Motion monitoring method and system based on Internet of Things

Abstract

The invention discloses a motion monitoring method and system based on the Internet of Things. The motion monitoring method comprises the steps that detection sound data sent in the process that a user uses a trampoline is monitored; analyzing the use proficiency of the user on the trampoline; detecting a muscle load value when the user uses the trampoline; according to the method, the jumping frequency of the trampoline is adjusted and managed according to sounds of different rhythms, so that the purpose of controlling the exercise amount is achieved; different users are distinguished, the user is helped to quantify the muscle load generated when the trampoline is used, and the physiological influence caused by the muscle load is evaluated; according to the method, the state of the user using the trampoline at present is judged by monitoring the different posture characteristics of the user in combination with the set posture characteristics at different heights, so that the monitoring accuracy in the process of using the trampoline by the user is improved, the possibility that the knee joint of the user is injured due to the too high fatigue value of the user during movement is greatly reduced, and the user experience is improved. The system has the advantages of being high in exercise process monitoring capacity and high in humanization degree.

Description

Technical Field

[0001] This invention relates to the field of motion monitoring technology, specifically to a motion monitoring method and system based on the Internet of Things. Background Technology

[0002] From the perspective of the overall development trend of the amusement industry, the application of large-scale amusement facilities will no longer be limited to the current traditional amusement parks and theme parks. Instead, with the continuous development of urban complex projects, indoor and outdoor trampoline activities combined with urban complexes will become an important market demand point in the future.

[0003] Trampoline exercise is a challenging sport, making safety paramount. Current technologies monitor user activity levels based on perspiration during trampoline use to create personalized workout plans. However, the skill levels of trampoline participants vary significantly, as do their individual sweat glands and physical fitness. Even with assistance and guidance from staff, safety can differ considerably among users. Measuring cardiovascular load alone cannot fully differentiate exercise intensity, especially when users are already overexerting themselves, which can lead to excessive fatigue and a significantly increased risk of knee injuries. Therefore, designing a robust and user-friendly IoT-based exercise monitoring method and system is essential. Summary of the Invention

[0004] The purpose of this invention is to provide a motion monitoring method and system based on the Internet of Things (IoT) to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a motion monitoring method and system based on the Internet of Things, comprising:

[0006] Multiple monitoring devices are set up to monitor the sound data emitted by the user during the trampoline use, and the sound data is stored.

[0007] Multiple monitoring devices are set up to monitor the sound data emitted by the user during the trampoline use, and the monitored sound data is stored;

[0008] After detecting and analyzing the character model extracted from the database during the trampoline use process, the trampoline device is activated, and the user's proficiency data in using the trampoline is analyzed.

[0009] Based on the user's proficiency data in using the trampoline obtained from the analysis, trampoline training information is pre-entered. The trampoline training information is retrieved by inputting the user's proficiency data in using the trampoline into the database. Based on the stored monitoring sound data, the muscle load value information of the user when using the trampoline is detected.

[0010] Based on the user's proficiency data in using the trampoline and the muscle load information when the user uses the trampoline, the user's current exercise volume is calculated, and the user is prompted to stop exercising after the exercise volume reaches the user's exercise volume limit.

[0011] According to the above technical solution, the step of setting up multiple monitoring devices to monitor the sound data emitted by the user during the trampoline use includes:

[0012] The multiple monitoring devices include: a sensing device, a data processing device, a loudspeaker, and a power supply device;

[0013] The sensing device includes an accelerometer, a gyroscope sensor, and a spectrum analyzer;

[0014] The amplification device includes a built-in speaker, an external speaker box, and a mobile communication terminal. The built-in speaker and the external speaker box are used to amplify the sound emitted by the trampoline, and the mobile communication terminal is used to store the amplified sound data in real time.

[0015] The spectrum analyzer is controlled to detect the frequency of trampoline jumps. The data processing device identifies the sound signal corresponding to the frequency of trampoline jumps, transmits the corresponding sound signal to the amplification device, and plays the corresponding detection sound data using the energy stored in the power device.

[0016] According to the above technical solution, the analysis of the user's proficiency in using the trampoline includes:

[0017] Extract the character model of the virtual character using the trampoline from the database. When the virtual character's feet reach different heights of the trampoline at different distances preset by the system, extract n joint points in the legs and waist of the character model. The posture of the character model during the virtual character's use of the trampoline is a preset standard posture.

