Multi-modal fusion muscular tension dynamic assessment method and system

Abstract

The invention discloses a multi-modal fusion muscular tension dynamic assessment method and system, relates to the technical field of biological dynamic assessment, and is used for solving the problem that muscle activity grade classification errors are increased due to dependence on single surface myoelectricity or joint angle sensor data. Joint angle variation, resistance variation and force feedback intensity are extracted, an evaluation mechanism is constructed in combination with region division and historical threshold values, and muscle activity evaluation levels are calculated; and comparing a preset threshold value to identify a flexibility level, entering a resistance evaluation mechanism when a condition is met, analyzing a muscular tension change trend in resistance data, completing dynamic refined judgment of a flexible state, realizing staged, regionalized and trended fusion evaluation, and improving muscular tension state identification and flexibility level judgment precision.

Description

Technical Field

[0001] The present invention relates to the technical field of biological dynamic assessment, and more specifically, to a multimodal fusion muscle tension dynamic assessment method and system. Background Art

[0002] Muscle tone is a manifestation of the nervous system's regulation of muscle tension. Its abnormal state is of great value in the rehabilitation assessment of neurological diseases such as cerebral palsy, post-stroke sequelae, and Parkinson's disease. Traditional muscle tone assessment often relies on manual assessment methods, such as the modified Ashworth Scale (MAS) and the modified Tardieu Scale. These results are highly dependent on the operator's experience and subjective judgment, making them difficult to quantify, with poor reproducibility and significant variation across time points and between evaluators.

[0003] The existing technology has the following deficiencies:

[0004] Currently, most dynamic muscle tension assessment methods rely on single surface electromyography or joint angle sensor data, which makes it difficult to fully capture the coordinated characteristics of mechanical, motion, and neural signals during muscle activity. This leads to increased errors in muscle activity level classification and reduced stability and reliability of assessment results. Therefore, a multimodal fusion method and system for dynamic muscle tension assessment is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a multimodal fusion muscle tension dynamic assessment method and system, which solves the problems raised in the above-mentioned background technology by utilizing a dynamic assessment mechanism based on multi-source data fusion, a flexible grading model for regional matching, and a resistance trend auxiliary judgment algorithm.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a multimodal fusion muscle tension dynamic assessment method and system, comprising the following steps: Step S1: Real-time acquisition of the human body's muscle tension state, and processing the acquired muscle tension state data to obtain the joint angle change, resistance change, and force feedback intensity of the muscle activity; Step S2: Divide the muscle activity area, collect historical data, set different level classification thresholds for different activity areas, identify the area where the muscle activity is located, and calculate the evaluation level of the muscle activity at that time by combining the change in joint angle, change in resistance, and force feedback intensity; Step S3: Compare the evaluation level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluate the flexibility level of the muscle activity at that time. If the flexibility level of the muscle activity at that time is level 1, enter the resistance evaluation mechanism; Step S4: When entering the resistance evaluation mechanism, the resistance detection data of the current muscle activity is called, the trend of muscle tension change before and after is determined based on the resistance detection data, and the flexibility level of the current muscle activity is further evaluated based on the trend of muscle tension change before and after.

[0008] In a preferred embodiment, in step S1, the time span of the complete muscle activity is used as a sampling period, and sampling moments of equal duration are evenly divided within the sampling period; Detect the rotational displacement of the skeletal structure driven by the muscles during the sampling period to obtain the joint angle value; Collect the reverse mechanical resistance value generated by the joint movement during the sampling period to obtain the resistance detection value; Record the muscle tension feedback data of the muscle in response to external force stimulation during the sampling period to obtain the force feedback value; The joint angle change is obtained by subtracting the joint angle values ​​obtained at the start and end of the sampling period; The resistance change is obtained by taking the difference between the maximum resistance detection value and the minimum resistance detection value within the sampling period; Select the force feedback value with the largest value as the force feedback strength.

[0009] In a preferred embodiment, in step S2, the muscle activity area of ​​the human body is pre-divided to obtain the muscle activity area; The historical data of muscle tension status of each muscle activity area are called up, and a weighted comprehensive method after standardization is used to construct a calculation model of the evaluation threshold to obtain the evaluation threshold; Based on the evaluation threshold, the quantile statistics method is used to calculate the quantile of the evaluation threshold to obtain the level division threshold, including level division threshold 1, level division threshold 2, level division threshold 3, and level division threshold 4, which are respectively denoted as 、 、 、 .

