A method and device for testing standing human balance ability

Abstract

The present invention discloses a standing human balance ability test method and test device, which relates to the technical field related to data processing. The method includes: clustering adolescent groups according to morphological features to determine multiple target groups and multiple group center features; determining a first associated motion set; obtaining a first motion qualified indicator set of the first associated motion set; determining a first adaptation test scalar based on the constraint of satisfying the first motion qualified indicator set; sequentially analyzing and obtaining multiple adaptation test scalar sets, integrating and generating multiple adaptation test evaluation tables, and evaluating balance ability. The method solves the technical problem that the existing standing balance ability test often directly conducts static evaluation based on fixed indicators, does not consider individual feature differences and the impact on life, and thus leads to poor accuracy, reliability and practicality of the evaluation results, and achieves the technical effect of improving the accuracy, reliability and practicality of the balance ability test results.

Description

Technical Field

[0001] The present application relates to data processing technology-related fields, and specifically to a method and device for testing standing human balance ability. Background Art

[0002] The balance ability of the human body is the key ability of an individual to effectively control the body's center of gravity and maintain stability when standing, walking or other sports postures. Especially for adolescents, good balance ability is not only related to the coordination of daily activities, but also closely related to sports performance, rehabilitation training and physical health. However, the existing balance ability test methods are mostly based on fixed evaluation indicators and a single test type, which makes it difficult to fully consider the morphological differences and diversity of motor abilities among adolescents, resulting in weak universality and pertinence of the test results. In actual tests, since adolescents are in the growth and development period, their body shape, motor function and coordination have significant individual differences. The same evaluation method may not be able to adapt to the specific needs of different adolescent groups, which in turn affects the accuracy and scientificity of the test results. For example, smaller individuals may perform well in static balance tests due to their lower center of gravity, while larger individuals may find it difficult to achieve ideal results due to their unstable center of gravity. In addition, differences in exercise habits and muscle strength distribution among different groups will also have a significant impact on the test results.

[0003] Therefore, in the current standing balance ability test related technologies, there is a technical problem that static evaluation is often performed directly based on fixed indicators, without considering individual characteristic differences and the impact on life, which leads to poor accuracy, reliability and practicality of the evaluation results. Summary of the invention

[0004] The present application provides a standing human balance ability testing method and testing device, thereby solving the technical problem that the existing standing balance ability tests often directly conduct static evaluations based on fixed indicators, do not consider individual characteristic differences and the impact on life, and thus lead to poor accuracy, reliability and practicality of the evaluation results, thereby achieving the technical effect of improving the accuracy, reliability and practicality of the balance ability test results.

[0005] The present application provides a standing human balance ability test method, the method comprising: clustering a group of adolescents according to morphological features to determine multiple target groups and multiple group center features; reading multiple static balance test types, and randomly selecting a first balance test type, performing association matching in a motion type library according to the first balance test type, and determining a first associated motion set; randomly selecting a first group center feature, and obtaining a first motion qualification indicator set of the first associated motion set based on the first group center feature; subjecting the first motion qualification indicator set to a constraint, performing test indicator optimization analysis of the first balance test type according to the first group center feature, and determining a first adaptation test scalar; sequentially analyzing and obtaining multiple adaptation test scalar sets, integrating and generating multiple adaptation test evaluation tables, and performing balance ability evaluation on the static balance test data of the multiple target groups.

[0006] In a possible implementation, the youth group is clustered according to morphological features to determine multiple target groups and multiple group center features, and the following processing is performed: features of the youth group are collected according to predetermined feature indicators to obtain multiple morphological feature data sets; the multiple morphological feature data sets are clustered using the K-Means algorithm to obtain multiple feature clustering results; the youth group is mapped and divided according to the multiple feature clustering results to determine multiple target groups and multiple group center features, wherein the group center feature is the median value of the feature clustering results.

[0007] In a possible implementation, an association match is performed in a motion type library according to the first balance test type to determine a first associated motion set, and the following processing is performed: a first motion type is selected from the motion type library, and a first associated record data set is acquired based on big data retrieval with the first balance test type and the first motion type as constraints; based on the first associated record data set, an association degree analysis is performed on the first balance test type and the first motion type to determine a first association degree; if the first association degree is greater than a predetermined association threshold, the first motion type is added to the first associated motion set.

[0008] In a possible implementation, a first movement qualification indicator set of the first associated movement set is obtained based on the first group center feature, and the following processing is performed: any associated movement in the first associated movement set is randomly selected as a first movement type, and a first movement correlation degree of the first movement type is obtained; with the first group center feature and the first movement type as constraints, a positive sample retrieval is performed based on big data to obtain a first movement record data set; according to the first movement correlation degree, an initial qualification ratio is optimized to obtain a first standard qualification ratio, wherein the first standard qualification ratio is positively correlated with the first movement correlation degree; with the first standard qualification ratio as a constraint, a qualification indicator analysis is performed based on the first movement record data set to obtain a first movement qualification indicator, and add it to the first movement qualification indicator set.

