Virtual reality assisted gait training system
Through virtual reality technology and data acquisition and analysis modules, a virtual reality-assisted gait training system was designed, which solved the problem of difficult to quantify training effects and low patient participation in traditional gait training methods, and achieved personalized and efficient and safe gait training effects.
Patent Information
- Application Number
- CN202411586723.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-08
- Publication Date
- 2025-02-14
AI Technical Summary
Traditional gait training methods have problems such as difficulty in quantifying the training effect, low patient active participation, and boring training process.
Design a virtual reality-assisted gait training system, including virtual reality module, data acquisition module, data processing module and data analysis and evaluation module, and collect and analyze patients' physiological and motor data in real time by simulating a multi-scenario gait training environment. , provide personalized training assessments and plans.
It has improved the patient's training interest and participation, achieved scientific evaluation and personalized plans for training effects, and promoted the patient's recovery process.
Smart Images
Figure CN119446412A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of rehabilitation medicine, and in particular to a virtual reality assisted gait training system. Background Art
[0002] Gait training plays an important role in rehabilitation medicine, especially for the rehabilitation of neurological diseases, musculoskeletal injuries and the elderly. However, traditional gait training methods are relatively simple, lack simulation of complex environments and dynamic changes, and have limited training effects. Traditional gait rehabilitation training methods often rely on manual guidance from therapists and self-practice by patients, and there are problems such as difficulty in quantifying training effects, low active participation of patients, and boring training process. With the rapid development of virtual reality technology, its application in the field of medical rehabilitation is becoming more and more extensive. Virtual reality technology can create a realistic training environment, improve patients' interest and participation in training through multi-sensory stimulation such as vision and hearing, and realize real-time monitoring and data analysis of the training process, providing a scientific basis for rehabilitation training.
[0003] Aiming at the problems that the existing gait training process is dull, inefficient and has poor effect, the present invention proposes a virtual reality assisted gait training system. Summary of the invention
[0004] Based on this, it is necessary to propose a virtual reality-assisted gait training system to address the problems of the existing gait training process being boring, inefficient and ineffective.
[0005] The present invention is implemented by the following technical scheme: a virtual reality assisted gait training system, comprising:
[0006] Virtual reality module, used to simulate multi-scenario gait training environment;
[0007] A data collection module is used to collect environmental parameters and the experiencer's reaction data; the reaction data includes physiological data and motion parameter data;
[0008] A data processing module, used to process the environmental parameters and the reaction data; wherein the environmental parameters are processed to remove outliers; the physiological data are processed by a denoising algorithm to obtain a heart rate change curve, a blood pressure change curve and a body temperature change curve; and the motion parameter data are normalized;
[0009] The data analysis and evaluation module is used to analyze whether the experiencer's gait training is effective based on the environmental parameters and the reaction data, and to form an evaluation report based on the analysis data.
[0010] Furthermore, the virtual reality module includes a VR headset and a handheld VR controller; the VR headset is worn on the head of the experiencer to transmit the gait training environment image; the handheld VR controller is used to simulate gait training environment parameters according to the input gait training data.
[0011] Furthermore, the data acquisition module includes a physiological sensor, a gait sensor module and a VR device camera. The physiological sensor is arranged on the experiencer's body to obtain the experiencer's physiological data; the gait sensor module is distributed on the experiencer's limbs to obtain the experiencer's motion parameter data; the VR device camera is set on the VR headset or independently set to obtain the environmental parameters of the experiencer's environment and the experiencer's motion posture and gait changes.
[0012] Furthermore, the gait sensor module includes a pelvic sensor, an arm sensor, a hip joint sensor, an in-shoe sensor, an ankle sensor and a knee joint sensor, which are respectively arranged at the pelvis, arm, hip joint, in-shoe, ankle and knee joint. The pelvic sensor, arm sensor, hip joint sensor, in-shoe sensor, ankle sensor and knee joint sensor all use inertial sensors.