[0010] In a preferred embodiment, in step S2, a historical average feature vector of each muscle activity area is constructed; The joint angle change, resistance change and force feedback intensity of the muscle activity at that time are constructed as the muscle activity feature vector at that time; Calculate the Euclidean distance between the current muscle activity feature vector and the historical average feature vector of each muscle activity area, and determine the muscle activity area corresponding to the minimum distance as the area where the current muscle activity occurs; After identifying the area where the muscle activity is located, the feature vector of the muscle activity is input into the calculation model of the evaluation threshold to obtain the evaluation level of the muscle activity.

[0011] In a preferred embodiment, in step S3, if , then the flexibility level of the muscle activity at that time is judged to be level 0 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 1 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 2 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 3 muscle tension; like , then the flexibility level of the muscle activity is judged to be level 4 muscle tension; in, It is the assessment level of muscle activity at that time; If the flexibility level of the muscle activity is level 1 muscle tension, the resistance assessment mechanism will be entered to further assess the flexibility level.

[0012] In a preferred embodiment, in step S4, the sampling period is divided into a first half interval and a second half interval according to a preset ratio, and the second half interval is further divided into a terminal interval and a middle and rear interval according to a preset ratio; The resistance detection value at each sampling moment within the sampling period is called, and the resistance evaluation mechanism is used to further determine whether it is refined into level 1+ muscle tension.

[0013] In a preferred embodiment, in step S4, the resistance evaluation mechanism is as follows: The instantaneous resistance mutation at each sampling moment is calculated by integrating the resistance detection value at preset small time intervals; If the instantaneous resistance mutation amount is greater than the preset mutation threshold, the corresponding sampling moment is marked as the mutation point; If the instantaneous resistance mutation amount at the adjacent sampling moments after the mutation point is less than the preset mutation threshold, it is judged that there is a release trend at the adjacent sampling moments; If the average resistance detection value of the terminal interval is less than the average resistance detection value of the middle and rear end intervals, and the instantaneous resistance mutation values ​​of the terminal interval are all less than the preset mutation threshold, it is judged that the resistance has returned to normal.

[0014] In a preferred embodiment, in step S4, when it is determined that there is a release trend at adjacent sampling moments and the resistance in the terminal interval returns to a normal state, the flexibility level of the muscle activity is determined to be level 1+ muscle tension; Otherwise, the flexibility level of the muscle activity is judged to be level 1 muscle tension.

[0015] A multimodal fusion muscle tension dynamic assessment system includes a muscle tension data acquisition module, a region identification and assessment module, a flexibility level determination module, and a trend correction module; The muscle tension data acquisition module collects the human body's muscle tension status in real time and processes it to obtain the joint angle change, resistance change and force feedback intensity of the muscle activity; The regional recognition and evaluation module divides muscle activity areas, collects historical data to set different level classification thresholds for different activity areas, and calculates the evaluation level of the current muscle activity based on the human body's muscle tension status data; The flexibility level determination module compares the assessment level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluates the flexibility level of the muscle activity at that time. If the flexibility level is level 1, the resistance assessment mechanism is entered; When the trend correction module enters the resistance evaluation mechanism, it calls the resistance detection data of the current muscle activity, determines the trend before and after the muscle tension change, and further evaluates the flexibility level of the current muscle activity.

[0016] The technical effects and advantages of the present invention are as follows: The present invention calls the muscle tension state data in the human body state database, extracts the joint angle change, resistance change and force feedback intensity corresponding to the current muscle activity, divides the muscle activity area and sets the regional level division threshold in combination with historical data, constructs an evaluation mechanism related to the regional characteristics, and then calculates the evaluation level of the muscle activity by integrating multimodal input parameters; by comparing the evaluation level with the preset level division threshold, the flexibility level of the current muscle activity is identified and evaluated, and when the flexibility level meets the set conditions, it further enters the resistance evaluation mechanism, and by analyzing the trend of muscle tension before and after the change in resistance detection data, completes the dynamic and detailed judgment of the muscle flexibility state, thereby realizing the staged, regionalized and trended fusion processing of muscle tension evaluation, improving the accurate judgment of the flexibility level of muscle activity, and enhancing the recognition ability of different muscle tension states. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a multimodal fusion method for dynamic muscle tension assessment of the present invention.

