Closed-loop monitoring and intelligent early warning method and system based on attitude sensor

Abstract

The embodiment of the invention relates to the technical field of intelligent monitoring, and discloses a closed-loop monitoring and intelligent early warning method and system based on attitude sensors, and the method comprises the steps: firstly obtaining the real-time monitoring data of a first attitude sensor and a second attitude sensor, and forming a first initial data set and a second initial data set; correcting the initial data set according to deformation characteristics of a sensor mounting part to obtain a first target data set and a second target data set; determining a real-time motion angle of the first joint body relative to the second joint body based on the target data set; then a time sequence simulation joint motion graph is constructed according to the real-time motion angle; and finally, generating an early warning signal according to the time sequence simulation joint motion graph or the real-time motion angle of the joint so as to remind a user to adjust a motion mode or stop motion. Therefore, according to the technical scheme, measurement errors caused by deformation of soft tissue around the joint can be reduced, the joint movement monitoring accuracy is improved, therefore, sport injuries are effectively prevented, and the safety and rationality of movement are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, and particularly to a closed-loop monitoring and intelligent early warning method and system based on an attitude sensor. Background Art

[0002] In the field of human motion health, the monitoring and evaluation of joint motion are of crucial significance for preventing sports injuries, improving sports performance, and rehabilitation medicine. With the continuous improvement of people's health awareness, the number of people participating in various sports activities is increasing day by day. However, the incidence of sports injuries has also risen accordingly. For example, in common knee joint movements, due to improper movement postures, excessive exercise intensity, or potential problems in the joints themselves, it is very easy to cause serious consequences such as knee sprains and ligament injuries, which not only affect an individual's daily life and sports ability but also may bring long-term health hazards.

[0003] Currently, the monitoring of joint motion mainly relies on traditional observation methods and simple measurement tools. Observation methods are often affected by the subjective factors of observers and are difficult to accurately and comprehensively capture the subtle changes and complex characteristics of joint motion. And simple measurement tools, such as goniometers, can only provide single-dimensional motion data and cannot reflect the multi-dimensional motion state of the joint in the entire motion process in real time and dynamically. In addition, most of the existing monitoring methods lack real-time feedback and early warning mechanisms. When abnormal joint motion occurs, users cannot be reminded in time to adjust their exercise methods or stop exercising, thus increasing the risk of sports injuries. Summary of the Invention

[0004] The main object of the present invention is to provide a closed-loop monitoring and intelligent early warning method and system based on an attitude sensor, aiming to solve the technical problems of inaccurate monitoring of joint motion data and lack of real-time feedback mechanism in the prior art.

[0005] To achieve the above object, in a first aspect, an embodiment of the present application provides a closed-loop monitoring and intelligent early warning method based on an attitude sensor, which is applied to the monitoring and early warning of joint motion. The method includes: Respectively obtain the real-time monitoring data of a first attitude sensor and a second attitude sensor to obtain a first initial data set and a second initial data set. The first initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of a first joint body, and the second initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of a second joint body; Perform data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation site to obtain a first target data set and a second target data set; Determine the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; Construct a time-series simulated joint motion graph according to the real-time motion angle of the first joint body relative to the second joint body; Generate a warning signal according to the time-series simulated joint motion graph or the real-time motion angle of the joint, and the warning signal is used to remind the user to adjust the motion mode or stop the motion.

[0006] In a possible implementation, the motion data includes one or more of acceleration, displacement, angle, or motion trajectory.

[0007] In a possible implementation, the joint is a knee joint, the first initial data set includes the pitch motion angle and yaw motion angle of the thigh, and the second initial data set includes the pitch motion angle and yaw motion angle of the calf; the data correction of the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation site to obtain the first target data set and the second target data set includes: Correct the pitch motion angle and yaw motion angle of the thigh according to the first deformation coefficient of the first attitude sensor at the thigh installation site to obtain the first target data set, and the first deformation coefficient characterizes the deformation ability of the soft tissue at the thigh installation site; Correct the pitch motion angle and yaw motion angle of the calf according to the second deformation coefficient of the second attitude sensor at the calf installation site to obtain the second target data set, and the second deformation coefficient characterizes the deformation ability of the soft tissue at the calf installation site.

[0008] In a possible implementation, the step of correcting the pitch motion angle and yaw motion angle of the thigh according to the first deformation coefficient of the first attitude sensor at the thigh installation site to obtain the first target data set includes: Construct a thigh soft tissue deformation correction model according to the first deformation coefficient. The correction model is based on the mechanical characteristics of human soft tissue, and uses the first deformation coefficient as a key parameter to describe the deformation law of the soft tissue at the thigh installation site under different motion angles; Input the initial measurement data into the thigh soft tissue deformation correction model, and use the correction model to perform correction calculations on the pitch motion angle measurement value and yaw motion angle measurement value in the initial measurement data to obtain the corrected pitch motion angle and yaw motion angle; Integrate the corrected pitch motion angle and yaw motion angle to form a first target data set containing corrected motion angle information.

[0009] In a possible implementation manner, determining the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set includes: Obtaining the real-time pitch motion angle of the first joint body relative to the second joint body according to the real-time pitch motion angle of the first joint body, the real-time pitch motion angle of the second joint body, and the pitch transformation relationship, where the pitch transformation relationship is the pitch motion coordinate transformation between the coordinates of the first joint body and the coordinates of the second joint body; Obtaining the real-time yaw motion angle of the first joint body relative to the second joint body according to the real-time yaw motion angle of the first joint body, the real-time yaw motion angle of the second joint body, and the yaw transformation relationship, where the yaw transformation relationship is the yaw motion coordinate transformation between the coordinates of the first joint body and the coordinates of the second joint body.

