Efficient intelligent polymorphic balance training system

Abstract

The invention discloses an efficient intelligent multi-state balance training system, and relates to the technical field of balance training. The system comprises a calculation unit, a wireless module, a database, a myoelectricity unit and a display module, a port of the calculation unit is in data connection with a port of the database, an output end of the myoelectricity unit is connected with an input end of the wireless module, and an output end of the wireless module is connected with an input end of the calculation unit. The output end of the calculation unit is connected with the input end of the display module, each module in the myoelectricity unit is composed of an acceleration sensor and a myoelectricity sensor, and the acceleration sensor obtains acceleration information A of the acceleration sensor and transmits the acceleration information A to the calculation unit through the wireless module; the control ability of the trainee for each limb is analyzed through the myoelectricity unit, so that the evaluation result is more real and effective, a proper training scheme is executed according to the evaluation result, and the training parameter k is adjusted to make the training scheme more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of balance training, and in particular to a highly efficient intelligent multi-state balance training system. Background Art

[0002] Polymorphic balance includes static balance and dynamic balance. Static balance is the most basic balance mode of the human body, that is, the ability of the human body to maintain a stable posture on a static support surface. Dynamic balance is a more advanced balance mode of the human body, that is, the ability of the human body to maintain a stable posture on a moving support surface or while moving. At present, polymorphic balance training mainly helps trainees restore their body balance function through system evaluation and equipment training.

[0003] Patent 1 [Publication No.: CN102028597A] discloses an intelligent polymorphic balance test and training system, which evaluates the trainee's center of gravity control ability by analyzing the force on the soles of the trainee's feet. However, this technical solution is too one-sided to judge the trainee's balance ability only by the change in gravity pressure. Due to differences between individuals, the muscle contraction ability of each person's left and right upper limbs, trunk and left and right lower limbs cannot be consistent. The solution of Patent 1 assumes that the trainee's limbs are in an ideal state when analyzing the force on the soles of the feet. Therefore, the analysis and evaluation results obtained by using the solution of Patent 1 are not comprehensive and objective. It is necessary to pre-analyze the trainee's control ability over each of his or her limbs in order to finally evaluate the trainee's polymorphic balance ability. Only after comprehensive analysis and evaluation can the corresponding training plan be executed to better help the trainee recover. Therefore, analyzing the balance ability of each limb of the trainee and then executing a suitable training plan is a technical problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a highly efficient intelligent multi-state balance training system, which solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above purpose, the present invention is implemented through the following technical solutions: an efficient intelligent multi-state balance training system, comprising a computing unit, a wireless module, a database, an electromyographic unit and a display module, wherein a port of the computing unit establishes a data connection with a port of the database, an output end of the electromyographic unit is connected to an input end of the wireless module, an output end of the wireless module is connected to an input end of the computing unit, and an output end of the computing unit is connected to an input end of the display module;

[0006] Each module in the electromyographic unit is composed of an acceleration sensor and an electromyographic sensor. The acceleration sensor obtains its own acceleration information A and transmits it to the calculation unit through a wireless module. Each module in the electromyographic unit is fixed to the corresponding limb of the trainee through a strap. The electrode sheet of the electromyographic sensor of each module covers the skin on the surface of the muscle of the trainee's limb that exerts force. The electromyographic sensor obtains the contraction force F of the corresponding muscle through the electrode sheet. The electromyographic sensor transmits the contraction force of the muscle to the calculation unit through the wireless module. The acceleration information A includes Azxb, Azdb, Azxt, Azdt, Ayxb, Aydb, Ayxt, Aydt, Aqx and Ahy, and the contraction force F includes Fzxb, Fzdb, Fzxt, Fzdt, Fyxb, Fydb, Fyxt, Fydt, Fqx and Fhy;

[0007] The electromyographic unit includes a left upper arm module, a right upper arm module, a left forearm module, a right forearm module, a left calf module, a right calf module, a left thigh module, a right thigh module, a front chest module and a back waist module. The left upper arm module obtains the acceleration information Azdb and the contraction force Fzdb of the trainee's left upper arm, the left forearm module obtains the acceleration information Azxb and the contraction force Fzxb of the trainee's left forearm, the right upper arm module obtains the acceleration information Aydb and the contraction force Fydb of the trainee's right upper arm, and the right forearm module obtains the acceleration information Ayxb and the contraction force Fydb of the trainee's right forearm. Fyxb, the left thigh module obtains the acceleration information Azdt and contraction force Fzdt of the trainee's left thigh, the left calf module obtains the acceleration information Azxt and contraction force Fzxt of the trainee's left calf, the right thigh module obtains the acceleration information Aydt and contraction force Fydt of the trainee's right thigh, the right calf module obtains the acceleration information Ayxt and contraction force Fyxt of the trainee's right calf, the front chest module obtains the acceleration information Aqx and contraction force Fqx of the trainee's front chest, and the back waist module obtains the acceleration information Ahy and contraction force Fhy of the trainee's back waist;

