Exercise evaluation system and method based on multi-dimensional data analysis
Through the multi-dimensional data analysis exercise evaluation system, the problem of difficulty in evaluating movement norms and muscle status in training of high-intensity professionals such as firefighters is solved, and the accurate evaluation of movement norms and muscle activation status is achieved, which improves the training quality and security.
Patent Information
- Application Number
- CN202411164597.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-22
AI Technical Summary
It is difficult to accurately determine whether high-intensity professionals such as firefighters comply with standard movement specifications and muscle activation and compensation during training, resulting in low training quality and high risk of injury.
Using a motor evaluation system based on multi-dimensional data analysis, the data collector collects the electromyography signal and posture data, the processor divides and analyzes the data, querys the action template database, and generates the motor evaluation results, including joint angle change scores and muscle activation scores. and response index, used to evaluate movement normativeness and muscle status.
It improves the accuracy of movement normative and muscle activation conditions, provides targeted training guidance, and reduces the risk of injury and the probability of accidents during training.
Smart Images

Figure CN118986339A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of motion assessment and the technical field of biological signal processing, and in particular to a motion assessment system and method based on multi-dimensional data analysis. Background Art
[0002] For some professions, such as firefighters, they need to perform tasks in high-intensity and high-risk environments. Therefore, people engaged in such professions need to have high physical fitness. On this basis, daily training is not only an important means to ensure that such personnel can effectively complete their tasks, but also a necessary condition to improve their occupational safety and health. However, the current training lacks a scientific monitoring and evaluation mechanism, making it difficult to provide timely feedback on the physical condition of such personnel during training, and it is also difficult to prevent and reduce injuries and accidents that may occur during training.
[0003] In order to solve the above problems, some researchers have tried to monitor the physical indicators of the above-mentioned personnel during training, such as heart rate, blood pressure, blood oxygen saturation, body temperature, respiratory rate, sweat composition and other physiological indicators.
[0004] In the process of realizing the inventive concept of the present disclosure, the inventors found that although the above-mentioned indicators can reflect the physiological characteristics of the above-mentioned persons to a certain extent, it is difficult to accurately judge whether the movements of the above-mentioned persons conform to the standard movement specifications, and it is also difficult to accurately determine the muscle activation and compensation status of the above-mentioned persons during exercise. Summary of the invention
[0005] In view of the above problems, the present disclosure provides a motion evaluation system and method based on multi-dimensional data analysis.
[0006] According to a first aspect of the present disclosure, a motion assessment system based on multidimensional data analysis is provided, comprising: a data collector, for collecting I multidimensional data of a target object when the target object is moving, wherein each multidimensional data comprises an electromyographic signal and posture data, and the I multidimensional data corresponds to I time moments, where I is an integer greater than 1; a processor, connected to the data collector, for: dividing the I multidimensional data based on the I posture data to obtain N multidimensional data groups, wherein each multidimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I; querying N groups of target template information corresponding to the N multidimensional data groups from an action template database; and analyzing the N multidimensional data groups based on the N groups of target template information to obtain a motion assessment result corresponding to the target object.
[0007] According to an embodiment of the present disclosure, the processor is also used to: determine J action change moments of the target object from I moments by matching pre-stored action change posture data with I posture data, wherein the action change posture data characterizes the limb posture when the object changes action, and J is an integer greater than or equal to 1 and less than I; based on the J action change moments, divide the I multi-dimensional data to obtain N multi-dimensional data groups.
[0008] According to an embodiment of the present disclosure, posture data includes acceleration change values and joint angle values; action change posture data includes pre-stored acceleration change values and pre-stored joint angle values; the processor is also used to: from I acceleration change values, identify E target acceleration change values that match the pre-stored acceleration change values, E is a positive integer less than I; from I joint angle values, identify Q target joint angle values that match the pre-stored joint angle value, Q is a positive integer less than I; based on the moments corresponding to the E target acceleration change values and the moments corresponding to the Q target joint angle values, determine J action change moments.
[0009] According to an embodiment of the present disclosure, the processor is also used to: determine, based on the nth multidimensional data group among the N multidimensional data groups, candidate motion information matching the nth multidimensional data group from the candidate motion information matching the n-1th multidimensional data group among the N multidimensional data groups, where n is an integer less than or equal to N and greater than 1; determine the candidate motion information matching the Nth multidimensional data group as motion information; and based on the motion information, query and obtain N groups of target template information from an action template database.
[0010] According to an embodiment of the present disclosure, the target object is an object that has performed target training movements; the posture data includes joint angle values; the target template information includes template posture data and template electromyographic signals, and the template posture data includes template joint angle change rates; the processor is also used to: for an nth multidimensional data group among N multidimensional data groups, based on the joint angle values in the nth multidimensional data group and the movement period corresponding to the nth multidimensional data group, determine the nth joint angle change rate of the target object, where n is a positive integer less than or equal to N; based on the nth joint angle change rate and the nth template joint angle change rate, generate an nth joint angle change score, wherein the joint angle change score is used to characterize the joint flexion condition of the target object during the movement; based on the nth multidimensional data group and the nth template electromyographic signals number, generate the nth muscle activation score of the target object, wherein the muscle activation score is used to characterize the degree of muscle activation of the target object; calculate the reaction index of the target object based on the N joint angle change scores and the N muscle activation scores, wherein the reaction index is used to characterize the reaction status of the muscles and joints of the target object during the movement; obtain the pre-stored reaction index of the target object before performing the target training movement, wherein the movement corresponding to the pre-stored reaction index is the same as the movement corresponding to the reaction index; based on the reaction index and the pre-stored reaction index of the target object, generate a movement evaluation result corresponding to the target training movement, wherein the pre-stored reaction index is obtained when the target object that has not performed the target training movement performs the movement, and the movement evaluation result is used to characterize the activation ability of the target training movement on the joints and muscles of the target object.
[0011] According to an embodiment of the present disclosure, the processor is also used to: determine the nth first target moment and the nth second target moment from the motion period corresponding to the nth multidimensional data group based on the joint angle value in the nth multidimensional data group, wherein the first target moment represents the moment when the joint bending angle of the target object is minimum, and the second target moment represents the moment when the joint bending angle of the target object is maximum; calculate the nth joint bending duration of the target object based on the nth first target moment and the nth second target moment; calculate the nth joint angle change of the target object based on the joint angle value corresponding to the nth first target moment and the joint angle value corresponding to the nth second target moment; calculate the nth joint angle change rate of the target object based on the nth joint angle change and the nth joint bending duration.
[0012] According to an embodiment of the present disclosure, the processor is also used to: calculate the nth electromyography root mean square value based on the electromyography signals in the nth multidimensional data group; calculate the nth template electromyography root mean square value based on the nth group of template electromyography signals; calculate the nth muscle activation score based on the nth electromyography root mean square value and the nth template electromyography root mean square value.
[0013] According to an embodiment of the present disclosure, the system also includes a human-computer interaction interface, which is connected to a processor; the processor is also used to: determine a risk object from the B target objects based on motion evaluation results corresponding to B target objects, wherein the B target objects are different, the risk object represents the object with the highest risk of sports injury among the B target objects, and B is an integer greater than 1; generate training suggestion information based on the motion evaluation results corresponding to the risk object and the multi-dimensional data corresponding to the risk object, wherein the training suggestion information includes training exercises recommended for the target object; and control the human-computer interaction interface to display the training suggestion information.
