Limb muscle endurance assessment method and device, storage medium and terminal equipment

Abstract

The invention provides a limb muscle endurance evaluation method and device, a storage medium and terminal equipment, and the limb muscle endurance evaluation method comprises the steps: obtaining each motion parameter of a human body part during motion, the human body part comprises an upper limb and / or a lower limb, and the motion parameters represent the posture change of the upper limb and / or the lower limb in a three-dimensional space; and inputting each motion parameter into a pre-trained first evaluation model to obtain an evaluation score of the human body part. The influence of subjectivity during manual judgment can be avoided, and the functional conditions of the limbs can be accurately and objectively evaluated.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method and apparatus for evaluating muscle endurance of limbs, a storage medium, and a terminal device. Background Art

[0002] In the prior art, by evaluating the body parts, such as the upper limb movements and lower limb movements of the user, it can be used to evaluate the functions of the upper and lower limbs, such as the functional status of the upper and lower limb muscles. The myasthenia gravis assessment includes the assessment of the patient's lower and upper limbs.

[0003] In the prior art, professionals mainly perform some simple tests through the MG quantitative scoring system (QMG).

[0004] However, existing evaluation schemes are highly subjective, and there is an urgent need for an objective evaluation scheme to accurately assess the functional status of human body parts. Summary of the invention

[0005] The application can accurately and objectively evaluate the functional status of human body parts.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] In a first aspect, a method for evaluating muscle endurance of limbs is provided, and the method for evaluating muscle endurance of limbs comprises: obtaining various motion parameters of a human body part during motion, wherein the human body part comprises an upper limb and / or a lower limb, and the motion parameters represent posture changes of the upper limb and / or the lower limb in a three-dimensional space; and inputting various motion parameters into a first evaluation model that has been pre-trained to obtain an evaluation score for the human body part.

[0008] Optionally, the motion parameter includes at least one of the following: a rotation angle, a vibration amplitude, a first duration when the rotation angle is less than an angle threshold, a second duration when the angular velocity falling height is less than a displacement threshold, and a falling velocity.

[0009] Optionally, the faster the rotation angle changes over time, the lower the evaluation score; the faster the vibration amplitude changes over time, the lower the evaluation score; the shorter the first duration, the lower the evaluation score; the faster the angular velocity changes over time, the lower the evaluation score; the shorter the second duration, the lower the evaluation score; the faster the falling speed, the lower the evaluation score.

[0010] Optionally, obtaining the motion parameters of a human body part during movement includes: collecting the initial acceleration of the upper limb and / or lower limb and the motion acceleration at each sampling moment; and calculating the rotation angle of the upper limb and / or lower limb at each sampling moment based on the initial acceleration and each motion acceleration.

[0011] Optionally, the method of obtaining motion parameters of a human body part during motion includes: collecting the motion acceleration of the upper limb and / or lower limb at each sampling moment; calculating the frequency distribution of the vibration amplitude of the upper limb and / or lower limb using each motion acceleration; and calculating the root mean square based on the frequency distribution of the vibration amplitude.

[0012] Optionally, calculating the frequency distribution of the vibration amplitude of the upper limb and / or lower limb using each motion acceleration includes: calculating the difference between the modulus of each motion acceleration and the gravitational acceleration; and performing Fourier transform on each difference to obtain the frequency distribution of the vibration amplitude.

[0013] Optionally, the first evaluation model is trained in the following manner: obtaining first training data, where the first training data includes various motion parameters and their corresponding scores; and using the first training data to train the first evaluation model.

[0014] Optionally, the motion parameters are collected using a measuring sensor, and the measuring sensor is fixed on the upper limb and / or lower limb.

[0015] Optionally, an image acquisition device is used to capture video and / or images, and the motion parameters are calculated based on the video and / or images.

[0016] Optionally, the human body part includes respiratory muscles, and the method further includes: obtaining audio data of the user, the audio data including vowel segments; inputting features of the vowel segments into a second evaluation model to obtain the forced vital capacity of the user; and determining the strength of the user's respiratory muscles based on the user's forced vital capacity and the forced vital capacity of the population.

