Gait stability assessment method and system based on exercise data of fitness equipment

Abstract

The invention discloses a gait stability assessment method and system based on exercise data of fitness equipment, and relates to the technical field of gait recognition, and the gait stability assessment method based on the exercise data of the fitness equipment comprises the following steps: obtaining exercise key feature data; the change trend of the gait stability is recognized; analyzing the change trend of the gait stability by using a factor analysis algorithm to obtain key factors influencing the gait stability; evaluating the key factors influencing the gait stability and the known key factors influencing the gait stability in the database, and adjusting the use strategy of the fitness equipment to optimize the gait stability. According to the invention, by using the gait recognition algorithm, the current gait stability can be evaluated, the change trend of the gait stability can be recognized, the influence mechanism of the gait stability can be better understood, and thus more effective intervention measures can be designed.

Description

Technical Field

[0001] The present invention relates to the technical field of gait recognition, and in particular to a gait stability evaluation method and system based on fitness equipment motion data. Background Art

[0002] Human gait stability refers to the ability to maintain body stability by sensing and controlling the position of the body's center of mass to keep it within the support surface during movement. This ability is the basis for daily activities, especially for the elderly, where the maintenance of gait stability is particularly important. With age, neuromuscular function gradually declines, and gait may become unstable, increasing the risk of falling. Therefore, effective gait stability assessment and training become particularly important.

[0003] In the field of modern medical and health technology, the use of high-tech fitness equipment to collect motion data for gait stability assessment has become an emerging research and application direction. By setting specific exercise tasks, such as walking or running on a treadmill, and using sensor technology to collect data on step length, pace, balance, etc., researchers and clinicians can analyze and evaluate an individual's gait stability. These data can not only be used to assess an individual's current level of gait stability, but also help develop targeted training plans to improve gait stability and reduce the risk of falls through targeted exercise training. In addition, continuous monitoring and evaluation can also help track training results, adjust training plans in a timely manner, and ensure the effectiveness and safety of exercise interventions.

[0004] In the existing technology, it is not easy to evaluate the current gait stability, and it is not easy to identify the changing trend of gait stability. It is not easy for medical professionals to find problems in time and take corresponding intervention measures. At the same time, it is not easy to analyze and identify the key factors affecting gait stability. It is not easy to better understand the influencing mechanism of gait stability and to compare it with known influencing factors, so it is impossible to adjust the fitness equipment strategy in a targeted manner, which reduces the overall training effect and safety.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the deficiencies of the prior art, the present invention proposes a gait stability evaluation method and system based on fitness equipment motion data, which solves the problems mentioned in the above background technology that it is not easy to evaluate the current gait stability and it is not easy to identify the changing trend of gait stability. It is not easy for medical professionals to find problems in time and take corresponding intervention measures. At the same time, it is not easy to analyze and identify the key factors affecting gait stability. It is not easy to better understand the influencing mechanism of gait stability, and it is not easy to compare with known influencing factors, so it is impossible to adjust the fitness equipment strategy in a targeted manner, which reduces the overall training effect and safety.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] According to one aspect of the present invention, a gait stability evaluation method based on fitness equipment motion data is provided, and the gait stability evaluation method based on fitness equipment motion data comprises the following steps:

[0009] S1. Obtaining motion data of fitness equipment and processing the motion data to obtain key motion feature data;

[0010] S2. Utilize gait recognition algorithm to analyze gait stability of key motion feature data and identify the changing trend of gait stability;

[0011] S3, using factor analysis algorithm to analyze the changing trend of gait stability and obtain the key factors affecting gait stability;

[0012] S4. Evaluate the key factors affecting gait stability with the key factors known in the database, and adjust the use strategy of fitness equipment to optimize gait stability.

[0013] Furthermore, obtaining the motion data of the fitness equipment and processing the motion data to obtain the key motion feature data includes the following steps:

[0014] S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the motion data of the fitness equipment, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values;

[0015] S12, connecting the unprocessed data in the motion data to generate a new data table, associating different data tables through external key values ​​to generate a complete data table, obtaining an accurate motion data set, and determining the initial key motion moment of the gait cycle;

[0016] S13. Using a curve amplitude algorithm, extract features of the initial key motion moment of the gait cycle to obtain key motion feature data.

[0017] Furthermore, the curve amplitude algorithm is used to extract the features of the initial key motion moment of the gait cycle to obtain the key motion feature data, which includes the following steps:

[0018] S131, constructing a characteristic curve according to the initial key movement moment of the gait cycle, and calculating the amplitude difference of the characteristic curve between adjacent movement moments;

[0019] S132, setting a threshold parameter. If the amplitude difference is less than the threshold parameter, there is no need to insert a new key motion moment. If the amplitude difference is greater than the threshold, there is a need to insert a new key motion moment.

[0020] S133, checking the obtained key motion moment set to determine whether there are too dense key motion moments, and if there are too dense key motion moments, obtaining motion key feature data by merging the too dense key motion moments.

[0021] Further, using a gait recognition algorithm to analyze the gait stability of the key motion feature data and identifying the changing trend of the gait stability includes the following steps:

[0022] S21, presetting the number of participants and analysis period of the gait recognition algorithm, and initializing the gait data of the participants;

[0023] S22, traverse all participants and calculate the fitness value of gait stability according to the key feature data of the movement;

[0024] S23, identifying the individuals with the most stable gait and the most unstable gait from the participants, and recording the gait data positions of the individuals with the most stable gait and the most unstable gait;

[0025] S24, calculating the distance difference between the gait data of each participant and the most stable gait and the least stable gait respectively according to the gait data of the participants, and dividing the participants into a subgroup with higher stability and a subgroup with lower stability based on the distance difference;

[0026] S25, respectively updating the subgroups with higher stability and the subgroups with lower stability, and then reorganizing after the updates;

[0027] S26. Repeat steps S22 to S25 until a preset analysis period is reached, and analyze the final participant's gait data to identify the changing trend of gait stability.

