Posture correction training method and device applied to human intelligence manufacturing

Abstract

The invention provides a posture correction training method and device applied to human intelligence manufacturing. The method provided by the invention comprises the following steps: acquiring a target joint point coordinate, and inputting the target joint point coordinate into a human body digital model to obtain a corresponding relationship between the target joint point coordinate and a human body joint; the human body digital model is used for matching the target joint point coordinates with the real posture data of the human body; calculating according to the vector relationship of the target joint point coordinates to obtain an inter-joint included angle and a joint torsion angle of the target joint point coordinates; determining a target human body risk score based on the corresponding relation, the inter-joint included angle and the joint torsion angle; the target human body risk score comprises an expert evaluation score; when the target human body risk score exceeds a preset risk threshold value, sending a posture correction notification by adopting a composite message; wherein the composite message simultaneously gives out a prompt based on multiple senses. The posture correction training method and device applied to human-based intellectual manufacture are used for correcting the posture of the human body accurately and reliably.

Description

Technical Field

[0001] The present application relates to the technical field of posture correction, and in particular to a posture correction training method and device applied to human-oriented intelligent manufacturing. Background Art

[0002] Musculoskeletal diseases are a common health problem, including cervical spondylosis, lumbar disc herniation, arthritis, back pain, etc. These diseases are often related to poor posture and working environment. The operator's ability to identify and optimize poor posture is a key factor in reducing musculoskeletal diseases, which is usually acquired through implicit experience accumulated through long-term work or systematic training. Therefore, regardless of the operator's age, skill level, and experience, systematic posture correction training is of great significance to improve awareness of identifying and optimizing poor posture.

[0003] Traditional posture correction training is conducted under the guidance of coaches or physiotherapists, which is not only costly but also difficult to popularize. At the same time, since existing research has not detailed the quantification process of the baseline posture, there is no unified posture quantification standard. Furthermore, the technology of using wearable devices to detect posture defects and provide vibration feedback not only has a single feedback method, but also causes discomfort when worn for a long time, which cannot meet actual usage needs. Summary of the invention

[0004] In view of this, the present application provides a posture correction training method and device applied to human-oriented intelligent manufacturing, so as to accurately and reliably correct the posture of the human body.

[0005] Specifically, the present application is implemented through the following technical solutions: The first aspect of the present application provides a posture correction training method applied to human-oriented intelligent manufacturing, the method comprising: Acquire target joint point coordinates, input the target joint point coordinates into a human body digital model, and obtain a corresponding relationship between the target joint point coordinates and human body joints; the human body digital model is used to match the target joint point coordinates with real posture data of the human body; Calculating according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and the joint torsion angle of the target joint point coordinates; Determining a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the degree of error of the human body joint; the target human body risk score includes an expert evaluation score; When the target human body risk score exceeds a preset risk threshold, a composite message is used to issue a posture correction notification; wherein the composite message is based on multi-sensory simultaneous reminders.

[0006] A second aspect of the present application provides a posture correction training device, the device comprising an acquisition module, a calculation module, a determination module and a notification module; wherein: The acquisition module is used to acquire the target joint point coordinates, input the target joint point coordinates into the human body digital model, and obtain the corresponding relationship between the target joint point coordinates and the human body joints; the human body digital model is used to match the target joint point coordinates with the real posture data of the human body; The calculation module calculates according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and the joint torsion angle of the target joint point coordinates; The determination module determines a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the error degree of the human body joint; and the target human body risk score includes an expert evaluation score; The notification module is used to send a posture correction notification using a composite message when the target human body risk score exceeds a preset risk threshold; wherein the composite message sends reminders based on multiple senses at the same time.

