CN118039068B - Comprehensive evaluation method and system for human body movement function - Google Patents
Comprehensive evaluation method and system for human body movement function Download PDFInfo
- Publication number
- CN118039068B CN118039068B CN202410420075.9A CN202410420075A CN118039068B CN 118039068 B CN118039068 B CN 118039068B CN 202410420075 A CN202410420075 A CN 202410420075A CN 118039068 B CN118039068 B CN 118039068B
- Authority
- CN
- China
- Prior art keywords
- evaluation
- parameter
- score
- grade
- test
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 221
- 238000012360 testing method Methods 0.000 claims abstract description 158
- 230000006870 function Effects 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims abstract description 31
- 238000011835 investigation Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000013139 quantization Methods 0.000 claims description 69
- 230000008569 process Effects 0.000 claims description 28
- 230000009471 action Effects 0.000 claims description 13
- 238000012512 characterization method Methods 0.000 claims description 12
- 230000001186 cumulative effect Effects 0.000 claims description 10
- 238000013210 evaluation model Methods 0.000 claims description 9
- 238000010219 correlation analysis Methods 0.000 claims description 8
- 238000013064 process characterization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000007659 motor function Effects 0.000 claims 3
- 238000010606 normalization Methods 0.000 claims 2
- 230000037147 athletic performance Effects 0.000 description 16
- 239000013598 vector Substances 0.000 description 10
- 210000002683 foot Anatomy 0.000 description 7
- 230000000386 athletic effect Effects 0.000 description 4
- 238000005452 bending Methods 0.000 description 4
- 238000011065 in-situ storage Methods 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 230000007105 physical stamina Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000007614 genetic variation Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Physical Education & Sports Medicine (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a comprehensive evaluation method and a comprehensive evaluation system for human body movement functions, wherein the method comprises the following steps: designing test contents for testing multi-dimensional motion indexes; collecting test data, and obtaining original data of test contents completed by a tester; preprocessing the original data to obtain evaluation parameters of the test contents completed by a tester; classifying the evaluation parameters of all the test contents according to the investigation contents to obtain a plurality of evaluation parameter types, and obtaining the calculated values of the corresponding evaluation parameters according to the parameter types; quantizing the evaluation parameters according to the calculated values to obtain quantized values of the evaluation parameters; and classifying the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types. The method has high reliability and interpretability of the comprehensive evaluation result, divides the evaluation parameter types, adopts different calculation methods for different parameter types, and can grade the grading of the sport function from multiple dimensions.
Description
Technical Field
The present invention relates to a method and a system for evaluating the exercise function of a human body, and more particularly, to a method and a system for comprehensively evaluating the exercise function of a human body.
Background
The comprehensive evaluation of the human body movement function is combined with the computer vision and the artificial intelligence calculation, and the comprehensive evaluation method is widely applied to the fields of health management, rehabilitation therapy and movement training. At present, the comprehensive evaluation of the exercise function is mainly carried out by obtaining an evaluation parameter through camera or manual measurement, constructing an evaluation model based on the evaluation parameter and a function problem item to carry out single-item scoring, and integrating to obtain a final score. Most of the existing evaluation methods calculate by single index when evaluating parameters, cannot practically reflect the condition of the sports function index, have more sports function scoring dimension, and simply score comprehensively from function problem items, so that the evaluation result has poor interpretation.
Disclosure of Invention
The invention aims to: the invention aims to provide a comprehensive evaluation method and system for human body movement functions, which can carry out classified calculation and multidimensional comprehensive evaluation on evaluation parameters.
The technical scheme is as follows: the invention relates to a comprehensive evaluation method for human body movement functions, which comprises the following steps,
Designing test contents for testing multi-dimensional motion indexes;
Collecting test data, and obtaining original data of test contents completed by a tester;
Preprocessing the original data to obtain evaluation parameters of the test contents completed by a tester;
classifying the evaluation parameters of all the test contents according to the investigation contents to obtain a plurality of evaluation parameter types, and obtaining the calculated values of the corresponding evaluation parameters according to the parameter types;
Quantizing the evaluation parameters according to the calculated values to obtain quantized values of the evaluation parameters;
Classifying the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types, and comprehensively scoring evaluation parameter quantized values of the exercise function evaluation dimension types;
And integrating the comprehensive scores to obtain a final evaluation result.
Further, the evaluating the parameter types includes:
The single-moment extremum type parameter is used for examining the fixed point capability of a tester at a certain moment in the process of completing the test content;
The process characterization type parameter is used for examining the reaction capability of a tester in the process of completing the test content;
And the process extremum type parameter is used for examining the limit capability of a tester in the process of completing the test content.
Further, the specific calculation modes of the calculated values of the various evaluation parameter types are as follows:
The single-time extremum type parameter is firstly determined at time T i according to the setting condition, and a calculated value corresponding to the time Ti is calculated;
The process characterization type parameter is characterized in that firstly, the starting and ending time T 1start and characterization data in the time from T 1end,T1start to T 1end of the calculation time are determined according to the setting condition, and then the characterization data are calculated values of the parameter;
the extremum type parameter of the process is obtained firstly, and the extremum in the time from T 2start and T 2end,T2start to T 2end for completing certain test content is the calculated value of the parameter.
Further, the specific calculation mode for quantifying the evaluation parameters is as follows:
Setting score grades L 1 、…、Lm, wherein each score grade corresponds to an evaluation parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the evaluation parameters, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value u and standard deviation sigma of the evaluation parameters of a plurality of testers;
Setting a quantization threshold value of each evaluation parameter of each test content, wherein 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, the quantization threshold values X 1 and X m+1 are determined according to expert experience, and the calculated values of the evaluation parameters are mapped to the corresponding quantization intervals to obtain the quantized values of the evaluation parameters corresponding to the quantization thresholds; the formula for X m is as follows:
X m=u+(Zm-1)* σ,Zm-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.