[0028] Further, according to the gait data of the participants, respectively calculating the distance difference between the gait data of each participant and the most stable gait and the most unstable gait, and dividing the participants into subgroups with higher stability and subgroups with lower stability based on the distance difference includes the following steps:

[0029] S241, obtaining gait data of each participant, and defining the most stable and the most unstable gait data;

[0030] S242. For each participant, check whether the distance difference between the participant's gait data and the most stable gait is no greater than half the distance difference between the participant's gait data and the most unstable gait;

[0031] S243. If the distance difference between the participant's gait data and the most stable gait is not greater than half of the distance difference between the participant's gait data and the most unstable gait, the participant is divided into a subgroup with higher stability; otherwise, the participant is divided into a subgroup with lower stability.

[0032] Furthermore, the formulas for calculating the distance difference between each participant's gait data and the most stable gait and the most unstable gait are as follows:

[0033]

[0034] In the formula, Range j_sturdiest It is expressed as the distance difference between the gait data of the jth participant and the most stable gait;

[0035] Range j_shakiest It is expressed as the distance difference between the jth participant’s gait data and the most unstable gait;

[0036] M j Represented as the location of the gait data of the jth participant;

[0037] M a The position of the gait data of the participant with the most stable gait is represented;

[0038] M b The location of the participant's gait data represented as the most unstable gait.

[0039] Further, the factor analysis algorithm is used to analyze the changing trend of gait stability, and the key factors affecting gait stability are obtained, including the following steps:

[0040] S31 initializes relevant parameters of the factor analysis algorithm;

[0041] S32, performing preliminary statistical analysis on the gait data of each participant to evaluate their initial stability indicators, and storing the gait data of each participant as baseline data in a variable;

[0042] S33, calculating the metric parameters according to the factor analysis algorithm, and updating the weight of each participant's gait data;

[0043] S34, after each iteration, recalculating the stability score of each participant's gait data according to the updated weight;

[0044] S35, looping through steps S33 to S34 until the set number of iterations is reached;

[0045] S36. Output the final stability analysis result and determine the key factors affecting gait stability.

[0046] Further, the key factors affecting gait stability are evaluated with the key factors affecting gait stability known in the database, and the use strategy of the fitness equipment is adjusted to optimize the gait stability, including the following steps:

[0047] S41. Establish an initial evaluation matrix based on the key factors affecting gait stability.

[0048] S42, randomly selecting a fitness equipment configuration to analyze the participant's gait, calculating and recording a matching score with other known stability parameters;

[0049] S43, selecting the optimal fitness equipment configuration according to the matching score of the participant's gait stability, and if the selected configuration matches the current fitness equipment configuration, maintaining it; if not, adjusting it to the fitness equipment configuration with the highest score;

[0050] S44, after the evaluation of each configuration of the fitness equipment is completed, insert a new configuration as needed, and return to step S42 to continue evaluating the unoptimized fitness equipment configuration;

[0051] S45. Calculate the overall gait stability score of the participants according to the final evaluation result, and save the adjusted fitness equipment configuration according to the updated fitness equipment usage strategy;

[0052] S46. Output the optimal fitness equipment configuration and the corresponding gait stability score obtained through evaluation, and adjust the use strategy of the fitness equipment to optimize gait stability.

[0053] Furthermore, randomly selecting fitness equipment configurations to analyze the participants' gait, calculating matching scores with other known stability parameters and recording them includes the following steps:

[0054] S421, defining configuration parameters of fitness equipment, and setting a variable range for the configuration parameters of fitness equipment;

[0055] S422, randomly select the configuration of each fitness equipment to ensure that the configuration at the beginning of each evaluation is random and non-repetitive;

[0056] S423, the participant sets up the fitness equipment by using the randomly selected configuration, and obtains the participant's gait data;

[0057] S424, comparing the acquired participant's gait data with the known gait stability influencing factors in the database, using a preset scoring model to calculate the matching score of each fitness equipment configuration parameter, and recording the matching score of each fitness equipment configuration and the gait stability factor.

[0058] According to another aspect of the present invention, a gait stability evaluation system based on the motion data of a fitness equipment is also provided. The gait stability evaluation system based on the motion data of the fitness equipment comprises:

[0059] A data acquisition module is used to acquire the motion data of the fitness equipment and process the motion data to obtain key motion feature data;

[0060] A gait recognition module is used to analyze the gait stability of key motion feature data using a gait recognition algorithm and identify the changing trend of gait stability;

[0061] A factor analysis module is used to analyze the changing trend of gait stability using a factor analysis algorithm to obtain key factors affecting gait stability;

[0062] The stability evaluation module is used to evaluate the key factors affecting gait stability with the key factors affecting gait stability known in the database, and adjust the use strategy of fitness equipment to optimize gait stability.

[0063] The beneficial effects of the present invention are:

[0064] 1. The present invention processes the motion data collected by fitness equipment and extracts key feature data, which can more accurately evaluate the gait characteristics of individuals, help to deeply understand the individual's motion pattern and potential gait problems, and use the gait recognition algorithm to not only evaluate the current gait stability, but also identify the changing trend of gait stability, so that medical professionals can find problems in time and take corresponding intervention measures. Through the factor analysis algorithm, it is possible to analyze and identify the key factors affecting gait stability. The identification of these key factors helps to better understand the influencing mechanism of gait stability, so as to design more effective intervention measures. After identifying the key factors, by comparing with the known influencing factors in the database, a more targeted fitness equipment adjustment strategy can be provided. The data-based equipment optimization can not only improve gait stability, but also make personalized adjustments based on individual differences, thereby improving the overall training effect and safety.

[0065] 2. The present invention utilizes the curve amplitude algorithm to perform feature extraction on the key moments of the gait cycle, so that the key movement moments can be accurately identified, and the key moments can be accurately inserted or merged through threshold setting, so as to better capture the dynamic changes of gait. By setting threshold parameters and checking the density of key movement moments, not only the sensitivity of capturing gait stability and key moments is improved, but also data redundancy caused by too dense moments can be avoided, thus ensuring the specificity and efficiency of the analysis. Accurate feature extraction and identification of key moments make the evaluation more targeted and effective. The use strategy of fitness equipment can be adjusted based on these data, and a more personalized training plan can be designed, thereby more effectively improving gait stability and reducing the risk of falling.