[0007] The posture correction training method and device provided by the present application for human-oriented intelligent manufacturing first obtain the target joint point coordinates, input the target joint point coordinates into the human body digital model, obtain the corresponding relationship between the target joint point coordinates and the human body joints, and then calculate according to the vector relationship of the target joint point coordinates to obtain the joint angle and joint torsion angle of the target joint point coordinates, and then determine the target human body risk score based on the corresponding relationship, the joint angle and the joint torsion angle, and finally use a composite message to send a posture correction notification when the target human body risk score exceeds the preset risk threshold. In this way, through the human body digital model, each joint position and posture of the human body can be accurately captured and analyzed. Further, by calculating the joint angle and the joint torsion angle, it is possible to quantify whether the posture is wrong and the degree of error, and then determine the human body risk score in combination with the corresponding relationship, complete the judgment of the posture through the human body risk score, and remind when it exceeds the preset risk threshold, so as to ensure the accuracy and credibility of the correction training. Further, by reminding through a multi-sensory composite message reminder, it can attract attention more effectively, so that posture adjustments can be made in time, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A flowchart of Embodiment 1 of the posture correction training method for human-centered intelligent manufacturing provided by the present application; Figure 2 A flowchart of Embodiment 2 of the posture correction training method for human-centered intelligent manufacturing provided by the present application; Figure 3A hardware structure diagram of the posture correction training device in which the posture correction training device of the present application is located; Figure 4 This is a structural schematic diagram of Example 1 of the posture correction training device provided in this application. DETAILED DESCRIPTION

[0009] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0010] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0011] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0012] The present application provides a posture correction training method and device applied to human-centered intelligent manufacturing, which is used to accurately and reliably correct the posture of the human body.

[0013] The posture correction training method and device provided by the present application for human-oriented intelligent manufacturing first obtain the target joint point coordinates, input the target joint point coordinates into the human body digital model, obtain the corresponding relationship between the target joint point coordinates and the human body joints, and then calculate according to the vector relationship of the target joint point coordinates to obtain the joint angle and joint torsion angle of the target joint point coordinates, and then determine the target human body risk score based on the corresponding relationship, the joint angle and the joint torsion angle, and finally use a composite message to send a posture correction notification when the target human body risk score exceeds the preset risk threshold. In this way, through the human body digital model, each joint position and posture of the human body can be accurately captured and analyzed. Further, by calculating the joint angle and the joint torsion angle, it is possible to quantify whether the posture is wrong and the degree of error, and then determine the human body risk score in combination with the corresponding relationship, complete the judgment of the posture through the human body risk score, and remind when it exceeds the preset risk threshold, so as to ensure the accuracy and credibility of the correction training. Further, by reminding through a multi-sensory composite message reminder, it can attract attention more effectively, so that posture adjustments can be made in time, and the user experience is improved.

[0014] Specific embodiments are given below to introduce the technical solution of the present application in detail.

[0015] Figure 1 This is a flowchart of the first embodiment of the posture correction training method for human-centered intelligent manufacturing provided by this application. Please refer to Figure 1 , the method provided in this embodiment may include: S101, obtaining target joint point coordinates, inputting the target joint point coordinates into a human body digital model, and obtaining a corresponding relationship between the target joint point coordinates and human body joints; the human body digital model is used to match the target joint point coordinates with real posture data of the human body.

[0016] Specifically, the target joint point coordinates are the specific positions of each joint of the person being measured in three-dimensional space. The posture of the person being measured can be determined by the joints corresponding to the target joint point coordinates. In specific implementation, the camera device for shooting the target joint point coordinates can be selected according to actual needs. For example, an ordinary camera or a depth camera can be used to obtain the target joint point coordinates.

[0017] Furthermore, the collected time series data can be determined as the target joint point coordinates of the skeleton of the person being measured at a collection frequency of 30 frames.

[0018] Furthermore, the coordinate system corresponding to the target joint point coordinates is determined based on the direction of the person being measured. For example, in one embodiment, the three-axis directions are specified, and when the person being measured faces the camera, the front of the person is the positive X direction, the top is the positive Y direction, and the left side is the positive Z direction.

[0019] It should be noted that the specific types of joints included in the target joint point coordinates are set according to actual needs, and are not limited in this embodiment. For example, in one embodiment, the joints corresponding to the target joint point coordinates may include the head, neck, left shoulder, left elbow, left wrist, left palm, left thumb, left middle finger tip, right shoulder, right elbow, right wrist, right palm, right thumb, right middle finger tip, upper spine, middle spine, lower spine, left hip, left knee, left ankle, left foot, right hip, right knee, right ankle, and right foot.

[0020] A specific embodiment is given below to introduce the process of obtaining the target joint point in detail: (1) Collect depth image data of the person being measured.

[0021] Specifically, the depth image data refers to image data containing information about the distance from each pixel in the scene to the camera, and the depth image data can be obtained by a depth sensor or a laser radar. For example, in one embodiment, the depth image data of the operator is captured in real time by a binocular depth camera Kinect v2.

