VR-based limb rehabilitation assistive system for amyotrophic lateral sclerosis (ALS) motor disorder

The VR-based rehabilitation assistive system for limbs with amyotrophic lateral sclerosis (ALS) utilizes varied 3D training scenarios and virtual character interaction to address the monotony of ALS rehabilitation training, thereby improving patients' training motivation and rehabilitation outcomes.

CN116525062BActive Publication Date: 2026-11-17THE FIRST AFFILIATED HOSPITAL OF ARMY MEDICAL UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202310456253.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-04-25
Publication Date
2026-11-17
Estimated Expiration
2043-04-25

AI Technical Summary

Technical Problem

Existing limb rehabilitation training for amyotrophic lateral sclerosis (ALS) is monotonous and repetitive in fixed settings, leading to poor patient compliance and reduced rehabilitation effectiveness.

Method used

The VR-based limb rehabilitation assistive system for amyotrophic lateral sclerosis (ALS) motor disorder enhances patients' motivation and training effectiveness by creating diverse 3D training scenarios and projects, combined with virtual character interaction and effect evaluation modules.

Benefits of technology

Through rich training scenarios and interactive methods, the patients' enthusiasm for rehabilitation training was enhanced, and the effectiveness of rehabilitation training was improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116525062B_ABST
    Figure CN116525062B_ABST
Patent Text Reader

Abstract

This invention relates to the field of virtual interaction technology, specifically disclosing a VR-based rehabilitation assistive system for amyotrophic lateral sclerosis (ALS) motor disorder. The system includes: a project creation module for creating several three-dimensional training scenes and training projects; a user login module for collecting the personal information of a first user; a task generation module for generating training tasks based on the first user's personal information and preset training rules, selecting three-dimensional training scenes and training projects; a VR interaction module for obtaining corresponding three-dimensional training scenes and training projects based on the training tasks, displaying the training projects in the three-dimensional training scenes, creating virtual characters in the three-dimensional training scenes, capturing the first user's limb movements, and synchronizing the first user's limb movements to the virtual characters; and an effect evaluation module for evaluating the achievement of the training tasks based on the first user's limb movements. The technical solution of this invention can effectively improve patient training motivation and enhance rehabilitation training effects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of virtual interaction technology, and in particular to a VR-based rehabilitation assistive system for limbs with amyotrophic lateral sclerosis (ALS) motor disorders. Background Technology

[0002] Amyotrophic lateral sclerosis (ALS), also known as motor neuron disease (MND), is caused by damage to the upper and lower motor neurons, resulting in gradual weakness and atrophy of the muscles in the bulbar region (the muscles innervated by the medulla oblongata), limbs, trunk, chest, and abdomen.

[0003] Clinically, in addition to treatment, patients with amyotrophic lateral sclerosis (ALS) also need to undergo rehabilitation training, such as limb movement exercises, as prescribed by their doctors in order to effectively control the further deterioration of the disease. Doctors typically conduct rehabilitation training in a fixed room, and the monotonous setting and repetitive training methods can easily lead to poor patient compliance and reduced patient participation.

[0004] Therefore, there is a need for a VR-based rehabilitation assistive system for limbs with amyotrophic lateral sclerosis (ALS) motor disorders that can improve patients' motivation for training and enhance the effectiveness of rehabilitation training. Summary of the Invention

[0005] This invention provides a VR-based rehabilitation assistive system for limbs with amyotrophic lateral sclerosis (ALS) motor disorders, which can effectively improve patients' training motivation and enhance the effect of rehabilitation training.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] A VR-based limb rehabilitation assistive system for amyotrophic lateral sclerosis (ALS) includes:

[0008] The project creation module is used to create several 3D training scenarios and several training projects.

[0009] The user login module is used to verify the identity of the first user and determine whether the first user is logging in for the first time. If so, it collects the first user's personal information.

[0010] The task generation module is used to select 3D training scenarios and training items to generate training tasks based on the first user's personal information and preset training rules.

[0011] The VR interaction module is used to obtain the corresponding 3D training scene and training items according to the training task, display the training items in the 3D training scene, and also to create virtual characters in the 3D training scene, capture the body movements of the first user, and synchronize the body movements of the first user to the virtual character.

