A wearable device and a dynamic measurement method for muscle tone

Abstract

This specification provides a wearable device and a method for dynamically measuring muscle tone. The wearable device includes a wristband, a lower housing, an upper housing, a display screen, an electromyography (EMG) sensor, a body temperature sensor, and a humidity sensor. The upper and lower housings cooperate to form a cavity for accommodating a battery and control components. The battery is electrically connected to the control components. The EMG sensor collects the wearer's EMG data, the body temperature sensor collects the wearer's body temperature data, and the humidity sensor collects the wearer's humidity data. The control components include an MPU6050 chip and a main chip. The MPU6050 chip determines the wearer's current movement state, and the main chip determines the wearer's muscle tone level in the current movement state based on the wearer's EMG data, body temperature data, humidity data, and current movement state. This solution addresses the technical problem that current wearable devices cannot measure muscle tone when the human body is in motion.

Description

Technical Field

[0001] This specification relates to the field of wearable device technology, and in particular to a wearable device and a method for dynamic measurement of muscle tone. Background Technology

[0002] Currently, wearable devices such as smartwatches and fitness trackers can measure a wearer's vital signs, such as steps, heart rate, and sleep index, to record their health status. Muscle tone is used to characterize the tension of muscles in a relaxed state at rest, and it is particularly useful for guiding patient rehabilitation.

[0003] In related technologies, current wearable devices can usually measure muscle tone when the human body is at rest (i.e., isometric motion), but it is difficult to measure muscle tone when the human body is in motion (i.e., isotonic motion).

[0004] Therefore, there is an urgent need for a wearable device and a dynamic measurement method for muscle tone to solve the above-mentioned technical problems. Summary of the Invention

[0005] To address the technical problem that current wearable devices cannot measure muscle tone when the human body is in motion, this specification provides a wearable device and a method for dynamically measuring muscle tone.

[0006] In a first aspect, embodiments of this specification provide a wearable device, including a wristband, a lower housing connected to the wristband, an upper housing connected to the lower housing, a display screen disposed on the upper housing, and an electromyography sensor, a body temperature sensor, and a humidity sensor disposed on the lower housing. The upper housing and the lower housing cooperate to form a cavity for accommodating a battery and a control component. The battery is electrically connected to the control component, and the control component is electrically connected to the display screen, the electromyography sensor, the body temperature sensor, and the humidity sensor, respectively.

[0007] The control components include: an MPU6050 chip and a main chip;

[0008] The main chip is electrically connected to the electromyography sensor, the body temperature sensor, the humidity sensor, and the MPU6050 chip, respectively, and is used to receive the wearer's electromyography data, body temperature data, humidity data, and current movement status;

[0009] The display screen is electrically connected to the main chip to receive and display the muscle tone level under the current movement state generated by the main chip based on the wearer's electromyography data, body temperature data, humidity data and current movement state.

[0010] In one possible design, a mode switch is also included, which is connected to the main chip and controls the operating mode of the main chip. The operating modes include a mode for measuring the wearer's muscle tone level during movement and a mode for measuring the wearer's muscle tone level at rest.

[0011] In one possible design, a device switch is also provided on the lower housing, the device switch being connected to the battery, and the connection between the battery and the control component is controlled by controlling the device switch.

[0012] In one possible design, the number of electromyography (EMG) sensors is three, and the three EMG sensors are arranged in a fan-shaped pattern.

[0013] In one possible design, the control component includes a main control circuit board and a first circuit board and a second circuit board electrically connected to the main control circuit board, respectively. The MPU6050 chip and the main chip are disposed on the main control circuit board. The first circuit board is electrically connected to the display screen, and the second circuit board is electrically connected to the electromyography sensor, the body temperature sensor and the humidity sensor, respectively.

[0014] In one possible design, the main control circuit board and the second circuit board are electrically connected via pin headers, and the battery is disposed between the main control circuit board and the second circuit board.