[0009] In a possible implementation, with the first motion qualified indicator set as a constraint, the test indicator optimization analysis of the first balance test type is performed according to the first group center feature to determine the first adaptation test scalar, and the following processing is also performed: the first test indicator threshold of the first balance test type is obtained, and the first test data is randomly selected; with the first group center feature, the first balance test type and the first test data as constraints, multiple sample motion indicator sets are obtained based on big data retrieval, and high-frequency feature analysis is performed on the multiple sample motion indicator sets to determine multiple sample motion indicators; the multiple sample motion indicators are judged according to the first motion qualified indicator set, and if the multiple sample motion indicators are all greater than the multiple corresponding qualified indicators in the first motion qualified indicator set, the first test fitness is calculated according to the first motion qualified indicator set and the multiple sample motion indicators to obtain; using the first test indicator threshold, the test indicator optimization analysis is continued until the predetermined number of iterations is met, and the test data with the largest test fitness is output as the first adaptation test scalar.

[0010] In a possible implementation, a high-frequency feature analysis is performed on the multiple sample motion index sets to determine multiple sample motion indexes, and the following processing is also performed: a first sample motion index set is randomly selected, and the first index mean is calculated; based on the first index mean, deviations are calculated for the multiple first sample motion indexes in the first sample motion index set to obtain multiple first indicator deviation sets; the multiple first indicator deviation sets are screened according to a predetermined deviation threshold to determine multiple first standard motion indexes, and the first sample motion index is obtained after the mean is calculated, and added to the multiple sample motion indexes.

[0011] In a possible implementation, a first test fitness is calculated based on the first motion qualified indicator set and multiple sample motion indicators, and the following processing is further performed: influence weights are set according to multiple motion associations of the first motion qualified indicator set to obtain multiple indicator weights, wherein the indicator weights are positively correlated with the motion associations; and a test fitness evaluation function is constructed:

[0012] ;

[0013] in, is the test fitness, N is the number of indicators in the motion indicator set, is the index weight of the nth sports index, is the movement qualification index of the nth movement index, A sample motion index of the nth motion index; based on the test fitness evaluation function, the fitness of the first motion qualified index set and multiple sample motion indexes is calculated, and the first test fitness is output.

[0014] The present application also provides a standing human balance ability testing device, including: a target group determination module, which is used to cluster the youth group according to the morphological characteristics, determine multiple target groups, and multiple group center features; a first associated motion set determination module, which is used to read multiple static balance test types, and randomly select a first balance test type, perform association matching in the motion type library according to the first balance test type, and determine a first associated motion set; a first motion qualified indicator set acquisition module, which is used to randomly select the first group center feature, and obtain the first motion qualified indicator set of the first associated motion set based on the first group center feature; a first adaptation test scalar determination module, which is used to perform test indicator optimization analysis of the first balance test type according to the first group center feature with the first motion qualified indicator set as a constraint, and determine a first adaptation test scalar; a balance ability evaluation module, which is used to analyze and obtain multiple adaptation test scalar sets in sequence, integrate and generate multiple adaptation test evaluation tables, and evaluate the balance ability of the static balance test data of the multiple target groups.

[0015] The present application proposes a standing human balance ability test method and test device, which clusters the youth group according to the morphological characteristics, determines multiple target groups, and multiple group center features; determines the first associated motion set; obtains the first motion qualified indicator set of the first associated motion set; determines the first adaptation test scalar with the first motion qualified indicator set as a constraint; sequentially analyzes and obtains multiple adaptation test scalar sets, integrates and generates multiple adaptation test evaluation tables, and evaluates the balance ability. This solves the technical problem that the existing standing balance ability test often directly conducts static evaluation based on fixed indicators, does not consider individual feature differences and the impact on life, and thus leads to poor accuracy, reliability and practicality of the evaluation results, and achieves the technical effect of improving the accuracy, reliability and practicality of the balance ability test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0017] Figure 1 A schematic flow chart of a method for testing the balance ability of a standing human body provided in an embodiment of the present application;

[0018] Figure 2 A schematic structural diagram of a standing human balance ability testing device provided in an embodiment of the present application.

[0019] Explanation of the reference numerals: target group determination module 10 , first associated motion set determination module 20 , first motion qualification indicator set acquisition module 30 , first adaptation test scalar determination module 40 , balance ability evaluation module 50 . DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0023] The present application embodiment provides a method for testing the balance ability of a standing human body. Figure 1 As shown, the method includes:

[0024] Step S100, clustering the youth groups according to their morphological features, and determining a plurality of target groups and a plurality of group center features.

[0025] Preferably, the external physical characteristics (morphological characteristics) of the adolescent group are collected by standard measuring equipment (such as height and weight measuring instruments, three-dimensional scanners, etc.), and the group is classified and grouped using a clustering algorithm, so that individuals with similar morphological characteristics are divided into the same target group, and representative characteristics (central characteristics) are extracted for each group. Specifically, morphological characteristics refer to characteristic data of the adolescent individual in terms of external morphology such as body shape and posture, usually including body size (such as height, weight, shoulder width, leg length, etc.), proportional relationships (such as the ratio of height to leg length, the ratio of upper body to lower body, etc.), body characteristics, such as standing posture (stability of posture when standing, distribution of center of gravity), bone morphology (back curvature, spinal curvature), etc. , using these feature data as sample data, and using algorithms such as K-means (K-Means), density clustering (DBSCAN), hierarchical clustering, etc. to calculate the similarity between morphological features, and divide similar teenagers into the same target group according to morphological features. Using multidimensional data (such as height, weight, proportional relationship, etc.) as input, clustering is achieved through distance calculation in feature space, and multiple target groups are output. The teenagers in each group have a high degree of similarity in morphological features; then the central features of each group are determined to represent the basic features of this group, including the average values ​​of various morphological features in each target group (such as average height, average weight), and the distribution of each feature of each group, such as the maximum and minimum values ​​of leg length ratio.