[0014] According to an embodiment of the present disclosure, the data collector includes a surface electromyography sensing unit and an inertial measurement unit; the surface electromyography sensing unit is also used to: collect the initial electromyography signal of the target object by using the electromyography acquisition electrode worn by the target object; the processor is also used to: perform DC filtering on the initial electromyography signal to obtain a first filtered electromyography signal; perform industrial frequency notch filtering on the first filtered electromyography signal to obtain a second filtered electromyography signal; perform 4th-order 20~500Hz Butterworth bandpass filtering on the second filtered electromyography signal to obtain a third filtered electromyography signal; perform full-wave rectification on the third filtered electromyography signal to obtain a rectified electromyography signal; perform 6 Hz Butterworth low-pass filtering on the rectified electromyography signal to obtain an electromyography signal envelope; and normalize the electromyography signal envelope to obtain an electromyography signal. The inertial measurement unit is also used to: collect initial posture data of the target object by using the inertial measurement unit worn by the target object; the processor is also used to: perform 4th-order 5Hz zero-lag Butterworth low-pass filtering on the initial posture data to obtain filtered posture data; and perform zero-point drift elimination on the filtered posture data to obtain posture data.
[0015] According to a second aspect of the present disclosure, a motion assessment method based on multidimensional data analysis is provided, comprising: when a target object is moving, collecting I multidimensional data of the target object, wherein each multidimensional data comprises an electromyographic signal and posture data, and the I multidimensional data corresponds to I time moments, where I is an integer greater than 1; based on the I posture data, dividing the I multidimensional data to obtain N multidimensional data groups, wherein each multidimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I; querying N groups of target template information corresponding to the N multidimensional data groups from an action template database; based on the N groups of target template information, analyzing the N multidimensional data groups to obtain a motion assessment result corresponding to the target object.
[0016] According to the embodiments of the present disclosure, the target object's motion phases are divided according to the collected posture data to obtain a multi-dimensional data group corresponding to each motion phase. On this basis, the multi-dimensional data group of each motion phase of the target object is analyzed by using the target template information corresponding to each multi-dimensional data group in the motion template database, thereby improving the accuracy of judging whether the target object's motion during the motion process conforms to the standard motion specification, and improving the accuracy of determining the target object's muscle activation status and compensation status when performing the motion. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:
[0018] Figure 1 The schematic diagram shows an architecture diagram of a motion assessment system based on multi-dimensional data analysis according to the first embodiment of the present disclosure.
[0019] Figure 2 A schematic diagram of a vertical jump landing motion according to an embodiment of the present disclosure is schematically shown.
[0020] Figure 3 The flowchart of the method for determining a landmark point according to an embodiment of the present disclosure is schematically shown.
[0021] Figure 4 The flowchart of the method for generating training suggestion information according to an embodiment of the present disclosure is schematically shown.
[0022] Figure 5 The schematic diagram shows an architecture diagram of a motion assessment system based on multi-dimensional data analysis according to the second embodiment of the present disclosure.
[0023] Figure 6 A schematic diagram of a motion assessment method based on multi-dimensional data analysis according to an embodiment of the present disclosure is schematically shown.
[0024] Figure 7 The block diagram of an electronic device implemented based on a processor according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION
[0025] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.
[0026] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.
[0027] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.
[0028] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).
[0029] In the process of realizing the invention concept disclosed in the present invention, the inventors found that although the above-mentioned indicators can reflect the physiological characteristics of the above-mentioned personnel, it is difficult to accurately judge whether the movements of the above-mentioned personnel follow the standard movement specifications, and it is difficult to accurately determine whether the above-mentioned personnel have abnormal movements or compensation conditions during the movement process. Therefore, it is difficult to provide targeted training guidance for the above-mentioned personnel to improve the quality of training and reduce the risk of injury. Among them, the standard movement specifications refer to the correct movement essentials and techniques that the above-mentioned personnel need to follow when performing training movements, which determines the training effect and safety of the above-mentioned personnel. Abnormal movements or compensation conditions refer to muscle activation or movement patterns that do not meet the standard movement specifications when the above-mentioned personnel perform training movements due to the influence of muscle function or fatigue level. It will reduce the training effect and safety of the above-mentioned personnel and increase the risk of injury and accidents.
[0030] Taking firefighters as an example, muscle function and fatigue level will directly affect the firefighters' athletic performance and safety. Muscle function refers to the strength, speed, endurance, coordination and other characteristics of muscles during contraction and relaxation, which determines the firefighters' athletic ability and efficiency. Muscle fatigue refers to the phenomenon of decreased muscle function due to changes in energy metabolism, nerve conduction, muscle fiber structure and other factors after long-term or high-intensity exercise. It will reduce the firefighters' athletic performance and safety and increase the risk of injury and accidents.
[0031] Therefore, monitoring and evaluating the muscle function and fatigue level of firefighters during training, as well as standard movement specifications and abnormal movements or compensation conditions, is of great significance for optimizing firefighters' training plans, improving firefighters' training effects and physical conditions, and preventing and reducing risks and injuries during training.
[0032] Based on this, the inventors found that there are still some problems and deficiencies in the training monitoring and evaluation of firefighters. Therefore, a system is needed that can comprehensively, accurately and timely reflect the muscle function and fatigue level of firefighters, as well as abnormal movements or compensation conditions, to guide and optimize the training plans of firefighters, improve the training effects of firefighters, and prevent and reduce risks and injuries during training. It should be understood that the disclosure only uses firefighters as examples and is not intended to limit the content of the embodiments of the disclosure.
[0033] In view of this, the present disclosure provides a motion evaluation system based on multidimensional data analysis, including: a data collector, which is used to collect I multidimensional data of the target object when the target object is moving, wherein each multidimensional data includes electromyographic signals and posture data, and I multidimensional data corresponds to I time, and I is an integer greater than 1. A processor is connected to the data collector and is used to: divide the I multidimensional data based on I posture data to obtain N multidimensional data groups, wherein each multidimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I. From the action template database, query N groups of target template information corresponding to the N multidimensional data groups. Based on the N groups of target template information, analyze the N multidimensional data groups to obtain a motion evaluation result corresponding to the target object.
[0034] Figure 1 The schematic diagram shows an architecture diagram of a motion assessment system based on multi-dimensional data analysis according to the first embodiment of the present disclosure.
[0035] like Figure 1 As shown, the motion assessment system based on multi-dimensional data analysis of this embodiment includes a data collector 110 and a processor 120 .
[0036] According to an embodiment of the present disclosure, the data collector 110 can be worn on the target object, and is used to collect I multi-dimensional data of the target object when the target object is exercising. Each multi-dimensional data includes electromyographic signals and posture data, and I multi-dimensional data corresponds to I time, where I is an integer greater than 1.
[0037] The target object may be an object to be detected. The motion may be a detection motion for detecting the condition of the object. The detection dimension includes but is not limited to at least one of a physical state and a motor ability. The physical state includes but is not limited to at least one of a muscle state and a joint state. However, the embodiments of the present disclosure are not limited thereto. In other embodiments of the present disclosure, the motion may also be a training motion for training the motor ability of the object.
[0038] The data collector 110 includes a surface electromyography sensing unit and an inertial measurement unit. The surface electromyography sensor is used to collect electromyographic signals of the target object by using electromyographic acquisition electrodes worn by the target object. The inertial measurement unit is used to collect the posture data of the target object. The electromyographic acquisition electrodes can be located on the vastus lateralis (VL), vastus medialis (VM), rectus femoris (RF), biceps femoris (BL), semitendinosus (SE), tibialis anterior (TIA), medial gastrocnemius (GAS.M) and lateral gastrocnemius (GAS.L) of the target object. The inertial measurement unit is located on the thigh, calf and foot of the target object. In the embodiment of the present disclosure, the electromyographic acquisition electrodes can be attached to the dominant limb of the target object. Similarly, the inertial measurement unit can also be tied to the dominant limb of the target object.