[0066] 3. The present invention calculates the fitness values ​​of the participants' gait stability, identifies the most stable and the most unstable gaits based on these values, and divides the participants into different subgroups. This can not only reveal the differences between individuals, but also adjust the strategies based on dynamic data updates, thereby improving the overall evaluation and training accuracy. The use of distance differences to classify participants can accurately distinguish individuals who need extra attention or intervention, while maintaining continuous monitoring of those individuals who already have good gait stability. Through periodic evaluation and group analysis, the training or treatment plans can be continuously optimized and adjusted. Such continuity and feedback loops ensure the timeliness and effectiveness of intervention measures, thereby helping participants achieve significant improvements in gait stability.

[0067] 4. The present invention can conduct an in-depth evaluation of each participant's gait data through factor analysis algorithm initialization and statistical analysis, thereby identifying potential variables that affect individual gait stability, providing a scientific basis for understanding and solving the root causes of gait instability. By calculating measurement parameters and updating weights, the evaluation process is allowed to dynamically adjust the degree of emphasis on different factors, ensuring that the evaluation process is more accurate and can adapt to actual changes in participant behavior and gait data. The final output not only helps to identify which factors are key to affecting gait stability, but also quantifies the specific impact of these factors on gait stability, making the adjustment of related fitness equipment and training programs more targeted and effective, and then the intervention measures can be customized according to the specific needs of each participant.

[0068] 5. The present invention ensures that the optimization of the configuration of fitness equipment is based on the actual effect data by randomly selecting the configuration of fitness equipment and calculating the matching score with the known stability parameters. The optimal configuration is selected according to the matching score, allowing the fitness equipment to be personalized according to the specific gait data of each participant. Such personalized adaptation not only improves the training effect, but also increases the satisfaction and safety of the participants. The summary evaluation and final decision output provide a systematic framework to evaluate and adjust the configuration of fitness equipment. This not only provides decision support for managers and trainers, but also provides more suitable training equipment for end users. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 is a flow chart of a method for evaluating gait stability based on motion data of fitness equipment according to an embodiment of the present invention;

[0071] Figure 2 4 is a principle block diagram of a gait stability evaluation system based on fitness equipment motion data according to an embodiment of the present invention.

[0072] In the figure:

[0073] 1. Data acquisition module; 2. Gait recognition module; 3. Factor analysis module; 4. Stability assessment module. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0075] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0076] According to an embodiment of the present invention, a method and system for evaluating gait stability based on motion data of fitness equipment are provided.

[0077] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1As shown, according to the gait stability evaluation method based on the motion data of fitness equipment according to an embodiment of the present invention, the gait stability evaluation method based on the motion data of fitness equipment comprises the following steps:

[0078] S1. Obtaining motion data of fitness equipment and processing the motion data to obtain key motion feature data;

[0079] Specifically, the sports data includes:

[0080] Force data: For example, force output measured using force sensors, such as pedal force, grip force, etc.

[0081] Speed ​​data: The speed at which the device is running, such as speed on a treadmill or rpm on a bicycle.

[0082] Position data: The position data of various parts of the participant's body can be obtained through a motion capture system or accelerometer.

[0083] Heart rate data: Variations in your heart rate collected via a heart rate monitor.

[0084] Acceleration data: Acceleration information of the body or equipment in three-dimensional space collected by accelerometers.

[0085] Tilt and attitude data: The tilt and attitude of a body part measured using a gyroscope or other sensors.

[0086] Specifically, the key feature data of the movement include:

[0087] Gait cycle features: such as step length, step speed, step frequency, etc., which are extracted from position and velocity data.

[0088] Peak force and duration: The maximum value of force output and its duration, analyzed from strength data.

[0089] Energy expenditure estimation: Estimates energy expenditure based on heart rate, speed and acceleration data.

[0090] Movement consistency: Assessing the consistency and stability of repeated movements, such as comparing movements of several consecutive jumps or walks.

[0091] Balance and stability index: Uses inclination and posture data to analyze the body's balance ability and overall stability.

[0092] Heart rate recovery time: Evaluates the time required for heart rate to return to resting level after exercise from heart rate data, reflecting the state of cardiopulmonary function.

[0093] S2. Utilize gait recognition algorithm to analyze gait stability of key motion feature data and identify the changing trend of gait stability;

[0094] Specifically, the changing trends of gait stability include:

[0095] Time series changes in gait parameters: This refers to the changes in gait parameters (such as step length, step frequency, and step speed) over time or under different fitness equipment settings. By analyzing the changes in these parameters, changes in individual adaptability and gait stability under different conditions can be observed.

[0096] Changes in periodicity and consistency: Analyze the consistency of each phase of the gait cycle, such as whether the changes within each gait cycle are regular, whether there are gait disruptions, etc. Decreased consistency may indicate a decrease in gait stability.

[0097] Response to external disturbances: The response of gait stability under the influence of changes in external environment or internal conditions (such as different gym equipment settings, fatigue status, etc.). For example, analyzing how gait parameters adapt to these changes while running on a treadmill at different slopes or speeds.

[0098] Reflection of health status or training effect: Long-term tracking and analysis of gait data can help understand the effect of training intervention, or the impact of health status (such as muscle function, nervous system diseases, etc.) on gait stability.

[0099] Prediction of fall risk: Through long-term and systematic analysis of gait data, gait patterns that may increase the risk of falls can be identified. For example, irregular stride length and reduced gait speed are often associated with an increased risk of falls.

[0100] S3, using factor analysis algorithm to analyze the changing trend of gait stability and obtain the key factors affecting gait stability;

[0101] Specifically, the key factors include:

[0102] 1) Physiological factors:

[0103] Muscle strength: Especially lower limb muscle strength is essential for maintaining gait stability.