[0018] When the trampoline device is detected to be activated, the camera captures footage of the user using the trampoline. The camera then identifies and extracts the user's leg and waist feature data from the footage. The user's leg and waist feature data includes the joints of the user's legs and waist at the corresponding positions on the virtual character model.

[0019] The user's leg and waist feature data are fitted to a virtual user model during trampoline use to locate the position of the user's leg and waist features within the virtual user model. The offset distances between the virtual character and the corresponding joint points of the user are sequentially obtained as L1, L2...L... n Then the offset coefficient between the user and the virtual character support model Where H is the height of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint point is obtained;

[0020] Input the different height values ​​of the virtual character's feet reaching the trampoline preset by the system, and sequentially detect the offset coefficients A1, A2...A at the corresponding heights of the user and the virtual character support model at the different heights preset by the system. k Then, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline that the detection is performed at, as preset by the system.

[0021] According to the above technical solution, obtaining the system's preset distance values ​​from different heights of the trampoline includes:

[0022] The system locates the corresponding positions of the virtual character's legs and waist features. The system's preset distance to the trampoline includes a first preset distance to the trampoline height value, a second preset distance to the trampoline height value, and a third preset distance to the trampoline height value.

[0023] The method for locating the first preset distance to the trampoline height value includes: detecting the user's foot stepping down posture features, and locating the current height value of the virtual character's feet as the first preset distance to the trampoline height value;

[0024] The method for locating the second preset distance to the trampoline height value includes: detecting the user's toes being outstretched in a posture, and locating the current height of the virtual character's feet as the second preset distance to the trampoline height value;

[0025] The third preset distance to trampoline height value positioning method includes: detecting the user's knee bending, knee extension until standing posture characteristics, and positioning the current height value of the virtual character's feet as the third preset distance to trampoline height value.

[0026] According to the above technical solution, the detection of muscle load values ​​when a user uses a trampoline includes:

[0027] When the system detects that a user is about to enter the trampoline, a prompt to "pre-wear the wristband" will pop up for the user. Before the user wears the wristband, trampoline training information will be pre-entered based on the user's proficiency data in using the trampoline. This includes the user's trampoline training movements, weights, number of repetitions per set, and the corresponding minimum number of exercise sets. The minimum number of exercise sets is less than or equal to the preset number of exercise sets, which is a variable value.

[0028] When the pressure sensor located inside the wristband detects that the detection value has reached a preset value, the accelerometer and the gyroscope sensor are activated. The accelerometer and the gyroscope sensor detect the user's use of the trampoline and obtain length-tension curve data and tension-velocity curve data. Based on the obtained length-tension curve data and tension-velocity curve data, specific muscle load report data is generated.

[0029] Extract the real-time stored spread spectrum audio data and retrieve the audio data influence coefficient F from the database;

[0030] Extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

[0031] According to the above technical solution, the step of prompting the user to end the exercise after detecting that the user's exercise intensity has reached a preset number of exercise sets includes:

[0032] Get user's exercise data Where μ1 and μ2 are the influence coefficients of user proficiency in trampoline use and user fatigue value when using trampoline, respectively, on user exercise volume obtained from the database; η1 is the unit conversion parameter corresponding to user proficiency in trampoline use and η2 is the unit conversion parameter corresponding to user fatigue value when using trampoline.

[0033] When the number of user exercise sets is detected to have reached the minimum number of exercise sets, it is checked whether the user's exercise volume has exceeded the user's exercise limit Z0 extracted from the database. If it has, the preset number of exercise sets is output as the minimum number of exercise sets. If it has not, the preset number of exercise sets is sequentially increased within the time interval t based on the difference between the user's exercise limit Z0 and the user's exercise volume, until the user's exercise volume is detected to have reached the user's exercise limit value, at which point the preset number of exercise sets is output.

[0034] According to the above technical solution, an Internet of Things-based motion monitoring system includes a device monitoring module, a proficiency analysis module, a motion detection module, and an output module;

[0035] The system is equipped with multiple monitoring devices to monitor and store the sound data emitted by the user during the trampoline use process.

[0036] The proficiency analysis module is used to control the trampoline device to start and analyze the user's proficiency data on using the trampoline after detecting the character model extracted from the database during the process of using the trampoline and completing the analysis steps.