[0018] Figure 2 This is a module schematic diagram of a multimodal fusion muscle tension dynamic assessment system of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] The present invention calls the muscle tension state data in the human body state database, extracts the joint angle change, resistance change and force feedback intensity corresponding to the current muscle activity, divides the muscle activity area and sets the regional level division threshold in combination with historical data, constructs an evaluation mechanism related to the regional characteristics, and then calculates the evaluation level of the muscle activity by integrating multimodal input parameters; by comparing the evaluation level with the preset level division threshold, the flexibility level of the current muscle activity is identified and evaluated, and when the flexibility level meets the set conditions, it further enters the resistance evaluation mechanism, and by analyzing the trend of muscle tension before and after the change in resistance detection data, completes the dynamic and detailed judgment of the muscle flexibility state, thereby realizing the staged, regionalized and trend-based fusion processing of muscle tension evaluation.

[0021] Example 1, a multimodal fusion method for dynamic muscle tension assessment, such as Figure 1 As shown, the following steps are included: Step S1: calling the human body state database human muscle tension state data, extracting the muscle activity of the joint angle change, resistance change and force feedback intensity in the human muscle tension state data; Step S2: Divide the muscle activity area, collect historical data, set different level division thresholds for different muscle activity areas, identify the area where the muscle activity is located, and calculate the evaluation level of the muscle activity at that time by combining the change in joint angle, change in resistance, and force feedback intensity; Step S3: Compare the evaluation level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluate the flexibility level of the muscle activity at that time. If the flexibility level of the muscle activity at that time is level 1, enter the resistance evaluation mechanism; Step S4: When entering the resistance evaluation mechanism, the resistance detection data of the current muscle activity is called, the trend of muscle tension change before and after is determined based on the resistance detection data, and the flexibility level of the current muscle activity is further evaluated based on the trend of muscle tension change before and after.

[0022] The specific implementation is as follows: In step S1, human muscle tension state data in a human body state database is called. The human body state database is a structured database for storing human muscle tension state data, wherein the stored human muscle tension state data is entered by a user through a preset operation interface. The preset operation interface is a parameter setting window on a control terminal. The user enters human muscle tension state data related to target muscle activity in a predetermined format in the parameter setting window. After the entry is completed, the human muscle tension state data is written into the corresponding database table entry to constitute a callable human body state database.

[0023] The above-mentioned human muscle tension state data includes the joint angle change, resistance change and force feedback intensity. The joint angle change is the total change amplitude of the joint angle caused by the muscle activity input by the user, the resistance change is the resistance change amplitude generated during the muscle activity input by the user, and the force feedback intensity is the tension feedback intensity of the muscle in response to external force stimulation input by the user. The human body muscle tension status data are all input by the user in the interactive interface. After the system verifies the legitimacy and formats the input data, it is written into the database structure in field order to form a complete muscle tension status record. Each record contains a unique identification field, a muscle activity area field, and a timestamp field to achieve data identifiability and traceability.

[0024] When the system starts, the human muscle tension state data in the human state database is called, and the joint angle change, resistance change and force feedback intensity in the corresponding area of ​​the current muscle activity are read, which are used as the input basis for subsequent muscle flexibility calculation and level evaluation. Through the above method, the automatic analysis and level classification of muscle state are completed based on manually preset data, which is suitable for teaching and simulation scenarios.

[0025] It should be noted that the preset operation interface refers to an interactive visual module for users to manually input human muscle tension state data, which is integrated into the control terminal in the form of a graphical user interface and will not be described in detail here.

[0026] In step S2, the muscle activity areas of the human body are pre-divided into the head area, upper limb area, lower limb area, and trunk area. The physiological structure and activity characteristics of different muscle activity areas are different and need to be independently evaluated. Call the pre-collected muscle tension status historical data, and count the historical values ​​of joint angle change, resistance change and force feedback intensity corresponding to each muscle activity area under normal activity state; Based on the historical data of muscle tension status, the evaluation threshold of each muscle activity area is calculated. The evaluation threshold is proportional to the change in joint angle and force feedback intensity, and inversely proportional to the change in resistance. When the change in joint angle and force feedback intensity is greater, and the change in resistance is smaller, it means that the activity ability of the muscle activity area is stronger, and the corresponding evaluation threshold is higher; For each muscle activity area, a calculation model for the evaluation threshold is constructed using a standardized weighted comprehensive method: ; in, To evaluate the threshold, 、 and They represent the normalized processing results of the historical values ​​of joint angle change, force feedback intensity, and resistance change respectively; are weight coefficients, which are set based on the characteristics of the muscle activity area and meet ; Based on the evaluation threshold, the quantile statistics method is used to calculate the quantile of the evaluation threshold and obtain the level division threshold. The calculation expression is as follows: ; in, To evaluate the threshold, is the grade classification threshold 1, P20 is the 20th percentile, is the second threshold for classification, P40 is the 40th percentile, is the third level classification threshold, P60 is the 60th percentile, is the fourth level classification threshold, and P80 is the 80th percentile.