[0015] Secondly, embodiments of this specification also provide a method for dynamically measuring muscle tone, applied to a wearable device as described in any of the foregoing claims, comprising:

[0016] The electromyography (EMG) sensor is used to collect the wearer's EMG data;

[0017] The wearer's body temperature data is collected using the aforementioned body temperature sensor;

[0018] The humidity sensor is used to collect the wearer's humidity data;

[0019] The wearer's current movement state is determined using the MPU6050 chip;

[0020] The main chip is used to determine the wearer's muscle tone level in the current movement state based on the wearer's electromyography data, body temperature data, humidity data, and current movement state.

[0021] In one possible design, determining the wearer's muscle tone level during the current movement state based on the wearer's electromyography data, body temperature data, humidity data, and current movement state includes:

[0022] Based on the wearer's current motion state and a pre-stored first mapping relationship, a target cost parameter vector corresponding to the current motion state is determined; wherein, the first mapping relationship is a mapping relationship between motion state and cost parameter vector;

[0023] Matrix operations are performed on the wearer's electromyography data, body temperature data, humidity data, and the target cost parameter vector to obtain compensated electromyography data, body temperature data, and humidity data;

[0024] Based on the wearer's current motion state and a pre-stored second mapping relationship, a target level assessment model corresponding to the current motion state is determined; wherein, the second mapping relationship is the mapping relationship between the motion state and the level assessment model;

[0025] The compensated electromyography data, body temperature data, and humidity data are input into the target level assessment model, which outputs the wearer's muscle tone level in the current exercise state.

[0026] In one possible design, the electromyographic data includes time-domain features and frequency-domain features, wherein the time-domain features include mean absolute value, waveform length, variance, root mean square, Wilson amplitude, and adjusted mean, and the frequency-domain features include mean frequency, frequency variance, frequency entropy, energy density, frequency skewness, and frequency kurtosis.

[0027] The rating assessment model is a random forest model;

[0028] The cost parameter vector is obtained in the following way:

[0029] The system iterates through each feature in the training data, inputs the current feature into the random forest model to be trained, calculates the Gini index for each node of the random forest model, and outputs the feature importance of the current feature; wherein, the training data includes electromyography data, body temperature data, and humidity data;

[0030] The feature importance is used as the weight value of the current feature at the corresponding position in the cost parameter vector.

[0031] This specification provides a wearable device and a method for dynamically measuring muscle tone. It utilizes an electromyography (EMG) sensor to collect the wearer's EMG data, a body temperature sensor to collect the wearer's body temperature data, and a humidity sensor to collect the wearer's humidity data. An MPU6050 chip is used to determine the wearer's current movement state, and a main chip, based on the wearer's EMG data, body temperature data, humidity data, and current movement state, determines the wearer's muscle tone level in that current movement state. Therefore, this solution addresses the technical problem that current wearable devices cannot measure muscle tone when the human body is in motion. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of a wearable device provided in one embodiment of this specification, excluding the wristband;

[0034] Figure 2 yes Figure 1 Another structural schematic diagram of the wearable device shown;

[0035] Figure 3 This is a schematic diagram of the wearable device provided in one embodiment of this specification, excluding the upper housing;

[0036] Figure 4 yes Figure 3 The diagram shows the structure of the wearable device excluding the first circuit board.

[0037] Figure 5 This is a flowchart of a dynamic measurement method for muscle tone provided in one embodiment of this specification;

[0038] Figure 6 This is a schematic diagram illustrating the feature importance provided in one embodiment of this specification.

[0039] Figure label:

[0040] 1-Wristband;

[0041] 21-Lower shell;

[0042] 22-Upper shell;

[0043] 3-Display screen;

[0044] 41-Electromyography sensor;

[0045] 42-Body temperature sensor;

[0046] 43 - Humidity sensor;

[0047] 5-Battery;

[0048] 6-Control components;

[0049] 61-MPU6050 chip;

[0050] 62-Main chip;

[0051] 63 - Main control circuit board;

[0052] 64 - First circuit board;

[0053] 65 - Second circuit board;

[0054] 7-Mode switch;

[0055] 8-Equipment switch. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments in this specification clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this specification.