[0037] The motion detection module is used to pre-record trampoline training information based on the analyzed user's proficiency data in using the trampoline, and to detect the muscle load value information of the user when using the trampoline based on the stored monitoring sound data.

[0038] The output module is used to calculate the user's current exercise volume based on the user's proficiency data in using the trampoline and the muscle load value information when the user uses the trampoline, and prompt the user to stop exercising after detecting that the user's exercise volume has reached the user's exercise volume limit.

[0039] According to the above technical solution, the proficiency analysis module includes a feature fitting module and a shift coefficient detection module;

[0040] The feature fitting module is used to extract the virtual character model during trampoline use from the database. When the virtual character's feet reach different heights on the trampoline at preset distances, n joint points on the legs and waist of the character model are extracted. The posture of the character model during trampoline use is a preset standard posture. When the trampoline device is detected to be activated, the camera captures the user's trampoline use footage. The user's leg and waist feature data are identified and extracted from the footage. The user's leg and waist feature data includes the joint points on the user's legs and waist at the corresponding positions on the virtual character model. The user's leg and waist feature data are fitted to the virtual user's trampoline use model to locate the position of the user's leg and waist features on the virtual user's trampoline use model.

[0041] The offset coefficient detection module is used to sequentially obtain the offset distances between the virtual character and the corresponding key points of the user, namely L1, L2...L... n Then the offset coefficient between the user and the virtual character support model Where H is the height value of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint points is obtained; the virtual character's feet reach different height values ​​of the trampoline preset by the system, and the offset coefficients A1, A2...A1 of the user and the virtual character support model are detected sequentially at the corresponding heights of the trampoline preset by the system. kThen, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline that the detection is performed at, as preset by the system.

[0042] According to the above technical solution, the motion detection module includes a wristband detection module and a fatigue value detection module;

[0043] The wristband detection module is used to prompt the user to "wear the wristband in advance" when it detects that the user is about to enter the trampoline. Before the user wears the wristband, the trampoline training information is pre-entered based on the user's proficiency data in using the trampoline. This information includes the user's trampoline training movements, weights, number of repetitions per set, and the corresponding minimum number of exercise sets. The minimum number of exercise sets is less than or equal to the preset number of exercise sets, which is a variable value.

[0044] The fatigue value detection module is used to extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

[0045] According to the above technical solution, the fatigue value detection module includes a muscle load report generation submodule and a sound data influence coefficient detection submodule;

[0046] The muscle load report generation submodule is used to activate the accelerometer and the gyroscope sensor when the pressure sensor set in the wristband detects that the detection value has reached a preset value. The accelerometer and the gyroscope sensor detect the muscle load when the user uses the trampoline and generate muscle load report data.

[0047] The sound data influence coefficient detection submodule is used to extract the real-time stored spread spectrum sound data and retrieve the sound data influence coefficient F from the database.

[0048] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention monitors the sound data emitted by users during trampoline use and adjusts the trampoline jumping frequency according to different rhythms of sound to control exercise intensity. Simultaneously, by analyzing users' proficiency with the trampoline and detecting muscle load values ​​during trampoline use, it differentiates between different users, helps users quantify the muscle load generated during trampoline use, and assesses its physiological impact. Furthermore, by combining pre-defined postural characteristics at different heights and monitoring users under different postural characteristics, it judges the user's current trampoline usage status, improving the accuracy of monitoring during trampoline use and significantly reducing the possibility of excessive user fatigue leading to knee joint injury. Attached Figure Description

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0050] Figure 1 This is a flowchart of a motion monitoring method based on the Internet of Things, which is an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please see Figure 1 The above is a flowchart of a motion monitoring method based on the Internet of Things according to an embodiment of the present invention. Figure 1 It can be seen that the aforementioned motion monitoring method based on the Internet of Things includes:

[0053] Step S1: Set up multiple monitoring devices to monitor the sound data emitted by the user during the trampoline use, and store the monitored sound data.

[0054] Step S2: After detecting and analyzing the character model extracted from the database during the trampoline use process, the trampoline device is started and the user's proficiency data in using the trampoline is analyzed.

[0055] Step S3: Based on the user's proficiency data in using the trampoline obtained from the analysis, trampoline training information is pre-entered. The trampoline training information is obtained by retrieving the user's proficiency data in using the trampoline from the database. Based on the stored monitoring sound data, the muscle load value information of the user when using the trampoline is detected.

