movement trajectory and the activity state of the waist and abdomen muscles.

[0037] The present invention applies inertial sensor analysis to abdominal breathing monitoring, collects motion data through a three-axis accelerometer and a gyroscope, builds a three-dimensional model of the human body, analyzes changes in body posture during breathing, and provides more intuitive kinematic indicators. It also uses high-precision electromyographic signal acquisition equipment to measure and analyze the electromyographic signals emitted during muscle contraction, reflecting the activity and functional status of the waist and abdominal muscles, and providing more accurate biological indicators.

[0038] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a module block diagram of the human abdominal respiration monitoring system of the present invention;

[0040] Figure 2 The figure is a schematic diagram of the three-dimensional structure of a waist belt of the present invention.

[0041] In the figure: 10, waist belt; 11, L-shaped groove; 12, Velcro; 13, rectangular through hole; 1011, rubber slide groove; 1012, fixing block. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Embodiment 1

[0044] See also Figure 1 , a human abdominal breathing monitoring system, comprising: a sensor module, a data visualization module, a data processing and analysis module, a cloud platform, a security module, and a breathing training module;

[0045] Among them, the sensor module collects pressure, inertia, and electromyography data in real time, and performs preliminary processing on the sensor data. The processed data is transmitted wirelessly to the cloud platform;

[0046] The data processing and analysis module receives the data transmitted by the sensor module, processes the data again, analyzes the processed data, identifies the breathing pattern, breathing cycle, respiratory muscle activity pattern, calculates the breathing frequency, depth, efficiency index, evaluates the respiratory health status and establishes a respiratory health model, and finally, predicts the user's respiratory health status and provides a training plan;

[0047] The data visualization module displays the data in the data processing and analysis module and the user's breathing change trend in the form of charts and curves;

[0048] The cloud platform is used to store basic user information, breathing data, and training data. The user data is stored in the cloud, and data is backed up and connected to other health monitoring devices for data sharing and function expansion. Users can view their breathing data and training progress by remotely accessing the cloud platform.

[0049] The security module encrypts user data and verifies user identity;

[0050] The breathing training module provides a breathing training program based on the user's breathing data and learning curve.

[0051] The sensor module includes a pressure sensor, an inertial sensor, and a surface electromyography sensor;

[0052] Among them, the pressure sensor is used to monitor the frequency and depth of abdominal breathing, as well as the degree of breathing completeness; the inertial sensor is used to collect movement posture, speed and trajectory and establish a three-dimensional model of the human body; the surface electromyography signal sensor is used to measure and analyze the electromyography signals emitted during muscle contraction, reflecting the activity status and functional status of the waist and abdominal muscles.

[0053] Specifically, when the human body performs abdominal breathing, the contraction and relaxation of the abdominal muscles causes changes in intra-abdominal pressure. The pressure sensor detects the pressure changes and converts them into electrical signals, thereby calculating the breathing frequency, depth, and completeness.

[0054] Inertial sensors contain three-axis accelerometers and gyroscopes to measure the acceleration and angular velocity of the human body. By analyzing these data, they can reconstruct a three-dimensional model of human motion and obtain changes in body posture during breathing.

[0055] When muscles contract, they generate weak electrical signals. Surface electromyography sensors are attached to the surface of the skin through electrodes, which collect these electrical signals and convert them into electrical signals to analyze the activity status of the muscles.

[0056] The data processing and analysis module includes a data preprocessing unit, a signal recognition unit, a feature extraction unit, a respiratory assessment unit, a respiratory health model unit, and a training program generation unit;

[0057] Among them, in the data preprocessing unit, noise and interference are removed through digital signal processing to extract useful signal features;

[0058] The signal recognition unit identifies the characteristics of the breathing signal through pattern recognition and compares it with the known breathing pattern to determine the breathing state;

[0059] The feature extraction unit uses feature extraction to extract feature parameters from the data;

[0060] The respiratory assessment unit calculates the respiratory index and assesses the respiratory health status based on the extracted characteristic parameters using the respiratory physiology model;

[0061] The respiratory health model unit uses machine learning algorithms to build a respiratory health model based on historical data and user characteristics to predict the user's future respiratory health status;

[0062] The training program generating unit generates a breathing training program according to the user's breathing data and training goals.

[0063] More specifically, the start and end of the breathing cycle are detected from the pressure sensor data, the time interval T between consecutive breathing cycles is calculated, and the breathing frequency RR is calculated using the breathing frequency calculation formula.