[0008] The computing unit establishes and initializes a spatial coordinate system, executes an evaluation program to obtain a first static index, a first dynamic index, and the number of instability events N of the trainee, executes a training program to obtain a training parameter k, and executes the evaluation program again to obtain a second static index and a second dynamic index of the trainee, the first static index, the first dynamic index, the second static index, and the second dynamic index are all obtained by executing the evaluation program, and the first and second here are used to distinguish different results obtained by executing the evaluation program before and after, the static index JT obtained by executing the evaluation program for the first time is the first static index, the dynamic index DT obtained by executing the evaluation program for the first time is the first dynamic index, and the static index JT obtained by executing the evaluation program for the second time is The second static index. The dynamic index DT obtained by executing the evaluation program for the second time is the second dynamic index. The calculation unit executes the optimization program to correct the training program. The database presets standard initialization actions, static actions and dynamic actions. The left upper arm, right upper arm, left forearm, right forearm, left calf, right calf, left thigh, right thigh, front chest and back waist on each action are all provided with nodes. It should be noted that each limb of the trainee is not affected by only one muscle. Therefore, the number of electromyographic sensors on each module is not limited to one. When a single module contains multiple electromyographic sensors, the contraction force F output by the module is the average contraction force of all electromyographic sensors corresponding to the module, which is convenient for better analysis of the force exerted by a single limb of the trainee.

[0009] Furthermore, the evaluation procedure includes a static evaluation process and a dynamic evaluation process. The computing unit first executes the static evaluation process and then executes the dynamic evaluation process. Both the static evaluation process and the dynamic evaluation process include evaluation contents of three stages: ordinary, medium and difficult. The computing unit executes them in the order of ordinary, medium and difficult. The computing unit presets an evaluation threshold of 0.8. During or after the execution of a stage, if the trainee's first static index is less than the evaluation threshold, the process stops immediately and outputs the first static index. If the trainee's first static index is greater than or equal to the evaluation threshold, the computing unit executes the next stage until all stages are completed and the process stops. If the trainee's first static index in the ordinary stage of the static evaluation process is less than the evaluation threshold, it indicates that the trainee's limb static balance ability is poor and the subsequent dynamic evaluation process cannot be carried out. In order to ensure the safety of the trainee, the computing unit stops executing the dynamic evaluation process.

[0010] When the static evaluation process is executed, the computing unit retrieves the static action from the database, and transmits the static action to the display module for the trainee to watch. The trainee adjusts the limb action according to the static action. The computing unit obtains Azxb and Azdb of the electromyographic unit, and inputs Azxb and Azdb into the spatial coordinate system to obtain the action of the trainee's left arm. The computing unit calculates the total error ΔAzb between the left forearm node and the left upper arm node and the left arm in the static action. The computing unit obtains Ayxb and Aydb of the electromyographic unit, and inputs Ayxb and Aydb into the spatial coordinate system to obtain the action of the trainee's right arm. The computing unit calculates the total error ΔAyb between the right forearm node and the right upper arm node and the right arm in the static action. The computing unit obtains Azxt and Azdt of the electromyographic unit, and inputs Azxt and Azdt into the spatial coordinate system to obtain the action of the trainee's left leg. Calculate the total error ΔAzt between the left calf node and the left thigh node and the left arm in static motion, the calculation unit obtains Ayxt and Aydt of the electromyographic unit, the calculation unit inputs Ayxt and Aydt into the spatial coordinate system to obtain the motion of the trainee's right leg, the calculation unit calculates the total error ΔAyt between the right calf node and the right thigh node and the right arm in static motion, the calculation unit obtains Aqx and Ahy of the electromyographic unit, the calculation unit inputs Aqx and Ahy into the spatial coordinate system to obtain the pitch motion of the trainee's torso, the calculation unit calculates the total error ΔAqxhy between the front chest node and the back waist node and the right arm in static motion, the common, medium and difficult static motions are: 1. Spread both hands, 2. Stand on one foot with the left or right foot, 3. Spread both hands and stand on one foot, the common, medium and difficult dynamic motions are: 1. Swing both hands, 2. Walk with both feet and swing both hands, 3. Stand on one foot and swing both hands;

[0011] The calculation unit is based on the following formula:

[0012] Calculate the trainee's static index JT, w1, w2, w3, w4 and w5 are weight coefficients and satisfy the condition w1+w2+w3+w4+w5=1, and the specific values ​​of w1, w2, w3, w4 and w5 are determined according to the trainee's arm span to leg length ratio;

[0013] When the dynamic evaluation process is executed, the computing unit retrieves the dynamic action from the database, outputs the dynamic action to the display module for the trainee to watch, and the trainee adjusts the limb action according to the dynamic action. The computing unit obtains Azxb, Azdb, Azxt, Azdt, Ayxb, Aydb, Ayxt, Aydt, Aqx and Ahy from the electromyographic unit, and the computing unit presets the equal condition and the trigger threshold of 5%;

[0014] The equality conditions include condition 1 Azxb+Azdb+Azxt+Azdt=-(Ayxb+Aydb+Ayxt+Aydt) and condition 2 Aqx=-Ahy. Condition 1 represents that the trainee can maintain left-right balance in dynamic movements, and condition 2 represents that the trainee can maintain front-back pitch balance in dynamic movements. When the difference between the equal signs of condition 1 or condition 2 is greater than the trigger threshold, the computing unit records an instability event, and the computing unit counts the number of instability events N.