[0012] The effectiveness evaluation module is used to assess the achievement of the training task based on the first user's body movements.

[0013] The basic principles and beneficial effects of the scheme are as follows:

[0014] This solution creates several 3D training scenarios and training programs. Based on the personal information of the first user (the patient), these scenarios and programs are selected to generate training tasks. The first user can enter the virtual 3D training scenario through a VR interaction module and perform rehabilitation training according to the programs. The system then assesses the user's limb movements to understand their progress in completing the training tasks. Compared to existing fixed-scene rehabilitation training, this solution offers more varied training scenarios, preventing boredom and increasing the user's motivation and effectiveness.

[0015] Furthermore, the project creation module is also used to set scene labels for the created 3D training scene and to set project labels for the created training project;

[0016] The training rules include the mapping relationship between personal information and preset training tasks, as well as the mapping relationship between training tasks and scene labels and project labels. The task generation module is also used to determine the training task based on personal information, then determine the scene label and project label based on the training task, randomly select a corresponding 3D training scene based on the scene label, and randomly select a corresponding training project based on the project label.

[0017] Setting scene tags and project tags makes it easier to select 3D training scenes and training projects.

[0018] Furthermore, the login module is also used to verify the identity of the second user, and after successful verification, to assign control permissions to the second user;

[0019] It also includes a display module, which is used to create a virtual camera in the 3D training scene, and to receive view control commands from a second user, adjust the view of the virtual camera in the 3D training scene according to the view control commands, and acquire and display the image of the virtual 3D training scene through the virtual camera.

[0020] The second user, i.e. the doctor, can view the content viewed by the first user through the display module. By using a virtual camera to view the content in a third-person perspective, this avoids discomfort such as dizziness compared to using the first user's first-person perspective.

[0021] Furthermore, the task generation module is also used to receive adjustment information from the second user, and adjust the three-dimensional training scene and / or training items in the training task according to the adjustment information.

[0022] The second user can manually adjust the 3D training scene and training items according to the actual situation.

[0023] Furthermore, the training program includes several body movements. The effect evaluation module is used to determine the similarity between the body movements of the training program and the user's body movements at the same time, and to evaluate the first user's training task achievement based on the similarity.

[0024] Furthermore, the effect evaluation module is also used to determine whether the similarity between the training item's limb movements and the first user's limb movements is within a preset range; if so, a recording instruction is generated.

[0025] The display module is also used to record and store the video of the first user's body movements via a virtual camera according to the recording instructions.

[0026] By recording and storing videos of the first user's body movements, it is convenient for subsequent reviews by both the first and second users. The preset range can be set according to the actual situation, for example, 60%-80%, which represents the body movements that the first user tried to complete but did not achieve the best effect, thus excluding body movements that were not completed with effort (less than 60%).

[0027] Furthermore, the VR interaction module is also used to capture the body movements of the second user, determine the part of the body that the second user and the first user are in contact based on the body movements of the second user, and send the part of the body in contact to the display module.

[0028] View control commands include automatic mode, fixed mode, and free mode;

[0029] The display module is also used to determine whether the current view control command is in automatic mode. If so, it will point the virtual camera's view at the part of the body that is in contact with the limb.

[0030] It allows a second user to easily observe how the parts of the body in contact are displayed in the 3D training scene. Attached Figure Description

[0031] Figure 1 This is a logic block diagram of a VR-based rehabilitation assistive system for limbs with amyotrophic lateral sclerosis (ALS) motor disorders. Detailed Implementation

[0032] The following detailed description illustrates the specific implementation method:

[0033] Example 1

[0034] like Figure 1 As shown, the VR-based limb rehabilitation assistive system for amyotrophic lateral sclerosis (ALS) motor disorder in this embodiment includes a project creation module, a user login module, a task generation module, a VR interaction module, an effect evaluation module, and a display module.