The athletic performance assessment dimension type comprises a functional question item, a test item and an athletic performance level, wherein the functional question item comprises flexibility, stability, action mode and physical stamina of a tester, the test item comprises all single test contents, and the athletic performance level comprises athletic ability, athletic function and athletic performance.
Further, the comprehensive scoring steps of the functional problem items are as follows:
the multiple experts score the single functional questions of all testers respectively, calculate the average score of each single functional question and take the average score as the score of the corresponding single functional question;
Constructing a factor graph evaluation model between the functional problem and the evaluation parameters, wherein the functional problem and the evaluation parameters are connected by adopting a Bayesian network, and each evaluation parameter is connected by adopting a Markov network;
Inputting the quantized value of the evaluation parameter into a constructed factor graph evaluation model to obtain the score of the single functional problem of the tester;
weighting and summing the scores of all the single functional questions according to the set weights to obtain the comprehensive scores of the functional question item dimensions;
And obtaining the grade of the dimension of the functional problem item according to the set score grade interval of the comprehensive score.
Further, the comprehensive scoring of the test items is as follows:
the method comprises the steps that multiple experts respectively score single test items of all testers, average score of each single test item is calculated, and the average score of each single test item is used as a single test item score;
Adopting a plurality of correlation analysis methods to analyze the correlation between the quantized value of the evaluation parameter of the single test item and the score of the single test item, and sequencing the evaluation parameter of the single test item from strong to weak according to the correlation;
Summarizing the weight assignment of the evaluation parameters of the single test items according to the correlation analysis result and expert experience;
Weighting and summing the evaluation parameters of the single test item according to the obtained weight to obtain a single test item score;
weighting and summing all the single test items according to the set test item weight to obtain the comprehensive score of the test item dimension;
And obtaining the grade of the dimension of the test item according to the set score grade interval of the comprehensive score.
Further, the step of comprehensive scoring of the exercise grade is as follows:
The multiple experts respectively score the single movement grades of all testers, calculate the average score of each single movement grade and take the average score as a single movement grade score;
Establishing a regression model between the evaluation parameters of the test content contained in the single exercise grade and the single exercise grade score by adopting a plurality of regression modes, and selecting the regression model with optimal performance as a final regression model;
inputting the evaluation parameter quantized value of the test content contained in the single motion level into a final regression model to obtain the score of each motion level;
weighting and summing all the single motion grades according to the set motion grade weight to obtain the comprehensive score of the motion grade dimension;
and obtaining the level of the motion level dimension according to the set score level interval of the comprehensive score.
Further, the specific steps of integrating the plurality of comprehensive scores are as follows:
Counting all grade results contained in the dimension type of the exercise function evaluation, and selecting the grade result with the highest number of votes as a final evaluation grade by adopting a voting mechanism;
When the voting numbers are consistent, taking comprehensive scores Si (i is more than or equal to 2) of different motion function evaluation dimension types, normalizing to obtain corresponding statistical accuracy Pi (i is more than or equal to 2), distributing method weights Ui (i is more than or equal to 2) according to different motion function evaluation dimension types, calculating the comprehensive scores by weighted summation, and obtaining final score grades according to a preset score interval.
Based on the same innovation, the invention also provides a comprehensive evaluation system for the human body movement function, which comprises
The voice guidance module can guide a tester to finish the test content of the designed multidimensional movement index in a voice manner;
The acquisition module can acquire the original data of the test content completed by the tester;
The data processing module is capable of analyzing and processing the input original data of the acquisition module and calculating a parameter quantization value of an evaluation parameter of the test content;
The multi-dimensional evaluation module can classify the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types, and comprehensively score evaluation parameter quantized values of the exercise function evaluation dimension types;
the comprehensive evaluation module can perform comprehensive evaluation calculation on a plurality of comprehensive scores of the multi-dimensional evaluation module and output a final evaluation result.
The beneficial effects are that: compared with the prior art, the invention has the following remarkable advantages: the reliability and the interpretability of the comprehensive evaluation result are high, the evaluation parameter types are divided, different calculation methods are adopted for different parameter types, the grading of the sport function is carried out from a plurality of dimensions, and a plurality of grading results are integrated based on a voting mechanism and a statistics accuracy, so that a final sport function grade is obtained; the comprehensive evaluation result is attached to the human motion scientific knowledge, and the functional problem evaluation not only considers the relation between the functional problem and the evaluation parameters, but also considers the dependency relation between different evaluation parameters.
Drawings
FIG. 1 is a schematic diagram of the method of the present invention.
Fig. 2 is a timing chart of the right take-off foot rotation angle of embodiment 1 of the present invention.
Fig. 3 is a timing chart of the rotation angle of the right landing foot of embodiment 1 of the present invention.
Fig. 4 is a timing chart of the angle between the coronal planes of the spinal column according to embodiment 1 of the present invention.
Fig. 5 is a timing chart of the right shoulder buckling angle of example 1 of the present invention.
Fig. 6 is a schematic diagram of the system of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
Example 1
The invention relates to a comprehensive evaluation method for human body movement functions, which comprises the following steps,
(1) Designing test contents for testing multi-dimensional motion indexes; based on sports medical expertise, test content design is carried out, and multidimensional movement indexes are evaluated by fewer movements and measurement items, wherein the test content comprises a breathing mode and a heart rate of a tester, wherein both hands pass through a top and back, a vertical body bends forward and touches the ground, a vertical hand rotates, both hands pass through a top and deep squat, a freehand bow and arrow walk swivel, a back stride swallow balance, an in-situ longitudinal jump, a retractive run, a bear climb.
(2) And collecting test data, and obtaining the original data of the test content completed by the tester.
(3) Preprocessing the original data, wherein the preprocessing comprises data filtering, key moment identification, action moment identification and joint point coordinate extraction, and the evaluation parameters of the test contents of the testers are obtained after the preprocessing.