[0104] Joint mobility: The range of motion of your joints affects your stride length and smoothness of walking.

[0105] Nervous system function: The effectiveness of neural control directly affects the coordination and balance of movement.

[0106] 2) Health status:

[0107] Age-related changes: such as muscle weakness, joint stiffness, etc.

[0108] Chronic diseases: such as Parkinson's disease, arthritis, etc. These diseases may affect gait stability.

[0109] Vision and hearing impairment: Decreased sensory function can reduce the ability to perceive the environment, thereby affecting gait balance.

[0110] 3) Biomechanical factors:

[0111] Gait parameters: such as stride length, cadence and speed, which are important indicators in gait analysis.

[0112] Body symmetry and center of gravity control: Body symmetry and how to effectively control the center of gravity are also key factors.

[0113] 4) Environmental factors:

[0114] Floor conditions: Uneven or slippery floors increase the risk of falls.

[0115] Fitness equipment used: Type of equipment and settings, such as speed and incline of a treadmill.

[0116] 5) Psychological factors:

[0117] Cognitive status: Reduced cognitive function may affect decision-making and reaction time, which in turn may affect gait stability.

[0118] Emotional state: Emotional fluctuations may also affect an individual's gait performance.

[0119] S4. Evaluate the key factors affecting gait stability with the key factors known in the database, and adjust the use strategy of fitness equipment to optimize gait stability.

[0120] It needs to be explained that, taking a treadmill as an example, first use the sensors equipped on the treadmill (such as force sensors, accelerometers) to collect motion data during running, such as cadence, stride length, heart rate, etc., and analyze the collected motion data through a gait recognition algorithm to determine the regularity and stability of the gait. The regularity of the gait can be evaluated by calculating the standard deviation of the stride length and cadence. Lower variability usually means higher gait stability. Factor analysis is applied to identify which motion characteristics (such as stride length consistency, heart rate changes) can best explain changes in gait stability. The gait analysis results are compared with similar cases stored in the database. For example, the speed and slope of the treadmill are adjusted when a specific unstable pattern is matched. By adjusting the fitness equipment to suit specific gait requirements, users can improve gait stability, thereby reducing the risk of falling and improving exercise efficiency.

[0121] Preferably, acquiring the motion data of the fitness equipment and processing the motion data to obtain the key motion feature data comprises the following steps:

[0122] S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the motion data of the fitness equipment, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values;

[0123] S12, connecting the unprocessed data in the motion data to generate a new data table, associating different data tables through external key values ​​to generate a complete data table, obtaining an accurate motion data set, and determining the initial key motion moment of the gait cycle;

[0124] S13. Using a curve amplitude algorithm, extract features of the initial key motion moment of the gait cycle to obtain key motion feature data.

[0125] It should be explained that sensors (such as force sensors and accelerometers) are used to collect data such as cadence, stride length, heart rate, etc. during running. Data cleaning techniques are used to identify and process duplicate records, missing values, and outliers, such as using the average value to fill missing data, eliminating data points that are obviously deviated from the normal range, combining data collected from different time periods and different sensors, and using database management systems (such as SQL) to associate these data through external keys (such as timestamps and user IDs). Analyze the merged data set, use algorithms (such as peak detection, etc.) to identify key moments in the gait cycle, such as the start and end points of walking, apply curve amplitude algorithms (such as time series-based analysis, etc.), calculate the amplitude changes of each step in the gait cycle, extract the changing trends of stride length and speed, analyze the changes in parameters such as stride length and speed, and determine the stability and efficiency of gait.

[0126] Preferably, extracting features from the initial key motion moments of the gait cycle using a curve amplitude algorithm to obtain key motion feature data comprises the following steps:

[0127] S131, constructing a characteristic curve according to the initial key movement moment of the gait cycle, and calculating the amplitude difference of the characteristic curve between adjacent movement moments;

[0128] S132, setting a threshold parameter. If the amplitude difference is less than the threshold parameter, there is no need to insert a new key motion moment. If the amplitude difference is greater than the threshold, there is a need to insert a new key motion moment.

[0129] S133, checking the obtained key motion moment set to determine whether there are too dense key motion moments, and if there are too dense key motion moments, obtaining motion key feature data by merging the too dense key motion moments.

[0130] It should be explained that the acceleration data of running is collected on a treadmill using an accelerometer. Identify the key movement moments of the gait cycle, such as heel strike and toe lift-off. Construct a characteristic curve of acceleration change over time. Calculate the amplitude difference of the characteristic curve between adjacent key movement moments, such as calculating the acceleration change between heel strike and toe lift-off. The construction of the characteristic curve helps to visualize the dynamic changes in the gait cycle. The amplitude difference can reflect the dynamic characteristics of the gait. Set the threshold parameters based on expert knowledge and data analysis results. For example, if the acceleration change is less than a certain value, it may not be necessary to further subdivide the key movement moments. If the amplitude difference exceeds the threshold, it indicates that there are important dynamic changes in the gait cycle. New key movement moments need to be inserted to describe the gait more finely. Analyze the distribution of key movement moments and check whether there are key movement moments that are too close in time. If there are too dense key movement moments, merge these moments through data aggregation or feature selection methods to reduce the redundancy of feature data.

[0131] It needs to be explained that, assuming that we have conducted a series of running tests on a healthy adult on a treadmill, first the treadmill is equipped with a three-axis accelerometer, the data sampling rate is 100Hz, which is sufficient to capture high-frequency motion changes, each test runs for 5 minutes, a long enough period of time to observe steady-state gait behavior, the average acceleration peak reaches 1.5g (g is the acceleration of gravity), usually the maximum value occurs when the heel touches the ground, and the threshold of the acceleration change is set to 0.5g. This means that if the acceleration change between two consecutive key moments exceeds 0.5g, it is considered that there is a significant dynamic change in the gait cycle, and a new key motion moment needs to be inserted. If the time between key motion moments is less than 0.2 seconds, consider merging them, because such a short time interval may be noise or non-critical dynamic changes. When merging, choose to retain the moment with the largest acceleration change and remove the others.