[0015] The calculation unit obtains Fzxb, Fzdb, Fzxt, Fzdt, Fyxb, Fydb, Fyxt, Fydt, Fqx and Fhy from the electromyographic unit. The calculation unit records the time T1 of each module from the time point when the instability event occurs to the time point when the contraction force is not zero. The calculation unit calculates the average value of T1 of all modules of the electromyographic unit and marks it as T2. The calculation unit calculates the average value of T1 of all modules of the electromyographic unit according to the formula Calculate the trainee's dynamic index DT, w6 and w7 are weight coefficients and satisfy the condition w6*w7, that is, w6 and w7 are reciprocals of each other, and the specific values ​​of w6 and w7 are determined according to the trainee's weight.

[0016] Further, after the instability event occurs, the calculation unit determines the deviation direction of the trainee's center of gravity according to the difference between the two sides of the equal sign of condition one or condition two. If the left side of the equal sign of condition one is greater than the right side, it means that the trainee's center of gravity is biased to the left; if the right side of the equal sign of condition one is greater than the left side, it means that the trainee's center of gravity is biased to the right; if the left side of the equal sign of condition two is greater than the right side, it means that the trainee's center of gravity is biased forward; if the right side of the equal sign of condition two is greater than the left side, it means that the trainee's center of gravity is biased backward. The calculation unit classifies the number of instability events N into the number of left instability events Nz, the number of right instability events Ny, the number of forward instability events Nq, and the number of backward instability events Nh.

[0017] When the training program is executed, the calculation unit presets the training parameter k as 8, and the calculation unit compares the sizes of Nz, Ny, Nq and Nh. When Nz is the largest, it means that the comprehensive strength of the trainee's left upper arm, left forearm, left thigh and left calf is not good, and the calculation unit will retrieve the plan one from the database and transmit it to the display module for the trainee to view. When Ny is the largest, it means that the comprehensive strength of the trainee's right upper arm, right forearm, right thigh and right calf is not good. The calculation unit will retrieve the plan two from the database and transmit it to the display module for the trainee to view. When Nq is the largest, it means that the trainee's front chest strength is not good. The calculation unit will retrieve the plan three from the database and transmit it to the display module for the trainee to view. When Nh is the largest, it means that the trainee's lower back strength is not good. The calculation unit will retrieve the plan four from the database and transmit it to the display module for the trainee to view. Plan one, plan two, plan three and plan four are all pre-stored in the database;

[0018] Plan 1: The trainee performs k sets of bending training for the left forearm, 0.5k times per set, k sets of lifting training for the left upper arm, 0.5k times per set, k sets of bending training for the left calf, k times per set, and k sets of lifting training for the left thigh, k times per set, with a rest period of 0.25k minutes between each set;

[0019] Plan 2: The trainee performs k sets of bending training on the right forearm, 0.5k times per set, k sets of lifting training on the right upper arm, 0.5k times per set, k sets of bending training on the right calf, k times per set, and k sets of lifting training on the right thigh, k times per set, with 0.25k minutes of rest between each set;

[0020] Plan 3: The trainee does chest expansion exercises, k times per set, with 0.5k minutes of rest between each set;

[0021] Plan 4: The trainee does waist twisting exercise training, k times per set, with a rest period of 0.5k minutes between each set. When the number of training times is a decimal, the calculation unit will calculate the decimal that is less than an integer as 1.

[0022] Further, when the optimization program is executed, the calculation unit compares the first static index, the second static index, the first dynamic index and the second dynamic index. If the second static index is greater than the first static index, it means that the training program has a positive effect, and the calculation unit increases the value of the training parameter k by 0.5. On the contrary, if the second static index is less than or equal to the first static index, it means that the positive effect of the training program is not obvious, and the calculation unit decreases the value of the training parameter k by 0.5. If the second dynamic index is greater than the first dynamic index, it means that the training program has a positive effect, and the calculation unit increases the value of the training parameter k by 1. On the contrary, if the second dynamic index is less than or equal to the first dynamic index, it means that the positive effect of the training program is not obvious, and the calculation unit decreases the value of the training parameter k by 1.

[0023] The minimum value of k is 2 and the maximum is 20. When the training parameter k changes, the computing unit replaces the original training parameter k with the changed training parameter k and saves it to the database. The next time the training program is executed, the computing unit retrieves the changed training parameter k from the database to execute the training program.