[0026] Furthermore, step S100 also includes step S110, collecting features of the youth group according to predetermined feature indicators to obtain multiple morphological feature data sets; step S120, clustering the multiple morphological feature data sets using the K-Means algorithm to obtain multiple feature clustering results; step S130, mapping and dividing the youth group according to the multiple feature clustering results, determining multiple target groups and multiple group center features, wherein the group center feature is the median value of the feature clustering results.

[0027] Preferably, feature collection is performed on a group of adolescents according to predetermined feature indicators, wherein the predetermined feature indicators mainly refer to key parameters related to adolescent appearance, such as weight, height, height-to-weight ratio (BMI), upper and lower body proportions, etc., which reflect the balance and coordination of individual appearance. These data are collected by standardized measurement tools or automated equipment (such as measuring instruments or three-dimensional scanning equipment) to form a multidimensional data set as multiple morphological feature data sets; the multiple morphological feature data sets are clustered using a K-Means algorithm, wherein the K-Means clustering algorithm is used to divide the data set into K clusters, and the core steps include randomly selecting K points in the data set as initial cluster centers, assigning the points to the nearest center according to the Euclidean distance between each point and the cluster center, and recalculating the center of each cluster, usually clustering. The mean of all points in the class, repeat the above steps until the clustering result is stable (that is, the allocation of each point no longer changes, or reaches the preset maximum number of iterations), and obtain multiple clustering results, each cluster contains member data points (features of adolescents belonging to the cluster) and cluster center points (central features of the cluster, such as the mean of cluster member features); divide the target groups according to the clustering result mapping, that is, according to the clustering results, adolescents with similar morphological features are classified into the same target group, such as adolescents with taller height and heavier weight; adolescents with moderate height and lighter weight; adolescents with shorter height and heavier weight; each cluster corresponds to a target group, and the group members are highly similar in morphological features. The group center feature is the representative feature of each target group, usually represented by the cluster center point, that is, the median value (mean) of the cluster member features.

[0028] Step S200 , reading a plurality of static balance test types, and randomly selecting a first balance test type, performing association matching in a motion type library according to the first balance test type, and determining a first associated motion set.

[0029] Preferably, the static balance test type refers to a series of standardized test methods for evaluating the body stability of adolescents when standing. Common test types include a single-leg standing test, standing on one foot to test the balance time or swing amplitude; a closed-eye standing test, standing with eyes closed to observe the center of gravity shift; a center of gravity swing test while standing, measuring the slight movement of the body's center of gravity during standing; a different support surface test, standing on a plane, inclined plane or unstable surface to test balance ability; from multiple optional static balance test types, randomly select one as the first test type; then perform association matching in the motion type library according to the first balance test type, that is, according to the selected static balance test type, search the motion type library for a dynamic motion type with similar balance requirements.

[0030] Preferably, the sports type library contains various sports scenes related to balance ability, which require individuals to maintain balance ability in dynamic activities, and may include walking, such as the proportion of falls when walking on uneven roads, running, such as the ability to maintain balance during high-speed running, especially stability when turning or braking, jumping, such as the ability to restore the center of gravity during continuous jumping, cycling, such as the ability to maintain vehicle balance and prevent falls, climbing sports, such as the ability to maintain control of the body's center of gravity when rock climbing; for example, if the selected static balance test type is "single-leg standing test", the corresponding associated sports scenes may be single-leg jumping, unilateral center of gravity offset control when running, etc., because these scenes have high requirements for unilateral balance ability; if the selected "closed eyes standing test" is, it may correspond to cycling or climbing sports, which require a high reliance on the body's instinctive center of gravity perception; if the "center swing test when standing" is selected, it may correspond to the ability to dynamically adjust the center of gravity when walking; the core of the association matching is to find out how the static test results are associated with dynamic sports scenes to build a more comprehensive balance ability assessment dimension.

[0031] Preferably, the first associated motion set is finally determined, that is, a set of dynamic motion scenes with similar balance feature requirements as the selected static test type. For example, if the selected test type is "single-leg standing test", the corresponding first associated motion set may include single-leg jumping, single-foot stepping on obstacles, turning while running, etc.; if the selected test type is "different support surface test", the corresponding first associated motion set may include walking on uneven roads, riding a bicycle on a trapezoidal slope, etc. By associating and matching static balance tests with motion scenes, the comprehensiveness of the test can be improved and the data relevance can be enhanced.

[0032] Furthermore, step S200 also includes step S210, selecting a first motion type from the motion type library, taking the first balance test type and the first motion type as constraints, and acquiring a first associated record data set based on big data retrieval; step S220, performing an association analysis on the first balance test type and the first motion type according to the first associated record data set to determine a first association degree; and step S230, if the first association degree is greater than a predetermined association threshold, adding the first motion type to the first associated motion set.

[0033] Preferably, the motion type library includes multiple motion scenes, each scene is related to balance ability, for example, walking scenes, ordinary roads, unstable ground, walking with obstacles, etc., running scenes, straight running, high-speed running, curved running, etc., jumping scenes, jumping in place, hopping on one foot, continuous jumping, etc., special sports, such as cycling, climbing, skating, etc., randomly select a motion type (such as "straight running" or "obstacle walking") from the motion type library as the analysis target, and then use the first balance test type and the first motion type as constraints, and use big data analysis methods to retrieve data sets related to the first balance test type and the first motion type from historical motion records or related databases, including balance test and motion test records of different populations, imbalance rate or movement stability of athletes when running, and correlation records of individual standing balance time and sports performance, etc., as the first associated record data set.