[0132] Preferably, using a gait recognition algorithm to perform gait stability analysis on key motion feature data to identify the changing trend of gait stability includes the following steps:

[0133] S21, presetting the number of participants and analysis period of the gait recognition algorithm, and initializing the gait data of the participants;

[0134] S22, traversing all participants and calculating the fitness value of gait stability according to the key feature data of the movement;

[0135] S23, identifying the individuals with the most stable gait and the most unstable gait from the participants, and recording the gait data positions of the individuals with the most stable gait and the most unstable gait;

[0136] S24, calculating the distance difference between the gait data of each participant and the most stable gait and the least stable gait respectively according to the gait data of the participants, and dividing the participants into a subgroup with higher stability and a subgroup with lower stability based on the distance difference;

[0137] S25, respectively updating the subgroups with higher stability and the subgroups with lower stability, and then reorganizing after the updates;

[0138] S26. Repeat steps S22 to S25 until a preset analysis period is reached, and analyze the final participant's gait data to identify the changing trend of gait stability.

[0139] It should be explained that, assuming that 20 healthy adults participated, the gait data of each person included stride length, cadence and ground reaction force. Each gait cycle consisted of one heel strike to the next ipsilateral heel strike. Each person performed a 5-minute running test, and data was collected using a multi-sensor system on a treadmill (including accelerometers and force sensors). The sampling rate of acceleration and force data was 100 Hz. The analysis period was set to 4 weeks, and tests were performed once a week to monitor and evaluate changes in gait stability. A baseline was set for the gait data collected from each participant during the first run, and a machine learning model (such as support vector machine or random forest, etc.) was used to analyze the gait feature data of each participant (such as stride length, cadence, etc.). and force output), calculate a gait stability fitness score, identify the participants with the highest score (most stable gait) and the lowest score (least stable gait) based on the fitness score, calculate the distance of each participant's gait data from the most stable and least stable gaits using Euclidean distance or other appropriate metrics, divide the participants into two subgroups with higher stability and lower stability based on the distance difference, perform further personalized training or intervention on the members of each subgroup, then reassess gait stability in the next analysis period and update the grouping accordingly, perform a final assessment of changes in gait stability for all participants after a preset 4-week analysis period to identify overall trends and any significant changes.

[0140] Specifically, the gait recognition algorithm is a dynamic twin-group strategy gray wolf algorithm. During the iteration process, the distance Range between the current gray wolf individual and the α wolf is calculated respectively. j_sturdiest The distance range from the worst individual in the contemporary era j_shakiest , if Range j_sturdiest ≤(Range j_shakiest) / 2, the gray wolf individuals are divided into a better subgroup with the contemporary optimal position α wolf as the geometric center; otherwise, they are divided into a worse subgroup with the contemporary worse individual as the center. According to the characteristics of the two subgroups, different nonlinear convergence factors are adopted to balance the local search ability and the global search ability. The traditional gray wolf algorithm coordinates the gray wolf population between global and local searches by adjusting the convergence factor. The convergence factor of the standard gray wolf algorithm decreases linearly, and it is difficult to better coordinate the global and local search capabilities. The gait recognition algorithm of the present invention uses different convergence factors for the better subgroup and the worse subgroup. For the better subgroup with higher fitness value, the nonlinear convergence factor value decreases rapidly in the early stage of iteration, so that the gray wolves with higher fitness quickly approach the optimal solution; the nonlinear convergence factor value decreases slowly in the later stage of iteration to avoid local optimality.

[0141] Preferably, according to the gait data of the participants, respectively calculating the distance difference between the gait data of each participant and the most stable gait and the most unstable gait, and dividing the participants into subgroups with higher stability and subgroups with lower stability based on the distance difference comprises the following steps:

[0142] S241, obtaining gait data of each participant, and defining the most stable and the most unstable gait data;

[0143] S242. For each participant, check whether the distance difference between the participant's gait data and the most stable gait is no greater than half the distance difference between the participant's gait data and the most unstable gait;

[0144] S243. If the distance difference between the participant's gait data and the most stable gait is not greater than half of the distance difference between the participant's gait data and the most unstable gait, the participant is divided into a subgroup with higher stability; otherwise, the participant is divided into a subgroup with lower stability.

[0145] To clarify, let's assume we are analyzing a dataset of 20 participants who performed multiple gait tests on a treadmill. Each participant's gait data includes stride length, cadence, and ground reaction force. We define the most stable gait, which has the highest fitness score (smallest stride length, cadence, and ground reaction force coefficient of variation) and the least stable gait, which has the lowest fitness score (largest stride length, cadence, and ground reaction force coefficient of variation). We use the Euclidean distance formula to calculate the distance. For each participant, we calculate the distance to the most stable gait and the least stable gait, and check whether the Range is met. j_sturdiest ≤(Range j_shakiest ) / 2, if it is satisfied, the participant is classified into the subgroup with higher stability; otherwise, the participant is classified into the subgroup with lower stability.

[0146] Preferably, the formula for calculating the distance difference between each participant's gait data and the most stable gait and the most unstable gait is:

[0147]

[0148] In the formula, Range j_sturdiest It is expressed as the distance difference between the gait data of the jth participant and the most stable gait;

[0149] Range j_shakiest It is expressed as the distance difference between the jth participant’s gait data and the most unstable gait;

[0150] M j Represented as the location of the gait data of the jth participant;

[0151] M a The position of the gait data of the participant with the most stable gait is represented;

[0152] M b The location of the participant's gait data represented as the most unstable gait.