[0024] Furthermore, the computing unit establishes a spatial coordinate system, obtains the initialization action from the database, the trainee maintains a standing posture, and executes initialization and sends an initialization instruction to each module in the electromyographic unit through the wireless module. The initialization action is a standing action. After receiving the initialization instruction, each module resets its own acceleration sensor to zero, and the computing unit projects the initialization action into the spatial coordinate system. The computing unit overlaps and binds each module in the electromyographic unit with the corresponding node in the initialization action. The acceleration sensor in the left upper arm module is bound to the left upper arm node in the initialization action, and the acceleration sensor in the right upper arm module is bound to the right upper arm node in the initialization action. The velocity sensor is bound to the left forearm node in the initialization action, the acceleration sensor in the right forearm module is bound to the right forearm node in the initialization action, the acceleration sensor in the left calf module is bound to the left calf node in the initialization action, the acceleration sensor in the right calf module is bound to the right calf node in the initialization action, the acceleration sensor in the left thigh module is bound to the left thigh node in the initialization action, the acceleration sensor in the right thigh module is bound to the right thigh node in the initialization action, the acceleration sensor in the front chest module is bound to the front chest node in the initialization action, and the acceleration sensor in the back waist module is bound to the back waist node in the initialization action, which is used to calibrate motion capture and complete initialization.

[0025] The present invention has the following beneficial effects:

[0026] 1. Through the electromyography unit, the trainee's control ability of each limb is analyzed, and the trainee's static balance ability and dynamic balance ability are evaluated. The difficulty of movement control in the evaluation process is gradual, which can conduct a comprehensive evaluation of the trainee's multi-state balance ability, making the evaluation result more real and effective.

[0027] 2. Execute appropriate training plans based on the evaluation results, determine whether the training program is effective through re-evaluation, and appropriately adjust the training parameter k to change the training volume to make the training plan more reasonable.

[0028] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 This is a block diagram of an efficient intelligent multi-state balance training system of the present invention;

[0031] Figure 2 This is a connection block diagram of the myoelectric unit and the computing unit of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] See also Figure 1-2 The present invention provides a technical solution: an efficient intelligent multi-state balance training system, such as Figure 1 As shown, it includes a computing unit, a wireless module, a database, an electromyographic unit and a display module, the port of the computing unit establishes a data connection with the port of the database, the output end of the electromyographic unit is connected to the input end of the wireless module, the output end of the wireless module is connected to the input end of the computing unit, and the output end of the computing unit is connected to the input end of the display module;

[0034] Each module in the electromyographic unit is composed of a LIS2DW12 model acceleration sensor and a ZJE-20D model electromyographic sensor. The acceleration sensor obtains its own acceleration information A and transmits it to the calculation unit through the wireless module. Each module in the electromyographic unit is fixed to the corresponding limb of the trainee through a strap. The electrode sheet of the electromyographic sensor of each module covers the skin on the surface of the muscle of the trainee's limb. The electromyographic sensor obtains the contraction force F of the corresponding muscle through the electrode sheet, and the electromyographic sensor transmits the contraction force of the muscle to the calculation unit through the wireless module.

[0035] like Figure 2As shown, the electromyographic unit includes a left upper arm module, a right upper arm module, a left forearm module, a right forearm module, a left calf module, a right calf module, a left thigh module, a right thigh module, a front chest module and a back waist module. The left upper arm module obtains the acceleration information Azdb and the contraction force Fzdb of the trainee's left upper arm, the left forearm module obtains the acceleration information Azxb and the contraction force Fzxb of the trainee's left forearm, the right upper arm module obtains the acceleration information Aydb and the contraction force Fydb of the trainee's right upper arm, and the right forearm module obtains the acceleration information Ayxb and the contraction force Fydb of the trainee's right forearm. force Fyxb, the left thigh module obtains the acceleration information Azdt and contraction force Fzdt of the trainee's left thigh, the left calf module obtains the acceleration information Azxt and contraction force Fzxt of the trainee's left calf, the right thigh module obtains the acceleration information Aydt and contraction force Fydt of the trainee's right thigh, the right calf module obtains the acceleration information Ayxt and contraction force Fyxt of the trainee's right calf, the front chest module obtains the acceleration information Aqx and contraction force Fqx of the trainee's front chest, and the back waist module obtains the acceleration information Ahy and contraction force Fhy of the trainee's back waist;