[0027] The historical values ​​of joint angle change, resistance change, and force feedback intensity of each muscle activity area over multiple historical acquisition cycles are called, and the historical average feature vector of each muscle activity area is constructed; The joint angle change, resistance change, and force feedback intensity of the muscle activity collected in step S1 are constructed as a feature vector of the muscle activity; Using the minimum feature distance matching method, the Euclidean distance is calculated between the feature vector of the current muscle activity and the historical average feature vector of each muscle activity area, and the muscle activity area corresponding to the minimum distance is determined as the area where the muscle activity is located. The identification formula is as follows: ; in, is the area where the muscle is active, A is the change in joint angle of the muscle activity, is the mean of the historical data of joint angle changes in each muscle activity area, is the force feedback intensity of the muscle activity at that time, is the mean of the historical data of force feedback intensity in each muscle activity area, is the resistance change of the muscle activity at that time, is the mean of the historical data of resistance change in each muscle activity area, and i is the index value of the muscle activity area.

[0028] After identifying the area where the muscle activity is located, the evaluation level of the muscle activity is calculated based on the calculation model of the evaluation threshold. The specific calculation formula is: ; in, For the evaluation level, 、 and They represent the standardized processing results of the joint angle change, force feedback intensity and resistance change of the muscle activity; are weight coefficients respectively, and satisfy ; If muscles in multiple muscle activity areas are active at the same time, the muscle status of each muscle activity area will be evaluated simultaneously, and the corresponding muscle activity area and evaluation level will be output respectively as the input basis for subsequent flexibility level determination and resistance trend correction.

[0029] It should be noted that the selected time period for the historical data of muscle tension status is based on a preset historical collection period, which is obtained by professionals based on the physiological rhythm characteristics of muscle tension changes and experimental data analysis; the quantile statistics method is a statistical analysis method that calculates representative quantiles based on a preset percentile ratio. In this implementation, the quantile statistics method is used to set the data grading threshold. P20, P40, P60, and P80 are all preset percentile ratios set by professionals through experiments; the Euclidean distance is a measurement method used in mathematics to measure the distance between two points, which will not be elaborated here.

[0030] In step S3, the evaluation level of the muscle activity at that time is combined with the level division threshold of the corresponding activity area to evaluate the flexibility level of the muscle activity at that time: like , then the flexibility level of the muscle activity at that time is judged to be level 0 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 1 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 2 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 3 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 4 muscle tension.

[0031] If the flexibility level of the muscle activity is level 1 muscle tension, the resistance assessment mechanism will be entered to further assess the flexibility level.

[0032] When the flexibility level of the secondary muscle activity is level 0 muscle tension, it means that there is no significant change in muscle resistance throughout the range of joint movement, and the muscle is completely relaxed. When the flexibility level of the secondary muscle activity is level 1 muscle tension, it indicates that there is minimal resistance at the end of the joint range of motion or a momentary freeze followed by release at a specific angle. The resistance assessment mechanism further refines the flexibility level and improves the recognition accuracy of the transition state between mild and moderate muscle tension abnormalities. When the flexibility level of the secondary muscle activity is 2 muscle tension, it means that the resistance is significantly increased throughout most of the range of motion of the joint; When the flexibility level of the muscle activity is level 3, it means that passive movement is obviously difficult and a large external force is needed to drive the joint to complete some movements. Some angles may be completely unable to move. When the flexibility level of the secondary muscle activity is level 4 muscle tension, it means that the muscle is completely stiff and the joint cannot move in the entire range of motion.

[0033] By grading the muscle activity status, it can not only identify the conventional muscle tension status of level 0 to level 4, but also improve the targetedness and adaptability of the assessment by flexibly calling the evaluation thresholds exclusive to each area, effectively enhancing the system's ability to identify mild muscle tension abnormalities and avoiding misjudgments caused by unified thresholds.