[0017] Optionally, the features of the vowel segment are extracted from the audio data in the following manner: extracting serialized features of the vowel segment, the serialized features including at least one of the following: resonance peak, fundamental frequency, amplitude envelope, harmonic structure; and performing statistics on the serialized features of the vowel segment to obtain the features of the vowel segment.

[0018] In the second aspect, the present application also discloses a limb muscle endurance assessment device, which includes: an acquisition module for acquiring various motion parameters of a human body part during movement, wherein the motion parameters represent the posture changes of the upper limbs and / or lower limbs in three-dimensional space; and an evaluation module for inputting various motion parameters into a pre-trained first evaluation model to obtain an evaluation score for the human body part.

[0019] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. The computer program is executed by a processor to execute any one of the methods provided in the first aspect or the second aspect.

[0020] In a fourth aspect, a terminal device is provided, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to execute the method provided in the first aspect.

[0021] According to a fifth aspect, a computer program product is provided, on which a computer program is stored, and the computer program is executed by a processor to execute a method provided in the first aspect.

[0022] In a sixth aspect, an embodiment of the present application further provides a chip (or a data transmission device) on which a computer program is stored, and when the computer program is executed by the chip, the steps of the above method are implemented.

[0023] In the seventh aspect, an embodiment of the present application also provides a system chip, which is applied to a terminal, and the chip system includes at least one processor and an interface circuit, the interface circuit and the at least one processor are interconnected through lines, and the at least one processor is used to execute instructions to execute a method provided in the first aspect.

[0024] Compared with the prior art, the technical solution of the embodiment of the present application has the following beneficial effects:

[0025] In the technical solution of the present application, by obtaining the motion parameters of the user's upper limbs and / or lower limbs during exercise, the first evaluation model is used to evaluate the motion parameters to obtain the evaluation scores of the user's upper limbs and / or lower limbs, and the evaluation scores can be used to assist in judging the functions of the limbs. Since the motion parameters are objective data and the motion parameters can reflect the functions of the limbs, the present application obtains the evaluation scores by collecting and analyzing the motion parameters, which can avoid the influence of subjectivity during manual judgment and make the action evaluation more objective and accurate. In addition, the technical solution of the present application does not rely on the judgment of professionals. For users, they only need to make prescribed actions, which is easy to use and improves the user experience.

[0026] Furthermore, the motion parameters include at least one of the following: rotation angle, vibration amplitude, first duration when the rotation angle is less than an angle threshold, second duration when the angular velocity drop height is less than a displacement threshold, and drop speed. The above motion parameters are highly correlated with limb functions. The technical solution of the present application can ensure the accuracy of the evaluation score by collecting the above motion parameters and inputting them into the first evaluation model for analysis.

[0027] Furthermore, the present application utilizes the correlation between the characteristics of vowel segments in audio data and the forced vital capacity. The user's forced vital capacity (FVC) can be obtained through the user's audio data, and then the strength of the user's respiratory muscles can be determined in combination with the forced vital capacity of the population, thereby determining the respiratory muscle strength through voice data and achieving accurate assessment of the respiratory muscle strength. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of a method for assessing muscle endurance of limbs provided in an embodiment of the present application;

[0029] Figure 2 is a timing diagram of an acceleration signal provided in an embodiment of the present application;

[0030] Figure 3 is a timing diagram of a rotation angle provided in an embodiment of the present application;

[0031] Figure 4 is a timing diagram of a vibration amplitude provided in an embodiment of the present application;

[0032] Figure 5 is a flow chart of another evaluation method provided in an embodiment of the present application;

[0033] Figure 6 It is a schematic structural diagram of a limb muscle endurance assessment device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] As described in the background technology, existing evaluation schemes are highly subjective, and an objective evaluation scheme is urgently needed to accurately evaluate the functional status of human body parts.