[0064] The formula used to calculate the respiratory rate is:

[0065] Where T is the time between two consecutive breathing cycles.

[0066] Extract the maximum and minimum pressure values ​​within a breathing cycle from the pressure sensor data and calculate the pressure change amplitude ΔP = Pmax -P min , calculate the average pressure P mean , use the breathing depth calculation formula to calculate the breathing depth RD.

[0067] Respiratory depth calculation formula:

[0068] Where ΔP is the pressure change during the breathing cycle, P mean is the average pressure.

[0069] Fourier transform is used to extract the frequency characteristics of the respiratory cycle. First, the pressure signal within the respiratory cycle is Fourier transformed to identify the main frequency components, which represent the rhythm and pattern of breathing, and the amplitude and phase of the main frequency components are calculated.

[0070] Calculate the RMS value within a respiratory cycle from the EMG sensor data to determine the baseline level of the EMG signal base , use the respiratory muscle activity intensity formula to calculate the respiratory muscle activity intensity MAI.

[0071] Respiratory muscle activity intensity calculation formula:

[0072] Among them, RMS is the average root mean square value of the electromyographic signal, EMG base is the baseline level of the EMG signal.

[0073] The data visualization module includes a chart generation unit, an animation display unit, a three-dimensional model display unit, an electromyography display unit, a real-time feedback unit, an operation interface unit, a setting unit, a data viewing unit, a training guidance unit, a data sharing unit, a networking unit, and a voice interaction unit;

[0074] Among them, the chart generation unit sets the style and layout of the chart according to the data type and user needs, and presents the data in a graphical manner;

[0075] The animation display unit reconstructs the three-dimensional model of the human body based on the data collected by the sensors, and simulates the body movements and muscle activities during the breathing process to generate an animation demonstration.

[0076] The 3D model display unit reconstructs the 3D model of the human body based on the data collected by the sensor, and uses different colors and textures to represent the contraction or relaxation of muscles;

[0077] The electromyography display unit presents the surface electromyography signal in a graphical way, and uses different colors and lines to represent different muscle activity states;

[0078] The real-time feedback unit evaluates the user's breathing status and training effect based on the data collected by the sensor and the breathing training program.

[0079] The operation interface unit facilitates the user to operate and set by setting the operation interface.

[0080] The setting unit stores the setting information of the user by using a database, and adjusts the breathing training program and the data analysis result according to the setting of the user;

[0081] The data viewing unit obtains data from the data processing and analysis module and displays it to the user in the form of charts and animations;

[0082] The training guidance unit provides voice and visual prompts according to the breathing training program and user feedback to guide the user to perform breathing training, and makes real-time adjustments based on the user's training results;

[0083] The data sharing unit ensures data security and privacy through data encryption and authorization mechanisms;

[0084] The networking unit connects the respiratory monitoring system to the Internet through wireless communication technology to achieve data synchronization and remote access functions;

[0085] The voice interaction unit recognizes the user's voice commands and converts them into corresponding operation commands.

[0086] The cloud platform includes a data storage unit, a data analysis unit, a model training unit, a data sharing unit, a remote access unit, a user management unit, and a service monitoring unit;

[0087] The data storage unit stores and manages the user's breathing data by using a NoSQL database;

[0088] The data analysis unit models and analyzes the user's breathing data through data mining and generates analysis results;

[0089] The model training unit trains the model and optimizes the model performance according to the user's breathing data and learning curve through a support vector machine.

[0090] The data sharing unit uses data encryption and authorization mechanisms to ensure data security and privacy;

[0091] The remote access unit uses RESTful API to provide a remote access interface for the cloud platform;

[0092] The user management unit ensures the security of user accounts through user registration, login, password management, and permission control;

[0093] The service monitoring unit monitors the service status of the cloud platform in real time through the performance monitoring and alarm system.

[0094] The security module includes a data encryption unit, an authentication unit, an authorization unit, a security audit unit, a security policy unit, and a security protection unit;

[0095] The data encryption unit encrypts data through asymmetric encryption; the authentication unit verifies the user's identity through user name and password authentication, fingerprint authentication, and face and voice recognition authentication; the authorization unit controls the user's access rights to the cloud platform through attribute-based access; the security audit unit records the user's access to the cloud platform through log records; the security policy unit ensures the security of the cloud platform by formulating and implementing security policies; and the security protection unit prevents the cloud platform from network attacks through an intrusion detection system.