(4) Classifying the evaluation parameters of all the test contents according to the investigation contents to obtain a plurality of evaluation parameter types, and obtaining the calculated values of the corresponding evaluation parameters according to the parameter types. Specifically, the evaluation parameter classification table is shown in table 1 below:
TABLE 1
Specifically, the evaluation parameter types include:
The single-moment extremum type parameter is used for examining the fixed point capability of a tester at a certain moment in the process of completing the test content; the calculation method is as follows: first, a time T i is determined according to a setting condition, and a calculated value corresponding to the time Ti is calculated. Where T i is typically the time of a fixation or time of the joint of the tester reaching the designated site.
Taking the calculation of the rotation angle of the right jump foot and the rotation angle of the right landing foot for in-situ longitudinal jump as an example, the rotation angle of the right landing foot refers to the projection included angle of the right knee, the right ankle and the right heel, the right toe on the opposite crown surface at the landing moment, and the calculation steps are as follows:
Judging the starting time: the first frame in which the z value of the left toe increases continuously by 5 frames and the first frame in which the z value of the right toe increases continuously by 5 frames are calculated, and the larger frame number of the two frame numbers is the take-off time, and as shown in fig. 2, the take-off frame calculated by the left toe is 61, and the take-off frame calculated by the right toe is 62, so the take-off time frame is 62.
Judging the landing time: and calculating a first frame with the z value of the left toe less than or equal to the z value of the right toe at the jump time plus 1cm and a first frame with the z value of the right toe less than or equal to the z value of the right toe at the jump time plus 1cm after the jump time, wherein the smaller frame number of the two frame numbers is the landing time. As shown in fig. 3, the landing frame calculated by the left toe is 77, and the landing frame calculated by the right toe is 76, so the landing time frame is 76.
And calculating the rotation angle of the right foot during the jump frame and the landing frame in such a way that the included angles of the right knee-right foot connecting line and the right heel-right toe connecting line on the coronal plane are calculated as 125.76 degrees and 151.39 degrees.
The process characterization type parameter is used for examining the reaction capability of a tester in the process of completing the test content; the calculation method is as follows: the characterization data in the time of the start-stop moments T 1start and T 1end,T1start to T 1end of the calculation time are determined according to the setting conditions, and are the calculated values of the parameters. The characterization parameters can be peak value, fluctuation interval and fluctuation recovery time, and the specific characterization parameter selection can be selected according to actual test conditions.
Taking calculation of spine left-right swing of the double hands over the top deep squat as an example, the spine left-right swing refers to the included angle of the spine on the coronal plane of the human body relative to the spine of the action initial frame in the whole process of the double hands over the top deep squat, and the calculation steps are as follows:
Firstly, calculating xyz direction vectors of a human body relative system consisting of a sagittal plane, a coronal plane and a horizontal plane of the human body, taking absolute upward as a Z axis, taking projection vectors of two shoulder connecting lines of a first frame of data on the horizontal plane as X axes, and carrying out cross multiplication to obtain a relative system Y axis, wherein the two shoulder coordinates of the first frame of the data of the example are (-29.3305, -5.2257,148.9221), (0.689, -7.5387, 148.3796), the projection vectors on the horizontal plane are (30.0195, -2.3130000000000006, 0), namely the relative system X axis direction vectors, the relative system Z axis direction vectors are (0, 1), and the relative system three direction unit directions are X (0.99704481, -0.07682222, 0), Y (0.07682222, 0.99704481, 0) and Z (0, 1).
And calculating a start-stop frame of the squatting action, wherein the start condition is a first frame with a hip center z coordinate reduced by 5 frames continuously, the end frame is a frame corresponding to the minimum value of the hip center z coordinate, the calculated start frame is a 45 th frame, and the end frame is a 96 th frame.
The characteristic parameters used in the example are the data integral values exceeding the fluctuation area, the allowable fluctuation interval is-1.5, as shown in fig. 4, the change condition of the included angle of the coronal surface of the spine during the action, and the included angle of the coronal surface of the spine is known to be in the allowable fluctuation interval range, the data integral value exceeding the fluctuation area is 0, namely the calculated value of the left-right swing characteristic quantity of the spine with both hands over the top deep squatting is 0.
The process extremum type parameter is used for examining the limit capability of a tester in the process of completing the test content; the calculation method is as follows: the extremum in the time T 2start and T 2end,T2start to T 2end, which are the test contents, is obtained first, and then the calculated value of the parameter is obtained.
Taking calculation of right shoulder buckling angle of back bending of both hands through the top as an example, the right shoulder buckling angle refers to an included angle between a right shoulder right elbow connecting line and the spine on a human sagittal plane in the whole process of back bending of both hands through the top, and the calculation steps are as follows:
Firstly, calculating xyz direction vectors of a human body relative system consisting of a sagittal plane, a coronal plane and a horizontal plane of the human body, taking absolute upward as a Z axis, taking projection vectors of two shoulder connecting lines of a first frame of data on the horizontal plane as X axes, and carrying out cross multiplication to obtain a relative system Y axis, wherein the two shoulder coordinates of the first frame of the data of the example are (-19.0828, -0.4878, 140.4878), (15.9198, -2.722, 140.1941), the projection vectors on the horizontal plane are (35.0026, -2.2342, 0), namely the relative system X axis direction vectors, the relative system Z axis direction vectors are (0, 1), and calculating relative system three direction unit directions are X (0.9979691, -0.06369991, 0), Y (0.06369991, 0.9979691, 0), and Z (0, 0).
And converting the joint point coordinates required for calculating the right shoulder buckling angle to a relative system.
The right shoulder flexion angle of each frame of data was calculated as shown in fig. 5.
The right shoulder buckling angle of the back bending of the two hands after passing the top is the maximum value of the right shoulder buckling angle in the whole process, namely the calculated angle is 200.77133355583297 degrees.