[0035] In the technical solution of the present application, by obtaining the motion parameters of the user's upper limbs and / or lower limbs during exercise, the first evaluation model is used to evaluate the motion parameters to obtain the evaluation scores of the user's upper limbs and / or lower limbs, and the evaluation scores can be used to assist in judging the functions of the limbs. Since the motion parameters are objective data and the motion parameters can reflect the functions of the limbs, the present application obtains the evaluation scores by collecting and analyzing the motion parameters, which can avoid the influence of subjectivity during manual judgment and make the action evaluation more objective and accurate. In addition, the technical solution of the present application does not rely on the judgment of professionals. For users, they only need to make prescribed actions, which is easy to use and improves the user experience.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 The method provided in this application specifically includes the following steps:

[0038] Step 101: acquiring various motion parameters of a human body part during motion, where the human body part includes an upper limb and / or a lower limb, and the motion parameters represent posture changes of the upper limb and / or the lower limb in a three-dimensional space;

[0039] Step 102: Input each movement parameter into the pre-trained first evaluation model to obtain an evaluation score of the human body part, wherein the evaluation score can be used to represent the muscle endurance of the upper limbs and / or lower limbs.

[0040] It should be pointed out that the serial numbers of the steps in this embodiment do not limit the execution order of the steps.

[0041] It is understandable that, in a specific implementation, the limb muscle endurance assessment method can be implemented in the form of a software program, and the software program runs in a processor integrated inside a chip or a chip module. The method can also be implemented in the form of software combined with hardware, which is not limited in this application.

[0042] In the specific implementation of step 101, various motion parameters of the user's upper limbs and / or lower limbs during exercise can be obtained, that is, the posture changes of the user's upper limbs and / or lower limbs in three-dimensional space can be obtained. Specifically, the movements of the user's upper limbs and / or lower limbs during exercise can be set according to the QMG scale, such as raising the left and right upper limbs by 90 degrees when sitting, and raising the left and right lower limbs by 45 degrees when lying flat, etc.

[0043] It should be noted that the movements of the user's upper limbs and / or lower limbs during exercise can be adaptively set according to the actual application scenario, and this application does not impose any restrictions on this.

[0044] In a specific embodiment, a measurement sensor may be used to collect motion parameters, and the measurement sensor may be fixed on the upper limb and / or the lower limb. Specifically, the measurement sensor may be an accelerometer and / or a gyroscope, or a terminal device equipped with an accelerometer and / or a gyroscope.

[0045] For example, a smartphone is equipped with an accelerometer and / or a gyroscope, and the smartphone is fixed on the user's ankles, and the accelerometer and / or gyroscope in the smartphone is used to collect motion parameters of the user's left and right lower limbs.

[0046] For another example, a smartphone is equipped with an accelerometer and / or a gyroscope. The user holds the smartphone or fixes the smartphone on the user's arm, and the accelerometer and / or gyroscope in the smartphone collects motion parameters of the left and right upper limbs.

[0047] In another specific embodiment, an image acquisition device may be used to acquire videos and / or images, and motion parameters may be calculated based on the videos and / or images.

[0048] For example, a smartphone is equipped with a camera, which is used to collect videos and / or images of the user's limbs, and the required motion parameters are obtained from the collected videos and / or images through an image processing algorithm.

[0049] In this embodiment, by collecting the motion parameters of the user's upper limbs and / or lower limbs over a period of time, multiple motion parameters can be obtained, and changes in the motion parameters can reflect the functions of the limbs. Then, by analyzing the above motion parameters, an evaluation of the functions of the user's upper limbs and / or lower limbs can be obtained.

[0050] Then in the specific implementation of step 102, the analysis of the above-mentioned motion parameters is realized by the first evaluation model that has been pre-trained. Specifically, each motion parameter can be input into the first evaluation model, and the first evaluation model can output a corresponding evaluation score for a set of motion parameters. The numerical value of the evaluation score can reflect the degree of completeness of the user's upper limb and / or lower limb function, for example, it can reflect the strength of the user's upper limb and / or lower limb muscles, then the higher the evaluation score, the higher the strength of the user's upper limb and / or lower limb muscles.

[0051] For another example, the numerical value of the evaluation score can reflect the standardization of the user's actions. The higher the evaluation score, the higher the standardization of the user's actions, which means that the strength of the muscles of the user's upper limbs and / or lower limbs is higher. In other words, the first evaluation model achieves the classification of the functions of the upper limbs and / or lower limbs by outputting the evaluation score, for example, by classifying the strength of the muscles of the user's upper limbs and / or lower limbs, thereby achieving the evaluation of the functions of the upper limbs and / or lower limbs.