[0039] The above-mentioned electromyographic signal may be a surface electromyography (sEMG) signal. Surface electromyography is a non-invasive, painless and non-destructive technology that records the electrical signals generated when muscles contract by attaching electrodes to the surface of the skin. The electrical signal is used to reflect the electrophysiological activity of the muscle. The advantage of this technology is that it can measure the activity state of the muscle in real time, continuously and dynamically, without being affected by the environment and movement mode, and does not interfere with the normal movement of the firefighter. It should be noted that the present disclosure only uses firefighters as an example. It can be understood that the motion assessment system of the present disclosure can also be used for other similar occupations, including but not limited to athletes, etc. The sEMG signal is closely related to functional parameters such as muscle strength and fatigue. By processing the sEMG signal and extracting the characteristic parameters, it can be used as a means to effectively monitor and evaluate muscle function and fatigue.
[0040] The above-mentioned posture data may include but is not limited to at least one kinematic parameter of the displacement, velocity, angle and acceleration of the target object that can describe the motion characteristics. The advantage of kinematic analysis is that it can intuitively, objectively and quantitatively reflect the posture of the target object.
[0041] According to an embodiment of the present disclosure, the processor 120 is connected to the data collector 110. The connection between the processor 120 and the data collector 110 may be a communication connection, an electrical connection, etc. Thus, the processor 120 can receive and process the electromyographic signal and posture data from the data collector 110.
[0042] For example, the processor 120 may preprocess the electromyographic signal and posture data received from the data collector 110 to obtain preprocessed electromyographic signal and preprocessed posture data.
[0043] Specifically, the surface electromyography sensing unit is used to collect the initial electromyography signal of the target object by using the electromyography collection electrode worn by the target object. The processor 120 is used to perform a DC filter on the initial electromyography signal to obtain a first filtered electromyography signal. Perform a power frequency notch filter on the first filtered electromyography signal to obtain a second filtered electromyography signal. Perform a 4th-order 20-500 Hz Butterworth bandpass filter on the second filtered electromyography signal to obtain a third filtered electromyography signal, wherein the power frequency is 50 Hz. Perform a full-wave rectification on the third filtered electromyography signal to obtain a rectified electromyography signal. Perform a 6 Hz Butterworth low-pass filter on the rectified electromyography signal to obtain an electromyography signal envelope. Normalize the electromyography signal envelope to obtain an electromyography signal. For example, the electromyography signal envelope can be normalized according to the maximum value of the electromyography signal envelope to obtain a preprocessed electromyography signal. Through the above preprocessing process, the noise in the initial electromyography signal can be removed in a targeted manner to obtain an accurate electromyography signal, which helps to extract accurate electromyography signal features.
[0044] The inertial measurement unit is used to collect the initial posture data of the target object by using the inertial measurement unit worn by the target object. The processor 120 is used to perform a 4th-order 5Hz zero-lag Butterworth low-pass filter on the initial posture data to obtain filtered posture data. Zero drift is eliminated on the filtered posture data to obtain preprocessed posture data. Through the above preprocessing process, high-frequency noise in the initial posture data can be removed in a targeted manner to obtain accurate posture data, which helps to extract accurate posture features.
[0045] For example, the processor 120 is further configured to: divide the I multidimensional data based on the I posture data to obtain N multidimensional data groups, wherein each multidimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to 1. Query N groups of target template information corresponding to the N multidimensional data groups from the motion template database. Based on the N groups of target template information, analyze the N multidimensional data groups to obtain a motion evaluation result corresponding to the target object.
[0046] It is understandable that the motion performed by the target object may include N motion stages. I posture data may be used to identify the motion stage to which each multidimensional data belongs. For example, the extreme value in I posture data may be used to identify the motion stage to which the multidimensional data belongs. Based on this, I multidimensional data may be divided by I posture data to obtain a multidimensional data group corresponding to each motion stage.
[0047] For example, the processor 120 is used to: determine J action change moments of the target object from I moments by matching the pre-stored action change posture data with I posture data, wherein the action change posture data characterizes the limb posture when the object changes the action, and J is an integer greater than or equal to 1 and less than I. Based on the J action change moments, the I multidimensional data are divided to obtain N multidimensional data groups. Based on this, by matching the action change posture data with the I posture data, the target posture data matching the action change posture data can be determined from the I posture data, thereby the moment corresponding to the target posture data can be determined as the action change moment. On this basis, by dividing the I multidimensional data according to the action change moment, the multidimensional data group corresponding to each movement stage can be accurately obtained.
[0048] In one embodiment of the present disclosure, the pre-stored action change posture data is manually determined from historical posture data of the target object. In another embodiment of the present disclosure, the above-mentioned action change posture data can also be manually determined from historical posture data collected from other objects different from the target object when performing the same movement as the target object.
[0049] In an embodiment of the present disclosure, the multi-dimensional data of the target object that has been collected can be matched with the historical multi-dimensional data of each of the M candidate motions stored in the database to determine the target motion that matches the motion being performed by the target object from the M candidate motions, where M is a positive integer greater than 1, and the database can be the above-mentioned action template database, or other databases different from the above-mentioned action template database, which is not limited by the present disclosure. On this basis, the action change posture data stored in association with the target motion can be determined as the above-mentioned action change posture data for matching with I posture data. Based on this, by matching the multi-dimensional data of the target object with the historical multi-dimensional data, the motion being performed by the target object can be accurately determined, thereby determining accurate action change posture data, accurately determining the above-mentioned action change time, and then accurately dividing the multi-dimensional data group according to the action change time.
[0050] Specifically, based on the n-th multidimensional data group among the N multidimensional data groups, the candidate motion information matching the n-th multidimensional data group among the N multidimensional data groups can be determined from the candidate motion information matching the n-1-th multidimensional data group among the N multidimensional data groups, where n is an integer less than or equal to N and greater than 1. The candidate motion information matching the N-th multidimensional data group is then determined as the motion information. Then, the action change posture data stored in association with the motion information is determined as the above-mentioned pre-stored action change posture data. Thus, by performing motion matching on each multidimensional data group, the action change posture data can be accurately determined.
[0051] However, the embodiments of the present disclosure are not limited thereto. In the embodiments of the present disclosure, a motion identifier input by the target object may be obtained, and the motion performed by the target object may be determined based on the motion identifier, thereby querying the above database to obtain the motion change posture data.
[0052] On this basis, the action change posture data that matches the action being performed by the target object can be matched with the above-mentioned posture data to identify the action change moment in I moments. For example, the posture data includes acceleration change values and joint angle values. The action change posture data includes pre-stored acceleration change values and pre-stored joint angle values. The processor 120 is also used to: from I acceleration change values, identify E target acceleration change values that match the pre-stored acceleration change values, E is a positive integer less than I. From I joint angle values, identify Q target joint angle values that match the pre-stored joint angle values, Q is a positive integer less than I. Based on the moments corresponding to the E target acceleration change values and the moments corresponding to the Q target joint angle values, J action change moments are determined. Thus, I multidimensional data can be divided according to the J action change moments to obtain N multidimensional data groups. Therefore, by respectively matching the acceleration change value and the joint angle value in the posture data, the target joint angle value and the target acceleration change value are determined, so that the moment corresponding to at least one of the target joint angle value and the target acceleration change value is determined as the action change moment, thereby improving the accuracy of determining the action change moment.
[0053] The following combination Figure 2 , taking the vertical jump landing movement as an example, the multi-dimensional data division process of the present disclosure is specifically described. It should be understood that the content is only an exemplary embodiment and is not used to limit the movement performed by the target object in the embodiment of the present disclosure.
