CN118016241A - Human body movement function assessment and correction training method and system - Google Patents
Human body movement function assessment and correction training method and system Download PDFInfo
- Publication number
- CN118016241A CN118016241A CN202410420081.4A CN202410420081A CN118016241A CN 118016241 A CN118016241 A CN 118016241A CN 202410420081 A CN202410420081 A CN 202410420081A CN 118016241 A CN118016241 A CN 118016241A
- Authority
- CN
- China
- Prior art keywords
- action
- evaluation
- test
- function
- exercise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012549 training Methods 0.000 title claims abstract description 51
- 238000012937 correction Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 132
- 230000009471 action Effects 0.000 claims abstract description 130
- 238000012360 testing method Methods 0.000 claims abstract description 113
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 110
- 238000013139 quantization Methods 0.000 claims description 54
- 210000003127 knee Anatomy 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 210000002683 foot Anatomy 0.000 claims description 12
- 210000001624 hip Anatomy 0.000 claims description 12
- 230000000386 athletic effect Effects 0.000 claims description 11
- 230000009194 climbing Effects 0.000 claims description 9
- 230000036387 respiratory rate Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000001186 cumulative effect Effects 0.000 claims description 7
- 230000007105 physical stamina Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 210000003423 ankle Anatomy 0.000 claims description 6
- 230000037147 athletic performance Effects 0.000 claims description 6
- 230000003139 buffering effect Effects 0.000 claims description 6
- 238000011065 in-situ storage Methods 0.000 claims description 6
- 210000004197 pelvis Anatomy 0.000 claims description 6
- 210000000689 upper leg Anatomy 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 5
- 230000002746 orthostatic effect Effects 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 2
- 230000007659 motor function Effects 0.000 claims description 2
- 230000006378 damage Effects 0.000 abstract description 2
- 208000024891 symptom Diseases 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000009084 cardiovascular function Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009747 swallowing Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a human body movement function assessment and correction training method and system, wherein when a tested person executes test actions in sequence, non-contact equipment is used for collecting movement test data, single-item scores of the test actions are calculated, and movement function comprehensive scores of the tested person are calculated according to the single-item scores; then calculating the exercise function grade of the tested person through a clustering algorithm according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score; the tested person adopts corresponding training according to the exercise function grade; according to the invention, a plurality of clustering distance indexes are adopted for grading, index weights are distributed according to priori accuracy obtained by grading different indexes, and a final grade assessment result is obtained based on a plurality of indexes, so that grading is more reasonable and accurate, and through designing a complete exercise function assessment and correction training scheme, the exercise function assessment dimension is expanded, and physical training injuries are effectively prevented and reduced.
Description
Technical Field
The invention relates to the field of exercise function assessment, in particular to a human body exercise function assessment and correction training method and system.
Background
As people continue to gain knowledge of health and exercise, more and more people begin to appreciate the importance of exercise function assessment and corrective training and actively seek related services and guidance. The exercise function refers to various functions and abilities exhibited by the human body during exercise. It is the mutual coordinated movement of various body systems involved in the movement of human body, and is an important basis for the movement of human body.
At present, the exercise function assessment mainly uses an American FMS assessment system as a main basis, adopts a motion screening mode to assess exercise flexibility and stability, and has the following problems: (1) more test actions but fewer evaluation items; (2) The evaluation action measurement mode mainly comprises naked eye judgment or computer intelligent measurement based on video data shot by a monocular camera, and usually has larger error; (3) The evaluation result cannot be directly related to the specific functional problem, and correction training cannot be performed according to the specific functional problem.
Disclosure of Invention
The invention aims to: the invention aims to provide a human body movement function evaluation and correction training method and system which can be used for accurately and comprehensively evaluating movement functions by less evaluation actions and guiding targeted training by using grading evaluation results.
The technical scheme is as follows: the invention relates to a human body movement function assessment and correction training method which is characterized by comprising the following steps of:
The tested personnel execute the test actions according to the design in sequence;
collecting movement test data by using non-contact equipment; the exercise test data comprises respiratory rate, heart beat times and evaluation parameters of each test action;
Calculating the single score of the test action, and calculating the comprehensive score of the exercise function of the tested person according to the single score;
Calculating the exercise function grade of the tested person according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score;
the tested person adopts corresponding training according to the exercise function grade;
The motion function grade is s-grade, s is more than or equal to 3, and the motion function grade of the tested person is calculated through a clustering algorithm; the evaluation parameters of each test action, the single score of each test action and the comprehensive score of the exercise function of the tested person are combined into sample characteristics of the tested person; classifying all sample characteristics into s classes according to the rating of each tested person by an expert, and calculating the average value of each class of sample characteristics to obtain an s class clustering center; for each sample feature, a plurality of clustering distance indexes are utilized to obtain a plurality of evaluation results; the sum of the first weights corresponding to the cluster distance indexes with the same evaluation results is the second weight of the evaluation results, and the evaluation result with the highest second weight is the exercise function grade of the tested person.