[0052] In this embodiment, since the motion parameters are objective data and can reflect the functions of the limbs, this application obtains evaluation scores by collecting and analyzing the motion parameters, which can avoid the influence of subjectivity in manual judgment and make the action evaluation more objective and accurate. In addition, the technical solution of this application does not rely on the judgment of professionals. For users, they only need to perform prescribed actions, which is easy to use and improves user experience.

[0053] In a non-limiting embodiment, the motion parameter includes at least one of the following: rotation angle, vibration amplitude, first duration when the rotation angle is less than an angle threshold, second duration when the angular velocity drop height is less than a displacement threshold, and drop velocity. The motion parameter may be directly acquired by a measurement sensor or calculated from data acquired by the measurement sensor.

[0054] For example, when the measuring sensor is a gyroscope, the rotation angle and angular velocity can be directly acquired, and the vibration amplitude, the first duration, the second duration and the falling speed can be calculated through the rotation angle and / or angular velocity.

[0055] For another example, the measuring sensor is an accelerometer, which can directly collect three-dimensional acceleration, and the rotation angle, vibration amplitude, first duration, second duration, falling speed and angular velocity can be calculated through the above three-dimensional acceleration.

[0056] Furthermore, when the first evaluation model outputs an evaluation score based on the motion parameters, the correlation between the various motion parameters and the evaluation scores is as follows: the evaluation score corresponding to the rotation angle that changes faster over time is lower than the evaluation score corresponding to the rotation angle that changes slower over time; the evaluation score corresponding to the vibration amplitude that changes faster over time is lower than the evaluation score corresponding to the vibration amplitude that changes slower over time; the evaluation score corresponding to the shorter first duration is lower than the evaluation score corresponding to the longer first duration; the evaluation score corresponding to the angular velocity that changes faster over time is lower than the evaluation score corresponding to the angular velocity that changes slower over time; the evaluation score corresponding to the shorter second duration is lower than the evaluation score corresponding to the longer second duration; and the evaluation score corresponding to the larger falling speed is lower than the evaluation score corresponding to the smaller falling speed.

[0057] In a specific implementation, the measuring sensor is an accelerometer, which can collect the movement acceleration of the upper limbs and / or lower limbs at each sampling moment. Taking the sampling frequency of the accelerometer as 100 Hz as an example, Figure 2 The figure shows the movement acceleration at each sampling moment when the accelerometer samples 35,000 sampling points (i.e., 350 seconds). The movement acceleration can be expressed as three-dimensional acceleration on the X-axis, Y-axis, and Z-axis. The initial acceleration of the upper limb and / or lower limb at the beginning of the movement is (accX0, accY0, accZ0).

[0058] In a specific embodiment, the rotation angle of the upper limb and / or lower limb at each sampling moment can be calculated using motion acceleration. First, the motion acceleration can be low-pass filtered, such as a Butterworth filter low-pass filtered, to filter out noise interference. Then, the rotation angle of the upper limb and / or lower limb at each sampling moment is calculated based on the initial acceleration and each motion acceleration. Specifically, the direction cosine between each motion acceleration and the initial acceleration is calculated, and then the inverse trigonometric cosine is used to obtain the rotation angle.

[0059] In another specific embodiment, the rotation angle can be directly measured using a gyroscope. Among the user's actions indicated by the QMG, some actions only have a rotation angle on a certain axis of the three-dimensional coordinate system. Due to the stability of the user's handheld device, there may be rotation angles on multiple axes of the three-dimensional coordinate system. Therefore, it is necessary to select the main axis and perform coordinate system conversion on the measurement result so that the rotation angle only exists on the main axis.

[0060] It should be noted that more specific implementations of coordinate system conversion can refer to existing technologies, and this application does not limit this.

[0061] Please refer to Figure 3 , Figure 3 Figure 2 shows a schematic diagram of the rotation angle changing with time. Figure 3 It can be seen that as time goes by, the rotation angle becomes larger and larger.

[0062] In a specific embodiment, the vibration amplitude of the upper limb and / or lower limb at each sampling time can be calculated using motion acceleration. Specifically, the modulus of each motion acceleration is obtained, and then the difference (difference) between the modulus of each motion acceleration and the gravity acceleration is calculated, and each difference is Fourier transformed to obtain the frequency distribution of the vibration amplitude. The root mean square is calculated based on the frequency distribution of the vibration amplitude.