[0034] Preferably, according to the first associated record data set, a correlation analysis is performed on the first balance test type and the first movement type, that is, the correlation coefficient between the balance test data and the movement performance data is calculated, for example, using the Pearson correlation coefficient or the Spearman rank correlation coefficient for calculation to quantify the relationship between the two, such as whether the balance test performance is directly related to a specific movement ability, whether good or poor performance can predict possible results in the movement, and then outputting a first correlation degree (such as a value from 0 to 1) to reflect the strength of the correlation between the two. For example, a correlation degree of 0.8 indicates that the two are highly correlated, indicating that the balance test can predict the movement performance well; a correlation degree of 0.3 indicates that the two are less correlated, indicating that the relationship between the test and the movement ability is limited; and then judging whether the correlation degree is greater than a predetermined correlation threshold, wherein the predetermined correlation threshold is a pre-set standard for judging whether the correlation degree is high enough. If the first correlation degree is greater than the predetermined correlation threshold, it means that the correlation between the first balance test type and the first movement type is strong, and the first movement type is added to the first associated movement set.

[0035] Step S300: randomly select a first group center feature, and obtain a first movement qualification indicator set of the first associated movement set based on the first group center feature.

[0036] Preferably, a representative group (first group) and its central feature are selected from the youth group clustering results as the first group central feature, and based on the central feature, corresponding sports ability evaluation indicators are formulated for the dynamic associated sports set, namely, the first sports qualified indicator set, wherein the first group central feature is comprehensive data representing the characteristics of a certain youth group (for example, a group of individuals with similar characteristics such as height, weight, and body proportions). Specifically, based on the selected group central feature, the potential impact of its characteristics on sports performance is analyzed, and specific performance standards are set for associated sports scenarios, such as the center of gravity deviation does not exceed 10% and the fall rate is less than 5% in walking scenarios; the pace stability reaches more than 90% in running scenarios; and the stability is maintained for 20 meters in cycling scenarios. Straight line and the deviation does not exceed 10 cm, and then determine the first sports qualified indicator set, that is, the specific requirements for performance in the associated sports scene, which is used to measure whether the target group meets the qualified standards of sports ability, which may include the fall ratio, the frequency of falls in specific scenes (such as walking, running), such as less than 1 fall in 10 consecutive walking tests is qualified; abnormal ratio, the proportion of abnormal performance in sports, such as unbalanced movements, abnormal postures, etc.; movement stability indicators, such as a group needs to maintain balance for more than 10 seconds when standing on one foot; the difference in performance in different scenes, examines whether balance can be maintained in different environments (such as flat ground, uneven roads), for example, the change in the fall ratio during normal running and slope running must not exceed 5%. Obtaining the first sports qualified indicator set based on the group center characteristics is a process of combining static balance ability with dynamic sports scenes. By setting the performance indicators of sports scenes (such as fall ratio and abnormal ratio), it provides a reference benchmark for evaluating the balance ability of the target group in dynamic sports, which can comprehensively evaluate the balance ability of the target group in different sports environments and contribute to the scientific evaluation of the balance ability of adolescents.

[0037] Furthermore, step S300 also includes step S310, randomly selecting any associated movement in the first associated movement set as a first movement type, and obtaining a first movement association degree of the first movement type; step S320, taking the first group center feature and the first movement type as constraints, performing positive sample retrieval based on big data, and obtaining a first movement record data set; step S330, optimizing the initial qualified ratio according to the first movement association degree, and obtaining a first standard qualified ratio, wherein the first standard qualified ratio is positively correlated with the first movement association degree; step S340, taking the first standard qualified ratio as a constraint condition, performing qualified indicator analysis according to the first movement record data set, obtaining a first movement qualified indicator, and adding it to the first movement qualified indicator set.

[0038] Preferably, any associated movement is randomly selected in the first associated movement set to be set as the first movement type as the analysis target, and the first movement correlation is obtained. Then, with the first group center feature and the first movement type as constraints, positive sample retrieval is performed based on big data, that is, the screening conditions are determined, and sample data that meets the target group characteristics and movement type requirements are retrieved from historical movement test data, records of motion capture systems, and actual movement performance data (such as movement data of sports competitions or daily activities) as the first movement record data set, for example, data samples (recording the specific performance of individuals in the group in the "single-leg jump" movement), sample content (such as the number of jumps, jump distance, number of falls, movement stability, etc.); then the initial qualified ratio is optimized according to the first movement correlation, wherein the initial qualified ratio is the set basic qualified standard, such as the initial qualified ratio may be 70%, that is, 70% of the movement performance can be considered qualified if it meets the requirements. Specifically, based on the first movement correlation, the initial qualified ratio is adjusted. If the correlation is high (such as 0.9), the expression It is clear that the type of exercise is highly correlated with the balance ability, and the qualified ratio can be appropriately increased (such as optimized from 70% to 85%). If the correlation is low (such as 0.6), the qualified ratio may be reduced (such as optimized from 70% to 60%), and then the first standard qualified ratio is determined. The first standard qualified ratio is positively correlated with the correlation degree of the first exercise. The higher the correlation degree, the stricter the standard. Finally, the qualified index analysis is performed according to the first exercise record data set with the first standard qualified ratio as the constraint condition, that is, according to the exercise record data, the specific conditions required to achieve the first standard qualified ratio are analyzed. Specifically, the distribution of various indicators in the exercise record, such as the mean value, standard deviation, etc., is calculated, and compared with the first standard qualified ratio, and the data that meets the qualified ratio is screened out, and the first exercise qualified index is obtained and added to the first exercise qualified index set. For example, the qualified index of "single-leg jump" is to complete 10 jumps in a row, the center of gravity deviation does not exceed ±5%, and the number of falls does not exceed 1. Among them, the exercise qualified index set is a complete set of indicators associated with a certain balance test type.