[0056] Step S4: Based on the user's proficiency data in using the trampoline and the muscle load information when the user uses the trampoline, calculate the user's current exercise volume, and prompt the user to stop exercising after detecting that the user's exercise volume has reached the user's exercise volume limit.

[0057] In embodiments of the present invention, by monitoring the sound data emitted by users during trampoline use, the jumping frequency of the trampoline is adjusted according to different rhythms of sound to control the amount of exercise. Simultaneously, by analyzing the user's proficiency in using the trampoline and detecting the muscle load value during trampoline use, different users are distinguished, helping users quantify the muscle load generated during trampoline use and assess its physiological impact. Combined with pre-defined postural characteristics at different heights, the current state of the user using the trampoline is judged by monitoring the user's postural characteristics under different postural conditions, improving the accuracy of monitoring during trampoline use and significantly reducing the possibility of excessive user fatigue leading to knee joint injury.

[0058] In some preferred embodiments, the provision of multiple monitoring devices to monitor sound data emitted by the user during trampoline use includes:

[0059] Step S11: The plurality of monitoring devices include: a sensing device, a data processing device, a loudspeaker, and a power supply device.

[0060] Step S12: The sensing device includes an accelerometer, a gyroscope sensor, and a spectrum analyzer.

[0061] Step S13: The amplification device includes a built-in speaker, an external speaker box, and a mobile communication terminal. The built-in speaker and the external speaker box are used to amplify the sound emitted by the trampoline, and the mobile communication terminal is used to store the amplified sound data in real time.

[0062] Step S14: Control the spectrum analyzer to detect the frequency of trampoline jumps, identify the sound signal corresponding to the frequency of trampoline jumps through the data processing device, transmit the corresponding sound signal to the amplification device, and play the corresponding detection sound data using the energy stored in the power device.

[0063] In some preferred embodiments, analyzing the user's proficiency in using the trampoline includes:

[0064] Step S21: Extract the character model of the virtual character using the trampoline from the database. When the virtual character's feet reach different heights of the trampoline at the distance preset by the system, extract n joint points in the legs and waist of the character model. The posture of the character model during the virtual character's use of the trampoline is a preset standard posture.

[0065] Step S22: When the trampoline device is detected to be activated, the camera captures the user's use of the trampoline. The user's leg and waist feature data are identified and extracted from the video information. The user's leg and waist feature data includes the joints of the user's legs and waist at the corresponding positions on the virtual character model.

[0066] Step S23: Fit the user's leg and waist feature data to the virtual user's trampoline model during the trampoline use process, locate the position of the user's leg and waist features in the virtual user's trampoline model during the trampoline use process, and sequentially obtain the offset distances L1, L2...L between the virtual character and the user's corresponding joint points. n Then the offset coefficient between the user and the virtual character support model Where H is the height of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint point is obtained.

[0067] Step S24: Input the different height values ​​of the virtual character's feet reaching the trampoline preset by the system, and sequentially detect the offset coefficients A1, A2...A at the corresponding heights of the user and the virtual character support model at the different heights of the trampoline preset by the system. k Then, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline preset by the system. Since the user's use of the trampoline is a cyclical process, different time points will reach the preset different heights from the trampoline multiple times. Therefore, the value of k is not the number of different heights from the trampoline preset by the system.

[0068] In some preferred embodiments, obtaining the system-preset distance values ​​from different heights of the trampoline includes:

[0069] Step S241: Locate the corresponding positions of the virtual character's legs and waist features. The system's preset distance trampoline height values ​​include a first preset distance trampoline height value, a second preset distance trampoline height value, and a third preset distance trampoline height value.

[0070] Step S242: The method for locating the first preset distance to trampoline height value includes: detecting the user's foot stepping down posture feature, and locating the current height value of the virtual character's foot as the first preset distance to trampoline height value;

[0071] Step S243: The method for locating the second preset distance to trampoline height value includes: detecting the posture feature of the user's toes being straight, and locating the current height value of the virtual character's feet as the second preset distance to trampoline height value.

[0072] Step S244: The method for locating the third preset distance to the trampoline height value includes: detecting the user's knee bending and knee extension until standing posture characteristics, and locating the current height value of the virtual character's feet as the third preset distance to the trampoline height value.