[0153] What needs to be explained is:

[0154] Assuming the most stable gait (M a ): step length = 1.5 = 1.5 m, step frequency = 1.8 = 1.8 Hz, ground reaction force = 600 = 600 N;

[0155] The most unstable gait (M b ): step length = 2.0 = 2.0 m, step frequency = 1.2 = 1.2 Hz, ground reaction force = 800 = 800 N;

[0156] Participant A(M j ): step length = 1.6 = 1.6 m, step frequency = 1.7 = 1.7 Hz, ground reaction force = 610 = 610 N, substitute the above parameters into the formula for the difference between the gait data of each participant and the distance between the most stable gait and the most unstable gait:

[0157]

[0158] The calculation results show that: 10.05≤190.37 / 2, which means that the distance difference of participant A meets the conditions, so he is classified into the subgroup with higher stability.

[0159] Preferably, using a factor analysis algorithm to analyze the changing trend of gait stability and obtaining key factors affecting gait stability includes the following steps:

[0160] S31 initializes relevant parameters of the factor analysis algorithm;

[0161] S32, performing preliminary statistical analysis on the gait data of each participant to evaluate their initial stability indicators, and storing the gait data of each participant as baseline data in a variable;

[0162] S33, calculating the measurement parameters according to the factor analysis algorithm, and updating the weight of each participant's gait data;

[0163] S34, after each iteration, recalculating the stability score of each participant's gait data according to the updated weight;

[0164] S35, looping through steps S33 to S34 until the set number of iterations is reached;

[0165] S36. Output the final stability analysis result and determine the key factors affecting gait stability.

[0166] It should be explained that the factor extraction methods including principal component analysis (PCA) were selected, the maximum variance method (Varimax) was used for factor rotation, the upper limit of the number of iterations and the convergence threshold were set (for example, stop when the change in factor loading was less than 0.001), the descriptive statistics (mean, standard deviation, coefficient of variation, etc.) of each participant's data were calculated and stored as baseline data, the factor analysis was run to obtain the factor loading of each factor, the loading scores were used to adjust the weights of each parameter in the gait data, and the stability score was recalculated using the weighted gait parameters, such as considering that the weight factors of stride length and cadence may increase or decrease due to the results of the factor analysis. The change in stability score was evaluated after each iteration, and the factor loadings and weights were adjusted until the results were stable or the upper limit of the number of iterations was reached. The results of the factor analysis were summarized, the most important factors were pointed out (such as the variation of stride length and cadence, etc.), and how these factors affected gait stability was explained.

[0167] Specifically, the factor analysis algorithm is an adaptive crow search algorithm. Based on the crow search algorithm, the adaptive crow search algorithm designs an adaptive value strategy for the two parameters of perception probability and flight distance, which effectively enhances the performance of the algorithm.

[0168] Preferably, evaluating the key factors affecting gait stability with the key factors affecting gait stability known in the database, and adjusting the use strategy of the fitness equipment to optimize gait stability comprises the following steps:

[0169] S41. Establish an initial evaluation matrix based on the key factors affecting gait stability.

[0170] S42, randomly selecting a fitness equipment configuration to analyze the participant's gait, calculating and recording a matching score with other known stability parameters;

[0171] S43, selecting the optimal fitness equipment configuration according to the matching score of the participant's gait stability, and if the selected configuration matches the current fitness equipment configuration, maintaining it; if not, adjusting it to the fitness equipment configuration with the highest score;

[0172] S44, after the configurations of the fitness equipment are evaluated, insert a new configuration as needed, and return to step S42 to continue evaluating the unoptimized configurations of the fitness equipment;

[0173] S45. Calculate the overall gait stability score of the participants according to the final evaluation result, and save the adjusted fitness equipment configuration according to the updated fitness equipment usage strategy;

[0174] S46. Output the optimal fitness equipment configuration and the corresponding gait stability score obtained through evaluation, and adjust the use strategy of the fitness equipment to optimize gait stability.

[0175] It should be explained that the key factors affecting gait stability are integrated, and an evaluation matrix containing these factors is established. According to literature research and experimental data, key factors such as step length, step frequency, ground reaction force, etc. are identified. These factors will constitute the rows of the evaluation matrix, and the columns represent different fitness equipment configurations. Using the exploration mechanism in the ant colony algorithm, different fitness equipment configurations (such as treadmill slope, elastic band strength, etc.) are randomly selected, and the gait data of participants using these configurations are collected. The improved ant colony algorithm is used for multiple sequence alignment to evaluate the degree of match between each configuration and the known stability parameters. According to the score, it is decided whether to keep the current configuration or adjust to a better configuration. Steps S42 and S43 are repeated. Each iteration prioritizes the potentially more effective configuration for testing according to the pheromone path updated by the ant colony algorithm. Based on the data of all iterations, the overall gait stability score is calculated using the global update rule of the ant colony algorithm, and the best configuration is saved. A final report is compiled to explain the optimal fitness equipment configuration determined by the algorithm, and provide specific usage suggestions and gait stability improvement strategies.

[0176] Specifically, the present invention evaluates the key factors affecting gait stability with the key factors affecting gait stability known in the database through a multiple sequence alignment method based on an improved ant colony algorithm. The algorithm changes the pheromone update method, the character selection method, the ants' round-trip search between the ant nest and the food, and the random assignment of the ant start sequence.

[0177] Preferably, randomly selecting a fitness equipment configuration to analyze the participant's gait, calculating and recording a matching score with other known stability parameters comprises the following steps:

[0178] S421, defining configuration parameters of fitness equipment, and setting a variable range for the configuration parameters of fitness equipment;

[0179] S422, randomly select the configuration of each fitness equipment to ensure that the configuration at the beginning of each evaluation is random and non-repetitive;

[0180] S423, the participant sets up the fitness equipment by using the randomly selected configuration, and obtains the participant's gait data;

[0181] S424, comparing the acquired participant's gait data with the known gait stability influencing factors in the database, using a preset scoring model to calculate the matching score of each fitness equipment configuration parameter, and recording the matching score of each fitness equipment configuration and the gait stability factor.