[0039] In step S400, based on the constraint of satisfying the first movement qualification indicator set, test indicator optimization analysis of the first balance test type is performed according to the first group center feature to determine a first adaptation test scalar.

[0040] Preferably, the indicators of the static balance test are optimized in combination with the motion qualification indicator set and the group center characteristics, so as to generate a specific test scalar adapted to the target group, i.e., the first adapted test scalar. Specifically, the first motion qualification indicator set is used as a constraint condition to ensure that the optimized static test indicators can effectively reflect the dynamic motion ability, and the test indicator optimization analysis of the first balance test type is performed according to the first group center characteristics, i.e., the specific evaluation indicators of the test type are adjusted through the optimization analysis to make them more suitable for the characteristics and motion ability requirements of the target group, including adjusting the test parameters according to the group center characteristics and the motion qualification indicator set; ensuring that the static test can reflect the balance ability in the dynamic scene, for example, if the qualified indicator of the dynamic motion scene requires the center of gravity offset to be less than 5%, then the center of gravity offset range of the static test should be set more strictly. (e.g. less than 3%); if the dynamic sports scene requires a low fall rate (less than 2%), the static test can be enhanced by increasing the difficulty (e.g. longer test time) to enhance its discrimination; based on the test index optimization analysis results, determine the first adaptive test scalar (test index parameter), which may include test scalars, such as single-leg standing time (30 seconds), center of gravity swing amplitude (±3%), allowable error range, etc., whether to add dynamic disturbances (e.g. unstable support surface), such as a single-leg standing test for a group, which requires a duration of ≥30 seconds and a center of gravity offset of ≤±3% to be qualified, and the adaptive test scalar must meet the characteristics of the target group. For example, the center of gravity offset of a group with a taller height may be larger, so its test scalar can be appropriately relaxed (e.g. ±5%), and the test time can be reduced for groups with weaker physical fitness (e.g. from 30 seconds to 20 seconds). The adaptive scalar avoids excessive or low test difficulty and improves the accuracy, scientificity and feasibility of the evaluation.

[0041] Furthermore, step S400 also includes step S410, obtaining a first test indicator threshold of the first balance test type and randomly selecting first test data; step S420, taking the first group center feature, the first balance test type and the first test data as constraints, obtaining multiple sample motion indicator sets based on big data retrieval, and performing high-frequency feature analysis on the multiple sample motion indicator sets to determine multiple sample motion indicators; step S430, judging the multiple sample motion indicators according to the first motion qualified indicator set, if the multiple sample motion indicators are all greater than multiple corresponding qualified indicators in the first motion qualified indicator set, then calculating and obtaining the first test fitness according to the first motion qualified indicator set and multiple sample motion indicators; step S440, using the first test indicator threshold, continuing to perform test indicator optimization analysis until a predetermined number of iterations is met, and outputting the test data with the largest test fitness as the first adaptation test scalar.

[0042] Preferably, a first test indicator threshold of the first balance test type is obtained, and the first test indicator threshold is an initial constraint condition of the balance test type, which is used to screen or guide the test process. Randomly selecting the first test data refers to randomly selecting a data point from historical test data or a pre-generated test data set as an initial sample for analysis. Based on multiple constraints such as the first group center feature, the first balance test type and the first test data, multiple sample motion indicator sets are obtained based on big data retrieval, that is, multiple sample motion records matching these constraints are retrieved to form a sample motion indicator set, each sample record may include motion performance, such as the number of jumps, the number of falls, the motion stability score, etc., and environmental influences, such as ground conditions, test equipment, etc.; then a high-frequency feature analysis is performed on the sample motion indicator set, that is, the frequency of occurrence of certain features in the sample motion indicator set is counted to determine the representative features of the sample motion indicator, so as to extract key indicators, such as the number of jumps, the number of falls, the stability score, etc.

[0043] Preferably, multiple sample motion indicators are judged according to the first motion qualified indicator set, that is, the sample motion indicators are compared with the qualified indicator set one by one. If multiple sample motion indicators all meet multiple corresponding qualified indicators in the first motion qualified indicator set, they are deemed qualified. The first test fitness is calculated according to the motion qualified indicators and the sample motion indicators to measure the degree of match between a certain test data (or condition) and the motion qualified indicators. Then, based on the fitness results, the test indicators (such as standing time, stability score, etc.) are adjusted, and iterative analysis is performed until the predetermined number of iterations set is met. The test data with the largest fitness is output as the first adaptation test scalar, that is, the test data with the largest fitness is selected as the final scalar for balance test and motion ability assessment, to ensure that the test conditions are scientific and reasonable and can accurately reflect the balance ability.