[0057] Figure 1 This is a schematic diagram of a wearable device provided in one embodiment of this specification, excluding the wristband; Figure 2 yes Figure 1 Another structural schematic diagram of the wearable device shown; Figure 3 This is a schematic diagram of the wearable device provided in one embodiment of this specification, excluding the upper housing; Figure 4 yes Figure 3 The diagram shows the structure of the wearable device excluding the first circuit board.

[0058] Please see Figures 1 to 4 This specification provides a wearable device, including a wristband 1, a lower housing 21 connected to the wristband 1, an upper housing 22 connected to the lower housing 21, a display screen 3 disposed on the upper housing 22, and an electromyography sensor 41, a body temperature sensor 42, and a humidity sensor 43 disposed on the lower housing 21. The upper housing 22 and the lower housing 21 cooperate to form a cavity for accommodating a battery 5 and a control component 6. The battery 5 is electrically connected to the control component 6, and the control component 6 is electrically connected to the display screen 3, the electromyography sensor 41, the body temperature sensor 42, and the humidity sensor 43, respectively.

[0059] Control component 6 includes: MPU6050 chip 61 and main chip 62;

[0060] The main chip 62 is electrically connected to the electromyography sensor 41, the body temperature sensor 42, the humidity sensor 43 and the MPU6050 chip 61 respectively. The main chip 62 is used to receive the wearer's electromyography data, body temperature data, humidity data and current movement status.

[0061] The display screen 3 is electrically connected to the main chip 62 to receive and display the muscle tone level in the current movement state generated by the main chip 62 based on the wearer's electromyography data, body temperature data, humidity data and current movement state.

[0062] In this embodiment, electromyography (EMG) data of the wearer is collected using an EMG sensor 41, body temperature data is collected using a body temperature sensor 42, and humidity data is collected using a humidity sensor 43. The wearer's current movement state is determined using an MPU6050 chip 61, and the wearer's muscle tone level in the current movement state is determined using a main chip 62 based on the EMG data, body temperature data, humidity data, and current movement state. Therefore, the above solution can solve the technical problem that current wearable devices cannot measure muscle tone when the human body is in motion.

[0063] In some implementations, wearable devices include, but are not limited to, smartwatches and wristbands.

[0064] It is known that the MPU6050 chip integrates a 3-axis MEMS gyroscope, a 3-axis MEMS accelerometer, and a scalable Digital Motion Processor (DMP). Using the MPU6050 chip, the x, y, and z-axis tilt angles (pitch, roll, and yaw) of the object under test (such as a quadcopter or a balance vehicle) can be obtained. By reading six data points (three-axis acceleration AD values ​​and three-axis angular velocity AD values) from the MPU6050 via I2C and performing attitude fusion, the pitch, roll, and yaw angles can be obtained. The DMP, the data processing module within the MPU6050 chip, (with a built-in Kalman filter algorithm) acquires data from the gyroscope and accelerometer, processes the data, and outputs quaternions, reducing the workload of the external microprocessor and avoiding cumbersome filtering and data fusion. In other words, by placing the MPU6050 chip in a wearable device, the wearer's current motion state can be identified, including normal walking, jogging, and running.

[0065] It should be noted that the main chip 62 is used to determine the wearer's muscle tone level in the current exercise state based on the wearer's electromyography data, body temperature data, humidity data and current exercise state. For specific technical details, please refer to the following text.