[0182] It should be explained that adjustable parameters and corresponding ranges of variation are defined for each fitness equipment, such as the speed, slope, and hardness of a treadmill. The speed of the treadmill can be adjusted from 4 km / h to 20 km / h, the slope from 0% to 15%, and the hardness has three adjustment options (soft, medium, and hard). Computer-generated random numbers are used to select the combination of configuration parameters to ensure the uniqueness of each experimental configuration. For example, an experiment may use a treadmill with a speed of 12 km / h, a slope of 5%, and a medium hardness. Participants run on the treadmill and use sensors and motion analysis software to collect gait data, including step length, step frequency, and ground reaction force. A preset scoring model (such as based on linear regression, logistic regression, or other statistical models, etc.) is used to calculate the matching degree of the configured gait data with the known stability data. For example, the matching score can be based on the accuracy of predicting gait stability, and the higher the score, the more the configuration can improve gait stability.

[0183] According to another embodiment of the present invention, Figure 2 As shown, a gait stability evaluation system based on the motion data of fitness equipment is also provided, and the gait stability evaluation system based on the motion data of fitness equipment includes:

[0184] The data acquisition module 1 is used to acquire the motion data of the fitness equipment and process the motion data to obtain the key feature data of the motion;

[0185] Gait recognition module 2, used to analyze gait stability of key motion feature data using gait recognition algorithm, and identify the changing trend of gait stability;

[0186] Factor analysis module 3, used to analyze the changing trend of gait stability using factor analysis algorithm to obtain key factors affecting gait stability;

[0187] The stability evaluation module 4 is used to evaluate the key factors affecting gait stability with the key factors affecting gait stability known in the database, and adjust the use strategy of the fitness equipment to optimize gait stability.

[0188] In summary, with the aid of the above-mentioned technical scheme of the present invention, the present invention utilizes the curve amplitude algorithm to perform feature extraction on the key moments of the gait cycle, so that the key movement moments can be accurately identified, and the key moments can be accurately inserted or merged through threshold setting, so as to better capture the dynamic changes of gait. By setting threshold parameters and checking the density of key movement moments, not only the sensitivity of capturing gait stability and key moments is improved, but also data redundancy caused by too dense moments can be avoided, thereby ensuring the specificity and efficiency of the analysis. Accurate feature extraction and identification of key moments make the evaluation more targeted and effective. The use strategy of fitness equipment can be adjusted according to these data, and a more personalized training plan can be designed, thereby more effectively improving gait stability and reducing the risk of falling. The present invention calculates the fitness values ​​of the participants' gait stability, identifies the most stable and the most unstable gaits based on these values, and divides the participants into different subgroups. It can not only reveal the differences between individuals, but also adjust the strategies based on dynamic data updates, thereby improving the overall evaluation and training accuracy. The distance difference is used to classify the participants, which can accurately distinguish the individuals who need extra attention or intervention, while maintaining continuous monitoring of those individuals who already have good gait stability. Through periodic evaluation and group analysis, the training or treatment plan can be continuously optimized and adjusted. Such continuity and feedback loop ensure the timeliness and effectiveness of the intervention measures, thereby helping the participants to achieve significant improvements in gait stability. The present invention can conduct an in-depth evaluation of the gait data of each participant through factor analysis algorithm initialization and statistical analysis, thereby identifying the potential variables that affect the stability of individual gait, providing a scientific basis for understanding and solving the root causes of gait instability, and allowing the evaluation process to dynamically adjust the degree of emphasis on different factors by calculating the metric parameters and updating the weights, ensuring that the evaluation process is more accurate and can adapt to the actual changes in the behavior and gait data of the participants. The final output not only helps to identify which factors are the key to affecting gait stability, but also quantifies the specific impact of these factors on gait stability, making the adjustment of related fitness equipment and training programs more targeted and effective, and then can customize intervention measures according to the specific needs of each participant. The present invention ensures that the optimization of the configuration of the fitness equipment is based on the actual effect data by randomly selecting the configuration of the fitness equipment and calculating the matching score with the known stability parameter, selecting the optimal configuration according to the matching score, and allowing the fitness equipment to be personalized according to the specific gait data of each participant. Such personalized adaptation not only improves the training effect, but also increases the satisfaction and safety of the participants. The summary evaluation and final decision output provide a systematic framework for evaluating and adjusting the configuration of fitness equipment. This not only provides decision support for managers and trainers, but also provides more suitable training equipment for end users.

[0189] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A gait stability evaluation method based on fitness equipment motion data, characterized in that: The gait stability evaluation method based on fitness equipment motion data comprises the following steps: S1. Obtaining motion data of fitness equipment and processing the motion data to obtain key motion feature data; S2. Utilize gait recognition algorithm to analyze gait stability of key motion feature data and identify the changing trend of gait stability; S3, using factor analysis algorithm to analyze the changing trend of gait stability and obtain the key factors affecting gait stability; S4. Evaluate the key factors affecting gait stability with the key factors known in the database, and adjust the use strategy of fitness equipment to optimize gait stability.

2. A gait stability evaluation method based on fitness equipment motion data according to claim 1, characterized in that: The step of obtaining the motion data of the fitness equipment and processing the motion data to obtain the key motion feature data comprises the following steps: S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the motion data of the fitness equipment, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values; S12, connecting the unprocessed data in the motion data to generate a new data table, associating different data tables through external key values ​​to generate a complete data table, obtaining an accurate motion data set, and determining the initial key motion moment of the gait cycle; S13. Using a curve amplitude algorithm, extract features of the initial key motion moment of the gait cycle to obtain key motion feature data.

3. A gait stability evaluation method based on fitness equipment motion data according to claim 2, characterized in that: The method of extracting features from the initial key motion moment of the gait cycle using the curve amplitude algorithm to obtain key motion feature data includes the following steps: S131, constructing a characteristic curve according to the initial key movement moment of the gait cycle, and calculating the amplitude difference of the characteristic curve between adjacent movement moments; S132, setting a threshold parameter. If the amplitude difference is less than the threshold parameter, there is no need to insert a new key motion moment. If the amplitude difference is greater than the threshold, there is a need to insert a new key motion moment. S133, checking the obtained key motion moment set to determine whether there are too dense key motion moments, and if there are too dense key motion moments, obtaining motion key feature data by merging the too dense key motion moments.