[0035] The project creation module is used to create several 3D training scenes and several training projects; it is used to set scene tags for the created 3D training scenes; and to set project tags for the created training projects. For example, creating 3D training scenes of an outdoor sports field and a grassy area will both be tagged as "Outdoor"; creating 3D training scenes of an indoor gym and a boxing gym will both be tagged as "Indoor". In this embodiment, project tags are divided according to whether they can be completed independently and their difficulty. For example, independently completed (Level 1 difficulty); independently completed (Level 2 difficulty); completed with assistance (Level 1 difficulty); completed with assistance (Level 2 difficulty), etc.; the higher the difficulty level, the greater the difficulty. A training project includes several physical movements, which are demonstrated by a virtual doctor avatar.

[0036] The user login module is used to verify the identity of the first user and determine whether the first user is logging in for the first time. If so, the first user's personal information is collected, including gender, age, and medical condition. In this embodiment, the first user is a patient.

[0037] The task generation module is used to generate training tasks by selecting 3D training scenes and training items based on the first user's personal information and preset training rules. Specifically, the training rules include the mapping relationship between personal information and preset training tasks, as well as the mapping relationship between training tasks and scene tags and item tags. The task generation module is also used to determine training tasks based on personal information, then determine scene tags and item tags based on training tasks, randomly select a corresponding 3D training scene based on scene tags, and randomly select a corresponding training item based on item tags. In this embodiment, the training rules include the mapping relationship between the patient's condition in personal information and preset training tasks. For example, the training task mapped to the current patient's condition is a self-training task, the scene tags mapped to the self-training task are indoor and outdoor, and the item tags mapped are self-completion and level 1 difficulty.

[0038] The VR interaction module is used to acquire corresponding 3D training scenes and training items according to training tasks, display training items in the 3D training scene, create virtual characters in the 3D training scene, capture the body movements of the first user, and synchronize the body movements of the first user to the virtual character. In this embodiment, the VR interaction module includes a head-mounted display device, a camera, and a processing device. The head-mounted display device displays the 3D training scene and training items, the camera captures images of the first user, the processing device identifies the first user in the images, further identifies various joints of the body, and obtains the body movements of the first user based on the position of each joint.

[0039] The performance evaluation module assesses the training task achievement based on the first user's body movements. Specifically, it determines the similarity between the training item's body movements and the user's body movements at the same time intervals, evaluates the first user's training task achievement based on the similarity, and displays the results through the display module. For example, it calculates the average similarity of all body movements for the training item based on the similarity of each body movement; if the average similarity is higher than 90%, the training task achievement is considered excellent.

[0040] The login module is also used to verify the identity of the second user. Once verification is successful, control permissions are assigned to the second user. In this embodiment, the second user is a doctor.

[0041] The display module is also used to create a virtual camera in the 3D training scene, receive view control commands from a second user, adjust the position of the virtual camera in the 3D training scene according to the view control commands, and acquire and display the image of the virtual 3D training scene through the virtual camera. In this embodiment, the display module is a tablet computer.

[0042] The task generation module is also used to receive adjustment information from a second user and, based on this information, adjust the 3D training scene and / or training items in the training task. For example, changing the training scene, changing the training items, or changing both the training scene and training items simultaneously.

[0043] The effect evaluation module is also used to determine whether the similarity between the training item's limb movements and the first user's limb movements is within a preset range. If it is, a recording instruction is generated. In this embodiment, the training item for similarity judgment needs to have a label that includes the type of autonomous completion, and the preset range is 60%-80%.

[0044] The display module is also used to record and store the video of the first user's body movements via a virtual camera according to the recording instructions.

[0045] Example 2

[0046] The difference between this embodiment and embodiment one is that in this embodiment, the VR interaction module is also used to capture the body movements of the second user, determine the part of the body that the second user and the first user are in contact based on the body movements of the second user, and send the part of the body in contact to the display module.

[0047] View control commands include automatic mode, fixed mode, and free mode;

[0048] The display module is also used to determine whether the current view control command is in automatic mode. If so, it directs the virtual camera's view towards the part of the limb in contact. Specifically:

[0049] The VR interaction module is also used to capture the head movements of the first user, control the viewpoint of the virtual character based on the head movements of the first user, and determine whether the viewpoint of the virtual character is facing the part of the body that is in contact. If it is facing the part of the body that is in contact, the VR interaction module is also used to collect the voice data of the first user and send the voice data to the display module.