[0036] The computing unit establishes and initializes a spatial coordinate system. The computing unit executes an evaluation program to obtain a first static index, a first dynamic index, and the number of instability events N of the trainee. The computing unit executes a training program to obtain a training parameter k. The computing unit executes the evaluation program again to obtain a second static index and a second dynamic index of the trainee. The first static index, the first dynamic index, the second static index, and the second dynamic index are all obtained by executing the evaluation program. The first and second here are used to distinguish different results obtained by executing the evaluation program before and after. The static index JT obtained by executing the evaluation program for the first time is the first static index, the dynamic index DT obtained by executing the evaluation program for the first time is the first dynamic index, and the static index JT obtained by executing the evaluation program for the second time is the second static index. Index, the dynamic index DT obtained by executing the evaluation program for the second time is the second dynamic index, and the calculation unit executes the optimization program to correct the training parameter k in the training program. The database presets standard initialization actions, static actions and dynamic actions. The left upper arm, right upper arm, left forearm, right forearm, left calf, right calf, left thigh, right thigh, front chest and back waist on each action are all provided with nodes. It should be noted that each limb of the trainee is not affected by only one muscle, therefore, the number of myoelectric sensors on each module is not limited to one. When a single module contains multiple myoelectric sensors, the contraction force F output by the module is the average contraction force of all myoelectric sensors corresponding to the module, which is convenient for better analysis of the force exerted by a single limb of the trainee.

[0037] The evaluation procedure includes a static evaluation process and a dynamic evaluation process. The computing unit first executes the static evaluation process and then executes the dynamic evaluation process. Both the static evaluation process and the dynamic evaluation process include evaluation contents of three stages: ordinary, medium and difficult. The computing unit executes them in the order of ordinary, medium and difficult. The computing unit presets an evaluation threshold of 0.8. During or after the execution of a stage, if the trainee's first static index is less than the evaluation threshold, the process stops immediately and outputs the first static index. If the trainee's first static index is greater than or equal to the evaluation threshold, the computing unit executes the next stage until all stages are completed and the process stops. If the trainee's first static index in the ordinary stage of the static evaluation process is less than the evaluation threshold, it indicates that the trainee's limb static balance ability is poor and the subsequent dynamic evaluation process cannot be carried out. In order to ensure the safety of the trainee, the computing unit stops executing the dynamic evaluation process.

[0038] When the static assessment process is executed, the computing unit retrieves the static action from the database, and transmits the static action to the display module for the trainee to watch. The trainee adjusts the limb action according to the static action. The computing unit obtains Azxb and Azdb of the electromyographic unit, and inputs Azxb and Azdb into the spatial coordinate system to obtain the action of the trainee's left arm. The computing unit calculates the total error ΔAzb between the left forearm node and the left upper arm node and the left arm in the static action. The computing unit obtains Ayxb and Aydb of the electromyographic unit, and inputs Ayxb and Aydb into the spatial coordinate system to obtain the action of the trainee's right arm. The computing unit calculates the total error ΔAyb between the right forearm node and the right upper arm node and the right arm in the static action. The computing unit obtains Azxt and Azdt of the trainee, the calculation unit inputs Azxt and Azdt into the spatial coordinate system to obtain the movement of the trainee's left leg, the calculation unit calculates the total error ΔAzt between the left calf node and the left thigh node and the left arm in the static movement, the calculation unit obtains Ayxt and Aydt of the electromyographic unit, the calculation unit inputs Ayxt and Aydt into the spatial coordinate system to obtain the movement of the trainee's right leg, the calculation unit calculates the total error ΔAyt between the right calf node and the right thigh node and the right arm in the static movement, the calculation unit obtains Aqx and Ahy of the electromyographic unit, the calculation unit inputs Aqx and Ahy into the spatial coordinate system to obtain the pitch movement of the trainee's torso, and the calculation unit calculates the total error ΔAqxhy between the front chest node and the back waist node and the right arm in the static movement;

[0039] The calculation unit is based on the following formula:

[0040] Calculate the trainee's static index JT, w1, w2, w3, w4 and w5 are weight coefficients and satisfy the condition w1+w2+w3+w4+w5=1, and the specific values ​​of w1, w2, w3, w4 and w5 are determined according to the trainee's arm span to leg length ratio;

[0041] When the dynamic evaluation process is executed, the computing unit retrieves the dynamic action from the database, outputs the dynamic action to the display module for the trainee to watch, and the trainee adjusts the limb action according to the dynamic action. The computing unit obtains Azxb, Azdb, Azxt, Azdt, Ayxb, Aydb, Ayxt, Aydt, Aqx and Ahy from the electromyographic unit, and the computing unit presets the equal condition and the trigger threshold of 5%;

[0042] The equality conditions include condition 1 Azxb+Azdb+Azxt+Azdt=-(Ayxb+Aydb+Ayxt+Aydt) and condition 2 Aqx=-Ahy. Condition 1 represents that the trainee can maintain left-right balance in dynamic movements, and condition 2 represents that the trainee can maintain front-back pitch balance in dynamic movements. When the difference between the equal signs of condition 1 or condition 2 is greater than the trigger threshold, the computing unit records an instability event, and the computing unit counts the number of instability events N.