[0063] Figure 4 A schematic diagram showing the variation of the root mean square of the vibration amplitude over time is shown in FIG. Figure 4 As shown, curve 40 represents the change of the root mean square of the vibration amplitude. As time goes by, the value of the root mean square of the vibration amplitude becomes larger and larger. That is, in the initial stage of the movement of the upper limbs and / or lower limbs, the root mean square of the vibration amplitude increases slowly over time, and in the second half of the stage, the root mean square of the vibration amplitude increases faster and faster over time. The root mean square of the vibration amplitude can reflect the function of the upper limbs and / or lower limbs, such as the degree of muscle weakness.

[0064] Furthermore, after obtaining the rotation angle, a first duration when the rotation angle is less than the angle threshold may also be obtained, and the first duration may also reflect the function of the upper limbs and / or lower limbs of the user.

[0065] Furthermore, the height of the fall of the upper limbs and / or lower limbs can be calculated, and the second duration when the fall height is less than the displacement threshold can be counted. The second duration can also reflect the function of the user's upper limbs and / or lower limbs.

[0066] Similarly, the falling speed of the upper limbs and / or lower limbs can also be calculated based on the collected motion acceleration, and the falling speed can also reflect the function of the upper limbs and / or lower limbs of the user. For example, the faster the falling speed of the upper limbs during exercise, the weaker the upper limb muscle strength, and the lower the evaluation score output by the first evaluation model.

[0067] Through the above embodiment, motion parameters for evaluating limb movements can be obtained. By inputting them into the first evaluation model, an evaluation score can be obtained. Among them, the first evaluation model can be pre-trained by first training data. The first training data includes various motion parameters and their corresponding scores. The method for obtaining the motion parameters in the first training data can refer to the above embodiment. The scores corresponding to the motion parameters in the first training data can be obtained in advance through annotation.

[0068] In a specific implementation, when constructing the first training data, the motion parameters of the user's upper limbs and / or lower limbs when they have different functions can be collected, for example, the various motion parameters of the user's upper limbs and / or lower limbs under different muscle strengths are collected, and the corresponding scores are marked.

[0069] Specifically, the motion parameters in the first training data are consistent with the motion parameters input into the first evaluation model, for example, the motion parameters are rotation angle, vibration amplitude, first duration of rotation angle, angular velocity, second duration and falling velocity.

[0070] Specifically, the first evaluation model can be constructed using machine learning models such as logistic regression and random forest.

[0071] It should be noted that the first evaluation model may also be constructed in any other feasible manner, such as by using a neural network algorithm, and this application does not impose any limitation on this.

[0072] In a specific example, the motion parameters involved in the training include the rotation angle at each sampling moment, the vibration amplitude at the beginning of the movement, the vibration amplitude at the end of the movement, the first duration when the rotation angle is less than the angle threshold, the ratio of the vibration amplitude at the end of the movement to the vibration amplitude at the beginning of the movement, the angular velocity at each sampling moment, for example, the angular velocity at each sampling moment when the upper limbs and / or lower limbs fall, the second duration when the falling height is less than the displacement threshold, and the falling velocity at each sampling moment.

[0073] It should be noted that the motion parameters in the first training data and the motion parameters input into the first evaluation model may also be a combination of the above-mentioned motion parameters, and the present application does not impose any limitation on this.

[0074] In a specific application scenario, an application and an accelerometer and / or a gyroscope are loaded in the terminal device, and the application can execute the various steps of the above-mentioned method for assessing muscle endurance of the limbs. Taking the example of raising the upper limbs 90 degrees in a sitting position, from the user's perspective, only the following operations need to be performed to achieve the assessment of the upper limb function, which is easy to operate. Specifically, the user is sitting in a seat with his arm fixing the above-mentioned terminal device; the arm is straightened and raised 90 degrees sideways or upward; the application is opened, and the terminal device will collect three-dimensional acceleration signals; the user continues to keep the arm raised 90 degrees until it can no longer be maintained, and then closes the application.

[0075] In another specific application scenario, an application and an accelerometer and / or a gyroscope are loaded in a terminal device. The terminal device uploads the collected acceleration signal or rotation angle to a server through the application, and the server executes each step of the above-mentioned limb muscle endurance evaluation method and sends the evaluation score to the application, which displays the evaluation score to the user.