[0034] In step S4, the sampling period is divided into a first half interval and a second half interval according to a preset ratio, and the second half interval is further divided into a terminal interval and a middle and rear interval according to a preset ratio; The resistance detection value at each sampling moment within the sampling period in step S1 is called. If the current flexibility level of the muscle activity is level 1, the resistance evaluation mechanism is used to further determine whether it is refined to level 1+. The resistance evaluation mechanism is as follows: Determine whether there is sudden resistance: Calculate the instantaneous resistance mutation at a preset small time interval: ,in, is the resistance detection value at the t-th sampling moment, For the The resistance detection value at each moment, For small time intervals, For the The instantaneous resistance mutation at each sampling moment; If the instantaneous resistance mutation amount is greater than the preset mutation threshold, the corresponding sampling moment is marked as the mutation point; Determine whether there is a resistance release trend: further analyze the release trend after the mutation point and calculate the instantaneous resistance mutation at the adjacent sampling moments after the mutation point. If the instantaneous resistance mutation at the adjacent sampling moments is less than the preset mutation threshold, it is determined that there is a release trend at the adjacent sampling moments; Confirm the resistance detection value of the terminal interval: If the average resistance detection value of each sampling moment in the terminal interval is less than the average resistance detection value of each sampling moment in the middle and rear end intervals, and the instantaneous resistance mutation amount at each sampling moment in the terminal interval is less than the mutation threshold, then it is determined that the resistance has returned to normal; When it is judged that there is a release trend between adjacent sampling moments and the resistance in the terminal interval returns to normal, the flexibility level of the muscle activity is judged to be 1+ level muscle tension; otherwise, the flexibility level of the muscle activity is judged to be 1 level muscle tension.

[0035] By analyzing the resistance change trend in the second half of muscle activity through the resistance assessment mechanism, it is possible to accurately identify the 1+ level state, a subcategory of the 1 level muscle tension, improve the recognition accuracy of the mild tension abnormality state, and avoid misjudging sudden resistance abnormalities as normal mild resistance.

[0036] It should be noted that the preset ratio refers to dividing the total duration into different intervals for evaluation when analyzing a complete muscle activity process; the preset micro time interval is an extremely short time span set when evaluating the instantaneous resistance mutation, which is used to determine whether there is a short-term rapid resistance increase trend; the preset mutation threshold is used to identify whether there is a sudden stuck resistance jump. The above preset parameters are set by professionals and will not be elaborated here.

[0037] Example 2, a multi-modal fusion muscle tension dynamic assessment system, such as Figure 2 As shown, a multimodal fusion muscle tension dynamic assessment method is used to implement the method, which includes a muscle tension data acquisition module, a region recognition and assessment module, a flexibility level determination module, and a trend correction module; The muscle tension data acquisition module collects the human body's muscle tension status in real time and processes it to obtain the joint angle change, resistance change and force feedback intensity of the muscle activity; The regional recognition and evaluation module divides muscle activity areas, collects historical data to set different level classification thresholds for different activity areas, and calculates the evaluation level of the current muscle activity based on the human body's muscle tension status data; The flexibility level determination module compares the assessment level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluates the flexibility level of the muscle activity at that time. If the flexibility level is level 1, the resistance assessment mechanism is entered; When the trend correction module enters the resistance evaluation mechanism, it calls the resistance detection data of the current muscle activity, determines the trend before and after the muscle tension change, and further evaluates the flexibility level of the current muscle activity.

[0038] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0039] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A multimodal fusion method for dynamic muscle tension assessment, characterized by: The following steps are involved: Step S1: calling the human body muscle tension state data in the human body state database, and extracting the joint angle change, resistance change and force feedback intensity of the current muscle activity from the human body muscle tension state data; Step S2: Divide the muscle activity area, collect historical data, set different level classification thresholds for different activity areas, identify the area where the muscle activity is located, and calculate the evaluation level of the muscle activity at that time by combining the change in joint angle, change in resistance, and force feedback intensity; Step S3: Compare the evaluation level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluate the flexibility level of the muscle activity at that time. If the flexibility level of the muscle activity at that time is level 1, enter the resistance evaluation mechanism; Step S4: When entering the resistance evaluation mechanism, the resistance detection data of the current muscle activity is called, the trend of muscle tension change before and after is determined based on the resistance detection data, and the flexibility level of the current muscle activity is further evaluated based on the trend of muscle tension change before and after.

2. The multimodal fusion muscle tension dynamic assessment method according to claim 1, characterized in that: In step S1, the user inputs human muscle tension state data, including joint angle change, resistance change, and force feedback intensity; The human body muscle tension state data is written into the human body state database and called.