[0043] The calculation unit obtains Fzxb, Fzdb, Fzxt, Fzdt, Fyxb, Fydb, Fyxt, Fydt, Fqx and Fhy from the electromyographic unit. The calculation unit records the time T1 of each module from the time point when the instability event occurs to the time point when the contraction force is not zero. The calculation unit calculates the average value of T1 of all modules of the electromyographic unit and marks it as T2. The calculation unit calculates the average value of T1 of all modules of the electromyographic unit according to the formula Calculate the trainee's dynamic index DT, w6 and w7 are weight coefficients and satisfy the condition w6*w7, that is, w6 and w7 are reciprocals of each other, and the specific values ​​of w6 and w7 are determined according to the trainee's weight.

[0044] Wherein, after the instability event occurs, the calculation unit determines the deviation direction of the trainee's center of gravity according to the difference between the two sides of the equal sign of condition one or condition two. If the left side of the equal sign of condition one is greater than the right side, it means that the trainee's center of gravity is biased to the left; if the right side of the equal sign of condition one is greater than the left side, it means that the trainee's center of gravity is biased to the right; if the left side of the equal sign of condition two is greater than the right side, it means that the trainee's center of gravity is biased forward; if the right side of the equal sign of condition two is greater than the left side, it means that the trainee's center of gravity is biased backward. The calculation unit classifies the number of instability events N into the number of left instability events Nz, the number of right instability events Ny, the number of forward instability events Nq, and the number of backward instability events Nh.

[0045] When the training program is executed, the calculation unit presets the training parameter k as 8, and the calculation unit compares the sizes of Nz, Ny, Nq and Nh. When Nz is the largest, it means that the comprehensive strength of the trainee's left upper arm, left forearm, left thigh and left calf is not good, and the calculation unit will retrieve the plan one from the database and transmit it to the display module for the trainee to view. When Ny is the largest, it means that the comprehensive strength of the trainee's right upper arm, right forearm, right thigh and right calf is not good. The calculation unit will retrieve the plan two from the database and transmit it to the display module for the trainee to view. When Nq is the largest, it means that the trainee's front chest strength is not good. The calculation unit will retrieve the plan three from the database and transmit it to the display module for the trainee to view. When Nh is the largest, it means that the trainee's lower back strength is not good. The calculation unit will retrieve the plan four from the database and transmit it to the display module for the trainee to view. Plan one, plan two, plan three and plan four are all pre-stored in the database;

[0046] Plan 1: The trainee performs k sets of bending training for the left forearm, 0.5k times per set, k sets of lifting training for the left upper arm, 0.5k times per set, k sets of bending training for the left calf, k times per set, and k sets of lifting training for the left thigh, k times per set, with a rest period of 0.25k minutes between each set;

[0047] Plan 2: The trainee performs k sets of bending training on the right forearm, 0.5k times per set, k sets of lifting training on the right upper arm, 0.5k times per set, k sets of bending training on the right calf, k times per set, and k sets of lifting training on the right thigh, k times per set, with 0.25k minutes of rest between each set;

[0048] Plan 3: The trainee does chest expansion exercises, k times per set, with 0.5k minutes of rest between each set;

[0049] Plan 4: The trainee does waist twisting exercise training, k times per set, with a rest period of 0.5k minutes between each set. When the number of training times is a decimal, the calculation unit will calculate the decimal that is less than an integer as 1.

[0050] Wherein, when the optimization program is executed, the calculation unit compares the sizes of the first static index, the second static index, the first dynamic index and the second dynamic index. If the second static index is greater than the first static index, it means that the training program has a positive effect, and the calculation unit increases the value of the training parameter k by 0.5. On the contrary, if the second static index is less than or equal to the first static index, it means that the positive effect of the training program is not obvious, and the calculation unit decreases the value of the training parameter k by 0.5. If the second dynamic index is greater than the first dynamic index, it means that the training program has a positive effect, and the calculation unit increases the value of the training parameter k by 1. On the contrary, if the second dynamic index is less than or equal to the first dynamic index, it means that the positive effect of the training program is not obvious, and the calculation unit decreases the value of the training parameter k by 1.

[0051] The minimum value of k is 2 and the maximum is 20. When the training parameter k changes, the computing unit replaces the original training parameter k with the changed training parameter k and saves it to the database. The next time the training program is executed, the computing unit retrieves the changed training parameter k from the database to execute the training program.