(5) Quantizing the evaluation parameters according to the calculated values to obtain quantized values of the evaluation parameters; the specific evaluation parameters were quantified as follows:
Setting score grades L 1 、L2 、…、Lm, wherein each score grade corresponds to an evaluation parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the evaluation parameters, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value u and standard deviation sigma of the evaluation parameters of a plurality of testers;
Setting a quantization threshold value of each evaluation parameter of each test content, wherein 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, the quantization threshold values X 1 and X m+1 are determined according to expert experience, and the calculated values of the evaluation parameters are mapped to the corresponding quantization intervals to obtain the quantized values of the evaluation parameters corresponding to the quantization thresholds; the formula for X m is as follows:
X m=u+(Zm-1)* σ,Zm-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.
(6) Classifying the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types, and comprehensively scoring evaluation parameter quantized values of the exercise function evaluation dimension types; the athletic performance assessment dimension type comprises a functional question item, a test item and an athletic performance level, wherein the functional question item comprises flexibility, stability, action mode and physical stamina of a tester, the test item comprises all single test contents, and the athletic performance level comprises athletic ability, athletic function and athletic performance. The test content corresponds to a classification table of different exercise function assessment dimensions, as shown in table 2 below:
TABLE 2
(6A) The comprehensive scoring steps of the functional problem items are as follows:
And (3) scoring the single-function questions of all testers by a plurality of experts, calculating average score of each single-function question and taking the average score as a corresponding single-function question score.
And constructing a factor graph evaluation model between the functional problem and the evaluation parameters, wherein the functional problem and the evaluation parameters are connected by adopting a Bayesian network, and each evaluation parameter is connected by adopting a Markov network. And constructing a Bayesian network structure by using a genetic variation algorithm, and learning the Markov network structure based on the MRF by using the relation between the parameter child nodes and the action scoring nodes as priori knowledge. The method mainly comprises the following steps:
① The score node is defined as a, and the parameter child nodes are P1, P2,..pn.
② The probability distribution between the parameter child nodes and the action scoring nodes is denoted as P (a|p1, P2, pn), and the probability distribution between the parameter child nodes is denoted as P (P1, P2, pn).
③ Constructing a Bayesian network structure between the parameter child nodes and the action scoring nodes based on a genetic variation algorithm:
1) Initializing a population: randomly generating a plurality of network structures as an initial population;
2) Selection operation: selecting a network structure with high fitness to perform crossing and mutation operations;
3) Crossover and mutation: generating a new network structure through crossover and mutation operations;
4) Evaluating fitness: calculating the fitness of each network structure, namely the accuracy of the model;
5) Selecting the next generation: selecting a next generation network structure according to the adaptability;
6) Repeating the above steps until convergence.
④ The relationship between the parameter child nodes and the action scoring nodes is used as priori knowledge, and the Markov network structure is learned based on the MRF:
1) Initializing a Markov network structure;
2) Updating the Markov network structure according to the relation and priori knowledge among the parameter sub-nodes;
3) Repeating the above steps until convergence.
And inputting the quantized value of the evaluation parameter into the constructed factor graph evaluation model to obtain the score of the single functional problem of the tester.
And carrying out weighted summation on the scores of all the single functional questions according to the set weights, and obtaining the comprehensive scores of the functional question item dimensions.
And obtaining the grade of the dimension of the functional problem item according to the set score grade interval of the comprehensive score.
(6B) The comprehensive scoring of the test items is as follows:
the method comprises the steps that multiple experts respectively score single test items of all testers, average score of each single test item is calculated, and the average score of each single test item is used as a single test item score;
Adopting a plurality of correlation analysis methods to analyze the correlation between the quantized value of the evaluation parameter of the single test item and the score of the single test item, and sequencing the evaluation parameter of the single test item from strong to weak according to the correlation;
Summarizing the weight assignment of the evaluation parameters of the single test items according to the correlation analysis result and expert experience; firstly, distributing parameter weights wi= [ W1, W2, ], and then, marking the importance of the parameters according to experience by an expert, distributing the parameter weights wi-z based on a hierarchical analysis method, and taking an average value to obtain a final parameter weight W=mean (W1, W2,.,. Wn, wi-z);
Weighting and summing the evaluation parameters of the single test item according to the obtained weight to obtain a single test item score;
weighting and summing all the single test items according to the set test item weight to obtain the comprehensive score of the test item dimension;
And obtaining the grade of the dimension of the test item according to the set score grade interval of the comprehensive score.
(6C) The comprehensive scoring of the exercise class is as follows:
The multiple experts respectively score the single movement grades of all testers, calculate the average score of each single movement grade and take the average score as a single movement grade score;
establishing a regression model between the evaluation parameters of the test content contained in the single exercise grade and the single exercise grade score by adopting a plurality of regression modes, and selecting the regression model with the optimal performance (highest accuracy) as a final regression model;
inputting the evaluation parameter quantized value of the test content contained in the single motion level into a final regression model to obtain the score of each motion level;
weighting and summing all the single motion grades according to the set motion grade weight to obtain the comprehensive score of the motion grade dimension;
and obtaining the level of the motion level dimension according to the set score level interval of the comprehensive score.
(7) And integrating the comprehensive scores to obtain a final evaluation result.
The specific steps for integrating the multiple comprehensive scores are as follows:
Counting all grade results contained in the dimension type of the exercise function evaluation, and selecting the grade result with the highest number of votes as a final evaluation grade by adopting a voting mechanism;
when the voting numbers are consistent, taking comprehensive scores Si (i is more than or equal to 2) of different motion function evaluation dimension types, normalizing to obtain corresponding statistical accuracy Pi (i is more than or equal to 2), wherein the evaluation accuracy of the different motion function evaluation dimension types is initially set to be 0, counting the accuracy of the different motion function evaluation dimension types in the follow-up process, continuously updating the statistical accuracy along with application, distributing method weights Ui (i is more than or equal to 2) according to the accuracy of the different motion function evaluation dimension types, calculating the comprehensive scores by weighted summation, and obtaining final score grades according to a preset score interval.