[0096] Specifically, data is encrypted on the user's device through an encryption algorithm and a key length, and the encrypted data is sent to the cloud, which stores the encrypted data and performs decryption processing when needed.

[0097] Use SHA-256 in combination with salt. When a user registers, a random salt is generated and combined with the user's password. The mixture of salt and password is hashed using the SHA-256 algorithm, and the hash value and salt are stored in the database. When the user logs in, the input password is hashed using the same hash algorithm and salt, and the stored hash value is compared with the hash value of the input password to verify the user's identity.

[0098] The breathing training module includes a training program generation unit, a training guidance unit, a breathing game unit, a training effect evaluation unit, a breathing pattern recognition unit, a respiratory muscle activity monitoring unit, and a respiratory physiology knowledge base;

[0099] The training program generation unit generates a breathing training program according to the user's breathing data and learning curve through reinforcement learning; the training guidance unit provides voice prompts, visual and tactile prompts according to the breathing training program and user feedback to guide the user to perform breathing training; the breathing game unit enables the user to perform breathing training in the game by designing breathing simulation breathing; the training effect evaluation unit evaluates the user's breathing training effect according to the user's breathing data and training progress; the breathing pattern recognition unit identifies the user's breathing pattern through cluster analysis, and adjusts the training program according to the breathing pattern; the respiratory muscle activity monitoring unit uses a surface electromyography signal sensor to monitor the user's respiratory muscle activity, and adjusts the training program according to the muscle activity; the respiratory physiology knowledge base stores basic knowledge of respiratory physiology, breathing training methods, and respiratory health information for users to view.

[0100] Specifically, a recommended breathing rate range based on the user's age, gender, and health status is determined, a target breathing rate is set, and the user is guided to maintain the target breathing rate through music, a metronome, or visual cues.

[0101] The target breathing depth is set according to the user's breathing capacity, and the user's actual breathing depth is displayed through a bar graph, guiding the user to reach the target breathing depth by gradually increasing the expansion of the abdomen.

[0102] Collect the user's breathing data, apply clustering algorithms to classify the data, identify different breathing patterns, and adjust the training plan based on the identified breathing patterns.

[0103] Collect the user's electromyographic signal data when breathing, calculate the amplitude of the computer electrical signal, evaluate the activity intensity of the respiratory muscles, and adjust the training intensity and type according to the muscle activity intensity.

[0104] Measure the user's breathing efficiency index before and after training, compare the changes in the index before and after training, evaluate the training effect, and adjust the training plan according to the evaluation results.

[0105] Embodiment 2

[0106] See also Figure 2 A human abdominal breathing monitoring belt includes a belt 10, one side of the belt 10 is provided with an L-shaped groove 11, the L-shaped groove 11 is provided with a rubber slide 1011, the inside of the rubber slide 1011 is slidably connected with a plurality of fixing blocks 1012, a sensor module is arranged between the fixing blocks 1012, and the belt 10 is provided with a rectangular through hole 13 for storing a wiring harness.

[0107] The sensor module is equipped with a pressure sensor, an inertial sensor, and a surface electromyography signal sensor.

[0108] Specifically, according to the position to be detected, the sensor module is placed between two fixed blocks 1012, and the outside of the fixed block 1012 and the inside of the rubber slide groove 1011 are set as rough friction surfaces to fix the sensor module. The wiring harness of the sensor module passes through the rectangular through hole 13 and can be wrapped around the belt 10 for arrangement and storage.

[0109] Each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0110] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A human abdominal breathing monitoring system, characterized in that: include: Sensor module, data visualization module, data processing and analysis module; Among them, the sensor module collects pressure, inertia, and electromyography data in real time, and performs preliminary processing on the sensor data. The processed data is transmitted wirelessly to the cloud platform; The data processing and analysis module receives the data transmitted by the sensor module, processes the data again, analyzes the processed data, identifies the breathing pattern, breathing cycle, respiratory muscle activity pattern, calculates the breathing frequency, depth, efficiency index, evaluates the respiratory health status and establishes a respiratory health model, and finally, predicts the user's respiratory health status and provides a training plan; The data visualization module displays the data in the data processing and analysis module and the user's breathing change trend in the form of charts and curves.