[0076] In a non-limiting embodiment, the human body part may include respiratory muscles, and the strength of the respiratory muscles may also be evaluated through audio data, specifically, the strength of the respiratory muscles in the user's lungs or vocal organs (such as throat) may be evaluated.

[0077] Please refer to Figure 5 , Figure 5 A flow chart for assessing respiratory muscle strength is shown.

[0078] In step 501, audio data of a user is acquired, where the audio data includes vowel segments.

[0079] In a specific implementation, a vowel refers to a speech unit in which the vocal cords vibrate and the vocal tract shape is relatively stable during the pronunciation process of the user. The acoustic characteristics of a vowel are usually manifested as an obvious resonance peak structure.

[0080] The applicant has found that the pronunciation duration of vowels and the audio features of some vowels are correlated to the forced vital capacity. Therefore, after obtaining the user's audio data, vowel segments and the features of vowel segments in the audio data can also be extracted. Specifically, the vowel segments in the audio data can be extracted by a vowel extraction algorithm, and non-vowel parts such as consonants and pauses can be removed.

[0081] It should be noted that the specific implementation process of the vowel extraction algorithm can refer to the prior art, and the present application does not limit this. In a specific embodiment, the features of the vowel segment can be extracted from the audio data in the following manner: extracting the serialized features of the vowel segment, the serialized features including at least one of the following: formant, fundamental frequency, amplitude envelope, harmonic structure.

[0082] Furthermore, statistics are performed on the serialized features of the vowel segment to obtain the features of the vowel segment. Specifically, one or more of the mean, median, mode, variance, standard deviation, skewness or kurtosis of the serialized features of the vowel segment can be calculated.

[0083] Specifically, the characteristics of the vowel segment can reflect the frequency jitter and / or amplitude shimmer of the audio data. The frequency jitter mainly focuses on the fluctuation of the fundamental frequency, reflecting the stability of the vocal cord vibration frequency, and the amplitude shimmer mainly focuses on the fluctuation of the amplitude, reflecting the stability of the vocal cord vibration intensity. Therefore, the characteristics of the above vowel segment can reflect the characteristics of vocal cord vibration, describe the periodic fluctuation of audio data, and can be used to evaluate the user's forced vital capacity.

[0084] In step 502, the features of the vowel segment are input into a second evaluation model to obtain the user's forced vital capacity, wherein the second evaluation model is a pre-trained model.

[0085] In specific implementation, forced vital capacity refers to the maximum amount of air that can be exhaled after a maximum inhalation and exhalation as quickly as possible. Forced vital capacity is an important indicator in lung function testing and can be used to evaluate the overall function of the lungs, especially the capacity of the lungs and the patency of the airways. Forced vital capacity is usually expressed in liters (L) or milliliters (mL).

[0086] In this embodiment, the features of the vowel segment are used as input to the second evaluation model, and the second evaluation model outputs the corresponding forced vital capacity.

[0087] Different from the prior art which requires the user to exhale as quickly and completely as possible after taking a maximum breath until he can no longer exhale, the present embodiment determines the user's forced vital capacity through the user's audio data, thus ensuring the accuracy of the forced vital capacity without the user's full cooperation, and is easy to use.

[0088] In some examples, the user's identity information may also be obtained, and the user's identity information and the features of the vowel segment are input together into the second evaluation model, and the second evaluation model outputs the predicted forced vital capacity of the user.

[0089] Specifically, the user's identity information may include but is not limited to the user's gender, age, height, weight, medical history, etc., which may be in the form of numerical values, enumerations, Boolean values, text fields or other forms, and it can be understood that the present disclosure is not limited to this.

[0090] In step 503, the strength of the user's respiratory muscles is determined according to the user's forced vital capacity and the population's forced vital capacity.

[0091] Among them, the forced vital capacity of the population can be a pre-calculated value, and the forced vital capacity of the population can reflect the forced vital capacity of the human race as a whole. The ratio of the forced vital capacity of the user to the forced vital capacity of the population can reflect the strength of the user's respiratory muscles. Specifically, the larger the ratio, the stronger the user's respiratory muscles; the smaller the ratio, the weaker the user's respiratory muscles.