[0044] Furthermore, step S420 also includes step S421, randomly selecting a first sample motion indicator set and calculating the mean to obtain a first indicator mean; step S422, taking the first indicator mean as a reference, performing deviation calculations on multiple first sample motion indicators in the first sample motion indicator set to obtain multiple first indicator deviation sets; step S423, screening the multiple first indicator deviation sets according to a predetermined deviation threshold, determining multiple first standard motion indicators, and calculating the mean of the multiple first standard motion indicators to obtain a first sample motion indicator, and adding it to the multiple sample motion indicators.

[0045] Preferably, one is randomly selected from the sample motion indicator set as the first sample motion indicator set (including the number of jumps, the number of falls, and the stability score), and the mean calculation is performed on each indicator in the first sample motion indicator set to obtain the average value representing the entire indicator set, and the first indicator mean is determined. Then, based on the first indicator mean, deviation calculations are performed on multiple first sample motion indicators in the first sample motion indicator set, that is, the relationship between each sample indicator and the corresponding first indicator mean is calculated to quantify the discrete degree of the sample, and multiple first indicator deviation sets are obtained; then, the multiple first indicator deviation sets are screened according to a predetermined deviation threshold, wherein the predetermined deviation threshold is a standard value for screening data, specifically, the data in the deviation set is screened, and samples with deviations within the threshold range are retained as the first standard motion indicators, and the mean calculation is performed on multiple first standard motion indicators to obtain the first sample motion indicator, and the calculated first sample motion indicator (mean) is added to multiple sample motion indicator sets to form an updated indicator set, which effectively improves the accuracy and scientificity of motion indicator analysis.

[0046] Further, step S430 also includes step S431, setting influence weights according to multiple motion associations of the first motion qualified indicator set to obtain multiple indicator weights, wherein the indicator weights are positively correlated with the motion associations; step S432, constructing a test fitness evaluation function:

[0047] ;

[0048] in, is the test fitness, N is the number of indicators in the motion indicator set, is the index weight of the nth sports index, is the movement qualification index of the nth movement index, is a sample motion index of the nth motion index; step S433, based on the test fitness evaluation function, performing fitness calculation on the first motion qualified index set and multiple sample motion indexes, and outputting a first test fitness.

[0049] Preferably, the influence weight is set according to the multiple movement associations of the first movement qualified indicator set, wherein the degree of association between each movement qualified indicator and the target balance test type can be quantified as the movement association, which indicates the importance of a certain indicator in the evaluation or test. The higher the movement association value, the greater the importance of the indicator in the test. The influence weight is set according to the multiple movement associations to obtain multiple indicator weights. The indicator weight is positively correlated with the movement association, which means that the indicator with high movement association is assigned a higher weight, and the indicator with low movement association is assigned a lower weight; then the fitness evaluation function is constructed:

[0050] ;

[0051] in, is the test fitness, N is the number of indicators in the motion indicator set, is the index weight of the nth sports index, is the movement qualification index of the nth movement index, is the sample motion index of the nth motion index. According to the test fitness evaluation function, the sample motion index is compared and calculated with the target qualified index, and the fitness score (i.e., the first test fitness) is generated by combining the weight and deviation analysis to quantify the degree of match between the test data and the target standard.

[0052] Step S500, analyzing and acquiring a plurality of adaptation test scalar sets in sequence, integrating and generating a plurality of adaptation test evaluation tables, and performing balance ability evaluation on the static balance test data of the plurality of target groups.

[0053] Preferably, by analyzing the adaptation test scalars of the static balance test for multiple target groups respectively, and further integrating them into a systematic evaluation form, a scientific evaluation of the static balance ability of each target group is performed. Specifically, the test index optimization analysis is performed on each target group to generate multiple adaptation test scalar sets, which reflect the evaluation index of each group in the static test and ensure that the adapted test scalars fully reflect the characteristics of each group. For example, for groups with unstable center of gravity, the scalars are analyzed to balance the difficulty and scientificity of the test; for groups with poor coordination, the scalars are analyzed to see whether the movement stability needs to be evaluated in detail; and then these scalars are integrated to generate multiple adaptation test evaluation forms, which may include test items, test indicators, test results, evaluation criteria, etc. For example, the adaptation test evaluation form may contain the following contents:

[0054]

[0055] Preferably, the balance ability is evaluated based on the static balance test data of multiple target groups, wherein the static balance test data are data collected during the actual test process, such as the average test performance of each target group (such as average standing time, deviation amplitude), the degree of dispersion of individuals within the group (such as standard deviation, reflecting the consistency of test results). Specifically, the evaluation is performed based on the test data and adaptation scalars in the evaluation table, which may include single ability evaluation, such as whether standing stability and center of gravity control ability meet the standards, comprehensive ability scoring, and combining multiple test items to calculate the overall balance ability score of the target group, thereby achieving a comprehensive, scientific and accurate evaluation of the static balance ability of different target groups, ensuring that the test results can not only reflect individual differences, but also provide an overall analysis of group characteristics.

[0056] In the above, refer to Figure 1A method for testing the balance ability of a standing human body according to an embodiment of the present invention is described in detail. Figure 2 A standing human balance ability testing device according to an embodiment of the present invention is described.