2. A human abdominal respiration monitoring system according to claim 1, characterized in that: The sensor module includes a pressure sensor, an inertial sensor, and a surface electromyography sensor; Among them, the pressure sensor is used to monitor the frequency and depth of abdominal breathing, as well as the degree of breathing completeness; the inertial sensor is used to collect movement posture, speed and trajectory and establish a three-dimensional model of the human body; the surface electromyography signal sensor is used to measure and analyze the electromyography signals emitted during muscle contraction.

3. A human abdominal respiration monitoring system according to claim 1, characterized in that: The data processing and analysis module includes a data preprocessing unit, a signal recognition unit, a feature extraction unit, a respiratory assessment unit, a respiratory health model unit, and a training program generation unit; Among them, the data preprocessing unit removes noise and interference through digital signal processing and extracts useful signal features; The signal recognition unit identifies the characteristics of the breathing signal through pattern recognition and compares it with the known breathing pattern to determine the breathing state; The feature extraction unit uses feature extraction to extract feature parameters from the data; The respiratory assessment unit calculates the respiratory index and assesses the respiratory health status based on the extracted characteristic parameters using the respiratory physiology model; The respiratory health model unit uses machine learning algorithms to build a respiratory health model based on historical data and user characteristics to predict the user's future respiratory health status; The training program generating unit generates a breathing training program according to the user's breathing data and training goals.

4. A human abdominal respiration monitoring system according to claim 1, characterized in that: The data visualization module includes a chart generation unit, an animation display unit, a three-dimensional model display unit, an electromyography display unit, a real-time feedback unit, an operation interface unit, a setting unit, a data viewing unit, a training guidance unit, a data sharing unit, a networking unit, and a voice interaction unit.

5. A human abdominal respiration monitoring system according to claim 1, characterized in that: It also includes a cloud platform, a security module, and a breathing training module; The cloud platform is used to store basic user information, breathing data, and training data. It stores user data in the cloud, backs up data, and connects with other health monitoring devices for data sharing and function expansion. Users can view their breathing data and training progress by remotely accessing the cloud platform. The security module encrypts user data and verifies user identity; The breathing training module provides a breathing training program based on the user's breathing data and learning curve.

6. A human abdominal respiration monitoring system according to claim 1, characterized in that: The cloud platform includes a data storage unit, a data analysis unit, a model training unit, a data sharing unit, a remote access unit, a user management unit, and a service monitoring unit; The data storage unit stores and manages the user's breathing data by using a NoSQL database; The data analysis unit models and analyzes the user's breathing data through data mining and generates analysis results; The model training unit trains the model and optimizes the model performance according to the user's breathing data and learning curve through a support vector machine; The data sharing unit uses data encryption and authorization mechanisms to ensure data security; The remote access unit uses RESTful API to provide a remote access interface for the cloud platform; The user management unit ensures the security of user accounts through user registration, login, password management, and permission control; The service monitoring unit monitors the service status of the cloud platform in real time through the performance monitoring and alarm system.

7. A human abdominal respiration monitoring system according to claim 1, characterized in that: The breathing training module includes a training program generation unit, a training guidance unit, a breathing game unit, a training effect evaluation unit, a breathing pattern recognition unit, a respiratory muscle activity monitoring unit, and a respiratory physiology knowledge base; The training program generation unit generates a breathing training program according to the user's breathing data and learning curve through reinforcement learning; The training guidance unit provides voice prompts, visual and tactile prompts according to the breathing training program and user feedback to guide the user to perform breathing training; The breathing game unit simulates breathing by designing breathing so that users can practice breathing in the game; The training effect evaluation unit evaluates the user's breathing training effect according to the user's breathing data and training progress; The breathing pattern recognition unit recognizes the user's breathing pattern through cluster analysis and adjusts the training program according to the breathing pattern; the respiratory muscle activity monitoring unit uses a surface electromyography signal sensor to monitor the user's respiratory muscle activity and adjusts the training program according to the muscle activity; The respiratory physiology knowledge base stores basic knowledge of respiratory physiology, methods of respiratory training, and respiratory health information for users to view.

8. A human abdominal breathing monitoring belt, characterized in that: The invention comprises a waist belt (10), wherein an L-shaped groove (11) is provided on one side of the waist belt (10), a rubber slide groove (1011) is provided on the L-shaped groove (11), a plurality of fixing blocks (1012) are slidably connected inside the rubber slide groove (1011), a sensor module is arranged between the fixing blocks (1012), and a rectangular through hole (13) for storing a wiring harness is provided on the waist belt (10).

Images