[0054] The vertical jump landing is a lower extremity strength training paradigm that consists of the subject jumping off a fixed platform, landing on both feet, then immediately performing a maximal effort vertical jump, and landing again. Figure 2As shown, in the disclosed embodiment, the vertical jump landing motion is pre-divided into two phases: a braking phase and a propulsion phase. The braking phase is defined as the phase from when the target object's feet touch the ground after jumping from a height to when the knee joint reaches the maximum flexion angle; the propulsion phase is defined as the phase from when the target object's knee joint reaches the maximum flexion angle to when the feet leave the ground again.
[0055] When analyzing the electromyographic signals of the vertical jump landing task, it is necessary to automatically divide the vertical jump landing movement into stages. The method for dividing the movement stage includes: ① analyzing the raw data provided by the IMU on the thigh and calf segments of the target object to obtain the knee joint angle data, so that the moment corresponding to the maximum flexion angle of the knee joint can be determined according to the knee joint angle data; ② in the first jump of the target object, the foot suddenly changes to 0 at the moment of contact with the ground, and the acceleration will also change dramatically. The characteristics of this change can be found as the landmark point for dividing the stage, and the landmark point corresponds to the above-mentioned action change moment, and the other landmark points in the embodiment of the present disclosure are the same; ③ at the moment when the feet of the target object leave the ground in the second jump, the speed of the foot increases rapidly from 0, and the acceleration will also change dramatically. The characteristics of this change can be found as the landmark point for dividing the stage. The acceleration data measured by the IMU deployed on the foot, thigh and calf segments can be used, after smoothing by a 4th-order 5Hz zero-lag Butterworth low-pass filter, and compared with the kinematic data obtained by the motion capture system and the ground reaction force data provided by the three-dimensional force platform, to find the characteristic landmark points to divide the movement stage. The kinematic data obtained by the motion capture system may include spatial position data of marker points. The above ground reaction force data may be used as core reference data for comparison.
[0056] Figure 3 The flowchart of the method for determining a landmark point according to an embodiment of the present disclosure is schematically shown.
[0057] like Figure 3 As shown, the landmark determination method of this embodiment includes operations S301 to S307.
[0058] In operation S301 , after the target object jumps off the box and at the moment when the foot contacts the ground, first acceleration data corresponding to the foot of the target object is collected by using an IMU.
[0059] In operation S302, the first acceleration data and the kinematic data of the motion capture system are analyzed to obtain a first pre-stored acceleration change value.
[0060] In operation S303, for the moment of maximum flexion of the knee joint of the target object, the original data collected by the IMU at this moment is analyzed to obtain the joint angle data of the target object at this moment, and the joint angle data is used to characterize the angle between the thigh and calf of the target object.
[0061] In operation S304, the joint angle data and the kinematic data of the motion capture system are analyzed to obtain pre-stored joint angle values.
[0062] In operation S305 , at the moment when both feet of the target object leave the ground after the target object jumps up again and the moment when the feet touch the ground, second acceleration data corresponding to the feet of the target object is collected by using an IMU.
[0063] In operation S306, the second acceleration data and the kinematic data of the motion capture system are analyzed to obtain a second pre-stored acceleration change value.
[0064] In operation S307, pre-stored action change posture data corresponding to the vertical jump landing is obtained based on the first pre-stored acceleration change value, the pre-stored joint angle value, and the second pre-stored acceleration change value.
[0065] The first pre-stored acceleration change value and the second pre-stored acceleration change value may correspond to the velocity mutation point of the target object. The other pre-stored acceleration change values in the disclosed embodiment are similar and will not be described in detail here. The pre-stored joint angle value corresponds to the maximum angle of joint flexion of the target object. The other pre-stored joint angle values in the disclosed embodiment are similar and will not be described in detail here.
[0066] It should be noted that the above example only shows the process of dividing I electromyographic signals. It should be understood that in the disclosed embodiment, the process of dividing I posture data is also included. The process of dividing I posture data is similar to the above process and will not be repeated here. Based on this, it can be achieved according to the movement stage, and a multi-dimensional data group corresponding to each movement stage is obtained.
[0067] In the embodiment of the present disclosure, for the multi-dimensional data group corresponding to each motion stage, the target template information corresponding to the motion stage can be queried from the action template database.
[0068] For example, the processor 120 is used to: determine candidate motion information matching the nth multidimensional data group from candidate motion information matching the n-1th multidimensional data group among the N multidimensional data groups based on the nth multidimensional data group among the N multidimensional data groups, where n is an integer less than or equal to N and greater than 1. The candidate motion information matching the Nth multidimensional data group is determined as motion information. Based on the motion information, N groups of target template information are queried from the action template database.
[0069] The candidate motion information may be information to be determined as the motion being performed by the target object. By matching the N multi-dimensional data groups and the candidate motion information layer by layer, the information of the motion being performed by the target object can be efficiently and accurately determined from the candidate motion information when the target object does not pre-set the motion being performed, thereby obtaining the target template information corresponding to the motion being performed by the target object.
[0070] The above-mentioned action template database can be a database under standard actions established by standardizing and normalizing the actions through kinematic analysis. For example, the database stores target template information corresponding to standard actions. The target template information can be representative action feature parameters obtained by collecting, processing, analyzing, and other operations on the surface electromyographic signals and kinematic data during the object's movement. The target template information may include template electromyographic signals corresponding to the above-mentioned surface electromyographic signals and template posture data corresponding to the above-mentioned kinematic data. Based on this, the action template database can be used to provide standard data and target data for actions, thereby evaluating and guiding the actions of the target object, thereby improving the movement effect and safety of the target object.
[0071] In the embodiments of the present disclosure, the initial electromyographic signal collected within the historical period can be processed by DC filtering, power frequency notch filtering, 4th-order 20-500 Hz Butterworth bandpass filtering, full-wave rectification, 6 Hz Butterworth low-pass filtering and normalization to obtain a template electromyographic signal. The processing process is similar to the preprocessing process of the above-mentioned electromyographic signal and will not be elaborated here.
[0072] In an embodiment of the present disclosure, the initial posture data collected in the historical period can be subjected to a 4th-order 5Hz zero-lag Butterworth low-pass filter to obtain filtered posture data. In this way, high-frequency noise in the initial posture data can be removed. Then, by detecting the resting bias in the static state, calibration is performed to eliminate zero drift, and then a lower limb motion model is established based on the static calibration to obtain knee and ankle joint angle data. Template posture data can be obtained in this way. This processing process is similar to the above-mentioned preprocessing process of the posture data, and will not be repeated here.
[0073] Taking the above-mentioned vertical jump landing movement as an example, the above-mentioned action template database contains a set of accurate, flexible, easy-to-use and supplementary template electromyographic signals for vertical jump landing movement, which are exclusively owned. Due to the precise collection and processing of data from multiple strictly selected subjects, the template electromyographic signal has a high degree of accuracy and stability. Moreover, the exclusive nature of the template electromyographic signal means that all subsequent operations are based on this template electromyographic signal. A specially designed algorithm or system can be used to achieve specific functions or purposes by comparing with the unique template electromyographic signal for vertical jump landing movement.
[0074] Based on the above content, the template posture data stored in the action template database may include template posture features. The template electromyographic signals stored in the action template database may include template electromyographic signal features. Based on this, in the embodiment of the present disclosure, the posture data and electromyographic signals of the target object can be feature extracted respectively, so as to obtain the posture features and electromyographic signal features of the target object. For example, the start and end time points of the action can be determined based on the kinematic data, and the electromyographic signals within the action execution time period can be intercepted, wherein the start and end time points correspond to the above-mentioned action change time. Thus, the electromyographic signal features can be extracted from the electromyographic signals within the time period, and the electromyographic signal features can be used as the template electromyographic signals. The electromyographic signal features may include the root mean square value, the integrated electromyographic value, the average power frequency value, the muscle co-contraction index, the muscle synergy pattern, etc. of the electromyographic signal.