Further, the calculating the sports function comprehensive score of the tested person according to the single score of the test action comprises the following steps:
Setting a quantization threshold value for each evaluation parameter of each test action, and converting the evaluation parameter corresponding to each test action into an integer parameter quantization value according to the quantization threshold value; for each test action, carrying out weighted summation on all the corresponding parameter quantized values to obtain a single score of the test action;
and carrying out weighted summation on all the single scores to obtain the comprehensive score of the movement function of the tested person.
Further, the quantization threshold value X 1、X2、…、Xm+1 forms a quantization interval [ X 1,X2]、…、[Xm,Xm+1 ], m is the number of quantization intervals, and the evaluation parameter is converted into a corresponding parameter quantization value according to the quantization interval in which the evaluation parameter is located;
Setting score grades L 1 、…、Lm, wherein each grade corresponds to a parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the motion test data quantity, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value mu and standard deviation sigma of motion test data of a plurality of tested objects;
the quantization thresholds X 1 and X m+1 are determined according to expert experience, and the calculation method of the quantization threshold X 2、…、Xm is as follows ; Wherein Z m-1 is a quantile corresponding to the cumulative normal distribution;
When the parameter quantization rule is smaller and better, Z m-1 is a quantile corresponding to the accumulated normal distribution P m-1, and the quantization interval [ X 1,X2] 、…、[Xm,Xm+1 ] sequentially corresponds to the parameter quantization value Y m、…、Y1;
when the parameter quantization rule is larger and better, Z m-1 is the quantile corresponding to the cumulative normal distribution 1-P m-1; the quantization interval X 2,X1] 、…、[Xm+1,Xm corresponds in turn to the parameter quantization value Y m、…、Y1.
Further, the calculating the first weight of the tested person in each sport function level through the clustering algorithm comprises:
the evaluation parameter of each test action, the single score of each test action and the sports function comprehensive score of the test object are combined into a sample characteristic x i of the tested person,
；
Wherein V i_q represents the q-th parameter quantization value of the ith tested person, q is more than or equal to 1 and less than or equal to m, S i_j represents the single-item score of the j-th test action of the ith tested person, j is more than or equal to 1 and less than or equal to k, and F i is the motion function comprehensive score of the ith tested person;
Dividing the sample to be tested into three types X a、Xb、Xc according to expert ratings, and taking the average value of the three types of sample characteristics as three clustering centers X oa、Xob、Xoc respectively;
Clustering all test samples by adopting n clustering distance indexes to obtain priori accuracy K 1,K2,...,Kn under different clustering distance indexes;
calculating a first weight of each cluster distance index, wherein the first weight W p= Kp/ (K1+K2+...+Kn is as follows;
for each tested person, calculating an evaluation result y 1,y2,...,yn under each cluster distance index, wherein y 1,y2,...,yn epsilon { a, b, c }; the sum of the first weights corresponding to the same evaluation result is the second weight of the sports function grade, and the sports function grade with the highest second weight is the sports function grade of the tested person.
Further, the clustering distance index includes: euclidean distance, manhattan distance, minkowski distance, chebyshev distance, mahalanobis distance, and cosine similarity.
Further, dividing the motion function evaluation item points into flexible items, stable items, action modes and physical stamina, and setting test actions according to the motion function evaluation item points; the test actions include a athletic performance assessment action, an athletic performance assessment action;
The exercise capacity assessment action is a structural exercise action, comprising: the hands are turned back by pushing the top, the upright body is bent forward to touch the ground and the upright body is rotated by bare hands, so that the exercise flexibility and stability are inspected;
The exercise function assessment action is a pattern type exercise action, comprising: the double hands pass the top deep squat, freehand bow-and-arrow walking swivel, back-stride swallow balance and in-situ longitudinal jump, and are used for examining movement flexibility, stability and action modes;
The athletic performance evaluation action is a performance investigation type athletic action, comprising: the retracing running and bear climbing are used for examining action modes and physical stamina;
The person to be tested executes the exercise capacity evaluation action, the exercise function evaluation action and the exercise performance evaluation action in sequence.