[0073] A person can fall from a certain height and bounce higher and higher, while an object falling will eventually come to a stable stop on the trampoline due to the energy consumed by air resistance and friction. Therefore, what enables a person to overcome gravity and air resistance is not only the initial elastic potential energy, but also the chemical energy consumed by the human body. When athletes land on the trampoline, their knees are slightly bent. As the trampoline deforms to a certain limit, their knees gradually straighten, creating a feeling of pushing off forcefully. When they leave the trampoline, their entire body is straight. When a person falls from a certain height, under the influence of gravity, gravitational potential energy is converted into kinetic energy. Upon contact with the trampoline, both kinetic and gravitational potential energy are converted into the elastic potential energy of the trampoline. Due to the velocity upon contact with the trampoline, the trampoline deforms. The spring force does work, consuming gravitational potential energy and kinetic energy, until the spring deforms to a certain limit and the velocity becomes zero. Furthermore, with the athlete's own exertion, the chemical energy consumed is converted into elastic potential energy in the thigh muscles. Both types of elastic potential energy are converted into kinetic energy as the body moves upward, straightening the body, reducing air resistance, and reaching the maximum height. During this process, the user exhibits different postural characteristics due to air resistance. Therefore, by combining the set postural characteristics at different heights and monitoring the user's different postural characteristics, the current state of the user using the trampoline can be judged.

[0074] In some preferred embodiments, detecting the muscle load value of the user using the trampoline includes:

[0075] Step S31: When the system detects that the user is about to enter the trampoline, a prompt to "pre-wear the wristband" is displayed to the user. Before the user wears the wristband, trampoline training information is pre-recorded based on the user's proficiency data in using the trampoline. This information includes the user's trampoline training movements, weights, number of repetitions per set, and the corresponding minimum number of exercise sets. The minimum number of exercise sets is less than or equal to the preset number of exercise sets, which is a variable value.

[0076] Step S32: When the pressure sensor located within the wristband detects that the measured value has reached a preset value, the accelerometer and gyroscope sensor are activated. The accelerometer and gyroscope sensor detect muscle load while the user is using the trampoline and generate muscle load report data.

[0077] The accelerometer and gyroscope sensors acquire information about the user's muscles being stretched to a certain extent. Based on the specific muscle contraction, and combined with the acquired length-tension curve data and tension-velocity curve data, specific muscle load report data is generated.

[0078] Muscle load report data includes the effect of preload or initial muscle length on muscle contraction, i.e., length-tension curve data, and the effect of afterload on muscle contraction, i.e., tension-velocity curve data. Preload is the load encountered before muscle contraction, and afterload is the load encountered after muscle contraction.

[0079] Isometric contraction is a contraction in which muscle tension increases while length remains constant; isotonic contraction is a contraction in which muscle length decreases while tension remains constant.

[0080] When the load is less than the muscle tone, isotonic contraction occurs; when the load is equal to or greater than the muscle tone, isometric contraction occurs.

[0081] Step S33: Extract the real-time stored spread spectrum audio data and retrieve the audio data influence coefficient F from the database.

[0082] Step S34: Extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

[0083] Fatigue can impair the kinesthetic and proprioceptive properties of joints. It increases the muscle spindle discharge threshold, interrupts afferent feedback, thereby altering joint awareness and affecting static postural control, with a smaller impact on dynamic postural control. In essence, fatigue can be described as the nervous system's inability to adequately recruit motor units, which are the basic functional units of the neuromuscular system associated with force generation. Therefore, afferent feedback affects efferent pathways and muscles; muscle fatigue can delay reaction time. Ankle sprains increase with increasing reaction time in the gastrocnemius and tibialis anterior muscles. Proprioceptive ability, motor control precision, and motor coordination are all affected by muscle fatigue. Therefore, the dynamics and kinematics of the lower limbs and the lumbar region (legs and lower back) can monitor whether a user is affected by fatigue.

[0084] In some preferred embodiments, prompting the user to end the exercise after detecting that the user's exercise intensity has reached a preset number of exercise sets includes:

[0085] Step S41: Obtain user's activity level Where μ1 and μ2 are the influence coefficients of user proficiency in trampoline use and user fatigue value on user exercise volume obtained from the database, respectively, and η1 is the unit conversion parameter corresponding to user proficiency in trampoline use and η2 is the unit conversion parameter corresponding to user fatigue value when using trampoline.