Example 2
The invention relates to a comprehensive evaluation system for human body movement functions, which comprises a voice guidance module, an acquisition module, a data processing module, a multidimensional evaluation module and a comprehensive evaluation module.
The voice guidance module can guide a tester to finish the designed test content of the multidimensional movement index, the test content is designed based on the professional knowledge of sports medicine, the purpose of the voice guidance module is to carry out multidimensional movement assessment by a small amount of movement, and the test content comprises a double-hand top-over back-leaning, a vertical body front-bending ground contact, a vertical free-hand rotation, a double-hand top-over deep squatting, a free-hand bow-and-arrow walking swivel, a back-stepping swallow balance, an in-situ longitudinal jump, a retractive running, a bear climbing, and heart rate and breathing modes of the tester.
And the acquisition module can acquire the original data of the test content completed by the tester.
The data processing module is capable of analyzing and processing the input original data of the acquisition module, the acquisition module carries out data filtering, key moment identification, action moment identification and joint point coordinate extraction on the original data to obtain moment data and joint coordinate data of the test content of a tester, and parameter quantization values of evaluation parameters of the test content are calculated; in order to facilitate parameter quantification, the evaluation parameters of all the test contents are classified according to the investigation contents, so as to obtain various evaluation parameter types, and the calculated values of the corresponding evaluation parameters are obtained according to the parameter types. The specific evaluation parameters are classified and calculated as follows:
The single-moment extremum type parameter is used for examining the fixed point capability of a tester at a certain moment in the process of completing the test content; the calculation method is as follows: first, a time T i is determined according to a setting condition, and a calculated value corresponding to the time Ti is calculated. Where Ti is typically some fixed time or time at which the tester's joint reaches a specified site.
The process characterization type parameter is used for examining the reaction capability of a tester in the process of completing the test content; the calculation method is as follows: the characterization data in the time of the start-stop moments T 1start and T 1end,T1start to T 1end of the calculation time are determined according to the setting conditions, and are the calculated values of the parameters. The characterization parameters can be peak value, fluctuation interval and fluctuation recovery time, and the specific characterization parameter selection can be selected according to actual test conditions.
The process extremum type parameter is used for examining the limit capability of a tester in the process of completing the test content; the calculation method is as follows: the extremum in the time T 2start and T 2end,T2start to T 2end, which are the test contents, is obtained first, and then the calculated value of the parameter is obtained.
After the calculated value of the parameter is obtained, the evaluation parameter is quantized according to the calculated value, namely the quantized value of the evaluation parameter is obtained, and the specific quantization mode of the evaluation parameter is as follows: setting score grades L 1 、L2 、…、Lm, wherein each score grade corresponds to an evaluation parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the evaluation parameters, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value u and standard deviation sigma of the evaluation parameters of a plurality of testers;
Setting a quantization threshold value of each evaluation parameter of each test content, wherein 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, the quantization threshold values X 1 and X m+1 are determined according to expert experience, and the calculated values of the evaluation parameters are mapped to the corresponding quantization intervals to obtain the quantized values of the evaluation parameters corresponding to the quantization thresholds; the formula for X m is as follows:
X m=u+(Zm-1)* σ,Zm-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.
The multidimensional evaluation module can classify the test content according to the athletic performance evaluation dimension to obtain a plurality of athletic performance evaluation dimension types, and comprehensively score evaluation parameter quantized values of the athletic performance evaluation dimension types. Multiple exercise function assessment dimension types can assess the exercise function of the tester from different dimensions, and the narrowness caused by single-dimension assessment can be avoided.
The athletic performance assessment dimension types include a functional question item, a test item, and an athletic performance level, wherein the functional question item includes a tester's flexibility, stability, motion patterns, and physical stamina, the test item includes all individual test content, and the athletic performance level includes athletic performance, and athletic performance.
The comprehensive scoring steps of the functional problem items are as follows:
the multiple experts score the single functional questions of all testers respectively, calculate the average score of each single functional question and take the average score as the score of the corresponding single functional question;
Constructing a factor graph evaluation model between the functional problem and the evaluation parameters, wherein the functional problem and the evaluation parameters are connected by adopting a Bayesian network, and each evaluation parameter is connected by adopting a Markov network;
Inputting the quantized value of the evaluation parameter into a constructed factor graph evaluation model to obtain the score of the single functional problem of the tester;
weighting and summing the scores of all the single functional questions according to the set weights to obtain the comprehensive scores of the functional question item dimensions;
And obtaining the grade of the dimension of the functional problem item according to the set score grade interval of the comprehensive score.
The comprehensive scoring of the test items is as follows:
the method comprises the steps that multiple experts respectively score single test items of all testers, average score of each single test item is calculated, and the average score of each single test item is used as a single test item score;
Adopting a plurality of correlation analysis methods to analyze the correlation between the quantized value of the evaluation parameter of the single test item and the score of the single test item, and sequencing the evaluation parameter of the single test item from strong to weak according to the correlation;
Summarizing the weight assignment of the evaluation parameters of the single test items according to the correlation analysis result and expert experience; firstly, distributing parameter weights wi= [ W1, W2, ], and then, marking the importance of the parameters according to experience by an expert, distributing the parameter weights wi-z based on a hierarchical analysis method, and taking an average value to obtain a final parameter weight W=mean (W1, W2,.,. Wn, wi-z);
Weighting and summing the evaluation parameters of the single test item according to the obtained weight to obtain a single test item score;
weighting and summing all the single test items according to the set test item weight to obtain the comprehensive score of the test item dimension;
And obtaining the grade of the dimension of the test item according to the set score grade interval of the comprehensive score.