Further, the evaluation parameters of the test actions include joint flexion and extension angles, distances between joints, spine swing angles and Xiong Pa grades, and the evaluation parameters corresponding to different test actions include:
The evaluation parameters of the double-hand top-down include: spine extension angle, right shoulder flexion angle, left shoulder flexion angle;
the evaluation parameters of the orthostatic antegrade touchdown include: right hip flexion angle, left hip flexion angle, hand to heel distance;
the evaluation parameters of the standing freehand rotation include: right_spinal column and pelvic rotation angle, left_spinal column and pelvic rotation angle, right_spinal column swing, left_spinal column swing;
The evaluation parameters of the double-hand over-top squat include: squat depth, spine left-right swing, spine forward tilting angle, right upper arm back-forth swing, left upper arm back-forth swing, right shoulder flexion angle, right hip flexion angle, right ankle extension angle, left shoulder flexion angle, left hip flexion angle, left ankle extension angle;
The evaluation parameters of the freehand bow walking swivel include: right_spine and pelvis rotation angle, left_spine and pelvis rotation angle, right_spine back and forth swing, right_spine left and right swing, left_spine back and forth swing, left_spine left and right swing;
the evaluation parameters of the back-stepping swallow balance include: the included angle between the right thigh and the horizontal plane, the included angle between the left thigh and the horizontal plane, the left spine swing left and right, the left knee center swing distance, the right ankle center swing distance, the left knee center swing distance and the left ankle center swing distance;
The evaluation parameters of the in-situ jump include: jump height, spine back and forth swing, spine left and right swing, spine twist, right jump knee adduction abduction angle, right landing knee adduction abduction angle, right buffering minimum point knee adduction angle, right jump foot rotation angle, right landing foot rotation angle, left jump knee adduction abduction angle, left landing knee adduction abduction angle, left buffering minimum point knee adduction angle, left jump foot rotation angle, left landing foot rotation angle;
The evaluation parameters of reentry run included: time;
The evaluation parameters of bear climbing include: bear climbing is classified.
The human motion function assessment and correction training system of the invention comprises:
the test data acquisition unit is used for acquiring the motion test data of the tested person by using non-contact equipment; the exercise test data comprise respiratory rate, heartbeat times and evaluation parameters of each test action, wherein the tested personnel execute the test actions in sequence according to the designed test actions;
The exercise function grade grading unit is used for calculating the single score of the test action and calculating the exercise function comprehensive score of the tested person according to the single score; calculating the exercise function grade of the tested person according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score;
the correction training unit is used for enabling the tested person to adopt corresponding training according to the exercise function grade;
In the athletic function grade grading unit, the athletic function grade is classified into s grades, s is more than or equal to 3, and the athletic function grade of the tested person is calculated through a clustering algorithm; the evaluation parameters of each test action, the single score of each test action and the comprehensive score of the exercise function of the tested person are combined into sample characteristics of the tested person; classifying all sample characteristics into s classes according to the rating of each tested person by an expert, and calculating the average value of each class of sample characteristics to obtain an s class clustering center; for each sample feature, a plurality of clustering distance indexes are utilized to obtain a plurality of evaluation results; the sum of the first weights corresponding to the cluster distance indexes with the same evaluation results is the second weight of the evaluation results, and the evaluation result with the highest second weight is the exercise function grade of the tested person.
The electronic equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the human body movement function evaluation and correction training method when being loaded to the processor.
The computer readable storage medium of the present invention stores a computer program, which is characterized in that the human body movement function evaluation and correction training method is implemented when the computer program is executed by a processor.
The beneficial effects are that: compared with the prior art, the invention has the advantages that: (1) Firstly, designing a set of evaluation and test actions and processes, establishing a complete exercise function evaluation and correction training scheme based on the evaluation and test actions and processes, classifying the exercise functions in a clustering mode, and taking different training/rehabilitation measures for different grades, thereby being beneficial to scientific training and effectively preventing and reducing physical training injuries; (2) According to the invention, the traditional comprehensive evaluation item points are expanded, the action mode evaluation and the physical ability evaluation are added under the condition that the traditional movement capability evaluation is only aimed at stability and flexibility, and the test action design is carried out according to the movement function evaluation item and the action form; (3) According to the invention, a plurality of clustering distance indexes are adopted for grading, the weight of the distributed indexes is calculated according to the prior accuracy of grading of different indexes, and a final grading evaluation result is obtained based on a plurality of indexes, so that unreasonable grading caused by absolute grading by only using a final score in the traditional method is avoided; (4) The training result is tracked and evaluated, the evaluation method and the corrective action library are continuously optimized, the model evaluation accuracy and the training effect can be continuously improved, and the universality is strong.
Drawings
FIG. 1 is a flow chart of the exercise function assessment and correction training method of the present invention.
Fig. 2 is a schematic diagram of a test action flow according to an embodiment of the invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the human motion function evaluation and correction training method comprises the following steps:
S1: and (5) testing the design of the action flow. And performing test action design based on the motion science knowledge.