[0050] The display module is also used to identify the decibel level of the voice data and determine the field of view based on the decibel level. In this embodiment, three decibel levels—low, medium, and high—are defined, corresponding to three field of view levels: far-field, medium-field, and close-up. Specifically, the low decibel level corresponds to the far-field. When the second user (i.e., the doctor) assists the first user (i.e., the patient) in rehabilitation training, the decibel level of the first user's voice data reflects the patient's reaction to the limb contact area (i.e., the area being assisted in rehabilitation training). The higher the decibel level, the greater the patient's reaction to the training item, requiring closer attention. In this embodiment, the far-field view includes the complete virtual avatar of the first user, with the limb contact area located in the center of the image; the medium-field view includes at least half of the second user's virtual avatar, with the limb contact area located in the center of the image; and the close-up view is a close-up of the limb contact area.

[0051] The task generation module is also used to record each training task of the first user and to determine the familiarity of the current training item based on the recorded training tasks. In this embodiment, from 0 to 10 times, the more times the training item has been trained, the higher the familiarity. After reaching 10 times, the familiarity is 100% and no longer changes.

[0052] The display module is also used to obtain the familiarity of the current training item from the task generation module, and the similarity between the user's training item limb movements and the user's limb movements. Based on the familiarity and similarity, the switching delay is determined. In this embodiment, the formula for calculating the switching delay T1 is:

[0053] T1 = T0 + aP + bS

[0054] Where T0 is the initial delay, which is 1 second in this embodiment, P is familiarity, S is similarity, and a and b are the weights of familiarity and similarity, respectively. In this embodiment, the higher the familiarity and similarity, the greater the switching delay. By setting a switching delay, frequent switching of perspectives is avoided, which could interfere with the doctor's observation.

[0055] The VR interaction module is also used to capture the head movements of the second user, determine whether the first user's viewpoint is facing the display module based on the first user's head movements, generate the first user's head orientation information, and send it to the display module.

[0056] During the switching delay, if the head orientation information indicates that the first user's viewpoint is not facing the display module, the display module is also used to obtain the second user's body movements from the VR interaction module and determine whether the second user's body movements are paused. If paused, the virtual camera's viewpoint is aligned with the body part in contact after the switching delay ends. If not paused, the virtual camera's viewpoint remains unchanged after the switching delay ends. When a doctor is performing complex rehabilitation training on a patient, if the doctor's body movements are not paused and the doctor is not looking at the display module, it indicates that the doctor does not need to understand the situation in the virtual scene viewed by the patient through the display module. If paused, it indicates that the doctor may need to understand the situation in the virtual scene, and in this case, the virtual camera's viewpoint is switched.

[0057] During the switching delay, if the head orientation information indicates that the first user's view is facing the display module, the display module also obtains the second user's body movements from the VR interaction module and determines whether the second user's body movements are paused. If paused, the virtual camera's view remains unchanged after the switching delay ends; if not paused, the virtual camera's view is aligned with the part of the body in contact after the switching delay ends. When the doctor looks at the display module to continuously monitor the virtual scene, and the body movements are paused, there is a higher probability that the doctor will manually control the view. In this case, the view is not switched to avoid conflict with the manual operation of medical staff. If the body movements are not paused, and the doctor does not currently need to manually switch, the virtual camera's view is automatically switched to help the doctor better understand the display of the part of the body in contact in the virtual scene.