[0066] In some implementations, the electromyographic data includes time-domain features and frequency-domain features. The time-domain features include mean absolute value, waveform length, variance, root mean square, Wilson amplitude, and adjusted mean. The frequency-domain features include mean frequency, frequency variance, frequency entropy, energy density, frequency skewness, and frequency kurtosis. These features are well known to those skilled in the art and will not be described in detail here.

[0067] For example, the absolute value of the mean is determined by the following formula:

[0068]

[0069] Where Mav is the absolute average, N is the total number of sampling points, and x i Let i be the feature value of the i-th sampling point;

[0070] The waveform length is determined by the following formula:

[0071]

[0072] Among them, WL k x is the waveform length. i Let i be the feature value of the i-th sampling point;

[0073] Variance is determined by the following formula:

[0074]

[0075] Among them, VAR k For variance, The square of the average eigenvalue of all sampled points;

[0076] The root mean square is determined by the following formula:

[0077]

[0078] Among them, RMS k It is the root of the square.

[0079] Wilson amplitude is determined by the following formula:

[0080]

[0081] Where WAMP is the Wilson amplitude and th is the preset threshold;

[0082] The adjusted average value is determined using the following formula:

[0083]

[0084] Among them, MMAVl k To adjust the average value.

[0085] In one embodiment of this specification, the main chip 62 is also used to determine the wearer's muscle tone level at rest based on the wearer's electromyography data;

[0086] The wearable device also includes a mode switch 7 located on the lower housing 21. The mode switch 7 is connected to the main chip 62, and the working mode of the main chip 62 is controlled by controlling the mode switch 7. The working modes include a mode for measuring the wearer's muscle tone level during exercise and a mode for measuring the wearer's muscle tone level at rest.

[0087] In this embodiment, by setting the mode switch 7, the working mode of the main chip 62 can be controlled, which is conducive to realizing the functional diversification of wearable devices.

[0088] It should be noted that the technical solution for the main chip 62 to determine the wearer's muscle tone level at rest based on the wearer's electromyography data can be found in the relevant technologies with publication numbers CN113509151A and CN113693604A, and will not be elaborated here.

[0089] In one embodiment of this specification, the wearable device further includes a device switch 8 disposed on the lower housing 21. The device switch 8 is connected to the battery 5, and the on / off state of the battery 5 and the control component 6 is controlled by controlling the device switch 8.

[0090] In one embodiment of this specification, the number of electromyography (EMG) sensors 41 is three, and the three EMG sensors 41 are arranged in a fan shape.

[0091] In this embodiment, since muscles are divided into regions, the electromyographic data measured by a single electromyographic sensor 41 cannot well characterize the muscle tone level. Therefore, in order to measure the muscle tone level more accurately, it is advisable to set the number of electromyographic sensors 41 to three, and arrange the three electromyographic sensors 41 in a fan-shaped arrangement.

[0092] In one embodiment of this specification, the control component 6 includes a main control circuit board 63 and a first circuit board 64 and a second circuit board 65 electrically connected to the main control circuit board 63. The MPU6050 chip 61 and the main chip 62 are disposed on the main control circuit board 63. The first circuit board 64 is electrically connected to the display screen 3, and the second circuit board 65 is electrically connected to the electromyography sensor 41, the body temperature sensor 42 and the humidity sensor 43, respectively.

[0093] In this embodiment, by setting a main control circuit board 63 and a first circuit board 64 and a second circuit board 65 that are electrically connected to the main control circuit board 63, the control component 6 can be electrically connected to the display screen 3, the electromyography sensor 41, the body temperature sensor 42 and the humidity sensor 43.

[0094] In one embodiment of this specification, the main control circuit board 63 and the second circuit board 65 are electrically connected by pin headers, and the battery 5 is disposed between the main control circuit board 63 and the second circuit board 65, which can ensure that the structure of the battery 5 and the control component 6 is more compact.

[0095] In one embodiment of this specification, the display screen 3 is soldered onto the first circuit board 64, which helps to ensure the stability of the connection between the display screen 3 and the first circuit board 64.