The comprehensive scoring of the exercise class is as follows:
The multiple experts respectively score the single movement grades of all testers, calculate the average score of each single movement grade and take the average score as a single movement grade score;
Establishing a regression model between the evaluation parameters of the test content contained in the single exercise grade and the single exercise grade score by adopting a plurality of regression modes, and selecting the regression model with optimal performance as a final regression model;
inputting the evaluation parameter quantized value of the test content contained in the single motion level into a final regression model to obtain the score of each motion level;
weighting and summing all the single motion grades according to the set motion grade weight to obtain the comprehensive score of the motion grade dimension;
and obtaining the level of the motion level dimension according to the set score level interval of the comprehensive score.
The comprehensive evaluation module can perform comprehensive evaluation calculation on a plurality of comprehensive scores of the multi-dimensional evaluation module and output a final evaluation result. The method comprises the following specific steps: counting all grade results contained in the dimension type of the exercise function evaluation, and selecting the grade result with the highest number of votes as a final evaluation grade by adopting a voting mechanism;
when the voting numbers are consistent, taking comprehensive scores Si (i is more than or equal to 2) of different motion function evaluation dimension types, normalizing to obtain corresponding statistical accuracy Pi (i is more than or equal to 2), wherein the evaluation accuracy of the different motion function evaluation dimension types is initially set to be 0, counting the accuracy of the different motion function evaluation dimension types in the follow-up process, continuously updating the statistical accuracy along with application, distributing method weights Ui (i is more than or equal to 2) according to the accuracy of the different motion function evaluation dimension types, calculating the comprehensive scores by weighted summation, and obtaining final score grades according to a preset score interval.
Claims (5)
1. A comprehensive evaluation method for human body movement functions is characterized in that: comprises the steps of,
Designing test contents for testing multi-dimensional motion indexes;
Collecting test data, and obtaining original data of test contents completed by a tester;
Preprocessing the original data to obtain evaluation parameters of the test contents completed by a tester;
Classifying the evaluation parameters of all the test contents according to the investigation contents to obtain a plurality of evaluation parameter types, and obtaining the calculated values of the corresponding evaluation parameters according to the parameter types; wherein the evaluating parameter types includes: the single-moment extremum type parameter is used for examining the fixed point capability of a tester at a certain moment in the process of completing the test content; the process characterization type parameter is used for examining the reaction capability of a tester in the process of completing the test content; the process extremum type parameter is used for examining the limit capability of a tester in the process of completing the test content;
The specific calculation modes of the calculated values of the various evaluation parameter types are as follows:
The single-time extremum type parameter is firstly determined at time T i according to the setting condition, and a calculated value corresponding to time T i is calculated;
The process characterization type parameter is characterized in that firstly, the starting and ending time T 1start and characterization data in the time from T 1end,T1start to T 1end of the calculation time are determined according to the setting condition, and then the characterization data are calculated values of the parameter;
The process extremum type parameter is obtained firstly, and the extremum in the time from T 2start and T 2end,T2start to T 2end for completing certain test content is the calculated value of the parameter;
Quantizing the evaluation parameters according to the calculated values to obtain quantized values of the evaluation parameters;
the specific calculation mode for quantifying the evaluation parameters is as follows:
Setting score grades L 1、L2、…、Lm, wherein each score grade corresponds to an evaluation parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the evaluation parameters, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value u and standard deviation sigma of the evaluation parameters of a plurality of testers;
Setting a quantization threshold value of each evaluation parameter of each test content, wherein 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, the quantization threshold values X 1 and X m+1 are determined according to expert experience, and the calculated values of the evaluation parameters are mapped to the corresponding quantization intervals to obtain the quantized values of the evaluation parameters corresponding to the quantization thresholds; the formula for X m is as follows:
X m＝u+(Zm-1)*σ,Zm-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 ] sequentially corresponds to the parameter quantization value Y m、…、Y1;
Classifying the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types, and comprehensively scoring evaluation parameter quantized values of the exercise function evaluation dimension types; the exercise function evaluation dimension type comprises a function problem item, a test item and an exercise grade, wherein the function problem item comprises flexibility, stability, action mode and physical ability of a tester, the test item comprises all single test contents, and the exercise grade comprises exercise capacity, exercise function and exercise performance;
integrating the comprehensive scores to obtain a final evaluation result;
the specific steps for integrating the multiple comprehensive scores are as follows:
Counting all grade results contained in the dimension type of the exercise function evaluation, and selecting the grade result with the highest number of votes as a final evaluation grade by adopting a voting mechanism;
When the voting numbers are consistent, the comprehensive scores Si of different motion function evaluation dimension types are taken for normalization, the corresponding statistical accuracy Pi is obtained, the method weights Ui are distributed according to the different motion function evaluation dimension types, the comprehensive scores are calculated through weighted summation, and the final score grade is obtained according to a preset score interval, wherein i is more than or equal to 2.
2. The comprehensive assessment method for human motor functions according to claim 1, wherein: the comprehensive scoring steps of the functional problem items are as follows:
the multiple experts score the single functional questions of all testers respectively, calculate the average score of each single functional question and take the average score as the score of the corresponding single functional question;
Constructing a factor graph evaluation model between the functional problem and the evaluation parameters, wherein the functional problem and the evaluation parameters are connected by adopting a Bayesian network, and each evaluation parameter is connected by adopting a Markov network;
Inputting the quantized value of the evaluation parameter into a constructed factor graph evaluation model to obtain the score of the single functional problem of the tester;
weighting and summing the scores of all the single functional questions according to the set weights to obtain the comprehensive scores of the functional question item dimensions;
And obtaining the grade of the dimension of the functional problem item according to the set score grade interval of the comprehensive score.