[0092] Specifically, demographic information (such as age, gender, height, weight, etc.) can be used to estimate the population forced vital capacity of a specific population. Exemplarily, the relationship between user identity information and lung function indicators can be linearly fitted using known statistical data to reflect the impact of different user identities on the corresponding lung function indicators. Thus, the population forced vital capacity calculated based on population statistical information, such as the predicted FVC of the population, can be obtained.

[0093] In a specific embodiment, the second evaluation model can be pre-trained using second training data. The second training data includes features of vowel segments and their corresponding forced vital capacity. The features of the vowel segments can be extracted from the audio data through the aforementioned feature extraction process, and the forced vital capacity can be measured by a spirometer.

[0094] Specifically, the second evaluation model may be a regression model, or a model constructed by any other feasible algorithm, and this application does not impose any limitation on this.

[0095] In a specific application scenario, the first evaluation model and the second evaluation model can be deployed in a server. The user's terminal device collects upper and / or lower limb motion parameters and uploads them to the server, and the evaluation scores of the upper and / or lower limbs are determined by the first evaluation model in the server. Alternatively, the user's terminal device collects the user's audio data and uploads the audio data to the server, which extracts the features of the vowel segment and determines the user's forced vital capacity through the second evaluation model in the server.

[0096] Please refer to Figure 6 The present application also discloses a limb muscle endurance assessment device 60. The limb muscle endurance assessment device 60 comprises:

[0097] A first acquisition module 601 is used to acquire various motion parameters of the upper limbs and / or lower limbs of the user during motion, wherein the motion parameters represent posture changes of the upper limbs and / or lower limbs in three-dimensional space;

[0098] The first evaluation module 602 is used to input various motion parameters into a pre-trained first evaluation model to obtain the evaluation scores of the upper limbs and / or lower limbs.

[0099] The embodiment of the present invention obtains the motion parameters of the user's upper limbs and / or lower limbs during exercise, and evaluates the motion parameters through a first evaluation model to obtain an evaluation score of the user's upper limbs and / or lower limbs, which can be used to assist in judging the functions of the limbs. Since the motion parameters are objective data and the motion parameters can reflect the functions of the limbs, the embodiment of the present invention obtains the evaluation score by collecting and analyzing the motion parameters, which can avoid the influence of subjectivity during manual judgment and make the action evaluation more objective and accurate. In addition, the technical solution of the present application does not rely on the judgment of professionals. For users, they only need to make prescribed actions, which is easy to use and improves the user experience.

[0100] Further, continue to refer to Figure 6 The limb muscle endurance evaluation device 60 may further include: a second acquisition module 603, used to acquire audio data of the user, the audio data including vowel segments. A second evaluation module 604, used to input the features of the vowel segments into a second evaluation model to obtain the user's forced vital capacity. A determination module 605, used to determine the strength of the user's respiratory muscles according to the user's forced vital capacity and the population's forced vital capacity.

[0101] This embodiment uses the correlation between the characteristics of vowel segments in audio data and the forced vital capacity. The user's forced vital capacity (FVC) can be obtained through the user's audio data, and then the strength of the user's respiratory muscles is determined in combination with the forced vital capacity of the crowd, thereby achieving the determination of respiratory muscle strength through voice data, avoiding the influence of subjectivity in manual judgment, and making the evaluation more objective and accurate.

[0102] For more specific implementation methods of the embodiments of the present application, please refer to the aforementioned embodiments, which will not be repeated here.

[0103] In a specific implementation, the above-mentioned limb muscle endurance evaluation device 60 may correspond to a chip with an evaluation function in a terminal device, such as a SOC, a baseband chip, etc.; or to a chip module with an evaluation function in a terminal device; or to a chip module with a data processing function chip, or to a terminal device. The terminal device may be a medical device, or a smart phone, a smart bracelet, a server, etc., and this application does not limit this.

[0104] For other related descriptions of the limb muscle endurance evaluation device 60, please refer to Figures 1 to 5 The relevant description in will not be repeated here.