[0075] In the disclosed embodiment, in order to evaluate the muscle contraction strategy of the target object, that is, how the target object coordinates and controls the contraction of different muscle groups when performing training movements, the present invention extracts the following characteristic parameters from the electromyographic signal:
[0076] The Co-contraction Index (CCI) is used to reflect the coordination relationship between the antagonist muscles and the agonist muscles. Its external manifestation is the stability and stiffness of the oppositely acting muscles around each joint, and then reflects the factors that maintain the stability of the joints when affected by the external environment (such as severe impact force) during exercise.
[0077] (1)
[0078] Among them, CCI is the muscle co-contraction index. EMG ANT EMG is the root mean square value (RMS) of the antagonist muscle; AG is the root mean square value (RMS) of the electromyography of the agonist muscle. The antagonist muscle is defined as the muscle or muscle group with lower activity during the action phase, that is, the muscle or muscle group with a smaller RMS. The agonist muscle is defined as the muscle or muscle group with higher activity during the action phase, that is, the muscle or muscle group with a larger RMS.
[0079] Muscle synergy (MS) refers to how a group of muscles work together to produce effective movement in a specific movement task. This involves adjustments in the activation sequence, amplitude, and timing of specific muscles.
[0080] V m*n =W m*s * H s*n (2)
[0081] Among them, V m*n is the myoelectric signal matrix. m*s is the synergy coefficient matrix. s*n is the activation coefficient matrix. Where m is the number of muscles. n is the number of data points of the electromyographic signal. s is the number of synergies.
[0082] EMG amplitude-related parameters are used to measure the intensity of muscle contraction and reflect muscle strength and fatigue, such as root mean square (RMS), integral electromyography (iEMG), mean frequency (MF), etc.
[0083] Exemplarily, the processor 120 of the embodiment of the present disclosure may include a data processing module and a standard action comparison module. The data processing module transmits the characteristic parameters of the electromyographic signal and the posture data to the action analysis module, and the action analysis module compares and analyzes the characteristic parameters with the corresponding standard template in the action template database to generate a motion evaluation result, so that it can be judged whether the action is standard based on the motion evaluation result, or whether there is abnormal muscle activation or compensation during the action, wherein the standard template corresponds to the above-mentioned target template information. The method for the action analysis module to perform analysis includes at least one of the following:
[0084] (1) Similarity-based methods, that is, calculating the similarity between feature parameters and target template information, such as Euclidean distance, cosine similarity, correlation coefficient, etc., and judging whether the action is standard or not according to the size of the similarity, or whether there is abnormal muscle activation or compensation during the action, and giving feedback and evaluation of the action. For example, the higher the similarity, the more standard the action is, and vice versa, it means that the action is abnormal or has compensation.
[0085] (2) Threshold-based method, that is, setting a threshold between the feature parameters and the target template information, such as maximum value, minimum value, average value, standard deviation, etc., and judging whether the action is standard or not based on whether the feature parameters are within the threshold range, or whether there is abnormal muscle activation or compensation during the action, and giving feedback and evaluation of the action. If the feature parameters are within the threshold range, it indicates a standard action, otherwise it indicates that the action is abnormal or has compensation.
[0086] (3) Classification-based methods, that is, using machine learning or deep learning methods, such as support vector machines, decision trees, neural networks, etc., to train and learn the target template information to obtain a classifier. When the feature parameters are input into the classifier, the output of the classifier can be used to determine whether the action is standard, or whether there is abnormal muscle activation or compensation during the action, and provide feedback and evaluation of the action. If the output of the classifier is positive, it indicates a standard action specification, otherwise it indicates that the action is abnormal or compensated.
[0087] Based on the above method, the embodiment of the present disclosure can implement at least one of the following analyses on the above characteristic parameters:
[0088] (1) Comparative analysis, that is, comparing the characteristic parameters of the target object with the target template information, finding out the differences and deviations, evaluating whether the muscle contraction strategy of the target object is reasonable and effective, and giving feedback and suggestions.
[0089] (2) Trend analysis, which is to compare the characteristic parameters of the target object in different time periods or different training stages, observe the changes and trends, evaluate whether the muscle contraction strategy of the target object is stable and consistent, and provide feedback and suggestions.
[0090] (3) Correlation analysis, that is, to conduct correlation analysis between the characteristic parameters of the target object and other indicators, such as movement characteristics, performance, effect, risk, etc., to explore the cause-effect relationship, evaluate the impact of the target object's muscle contraction strategy on training, and provide feedback and suggestions.
[0091] Based on this, the motion evaluation result of the embodiment of the present disclosure may include at least one of the following information:
[0092] (1) The quality of the target subject’s muscle contraction strategy, that is, whether the target subject can effectively coordinate and control the contraction of different muscle groups when performing training movements to achieve the best exercise effect and minimize risk.
[0093] (2) Improvement of the target subject’s muscle contraction strategy, that is, how the target subject should adjust and optimize the contraction of different muscle groups when performing training movements to improve exercise quality and safety.
[0094] (3) Evaluation of the target subject’s muscle contraction strategy, that is, when the target subject performs the training movements, the target subject’s muscle contraction strategy is scored and graded according to different evaluation criteria to reflect the target subject’s training level and ability.
[0095] Based on this, by analyzing the multi-dimensional data according to the target template data, a motion evaluation result can be obtained. For example, the collected posture data can be analyzed according to the template posture data to obtain a first motion evaluation result corresponding to the posture data. And the collected electromyographic signal can be analyzed according to the template electromyographic signal to obtain a second motion evaluation result corresponding to the electromyographic signal. Based on the first motion evaluation result and the second motion evaluation result, the above-mentioned motion evaluation result is generated. It should be noted that the motion evaluation results of the embodiments of the present disclosure are only used as reference data and are not directly used to treat the target object or diagnose the disease of the target object.
[0096] In the disclosed embodiment, the processor 120 is also used to: divide the N multi-dimensional data groups into N electromyographic signal groups and N posture data groups. Based on the nth group of template electromyographic signals in the N groups of template electromyographic signals and the nth electromyographic signal group in the N electromyographic signal groups, generate the nth first motion error information. Based on the N first motion error information, generate the first motion trend information of the target object. Thus, the first motion evaluation result can be generated based on the first motion trend information. The analysis of the posture data is similar to the analysis method of the electromyographic signal, which will not be repeated here.
[0097] According to an embodiment of the present disclosure, the target object is an object that has performed a target training exercise. The posture data includes a joint angle value. The target template information includes template posture data and template electromyographic signals, and the template posture data includes a template joint angle change rate. The processor 120 is also used to: for the nth multidimensional data group in the N multidimensional data groups, based on the joint angle values in the nth multidimensional data group and the exercise period corresponding to the nth multidimensional data group, determine the nth joint angle change rate of the target object, where n is a positive integer less than or equal to N. Based on the nth joint angle change rate and the nth template joint angle change rate, generate the nth joint angle change score, wherein the joint angle change score is used to characterize the joint flexion condition of the target object during the exercise. Based on the electromyographic signals in the nth multidimensional data group and the nth group of template electromyographic signals, generate the nth muscle activation score of the target object, wherein the muscle activation score is used to characterize the muscle activation degree of the target object. Based on the N joint angle change scores and the N muscle activation scores, calculate the reaction index of the target object, wherein the reaction index is used to characterize the reaction condition of the muscles and joints of the target object during the exercise. A pre-stored reaction index of the target object before performing the target training exercise is obtained, wherein the exercise corresponding to the pre-stored reaction index is the same as the exercise corresponding to the reaction index. Based on the reaction index and the pre-stored reaction index of the target object, a movement evaluation result corresponding to the target training exercise is generated, wherein the pre-stored reaction index is obtained when the target object who has not performed the target training exercise performs the exercise, and the movement evaluation result is used to characterize the activation ability of the target training exercise on the joints and muscles of the target object.