[0052] Among them, the computing unit establishes a spatial coordinate system, obtains the initialization action from the database, the trainee keeps standing still, the computing unit performs initialization and sends initialization instructions to each module in the electromyographic unit through the wireless module, the initialization action is a standing action, each module resets its own acceleration sensor to zero after receiving the initialization instruction, and the computing unit projects the initialization action into the spatial coordinate system. The computing unit overlaps and binds each module in the electromyographic unit with the corresponding node in the initialization action, the acceleration sensor in the left upper arm module is bound to the left upper arm node in the initialization action, the acceleration sensor in the right upper arm module is bound to the right upper arm node in the initialization action, and the acceleration sensor in the left forearm module is bound to the left upper arm node in the initialization action. The accelerometer in the right forearm module is bound to the left forearm node in the initialization action, the accelerometer in the left calf module is bound to the left calf node in the initialization action, the accelerometer in the right calf module is bound to the right calf node in the initialization action, the accelerometer in the left thigh module is bound to the left thigh node in the initialization action, the accelerometer in the right thigh module is bound to the right thigh node in the initialization action, the accelerometer in the front chest module is bound to the front chest node in the initialization action, and the accelerometer in the back waist module is bound to the back waist node in the initialization action, which is used to calibrate motion capture and complete initialization.

[0053] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An efficient intelligent multi-state balance training system, comprising a computing unit, a wireless module, a database, an electromyographic unit and a display module, wherein a port of the computing unit establishes a data connection with a port of the database, an output end of the electromyographic unit is connected to an input end of the wireless module, an output end of the wireless module is connected to an input end of the computing unit, and an output end of the computing unit is connected to an input end of the display module; characterized in that: Each module in the electromyographic unit is composed of an acceleration sensor and an electromyographic sensor. The acceleration sensor obtains its own acceleration information A and transmits it to the calculation unit through the wireless module. The electromyographic sensor obtains the contraction force F of the corresponding muscle through the electrode sheet, and the electromyographic sensor transmits the contraction force of the muscle to the calculation unit through the wireless module. The electromyographic unit includes a left upper arm module, a right upper arm module, a left forearm module, a right forearm module, a left calf module, a right calf module, a left thigh module, a right thigh module, a front chest module and a back waist module. The left upper arm module obtains acceleration information Azdb and contraction force Fzdb of the trainer's left upper arm, the left forearm module obtains acceleration information Azxb and contraction force Fzxb of the left forearm, the right upper arm module obtains acceleration information Aydb and contraction force Fydb of the right upper arm, and the right forearm module obtains acceleration information Ayxb and contraction force Fydb of the right forearm. b and contraction force Fyxb, the left thigh module obtains the acceleration information Azdt and contraction force Fzdt of the left thigh, the left calf module obtains the acceleration information Azxt and contraction force Fzxt of the left calf, the right thigh module obtains the acceleration information Aydt and contraction force Fydt of the right thigh, the right calf module obtains the acceleration information Ayxt and contraction force Fyxt of the right calf, the front chest module obtains the acceleration information Aqx and contraction force Fqx of the front chest, and the back waist module obtains the acceleration information Ahy and contraction force Fhy of the back waist; The computing unit establishes and initializes a spatial coordinate system, executes an evaluation program to obtain a first static index, a first dynamic index, and the number of instability events N of the trainee, executes a training program to obtain a training parameter k, executes the evaluation program again to obtain a second static index and a second dynamic index of the trainee, and executes an optimization program to modify the training program.

2. The efficient intelligent multi-state balance training system according to claim 1, characterized in that: The evaluation procedure includes a static evaluation process and a dynamic evaluation process. The computing unit first executes the static evaluation process and then executes the dynamic evaluation process. Both the static evaluation process and the dynamic evaluation process include evaluation contents of three stages: ordinary, medium and difficult. The evaluation contents are executed in the order of ordinary, medium and difficult. An evaluation threshold is preset. During or after the execution of a stage, if the first static index of the trainee is less than the evaluation threshold, the process stops immediately and outputs the first static index. If the first static index of the trainee is greater than or equal to the evaluation threshold, the next stage is executed until all stages are completed and the process stops. If the first static index of the trainee in the ordinary stage of the static evaluation process is less than the evaluation threshold, the dynamic evaluation process stops. When the static assessment process is executed, the computing unit retrieves the static action from the database, and transmits the static action to the display module for the trainee to watch. The trainee adjusts the limb action according to the static action, obtains Azxb and Azdb of the electromyographic unit, inputs Azxb and Azdb into the spatial coordinate system to obtain the action of the trainee's left arm, calculates the total error ΔAzb between the left forearm node and the left upper arm node and the left arm in the static action, obtains Ayxb and Aydb of the electromyographic unit, inputs Ayxb and Aydb into the spatial coordinate system to obtain the action of the trainee's right arm, calculates the total error ΔAyb between the right forearm node and the right upper arm node and the right arm in the static action, and obtains Azxt and Azdt of the electromyographic unit, input Azxt and Azdt into the spatial coordinate system to obtain the movement of the trainee's left leg, calculate the total error ΔAzt between the left calf node and the left thigh node and the left arm in static movement, obtain Ayxt and Aydt of the myoelectric unit, input Ayxt and Aydt into the spatial coordinate system to obtain the movement of the trainee's right leg, calculate the total error ΔAyt between the right calf node and the right thigh node and the right arm in static movement, obtain Aqx and Ahy of the myoelectric unit, input Aqx and Ahy into the spatial coordinate system to obtain the movement of the trainee's torso, calculate the total error ΔAqxhy between the front chest node and the back waist node and the right arm in static movement; According to the following formula: Calculate the trainee's static index JT, w1, w2, w3, w4 and w5 are weight coefficients and satisfy the condition w1+w2+w3+w4+w5=1; When the dynamic evaluation process is executed, the computing unit retrieves the dynamic actions from the database and outputs the dynamic actions to the display module for the trainee to watch. The trainee adjusts the limb movements according to the dynamic actions, obtains Azxb, Azdb, Azxt, Azdt, Ayxb, Aydb, Ayxt, Aydt, Aqx and Ahy from the electromyographic unit, and presets the equal conditions and trigger thresholds; The equality conditions include condition 1 Azxb+Azdb+Azxt+Azdt=-(Ayxb+Aydb+Ayxt+Aydt) and condition 2 Aqx=-Ahy. Condition 1 means that the trainee can maintain left-right balance in dynamic movements, and condition 2 means that the trainee can maintain front-back balance in dynamic movements. When the difference between the equal signs of condition 1 or condition 2 is greater than the trigger threshold, an instability event is recorded, and the number of instability events N is counted. Get Fzxb, Fzdb, Fzxt, Fzdt, Fyxb, Fydb, Fyxt, Fydt, Fqx and Fhy from the EMG unit, record the time T1 of each module from the time point when the instability event occurs to the time point when the contraction force is not zero, calculate the average value of T1 of all modules of the EMG unit and mark it as T2, according to the formula Calculate the trainer's dynamic index DT, w6 and w7 are weight coefficients and satisfy the condition w6*w7.