3. The comprehensive assessment method for human motor functions according to claim 1, wherein: the comprehensive scoring steps of the test items are as follows:
the method comprises the steps that multiple experts respectively score single test items of all testers, average score of each single test item is calculated, and the average score of each single test item is used as a single test item score;
Adopting a plurality of correlation analysis methods to analyze the correlation between the quantized value of the evaluation parameter of the single test item and the score of the single test item, and sequencing the evaluation parameter of the single test item from strong to weak according to the correlation;
Summarizing the weight assignment of the evaluation parameters of the single test items according to the correlation analysis result and expert experience;
Weighting and summing the evaluation parameters of the single test item according to the obtained weight to obtain a single test item score;
weighting and summing all the single test items according to the set test item weight to obtain the comprehensive score of the test item dimension;
And obtaining the grade of the dimension of the test item according to the set score grade interval of the comprehensive score.
4. The comprehensive assessment method for human motor functions according to claim 1, wherein: the comprehensive scoring of the exercise grade comprises the following steps:
The multiple experts respectively score the single movement grades of all testers, calculate the average score of each single movement grade and take the average score as a single movement grade score;
Establishing a regression model between the evaluation parameters of the test content contained in the single exercise grade and the single exercise grade score by adopting a plurality of regression modes, and selecting the regression model with optimal performance as a final regression model;
inputting the evaluation parameter quantized value of the test content contained in the single motion level into a final regression model to obtain the score of each motion level;
weighting and summing all the single motion grades according to the set motion grade weight to obtain the comprehensive score of the motion grade dimension;
and obtaining the level of the motion level dimension according to the set score level interval of the comprehensive score.
5. A human motion function comprehensive evaluation system is characterized in that: comprising
The voice guidance module can guide a tester to finish the test content of the designed multidimensional movement index in a voice manner;
The acquisition module can acquire the original data of the test content completed by the tester;
The data processing module is capable of analyzing and processing the input original data of the acquisition module and calculating a parameter quantization value of an evaluation parameter of the test content; classifying the evaluation parameters of all the test contents according to the investigation contents to obtain a plurality of evaluation parameter types, and obtaining the calculated values of the corresponding evaluation parameters according to the parameter types; wherein the evaluating parameter types includes: the single-moment extremum type parameter is used for examining the fixed point capability of a tester at a certain moment in the process of completing the test content; the process characterization type parameter is used for examining the reaction capability of a tester in the process of completing the test content; the process extremum type parameter is used for examining the limit capability of a tester in the process of completing the test content;
The specific calculation modes of the calculated values of the various evaluation parameter types are as follows:
The single-time extremum type parameter is firstly determined at time T i according to the setting condition, and a calculated value corresponding to time T i is calculated;
The process characterization type parameter is characterized in that firstly, the starting and ending time T 1start and characterization data in the time from T 1end,T1start to T 1end of the calculation time are determined according to the setting condition, and then the characterization data are calculated values of the parameter;
The process extremum type parameter is obtained firstly, and the extremum in the time from T 2start and T 2end,T2start to T 2end for completing certain test content is the calculated value of the parameter;
Quantizing the evaluation parameters according to the calculated values to obtain quantized values of the evaluation parameters;
the specific calculation mode for quantifying the evaluation parameters is as follows:
Setting score grades L 1、L2、…、Lm, wherein each score grade corresponds to an evaluation parameter quantized value Y 1、Y2、…、Ym, dividing the proportion of each grade according to the evaluation parameters, calculating a corresponding accumulated data duty ratio P 1、P2、…、Pm-1, and calculating the mean value u and standard deviation sigma of the evaluation parameters of a plurality of testers;
Setting a quantization threshold value of each evaluation parameter of each test content, wherein 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, the quantization threshold values X 1 and X m+1 are determined according to expert experience, and the calculated values of the evaluation parameters are mapped to the corresponding quantization intervals to obtain the quantized values of the evaluation parameters corresponding to the quantization thresholds; the formula for X m is as follows:
X m＝u+(Zm-1)*σ,Zm-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 ] sequentially corresponds to the parameter quantization value Y m、…、Y1;
The multi-dimensional evaluation module can classify the test content according to the exercise function evaluation dimension to obtain a plurality of exercise function evaluation dimension types, and comprehensively score evaluation parameter quantized values of the exercise function evaluation dimension types; the exercise function evaluation dimension type comprises a function problem item, a test item and an exercise grade, wherein the function problem item comprises flexibility, stability, action mode and physical ability of a tester, the test item comprises all single test contents, and the exercise grade comprises exercise capacity, exercise function and exercise performance;
the comprehensive evaluation module can perform comprehensive evaluation calculation on a plurality of comprehensive scores of the multi-dimensional evaluation module and output a final evaluation result; the specific steps of the comprehensive evaluation calculation of the comprehensive scores are as follows:
Counting all grade results contained in the dimension type of the exercise function evaluation, and selecting the grade result with the highest number of votes as a final evaluation grade by adopting a voting mechanism;