The motion function evaluation item points are divided into flexible items, stable items, action modes and physical stamina, wherein the flexible items are used for evaluating the maximum movement range of joints, the stable items are used for evaluating the stability and action control capability of the joints, the action modes are used for evaluating the overall action completion capability and action gesture, and the physical stamina is used for evaluating the heart-lung endurance and the like.
According to the motion function evaluation items and the motion forms, the motion is further divided into a motion ability evaluation motion, a motion function evaluation motion and a motion performance evaluation motion, wherein the motion ability evaluation motion is mainly structural motion and comprises the following steps: the hands are turned back by pushing the top, the upright body is bent forward to touch the ground, and the upright body is rotated by bare hands, so that the movement flexibility and stability are inspected; the exercise function assessment action is mainly a mode type exercise, including: the double hands pass the top deep squat, hiking, walking and turning, back striding and swallowing balance and in-situ longitudinal jump, the flexibility, stability and action mode of the exercise are inspected, the exercise performance evaluation action mainly comprises the following steps: turning back running, bear climbing, examining action modes and physical stamina, etc.
The test is a sequential test in the order of exercise ability assessment action, exercise function assessment action, and exercise performance assessment action, as shown in fig. 2.
S2: and (5) collecting exercise test data. And testing sequentially, including exercise action testing and other evaluation parameter testing, and acquiring exercise test data based on multiple devices. The acquisition device mainly comprises: binocular camera, millimeter wave measuring device, touch timing device; the acquired data mainly comprise shooting sport action videos, heart rate, respiratory rate, action duration and the like. The data acquisition equipment used for each test content in this example is shown in the following table.
Table 1 test data acquisition device table
S3: test data preprocessing. Preprocessing the acquired data, and adopting different preprocessing operations for different data types. Mainly comprises the following steps: data filtering, key moment identification, action moment identification, joint point coordinate extraction and the like.
S4: and (5) evaluating parameter calculation. Based on the preprocessed test data, evaluation parameter calculation is performed on different parameters, and parameter quantization is performed based on a preset parameter quantization threshold, wherein the evaluation parameters include but are not limited to: joint flexion/extension angle, spine swing angle, respiratory rate, number of heartbeats, etc. The evaluation parameters of the different actions in this embodiment are as follows.
(A) The evaluation parameters of the double-hand top-down include: spine extension angle, right shoulder flexion angle, left shoulder flexion angle;
(b) The evaluation parameters of the orthostatic antegrade touchdown include: right hip flexion angle, left hip flexion angle, hand to heel distance;
(c) The evaluation parameters of the standing freehand rotation include: right_spinal column and pelvic rotation angle, left_spinal column and pelvic rotation angle, right_spinal column swing, left_spinal column swing;
(d) The evaluation parameters of the double-hand over-top squat include: squat depth, spine left-right swing, spine forward tilting angle, right upper arm back-forth swing, left upper arm back-forth swing, right shoulder flexion angle, right hip flexion angle, right ankle extension angle, left shoulder flexion angle, left hip flexion angle, left ankle extension angle;
(e) The evaluation parameters of the freehand bow walking swivel (prescribed action squats before turns) include: right_spine and pelvis rotation angle, left_spine and pelvis rotation angle, right_spine back and forth swing, right_spine left and right swing, left_spine back and forth swing, left_spine left and right swing;
(f) The evaluation parameters of the back stride swallow balance (right first then left specified) include: the included angle between the right thigh and the horizontal plane, the included angle between the left thigh and the horizontal plane, the left spine swing left and right, the left knee center swing distance, the right ankle center swing distance, the left knee center swing distance and the left ankle center swing distance;
(g) The evaluation parameters of the in-situ jump include: jump height, spine back and forth swing, spine left and right swing, spine twist, right jump knee adduction abduction angle, right landing knee adduction abduction angle, right buffering minimum point knee adduction angle, right jump foot rotation angle, right landing foot rotation angle, left jump knee adduction abduction angle, left landing knee adduction abduction angle, left buffering minimum point knee adduction angle, left jump foot rotation angle, left landing foot rotation angle;
(h) The evaluation parameters of the breathing pattern include: respiratory rate, thoracic respiratory index;
(i) The evaluation parameters of reentry run included: time;
(j) The evaluation parameters of cardiovascular function include: improving cardiovascular function index;
(k) The evaluation parameters of bear climbing include: bear climbing is classified.