[0013] Further, the data analysis and evaluation module includes a feature extraction unit, a gait analysis unit, a rehabilitation evaluation unit, a rehabilitation planning unit and a report generation unit;
[0014] The feature extraction unit is used to extract the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data;
[0015] The gait analysis unit is used to construct a gait analysis model, use normal person gait big data and patient gait big data for training, train and retain a gait training analysis model that meets the test accuracy, input the extracted features, and output the corresponding gait training degree;
[0016] The rehabilitation evaluation unit is used to determine whether the desensitization training is effective according to the degree of consistency between the gait training data of the experiencer in multiple gait training sessions and the gait big data of normal people and the gait big data of patients;
[0017] The rehabilitation planning unit is used to re-formulate a rehabilitation plan based on the data obtained by the rehabilitation assessment unit;
[0018] The report forming unit is used to form an assessment report according to the data obtained by the rehabilitation assessment unit.
[0019] Furthermore, a virtual reality-assisted gait training method is also provided, which specifically comprises the following steps:
[0020] S1: The experiencer wears a virtual reality device that simulates a multi-scenario gait environment;
[0021] S2: adjusting the output parameters of the virtual reality device, and collecting the reaction data of the experiencer under different parameters respectively; wherein the reaction data includes physiological data and motion parameter data;
[0022] S3: processing the reaction data;
[0023] S4: constructing a feature extraction model to obtain the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data;
[0024] S5: construct a gait analysis model, use normal human gait big data for training, retain the motion sickness analysis model that meets the test accuracy, input the hip, knee, ankle and pelvic activity angle curve characteristics, single support phase / double support phase data characteristics, swing phase data characteristics, step length characteristics, step frequency characteristics, step number characteristics, step speed characteristics, foot lift height characteristics, turn time characteristics and turn step number characteristics into the gait training analysis model, and output the gait training degree;
[0025] S6: Determine whether the gait training is effective based on the degree of consistency between the gait training data of the experiencer in multiple gait training sessions and the gait big data of normal people and the gait big data of patients;
[0026] S7: Re-formulate the rehabilitation plan based on the effectiveness of the experiencer's gait training;
[0027] S8: Form an evaluation report.
[0028] Compared with the prior art, the present invention has the following beneficial effects:
[0029] The virtual reality-assisted gait training system of the present invention uses virtual reality technology to immerse patients in realistic training scenes, such as forest trails, city streets, stairs, etc. This sense of immersion can stimulate patients' interest in training and improve their participation in training;
[0030] The system of the present invention can capture the patient's gait data in real time, including step length, step frequency, gait symmetry, joint angles, etc., and conduct in-depth analysis. These data provide a scientific basis for the evaluation of training effects;
[0031] The virtual reality technology of the present invention provides a safe and controllable training environment for patients. In the virtual scene, patients can perform various gait training without worrying about the risks in the actual environment, such as falling, collision, etc.
[0032] The present invention can accelerate the patient's rehabilitation process by providing a personalized, efficient and safe training program. Patients can train at home or in hospitals and other places without having to go to rehabilitation centers frequently, which improves the convenience and efficiency of rehabilitation. Through repeated intensive training, the system can promote the patient's nervous system reconstruction and muscle strength recovery, thereby improving their motor function. Patients can gradually restore their walking ability and improve gait stability and symmetry. The system not only focuses on short-term rehabilitation effects, but also pays attention to maintaining long-term effects. By regularly evaluating and adjusting the training program, the system can ensure that patients can continue to maintain good gait and motor function after rehabilitation. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 A framework diagram of the virtual reality-assisted gait training system proposed in the present invention;
[0034] Figure 2 This is a framework diagram of the gait sensor module in the virtual reality-assisted gait training system proposed in the present invention. DETAILED DESCRIPTION
[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component at the same time. When a component is considered to be "fixed to" another component, it may be directly fixed on the other component or there may be a central component at the same time.
[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.