[0057] A standing human balance ability test device according to an embodiment of the present invention is used to solve the technical problem that the existing standing balance ability test often directly conducts static evaluation based on fixed indicators, does not consider individual characteristic differences and the impact on life, and thus leads to poor accuracy, reliability and practicality of the evaluation results, thereby achieving the technical effect of improving the accuracy, reliability and practicality of the balance ability test results. A standing human balance ability test device includes: a target group determination module 10, a first associated motion set determination module 20, a first motion qualified indicator set acquisition module 30, a first adaptation test scalar determination module 40, and a balance ability evaluation module 50.

[0058] A target group determination module 10 is used to cluster the youth group according to morphological features, determine multiple target groups, and multiple group center features; a first associated motion set determination module 20 is used to read multiple static balance test types, and randomly select a first balance test type, perform associated matching in the motion type library according to the first balance test type, and determine a first associated motion set; a first motion qualified indicator set acquisition module 30 is used to randomly select a first group center feature, and obtain a first motion qualified indicator set of the first associated motion set based on the first group center feature; a first adaptation test scalar determination module 40 is used to perform test indicator optimization analysis of the first balance test type according to the first group center feature with the first motion qualified indicator set as a constraint, and determine a first adaptation test scalar; a balance ability evaluation module 50 is used to sequentially analyze and obtain multiple adaptation test scalar sets, integrate and generate multiple adaptation test evaluation tables, and perform balance ability evaluation on the static balance test data of the multiple target groups.

[0059] The specific configuration of the target group determination module 10 will be described in detail below. The target group determination module 10 may further include: collecting features of the youth group according to predetermined feature indicators to obtain multiple morphological feature data sets; clustering the multiple morphological feature data sets using the K-Means algorithm to obtain multiple feature clustering results; mapping and dividing the youth group according to the multiple feature clustering results to determine multiple target groups and multiple group center features, wherein the group center feature is the median value of the feature clustering results.

[0060] The specific configuration of the first associated motion set determination module 20 will be described in detail below. The first associated motion set determination module 20 further includes: selecting a first motion type from the motion type library, taking the first balance test type and the first motion type as constraints, and acquiring a first associated record data set based on big data retrieval; performing a correlation analysis on the first balance test type and the first motion type according to the first associated record data set to determine a first correlation; if the first correlation is greater than a predetermined correlation threshold, adding the first motion type to the first associated motion set.

[0061] The specific configuration of the first movement qualified indicator set acquisition module 30 will be described in detail below. The first movement qualified indicator set acquisition module 30 may further include: randomly selecting any associated movement in the first associated movement set as the first movement type, and obtaining the first movement correlation of the first movement type; taking the first group center feature and the first movement type as constraints, performing positive sample retrieval based on big data, and obtaining the first movement record data set; optimizing the initial qualified ratio according to the first movement correlation, and obtaining the first standard qualified ratio, wherein the first standard qualified ratio is positively correlated with the first movement correlation; taking the first standard qualified ratio as a constraint condition, performing qualified indicator analysis according to the first movement record data set, obtaining the first movement qualified indicator, and adding it to the first movement qualified indicator set.

[0062] The specific configuration of the first adaptation test scalar determination module 40 will be described in detail below. The first adaptation test scalar determination module 40 may further include: obtaining the first test indicator threshold of the first balance test type, and randomly selecting the first test data; taking the first group center feature, the first balance test type and the first test data as constraints, obtaining multiple sample motion indicator sets based on big data retrieval, and performing high-frequency feature analysis on the multiple sample motion indicator sets to determine multiple sample motion indicators; judging the multiple sample motion indicators according to the first motion qualified indicator set, if the multiple sample motion indicators are all greater than the multiple corresponding qualified indicators in the first motion qualified indicator set, then calculating and obtaining the first test fitness according to the first motion qualified indicator set and the multiple sample motion indicators; using the first test indicator threshold, continue to perform test indicator optimization analysis until the predetermined number of iterations is met, and output the test data with the maximum test fitness as the first adaptation test scalar.

[0063] The specific configuration of the first adaptation test scalar determination module 40 will be described in detail below. The first adaptation test scalar determination module 40 may further include: sorting the set of abnormal regions to be fused in order of region volume from small to large to obtain a sequence of abnormal regions to be fused; sorting the set of abnormal regions that can be fused in order of region volume from large to small to obtain a sequence of abnormal regions that can be fused; and sequentially integrating the sequence of abnormal regions to be fused into the sequence of abnormal regions that can be fused to obtain a fusion result.

[0064] The specific configuration of the first adaptation test scalar determination module 40 will be described in detail below. The first adaptation test scalar determination module 40 may further include: setting influence weights according to multiple motion associations of the first motion qualified indicator set to obtain multiple indicator weights, wherein the indicator weights are positively correlated with the motion associations; and constructing a test fitness evaluation function:

[0065] ;

[0066] in, is the test fitness, N is the number of indicators in the motion indicator set, is the index weight of the nth sports index, is the movement qualification index of the nth movement index, A sample motion index of the nth motion index; based on the test fitness evaluation function, the fitness of the first motion qualified index set and multiple sample motion indexes is calculated, and the first test fitness is output.