[0010] In a possible implementation manner, constructing a time-series simulated joint motion graph according to the real-time motion angle of the first joint body relative to the second joint body includes: Sequentially obtaining the real-time motion angle data of the first joint body relative to the second joint body in chronological order; According to a preset joint model, mapping the real-time motion angle data at each time point to the corresponding position of the joint model, where the joint model is a three-dimensional model simulating the connection relationship between the first joint body and the second joint body; Combining the states of the joint model at each mapped time point in chronological order to form a time-series simulated joint motion graph that can dynamically display the motion process of the first joint body relative to the second joint body.

[0011] In a possible implementation manner, the warning signal includes one or more of a voice signal, a vibration signal, or an APP push signal.

[0012] In a possible implementation manner, generating a warning signal according to the time-series simulated joint motion graph or the real-time motion angle of the joint includes: Inputting the time-series simulated joint motion graph into a risk identification model to obtain a risk coefficient characterization value; Generating warning signals of different levels according to the risk coefficient characterization value; Among them, when the risk coefficient characterization value is greater than or equal to the first threshold, the user is reminded to stop the motion by voice; when the risk coefficient characterization value is greater than or equal to the second threshold and less than the first threshold, the user is reminded to adjust the motion mode by vibration.

[0013] In a possible implementation manner, the step of inputting the time-series simulated joint motion graph into a risk identification model to obtain a risk coefficient characterization value includes: Extract features from the sequential simulated joint motion diagram to obtain a joint motion feature vector, where the joint motion feature vector includes at least two of joint motion angle features, joint motion speed features, joint motion acceleration features, and joint motion trajectory features; Input the joint motion feature vector into a pre-trained risk identification model, where the risk identification model is constructed based on a deep learning algorithm; The risk identification model calculates according to the input joint motion feature vector and outputs a risk coefficient characterization value, where the risk coefficient characterization value reflects the likelihood of a risk existing in the current joint motion state.

[0014] In a second aspect, an embodiment of the present application further provides a closed-loop monitoring and intelligent warning system, including: A first attitude sensor, where the first attitude sensor is disposed on a first joint body; A second attitude sensor, where the second attitude sensor is disposed on a second joint body, and the second joint body is rotationally connected to the first joint body to form a joint; and A memory and a processor, where the memory is used to store program code; the processor is used to call the program code to execute the method as described in the first aspect.

[0015] Different from the prior art, a closed-loop monitoring and intelligent warning method based on attitude sensors provided by an embodiment of the present application first obtains real-time monitoring data of the first attitude sensor and the second attitude sensor to obtain a first initial data set and a second initial data set; then corrects the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation part to obtain a first target data set and a second target data set; then determines the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; then constructs a sequential simulated joint motion diagram according to the real-time motion angle of the first joint body relative to the second joint body; and finally generates a warning signal according to the sequential simulated joint motion diagram or the real-time motion angle of the joint to remind the user to adjust the motion mode or stop the motion. In this way, the technical solution of the present application can effectively reduce the measurement error caused by the deformation of the soft tissues around the joint, improve the accuracy of joint motion monitoring, and can present the joint motion process in real time, dynamically and intuitively, promptly detect abnormal motion states and issue warnings, effectively preventing sports injuries and improving the safety and rationality of sports. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0017] Figure 1 Schematic diagram of the layout of the attitude sensor in the joint in some embodiments of the present application; Figure 2 Schematic diagram of the flow of the closed-loop monitoring and intelligent early warning method based on the attitude sensor in some embodiments of the present application; Figure 3 Schematic diagram of the flow of step S200 of the closed-loop monitoring and intelligent early warning method based on the attitude sensor in some embodiments of the present application; Figure 4 Schematic diagram of the flow of step S300 of the closed-loop monitoring and intelligent early warning method based on the attitude sensor in some embodiments of the present application; Figure 5 Schematic diagram of the hardware structure of the closed-loop monitoring and intelligent early warning system in some embodiments of the present application.

[0018] The realization, functional features and advantages of the object of the present invention will be further described in conjunction with the embodiments and with reference to the drawings. Specific embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0021] In addition, the descriptions involving "first", "second", etc. in the present invention are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or is unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] In the field of human motion health, the monitoring and evaluation of joint motion are of crucial significance for preventing sports injuries, improving sports performance, and rehabilitation medicine. With the continuous improvement of people's health awareness, the number of people participating in various sports activities is increasing day by day. However, the incidence of sports injuries has also risen accordingly. For example, in common knee joint movements, due to improper movement postures, excessive exercise intensity, or potential problems in the joint itself, it is very easy to cause serious consequences such as knee joint sprains and ligament injuries, which not only affect an individual's daily life and motor ability but also may bring long-term health hazards.

[0023] Currently, the monitoring of joint motion mainly relies on traditional observation methods and simple measurement tools. Observation methods are often affected by the subjective factors of observers and are difficult to accurately and comprehensively capture the subtle changes and complex characteristics of joint motion. And simple measurement tools, such as goniometers, etc., can only provide single-dimensional motion data and cannot reflect the multi-dimensional motion state of the joint in the entire motion process in real time and dynamically. In addition, most of the existing monitoring methods lack real-time feedback and warning mechanisms. When abnormal joint motion occurs, users cannot be reminded in time to adjust their exercise methods or stop exercising, thus increasing the risk of sports injuries.