[0086] Step S42: When it is detected that the number of user exercise sets has reached the minimum number of exercise sets, it is checked whether the user's exercise volume has exceeded the user-limited exercise volume Z0 extracted from the database. If it has, the preset number of exercise sets is output as the minimum number of exercise sets; if it has not, the preset number of exercise sets is sequentially increased within the time interval t based on the difference between the user-limited exercise volume Z0 and the user's exercise volume, until it is detected that the user's exercise volume has reached the user's exercise volume limit value, at which point the preset number of exercise sets is output.

[0087] Based on the same concept as the above embodiments, embodiments of the present invention also provide an Internet of Things-based motion monitoring system, including a device monitoring module, a proficiency analysis module, a motion detection module, and an output module;

[0088] The system is equipped with multiple monitoring devices to monitor and store the sound data emitted by the user during the trampoline use process.

[0089] The proficiency analysis module is used to control the trampoline device to start and analyze the user's proficiency data on using the trampoline after detecting the character model extracted from the database during the process of using the trampoline and completing the analysis steps.

[0090] The motion detection module is used to pre-record trampoline training information based on the analyzed user's proficiency data in using the trampoline, and to detect the muscle load value information of the user when using the trampoline based on the stored monitoring sound data.

[0091] The output module is used to calculate the user's current exercise volume based on the user's proficiency data in using the trampoline and the muscle load value information when the user uses the trampoline, and prompt the user to stop exercising after detecting that the user's exercise volume has reached the user's exercise volume limit.

[0092] In this embodiment, the proficiency analysis module includes a feature fitting module and a shift coefficient detection module;

[0093] The feature fitting module is used to extract the virtual character model during trampoline use from the database. When the virtual character's feet reach different heights on the trampoline at preset distances, n joint points on the legs and waist of the character model are extracted. The posture of the character model during trampoline use is a preset standard posture. When the trampoline device is detected to be activated, the camera captures the user's trampoline use footage. The user's leg and waist feature data are identified and extracted from the footage. The user's leg and waist feature data includes the joint points on the user's legs and waist at the corresponding positions on the virtual character model. The user's leg and waist feature data are fitted to the virtual user's trampoline use model to locate the position of the user's leg and waist features on the virtual user's trampoline use model.

[0094] The offset coefficient detection module is used to sequentially obtain the offset distances between the virtual character and the corresponding key points of the user, namely L1, L2...L... n Then the offset coefficient between the user and the virtual character support model Where H is the height value of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint points is obtained; the virtual character's feet reach different height values ​​of the trampoline preset by the system, and the offset coefficients A1, A2...A1 of the user and the virtual character support model are detected sequentially at the corresponding heights of the trampoline preset by the system. k Then, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline that the detection is performed at, as preset by the system.

[0095] In this embodiment, the motion detection module includes a wristband detection module and a fatigue value detection module;

[0096] The wristband detection module is used to prompt the user to "put on the wristband in advance" when it detects that the user is about to enter the trampoline. Before the user puts on the wristband, the trampoline training information is pre-entered based on the user's proficiency data in using the trampoline, including the user's trampoline training movements, weights, number of repetitions per set, and the corresponding minimum number of exercise sets.

[0097] The fatigue value detection module is used to extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

[0098] In this embodiment, the fatigue value detection module includes a muscle load report generation submodule and a sound data influence coefficient detection submodule;

[0099] The muscle load report generation submodule is used to activate the accelerometer and gyroscope sensor when the pressure sensor located in the wristband detects that the detection value has reached a preset value. The accelerometer and gyroscope sensor detect the muscle load while the user is using the trampoline and generate muscle load report data.

[0100] The sound data influence coefficient detection submodule is used to extract the real-time stored spread spectrum sound data and retrieve the sound data influence coefficient F from the database.

[0101] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0102] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A motion monitoring method based on the Internet of Things, characterized in that: include: Multiple monitoring devices are set up to monitor the sound data emitted by the user during the trampoline use, and the monitored sound data is stored; After detecting and analyzing the character model extracted from the database during the trampoline use process, the trampoline device is activated, and the user's proficiency data in using the trampoline is analyzed. Based on the user's proficiency data in using the trampoline obtained from the analysis, trampoline training information is pre-entered. The trampoline training information is retrieved by inputting the user's proficiency data in using the trampoline into the database. Based on the stored monitoring sound data, the muscle load value information of the user when using the trampoline is detected. Based on the user's proficiency data in using the trampoline and the muscle load information when the user uses the trampoline, the user's current exercise volume is calculated, and the user is prompted to stop exercising after the exercise volume reaches the user's exercise volume limit.