3. The multimodal fusion muscle tension dynamic assessment method according to claim 2, characterized in that: In step S2, the muscle activity area of ​​the human body is pre-divided to obtain the muscle activity area; The historical data of muscle tension status of each muscle activity area are called up, and a weighted comprehensive method after standardization is used to construct a calculation model of the evaluation threshold to obtain the evaluation threshold; Based on the evaluation threshold, the quantile statistics method is used to calculate the quantile of the evaluation threshold to obtain the level division threshold, including level division threshold 1, level division threshold 2, level division threshold 3, and level division threshold 4, which are respectively recorded as 、 、 、 .

4. The multimodal fusion muscle tension dynamic assessment method according to claim 3, characterized in that: In step S2, the historical average feature vector of each muscle activity area is constructed; The joint angle change, resistance change and force feedback intensity of the muscle activity at that time are constructed as the muscle activity feature vector at that time; Calculate the Euclidean distance between the current muscle activity feature vector and the historical average feature vector of each muscle activity area, and determine the muscle activity area corresponding to the minimum distance as the area where the current muscle activity occurs; After identifying the area where the muscle activity is located, the feature vector of the muscle activity is input into the calculation model of the evaluation threshold to obtain the evaluation level of the muscle activity.

5. The multimodal fusion muscle tension dynamic assessment method according to claim 1, characterized in that: In step S3, if , then the flexibility level of the muscle activity at that time is judged to be level 0 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 1 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 2 muscle tension; like , then the flexibility level of the muscle activity at that time is judged to be level 3 muscle tension; like , then the flexibility level of the muscle activity is judged to be level 4 muscle tension; in, It is the assessment level of muscle activity at that time; If the flexibility level of the muscle activity is level 1 muscle tension, the resistance assessment mechanism will be entered to further assess the flexibility level.

6. The multimodal fusion muscle tension dynamic assessment method according to claim 1, characterized in that: In step S4, the sampling period is divided into a first half interval and a second half interval according to a preset ratio, and the second half interval is further divided into a terminal interval and a middle and rear interval according to a preset ratio; The resistance detection value at each sampling moment within the sampling period is called, and the resistance evaluation mechanism is used to further determine whether it is refined into level 1+ muscle tension.

7. The multimodal fusion muscle tension dynamic assessment method according to claim 6, characterized in that: In step S4, the resistance evaluation mechanism is as follows: The instantaneous resistance mutation at each sampling moment is calculated by integrating the resistance detection value at preset small time intervals; If the instantaneous resistance mutation amount is greater than the preset mutation threshold, the corresponding sampling moment is marked as the mutation point; If the instantaneous resistance mutation amount at the adjacent sampling moments after the mutation point is less than the preset mutation threshold, it is judged that there is a release trend at the adjacent sampling moments; If the average resistance detection value of the terminal interval is less than the average resistance detection value of the middle and rear end intervals, and the instantaneous resistance mutation values ​​of the terminal interval are all less than the preset mutation threshold, it is judged that the resistance has returned to normal.

8. The multimodal fusion muscle tension dynamic assessment method according to claim 7, characterized in that: In step S4, when it is determined that there is a release trend between adjacent sampling moments and the resistance in the terminal interval returns to a normal state, the flexibility level of the muscle activity is determined to be level 1+ muscle tension; Otherwise, the flexibility level of the muscle activity is judged to be level 1 muscle tension.

9. A multimodal fusion muscle tension dynamic assessment system, used to implement the multimodal fusion muscle tension dynamic assessment method according to any one of claims 1 to 8, characterized in that: It includes muscle tension data acquisition module, area identification and evaluation module, flexibility level determination module and trend correction module; The muscle tension data acquisition module collects the human body's muscle tension status in real time and processes it to obtain the joint angle change, resistance change and force feedback intensity of the muscle activity; The regional recognition and evaluation module divides muscle activity areas, collects historical data to set different level classification thresholds for different activity areas, and calculates the evaluation level of the current muscle activity based on the human body's muscle tension status data; The flexibility level determination module compares the assessment level of the muscle activity at that time with the level division threshold of the corresponding activity area, and evaluates the flexibility level of the muscle activity at that time. If the flexibility level is level 1, the resistance assessment mechanism is entered; When the trend correction module enters the resistance evaluation mechanism, it calls the resistance detection data of the current muscle activity, determines the trend before and after the muscle tension change, and further evaluates the flexibility level of the current muscle activity.

Images