[0096] Figure 5 This is a flowchart of a dynamic measurement method for muscle tone provided in one embodiment of this specification. Please refer to [link / reference]. Figure 5 This specification provides a dynamic measurement method for muscle tone, applicable to the wearable device of any of the above embodiments. Specifically, this dynamic measurement method may include:

[0097] Step S1: Collect electromyographic data of the wearer using electromyography sensor 41;

[0098] Step S2: Collect the wearer's body temperature data using the body temperature sensor 42;

[0099] Step S3: Collect the wearer's humidity data using humidity sensor 43;

[0100] Step S4: Use the MPU6050 chip 61 to determine the wearer's current motion state;

[0101] Step S5: Using the main chip 62, determine the wearer's muscle tone level in the current exercise state based on the wearer's electromyography data, body temperature data, humidity data and current exercise state.

[0102] In this embodiment, electromyography (EMG) data of the wearer is collected using an EMG sensor 41, body temperature data is collected using a body temperature sensor 42, and humidity data is collected using a humidity sensor 43. The wearer's current movement state is determined using an MPU6050 chip 61, and the wearer's muscle tone level in the current movement state is determined using a main chip 62 based on the EMG data, body temperature data, humidity data, and current movement state. Therefore, the above solution can solve the technical problem that current wearable devices cannot measure muscle tone when the human body is in motion.

[0103] It should be noted that there is no obvious order among steps S1, S2, S3 and S4, so the order of these four steps is not specified here.

[0104] In a static state, different weights are lifted to simulate different levels of muscle tension. The time-domain and frequency-domain features of the electromyography signals in the corresponding states are extracted to construct a dataset for analysis, thereby realizing the identification of static muscle tension levels.

[0105] During exercise, the identification of muscle tone levels shifts from isometric to isotonic. Considering the increased complexity during exercise, body temperature and skin humidity are introduced as new feature vectors to achieve accurate dynamic muscle tone level identification. A classification method is designed to dynamically adjust weight values ​​based on the wearer's exercise state (i.e., using a cost parameter vector to compensate for the feature data), thereby improving the accuracy of dynamic muscle tone level measurement. In other words, during actual measurement, different cost parameter vectors are used to adjust the feature data according to different exercise states, thus enabling the identification of muscle tone levels during exercise.

[0106] In one embodiment of this specification, step S5 may specifically include:

[0107] Based on the wearer's current motion state and a pre-stored first mapping relationship, the target cost parameter vector corresponding to the current motion state is determined; wherein, the first mapping relationship is the mapping relationship between the motion state and the cost parameter vector;

[0108] Matrix operations are performed on the wearer's electromyography (EMG) data, body temperature data, humidity data, and target cost parameter vector to obtain compensated EMG data, body temperature data, and humidity data;

[0109] Based on the wearer's current motion state and a pre-stored second mapping relationship, a target level assessment model corresponding to the current motion state is determined; wherein, the second mapping relationship is the mapping relationship between the motion state and the level assessment model;

[0110] The compensated electromyography data, body temperature data, and humidity data are input into the target level assessment model, which outputs the wearer's muscle tone level under the current exercise state.

[0111] In this embodiment, based on the wearer's current movement state, a target cost parameter vector and a target level evaluation model corresponding to the current movement state can be determined. Then, by performing matrix operations on the wearer's electromyography (EMG) data, body temperature data, humidity data, and target cost parameter vector, compensated EMG data, body temperature data, and humidity data are obtained. Finally, the compensated EMG data, body temperature data, and humidity data are input into the target level evaluation model to output the wearer's muscle tone level in the current movement state.

[0112] It should be noted that, according to the Ashworth scale, muscle tone is divided into multiple levels, which allows for the construction of a grade assessment model with the same number of levels.