[0098] In the disclosed embodiment, the reaction index of the target object can be calculated and then compared with the pre-stored reaction index of the target object before the target training exercise, so as to generate a motion evaluation result for characterizing the ability of the target training exercise to affect the target object.
[0099] Based on this, the reaction index of the target object is determined based on the joint angle change score and muscle activation score of the target object, and then the reaction index is compared with the pre-stored reaction index of the target object before the target training exercise is performed, so as to obtain a motion evaluation result for characterizing the activation ability of the target training exercise on the joints and muscles of the target object, thereby improving the accuracy of determining the activation ability of the target training exercise on the joints and muscles of the target object, thereby accurately adjusting the training plan of the target object.
[0100] According to an embodiment of the present disclosure, the processor 120 is also used to: determine the nth first target moment and the nth second target moment from the motion period corresponding to the nth multidimensional data group based on the joint angle value in the nth multidimensional data group, wherein the first target moment represents the moment when the joint bending angle of the target object is the smallest, and the second target moment represents the moment when the joint bending angle of the target object is the largest. Based on the nth first target moment and the nth second target moment, calculate the nth joint bending duration of the target object. Based on the joint angle value corresponding to the nth first target moment and the joint angle value corresponding to the nth second target moment, calculate the nth joint angle change of the target object. Based on the nth joint angle change and the nth joint bending duration, calculate the nth joint angle change rate of the target object. Thus, the nth joint angle change score can be generated based on the nth joint angle change rate and the nth template joint angle change rate. Based on this, by determining the exact joint bending period according to the first target moment and the second target moment, the joint angle change rate can be accurately determined based on the duration of the joint bending period and the amount of joint angle change, thereby improving the accuracy of determining the joint angle change score.
[0101] In the embodiment of the present disclosure, taking the vertical jump landing movement as an example, the change rate of the target object from the initial contact with the ground to the time when the maximum joint angle is reached during the movement can be calculated, and the Z score can be normalized to obtain the nth joint angle change score. As shown in the following formula:
[0102] (3)
[0103] Where ACR represents the joint angle change score. Δθ is the angle change. RT is the reaction time (RT), which is the time duration of the joint bending mentioned above, used to record the time duration from the initial posture to the maximum angle of the joint. μ ACR is the mean value of the joint angle change rate in the template posture data. ACR is the standard deviation of the joint angle change rate in the template posture data. The larger the value of the joint angle change score, the faster the joint flexion of the target object in this movement phase and the lower the risk of injury.
[0104] According to an embodiment of the present disclosure, the processor 120 is further used to: calculate the nth electromyographic root mean square value based on the electromyographic signal in the nth multidimensional data group. Calculate the nth template electromyographic root mean square value based on the nth group of template electromyographic signals. Calculate the nth muscle activation score based on the nth electromyographic root mean square value and the nth template electromyographic root mean square value. Based on this, by calculating the muscle activation score according to the electromyographic root mean square value, the accuracy of the calculated muscle activation score is improved.
[0105] In the embodiment of the present disclosure, taking the vertical jump landing movement as an example, the surface electromyography root mean square value of the target object from the initial contact with the ground to the time when the maximum joint angle is reached during the movement can be calculated, and the Z score can be normalized to obtain the muscle activation score, as shown in the following formula:
[0106] (4)
[0107] Where N is the number of surface electromyography data points collected. i is the i-th data in the surface electromyography signal data sequence, which includes the collected surface electromyography signals of the hamstring muscles (semitendinosus and biceps femoris). RMS H is the mean of the surface EMG RMS values of the hamstring muscles (semitendinosus and biceps femoris) in the template EMG signal. RMS H is the standard deviation of the surface EMG RMS value of the hamstring muscles (semitendinosus and biceps femoris) in the template EMG signal.
[0108] The surface electromyography root mean square value of the hamstring muscles (semitendinosus and biceps femoris) is calculated and the muscle activation score is determined based on this value. The larger the muscle activation score, the higher the degree of activation of the corresponding muscle during the movement. The preferential activation of the hamstring muscles helps reduce the risk of injury in jumping movements.
[0109] Based on this, the reaction index of the target object can be calculated based on the joint angle change score and the muscle activation score. The reaction index is dimensionless. It is shown in the following formula:
[0110] (5)
[0111] Wherein, MJCRI is the above reaction index. n is the number of actions of the target object, corresponding to the number of the above action stages. ACR j Score the change in angle of the above joints. RMS j H Score activation of the above muscles.
[0112] The above-mentioned reaction index can be the Muscle Joint Combined Response Index (MJCRI), which can be used to characterize the state and injury risk of the human knee and ankle joints during vertical jump landing movements, and can also be used to evaluate the movement ability of joints and muscles during dynamic movements and the effect of muscle activation to maintain stability. Through the muscle-joint combined response index parameters, the movement and activation of joints and muscles in dynamic movements can be quantified to help assess the risk of injury. The muscle-joint combined response index (MJCRI) combines factors such as joint angle changes, reaction time, and surface electromyography root mean square value. The larger the value of this parameter, the better the joint movement ability, the correct activation of related muscles, and the lower the risk of sports injuries.
[0113] Based on this, the above reaction index and the pre-stored reaction index may be combined to generate a motion evaluation result, which may include the above reaction index.
[0114] In an embodiment of the present disclosure, the target objects may be B. Motion evaluation results of the B target objects may be obtained. The system also includes a human-computer interaction interface, which is connected to the processor 120. Thus, in one embodiment of the present disclosure, the processor 120 may control the human-computer interaction interface to display the motion evaluation results of the B target objects. In another embodiment of the present disclosure, the processor 120 is also used to: determine the risk object from the B target objects based on the motion evaluation results corresponding to the B target objects, wherein the B target objects are different, the risk object represents the object with the highest risk of sports injury among the B target objects, and B is an integer greater than 1. Based on the motion evaluation results corresponding to the risk object and the multi-dimensional data corresponding to the risk object, generate training suggestion information, wherein the training suggestion information includes training exercises for suggesting the target object to perform. Control the human-computer interaction interface to display the training suggestion information.
[0115] In an embodiment of the present disclosure, by comparing the reaction indexes in the motion evaluation results of B target objects, the risk objects that are more likely to be injured during exercise can be determined. And, based on the motion evaluation results, electromyographic signals, and posture data, training suggestion information that matches at least one of the motion evaluation results, electromyographic signals, and posture data can be queried from a suggestion database. However, the embodiment of the present disclosure is not limited to this. In another embodiment of the present disclosure, training suggestion information can be generated based on the motion evaluation results and a predetermined joint motion injury risk assessment model.
[0116] Based on this, by generating training suggestion information based on the sports assessment results and multi-dimensional data of the risk object, targeted training suggestions can be given to the risk object, improving the accuracy of generating training suggestion information. On this basis, the training suggestion information is displayed by controlling the human-computer interaction interface to improve the user experience.
[0117] Figure 4 The flowchart of the method for generating training suggestion information according to an embodiment of the present disclosure is schematically shown.
[0118] like Figure 4 As shown, the training suggestion information generating method of this embodiment includes operations S401 to S404.
[0119] In operation S401, during a historical period, electromyographic signals and posture data are collected to construct an action template database.