The quantization rules are divided into smaller and larger and better, and the threshold value presetting and parameter quantization methods are as follows: setting a score grade { L 1,L2..Lm } (from low to high), wherein each grade corresponds to a parameter quantized value { Y 1,Y2..Ym }, corresponds to an accumulated data duty ratio { P 1,P2..Pm-1 }, calculates a test data parameter mean mu and a standard deviation sigma, and a score grade threshold X m is calculated as follows:
；
Wherein Z m-1 is a quantile corresponding to the cumulative normal distribution, Z m-1 is a quantile corresponding to the cumulative normal distribution P m-1 when the parameter quantization rule is smaller and better, and Z m-1 is a quantile corresponding to the cumulative normal distribution 1-P m-1 when the parameter quantization rule is larger and better.
When the quantization rule is smaller and better, all the score grade values X 1,X2,…,Xm+1 form a quantization interval, wherein X 1 is the minimum value, X m+1 is the maximum value, the quantization interval curve 1=[X1.X2 corresponds to the parameter quantization value Y m,curve2=[X2,X3, the quantization interval Y m-1,…,curvem+l=[xm,Xm+1 corresponds to the parameter quantization value Y 1, the parameter calculation result corresponds to a specific interval, and the corresponding parameter quantization value is obtained.
When the quantization rule is that the larger and the better are, all the score grade values X 1,X2,…,Xm+1 form a quantization interval, wherein X 1 is the maximum value, X m+1 is the minimum value, the quantization interval curve 1=[X2,X1 corresponds to the parameter quantization value Y m,curve2=[X3,X2 and the parameter quantization value Y m-1,…,curvem+1=[xm+1,xm corresponds to the parameter quantization value Y 1, and the parameter calculation result corresponds to the specific interval and the corresponding parameter quantization value is obtained.
S5: motor function composite score. And carrying out single score calculation on different actions based on the key parameters and the set parameter scoring weights, and carrying out weighted summation on each action score and each action scoring weight to obtain the motion function comprehensive score.
S6: and (5) grading sports functions. And grading is carried out based on a motion function grading model, wherein the grading model establishment flow is as follows:
(1) All test subjects were rated by the sports medical expert, the class being classified into three classes, the three classes corresponding to the result generally being: the obvious abnormal symptoms need medical treatment and rehabilitation (grade mark a), the normal exercise training can be carried out when no symptoms exist and the exercise function reaches the standard (grade mark b), and the correction training needs to be carried out when weak links and exercise defects exist (grade mark c);
(2) The single sample feature x i is composed of action parameters, single scores and composite scores,
；
(3) Classifying the test specimens into three types X a、Xb、Xc according to expert ratings;
(4) The average value of three types of samples is calculated as a three-type grade center X oa、Xob、Xoc;
(5) Clustering all test data by adopting different clustering distance indexes by taking the hierarchical center X oa、Xob、Xoc as a clustering center to obtain priori accuracy K 1,K2,...Kn (n is the number of the used clustering distance indexes) under different clustering indexes;
(6) Calculating different clustering index weights W p according to the clustering accuracy K 1,K2,...Kn under different clustering indexes;
Wp= Kp/ (K1+K2+...+Kn)；
(7) For a single test sample, calculating a grading result y 1,y2,...yn (y epsilon { a, b, c } under different clustering distance indexes, adding the same distance index weights of the grading results to obtain the scoring weights of different grades, and taking the highest weight as a final grade.
S7: different training/rehabilitation measures are adopted according to the grading result, and the method is as follows:
(1) The evaluation result is that obvious abnormal symptoms exist, namely medical treatment and rehabilitation are needed, treatment and rehabilitation training are carried out after the symptom is evaluated, and then the exercise function is evaluated again;
(2) The assessment result is asymptomatic and the exercise function reaches the standard, so that physical training can be normally performed, physical training is performed through physical assessment, various physical attributes are improved, and then part of targeted special training is performed:
(3) The evaluation result is weak links and bad movements, namely, correction training is needed. Classifying functional problems based on the evaluation parameter types and joint types, classifying the problem evaluation parameters, scoring specific functional problems, matching correction training action groups of non-full-score problems based on a preset correction action library, outputting correction training program training, tracking correction training conditions, manually calibrating comprehensive evaluation results and training action effectiveness, and performing optimization iteration on the correction action library and the comprehensive evaluation parts S4-S6.