[0113] In one embodiment of this specification, electromyographic data includes time-domain features and frequency-domain features. The time-domain features include mean absolute value, waveform length, variance, root mean square, Wilson amplitude, and adjusted mean. The frequency-domain features include mean frequency, frequency variance, frequency entropy, energy density, frequency skewness, and frequency kurtosis.

[0114] The rating model is a random forest model;

[0115] The cost parameter vector is obtained as follows:

[0116] Iterate through each feature in the training data, input the current feature into the random forest model to be trained, calculate the Gini index for each node of the random forest model, and output the feature importance of the current feature (see [link to relevant documentation]). Figure 6 , Figure 6 (A schematic diagram showing the normalized feature importance of each of the 14-dimensional feature data); where the training data includes electromyography data, body temperature data, and humidity data;

[0117] The feature importance is used as the weight value of the current feature at the corresponding position in the cost parameter vector.

[0118] In this embodiment, by inputting each feature of the training data into the random forest model to be trained, the Gini index is calculated for each node of the random forest model, thereby outputting the feature importance of the current feature, and then obtaining the weight value of the current feature at the corresponding position in the cost parameter vector.

[0119] For example, the formula for calculating the Gini index of a certain feature in a classification model is:

[0120]

[0121] For an eigenvalue j and a node m that contains that eigenvalue, the node feature importance based on eigenvalue j is defined as follows:

[0122] VIM jm =GI m -GI l -GI r

[0123] In the formula, GI m The Gini index, GI, represents the intermediate node. l GI r These represent the Gini indexes of the left and right nodes that split from the intermediate node, respectively.

[0124] Let M be the set of nodes where feature value j appears. Then the feature importance of feature value j in decision tree i can be expressed by the following formula:

[0125] VIM ij =∑ m∈M VIM jm

[0126] The feature importance of feature value j in the entire random forest model is:

[0127]

[0128] Given a total of m feature vectors, normalizing the feature importance of feature value j in the random forest yields:

[0129]

[0130] in, This represents the sum of the feature importance of all feature values ​​in the random forest model. Based on the feature importance calculation above, the feature cost parameter vectors are constructed.

[0131] The Gini index (Gini impurity) represents the probability that a randomly selected sample in a set will be misclassified. A smaller Gini index indicates a lower probability of misclassification, meaning the set is more pure; conversely, a larger Gini index indicates a less pure set. The Gini index is 0 when all samples in the set belong to the same class.

[0132] Random forest models can solve the overfitting problem of decision tree models. Random forest models generate multiple decision trees using a training set. During prediction, each tree predicts a result, and each result is weighted and voted on to avoid overfitting.

[0133] It is understandable that, since the training data is 14-dimensional, each cost parameter vector is a 1*14 matrix.

[0134] This specification also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a wearable device according to any embodiment of this specification.

[0135] This specification also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a wearable device according to any embodiment of this specification.

[0136] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0137] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute a part of this specification.

[0138] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0139] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0140] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0141] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0142] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this specification, and are not intended to limit them. Although this specification has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this specification.