[0022] (2) Processing the depth image data based on a human skeleton point recognition algorithm to obtain the coordinates of the target joint points.

[0023] Specifically, the human skeleton point recognition algorithm can detect and identify the joints of the human body through the information in the image. It should be noted that the specific human skeleton point recognition algorithm can be determined according to actual needs, and this is not limited in this embodiment. For example, the OpenPose algorithm can be selected as the human skeleton point algorithm for processing depth image data. For another example, in another embodiment, the MediaPipe algorithm can be selected as the human skeleton point algorithm for processing depth image data.

[0024] The posture correction training method applied to human-centered intelligent manufacturing provided in this embodiment first collects the depth image data of the person being tested, and then processes the depth image data based on the human skeleton point recognition algorithm to obtain the target joint point coordinates. In this way, the target joint point coordinates of the person being tested can be accurately obtained and identified, thereby providing a reliable data basis for further posture correction.

[0025] Furthermore, the human body digital model is a three-dimensional virtual model generated by a computer. The joint points contained in the human body digital model can accurately represent the real posture data of the human body, which facilitates the calibration and configuration of the joints and bones of the human body.

[0026] In specific implementation, the target joint point coordinates are mapped to the human body digital model to obtain the corresponding relationship between each target joint point coordinate and the human body joint.

[0027] S102, calculating according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and the joint torsion angle of the target joint point coordinates.

[0028] Specifically, the inter-articular angle refers to the angle between two adjacent bone segments, and the inter-articular angle is determined by calculating the angle between the vectors of the two bone segments.

[0029] Furthermore, the joint torsion angle represents the amount of torsion or rotation around a joint, and the joint torsion angle is used to describe the rotation angle along the axis of a bone segment or joint.

[0030] In specific implementation, the three-dimensional coordinates of the joints can be obtained through the coordinates of the target joint points, and the corresponding joint angles and joint torsion angles are calculated through the coordinates. For example, in one embodiment, taking the joint angles of the shoulder, elbow, and wrist as an example, the vector v1 from the shoulder to the elbow and the vector v2 from the elbow to the wrist are calculated, and the joint angles θ of the shoulder, elbow, and wrist are obtained by calculation based on v1 and v2.

[0031] S103. Determine a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the degree of error of the human body joints; and the target human body risk score includes an expert evaluation score.

[0032] Specifically, the target human risk score is used to evaluate the correctness and potential health risks of the person being tested, and is used to assess the health status of the human body posture and joints. The target human risk score can provide a quantitative assessment of the degree of error in the human body joint posture. It should be noted that the larger the value of the target human risk score, the more serious the error in the human body joints.

[0033] In specific implementation, the target human body risk score can be obtained based on a traditional human body risk score assessment method, or based on a neural network human body risk score assessment method, which is not limited in this embodiment. For example, in one embodiment, a rapid whole body assessment method can be used to analyze and process the correspondence, the angle between joints, and the joint torsion angle based on computer vision and kinematics principles, so as to obtain the target human body risk score.

[0034] Furthermore, the target human body score also includes an expert evaluation score. For example, in one embodiment, after the target human body risk score is calculated, the expert can modify or confirm the target human body risk score according to the actual situation. For another example, in another embodiment, the expert determines the score according to the actual situation, and after a weighted operation, the target human body risk score is obtained together with the calculated score.

[0035] S104. When the target human body risk score exceeds a preset risk threshold, a composite message is used to issue a posture correction notification; wherein the composite message is based on multi-sensory simultaneous reminders.

[0036] Specifically, the preset risk threshold is determined based on medical data and is a health risk value used to determine whether there are any adverse problems with human posture. In other words, when the target human risk score exceeds the preset risk threshold, it means that the current posture poses a health risk and needs to be corrected.

[0037] In specific implementation, the specific value of the preset risk threshold is set according to actual needs, and this embodiment is not limited to this. For example, in one embodiment, the specific value of the preset risk threshold can be determined in combination with historical posture data in a medical database.

[0038] Furthermore, different human joints have different preset risk thresholds, which can be set according to the importance and health risks of different human joints in posture. For example, in one embodiment, the preset health risk thresholds are: 2 points for the neck, 3 points for the trunk, 2 points for the legs, 3 points for the upper arms, 2 points for the forearms, and 2 points for the wrists.