[0058] The above are merely embodiments of the present invention. The invention is not limited to the fields covered by these embodiments. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are able to access all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A VR-based motor disorder limb rehabilitation auxiliary system for amyotrophic lateral sclerosis, characterized in that, include: The project creation module is used to create several 3D training scenarios and several training projects. The user login module is used to verify the identity of the first user and determine whether the first user is logging in for the first time. If so, it collects the first user's personal information. The task generation module is used to select 3D training scenarios and training items to generate training tasks based on the first user's personal information and preset training rules. The VR interaction module is used to obtain the corresponding 3D training scene and training items according to the training task, display the training items in the 3D training scene, and also to create virtual characters in the 3D training scene, capture the body movements of the first user, and synchronize the body movements of the first user to the virtual character. The effectiveness evaluation module is used to assess the achievement of the training task based on the first user's body movements. The login module is also used to verify the identity of the second user, and after successful verification, to assign control permissions to the second user. It also includes a display module, which is used to create a virtual camera in the 3D training scene, and to receive the view control instructions of the second user, adjust the view of the virtual camera in the 3D training scene according to the view control instructions, and acquire and display the image of the virtual 3D training scene through the virtual camera; The training program includes several body movements. The effect evaluation module is used to determine the similarity between the body movements of the training program and the user's body movements at the same time, and to evaluate the first user's training task achievement based on the similarity. The VR interaction module is also used to capture the body movements of the second user, determine the part of the body that the second user and the first user are in contact based on the body movements of the second user, and send the part of the body in contact to the display module. View control commands include automatic mode, fixed mode, and free mode; The display module is also used to determine whether the current view control command is in automatic mode. If so, it will point the virtual camera's view at the part of the body that is in contact with the body. The VR interaction module is also used to capture the head movements of the first user, control the viewpoint of the virtual character based on the head movements of the first user, and determine whether the viewpoint of the virtual character is facing the part of the body that is in contact. If it is facing the part of the body that is in contact, the VR interaction module is also used to collect the voice data of the first user and send the voice data to the display module. The display module is also used to identify the decibel level of the voice data and determine the scene type based on the decibel level of the voice data; it divides the voice data into three decibel levels: low, medium, and high, corresponding to three scene types: far-field, medium-field, and close-up. The task generation module is also used to record each training task of the first user and to determine the familiarity with the current training item based on the recorded training tasks. The display module is also used to obtain the familiarity of the current training item from the task generation module, as well as the similarity between the user's training item's limb movements and the user's limb movements. The switching delay is determined based on the familiarity and similarity, and the formula for calculating the switching delay is: ; wherein, is an initial delay, is set to 1 second, is familiarity, is similarity, a and b are weights of the familiarity and the similarity, respectively, and the higher the familiarity and the similarity, the greater the switching delay; The VR interaction module is also used to capture the head movements of the first user, determine whether the first user's viewpoint is facing the display module based on the head movements, generate the first user's head orientation information, and send it to the display module. During the switching delay, if the head orientation information indicates that the first user's viewpoint is not facing the display module, the display module is also used to obtain the second user's body movements from the VR interaction module and determine whether the second user's body movements are paused. If paused, the virtual camera's viewpoint is aligned with the body contact area after the switching delay ends. If not paused, the virtual camera's viewpoint is not changed after the switching delay ends. During the switching delay, if the head orientation information indicates that the first user's view is facing the display module, the display module is also used to obtain the second user's body movements from the VR interaction module and determine whether the second user's body movements are paused. If paused, the virtual camera's view will not be changed after the switching delay ends. If not paused, after the switching delay ends, point the virtual camera's view at the part of the body that is in contact.

2. The VR-based motor disorder limb rehabilitation assisting system of amyotrophic lateral sclerosis according to claim 1, characterized in that: The project creation module is also used to set scene labels for the created 3D training scene and to set project labels for the created training project; The training rules include the mapping relationship between personal information and preset training tasks, as well as the mapping relationship between training tasks and scene labels and project labels; The task generation module is also used to determine training tasks based on personal information, then determine scene labels and project labels based on the training tasks, randomly select a corresponding 3D training scene based on the scene label, and randomly select a corresponding training project based on the project label.

3. The VR-based motor disorder limb rehabilitation assistance system of amyotrophic lateral sclerosis according to claim 2, characterized in that: The task generation module is also used to receive adjustment information from the second user and adjust the 3D training scene and / or training items in the training task according to the adjustment information.

4. The VR-based motor disorder limb rehabilitation assisting system of amyotrophic lateral sclerosis according to claim 3, characterized in that: The effect evaluation module is also used to determine whether the similarity between the training item's limb movements and the first user's limb movements is within a preset range. If it is, a recording instruction is generated. The display module is also used to record and store the video of the first user's body movements via a virtual camera according to the recording instructions.

Citation Information

Patent Citations

  • Cerebral trauma upper limb dyskinesia rehabilitation system based on VR equipment

    CN114822760A