3. The efficient intelligent multi-state balance training system according to claim 1, characterized in that: After the instability event occurs, the calculation unit determines the direction of the trainee's center of gravity deviation and classifies the number of instability events N into the number of left instability events Nz, the number of right instability events Ny, the number of forward instability events Nq and the number of backward instability events Nh; When the training program is executed, the training parameter k is preset, and the sizes of Nz, Ny, Nq and Nh are compared. When Nz is the largest, the scheme 1 is retrieved from the database and transmitted to the display module for the trainer to view. When Ny is the largest, the scheme 2 is retrieved from the database and transmitted to the display module. When Nq is the largest, the scheme 3 is retrieved from the database and transmitted to the display module. When Nh is the largest, the scheme 4 is retrieved from the database and transmitted to the display module. The schemes 1, 2, 3 and 4 are all pre-stored in the database. Plan 1: The trainee performs k sets of bending training for the left forearm, 0.5k times per set, k sets of lifting training for the left upper arm, 0.5k times per set, k sets of bending training for the left calf, k times per set, and k sets of lifting training for the left thigh, k times per set, with a rest period of 0.25k minutes between each set; Plan 2: The trainee performs k sets of bending training on the right forearm, 0.5k times per set, k sets of lifting training on the right upper arm, 0.5k times per set, k sets of bending training on the right calf, k times per set, and k sets of lifting training on the right thigh, k times per set, with 0.25k minutes of rest between each set; Plan 3: The trainee does chest expansion exercises, k times per set, with 0.5k minutes of rest between each set; Plan 4: The trainee does waist twisting exercise training, k times per set, with a rest period of 0.5k minutes between each set. When the number of training times is a decimal, the decimal that is less than an integer will be calculated as 1.

4. The efficient intelligent multi-state balance training system according to claim 1, characterized in that: When the optimization program is executed, the calculation unit compares the first static index, the second static index, the first dynamic index and the second dynamic index. If the second static index is greater than the first static index, the value of the training parameter k is increased by 0.

5. Otherwise, if the second static index is less than or equal to the first static index, the value of the training parameter k is reduced by 0.

5. If the second dynamic index is greater than the first dynamic index, the value of the training parameter k is increased by 1. Otherwise, if the second dynamic index is less than or equal to the first dynamic index, the value of the training parameter k is reduced by 1. The minimum value of k is 2 and the maximum is 20. When the training parameter k changes, the changed training parameter k replaces the original training parameter k and is saved in the database. The next time the training program is executed, the changed training parameter k is retrieved from the database to execute the training program.

5. The efficient intelligent multi-state balance training system according to claim 1, characterized in that: The database presets standard initialization movements, static movements and dynamic movements. Nodes are set for the left upper arm, right upper arm, left forearm, right forearm, left calf, right calf, left thigh, right thigh, front chest and back waist on each movement; the computing unit establishes a spatial coordinate system and obtains the initialization movement from the database. The trainee keeps standing and performs initialization by sending initialization instructions to each module in the electromyographic unit through the wireless module. After receiving the initialization instruction, each module resets its own acceleration sensor to zero and projects the initialization movement into the spatial coordinate system. Each module in the electromyographic unit is overlapped and bound to the corresponding node in the initialization movement for calibrating motion capture to complete the initialization.

Images