[0120] In operation S402 , multi-dimensional data of the target object is collected.
[0121] In operation S403, based on the target template information in the motion template database, the multi-dimensional data of the target object is analyzed to obtain a motion evaluation result.
[0122] In operation S404, training suggestion information is generated based on the motion assessment result and a predetermined joint motion injury risk assessment model.
[0123] According to the embodiments of the present disclosure, the target object's motion phases are divided according to the collected posture data to obtain a multi-dimensional data group corresponding to each motion phase. On this basis, the multi-dimensional data group of each motion phase of the target object is analyzed by using the target template information corresponding to each multi-dimensional data group in the motion template database, thereby improving the accuracy of judging whether the target object's motion during the motion process conforms to the standard motion specification, and improving the accuracy of determining the target object's muscle activation status and compensation status when performing the motion.
[0124] In order to better understand the content of the present disclosure, the following takes firefighters as an example. Figure 5 The contents of the present disclosure are further elaborated.
[0125] Figure 5 The schematic diagram shows an architecture diagram of a motion assessment system based on multi-dimensional data analysis according to the second embodiment of the present disclosure.
[0126] like Figure 5As shown, the system of this embodiment includes a data collector 510 and a processor 520. The data collector 510 includes a surface electromyography sensor unit 511 and an inertial measurement unit 512. The processor 520 may include a data storage module 521, a human-computer interaction interface 522, a standard action comparison module 523 and a data processing module 524. Among them, the data storage module 521 can be built based on a solid state drive. The human-computer interaction interface 522 can be connected to devices such as a keyboard and a speaker to display information and obtain input information. The standard action comparison template 523 is used to compare and analyze multi-dimensional data with target template information. The data processing module 524 is used to perform all data processing operations except the data processing operations performed by the data storage module 521, the human-computer interaction interface 522 and the standard action comparison module 523.
[0127] In the disclosed embodiment, 3 to 5 healthy and experienced firefighters (hereinafter referred to as "template subjects") can be selected as collectors of template signals. When the firefighters are training, the surface electromyography sensing unit 511 and the inertial measurement unit 512 are attached to the corresponding muscle parts of the firefighters, and the basic information and training parameters of the firefighters are input through the human-computer interaction module to start training. For example, after wiping the skin surface with alcohol, the electromyography signal acquisition electrodes of the surface electromyography sensing unit 511 are respectively attached to the vastus lateralis, vastus medialis, rectus femoris, biceps femoris, semitendinosus, tibialis anterior, medial gastrocnemius, and lateral gastrocnemius of the dominant limbs of the template subjects. And the inertial measurement unit 512 is tied to the thigh, calf and foot body segments of the dominant limbs of the template subjects. The template subjects are asked to repeat 10 vertical jump landing action tasks under the guidance of professional coaches. Synchronously collect electromyographic signals and kinematic signals during the action. The surface electromyography sensing unit 511 and the inertial measurement unit 512 collect data to the data processing module 524, and the data is pre-processed in the data processing module 524.
[0128] The data processing module 524 pre-processes and analyzes the data, and calculates the joint angle, muscle activation state and fatigue level during the execution of the action. At the same time, the data processing module 524 transmits the characteristic parameters of the data to the standard action comparison module 523. The standard action comparison module 523 compares the characteristic parameters of the data with the corresponding standard template in the action template database to determine whether the action is standard or whether there is abnormal muscle activation or compensation during the action, and gives feedback and evaluation of the action. Combined with the existing firefighter sports injury risk assessment model, visual feedback and suggestions are provided to firefighters and coaches through the human-computer interaction interface 522. After the firefighters are trained, the data processing module 524 stores the original data and processed data in the data storage module 521 for subsequent query and analysis by firefighters and coaches.
[0129] Based on the above content, the embodiment of the present disclosure provides a motion assessment system based on multi-dimensional data analysis, which monitors and evaluates the muscle function and fatigue level, as well as abnormal movement or compensation of the target object by collecting the surface electromyography signal and kinematic data of the target object. Through the human-computer interaction interface, visual feedback and suggestions are provided to firefighters and coaches to guide and optimize the training plan of firefighters, improve the training effect of firefighters, and prevent and reduce risks and injuries in training.
[0130] According to the embodiments of the present disclosure, the present disclosure can use non-invasive, painless, and non-destructive surface electromyography technology to monitor and evaluate the muscle function and fatigue level of firefighters, as well as standard action specifications and abnormal or compensatory conditions in real time, and determine whether the actions are standard. By using a human-computer interaction module, various forms of feedback and suggestions are provided to firefighters and coaches to guide and optimize the training plans of firefighters, improve the training effects and physical conditions of firefighters, prevent and reduce risks and injuries in training, and has the advantages of accuracy, portability, real-time, dynamic, practical, and interactive friendliness.
[0131] According to the embodiments of the present disclosure, the system proposed in the present disclosure can solve the problem of insufficient or overloaded training caused by the fact that the focus of daily scientific training of firefighters is mostly on the subjective experience judgment of the instructor and the different physical fitness of firefighters. It can process the surface electromyography signals of firefighters during training in real time and compare them with the target template information to determine whether the movements are standard or whether there are abnormal muscle activation or compensation during the movement, give feedback and evaluation of the movements, and improve the quality and safety of firefighters' movements.
[0132] According to the embodiments of the present disclosure, the system proposed in the present disclosure collects surface electromyography signals of firefighters when they perform specific training movements, and compares them with more reasonable template surface electromyography signals after kinematic analysis. This can detect and remind firefighters of incorrect muscle use or compensation in the process of completing movements, and give the degree of injury risk in combination with the existing firefighter sports injury risk assessment model. The sports assessment results are used to remind firefighters to consciously improve their movements, thereby better completing target movements, improving training quality, and reducing injury risks.
[0133] Figure 6 A schematic diagram of a motion assessment method based on multi-dimensional data analysis according to an embodiment of the present disclosure is schematically shown.
[0134] like Figure 6 As shown, the motion evaluation method based on multi-dimensional data analysis of this embodiment includes operations S610 to S640.
[0135] In operation S610, when the target object is moving, I multi-dimensional data of the target object are collected, wherein each multi-dimensional data includes an electromyographic signal and posture data, and the I multi-dimensional data corresponds to I time moments, where I is an integer greater than 1.
[0136] In operation S620, based on I posture data, I multi-dimensional data are divided to obtain N multi-dimensional data groups, wherein each multi-dimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I.
[0137] In operation S630, N groups of target template information corresponding to the N multi-dimensional data groups are queried from the action template database.
[0138] In operation S640, based on the N groups of target template information, the N multi-dimensional data groups are analyzed to obtain motion evaluation results corresponding to the target object.
[0139] It should be noted that the motion evaluation method based on multi-dimensional data analysis of the embodiment of the present disclosure corresponds to the data processing process of the motion evaluation system based on multi-dimensional data analysis mentioned above, which will not be elaborated here.
[0140] It can be understood that in the embodiments of the present disclosure, the above-mentioned processor can be integrated with the above-mentioned data collector, or can be separately integrated into an independent electronic device.
[0141] Figure 7 The block diagram of an electronic device implemented based on a processor according to an embodiment of the present disclosure is schematically shown.
[0142] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.
[0143] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.
[0144] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.
[0145] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.
[0146] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.
[0147] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.
[0148] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.
[0149] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 709, and / or installed from a removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0150] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.
[0151] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).
[0152] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0153] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.
[0154] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.