[0039] In this way, by setting different preset risk thresholds, the actual risk of each joint can be more accurately reflected, providing a more refined and personalized posture assessment, and improving the accuracy and reliability of the overall assessment.

[0040] In this step, when the human body risk score exceeds the preset risk threshold, a composite message is generated. The composite message is used to convey a message to the person being measured to remind the person of the posture problem. It should be noted that the composite message is based on the simultaneous reminder of multiple senses, and the specific multi-sensory reminder method can be selected according to actual needs, and this is not limited in this embodiment.

[0041] Optionally, the composite message includes at least a visual message, an auditory message and a tactile message.

[0042] Specifically, the visual message reminds the person being tested visually. When implemented specifically, for example, in one embodiment, different videos can be pre-recorded for different joints, and the person being tested can wear a mixed reality glasses device during training. When the target human body risk score of a joint exceeds a preset risk threshold, the corresponding video will be displayed in the mixed reality glasses device, so that the person being tested can receive real-time visual messages about adjusting posture and movements, thereby achieving a reminder function.

[0043] Furthermore, the auditory message reminds the person being tested through hearing. In specific implementation, for example, in one embodiment, different audios can be pre-recorded for different joints, and the person being tested wears a wireless headset device during training. When the human body risk score of a joint target exceeds a preset risk threshold, the corresponding audio is played on the wireless headset device, so that the person being tested receives the auditory message about adjusting posture and movement in real time, thereby achieving the reminder function.

[0044] Furthermore, the tactile message reminds the person being tested through touch. In the specific implementation, for example, in one embodiment, a tactile device including a single-chip microcomputer and a micro vibration motor is pre-set, and the tactile device is fixed to each joint by a strap. When the target human body risk score of a joint exceeds a preset risk threshold, the control signal of the tactile device is packaged on the upper computer side, transmitted to the single-chip microcomputer through serial port communication, and unpacked on the single-chip microcomputer side, and then the micro vibration motor of the corresponding joint is driven to vibrate, thereby achieving the reminder function.

[0045] Furthermore, one or more reminder methods may be used simultaneously to form a composite message to remind the person being tested.

[0046] The method provided in this embodiment uses a composite message based on a combination of visual, auditory, and tactile methods for reminders. It can be applied to various environments and scenarios and is not affected by the limitations of a single sensory feedback. At the same time, users can choose the reminder method that best suits them based on their personal preferences and usage environment, reducing the interference of a single reminder method on users and improving user experience and satisfaction.

[0047] Furthermore, the posture correction notification may include the specific part that needs to be corrected and the specific correction method. After the person being measured receives the posture correction notification, he or she may complete the posture correction according to the information in the posture correction notification.

[0048] The posture correction training method applied to human-oriented intelligent manufacturing provided by the present application first obtains the target joint point coordinates, inputs the target joint point coordinates into the human digital model, obtains the corresponding relationship between the target joint point coordinates and the human joints, and then calculates according to the vector relationship of the target joint point coordinates to obtain the joint angle and joint torsion angle of the target joint point coordinates, and then determines the target human risk score based on the corresponding relationship, the joint angle and the joint torsion angle, and finally, when the target human risk score exceeds the preset risk threshold, a composite message is used to issue a posture correction notification. In this way, through the human digital model, each joint position and posture of the human body can be accurately captured and analyzed. Further, by calculating the joint angle and the joint torsion angle, it is possible to quantify whether the posture is wrong and the degree of error, and then determine the human risk score in combination with the corresponding relationship, complete the judgment of the posture through the human risk score, and remind when it exceeds the preset risk threshold, so as to ensure the accuracy and credibility of the correction training. Further, by reminding through a multi-sensory composite message reminder, it can attract attention more effectively, so that posture adjustments can be made in time, and the user experience is improved.

[0049] Optionally, when the target human body risk score is less than a preset risk threshold, the method further includes: Return to the process of obtaining the target joint point coordinates, and recalculate the target human body risk score.

[0050] Specifically, when the target human body risk score is less than the preset risk threshold, it means that the current posture is within a safe range and no posture correction is required. At this time, return to the step of re-obtaining the joint point coordinates to continuously monitor the user's posture.

[0051] The method provided in this embodiment can continuously monitor and dynamically adjust by returning to reacquire the joint point coordinates and recalculate the risk score, thereby ensuring that the user always maintains a healthy posture, reducing unnecessary interference, and ensuring the reliability of posture correction.