The human motion function assessment and correction training system of the invention comprises:
the test data acquisition unit is used for acquiring the motion test data of the tested person by using non-contact equipment; the exercise test data comprise respiratory rate, heartbeat times and evaluation parameters of each test action, wherein the tested personnel execute the test actions in sequence according to the designed test actions;
The exercise function grade grading unit is used for calculating the single score of the test action and calculating the exercise function comprehensive score of the tested person according to the single score; calculating the exercise function grade of the tested person according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score;
the correction training unit is used for enabling the tested person to adopt corresponding training according to the exercise function grade;
In the athletic function grade grading unit, the athletic function grade is divided into a, b and c grades, and the athletic function grade of the tested person is calculated through a clustering algorithm; the evaluation parameters of each test action, the single score of each test action and the comprehensive score of the exercise function of the tested person are combined into sample characteristics of the tested person; classifying all sample characteristics into three types according to the rating of each tested person by an expert, and calculating the average value of each type of sample characteristics to obtain three types of clustering centers; for each sample feature, a plurality of clustering distance indexes are utilized to obtain a plurality of evaluation results; the sum of the first weights corresponding to the cluster distance indexes with the same evaluation results is the second weight of the evaluation results, and the evaluation result with the highest second weight is the exercise function grade of the tested person.
The electronic equipment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes the human body movement function evaluation and correction training method when being loaded to the processor.
The computer readable storage medium of the present invention stores a computer program which, when executed by a processor, implements the human motion function assessment and correction training method.
The computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The processor is configured to execute the computer program stored in the memory to implement the steps in the method according to the above-mentioned embodiments.
Claims (10)
1. The human body movement function assessment and correction training method is characterized by comprising the following steps of:
The tested personnel execute the test actions according to the design in sequence;
collecting movement test data by using non-contact equipment; the exercise test data comprises respiratory rate, heart beat times and evaluation parameters of each test action;
Calculating the single score of the test action, and calculating the comprehensive score of the exercise function of the tested person according to the single score;
Calculating the exercise function grade of the tested person according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score;
the tested person adopts corresponding training according to the exercise function grade;
The motion function grade is s-grade, s is more than or equal to 3, and the motion function grade of the tested person is calculated through a clustering algorithm; the evaluation parameters of each test action, the single score of each test action and the comprehensive score of the exercise function of the tested person are combined into sample characteristics of the tested person; classifying all sample characteristics into s classes according to the rating of each tested person by an expert, and calculating the average value of each class of sample characteristics to obtain an s class clustering center; for each sample feature, a plurality of clustering distance indexes are utilized to obtain a plurality of evaluation results; the sum of the first weights corresponding to the cluster distance indexes with the same evaluation results is the second weight of the evaluation results, and the evaluation result with the highest second weight is the exercise function grade of the tested person.
2. The method for evaluating and correcting a human body movement function according to claim 1, wherein the calculating the movement function integrated score of the person under test according to the single score of the test action comprises:
Setting a quantization threshold value for each evaluation parameter of each test action, and converting the evaluation parameter corresponding to each test action into an integer parameter quantization value according to the quantization threshold value; for each test action, carrying out weighted summation on all the corresponding parameter quantized values to obtain a single score of the test action;
and carrying out weighted summation on all the single scores to obtain the comprehensive score of the movement function of the tested person.
3. The human motion function assessment and correction training method according to claim 2, wherein the quantization threshold X 1、X2、…、Xm+1 constitutes a quantization interval [ X 1,X2]、…、[Xm,Xm+1 ], m is the number of quantization intervals, and the assessment parameters are converted into corresponding parameter quantization values according to the quantization interval in which the assessment parameters are located;
Setting score grades L 1 、…、Lm, wherein each grade corresponds to a parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the motion test data quantity, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value mu and standard deviation sigma of motion test data of a plurality of tested objects;
the quantization thresholds X 1 and X m+1 are determined according to expert experience, and the calculation method of the quantization threshold X 2、…、Xm is as follows ; Wherein Z m-1 is a quantile corresponding to the cumulative normal distribution;
When the parameter quantization rule is smaller and better, Z m-1 is a quantile corresponding to the accumulated normal distribution P m-1, and the quantization interval [ X 1,X2]、…、[Xm,Xm+1 ] sequentially corresponds to the parameter quantization value Y m、…、Y1;
When the parameter quantization rule is larger and better, Z m-1 is the quantile corresponding to the cumulative normal distribution 1-P m-1; the quantization interval X 2,X1]、…、[Xm+1,Xm corresponds in turn to the parameter quantization value Y m、…、Y1.