[0038] See also Figure 1 and Figure 2 , this embodiment provides a virtual reality assisted gait training system, including:
[0039] Virtual reality module, used to simulate multi-scenario gait training environment;
[0040] A data collection module is used to collect environmental parameters and the experiencer's reaction data; the reaction data includes physiological data and motion parameter data;
[0041] The data processing module is used to process the environmental parameters and the reaction data; wherein the environmental parameters are processed to remove outliers; the physiological data is processed by a denoising algorithm to obtain a heart rate change curve, a blood pressure change curve and a body temperature change curve. The corresponding changes in heart rate, blood pressure and body temperature can reflect the training status of the experiencer to avoid accidents caused by excessive training. In some embodiments, the degree of physical recovery of the experiencer's gait training can also be judged based on the heart rate, blood pressure and body temperature data, and directly used as a basis for judging the effectiveness of gait training; the motion parameter data is normalized; the normalization of gait motion parameter data has many benefits in gait analysis. It can not only eliminate dimensional effects, improve algorithm performance, and facilitate data visualization and comparison, but also reduce the impact of outliers and meet the assumptions of certain algorithms.
[0042] The data analysis and evaluation module is used to analyze whether the experiencer's gait training is effective based on the environmental parameters and the reaction data, and to form an evaluation report based on the analysis data.
[0043] Furthermore, the virtual reality module includes a VR headset and a handheld VR controller; the VR headset is worn on the head of the experiencer to transmit the gait training environment image; the handheld VR controller is used to simulate gait training environment parameters according to the input gait training data.
[0044] Furthermore, the data acquisition module includes a physiological sensor, a gait sensor module and a VR device camera. The physiological sensor is arranged on the experiencer's body to obtain the experiencer's physiological data; the gait sensor module is distributed on the experiencer's limbs to obtain the experiencer's motion parameter data; the VR device camera is set on the VR headset or independently set to obtain the environmental parameters of the experiencer's environment and the experiencer's motion posture and gait changes.
[0045] Furthermore, the gait sensor module includes a pelvic sensor, an arm sensor, a hip joint sensor, an in-shoe sensor, an ankle sensor and a knee joint sensor, which are respectively arranged at the pelvis, arm, hip joint, in-shoe, ankle and knee joint. The pelvic sensor, arm sensor, hip joint sensor, in-shoe sensor, ankle sensor and knee joint sensor all use inertial sensors.
[0046] Further, the data analysis and evaluation module includes a feature extraction unit, a gait analysis unit, a rehabilitation evaluation unit, a rehabilitation planning unit and a report generation unit;
[0047] The feature extraction unit is used to extract the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data;
[0048] The gait analysis unit is used to construct a gait analysis model, use normal person gait big data and patient gait big data for training, train and retain a gait training analysis model that meets the test accuracy, input the extracted features, and output the corresponding gait training degree;
[0049] The rehabilitation evaluation unit is used to judge whether the desensitization training is effective according to the degree of consistency between the gait training data of the experiencer in multiple gait trainings and the gait big data of normal people and the gait big data of patients. When the gait training data of the experiencer is consistent with the gait data of normal people, the training can be stopped or reduced;
[0050] Big data of normal people’s gait:
[0051] 1. Stride length and stride length Stride length: refers to the distance between the two points where the left and right heels or toes touch the ground one after another when walking. The stride length of a normal person is generally 50-80cm. Stride length: also known as the stride length, is the distance between the two points where the heel (or toe) of the same side touches the ground one after another, usually twice the stride length, about 100-160cm.
[0052] 2. Cadence Cadence refers to the number of steps per minute. The cadence of healthy people is about 95-125 steps / minute. Specifically, the cadence of oriental men is about 112.2±8.9 steps / minute, and that of women is about 123.4±8.0 steps / minute.
[0053] 3. Pace Pace refers to the distance walked per minute. A healthy person walks at a speed of about 65-95 meters per minute, which is equivalent to a speed of about 1.08-1.58 meters per second, or 0.6-0.95 kilometers per hour.
[0054] 4. Gait cycle The walking cycle refers to the process from the time when the heel of one side touches the ground to the time when the heel of the same side touches the ground again, which takes about 1-1.32 seconds.
[0055] 5. Other related parameters Foot angle: The foot angle of healthy people when walking is about 6.75°. Joint range of motion: Different joints have different normal ranges of motion, such as shoulder flexion 0°-180°, extension 0°-50°; hip flexion 0°-90° (when knees are bent), extension 0°-15°; knee flexion 0°-130°, extension 0°; ankle dorsiflexion 0°-20°, plantar flexion 0°-45°, etc.
[0056] Patient gait big data analysis:
[0057] 1. Step length:
[0058] Stride length refers to the distance from when one heel (or toe) touches the ground to when the same heel (or toe) touches the ground again when walking. The normal stride length of a person is about 50-80cm, but the stride length of a patient may be shortened due to pain, muscle weakness, joint stiffness, etc.
[0059] 2. Cadence:
[0060] Cadence refers to the number of steps you take per minute. A healthy person's cadence is about 95-125 steps per minute. A patient's cadence may decrease due to difficulty walking, decreased balance, and other reasons.
[0061] 3. Pace:
[0062] Gait speed refers to the distance walked per unit time, usually measured in meters per second (m / s). The average natural walking speed of a normal person is about 1.2 m / s. The patient's walking speed may decrease due to pain, fatigue, decreased physical strength, etc.
[0063] 4. Walking cycle:
[0064] The gait cycle is the process from one heel touching the ground to the next heel touching the ground, which takes about 1-1.32 seconds. The patient's gait cycle may change due to gait abnormalities, uneven distribution of the time between the stance phase and the swing phase, etc.
[0065] 5. Gait symmetry:
[0066] Gait symmetry refers to the coordination and consistency of the lower limbs during walking. The patient's gait symmetry may be reduced due to muscle weakness, joint stiffness, pain, etc.
[0067] The rehabilitation planning unit is used to re-formulate a rehabilitation plan based on the data obtained by the rehabilitation assessment unit;
[0068] The report forming unit is used to form an assessment report according to the data obtained by the rehabilitation assessment unit.
[0069] Furthermore, a virtual reality-assisted gait training method is also provided, which specifically comprises the following steps:
[0070] S1: The experiencer wears a virtual reality device that simulates a multi-scenario gait environment;
[0071] S2: adjusting the output parameters of the virtual reality device, and collecting the reaction data of the experiencer under different parameters respectively; wherein the reaction data includes physiological data and motion parameter data;
[0072] S3: processing the reaction data;
[0073] S4: constructing a feature extraction model to obtain the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data;
[0074] S5: construct a gait analysis model, use normal human gait big data for training, retain the motion sickness analysis model that meets the test accuracy, input the hip, knee, ankle and pelvic activity angle curve characteristics, single support phase / double support phase data characteristics, swing phase data characteristics, step length characteristics, step frequency characteristics, step number characteristics, step speed characteristics, foot lift height characteristics, turn time characteristics and turn step number characteristics into the gait training analysis model, and output the gait training degree;
[0075] S6: Determine whether the gait training is effective based on the degree of consistency between the gait training data of the experiencer in multiple gait training sessions and the gait big data of normal people and the gait big data of patients;
[0076] S7: Re-formulate the rehabilitation plan based on the effectiveness of the experiencer's gait training;
[0077] S8: Form an evaluation report.
[0078] The virtual reality-assisted gait training system of the present invention uses virtual reality technology to immerse patients in realistic training scenes, such as forest trails, city streets, stairs, etc. This sense of immersion can stimulate patients' interest in training and improve their participation in training;
[0079] The system of the present invention can capture the patient's gait data in real time, including step length, step frequency, gait symmetry, joint angles, etc., and conduct in-depth analysis. These data provide a scientific basis for the evaluation of training effects;
[0080] The virtual reality technology of the present invention provides a safe and controllable training environment for patients. In the virtual scene, patients can perform various gait training without worrying about the risks in the actual environment, such as falling, collision, etc.
[0081] The present invention can accelerate the patient's rehabilitation process by providing a personalized, efficient and safe training program. Patients can train at home or in hospitals and other places without having to go to rehabilitation centers frequently, which improves the convenience and efficiency of rehabilitation. Through repeated intensive training, the system can promote the patient's nervous system reconstruction and muscle strength recovery, thereby improving their motor function. Patients can gradually restore their walking ability and improve gait stability and symmetry. The system not only focuses on short-term rehabilitation effects, but also pays attention to maintaining long-term effects. By regularly evaluating and adjusting the training program, the system can ensure that patients can continue to maintain good gait and motor function after rehabilitation.
[0082] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0083] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A virtual reality assisted gait training system, characterized in that: include: Virtual reality module, used to simulate multi-scenario gait training environment; A data collection module is used to collect environmental parameters and the experiencer's reaction data; the reaction data includes physiological data and motion parameter data; A data processing module, used to process the environmental parameters and the reaction data; wherein the environmental parameters are processed to remove outliers; the physiological data are processed by a denoising algorithm to obtain a heart rate change curve, a blood pressure change curve and a body temperature change curve; and the motion parameter data are normalized; The data analysis and evaluation module is used to analyze whether the experiencer's gait training is effective based on the environmental parameters and the reaction data, and to form an evaluation report based on the analysis data.
2. A virtual reality assisted gait training system according to claim 1, characterized in that: The virtual reality module includes a VR headset and a handheld VR controller; the VR headset is worn on the head of the experiencer to transmit the gait training environment image; the handheld VR controller is used to simulate gait training environment parameters according to the input gait training data.
3. A virtual reality assisted gait training system according to claim 2, characterized in that: The data acquisition module includes a physiological sensor, a gait sensor module and a VR device camera. The physiological sensor is arranged on the experiencer's body to obtain the experiencer's physiological data; the gait sensor module is distributed on the experiencer's limbs to obtain the experiencer's motion parameter data; the VR device camera is set on the VR head display or independently set to obtain the environmental parameters of the experiencer's environment and the experiencer's motion posture and gait changes.
4. A virtual reality assisted gait training system according to claim 3, characterized in that: The gait sensor module includes a pelvic sensor, an arm sensor, a hip joint sensor, a shoe sensor, an ankle sensor and a knee joint sensor, which are respectively arranged at the pelvis, arm, hip joint, shoe, ankle and knee joint. The pelvic sensor, arm sensor, hip joint sensor, shoe sensor, ankle sensor and knee joint sensor all use inertial sensors.
5. A virtual reality assisted gait training system according to claim 4, characterized in that: The data analysis and evaluation module includes a feature extraction unit, a gait analysis unit, a rehabilitation evaluation unit, a rehabilitation planning unit and a report generation unit; The feature extraction unit is used to extract the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data; The gait analysis unit is used to construct a gait analysis model, use normal person gait big data and patient gait big data for training, train and retain a gait training analysis model that meets the test accuracy, input the extracted features, and output the corresponding gait training degree; The rehabilitation evaluation unit is used to determine whether the desensitization training is effective according to the degree of consistency between the gait training data of the experiencer in multiple gait training sessions and the gait big data of normal people and the gait big data of patients; The rehabilitation planning unit is used to re-formulate a rehabilitation plan based on the data obtained by the rehabilitation assessment unit; The report forming unit is used to form an assessment report according to the data obtained by the rehabilitation assessment unit.
6. A virtual reality assisted gait training system according to claim 5, characterized in that: It also includes a virtual reality-assisted gait training method, which specifically includes the following steps: S1: The experiencer wears a virtual reality device that simulates a multi-scenario gait environment; S2: adjusting the output parameters of the virtual reality device, and collecting the reaction data of the experiencer under different parameters respectively; wherein the reaction data includes physiological data and motion parameter data; S3: processing the reaction data; S4: constructing a feature extraction model to obtain the hip, knee, ankle and pelvic activity angle curve features, single support phase / double support phase data features, swing phase data features, step length features, step frequency features, step number features, step speed features, foot lift height features, turn time features and turn step number features from the motion parameter data; S5: construct a gait analysis model, use normal human gait big data for training, retain the motion sickness analysis model that meets the test accuracy, input the hip, knee, ankle and pelvic activity angle curve characteristics, single support phase / double support phase data characteristics, swing phase data characteristics, step length characteristics, step frequency characteristics, step number characteristics, step speed characteristics, foot lift height characteristics, turn time characteristics and turn step number characteristics into the gait training analysis model, and output the gait training degree; S6: Determine whether the gait training is effective based on the degree of consistency between the gait training data of the experiencer in multiple gait training sessions and the gait big data of normal people and the gait big data of patients; S7: Re-formulate the rehabilitation plan based on the effectiveness of the experiencer's gait training; S8: Form an evaluation report.