Claims
1. A sports evaluation system based on multi-dimensional data analysis, comprising: A data collector, used for collecting I multi-dimensional data of the target object when the target object is moving, wherein each of the multi-dimensional data includes an electromyographic signal and posture data, the I multi-dimensional data corresponds to the I moment, and I is an integer greater than 1; A processor is connected to the data collector and is used to: Based on the I posture data, the I multi-dimensional data are divided to obtain N multi-dimensional data groups, wherein each multi-dimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I; Querying N groups of target template information corresponding to the N multi-dimensional data groups from an action template database; Based on the N groups of target template information, the N multi-dimensional data groups are analyzed to obtain motion evaluation results corresponding to the target objects.
2. The system according to claim 1, characterized in that The processor is further configured to: By matching pre-stored action change posture data with I of the posture data, J action change moments of the target object are determined from the I moments, wherein the action change posture data represents the limb posture of the object when the action is changed, and J is an integer greater than or equal to 1 and less than 1; Based on the J action change moments, the I multi-dimensional data are divided to obtain the N multi-dimensional data groups.
3. The system according to claim 2, characterized in that The posture data includes acceleration change value and joint angle value; the action change posture data includes pre-stored acceleration change value and pre-stored joint angle value; The processor is further configured to: From the I acceleration change values, identifying E target acceleration change values that match the pre-stored acceleration change value, where E is a positive integer less than I; From the I joint angle values, identifying Q target joint angle values that match the pre-stored joint angle values, where Q is a positive integer less than I; The J action change times are determined based on the times corresponding to the E target acceleration change values and the times corresponding to the Q target joint angle values.
4. The system according to any one of claims 1 to 3, characterized in that: The processor is further configured to: Based on an n-th multi-dimensional data group among the N multi-dimensional data groups, determine candidate motion information matching the n-th multi-dimensional data group from candidate motion information matching an n-1-th multi-dimensional data group among the N multi-dimensional data groups, where n is an integer less than or equal to N and greater than 1; Determine candidate motion information matching the Nth multi-dimensional data group as the motion information; Based on the motion information, the N groups of target template information are queried from the action template database.
5. The system according to any one of claims 1 to 3, characterized in that: The target object is an object that has performed target training movements; the posture data includes joint angle values; the target template information includes template posture data and template electromyographic signals, and the template posture data includes template joint angle change rates; The processor is further configured to: For the nth multidimensional data set among the N multidimensional data sets, Determine an nth joint angle change rate of the target object based on the joint angle values in the nth multidimensional data group and the motion period corresponding to the nth multidimensional data group, where n is a positive integer less than or equal to N; Based on the nth joint angle change rate and the nth template joint angle change rate, generating an nth joint angle change score, wherein the joint angle change score is used to characterize the joint flexion condition of the target object during the movement; Generate an nth muscle activation score of the target object based on the electromyographic signals in the nth multidimensional data group and the nth group of template electromyographic signals, wherein the muscle activation score is used to characterize the degree of muscle activation of the target object; Calculating a reaction index of the target object based on the N joint angle change scores and the N muscle activation scores, wherein the reaction index is used to characterize the reaction status of the muscles and joints of the target object during the movement; Acquiring a pre-stored reaction index of the target object before performing the target training exercise, wherein the exercise corresponding to the pre-stored reaction index is the same as the exercise corresponding to the reaction index; Based on the reaction index and the pre-stored reaction index of the target object, a motion evaluation result corresponding to the target training movement is generated, wherein the pre-stored reaction index is obtained when the target object who has not performed the target training movement performs the movement, and the motion evaluation result is used to characterize the activation ability of the target training movement on the joints and muscles of the target object.
6. The system according to claim 5, characterized in that The processor is further configured to: Based on the joint angle values in the nth multidimensional data group, determining an nth first target moment and an nth second target moment from a movement period corresponding to the nth multidimensional data group, wherein the first target moment represents a moment when the joint bending angle of the target object is minimum, and the second target moment represents a moment when the joint bending angle of the target object is maximum; Calculating the bending duration of an nth joint of the target object based on the nth first target moment and the nth second target moment; Calculating an nth joint angle change of the target object based on the joint angle value corresponding to the nth first target moment and the joint angle value corresponding to the nth second target moment; Based on the nth joint angle change amount and the nth joint bending duration, the nth joint angle change rate of the target object is calculated.
7. The system according to claim 5, characterized in that The processor is further configured to: Calculating the nth myoelectric root mean square value based on the myoelectric signal in the nth multidimensional data group; Based on the template electromyographic signal of the nth group, calculating the root mean square value of the nth template electromyographic signal; The nth muscle activation score is calculated based on the nth myoelectric root mean square value and the nth template myoelectric root mean square value.
8. The system according to claim 5, characterized in that The system further comprises a human-computer interaction interface connected to the processor; The processor is further configured to: Based on the motion assessment results corresponding to B target objects, determine a risk object from the B target objects, wherein the B target objects are different, the risk object represents an object with the highest risk of motion injury among the B target objects, and B is an integer greater than 1; Generate training suggestion information based on the exercise evaluation result corresponding to the risk object and the multi-dimensional data corresponding to the risk object, wherein the training suggestion information includes training exercises recommended for the target object; Control the human-computer interaction interface to display the training suggestion information.
9. The system according to claim 7, characterized in that The data acquisition device includes a surface electromyography sensor unit and an inertial measurement unit; The surface electromyography sensing unit is also used to: collect initial electromyography signals of the target object by using electromyography collection electrodes worn by the target object; The processor is further configured to: Performing direct current filtering on the initial electromyographic signal to obtain a first filtered electromyographic signal; Performing power frequency notch filtering on the first filtered electromyographic signal to obtain a second filtered electromyographic signal; Performing a 4th-order 20-500 Hz Butterworth bandpass filter on the second filtered electromyographic signal to obtain a third filtered electromyographic signal; Performing full-wave rectification on the third filtered electromyographic signal to obtain a rectified electromyographic signal; Performing a 6 Hz Butterworth low-pass filter on the rectified electromyographic signal to obtain an electromyographic signal envelope; The electromyographic signal envelope is normalized to obtain the electromyographic signal. The inertial measurement unit is further used to: collect initial posture data of the target object by using the inertial measurement unit worn by the target object; The processor is further configured to: The initial posture data is subjected to a 4th-order 5 Hz zero-lag Butterworth low-pass filter process to obtain filtered posture data; Zero drift elimination is performed on the filtered attitude data to obtain the attitude data.
10. A motion assessment method based on multi-dimensional data analysis, comprising: When the target object is moving, collect I multi-dimensional data of the target object, wherein each of the multi-dimensional data includes an electromyographic signal and posture data, the I multi-dimensional data corresponds to the I moment, and I is an integer greater than 1; Based on the I posture data, the I multi-dimensional data are divided to obtain N multi-dimensional data groups, wherein each multi-dimensional data group corresponds to a different motion stage, and N is a positive integer less than or equal to I; Querying N groups of target template information corresponding to the N multi-dimensional data groups from an action template database; Based on the N groups of target template information, the N multi-dimensional data groups are analyzed to obtain motion evaluation results corresponding to the target objects.
Citation Information
Patent Citations
Digital evaluation and training system for motion function
CN114247123A
Stroke lower limb function evaluation method and system based on myoelectric motion multi-data fusion
CN115399791A
Muscle recognition method based on posture division
CN115399792A
Rehabilitation support system, information processing method and program
JP2023115876A
Muscle synergy analysis method, muscle synergy analyzer, and muscle synergy interface
US20120172745A1
Cited By
Swimming underwater physical training effect analysis system based on training data
CN119862399A
A swimming underwater physical training effect analysis system based on training data
CN119862399B
Lower limb muscle fatigue state identification method and system based on multi-modal feature fusion
CN120144985A
Computer user information security intelligent management method and system
CN120474811A
Athlete action assessment method and system
CN121074984A