4. The method for evaluating and correcting human body movement function according to claim 2, wherein the calculating the first weight of the person under test at each movement function level by the clustering algorithm comprises:
the evaluation parameter of each test action, the single score of each test action and the sports function comprehensive score of the test object are combined into a sample characteristic x i of the tested person,
；
Wherein V i_q represents the q-th parameter quantization value of the ith tested person, q is more than or equal to 1 and less than or equal to m, S i_j represents the single-item score of the j-th test action of the ith tested person, j is more than or equal to 1 and less than or equal to k, and F i is the motion function comprehensive score of the ith tested person;
Dividing the sample to be tested into three types X a、Xb、Xc according to expert ratings, and taking the average value of the three types of sample characteristics as three clustering centers X oa、Xob、Xoc respectively;
Clustering all test samples by adopting n clustering distance indexes to obtain priori accuracy K 1,K2,...,Kn under different clustering distance indexes;
Calculating a first weight of each cluster distance index, wherein the first weight W p = Kp / (K1+K2+...+Kn is as follows;
for each tested person, calculating an evaluation result y 1,y2,...,yn under each cluster distance index, wherein y 1,y2,...,yn epsilon { a, b, c }; the sum of the first weights corresponding to the same evaluation result is the second weight of the sports function grade, and the sports function grade with the highest second weight is the sports function grade of the tested person.
5. The method for evaluating and correcting a human motion function according to claim 1, wherein the clustering distance index comprises: euclidean distance, manhattan distance, minkowski distance, chebyshev distance, mahalanobis distance, and cosine similarity.
6. The human body movement function evaluation and correction training method according to claim 1, wherein movement function evaluation item points are divided into flexible items, stable items, action modes, physical stamina, and test actions are set according to the movement function evaluation item points; the test actions include a athletic performance assessment action, an athletic performance assessment action;
The exercise capacity assessment action is a structural exercise action, comprising: the hands are turned back by pushing the top, the upright body is bent forward to touch the ground and the upright body is rotated by bare hands, so that the exercise flexibility and stability are inspected;
The exercise function assessment action is a pattern type exercise action, comprising: the double hands pass the top deep squat, freehand bow-and-arrow walking swivel, back-stride swallow balance and in-situ longitudinal jump, and are used for examining movement flexibility, stability and action modes;
The athletic performance evaluation action is a performance investigation type athletic action, comprising: the retracing running and bear climbing are used for examining action modes and physical stamina;
The person to be tested executes the exercise capacity evaluation action, the exercise function evaluation action and the exercise performance evaluation action in sequence.
7. The method according to claim 6, wherein the evaluation parameters of the test actions include joint flexion and extension angles, distances between joints, spine swing angles, xiong Pa grades, and the evaluation parameters corresponding to different test actions include:
The evaluation parameters of the double-hand top-down include: spine extension angle, right shoulder flexion angle, left shoulder flexion angle;
the evaluation parameters of the orthostatic antegrade touchdown include: right hip flexion angle, left hip flexion angle, hand to heel distance;
the evaluation parameters of the standing freehand rotation include: right_spinal column and pelvic rotation angle, left_spinal column and pelvic rotation angle, right_spinal column swing, left_spinal column swing;
The evaluation parameters of the double-hand over-top squat include: squat depth, spine left-right swing, spine forward tilting angle, right upper arm back-forth swing, left upper arm back-forth swing, right shoulder flexion angle, right hip flexion angle, right ankle extension angle, left shoulder flexion angle, left hip flexion angle, left ankle extension angle;
The evaluation parameters of the freehand bow walking swivel include: right_spine and pelvis rotation angle, left_spine and pelvis rotation angle, right_spine back and forth swing, right_spine left and right swing, left_spine back and forth swing, left_spine left and right swing;
the evaluation parameters of the back-stepping swallow balance include: the included angle between the right thigh and the horizontal plane, the included angle between the left thigh and the horizontal plane, the left spine swing left and right, the left knee center swing distance, the right ankle center swing distance, the left knee center swing distance and the left ankle center swing distance;
The evaluation parameters of the in-situ jump include: jump height, spine back and forth swing, spine left and right swing, spine twist, right jump knee adduction abduction angle, right landing knee adduction abduction angle, right buffering minimum point knee adduction angle, right jump foot rotation angle, right landing foot rotation angle, left jump knee adduction abduction angle, left landing knee adduction abduction angle, left buffering minimum point knee adduction angle, left jump foot rotation angle, left landing foot rotation angle;
The evaluation parameters of reentry run included: time;
The evaluation parameters of bear climbing include: bear climbing is classified.