[0067] A standing human balance ability testing device provided by an embodiment of the present invention can execute a standing human balance ability testing method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0068] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0069] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for testing the balance ability of a standing human body, characterized in that: include: Cluster the youth groups according to their morphological characteristics, identify multiple target groups, and multiple group center characteristics; Read multiple static balance test types, randomly select a first balance test type, perform association matching in a motion type library according to the first balance test type, and determine a first associated motion set; Randomly selecting a first group center feature, and obtaining a first movement qualification indicator set of the first associated movement set based on the first group center feature; Taking the first movement qualification indicator set as a constraint, performing the test indicator optimization analysis of the first balance test type according to the first group center feature to determine a first adaptation test scalar; Analyze and obtain multiple adaptation test scalar sets in sequence, integrate and generate multiple adaptation test evaluation tables, and evaluate the balance ability of the static balance test data of the multiple target groups; Wherein, taking the first movement qualification indicator set as a constraint, performing the test indicator optimization analysis of the first balance test type according to the first group center feature, and determining the first adaptation test scalar includes: Obtaining a first test indicator threshold of the first balance test type, and randomly selecting first test data; Taking the first group center feature, the first balance test type and the first test data as constraints, obtaining multiple sample motion indicator sets based on big data retrieval, and performing high-frequency feature analysis on the multiple sample motion indicator sets to determine multiple sample motion indicators; Judging the plurality of sample motion indices according to the first motion qualified indicator set, if the plurality of sample motion indices are all greater than a plurality of corresponding qualified indicators in the first motion qualified indicator set, calculating and obtaining a first test fitness according to the first motion qualified indicator set and the plurality of sample motion indices; Using the first test indicator threshold, continue to perform test indicator optimization analysis until a predetermined number of iterations is met, and output the test data with the maximum test fitness as a first adaptation test scalar; The step of calculating and obtaining a first test fitness according to the first motion qualified indicator set and a plurality of sample motion indicators includes: Setting influence weights according to multiple sports associations of the first sports qualified indicator set to obtain multiple indicator weights, wherein the indicator weights are positively correlated with the sports associations; Construct a test fitness evaluation function: ； in, is the test fitness, N is the number of indicators in the motion indicator set, is the index weight of the nth sports index, is the movement qualification index of the nth movement index, is the sample motion index of the nth motion index; Based on the test fitness evaluation function, fitness calculation is performed on the first motion qualified index set and multiple sample motion indexes, and a first test fitness is output.

2. A standing human balance ability testing method according to claim 1, characterized in that: Cluster the youth groups according to their morphological characteristics, identify multiple target groups, and multiple group center features, including: Collect characteristics of the youth group according to predetermined characteristic indicators to obtain multiple morphological characteristic data sets; Clustering the multiple morphological feature data sets using a K-Means algorithm to obtain multiple feature clustering results; The youth group is mapped and divided according to the multiple feature clustering results to determine multiple target groups and multiple group center features, wherein the group center feature is the middle value of the feature clustering results.

3. A standing human balance ability testing method according to claim 1, characterized in that: According to the first balance test type, an association match is performed in a motion type library to determine a first associated motion set, including: Selecting a first motion type from the motion type library, taking the first balance test type and the first motion type as constraints, and acquiring a first associated record data set based on big data retrieval; performing a correlation analysis on the first balance test type and the first exercise type according to the first correlation record data set to determine a first correlation degree; If the first association degree is greater than a predetermined association threshold, the first motion type is added to the first associated motion set.

4. A standing human balance ability testing method according to claim 3, characterized in that: Acquiring a first movement qualification indicator set of the first associated movement set based on the first group center feature includes: Randomly selecting any associated motion in the first associated motion set as a first motion type, and obtaining a first motion association degree of the first motion type; Taking the first group center feature and the first sport type as constraints, performing positive sample retrieval based on big data to obtain a first sport record data set; Optimizing the initial qualified ratio according to the first motion correlation to obtain a first standard qualified ratio, wherein the first standard qualified ratio is positively correlated with the first motion correlation; Taking the first standard qualified ratio as a constraint condition, a qualified index analysis is performed based on the first motion record data set to obtain a first motion qualified index, which is added to the first motion qualified index set.

5. A standing human balance ability testing method according to claim 1, characterized in that: Performing high-frequency feature analysis on the plurality of sample motion index sets to determine a plurality of sample motion indexes includes: Randomly select a first sample motion index set, and calculate the mean to obtain a first index mean; Taking the first indicator mean as a reference, respectively calculating deviations of a plurality of first sample motion indicators in the first sample motion indicator set to obtain a plurality of first indicator deviation sets; The plurality of first indicator deviation sets are screened according to a predetermined deviation threshold to determine a plurality of first standard motion indicators, and a first sample motion indicator is obtained after averaging the plurality of first standard motion indicators, and added to the plurality of sample motion indicators.

6. A standing human balance ability testing device, characterized in that: The device is used to implement a standing human balance ability testing method according to any one of claims 1 to 5, and the device comprises: The target group determination module is used to cluster the youth groups according to their morphological characteristics, determine multiple target groups, and multiple group center features; A first associated motion set determination module, configured to read a plurality of static balance test types, randomly select a first balance test type, perform associated matching in a motion type library according to the first balance test type, and determine a first associated motion set; A first movement qualified indicator set acquisition module, used for randomly selecting a first group center feature, and acquiring a first movement qualified indicator set of the first associated movement set based on the first group center feature; A first adaptation test scalar determination module is used to perform test index optimization analysis of the first balance test type according to the first group center feature, with the first movement qualified index set as a constraint, to determine a first adaptation test scalar; The balance ability evaluation module is used to analyze and obtain multiple adaptation test scalar sets in sequence, integrate and generate multiple adaptation test evaluation tables, and perform balance ability evaluation on the static balance test data of the multiple target groups.

Images