[0105] Regarding the various modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, or hardware modules / units, or they can be partially software modules / units and partially hardware modules / units. For example, for various devices and products applied to or integrated in a chip, the various modules / units included therein can all be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in a chip module, the various modules / units included therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component of the chip module (such as a chip, circuit module, etc.) or in different components, or at least some of the modules / units can be implemented in the form of software programs. It is implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0106] The embodiment of the present application also discloses a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is run, the steps of the aforementioned method for assessing muscle endurance of the limbs can be executed. The storage medium may include a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. The storage medium may also include a non-volatile memory (non-volatile) or a non-transitory memory, etc.

[0107] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship.

[0108] The "plurality" appearing in the embodiments of the present application refers to two or more.

[0109] The first, second, etc. descriptions appearing in the embodiments of the present application are only used for illustration and distinction of the description objects. There is no order, nor do they indicate any special limitation on the number of devices in the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.

[0110] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means.

[0112] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0116] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the method described in each embodiment of the present application.

[0117] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for assessing muscle endurance of limbs, characterized in that: include: Acquire various motion parameters of a human body part during motion, wherein the human body part includes an upper limb and / or a lower limb, and the motion parameters represent posture changes of the upper limb and / or the lower limb in a three-dimensional space; Various motion parameters are input into a pre-trained first evaluation model to obtain an evaluation score for the human body part, wherein the evaluation score is used to represent the muscle endurance of the upper limbs and / or lower limbs.

2. The method for evaluating muscle endurance of limbs according to claim 1, characterized in that: The motion parameter includes at least one of the following: Rotation angle, vibration amplitude, first duration when the rotation angle is less than the angle threshold, angular velocity, second duration when the falling height is less than the displacement threshold, and falling velocity.

3. The method for assessing muscle endurance of limbs according to claim 2, characterized in that: The faster the rotation angle changes over time, the lower the evaluation score; the faster the vibration amplitude changes over time, the lower the evaluation score; the shorter the first duration, the lower the evaluation score; the faster the angular velocity changes over time, the lower the evaluation score; the shorter the second duration, the lower the evaluation score; the faster the falling speed, the lower the evaluation score.

4. The method for evaluating muscle endurance of limbs according to claim 1, characterized in that: The obtaining of the motion parameters of the human body parts during motion comprises: Collect the initial acceleration of the upper limb and / or lower limb and the movement acceleration at each sampling moment; calculate the rotation angle of the upper limb and / or lower limb at each sampling moment according to the initial acceleration and each movement acceleration.

5. The method for evaluating muscle endurance of limbs according to claim 1, characterized in that: The obtaining of the motion parameters of the human body parts during motion comprises: Collecting the movement acceleration of the upper limb and / or lower limb at each sampling moment; Calculating the frequency distribution of the vibration amplitude of the upper limb and / or lower limb using each movement acceleration; A root mean square is calculated based on the frequency distribution of the vibration amplitude.

6. The method for assessing muscle endurance of limbs according to claim 5, characterized in that: The frequency distribution of the vibration amplitude of the upper limb and / or lower limb calculated by using each motion acceleration includes: Calculate the difference between the modulus of each motion acceleration and the gravitational acceleration; The individual differences are Fourier transformed to obtain the frequency distribution of the vibration amplitude.

7. The method for assessing muscle endurance of limbs according to claim 1, characterized in that: The first evaluation model is trained in the following manner: Acquire first training data, where the first training data includes various motion parameters and their corresponding scores; The first evaluation model is trained using the first training data.

8. The method for evaluating muscle endurance of limbs according to any one of claims 1 to 7, characterized in that: The movement parameters are collected using measurement sensors, which are fixed on the upper limbs and / or lower limbs.

9. The method for assessing muscle endurance of limbs according to any one of claims 1 to 7, characterized in that: An image acquisition device is used to acquire video and / or images, and the motion parameters are calculated based on the video and / or images.

10. A limb muscle endurance assessment device, characterized in that: include: An acquisition module, used to acquire various motion parameters of a human body part during motion, wherein the human body part includes an upper limb and / or a lower limb, and the motion parameters represent posture changes of the upper limb and / or the lower limb in a three-dimensional space; The evaluation module is used to input various motion parameters into a pre-trained first evaluation model to obtain an evaluation score of the human body part.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for assessing muscle endurance of the limbs according to any one of claims 1 to 9 are executed.

12. A terminal device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor runs the computer program, the processor executes the steps of the method for assessing muscle endurance of the limbs according to any one of claims 1 to 9.

Images