[0052] Optionally, the method for constructing the human body digital model includes: (1) Obtain the standard joint point coordinates under the standard posture, and calculate the posture data of the standard joint point coordinates.

[0053] Specifically, the characterizing posture is a healthy and ideal posture for human body during training, and the standard posture can be determined through a medical database. It can be understood that the coordinates of the joint points under the standard posture are the standard joint point coordinates.

[0054] In this step, the posture data of each joint point is calculated based on the collected standard joint point coordinates. The posture data of each joint point can be represented by the angle between the joints and the joint torsion angle.

[0055] (2) Correcting the posture data, and constructing the human body digital model based on the corrected posture data.

[0056] Specifically, the posture data is corrected to eliminate measurement errors and noise to ensure the accuracy and reliability of the posture data. In specific implementation, after the posture data is corrected, it can be standardized to conform to a unified scale and format to facilitate subsequent model construction.

[0057] Optionally, the human body digital model is created and deployed on a Unity3D platform; and the correcting the posture data and constructing the human body digital model based on the corrected posture data includes: The posture data is represented by a sphere element, and the lines connecting the standard joint point coordinates are drawn by line renderer parameters.

[0058] Specifically, the human body digital model may include 25 joints to facilitate matching with the joint point posture data. The human body digital model is created and deployed on the Unity3D platform, and the lines between the joints are drawn by editing the LineRenderer parameters of the joints.

[0059] The method provided in this embodiment constructs a human digital model through posture data under standard postures, which can accurately analyze and monitor human postures. The constructed human digital model provides a solid foundation for posture correction and ensures the effect of posture correction training.

[0060] Figure 2 This is a flowchart of Embodiment 2 of the posture correction training method for human-centered intelligent manufacturing provided by this application. Figure 2 , the method provided in this embodiment may include: S201. Power on the depth camera, reminder device, and related devices.

[0061] In specific implementation, the specific models of the depth camera, reminder device and related devices can be selected according to actual needs, and this is not limited in this embodiment. For example, the depth camera, reminder device and related devices can be powered on after power connection, device startup, system initialization, device calibration and function testing.

[0062] It should be noted that the wireless transmission module can be responsible for the communication between various devices.

[0063] S202: Detect whether the depth camera captures the person being measured, and detect whether the reminder device and the related devices are successfully connected.

[0064] In a specific implementation, the depth image data can be analyzed through an image processing algorithm to identify and extract the human body contour and joint points. After the human body contour and joint points are extracted, it is determined that the person being measured is captured.

[0065] Furthermore, the test signal can be used to detect whether the reminder device responds as expected. For example, in one embodiment, it is determined whether the display displays a test image, whether the speaker plays a test audio, and whether the vibration device generates vibrations to determine whether the reminder device and related devices are connected successfully.

[0066] It should be noted that if the reminder device and related devices are not connected successfully, repeat the power-on process until the connection is successful.

[0067] S203. After the reminder device and the related devices are successfully connected, the target joint point coordinates are obtained, and the target joint point coordinates are input into the human body digital model to obtain the corresponding relationship between the target joint point coordinates and the human body joints; the human body digital model is used to match the target joint point coordinates with the real posture data of the human body.

[0068] In the specific implementation, the relevant explanation of this step can be found in the description of the previous embodiment, and will not be repeated here.

[0069] S204: Calculate the target distance between the coordinates of the corresponding target joint point pairs in the depth image data of two adjacent frames.

[0070] Specifically, the target joint point pair is two adjacent and connected nodes of the human body in a frame of image, and the straight-line distance between the two nodes is the target distance.

[0071] In a specific implementation, for example, in one embodiment, the depth images of two adjacent frames are the nth frame and the n-1th frame, respectively, and the target distance is calculated according to the coordinates of the target joint point pair: ; Among them, L n is the target distance in the nth frame, x n ,y n 、z n is the three-axis coordinate of a joint point in the target joint point pair, x n ´,y n ´, z n ' is the three-axis coordinate of another joint point in the target joint point pair.

[0072] S205 . Correct the coordinates of the target joint point pair in the depth image data when the target distance is not equal to a preset error value.

[0073] Specifically, the specific numerical value of the preset error value is set according to actual needs, and is not limited in this embodiment.

[0074] In specific implementation, when the target distance is greater than the preset error value, the relationship between the target distance and the preset error value can be determined based on the following formula: ; Among them, L n is the target distance of the nth frame, L n-1 is the target distance of the n-1th frame, and ξ is the preset error value.

[0075] Furthermore, when the target distance is greater than a preset error value, the coordinates of the target joint point pair in the depth image data are corrected based on the following formula: ; Among them A n is the corrected three-dimensional coordinate value of the joint point in the nth frame, A n-1 and A n-1-σ are the initial coordinate values ​​of the joint points in the n-1th frame and the n-1-σth frame respectively.

[0076] Furthermore, if the difference between the target distance of the nth frame and the target distance of the n-1th frame is less than the maximum allowable error value, the coordinate value of the joint point is modified to be equal to the initial coordinate value.

[0077] The method provided in this embodiment corrects the coordinates of the joint points based on the physiological and kinematic laws of the human body, that is, the distance between the joint points connected to the human joints will not change with the movement of the human body. This can eliminate measurement inaccuracies caused by noise, interference or equipment errors, thereby improving the accuracy of posture correction training.

[0078] S206. Calculate according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and the joint torsion angle of the target joint point coordinates.

[0079] In some embodiments, the corrected coordinate values ​​are used to calculate all joint vectors and joint angles included in the kinematic model of the nth frame, and the calculation formula is as follows: ; in, is the joint vector, , , is the corrected three-dimensional coordinate value of the child node, , , is the corrected three-dimensional coordinate value of the mother node, , , are the unit vectors of the x-axis, y-axis, and z-axis respectively; ; in, is the angle between joints, and Two joint vectors for calculating joint angles; The joint torsion angle calculation method includes: The rotation angle is calculated based on the quaternion of the two joint points. The calculation formula of the torsion angle is as follows: ; ; ; ; Among them, q, q´, Q, Q´ are the quaternions of the joint points; The rotation matrix is ​​calculated based on the following formula: ; Among them, Q and Q' are the quaternions of the joint points, and R is the rotation matrix; The rotation angle is calculated based on the following formula: ; Among them, q, q´, Q, Q´ are the quaternions of the joint points, R is the rotation matrix, and θ is the rotation angle.

[0080] It should be noted that the calculation process of calculating the torsion angles of other joints using the measured quaternion values ​​is the same as described above.

[0081] S207. Determine a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the degree of error of the human body joints; and the target human body risk score includes an expert evaluation score.

[0082] In the specific implementation, the relevant explanation of this step can be found in the description of the previous embodiment, and will not be repeated here.

[0083] S208. When the target human body risk score exceeds a preset risk threshold, a composite message is used to issue a posture correction notification; wherein the composite message is based on multiple senses to issue reminders simultaneously.

[0084] In the specific implementation, the relevant explanation of this step can be found in the description of the previous embodiment, and will not be repeated here.

[0085] S209, recording each of the composite messages, and obtaining a posture correction degree in each of the composite messages; wherein the posture correction degree represents a degree to which the composite message reminds the target human body of posture deviation.

[0086] Specifically, the posture correction degree can quantify the difference between a person's current posture and a standard posture. In specific implementation, the posture correction degree can be determined by the degree of posture adjustment required by the measured person in the composite message.

[0087] S210, calculating the posture improvement effect of the target human body by combining the number of the composite messages, the posture correction degree and related parameters.

[0088] Specifically, the number of composite messages can reflect the frequency of the user's posture deviation from the standard; the degree of posture correction can determine the user's posture training habits; and the posture improvement effect can be judged through relevant parameters such as timestamps to determine the effectiveness of this training.

[0089] The posture correction training method applied to human-oriented intelligent manufacturing provided in this application can accurately capture and analyze each joint position and posture of the human body through a digital model of the human body. Furthermore, by calculating the angle between joints and the torsion angle of the joints, it is possible to quantify whether the posture is wrong and the degree of error, and then determine the human risk score based on the corresponding relationship. The posture is judged by the human risk score, and a reminder is given when the preset risk threshold is exceeded. In this way, the accuracy and credibility of the correction training are guaranteed. Furthermore, reminders through multi-sensory composite message reminders can more effectively attract attention, thereby adjusting the posture in time and improving the user experience.

[0090] Corresponding to the aforementioned embodiment of a posture correction training method applied to human-oriented intelligent manufacturing, the present application also provides an embodiment of a posture correction training device.

[0091] The embodiment of a posture correction training device of the present application can be applied to a posture correction training device. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of the posture correction training device in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, if Figure 3 As shown, it is a hardware structure diagram of the posture correction training device of the present application, except Figure 3 In addition to the processor, memory, network interface, and non-volatile memory shown, the posture correction training device in the embodiment where the device is located may also include other hardware according to the actual function of the posture correction training device, which will not be described in detail.

[0092] Figure 4 This is a structural diagram of the first embodiment of the posture correction training device provided by this application. Figure 4The device provided in this embodiment includes an acquisition module 410, a calculation module 420, a determination module 430 and a notification module 440; wherein, The acquisition module 410 is used to acquire the target joint point coordinates, input the target joint point coordinates into the human body digital model, and obtain the corresponding relationship between the target joint point coordinates and the human body joints; the human body digital model is used to match the target joint point coordinates with the real posture data of the human body; The calculation module 420 is used to calculate according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and joint torsion angle of the target joint point coordinates; The determination module 430 is used to determine a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the error degree of the human body joint; and the target human body risk score includes an expert evaluation score; The notification module 440 is used to send a posture correction notification using a composite message when the target human body risk score exceeds a preset risk threshold; wherein the composite message sends a reminder based on multiple senses at the same time.

[0093] The device of this embodiment can be used to perform Figure 1 The steps, specific implementation principles and implementation processes of the method embodiment shown are similar and will not be repeated here.

[0094] Optionally, the acquisition module 410 is specifically used to collect depth image data of the person being measured; The acquisition module 410 is further specifically configured to process the depth image data based on a human skeleton point recognition algorithm to obtain the target joint point coordinates.

[0095] Optionally, the acquisition module 410 is further specifically used to power on the depth camera, the reminder device and related devices; The acquisition module 410 is further specifically used to detect whether the depth camera captures the measured person, and detect whether the reminder device and the related devices are successfully connected; The acquisition module 410 is further specifically configured to repeat the power-on process when the reminder device and the related device are not successfully connected.

[0096] Optionally, the determination module 430 is further configured to return to the process of obtaining the target joint point coordinates and recalculate the target human body risk score.

[0097] Optionally, the composite message includes at least a visual message, an auditory message and a tactile message.

[0098] Optionally, the acquisition module 410 is further specifically used to acquire standard joint point coordinates under a standard posture, and calculate the posture data of the standard joint point coordinates; The acquisition module 410 is further specifically used to correct the posture data and construct the human body digital model based on the corrected posture data.

[0099] Optionally, the notification module 440 is further used to record each of the composite messages and obtain the posture correction degree in each of the composite messages; wherein the posture correction degree represents the degree to which the composite message reminds the target human body of the deviation of the posture; The notification module 440 is further configured to calculate the posture improvement effect of the target human body by combining the number of the composite messages, the posture correction degree and related parameters.

[0100] Optionally, the acquisition module 410 is further specifically configured to calculate a target distance between coordinates of a pair of target joint points corresponding to two adjacent frames of the depth image data; The acquisition module 410 is further specifically configured to correct the coordinates of the target joint point pair in the depth image data when the target distance is not equal to a preset error value.

[0101] Optionally, the acquisition module 410 is further specifically configured to use a spherical element to represent the posture data, and to draw a line connecting the standard joint point coordinates through line renderer parameters.

[0102] Please continue to refer to Figure 3 The present application also provides a posture correction training device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0103] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of any one of the methods provided in the present application are implemented.

[0104] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0105] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0106] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A posture correction training method applied to human-oriented intelligent manufacturing, characterized in that: The method comprises: Acquire target joint point coordinates, input the target joint point coordinates into a human body digital model, and obtain a corresponding relationship between the target joint point coordinates and human body joints; the human body digital model is used to match the target joint point coordinates with real posture data of the human body; Calculating according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and the joint torsion angle of the target joint point coordinates; Determining a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the degree of error of the human body joint; the target human body risk score includes an expert evaluation score; When the target human body risk score exceeds a preset risk threshold, a composite message is used to issue a posture correction notification; wherein the composite message is based on multi-sensory simultaneous reminders.

2. The method according to claim 1, characterized in that The step of obtaining the target joint point coordinates includes: Collecting depth image data of the person being measured; The depth image data is processed based on a human skeleton point recognition algorithm to obtain the coordinates of the target joint points.

3. The method according to claim 2, characterized in that The method for calculating the angle between the joints includes: Use the corrected coordinate values ​​to calculate all joint vectors and joint angles contained in the kinematic model of the nth frame. The calculation formula is as follows: ； in, is the joint vector, , , is the corrected three-dimensional coordinate value of the child node, , , is the corrected three-dimensional coordinate value of the mother node, , , are the unit vectors of the x-axis, y-axis, and z-axis respectively; ； Among them, the is the angle between joints, and stated The two joint vectors for calculating the joint angle; The joint torsion angle calculation method comprises: The rotation angle is calculated based on the quaternion of the two joint points. The calculation formula of the torsion angle is as follows: ； ； ； ； Wherein, the q, the q´, the Q, and the Q´ are the quaternions of the joint points; The rotation matrix is ​​calculated based on the following formula: ； Wherein, the Q and Q´ are the quaternions of the joint points, and the R is the rotation matrix; The rotation angle is calculated based on the following formula: ； Among them, q, q´, Q, and Q´ are quaternions of the joint points, R is the rotation matrix, and θ is the rotation angle.

4. The method according to claim 1, characterized in that: When the target human body risk score is less than a preset risk threshold, the method further includes: Return to the process of obtaining the target joint point coordinates, and recalculate the target human body risk score.

5. The method according to claim 1, characterized in that: The composite message includes at least a visual message, an auditory message and a tactile message.

6. The method according to claim 1, characterized in that The method for constructing the human body digital model comprises: Obtaining standard joint point coordinates under a standard posture, and calculating posture data of the standard joint point coordinates; The posture data is corrected, and the human body digital model is constructed based on the corrected posture data.

7. The method according to claim 1, characterized in that After sending a posture correction notification using a composite message when the target human body risk score exceeds a preset risk threshold, the method further includes: Recording each of the composite messages, and obtaining a posture correction degree in each of the composite messages; wherein the posture correction degree represents a degree to which the composite message reminds the target human body of a posture deviation; The posture improvement effect of the target human body is calculated by combining the number of the composite messages, the posture correction degree and related parameters.

8. The method according to claim 2, characterized in that: After the depth image data is processed based on the human skeleton point recognition algorithm to obtain the coordinates of the target joint point, the method further includes: Calculate the target distance L of the coordinates of the corresponding target joint point pairs in the depth image data of two adjacent frames n ; ； Among them, L n is the target distance in the nth frame, x n ,y n 、z n is the three-axis coordinate of a joint point in the target joint point pair, x n ´,y n ´, z n ´ is the three-axis coordinate of another joint point in the target joint point pair; When the target distance is not equal to a preset error value, the coordinates of the target joint point pair in the depth image data are corrected.

9. The method according to claim 8, characterized in that The step of correcting the coordinates of the target joint point pair in the depth image data when the target distance is not equal to the preset error value includes: When the target distance is greater than the preset error value, the coordinates of the target joint point pair in the depth image data are corrected based on the following formula: ； Among them A n is the corrected three-dimensional coordinate value of the joint point in the nth frame, A n-1 and A n-1-σ are the initial coordinate values ​​of the joint points in the n-1th frame and the n-1-σth frame respectively; When the target distance difference is less than the maximum allowable error value, the coordinate value of the joint point is modified to be equal to the initial coordinate value.

10. A posture correction training device, characterized in that: The device includes an acquisition module, a calculation module, a determination module and a notification module; wherein, The acquisition module is used to acquire the target joint point coordinates, input the target joint point coordinates into the human body digital model, and obtain the corresponding relationship between the target joint point coordinates and the human body joints; the human body digital model is used to match the target joint point coordinates with the real posture data of the human body; The calculation module is used to calculate according to the vector relationship of the target joint point coordinates to obtain the inter-joint angle and joint torsion angle of the target joint point coordinates; The determination module is used to determine a target human body risk score based on the corresponding relationship, the angle between the joints and the joint torsion angle; wherein the target human body risk score represents the error degree of the human body joint; and the target human body risk score includes an expert evaluation score; The notification module is used to send a posture correction notification using a composite message when the target human body risk score exceeds a preset risk threshold; wherein the composite message sends reminders based on multiple senses at the same time.

Images