[0024] The following takes the closed-loop monitoring and intelligent warning system executing the closed-loop monitoring and intelligent warning method based on the attitude sensor as an example for illustration. As Figure 1 shown, in the embodiments of the present application, the closed-loop monitoring and intelligent warning system at least includes a first attitude sensor 100 and a second attitude sensor 200. Among them, the first attitude sensor 100 is disposed on the first joint body L100; the second attitude sensor 200 is disposed on the second joint body L200, and the second joint body L200 is rotatably connected to the first joint body L100 to form a joint, and the joint can be a movable joint such as a knee joint, a shoulder joint, a hip joint, an elbow joint, an ankle joint, etc.

[0025] Optionally, the first attitude sensor 100 and the second attitude sensor 200 in this application may be inertial measurement units (IMUs). An inertial measurement unit is a device used to measure the three-axis attitude angles (or angular rates) and accelerations of an object. It is also possible to integrate a displacement detection function based on the detection of angles, angular velocities, and accelerations to achieve displacement measurement.

[0026] It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here. Please refer to the appendix Figures 1-4 , and the method includes the following steps S100 - step S500: Step S100, respectively obtain the real-time monitoring data of the first attitude sensor and the second attitude sensor to obtain a first initial data set and a second initial data set. The first initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of the first joint body, and the second initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of the second joint body; Specifically, the first initial data set may include the pitch motion data, yaw motion data, and roll motion data of the first joint body. The pitch motion data may be one or more of the angle, acceleration, displacement amount, or motion trajectory of the pitch motion; the yaw motion data may also be one or more of the angle, acceleration, displacement amount, or motion trajectory of the yaw motion; the roll motion data may also be one or more of the angle, acceleration, displacement amount, or motion trajectory of the roll motion.

[0027] Pitch motion refers to the up and down motion of the joint body around the transverse axis. For example, the motion of the neck when a person raises or lowers their head; yaw motion is the left and right rotation of the joint body around the vertical axis, like when a person turns their head left and right; roll motion is the rotation of the joint body around the longitudinal axis, similar to the motion of the torso when a person twists their body. These data can be of various types. For example, the angle value can directly reflect the degree of rotation of the joint body in different motion directions; the acceleration data can reflect the speed change of the joint body's motion; the displacement amount can represent the position movement of the joint body in space; and the motion trajectory can visually display the path of the joint body's motion.

[0028] Exemplarily, it is possible to obtain the pitch motion data and yaw motion data of the first joint body sensed by the first attitude sensor to obtain a first initial data set, obtain the pitch motion data and yaw motion data of the second joint body sensed by the second attitude sensor to obtain a second initial data set, and use the first initial data set and the second initial data set as the data basis for joint motion analysis.

[0029] Step S200: Perform data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation part to obtain a first target data set and a second target data set; During the process of monitoring joint movement based on an attitude sensor, although the first initial data set and the second initial data set obtained in step S100 contain the movement information of the first joint body and the second joint body, there are data deviations. This deviation mainly stems from the installation position of the attitude sensor and the characteristics of the soft tissues around the human joints.

[0030] Soft tissues around human joints, such as muscles and skin, have elasticity and deformation ability. When the joint body moves, the soft tissues will undergo corresponding deformations. Taking the knee joint as an example, when the knee joint bends, the soft tissues in the thigh and calf areas will be squeezed and stretched. Since the attitude sensor is installed at a specific part of the joint body, for example, to reduce the influence of other environmental factors, the first attitude sensor is usually installed on the outside of the thigh, and the second attitude sensor is generally installed on the outside of the calf. At this time, the deformation of the soft tissues will cause the actual movement state of the attitude sensor itself not to fully match the actual movement state of the joint body. This makes the movement data measured by the attitude sensor unable to accurately reflect the real movement of the joint body.

[0031] In order to obtain data that can truly reflect the movement of the joint body, the embodiments of the present application perform data correction on the first initial data set and the second initial data set. The data correction needs to be carried out according to the deformation characteristics of the sensor installation part. The deformation characteristics of the soft tissues in different joint parts are different. For example, the soft tissues around the knee joint are relatively thick and have strong toughness, and the degree of deformation may be relatively large during movement; while the soft tissues around the wrist joint are relatively thin, and the degree of deformation may be relatively small. By studying and analyzing the mechanical properties and deformation laws of the soft tissues in specific joint parts, the deformation characteristics are determined and described by specific parameters (such as deformation coefficients).

[0032] For each item of movement data in the first initial data set, such as pitch movement data and yaw movement data, etc., it will be adjusted in combination with the corresponding deformation characteristics. If the deformation coefficient of the installation part of the first attitude sensor in a certain movement direction is known, the movement data in the initial data set in this direction can be corrected and calculated according to this coefficient, so as to reduce or even eliminate the error caused by the deformation of the soft tissues. The same correction method is also used for the second initial data set, and finally a first target data set and a second target data set that can more accurately reflect the actual movement states of the first joint body and the second joint body are obtained.

[0033] The target data set obtained through data correction can lay a reliable data foundation for subsequent steps such as accurately calculating the real-time movement angle of the first joint body relative to the second joint body, constructing a sequential simulated joint motion graph, and generating a warning signal.