2. The motion monitoring method based on the Internet of Things according to claim 1, characterized in that: The setup of multiple monitoring devices to monitor the sound data emitted by the user during trampoline use includes: The multiple monitoring devices include: a sensing device, a data processing device, a loudspeaker, and a power supply device; The sensing device includes an accelerometer, a gyroscope sensor, and a spectrum analyzer; The amplification device includes a built-in speaker, an external speaker box, and a mobile communication terminal. The built-in speaker and the external speaker box are used to amplify the sound emitted by the trampoline, and the mobile communication terminal is used to store the amplified sound data in real time. The spectrum analyzer is controlled to detect the frequency of trampoline jumps. The data processing device identifies the sound signal corresponding to the frequency of trampoline jumps, transmits the corresponding sound signal to the amplification device, and plays the corresponding detection sound data using the energy stored in the power device.

3. The motion monitoring method based on the Internet of Things according to claim 2, characterized in that: The analysis of users' proficiency in using trampolines includes: Extract the character model of the virtual character using the trampoline from the database. When the virtual character's feet reach different heights of the trampoline at different distances preset by the system, extract n joint points in the legs and waist of the character model. The posture of the character model during the virtual character's use of the trampoline is a preset standard posture. When the trampoline device is detected to be activated, the camera captures footage of the user using the trampoline. The camera then identifies and extracts the user's leg and waist feature data from the footage. The user's leg and waist feature data includes the joints of the user's legs and waist at the corresponding positions on the virtual character model. The user's leg and waist feature data are fitted to a virtual user model during trampoline use to locate the position of the user's leg and waist features within the virtual user model. The offset distances between the virtual character and the corresponding joint points of the user are sequentially obtained as L1, L2...L... n Then the offset coefficient between the user and the virtual character support model Where H is the height of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint point is obtained; Input the different height values ​​of the virtual character's feet reaching the trampoline preset by the system, and sequentially detect the offset coefficients A1, A2...A at the corresponding heights of the user and the virtual character support model at the different heights preset by the system. k Then, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline that the detection is performed at, as preset by the system.

4. The motion monitoring method based on the Internet of Things according to claim 3, characterized in that: The acquisition system presets different height values ​​of the trampoline, including: The system locates the corresponding positions of the virtual character's legs and waist features. The system's preset distance to the trampoline includes a first preset distance to the trampoline height value, a second preset distance to the trampoline height value, and a third preset distance to the trampoline height value. The method for locating the first preset distance to the trampoline height value includes: detecting the user's foot stepping down posture features, and locating the current height value of the virtual character's feet as the first preset distance to the trampoline height value; The method for locating the second preset distance to the trampoline height value includes: detecting the user's toes being outstretched in a posture, and locating the current height of the virtual character's feet as the second preset distance to the trampoline height value; The third preset distance to trampoline height value positioning method includes: detecting the user's knee bending, knee extension until standing posture characteristics, and positioning the current height value of the virtual character's feet as the third preset distance to trampoline height value.

5. A motion monitoring method based on the Internet of Things according to claim 4, characterized in that: The detection of muscle load values ​​when a user uses the trampoline includes: When the system detects that a user is about to enter the trampoline, a prompt to "pre-wear the wristband" will pop up for the user. Before the user wears the wristband, trampoline training information will be pre-entered based on the user's proficiency data in using the trampoline. This information includes the user's trampoline training movements, weights, number of repetitions per set, and the corresponding minimum number of exercise sets. The minimum number of exercise sets is less than or equal to the preset number of exercise sets, which is a variable value. When the pressure sensor located inside the wristband detects that the detection value has reached a preset value, the accelerometer and the gyroscope sensor are activated. The accelerometer and the gyroscope sensor detect the user's use of the trampoline and obtain length-tension curve data and tension-velocity curve data. Based on the obtained length-tension curve data and tension-velocity curve data, specific muscle load report data is generated. Extract the real-time stored spread spectrum audio data and retrieve the audio data influence coefficient F from the database; Extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