4. The gait stability evaluation method based on the motion data of fitness equipment according to claim 1, characterized in that: The method of using a gait recognition algorithm to perform gait stability analysis on key motion feature data and identifying a change trend of gait stability comprises the following steps: S21, presetting the number of participants and analysis period of the gait recognition algorithm, and initializing the gait data of the participants; S22, traversing all participants and calculating the fitness value of gait stability according to the key feature data of the movement; S23, identifying the individuals with the most stable gait and the most unstable gait from the participants, and recording the gait data positions of the individuals with the most stable gait and the most unstable gait; S24, calculating the distance difference between the gait data of each participant and the most stable gait and the least stable gait respectively according to the gait data of the participants, and dividing the participants into a subgroup with higher stability and a subgroup with lower stability based on the distance difference; S25, respectively updating the subgroups with higher stability and the subgroups with lower stability, and then reorganizing after the updates; S26. Repeat steps S22 to S25 until a preset analysis period is reached, and analyze the final participant's gait data to identify the changing trend of gait stability.

5. The gait stability evaluation method based on the motion data of fitness equipment according to claim 4, characterized in that: The method of calculating the distance difference between each participant's gait data and the most stable gait and the most unstable gait according to the participant's gait data, and dividing the participants into a subgroup with higher stability and a subgroup with lower stability based on the distance difference comprises the following steps: S241, obtaining gait data of each participant, and defining the most stable and the most unstable gait data; S242. For each participant, check whether the distance difference between the participant's gait data and the most stable gait is no greater than half the distance difference between the participant's gait data and the most unstable gait; S243. If the distance difference between the participant's gait data and the most stable gait is not greater than half of the distance difference between the participant's gait data and the most unstable gait, the participant is divided into a subgroup with higher stability; otherwise, the participant is divided into a subgroup with lower stability.

6. A gait stability evaluation method based on fitness equipment motion data according to claim 5, characterized in that: The formula for calculating the distance difference between each participant's gait data and the most stable gait and the most unstable gait is: In the formula, Range j_sturdiest It is expressed as the distance difference between the gait data of the jth participant and the most stable gait; Range j_shakiest It is expressed as the distance difference between the jth participant’s gait data and the most unstable gait; M j Represented as the location of the gait data of the jth participant; M a The position of the gait data of the participant with the most stable gait is represented; M b The location of the participant's gait data represented as the most unstable gait.

7. The gait stability evaluation method based on the motion data of fitness equipment according to claim 1, characterized in that: The method of analyzing the changing trend of gait stability by using a factor analysis algorithm to obtain key factors affecting gait stability comprises the following steps: S31 initializes relevant parameters of the factor analysis algorithm; S32, performing preliminary statistical analysis on the gait data of each participant to evaluate their initial stability indicators, and storing the gait data of each participant as baseline data in a variable; S33, calculating the metric parameters according to the factor analysis algorithm, and updating the weight of each participant's gait data; S34, after each iteration, recalculating the stability score of each participant's gait data according to the updated weight; S35, looping through steps S33 to S34 until the set number of iterations is reached; S36. Output the final stability analysis result and determine the key factors affecting gait stability.

8. The gait stability evaluation method based on the motion data of fitness equipment according to claim 1, characterized in that: The step of evaluating the key factors affecting gait stability with the key factors affecting gait stability known in the database and adjusting the use strategy of fitness equipment to optimize gait stability comprises the following steps: S41. Establish an initial evaluation matrix based on the key factors affecting gait stability. S42, randomly selecting a fitness equipment configuration to analyze the participant's gait, calculating and recording a matching score with other known stability parameters; S43, selecting the optimal fitness equipment configuration according to the matching score of the participant's gait stability, and if the selected configuration matches the current fitness equipment configuration, maintaining it; if not, adjusting it to the fitness equipment configuration with the highest score; S44, after the configurations of the fitness equipment are evaluated, insert a new configuration as needed, and return to step S42 to continue evaluating the unoptimized configurations of the fitness equipment; S45. Calculate the overall gait stability score of the participants according to the final evaluation result, and save the adjusted fitness equipment configuration according to the updated fitness equipment usage strategy; S46. Output the optimal fitness equipment configuration and the corresponding gait stability score obtained through evaluation, and adjust the use strategy of the fitness equipment to optimize gait stability.

9. The gait stability evaluation method based on the motion data of fitness equipment according to claim 8, characterized in that: The randomly selected fitness equipment configuration is used to analyze the participant's gait, and the matching score with other known stability parameters is calculated and recorded, including the following steps: S421, defining fitness equipment configuration parameters, and setting a variable range for the fitness equipment configuration parameters; S422, randomly select the configuration of each fitness equipment to ensure that the configuration at the beginning of each evaluation is random and non-repetitive; S423, the participant sets up the fitness equipment by using the randomly selected configuration, and obtains the participant's gait data; S424, comparing the acquired participant's gait data with the known gait stability influencing factors in the database, using a preset scoring model to calculate the matching score of each fitness equipment configuration parameter, and recording the matching score of each fitness equipment configuration and the gait stability factor.

10. A gait stability evaluation system based on fitness equipment motion data, used to implement the gait stability evaluation method based on fitness equipment motion data according to any one of claims 1 to 9, characterized in that: The gait stability evaluation system based on the motion data of fitness equipment includes: A data acquisition module is used to acquire the motion data of the fitness equipment and process the motion data to obtain key motion feature data; A gait recognition module is used to analyze the gait stability of key motion feature data using a gait recognition algorithm and identify the changing trend of gait stability; A factor analysis module is used to analyze the changing trend of gait stability using a factor analysis algorithm to obtain key factors affecting gait stability; The stability evaluation module is used to evaluate the key factors affecting gait stability with the key factors affecting gait stability known in the database, and adjust the use strategy of fitness equipment to optimize gait stability.

Images