[0034] In one embodiment, the joint is a knee joint. The first initial data set includes the pitch motion angle and yaw motion angle of the thigh, and the second initial data set includes the pitch motion angle and yaw motion angle of the calf. The step S200: performing data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation site to obtain a first target data set and a second target data set, including: Step S210: correcting the pitch motion angle and yaw motion angle of the thigh according to the first deformation coefficient of the first attitude sensor at the thigh installation site to obtain a first target data set, where the first deformation coefficient characterizes the deformation ability of the soft tissue at the thigh installation site; Step S220: correcting the pitch motion angle and yaw motion angle of the calf according to the second deformation coefficient of the second attitude sensor at the calf installation site to obtain a second target data set, where the second deformation coefficient characterizes the deformation ability of the soft tissue at the calf installation site.

[0035] The first deformation coefficient is used to characterize the deformation ability of the soft tissue at the thigh installation site. For different individuals and different thigh parts, the deformation ability of their soft tissues is different. For example, for people who often do physical exercises, the muscles in the thigh part may be more developed, the toughness of the soft tissue is relatively good, and the deformation coefficient may be smaller; while for some people who lack exercise, the soft tissue in the thigh part may be relatively loose, and the deformation coefficient may be larger. Through the research and analysis of a large number of samples, the deformation coefficient of the soft tissue at the thigh installation site of a specific individual can be determined.

[0036] The second deformation coefficient is used to characterize the deformation ability of the soft tissue at the calf installation site. Similar to the thigh, the deformation ability of the soft tissue at the calf installation site is also affected by individual factors, exercise habits, etc. For example, for people who often run, the muscles in the calf part may be more firm, and the deformation coefficient of the soft tissue may be smaller; while for people who sit for a long time, the soft tissue in the calf part may be relatively soft, and the deformation coefficient may be larger. Through research and analysis, the deformation coefficient of the soft tissue at the calf installation site of a specific individual is determined.

[0037] It can be understood that for the first posture sensor installed at the same part of the thigh, the first deformation coefficient corresponding to the pitch motion and the first deformation coefficient corresponding to the yaw motion may be the same or different. When the mechanical properties of the soft tissue around the part where the first posture sensor is installed on the thigh are relatively uniform in all directions, the first deformation coefficients of the pitch motion and the yaw motion may be the same. For example, in the middle and outer areas of the thighs of some individuals, the muscle distribution is relatively uniform, and there is no obvious directional difference. In this case, whether it is a pitch motion (swinging the thigh forward and backward) or a yaw motion (rotating the thigh left and right), the degree and manner of deformation of the soft tissue may be similar. Therefore, the first deformation coefficient used to describe the deformation capacity of the soft tissue under these two movements can be set to the same value. Similarly, for the second posture sensor installed at the same part of the calf, the second deformation coefficient corresponding to the pitch motion and the second deformation coefficient corresponding to the yaw motion may be the same or different. It can be determined specifically according to individual differences.

[0038] In one embodiment, to improve the accuracy of data correction, the step S210: correcting the pitch motion angle and the yaw motion angle of the thigh according to the first deformation coefficient of the first posture sensor at the thigh installation position to obtain the first target data set includes: A thigh soft tissue deformation correction model is constructed according to the first deformation coefficient. The correction model is based on the mechanical properties of human soft tissue and uses the first deformation coefficient as a key parameter to describe the deformation law of the soft tissue at the thigh installation site under different movement angles. The initial measurement data is input into the thigh soft tissue deformation correction model, and the pitch motion angle measurement value and the yaw motion angle measurement value in the initial measurement data are corrected and calculated using the correction model to obtain the corrected pitch motion angle and yaw motion angle; The corrected pitch motion angle and yaw motion angle are integrated to form a first target data set containing corrected motion angle information.

[0039] Specifically, human soft tissue has unique mechanical properties, such as elasticity and viscoelasticity, which determine that it will deform when subjected to force. In this embodiment, a thigh soft tissue deformation correction model is constructed based on the mechanical properties of human soft tissue, and the first deformation coefficient k1 is introduced into the model as a key parameter. The first deformation coefficient k1 is a quantitative indicator of the soft tissue deformation ability of the thigh installation part, which comprehensively considers the structure of the soft tissue (such as the direction of muscle fibers, the distribution of fascia, etc.), material properties (such as elastic modulus, Poisson's ratio, etc.) and individual differences (such as age, gender, exercise habits, etc.) and other factors. Through a large number of experimental studies and data analysis, the first deformation coefficient k1 of different individuals and different thigh parts can be determined.

[0040] The core function of the calibration model is to describe the deformation law of the soft tissue at the thigh mounting position under different movement angles. When the knee joint performs pitching or yawing movements, the thigh soft tissue will be subjected to corresponding forces and torques, resulting in deformation. The calibration model can predict the deformation of the soft tissue based on the input movement angle (such as the pitching movement angle θ 1m ) measured initially and the first deformation coefficient k1, providing a basis for subsequent calibration of the measurement data.

[0041] Assume that the thigh pitching movement angle measured by the first attitude sensor is θ 1m , and the first deformation coefficient is k1. The calibrated thigh pitching movement angle θ 1t can be calculated through the pre-constructed calibration model θ 1t = θ 1m −k1×f(θ 1m ). Here, f(θ 1m ) is a function related to θ 1m , which is used to more accurately describe the influence of soft tissue deformation on the measured angle.

[0042] For the yaw movement angle of the thigh, a similar method is also used for calibration. Assume that the thigh yaw movement angle measured by the first attitude sensor is θ 2m , and similarly, according to the first deformation coefficient k1 (in the yaw movement calibration, the mechanism of the first deformation coefficient is similar, but the specific value may vary due to different movement directions. Here, for simplicity of description, it is still denoted as k1) and the corresponding function f(θ 2m ), the calibrated yaw movement angle θ 2t is calculated.

[0043] Integrating the calibrated pitching movement angle θ 1t and the yaw movement angle θ 2t can form a first target data set containing the calibrated movement angle information. This data set reflects the movement state of the thigh during actual movement in a more accurate way.

[0044] It can be understood that when the elasticity of the thigh sensor mounting position is greater, the displacement amount of the elastic displacement of the sensor is also greater, and the gap between the actual sensed angle value of the sensor and the actual movement angle value of the thigh is also greater. Therefore, subtracting the calibration value from the actual sensed angle value of the sensor can obtain the actual movement angle value of the thigh.

[0045] In other embodiments, according to the second deformation coefficient of the second attitude sensor at the calf mounting position, the pitching movement angle and yaw movement angle of the calf are calibrated to obtain a second target data set. The calibration principle is similar to the above, and will not be elaborated here.

[0046] Step S300: Determine the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; In one embodiment, step S300: determining the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set includes: Step S310: Obtain the real-time pitch motion angle of the first joint body relative to the second joint body according to the real-time pitch motion angle of the first joint body, the real-time pitch motion angle of the second joint body, and the pitch transformation relationship, where the pitch transformation relationship is the pitch motion coordinate transformation between the first joint body coordinate and the second joint body coordinate; Step S320: Obtain the real-time yaw motion angle of the first joint body relative to the second joint body according to the real-time yaw motion angle of the first joint body, the real-time yaw motion angle of the second joint body, and the yaw transformation relationship, where the yaw transformation relationship is the yaw motion coordinate transformation between the first joint body coordinate and the second joint body coordinate.

[0047] It can be understood that the first target data set contains the real-time pitch motion angle of the first joint body (such as the thigh) after correction, and the second target data set contains the real-time pitch motion angle of the second joint body (such as the calf) after correction. These data are accurate data after being corrected in step S200 and can more truly reflect the actual motion of the joint body.

[0048] The pitch transformation relationship describes the pitch motion coordinate transformation between the first joint body coordinate and the second joint body coordinate. In a three-dimensional space, the motion of the joint body can be represented by a coordinate system, and different joint bodies have their own coordinate systems. The pitch motion refers to the up-and-down motion of the joint body around the horizontal axis, and the pitch transformation relationship takes into account the relative position and angle change of the two joint bodies in the pitch motion direction. For example, in the knee joint motion, the pitch motions of the thigh and the calf are interrelated. By establishing the coordinate transformation relationship between them, the pitch motion angles of the thigh and the calf can be converted to the relative angles.

[0049] Based on this, according to the real-time pitch motion angle of the first joint body, the real-time pitch motion angle of the second joint body, and the pitch transformation relationship, the real-time pitch motion angle of the first joint body relative to the second joint body can be obtained through a specific calculation formula.

[0050] Similarly, the first target data set and the second target data set respectively provide the real-time yaw motion angles of the first joint body and the second joint body after correction. The yaw motion refers to the left-and-right rotation of the joint body around the vertical axis, and these data are the basis for calculating the relative yaw motion angle.

[0051] The yaw transformation relationship describes the coordinate transformation of the yaw motion between the first joint body coordinates and the second joint body coordinates. Similar to the pitch transformation relationship, it takes into account the relative position and angular change of the two joint bodies in the yaw motion direction. In knee joint movement, there is also an interrelationship between the yaw motions of the thigh and the calf. By establishing the yaw transformation relationship, the yaw motion angles of each of them can be converted to relative angles.

[0052] Based on this, according to the real-time yaw motion angle of the first joint body, the real-time yaw motion angle of the second joint body, and the yaw transformation relationship, the corresponding calculation formula can be used to obtain the real-time yaw motion angle of the first joint body relative to the second joint body.

[0053] It should be noted that the transformation between the two joint body coordinate systems can be described by Euler angles. The description method of Euler angles and the principle of coordinate system transformation are prior arts and not the improved part of this application, so the specific transformation process will not be described in detail here.

[0054] Step S400: Construct a time-sequence simulated joint motion diagram according to the real-time motion angle of the first joint body relative to the second joint body; In one embodiment, the step S400: Constructing a time-sequence simulated joint motion diagram according to the real-time motion angle of the first joint body relative to the second joint body includes: Sequentially obtain the real-time motion angle data of the first joint body relative to the second joint body in chronological order; According to a preset joint model, map the real-time motion angle data of each time point to the corresponding position of the joint model, and the joint model is a three-dimensional model simulating the connection relationship between the first joint body and the second joint body; Combine the joint model states of each mapped time point in chronological order to form a time-sequence simulated joint motion diagram that can dynamically display the motion process of the first joint body relative to the second joint body.

[0055] The real-time motion angle data is the real-time motion angle of the first joint body relative to the second joint body calculated in step S300 (which can be the pitch motion angle or the yaw motion angle or the roll motion angle). These data are sequentially obtained in chronological order and record the motion states of the joint at different times.

[0056] The preset joint model is a three-dimensional model simulating the connection relationship between the first joint body and the second joint body. This model accurately describes the geometric structure, motion range, and connection method of the joint, providing a basis for the mapping of real-time motion angle data.

[0057] Map the real-time motion angle data at each time point to the corresponding positions of the joint model. Specifically, according to the real-time motion angle data, adjust the position and orientation of the first joint body relative to the second joint body in the joint model to match the actual motion situation. For example, if the real-time motion angle data shows that the joint is at a specific pitch and yaw angle at a certain moment, then adjust the first joint body to the corresponding angular position in the joint model.

[0058] Combine the joint model states at each mapped time point in chronological order. The joint model state at each time point represents the motion posture of the joint at that moment. By arranging these states in sequence, a continuous motion sequence can be formed.

[0059] Using animation technology, convert the combined joint model state sequence into a dynamic time-sequential simulated joint animation. This animation can visually display the dynamic changes of the first joint body relative to the second joint body during the motion process, including actions such as rotation and flexion / extension of the joint.

[0060] The time-sequential simulated joint animation provides an intuitive visualization analysis method, enabling doctors and researchers to more clearly observe the motion process of the joint and discover potential motion abnormalities or lesions. By observing the animation, doctors can more accurately judge the type and degree of joint diseases, providing a basis for formulating treatment plans. In rehabilitation therapy, the time-sequential simulated joint animation can be used to evaluate the rehabilitation effect of patients, observe the recovery of joint motion function, and timely adjust the rehabilitation plan.

[0061] Step S500: Generate a warning signal according to the time-sequential simulated joint animation or the real-time motion angle of the joint. The warning signal is used to remind the user to adjust the motion mode or stop the motion.

[0062] This application can issue a warning through the real-time motion angle of the joint. For example, when there is a serious deviation between the angle and the threshold during joint movement, it indicates that the joint movement may be in an abnormal state, and a warning will be triggered at this time. For example, during knee joint movement, if the real-time pitch or yaw motion angle of the thigh relative to the calf exceeds the normal range, it may mean that the joint is under excessive stress or there is a risk of sports injury, and the system will issue a warning in a timely manner.

[0063] It can be understood that the time-series simulated joint motion diagram can fully present the dynamic changes of the joint during the entire movement process. Compared with simply relying on the real-time movement angle of the joint, the motion diagram contains more abundant information, such as the position, posture, and movement trajectory of the joint at different moments. For example, in the flexion and extension movement of the knee joint, the motion diagram can clearly show the entire process from the starting position to the maximum flexion and extension angle and then back to the starting position, while the real-time movement angle may only provide the angle value at a certain moment. By observing and analyzing the entire movement process, the system can more accurately identify abnormal patterns in joint movement, such as unsmooth movement and abnormal postures, thereby improving the accuracy of early warning. Based on this, this application can also issue an early warning according to the time-series simulated joint motion diagram.

[0064] In one embodiment, the step S500: generating an early warning signal according to the time-series simulated joint motion diagram or the real-time movement angle of the joint includes: inputting the time-series simulated joint motion diagram into a risk identification model to obtain a risk coefficient characterization value; generating early warning signals of different levels according to the risk coefficient characterization value; wherein, when the risk coefficient characterization value is greater than or equal to the first threshold, the user is reminded to stop the movement by voice; when the risk coefficient characterization value is greater than or equal to the second threshold and less than the first threshold, the user is reminded to adjust the movement mode by vibration.

[0065] Specifically, first, the time-series simulated joint motion diagram is input into a pre-trained risk identification model. This model is trained based on a large amount of normal and abnormal joint movement motion diagram data. It can automatically extract the feature information in the motion diagram through technologies such as deep learning and judge the risk degree of joint movement according to these features. The model will output a risk coefficient characterization value, which reflects the likelihood of abnormal joint movement. According to the size of the risk coefficient characterization value, the system will generate early warning signals of different levels.

[0066] When the risk coefficient characterization value is greater than or equal to the first threshold, it indicates that there is a high risk in joint movement, which may cause serious injuries. At this time, the system will remind the user to stop the movement by voice. The voice reminder has the characteristics of directness and clarity, which can ensure that the user receives the early warning information in time and takes corresponding actions. For example, the system can issue a voice prompt such as "Please note that there is a high risk in your joint movement. Please stop the movement immediately."

[0067] When the risk coefficient characterization value is greater than or equal to the second threshold and less than the first threshold, it indicates that although there is a certain risk in joint movement, it has not reached the level where movement needs to be stopped immediately. The system will remind the user to adjust the movement mode by vibration to reduce the risk. The vibration reminder can attract the user's attention without disturbing the user's normal movement. At the same time, the system can also combine simple beep sounds to enhance the reminder effect. For example, the device emits vibration and is accompanied by a beep sound of "Please adjust the movement mode to avoid excessive movement".

[0068] Under other necessary conditions, an early warning signal can also be sent to the user or supervisor through the APP push method.

[0069] In one embodiment, obtaining the risk coefficient characterization value by inputting the time-sequential simulated joint motion graph into the risk recognition model includes: extracting features from the time-sequential simulated joint motion graph to obtain a joint motion feature vector, where the joint motion feature vector includes at least two of joint motion angle feature, joint motion speed feature, joint motion acceleration feature, and joint motion trajectory feature; inputting the joint motion feature vector into a pre-trained risk recognition model, where the risk recognition model is constructed based on a deep learning algorithm; the risk recognition model calculates according to the input joint motion feature vector and outputs a risk coefficient characterization value, and the risk coefficient characterization value reflects the likelihood of risk existing in the current joint motion state.

[0070] Specifically, computer vision and image processing technologies can be used to analyze and process the time-sequential simulated joint motion graph. For example, by methods such as edge detection and feature point tracking, the position information of the joint is extracted, and then features such as angle, speed, and acceleration are calculated.

[0071] A risk recognition model is constructed using deep learning algorithms, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs) and their variants (such as LSTMs, GRUs), etc. These deep learning models have powerful feature learning and classification capabilities and can automatically learn the complex relationship between joint motion features and risks from a large amount of training data. The model is trained using a large amount of labeled normal and abnormal joint motion data. During the training process, the model continuously adjusts its own parameters so that after inputting the joint motion feature vector, the output risk coefficient characterization value can accurately reflect the likelihood of risk existing in the joint motion state. The extracted joint motion feature vector is input into the pre-trained risk recognition model. The model calculates according to the input feature vector and outputs a risk coefficient characterization value. This value is a continuous numerical value, and its range can be set according to the specific application scenario. For example, between 0 and 1, and the larger the value, the higher the likelihood of risk existing in the joint motion state.

[0072] Exemplarily, in the scenario of monitoring the movement state of the knee joint. First, feature extraction is performed on the time-series simulated knee joint movement images to obtain feature vectors including features such as the flexion and extension angle, movement speed, acceleration, and movement trajectory of the knee joint. Then, these feature vectors are input into a pre-trained risk recognition model based on LSTM. After calculation by the model, a risk coefficient characterization value is output, such as 0.7 (assuming the risk coefficient range is 0 - 1). If the set first threshold is 0.8 and the second threshold is 0.5, since the risk coefficient characterization value is greater than the second threshold but less than the first threshold, the system will issue a vibration reminder at this time to prompt the user to adjust the movement mode.

[0073] This application can also store information such as the monitored angle data, simulation analysis results, and warning records to establish a personal joint movement health database. Using data analysis technology, personalized exercise suggestions and rehabilitation plans are provided for users to help them better protect their joints.

[0074] Based on this, a closed-loop monitoring and intelligent warning method based on a posture sensor provided by an embodiment of this application first obtains the real-time monitoring data of the first posture sensor and the second posture sensor to obtain a first initial data set and a second initial data set; then corrects the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation part to obtain a first target data set and a second target data set; then determines the real-time movement angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; then constructs a time-series simulated joint movement image according to the real-time movement angle of the first joint body relative to the second joint body; and finally generates a warning signal according to the time-series simulated joint movement image or the real-time movement angle of the joint to remind the user to adjust the movement mode or stop the movement. In this way, the technical solution of this application can effectively reduce the measurement error caused by the deformation of the soft tissues around the joint, improve the accuracy of joint movement monitoring, and can present the joint movement process in real time, dynamically and intuitively, detect abnormal movement states in time and issue warnings, effectively preventing sports injuries and improving the safety and rationality of sports.

[0075] As Figure 5 shown, Figure 5 is a schematic hardware structure diagram of a closed-loop monitoring and intelligent warning system in some embodiments of this application. The closed-loop monitoring and intelligent warning system provided by an embodiment of this application further includes a memory 1000 and a processor 2000. Among them, the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the closed-loop monitoring and intelligent warning method based on a posture sensor as described above.

[0076] Among them, the processor 2000 is used to provide computing and control capabilities to control the closed-loop monitoring and intelligent warning system to perform corresponding tasks. For example, it controls the closed-loop monitoring and intelligent warning system to execute the closed-loop monitoring and intelligent warning method based on the attitude sensor in any of the above method embodiments. The method includes: respectively obtaining the real-time monitoring data of the first attitude sensor and the second attitude sensor to obtain a first initial data set and a second initial data set. The first initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of the first joint body. The second initial data set includes at least one of the pitch motion data, yaw motion data, and roll motion data of the second joint body; performing data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation site to obtain a first target data set and a second target data set; determining the real-time motion angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; constructing a time-sequence simulated joint motion diagram according to the real-time motion angle of the first joint body relative to the second joint body; generating a warning signal according to the time-sequence simulated joint motion diagram or the real-time motion angle of the joint. The warning signal is used to remind the user to adjust the motion mode or stop the motion.

[0077] The processor 2000 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0078] The memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions / modules corresponding to the closed-loop monitoring and intelligent warning method based on an attitude sensor in the embodiments of the present application. By running the non-transitory software programs, instructions, and modules stored in the memory 1000, the processor 2000 can implement the closed-loop monitoring and intelligent warning method based on an attitude sensor in any of the above method embodiments.

[0079] Specifically, the memory 1000 may include a volatile memory (VM), such as a random access memory (RAM); the memory 1000 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), or other non-transitory solid-state storage devices; the memory 1000 may further include a combination of the above types of memories.

[0080] In summary, the closed-loop monitoring and intelligent warning system of the present application adopts the technical solution of any one of the above embodiments of the closed-loop monitoring and intelligent warning method based on an attitude sensor. Therefore, it has at least the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated here one by one.

[0081] The embodiments of the present application also provide a computer-readable storage medium, such as a memory including program code, and the above program code can be executed by a processor to complete the closed-loop monitoring and intelligent warning method based on an attitude sensor in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0082] The embodiments of the present application also provide a computer program product, which includes one or more pieces of program code, and the program code is stored in a computer-readable storage medium. The processor of the warning system reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the closed-loop monitoring and intelligent warning method based on an attitude sensor provided in the above embodiments.

[0083] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by hardware related to program code. The program can be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disk, or the like.

[0084] It should be noted that the device embodiments described above are merely illustrative. 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 may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0086] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural transformation made by using the description and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields is included in the patent protection scope of the present invention.

Claims

1. A closed-loop monitoring and intelligent early warning method based on an attitude sensor, characterized in that, Applied to the monitoring and early warning of joint movement, the method includes: Obtaining the real-time monitoring data of the first attitude sensor and the second attitude sensor respectively to obtain a first initial data set and a second initial data set. The first initial data set includes at least one of the pitch movement data, yaw movement data, and roll movement data of the first joint body, and the second initial data set includes at least one of the pitch movement data, yaw movement data, and roll movement data of the second joint body; Performing data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation part to obtain a first target data set and a second target data set; Determining the real-time movement angle of the first joint body relative to the second joint body according to the first target data set and the second target data set; Constructing a time-series simulated joint movement graph according to the real-time movement angle of the first joint body relative to the second joint body; Generating an early warning signal according to the time-series simulated joint movement graph or the real-time movement angle of the joint, and the early warning signal is used to remind the user to adjust the movement mode or stop the movement.

2. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 1, characterized in that The movement data includes one or more of acceleration, displacement, angle, or movement trajectory.

3. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 2, wherein The joint is a knee joint. The first initial data set includes the pitch movement angle and yaw movement angle of the thigh, and the second initial data set includes the pitch movement angle and yaw movement angle of the calf; The performing data correction on the first initial data set and the second initial data set according to the deformation characteristics of the sensor installation part to obtain a first target data set and a second target data set includes: Correcting the pitch movement angle and yaw movement angle of the thigh according to the first deformation coefficient of the first attitude sensor at the thigh installation part to obtain a first target data set, and the first deformation coefficient represents the deformation ability of the soft tissue at the thigh installation part; Correcting the pitch movement angle and yaw movement angle of the calf according to the second deformation coefficient of the second attitude sensor at the calf installation part to obtain a second target data set, and the second deformation coefficient represents the deformation ability of the soft tissue at the calf installation part.

4. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 3, characterized in that, The correcting the pitch movement angle and yaw movement angle of the thigh according to the first deformation coefficient of the first attitude sensor at the thigh installation part to obtain a first target data set includes: Constructing a thigh soft tissue deformation correction model according to the first deformation coefficient. The correction model is based on the mechanical characteristics of human soft tissue, uses the first deformation coefficient as a key parameter, and is used to describe the deformation law of the soft tissue at the thigh installation part under different movement angles; Inputting the initial measurement data into the thigh soft tissue deformation correction model, and using the correction model to perform correction calculations on the pitch movement angle measurement value and yaw movement angle measurement value in the initial measurement data to obtain the corrected pitch movement angle and yaw movement angle; Integrating the corrected pitch movement angle and yaw movement angle to form a first target data set including corrected movement angle information.

5. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 1, wherein Determining the real-time movement angle of the first joint body relative to the second joint body according to the first target data set and the second target data set includes: Obtain the real-time pitch motion angle of the first joint body relative to the second joint body based on the real-time pitch motion angle of the first joint body, the real-time pitch motion angle of the second joint body, and the pitch transformation relationship, where the pitch transformation relationship is the pitch motion coordinate transformation between the coordinates of the first joint body and the coordinates of the second joint body; Obtain the real-time yaw motion angle of the first joint body relative to the second joint body based on the real-time yaw motion angle of the first joint body, the real-time yaw motion angle of the second joint body, and the yaw transformation relationship, where the yaw transformation relationship is the yaw motion coordinate transformation between the coordinates of the first joint body and the coordinates of the second joint body.

6. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 1, characterized in that Constructing a sequential simulated joint animation diagram according to the real-time motion angle of the first joint body relative to the second joint body includes: Sequentially obtain the real-time motion angle data of the first joint body relative to the second joint body in chronological order; According to a preset joint model, map the real-time motion angle data of each time point to the corresponding position of the joint model, where the joint model is a three-dimensional model simulating the connection relationship between the first joint body and the second joint body; Combine the states of the joint models at each mapped time point in chronological order to form a sequential simulated joint animation diagram that can dynamically display the motion process of the first joint body relative to the second joint body.

7. The closed-loop monitoring and intelligent early warning method based on an attitude sensor according to claim 1, characterized in that, The warning signal includes one or more of a voice signal, a vibration signal, or an APP push signal.

8. The closed-loop monitoring and intelligent warning method based on an attitude sensor according to claim 7, wherein Generating a warning signal according to the sequential simulated joint animation diagram or the real-time motion angle of the joint includes: Input the sequential simulated joint animation diagram into a risk identification model to obtain a risk coefficient characterization value; Generate warning signals of different levels according to the risk coefficient characterization value; Among them, when the risk coefficient characterization value is greater than or equal to a first threshold, remind the user to stop the movement by voice; when the risk coefficient characterization value is greater than or equal to a second threshold and less than the first threshold, remind the user to adjust the movement mode by vibration.

9. The closed-loop monitoring and intelligent early warning method based on an attitude sensor according to claim 8, characterized in that, The step of inputting the sequential simulated joint animation diagram into a risk identification model to obtain a risk coefficient characterization value includes: Extract features from the sequential simulated joint animation diagram to obtain a joint motion feature vector, where the joint motion feature vector includes at least two of joint motion angle features, joint motion speed features, joint motion acceleration features, and joint motion trajectory features; Input the joint motion feature vector into a pre-trained risk identification model, where the risk identification model is constructed based on a deep learning algorithm; The risk identification model calculates according to the input joint motion feature vector and outputs a risk coefficient characterization value, and the risk coefficient characterization value reflects the magnitude of the possibility that the current joint motion state has a risk.

10. A closed-loop monitoring and intelligent early warning system, characterized in that, including: A first attitude sensor disposed on the first joint body; A second attitude sensor disposed on the second joint body, and the second joint body is rotatably connected to the first joint body to form a joint; and A memory and a processor, where the memory is used to store program code; The processor is used to call the program code to execute the method according to any one of claims 1 to 9.

Images