8. A human motor function assessment and correction training system, comprising:
the test data acquisition unit is used for acquiring the motion test data of the tested person by using non-contact equipment; the exercise test data comprise respiratory rate, heartbeat times and evaluation parameters of each test action, wherein the tested personnel execute the test actions in sequence according to the designed test actions;
The exercise function grade grading unit is used for calculating the single score of the test action and calculating the exercise function comprehensive score of the tested person according to the single score; calculating the exercise function grade of the tested person according to the evaluation parameter of each test action, the single score of each test action and the exercise function comprehensive score;
the correction training unit is used for enabling the tested person to adopt corresponding training according to the exercise function grade;
In the athletic function grade grading unit, the athletic function grade is classified into s grades, s is more than or equal to 3, and the athletic function grade of the tested person is calculated through a clustering algorithm; the evaluation parameters of each test action, the single score of each test action and the comprehensive score of the exercise function of the tested person are combined into sample characteristics of the tested person; classifying all sample characteristics into s classes according to the rating of each tested person by an expert, and calculating the average value of each class of sample characteristics to obtain an s class clustering center; for each sample feature, a plurality of clustering distance indexes are utilized to obtain a plurality of evaluation results; the sum of the first weights corresponding to the cluster distance indexes with the same evaluation results is the second weight of the evaluation results, and the evaluation result with the highest second weight is the exercise function grade of the tested person.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when loaded into the processor implements the human movement function assessment and correction training method according to any of claims 1-7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the human movement function assessment and correction training method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410420081.4A CN118016241B (en) | 2024-04-09 | 2024-04-09 | Human body movement function assessment and correction training method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410420081.4A CN118016241B (en) | 2024-04-09 | 2024-04-09 | Human body movement function assessment and correction training method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118016241A true CN118016241A (en) | 2024-05-10 |
| CN118016241B CN118016241B (en) | 2024-06-07 |
Family
ID=90958167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410420081.4A Active CN118016241B (en) | 2024-04-09 | 2024-04-09 | Human body movement function assessment and correction training method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118016241B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883229A (en) * | 2020-07-31 | 2020-11-03 | 焦点科技股份有限公司 | Intelligent movement guidance method and system based on visual AI |
| CN116758627A (en) * | 2023-05-26 | 2023-09-15 | 广西师范大学 | Automatic evaluation method for motion of straight jump air technology |
| CN117037278A (en) * | 2023-08-24 | 2023-11-10 | 首都体育学院 | Jump floor error assessment method and apparatus |
-
2024
- 2024-04-09 CN CN202410420081.4A patent/CN118016241B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883229A (en) * | 2020-07-31 | 2020-11-03 | 焦点科技股份有限公司 | Intelligent movement guidance method and system based on visual AI |
| CN116758627A (en) * | 2023-05-26 | 2023-09-15 | 广西师范大学 | Automatic evaluation method for motion of straight jump air technology |
| CN117037278A (en) * | 2023-08-24 | 2023-11-10 | 首都体育学院 | Jump floor error assessment method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118016241B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Blair et al. | Concurrent validation of an inertial measurement system to quantify kicking biomechanics in four football codes | |
| Wagner et al. | Kinematic analysis of volleyball spike jump | |
| Kim et al. | Inter-joint coordination in producing kicking velocity of Taekwondo kicks | |
| US20150374283A1 (en) | Method and device for mobile training data acquisition and analysis of strength training | |
| Hanley et al. | Kinematic characteristics of elite men's 50 km race walking | |
| US20220207921A1 (en) | Motion recognition method, storage medium, and information processing device | |
| AU2021202003B2 (en) | Methods and systems for bicycle fitting | |
| CN103732296A (en) | Training device | |
| US20230355135A1 (en) | Intelligent gait analyzing apparatus | |
| CN112568898A (en) | Method, device and equipment for automatically evaluating injury risk and correcting motion of human body motion based on visual image | |
| Ross et al. | Classifying elite from novice athletes using simulated wearable sensor data | |
| CN115661930A (en) | Action scoring method and device, action scoring equipment and storage medium | |
| Severin et al. | The required number of trials for biomechanical analysis of a golf swing | |
| CN117653084A (en) | Method for evaluating scoliosis rehabilitation state by using gait | |
| CN118016241B (en) | Human body movement function assessment and correction training method and system | |
| CN115837147B (en) | Scene interactive lower limb muscle strengthening training method and system | |
| CN113012812B (en) | Knee, ankle joint and plantar pressure data integration method and system | |
| Keith et al. | Anthropometric predictors of conventional deadlift kinematics and kinetics: a preliminary study | |
| CN111353345A (en) | Method, device and system for providing training feedback, electronic equipment and storage medium | |
| CN118016242B (en) | Method and system for generating human body movement function correction training scheme | |
| Przednowek et al. | Estimation of VO 2 max based on 20 m shuttle run test using statistical learning methods: An example of male physical education students | |
| Manzi et al. | Kinematic Models For Pitch Location Metrics in Professional Baseball Pitchers | |
| US20230172491A1 (en) | System and method for motion analysis including impairment, phase and frame detection | |
| CN118039068A (en) | Comprehensive evaluation method and system for human body movement function | |
| Zhang et al. | Edge Computing Assisted Internet of Things in Sports Management System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |