Rehabilitation training method, device and equipment based on intelligent machine horse and medium
Intelligent robotic horses solve the problems of high cost and space limitations in traditional equestrian rehabilitation training by constructing a pelvic kinematic model and a biomimetic rehabilitation gait, achieving personalized and efficient rehabilitation training results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU YUNSHENCHU TECH CO LTD
- Filing Date
- 2026-01-23
- Publication Date
- 2026-04-17
AI Technical Summary
Traditional equestrian rehabilitation training is costly and limited in space, making it difficult to accurately adjust training intensity and posture according to individual patient differences, resulting in poor rehabilitation outcomes.
Rehabilitation training is conducted using an intelligent robotic horse. By acquiring user physical condition data and rehabilitation goal data, a pelvic kinematic model is constructed, pelvic displacement parameters are calculated, a three-dimensional pelvic motion trajectory is generated, kinematic parameters are extracted, a bionic rehabilitation gait is determined, and the intelligent robotic horse is controlled for training.
Reduce training costs, remove venue restrictions, achieve personalized and precise rehabilitation training, and improve training suitability and effectiveness.
Smart Images
Figure CN121868085A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of this disclosure relate to the field of medical technology, and more specifically, to a rehabilitation training method, apparatus, device, and medium suitable for an intelligent robotic horse. Background Technology
[0002] Rehabilitation training can effectively help patients restore limb motor function, especially for patients with lower limb motor disorders. Through rehabilitation training, patients can be guided to carry out scientific and standardized gait training, which can promote the remodeling and recovery of neuromuscular function.
[0003] In related technologies, traditional equestrian rehabilitation methods are usually used for patients' limb rehabilitation training. The training process requires professional horse trainers and training horses, which is not only costly and limited by space, but also difficult to accurately adjust the training intensity and posture according to the individual differences of patients, resulting in poor rehabilitation training effects. Summary of the Invention
[0004] The embodiments described herein provide a rehabilitation training method, apparatus, device, and medium based on an intelligent robotic horse, overcoming the aforementioned problems.
[0005] Firstly, according to the content of this disclosure, a rehabilitation training method based on an intelligent robotic horse is provided, including: Acquire physical condition data and rehabilitation goal data of the users to be trained; Based on the physical condition data and rehabilitation target data of the user to be trained, a corresponding pelvic kinematic model is constructed. The displacement parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension, are calculated using the pelvic kinematic model. By using a preset time series model, dynamic trajectory points are generated for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension, and the dynamic trajectory points are connected in sequence to obtain the corresponding three-dimensional pelvic motion trajectory. Kinematic parameters are extracted from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension. The bionic rehabilitation gait of the intelligent robotic horse is determined by using an inverse kinematics algorithm based on the kinematic parameters and the body structure parameters of the intelligent robotic horse. The intelligent robotic horse is controlled to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user through the intelligent robotic horse.
[0006] Secondly, according to the present disclosure, a rehabilitation training device based on an intelligent robotic horse is provided, comprising: The acquisition module is used to acquire physical status data and rehabilitation goal data of the user to be trained. The construction module is used to construct a corresponding pelvic kinematic model based on the physical state data and rehabilitation target data of the user to be trained. The calculation module is used to calculate the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through the pelvic kinematic model. The generation module is used to generate dynamic trajectory points for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through a preset time series model, and to connect each of the dynamic trajectory points in sequence to obtain the corresponding three-dimensional pelvic motion trajectory. The extraction module is used to extract kinematic parameters from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension. The determination module is used to determine the bionic rehabilitation gait of the intelligent robotic horse based on the kinematic parameters and the body structure parameters of the intelligent robotic horse by using an inverse kinematics solution algorithm. The control module is used to control the intelligent robotic horse to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user to be trained through the intelligent robotic horse.
[0007] Thirdly, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the rehabilitation training method based on an intelligent robotic horse as described in any of the above embodiments.
[0008] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, and when executed by a processor, the computer program implements the steps of the rehabilitation training method based on an intelligent robotic horse as described in any of the above embodiments.
[0009] The rehabilitation training method based on an intelligent robotic horse provided in this application involves: acquiring the physical state data and rehabilitation goal data of the user to be trained; constructing a corresponding pelvic kinematic model based on the physical state data and rehabilitation goal data; calculating the displacement parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension using the pelvic kinematic model; generating dynamic trajectory points for the displacement parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension using a preset time series model, and sequentially connecting each dynamic trajectory point to obtain the corresponding three-dimensional pelvic motion trajectory; extracting kinematic parameters from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension; determining the corresponding bionic rehabilitation gait of the intelligent robotic horse based on the kinematic parameters and the body structure parameters of the intelligent robotic horse using an inverse kinematics algorithm; and controlling the intelligent robotic horse to move according to the bionic rehabilitation gait during the user's rehabilitation training process, thereby conducting rehabilitation training for the user using the intelligent robotic horse. Thus, biomimetic training using intelligent robotic horses eliminates the need for real horses, reducing training costs and freeing up training space. By combining the physical condition of the user to be trained with the abstract rehabilitation goals, the specific biomimetic rehabilitation gait of the intelligent robotic horse can be transformed. This allows for precise matching of the robotic horse gait to individual user differences, thereby effectively improving the suitability and effectiveness of rehabilitation training.
[0010] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description
[0011] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. It should be understood that the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure, wherein: Figure 1 This is a flowchart illustrating a rehabilitation training method based on an intelligent robotic horse, as disclosed in this publication.
[0012] Figure 2 This is a schematic diagram of the structure of a rehabilitation training device based on an intelligent robotic horse, as disclosed in this publication.
[0013] Figure 3 This is a schematic diagram of the structure of a computer device provided in this disclosure.
[0014] It should be noted that the elements in the attached diagram are schematic and not drawn to scale. Detailed Implementation
[0015] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are also within the scope of protection of this disclosure.
[0016] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject matter pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the specification and in the relevant art, and shall not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, the statement of “connecting” or “coupling” two or more parts together shall mean that these parts are directly joined together or joined through one or more intermediate components.
[0017] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0018] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists, A and B exist simultaneously, or B exists. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).
[0019] In the description of this application, unless otherwise stated, "multiple" means two or more (including two), and similarly, "multiple groups" means two or more (including two groups).
[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
[0021] Figure 1 This is a flowchart illustrating a rehabilitation training method based on an intelligent robotic horse, as provided in an embodiment of this disclosure. Figure 1As shown, the specific process of the rehabilitation training method based on intelligent robotic horses includes: S110. Obtain the physical condition data and rehabilitation goal data of the user to be trained; construct the corresponding pelvic kinematic model based on the physical condition data and rehabilitation goal data of the user to be trained.
[0022] The users to be trained can be individuals with rehabilitation training needs, such as children with cerebral palsy, spinal cord injury patients, stroke sequelae, and children with self-diagnosis / developmental delay. Physical status data may include: the user's height, weight, age, gender, affected limb, joint range of motion, muscle strength grade, muscle tone, balance function assessment results, walking ability rating, past medical history, current medication information, and whether there is cognitive impairment, pelvic-related parameters, or other comorbidities. Rehabilitation goal data can be the specific functional recovery indicators that the user expects to achieve through rehabilitation training. For example, for children with cerebral palsy, rehabilitation goals may include: improving muscle tone, symmetry, and sitting posture control; for spinal cord injury patients, rehabilitation goals may include: activating core muscle groups, preventing osteoporosis, and promoting intestinal motility; for stroke sequelae patients, rehabilitation goals may include: rebuilding balance reflexes and improving trunk stability; for children with self-diagnosis / developmental delay, rehabilitation goals may include: sensory integration training and emotion regulation.
[0023] Pelvic kinematic models can be used to simulate the three-dimensional motion trajectory, angle changes, and force conditions of the pelvis under different rehabilitation training movements for a user. Specifically, pelvic-related parameters (pelvic width, iliac crest distance, sacral tilt, etc.) in body condition data are standardized to eliminate model errors caused by individual physiological differences. Then, dynamic constraints are determined by combining the exercise intensity level, joint range of motion threshold, and training cycle determined by rehabilitation target data. By integrating biomechanical principles and deep learning algorithms, the standardized pelvic-related parameters and dynamic constraints are input into a neural network model for training, generating a personalized pelvic kinematic model that can reflect the user's pelvic motion characteristics in real time.
[0024] S120. Calculate the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension using the pelvic kinematic model.
[0025] The three-dimensional pelvic dimension can be a dimension in a three-dimensional rectangular coordinate system with the geometric center of the user's pelvis as the origin. The X-axis represents the direction of the human body's coronal axis (left-right direction), i.e., the coronal plane; the Y-axis represents the direction of the human body's sagittal axis (front-back direction), i.e., the sagittal plane; and the Z-axis represents the direction of the human body's vertical axis (up-down direction), i.e., the horizontal plane.
[0026] In some embodiments, the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension are calculated using a pelvic kinematic model. This includes: collecting real-time three-dimensional coordinate data of key pelvic landmarks of the user to be trained under specific actions; and performing coordinate transformation and matrix operations on the real-time three-dimensional coordinate data using the pelvic kinematic model to calculate the translational and rotational displacement parameters of the user's pelvic structure in the sagittal plane, the coronal plane, and the horizontal plane.
[0027] The translational displacement parameters in the coronal plane can include left and right translational distances along the X-axis, and the rotational displacement parameters can include the lateral tilt angles around the Y-axis (i.e., the left and right pelvic tilt angles). The translational displacement parameters in the sagittal plane can include anterior and posterior translational distances along the Y-axis, and the rotational displacement parameters can include the pitch angles around the X-axis (i.e., the anterior and posterior pelvic tilt angles). The translational displacement parameters in the horizontal plane can include vertical translational distances along the Z-axis, and the rotational displacement parameters can include the rotation angles around the Z-axis (i.e., the left and right pelvic rotation angles). Thus, the motion state of the pelvis in three-dimensional space can be comprehensively quantified through these displacement parameters.
[0028] S130. Using a preset time series model, dynamic trajectory points are generated for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension, and the dynamic trajectory points are connected in sequence to obtain the corresponding three-dimensional pelvic motion trajectory.
[0029] Among them, the three-dimensional pelvic motion trajectory is a continuous curve formed by connecting the dynamic trajectory points corresponding to the displacement parameters of the pelvic structure at different times in three-dimensional space in chronological order. It not only includes the translational and rotational motion information of the pelvis in the sagittal, coronal and horizontal planes, but also clearly presents the overall three-dimensional motion posture of the pelvis through the changes in coordinate values in the three-dimensional coordinate system.
[0030] In some embodiments, a preset time series model is used to generate dynamic trajectory points for the displacement parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension. These dynamic trajectory points are then connected sequentially to obtain the corresponding three-dimensional pelvic motion trajectory. This includes: serializing the translational and rotational displacement parameters of the pelvic structure of the user to be trained in the sagittal plane, the coronal plane, and the horizontal plane to obtain a time series dataset; inputting the time series dataset into the preset time series model to generate predicted displacement parameter values within a preset time step; using the predicted displacement parameter values as the coordinate data of the dynamic trajectory points; and sequentially mapping the actual displacement parameter values at historical moments and the predicted displacement parameter values within the preset time step to three-dimensional coordinates to obtain the corresponding three-dimensional pelvic motion trajectory.
[0031] The preset time series model, such as a Long Short-Term Memory (LSTM) network, learns from historical time series data to capture the nonlinear patterns and long-term dependencies of displacement parameters over time, thereby improving the accuracy of displacement parameter predictions. When mapping the actual values of displacement parameters at historical moments to the predicted values at future moments to three-dimensional coordinates, the translation and rotation parameters of the sagittal plane, the translation and rotation parameters of the coronal plane, and the translation and rotation parameters of the horizontal plane can correspond to the X-axis, Y-axis, and Z-axis coordinate components in the three-dimensional coordinate system, respectively. Through coordinate transformation and synthesis algorithms, the motion parameters of each plane are integrated into coordinate points in three-dimensional space, and then connected sequentially to form a continuous and smooth motion trajectory curve, i.e., the three-dimensional pelvic motion trajectory.
[0032] S140. Extract kinematic parameters from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension.
[0033] The kinematic parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension, may include, but are not limited to: pelvic anterior tilt angle, posterior tilt angle, the difference between the maximum anterior tilt angle and the maximum posterior tilt angle, the angular velocity of the anterior / posterior tilt movement, pelvic left tilt angle, right tilt angle, the difference between the maximum left tilt angle and the maximum right tilt angle, the angular velocity of the left / right tilt movement, pelvic left rotation angle, right rotation angle, the difference between the maximum left rotation angle and the maximum right rotation angle, and the angular velocity of the left / right rotation movement.
[0034] In some embodiments, kinematic parameters are extracted from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension. This includes: extracting the kinematic parameters corresponding to the sagittal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the sagittal plane include: pelvic anteversion angle, posterior tilt angle, the difference between the maximum anteversion angle and the maximum posterior tilt angle, and the angular velocity of the anteversion / posterior tilt motion; extracting the kinematic parameters corresponding to the coronal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the coronal plane include: pelvic left tilt angle, right tilt angle, the difference between the maximum left tilt angle and the maximum right tilt angle, and the angular velocity of the left tilt / right tilt motion; extracting the kinematic parameters corresponding to the horizontal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the horizontal plane include: pelvic left rotation angle, right rotation angle, the difference between the maximum left rotation angle and the maximum right rotation angle, and the angular velocity of the left rotation / right rotation motion.
[0035] Specifically, by analyzing the projection curve of the three-dimensional pelvic motion trajectory onto the sagittal plane, the angular changes of the pelvis during rotation around the coronal axis (Y-axis) can be identified, thus determining the anterior and posterior tilt angles at each moment. The maximum anterior and posterior tilt angles are then obtained by comparing the anterior / posterior tilt angles at different moments. The angular velocity of the anterior / posterior tilt movement is calculated based on the ratio of the angular change to the time interval between adjacent moments. Similarly, by analyzing the projection curve of the three-dimensional pelvic motion trajectory onto the sagittal plane, the angular changes of the pelvis around the sagittal axis (X-axis) can be identified, determining the left and right tilt angles at each moment, thus obtaining the maximum left and right tilt angles. The angular velocity of the left / right tilt movement is then calculated based on the angular change and the time interval. Finally, by analyzing the projection curve of the three-dimensional pelvic motion trajectory onto the horizontal plane, the angular changes of the pelvis around the vertical axis (Z-axis) can be identified, determining the left and right rotation angles, obtaining the maximum left and right rotation angles. The angular velocity of the left / right rotation movement is then calculated based on the angular change and the time interval. This ensures that the extracted kinematic parameters accurately reflect the motion characteristics of the user's pelvis in various planes.
[0036] S150. Using an inverse kinematics algorithm, the bionic rehabilitation gait of the intelligent robotic horse is determined based on kinematic parameters and the body structure parameters of the intelligent robotic horse.
[0037] Among them, the bionic rehabilitation gait of the intelligent robotic horse can accurately match the pelvic movement characteristics of the user to be trained, providing precise movement guidance for rehabilitation training.
[0038] In some embodiments, the bionic rehabilitation gait corresponding to the intelligent robotic horse is determined based on kinematic parameters and the body structure parameters of the intelligent robotic horse using an inverse kinematics algorithm. This includes: using kinematic parameters as constraints for inverse kinematics; calculating the motion angles of each joint of the intelligent robotic horse at different times using an inverse kinematics algorithm based on the body structure parameters of the intelligent robotic horse; and combining the motion angles of each joint of the intelligent robotic horse at different times into a coherent motion sequence to obtain the bionic rehabilitation gait corresponding to the intelligent robotic horse.
[0039] The structural parameters of the intelligent robotic horse include the length of each limb, the range of motion of the joints, and the connection relationships between the links. By using kinematic parameters as constraints, the solved bionic rehabilitation gait can closely match the actual pelvic movement of the user being trained, thereby achieving precise guidance and effective assistance for the user's movement during rehabilitation training.
[0040] The intelligent robotic horse in this embodiment features a 16-DOF (4×4) high-torque servo motor drive architecture, supporting force-position hybrid control; a maximum load ≥80kg; a slow gait frequency of 1.5-2.5Hz (adjustable); and vertical / lateral amplitude of 2–5cm (programmable). It boasts an IP54 protection rating, full body rounded corners, and an emergency stop button (physical + voice dual trigger). The back has pre-installed CAN / USB / power supply contacts, supporting plug-and-play use of saddles and accessories. Furthermore, it is equipped with an intelligent saddle system, including a torso support frame: adjustable height side armrests + chest safety belt (five-point restraint); an anti-pressure sore seat cushion: zoned gel + breathable mesh fabric, with built-in pressure distribution monitoring; a physiological signal interface: reserved ports for sEMG, heart rate, and breathing belt connections; and a center of gravity feedback mechanism: transmitting patient offset data to the main controller in real time to trigger gait compensation.
[0041] S160. Control the intelligent robotic horse to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user to be trained through the intelligent robotic horse.
[0042] The intelligent robotic horse can be controlled to move in a biomimetic rehabilitation gait using a 16-DOF (4×4) high-torque servo motor drive architecture. This allows for precise control of the movement trajectory and force of each joint according to the requirements of the biomimetic rehabilitation gait. With a maximum load capacity of ≥80kg, it can accommodate users of different weights. The slow walking frequency is adjustable from 1.5-2.5Hz, and the vertical / lateral amplitude is programmable from 2–5cm, ensuring the diversity and adaptability of the biomimetic rehabilitation gait and meeting the needs of different rehabilitation stages and training goals. Furthermore, the intelligent robotic horse has an IP54 protection rating, a rounded corner design throughout the body, and a dual physical and voice-triggered emergency stop button, providing comprehensive safety assurance during rehabilitation training.
[0043] In this embodiment, the body state data and rehabilitation goal data of the user to be trained are acquired; based on the body state data and rehabilitation goal data, a corresponding pelvic kinematic model is constructed; the displacement parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension are calculated using the pelvic kinematic model; dynamic trajectory points are generated for the displacement parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension using a preset time series model, and each dynamic trajectory point is connected sequentially to obtain the corresponding three-dimensional pelvic motion trajectory; kinematic parameters are extracted from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the user's pelvic structure corresponding to the three-dimensional pelvic dimension; the bionic rehabilitation gait corresponding to the intelligent robotic horse is determined based on the kinematic parameters and the body structure parameters of the intelligent robotic horse using an inverse kinematics algorithm; the intelligent robotic horse is controlled to move according to the bionic rehabilitation gait during the user's rehabilitation training process, so as to conduct rehabilitation training for the user through the intelligent robotic horse. Thus, biomimetic training using intelligent robotic horses eliminates the need for real horses, reducing training costs and freeing up training space. By combining the physical condition of the user to be trained with the abstract rehabilitation goals, the specific biomimetic rehabilitation gait of the intelligent robotic horse can be transformed. This allows for precise matching of the robotic horse gait to individual user differences, thereby effectively improving the suitability and effectiveness of rehabilitation training.
[0044] In some embodiments, the method further includes: matching the user with a corresponding rehabilitation assistive device based on the user's rehabilitation goal data; and issuing a device wearing prompt to the user during the user's rehabilitation training process to remind the user to wear the rehabilitation assistive device for rehabilitation training.
[0045] The intelligent robotic horse also features a smart carrier and accessory interface for connecting rehabilitation assistive devices such as eye-tracking screens, breathing trainers, and upper limb support arms. It employs a standardized magnetic and mechanical locking platform, automatically identifying accessory types and loading corresponding control strategies. If the user's rehabilitation goal is lower limb joint mobility recovery with balance impairment, a walking aid with gait correction and balance support functions can be prioritized. The device's model number, instructions, and compatibility parameters will be synchronized to the intelligent robotic horse's control system to achieve precise rehabilitation assistance during training.
[0046] In some embodiments, the method further includes: collecting limb response data of the user to be trained during the rehabilitation training process; and generating rehabilitation assessment results corresponding to the user to be trained based on the limb response data.
[0047] The limb response data includes the user's response to the biomimetic rehabilitation gait of the intelligent robotic horse during rehabilitation training. This data may include: joint angle data, electromyographic signal data, pressure distribution data, movement trajectory data, balance status data, and movement speed data. Joint angle data includes the flexion, extension, and rotation angles of the hip, knee, and ankle joints; electromyographic signal data reflects muscle activation and force application; pressure distribution data analyzes the dynamic changes in the user's center of gravity and the location of force application; movement trajectory data shows the displacement path of the user's limbs in three-dimensional space; balance status data includes the tilt angle, sway amplitude, and recovery time of the user's upper body; and movement speed data reflects the user's motor control ability and dynamic response to rehabilitation training.
[0048] Therefore, by collecting limb response data in real time, rehabilitation assessment results are generated for the user to be trained, which can clearly show the user's recovery progress in each rehabilitation dimension, the current functional impairment points, and subsequent training suggestions, thus serving as the basis or reference for the user's subsequent rehabilitation training.
[0049] Figure 2 This is a schematic diagram of a rehabilitation training device based on an intelligent robotic horse provided in this embodiment. The rehabilitation training device based on the intelligent robotic horse may include: The acquisition module 210 is used to acquire the physical status data and rehabilitation goal data of the user to be trained.
[0050] Module 220 is used to construct a corresponding pelvic kinematic model based on the physical condition data and rehabilitation goal data of the user to be trained.
[0051] The calculation module 230 is used to calculate the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through the pelvic kinematic model.
[0052] The generation module 240 is used to generate dynamic trajectory points for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through a preset time series model, and then connect each dynamic trajectory point in sequence to obtain the corresponding three-dimensional pelvic motion trajectory.
[0053] The extraction module 250 is used to extract kinematic parameters from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension.
[0054] The determination module 260 is used to determine the bionic rehabilitation gait of the intelligent robotic horse based on kinematic parameters and the body structure parameters of the intelligent robotic horse through an inverse kinematics solution algorithm.
[0055] The control module 270 is used to control the intelligent robotic horse to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user to be trained through the intelligent robotic horse.
[0056] In this embodiment, optionally, the calculation module 230 is specifically used for: Real-time three-dimensional coordinate data of key pelvic landmarks of the user under training during specific movements are collected; coordinate transformation and matrix operation are performed on the real-time three-dimensional coordinate data through pelvic kinematic model to calculate the translational and rotational displacement parameters of the pelvic structure of the user under training in the sagittal plane, the coronal plane, and the horizontal plane.
[0057] In this embodiment, optionally, the generation module 240 is specifically used for: The translational and rotational displacement parameters of the pelvic structure of the training user in the sagittal, coronal, and horizontal planes are serialized to obtain a time-series dataset. This time-series dataset is then input into a preset time-series model to generate predicted displacement parameter values within a preset time step. These predicted displacement parameter values are used as coordinate data for dynamic trajectory points. The actual displacement parameter values at historical moments and the predicted displacement parameter values within the preset time step are sequentially mapped to three-dimensional coordinates to obtain the corresponding three-dimensional pelvic motion trajectory.
[0058] In this embodiment, optionally, the extraction module 250 is specifically used for: Kinematic parameters corresponding to the sagittal plane in the three-dimensional pelvic motion trajectory are extracted. These parameters include: pelvic anterior tilt angle, posterior tilt angle, the difference between the maximum anterior tilt angle and the maximum posterior tilt angle, and the angular velocity of the anterior / posterior tilt motion. Kinematic parameters corresponding to the coronal plane in the three-dimensional pelvic motion trajectory are also extracted. These parameters include: pelvic left tilt angle, right tilt angle, the difference between the maximum left tilt angle and the maximum right tilt angle, and the angular velocity of the left / right tilt motion. Kinematic parameters corresponding to the horizontal plane in the three-dimensional pelvic motion trajectory are also extracted. These parameters include: pelvic left rotation angle, right rotation angle, the difference between the maximum left rotation angle and the maximum right rotation angle, and the angular velocity of the left / right rotation motion.
[0059] In this embodiment, optionally, the determining module 260 is specifically used for: Using kinematic parameters as constraints for inverse kinematics, the inverse kinematics algorithm is used to calculate the motion angles of each joint of the intelligent robotic horse at different times based on the body structure parameters of the intelligent robotic horse. The motion angles of each joint of the intelligent robotic horse at different times are combined into a coherent motion sequence to obtain the bionic rehabilitation gait of the intelligent robotic horse.
[0060] In this embodiment, optionally, a prompting module is also included.
[0061] The prompting module is used to match the corresponding rehabilitation assistive devices to the user based on the user's rehabilitation goal data; and to issue device wearing prompts to the user during the user's rehabilitation training process, so as to remind the user to wear the rehabilitation assistive devices for rehabilitation training.
[0062] In this embodiment, optionally, a data acquisition module may also be included.
[0063] The data acquisition module is used to collect limb response data of the user being trained during the rehabilitation training process.
[0064] The generation module 240 is also used to generate rehabilitation assessment results for the user to be trained based on limb response data.
[0065] The rehabilitation training device based on the intelligent robotic horse provided in this disclosure can perform the above-described method embodiments. Its specific implementation principle and technical effects can be found in the above-described method embodiments, and will not be repeated here.
[0066] This application also provides a computer device. Please refer to the following for details. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.
[0067] The computer device includes a memory 310 and a processor 320 that are interconnected via a system bus. It should be noted that only a computer device with memory 310 and processor 320 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.
[0068] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.
[0069] The memory 310 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card equipped on the computer device. Of course, the memory 310 may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory 310 is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method described above. In addition, the memory 310 can also be used to temporarily store various types of data that have been output or will be output.
[0070] Processor 320 is typically used to perform overall operations of a computer device. In this embodiment, memory 310 is used to store program code or instructions, including computer operation instructions, and processor 320 is used to execute the program code or instructions stored in memory 310 or process data, such as program code that runs the methods described above.
[0071] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus system can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.
[0072] Another embodiment of this application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method; and to generate means for implementing the functional actions specified in each block or combination of blocks in the block diagram.
[0073] Computer-readable media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any suitable combination thereof, wherein the memory is used to store program code or instructions, the program code including computer operation instructions, and the processor is used to execute the program code or instructions of the above-described methods stored in the memory.
[0074] The definitions of memory and processor can be found in the description of the foregoing computer device embodiments, and will not be repeated here.
[0075] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0076] In the various embodiments of this application, the functional units or modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0077] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0078] In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" as described in this application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims listing several means, several units of these means may be embodied by the same item of hardware. The use of "first," "second," and "third," etc., does not indicate any order and these words should be interpreted as names. Unless otherwise specified, the steps in the above embodiments should not be construed as limiting the order of execution.
[0079] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A rehabilitation training method based on an intelligent robotic horse, characterized in that, include: Acquire physical condition data and rehabilitation goal data of the users to be trained; Based on the physical condition data and rehabilitation target data of the user to be trained, a corresponding pelvic kinematic model is constructed. The displacement parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension, are calculated using the pelvic kinematic model. By using a preset time series model, dynamic trajectory points are generated for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension, and the dynamic trajectory points are connected in sequence to obtain the corresponding three-dimensional pelvic motion trajectory. Kinematic parameters are extracted from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension. The bionic rehabilitation gait of the intelligent robotic horse is determined by using an inverse kinematics algorithm based on the kinematic parameters and the body structure parameters of the intelligent robotic horse. The intelligent robotic horse is controlled to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user through the intelligent robotic horse.
2. The method according to claim 1, characterized in that, The displacement parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension, are calculated using the pelvic kinematic model, including: Collect real-time three-dimensional coordinate data of key pelvic landmarks of the user to be trained under specific actions; The pelvic kinematic model is used to perform coordinate transformation and matrix operations on the real-time three-dimensional coordinate data to calculate the translational and rotational displacement parameters of the pelvic structure of the user to be trained in the sagittal plane, the coronal plane, and the horizontal plane.
3. The method according to claim 2, characterized in that, Using a preset time series model, dynamic trajectory points are generated for the displacement parameters of the pelvic structure of the user to be trained, corresponding to the three-dimensional pelvic dimension. These dynamic trajectory points are then connected sequentially to obtain the corresponding three-dimensional pelvic motion trajectory, including: The translational and rotational displacement parameters of the pelvic structure of the user to be trained in the sagittal plane, the coronal plane, and the horizontal plane are serialized to obtain a time series dataset. The time series dataset is input into a preset time series model to generate predicted displacement parameters within a preset time step; and the predicted displacement parameters are used as coordinate data of dynamic trajectory points. The actual values of displacement parameters at historical moments and the predicted values of displacement parameters within a preset time step are sequentially mapped to three-dimensional coordinates to obtain the corresponding three-dimensional pelvic motion trajectory.
4. The method according to claim 1, characterized in that, Kinematic parameters are extracted from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension, including: Extract the kinematic parameters corresponding to the sagittal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the sagittal plane include: pelvic anterior tilt angle, posterior tilt angle, the difference between the maximum anterior tilt angle and the maximum posterior tilt angle, and the angular velocity of the anterior / posterior tilt motion; Extract the kinematic parameters corresponding to the coronal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the coronal plane include: left tilt angle, right tilt angle, the difference between the maximum left tilt angle and the maximum right tilt angle, and the angular velocity of the left / right tilt motion; Extract the kinematic parameters corresponding to the horizontal plane in the three-dimensional pelvic motion trajectory; the kinematic parameters corresponding to the horizontal plane include: left rotation angle, right rotation angle, the difference between the maximum left rotation angle and the maximum right rotation angle, and the angular velocity of the left / right rotation motion.
5. The method according to claim 1, characterized in that, The biomimetic rehabilitation gait of the intelligent robotic horse is determined using an inverse kinematics algorithm based on the kinematic parameters and the body structure parameters of the intelligent robotic horse, including: Using the kinematic parameters as constraints for inverse kinematics solution, and based on the body structure parameters of the intelligent robotic horse, the motion angles of each joint of the intelligent robotic horse at different times are calculated by the inverse kinematics solution algorithm. By combining the joints of the intelligent robotic horse at different times with their corresponding motion angles into a coherent motion sequence, the bionic rehabilitation gait corresponding to the intelligent robotic horse is obtained.
6. The method according to claim 1, characterized in that, Also includes: Match the corresponding rehabilitation assistive devices to the user to be trained based on the user's rehabilitation goal data; During the rehabilitation training process of the user to be trained, a device wearing prompt is issued to the user to be trained, so as to remind the user to wear the rehabilitation assistive device for rehabilitation training.
7. The method according to claim 1, characterized in that, Also includes: Collect limb response data of the user to be trained during the rehabilitation training process; The rehabilitation assessment results for the user to be trained are generated based on the limb response data.
8. A rehabilitation training device based on an intelligent robotic horse, characterized in that, include: The acquisition module is used to acquire physical status data and rehabilitation goal data of the user to be trained. The construction module is used to construct a corresponding pelvic kinematic model based on the physical state data and rehabilitation target data of the user to be trained. The calculation module is used to calculate the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through the pelvic kinematic model. The generation module is used to generate dynamic trajectory points for the displacement parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension through a preset time series model, and to connect each of the dynamic trajectory points in sequence to obtain the corresponding three-dimensional pelvic motion trajectory. The extraction module is used to extract kinematic parameters from the three-dimensional pelvic motion trajectory to obtain the kinematic parameters of the pelvic structure of the user to be trained corresponding to the three-dimensional pelvic dimension. The determination module is used to determine the bionic rehabilitation gait of the intelligent robotic horse based on the kinematic parameters and the body structure parameters of the intelligent robotic horse by using an inverse kinematics algorithm. The control module is used to control the intelligent robotic horse to move according to the bionic rehabilitation gait during the rehabilitation training of the user to be trained, so as to carry out rehabilitation training for the user to be trained through the intelligent robotic horse.
9. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the rehabilitation training method based on an intelligent robotic horse as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the rehabilitation training method based on the intelligent robotic horse as described in any one of claims 1 to 7.