Claims

1. A wearable device, characterized in that, The device includes a wristband (1), a lower housing (21) connected to the wristband (1), an upper housing (22) connected to the lower housing (21), a display screen (3) disposed on the upper housing (22), and an electromyography sensor (41), a body temperature sensor (42), and a humidity sensor (43) disposed on the lower housing (21). The upper housing (22) and the lower housing (21) cooperate to form a cavity for accommodating a battery (5) and a control component (6). The battery (5) is electrically connected to the control component (6), and the control component (6) is electrically connected to the display screen (3), the electromyography sensor (41), the body temperature sensor (42), and the humidity sensor (43), respectively. The control component (6) includes: an MPU6050 chip (61) and a main chip (62). The main chip (62) is electrically connected to the electromyography sensor (41), the body temperature sensor (42), the humidity sensor (43) and the MPU6050 chip (61) respectively, and is used to receive the wearer's electromyography data, body temperature data, humidity data and current movement status; The display screen (3) is electrically connected to the main chip (62) to receive and display the muscle tension level in the current exercise state generated by the main chip (62) based on the wearer's electromyography data, body temperature data, humidity data and current exercise state; The determination of the wearer's muscle tone level in the current exercise state based on the wearer's electromyography data, body temperature data, humidity data, and current exercise state includes: Based on the wearer's current motion state and a pre-stored first mapping relationship, a target cost parameter vector corresponding to the current motion state is determined; wherein, the first mapping relationship is a mapping relationship between motion state and cost parameter vector; Matrix operations are performed on the wearer's electromyography data, body temperature data, humidity data, and the target cost parameter vector to obtain compensated electromyography data, body temperature data, and humidity data; Based on the wearer's current motion state and a pre-stored second mapping relationship, a target level assessment model corresponding to the current motion state is determined; wherein, the second mapping relationship is the mapping relationship between the motion state and the level assessment model; The compensated electromyography data, body temperature data, and humidity data are input into the target level assessment model, and the wearer's muscle tone level in the current exercise state is output. The electromyographic data includes time-domain features and frequency-domain features. The time-domain features include mean absolute value, waveform length, variance, root mean square, Wilson amplitude, and adjusted mean. The frequency-domain features include mean frequency, frequency variance, frequency entropy, energy density, frequency skewness, and frequency kurtosis. The rating assessment model is a random forest model; The cost parameter vector is obtained in the following way: The system iterates through each feature in the training data, inputs the current feature into the random forest model to be trained, calculates the Gini index for each node of the random forest model, and outputs the feature importance of the current feature; wherein, the training data includes electromyography data, body temperature data, and humidity data; The feature importance is used as the weight value of the current feature at the corresponding position in the cost parameter vector.

2. The wearable device according to claim 1, characterized in that, It also includes a mode switch (7) disposed on the lower housing (21), the mode switch (7) being connected to the main chip (62), and the working mode of the main chip (62) being controlled by controlling the mode switch (7); wherein, the working mode includes a mode for measuring the wearer's muscle tone level in a state of motion and a mode for measuring the wearer's muscle tone level in a state of rest.

3. The wearable device according to claim 1, characterized in that, It also includes a device switch (8) disposed on the lower housing (21), the device switch (8) being connected to the battery (5), and the on / off state of the battery (5) and the control component (6) being controlled by controlling the device switch (8).

4. The wearable device according to claim 1, characterized in that, The number of electromyography sensors (41) is three, and the three electromyography sensors (41) are arranged in a fan shape.

5. The wearable device according to any one of claims 1-4, characterized in that, The control component (6) includes a main control circuit board (63) and a first circuit board (64) and a second circuit board (65) electrically connected to the main control circuit board (63). The MPU6050 chip (61) and the main chip (62) are disposed on the main control circuit board (63). The first circuit board (64) is electrically connected to the display screen (3). The second circuit board (65) is electrically connected to the electromyography sensor (41), the body temperature sensor (42) and the humidity sensor (43) respectively.

6. The wearable device according to claim 5, characterized in that, The main control circuit board (63) and the second circuit board (65) are electrically connected by a pin header, and the battery (5) is disposed between the main control circuit board (63) and the second circuit board (65).

7. The wearable device according to claim 5, characterized in that, The display screen (3) is soldered onto the first circuit board (64).

8. A method for dynamically measuring muscle tone, characterized in that, Applied to a wearable device as described in any one of claims 1-7, comprising: The electromyography data of the wearer are collected using the electromyography sensor (41); The wearer's body temperature data is collected using the body temperature sensor (42); The humidity sensor (43) is used to collect the wearer's humidity data; The wearer's current motion state is determined using the MPU6050 chip (61); The main chip (62) determines the wearer's muscle tone level in the current exercise state based on the wearer's electromyography data, body temperature data, humidity data and current exercise state.

Images