6. The motion monitoring method based on the Internet of Things according to claim 5, characterized in that: The step of prompting the user to end the exercise after detecting that the user's exercise intensity has reached the preset number of exercise sets includes: Get user's exercise data Where μ1 and μ2 are the influence coefficients of user proficiency in trampoline use and user fatigue value when using trampoline, respectively, on user exercise volume obtained from the database; η1 is the unit conversion parameter corresponding to user proficiency in trampoline use and η2 is the unit conversion parameter corresponding to user fatigue value when using trampoline. When the number of user exercise sets is detected to have reached the minimum number of exercise sets, it is checked whether the user's exercise volume has exceeded the user's exercise limit Z0 extracted from the database. If it has, the preset number of exercise sets is output as the minimum number of exercise sets. If it has not, the preset number of exercise sets is sequentially increased within the time interval t based on the difference between the user's exercise limit Z0 and the user's exercise volume, until the user's exercise volume is detected to have reached the user's exercise limit value, at which point the preset number of exercise sets is output.

7. A motion monitoring system based on the Internet of Things, characterized in that: The motion monitoring system includes a device monitoring module, a proficiency analysis module, a motion detection module, and an output module. The system is equipped with multiple monitoring devices to monitor and store the sound data emitted by the user during the trampoline use process. The proficiency analysis module is used to control the trampoline device to start and analyze the user's proficiency data on using the trampoline after detecting the character model extracted from the database during the process of using the trampoline and completing the analysis steps. The motion detection module is used to pre-record trampoline training information based on the analyzed user's proficiency data in using the trampoline, and to detect the muscle load value information of the user when using the trampoline based on the stored monitoring sound data. The output module is used to calculate the user's current exercise volume based on the user's proficiency data in using the trampoline and the muscle load value information when the user uses the trampoline, and prompt the user to stop exercising after detecting that the user's exercise volume has reached the user's exercise volume limit.

8. A motion monitoring system based on the Internet of Things according to claim 7, characterized in that: The proficiency analysis module includes a feature fitting module and a shift coefficient detection module; The feature fitting module is used to extract the virtual character model during trampoline use from the database. When the virtual character's feet reach different heights on the trampoline at preset distances, n joint points on the legs and waist of the character model are extracted. The posture of the character model during trampoline use is a preset standard posture. When the trampoline device is detected to be activated, the camera captures the user's trampoline use footage. The user's leg and waist feature data are identified and extracted from the footage. The user's leg and waist feature data includes the joint points on the user's legs and waist at the corresponding positions on the virtual character model. The user's leg and waist feature data are fitted to the virtual user's trampoline use model to locate the position of the user's leg and waist features on the virtual user's trampoline use model. The offset coefficient detection module is used to sequentially obtain the offset distances between the virtual character and the corresponding key points of the user, namely L1, L2...L... n Then the offset coefficient between the user and the virtual character support model Where H is the height value of the trampoline, δ is the model offset error coefficient, and n is the number of times the offset distance between the virtual character and the user's corresponding joint points is obtained; the virtual character's feet reach different height values ​​of the trampoline preset by the system, and the offset coefficients A1, A2...A1 of the user and the virtual character support model are detected sequentially at the corresponding heights of the trampoline preset by the system. k Then, user proficiency data on trampoline use k represents the number of time points at different heights from the trampoline that the detection is performed at, as preset by the system.

9. A motion monitoring system based on the Internet of Things according to claim 8, characterized in that: The motion detection module includes a wristband detection module and a fatigue value detection module; The wristband detection module is used to prompt the user to "wear the wristband in advance" when it detects that the user is about to enter the trampoline. Before the user wears the wristband, the trampoline training information is pre-recorded based on the user's proficiency data in using the trampoline, including the user's trampoline training movements, weight, number of repetitions per set, and the corresponding minimum number of exercise sets. The fatigue value detection module is used to extract the muscle load report data generated when the user uses the trampoline, obtain the user's muscle load parameter value G from the load report data, and detect the user's fatigue value W=FG when using the trampoline.

10. A motion monitoring system based on the Internet of Things according to claim 9, characterized in that: The fatigue value detection module includes a muscle load report generation submodule and a sound data influence coefficient detection submodule; The muscle load report generation submodule is used to activate the accelerometer and the gyroscope sensor when the pressure sensor set in the wristband detects that the detection value has reached a preset value. The accelerometer and the gyroscope sensor detect the muscle load when the user uses the trampoline and generate muscle load report data. The sound data influence coefficient detection submodule is used to extract the real-time stored spread spectrum sound data and retrieve the sound data influence coefficient F from the database.

Images