When the voting numbers are consistent, the comprehensive scores Si of different motion function evaluation dimension types are taken for normalization, the corresponding statistical accuracy Pi is obtained, the method weights Ui are distributed according to the different motion function evaluation dimension types, the comprehensive scores are calculated through weighted summation, and the final score grade is obtained according to a preset score interval, wherein i is more than or equal to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410420075.9A CN118039068B (en) | 2024-04-09 | 2024-04-09 | Comprehensive evaluation method and system for human body movement function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410420075.9A CN118039068B (en) | 2024-04-09 | 2024-04-09 | Comprehensive evaluation method and system for human body movement function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118039068A CN118039068A (en) | 2024-05-14 |
| CN118039068B true CN118039068B (en) | 2024-07-19 |
Family
ID=90995459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410420075.9A Active CN118039068B (en) | 2024-04-09 | 2024-04-09 | Comprehensive evaluation method and system for human body movement function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118039068B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725509A (en) * | 2016-12-15 | 2017-05-31 | 佛山科学技术学院 | Motor function comprehensive estimation method based on patients with cerebral apoplexy |
| CN112244774A (en) * | 2020-10-19 | 2021-01-22 | 西安臻泰智能科技有限公司 | Brain-computer interface rehabilitation training system and method |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1987007969A2 (en) * | 1986-06-23 | 1987-12-30 | Board Of Regents, The University Of Texas System | Computer automated sensory and motor function assessment |
| US20060147947A1 (en) * | 2002-12-04 | 2006-07-06 | Javier Apfeld | AMPK pathway components |
| US20130253375A1 (en) * | 2012-03-21 | 2013-09-26 | Henry Nardus Dreifus | Automated Method Of Detecting Neuromuscular Performance And Comparative Measurement Of Health Factors |
| WO2014081442A1 (en) * | 2012-11-20 | 2014-05-30 | Nike International Ltd. | Golf athleticism rating system |
| JP6183827B2 (en) * | 2013-03-14 | 2017-08-23 | 株式会社タニタ | Motor function evaluation apparatus and motor function evaluation method |
| CN108665956A (en) * | 2018-06-05 | 2018-10-16 | 陈燕 | The integrated estimation system and method for physical efficiency and muscle performance |
| KR101959079B1 (en) * | 2018-10-08 | 2019-03-18 | 주식회사 마이베네핏 | Method for measuring and evaluating body performance of user |
| CN110732130A (en) * | 2019-10-11 | 2020-01-31 | 苏州菠萝健康科技有限公司 | physical rehabilitation training process and action quality evaluation method |
| JP2024021088A (en) * | 2020-10-02 | 2024-02-16 | オリジン ワイヤレス， インコーポレイテッド | Method, apparatus and system for wireless monitoring to ensure security |
| CN114711754A (en) * | 2021-01-04 | 2022-07-08 | 深圳职业技术学院 | Motion evaluation method, system, device and computer readable storage medium |
| CN114203274B (en) * | 2021-12-14 | 2024-08-23 | 浙江大学 | Remote rehabilitation training guidance system for chronic respiratory failure patient |
| CN114403858B (en) * | 2021-12-29 | 2023-10-03 | 杭州程天科技发展有限公司 | Human body movement function assessment method, device and system |
| CN115067934A (en) * | 2022-06-16 | 2022-09-20 | 上海大学 | Hand motion function analysis system based on machine intelligence |
| CN116616729A (en) * | 2023-05-22 | 2023-08-22 | 趣动未来(深圳)科技有限公司 | Digital healthy body fitness test method |
-
2024
- 2024-04-09 CN CN202410420075.9A patent/CN118039068B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725509A (en) * | 2016-12-15 | 2017-05-31 | 佛山科学技术学院 | Motor function comprehensive estimation method based on patients with cerebral apoplexy |
| CN112244774A (en) * | 2020-10-19 | 2021-01-22 | 西安臻泰智能科技有限公司 | Brain-computer interface rehabilitation training system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118039068A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110322947B (en) | Hypertension elderly exercise prescription recommendation method based on deep learning | |
| Karg et al. | Human movement analysis as a measure for fatigue: A hidden Markov-based approach | |
| CN105615890A (en) | Angle and myoelectricity continuous decoding method for human body lower limb walking joint | |
| US20170027501A1 (en) | Realtime biofeedback mechanism and data presentation for knee injury rehabilitation monitoring and a soft real time intelligent system thereof | |
| Tang | Hybridized hierarchical deep convolutional neural network for sports rehabilitation exercises | |
| CN102438519A (en) | Characterization of physical abilities by motion analysis | |
| CN114822763A (en) | Personalized exercise prescription recommendation method driven by exercise data | |
| CN110570946A (en) | Lower limb rehabilitation robot rehabilitation training motor function rehabilitation evaluation method | |
| CN113974612A (en) | Automatic assessment method and system for upper limb movement function of stroke patient | |
| CN115837147B (en) | Scene interactive lower limb muscle strengthening training method and system | |
| CN118039068B (en) | Comprehensive evaluation method and system for human body movement function | |
| CN109009148A (en) | A kind of gait function appraisal procedure | |
| CN108985278A (en) | A kind of construction method of the gait function assessment models based on svm | |
| CN117666788B (en) | Action recognition method and system based on wearable interaction equipment | |
| CN117653084A (en) | Method for evaluating scoliosis rehabilitation state by using gait | |
| CN106407706A (en) | Boruta algorithm-based multi-level old people physical state quantization level calculation method | |
| Mack et al. | Movement prototypes and their relationship in the performance of a gymnastics floor routine | |
| CN116747495A (en) | Action counting method and device, terminal equipment and readable storage medium | |
| CN108877931A (en) | Shoulder rehabilitation evaluation method, apparatus and system | |
| CN114171194B (en) | Quantitative assessment method, device, electronic device and medium for Parkinson multiple symptoms | |
| CN115147768A (en) | Fall risk assessment method and system | |
| KR102570665B1 (en) | CNN-based exercise intensity classification system using pulse waves | |
| CN115565639A (en) | Exercise heart rate prediction method, device and equipment | |
| CN114642424A (en) | Physical ability assessment method and device based on somatosensory interaction technology | |
| CN118016241B (en) | Human body movement function assessment and correction training method and 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 | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No.2 Huaxia West Road, Jianxi District, Luoyang City, Henan Province Patentee after: THE 989 HOSPITAL OF THE PEOPLE'S LIBERATION ARMY JOINT SERVICE SUPPORT FORCE Country or region after: China Patentee after: NANJING KANGNI MECHANICAL & ELECTRICAL Co.,Ltd. Address before: 210038 No. 19 Hengda Road, Nanjing economic and Technological Development Zone, Jiangsu, China Patentee before: NANJING KANGNI MECHANICAL & ELECTRICAL Co.,Ltd. Country or region before: China Patentee before: THE 989 HOSPITAL OF THE PEOPLE'S LIBERATION ARMY JOINT SERVICE SUPPORT FORCE |