Training method and system for upper limb rehabilitation training
By generating personalized training graphics and dynamically adjusting the difficulty, the problem of monotonous movements in upper limb rehabilitation training is solved, improving the relevance and efficiency of training while ensuring safety.
Patent Information
- Application Number
- CN202510893434.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-30
- Publication Date
- 2025-10-17
AI Technical Summary
Existing upper limb rehabilitation training movements are single and cannot be combined with the actual situation of the user to carry out targeted training, resulting in mediocre training effects.
By collecting the user's joint motion angle values, personalized training graphics are generated. Combining the user's target joint and target motion angle values, the difficulty and size of the training graphics are dynamically adjusted to ensure that the training takes place within the user's activity space.
It improves the pertinence and efficiency of rehabilitation training, mobilizes users' training enthusiasm, avoids insufficient or excessive training, and ensures the safety of training.
Smart Images
Figure CN120789601A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of rehabilitation equipment, and more particularly to a training method and system for upper limb rehabilitation training. Background Art
[0002] For patients with limited upper limb mobility, clinicians or rehabilitation therapists usually complete the assessment of the patient's upper limb function through scale assessment, instrument measurement, etc., and then determine the user's training movements (such as lifting, stretching, etc.) based on the assessment results; during training, patients use upper limb training equipment (such as Figure 3 Upper limb training can be achieved by completing these movements actively (patients actively perform the movements, and the upper limb training device may provide some assistance or resistance) or passively (the upper limb training device completely drives the patient to perform the training). However, these movements are relatively simple and not targeted, and cannot be combined with the user's actual training situation. Summary of the Invention
[0003] In order to solve the technical problem that the above-mentioned training movements are single and cannot be combined with the actual situation of the user for training, the present invention provides solutions in the following aspects.
[0004] In the first aspect, the present invention provides a training method for upper limb rehabilitation training, which is applied to upper limb rehabilitation training equipment, including: collecting the activity angle values of the joints when the user performs multiple preset evaluation actions; determining the target joints and target activity angle values to be trained; based on the target joints and the target activity angle values, generating a training graphic for the user to draw; and outputting the training graphic to assist the user in training the target joints.
[0005] Furthermore, based on the target joint and the target activity angle value, a training graphic for the user to draw is generated, including: searching for a target graphic that meets the set conditions from a preset graphic database, the set conditions including: when the user draws the target graphic, the user needs to use the target joint and an action similar to or the same as the evaluation action corresponding to the target activity angle value; adjusting the size of the target graphic according to the target activity angle value to obtain the training graphic.
[0006] Furthermore, the setting condition also includes: if the target joint is one joint, searching for the target graph from a two-dimensional graph; if the target joint is multiple joints, searching for the target graph from a three-dimensional graph.
[0007] Furthermore, during the training process, the training method further includes: recording the completion time of the user drawing the training graphic, and adjusting the difficulty of drawing the training graphic according to the completion time.
[0008] Furthermore, adjusting the drawing difficulty of the training graphic according to the completion time includes: determining a reference time according to the training graphic; and increasing the size of the training graphic or changing the training graphic in response to the completion time being less than the reference time.
[0009] Furthermore, matching the reference time according to the training pattern includes: determining the reference time according to a preset mapping relationship between the reference pattern and the reference time; adjusting the reference time according to a size difference between the training pattern and the reference pattern, and the reference time is positively correlated with the size difference.
[0010] Further, when the training graphic is a three-dimensional graphic, the reference time includes a horizontal reference time, and the completion time includes a horizontal completion time; in response to the completion time being less than the reference time, the size of the training graphic is increased; including: if the horizontal completion time is less than the horizontal reference time, the horizontal length of the training graphic is increased.
[0011] Furthermore, after collecting the activity angle value, the training method further includes: generating the activity space of the user according to the activity angle value, wherein the activity space represents the range in which the user can move and is used to limit the size of the training graph.
[0012] Furthermore, the training method further includes: generating a training report in response to the end of training, wherein the training report includes an activity angle value, an evaluation object, and a training graph.
[0013] In a second aspect, the present invention provides a training system for upper limb rehabilitation training, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the training method for upper limb rehabilitation training described in the first aspect is implemented.
[0014] The beneficial effects of the present application are that: by matching different training graphics according to the target joint and the target activity angle value of the user, the user can use the target joint when training by drawing these training graphics, and make the same or similar action as the evaluation action corresponding to the target activity angle value, so as to improve the situation that the target joint of the user is limited in a specific direction, and at the same time, the enthusiasm of the user in training is also mobilized through the way of drawing graphics; and since the training graphics are generated according to the actual situation of the user, the user can get targeted training, so as to improve the efficiency of rehabilitation and avoid the problem that the training effect is general caused by using a single action; by dynamically adjusting the drawing difficulty according to the completion time of the user in drawing the training graphics, the user can always train in a suitable training difficulty, so as to avoid the situation of insufficient training or excessive training; in addition, the generated graphics are in the activity space of the user, so as to ensure the safety of the user in training. BRIEF DESCRIPTION OF DRAWINGS
[0015] Figure 1 is a flow chart schematically showing a training method for upper limb rehabilitation training according to an embodiment of the present application;
[0016] Figure 2 is a schematic view schematically showing an activity space according to an embodiment of the present application;
[0017] Figure 3 is a schematic view schematically showing an upper limb rehabilitation device in the prior art;
[0018] Figure 4 is a schematic view schematically showing a training graphic according to an embodiment of the present application;
[0019] Figure 5 is a structural block diagram schematically showing a training system for upper limb rehabilitation training according to an embodiment of the present application. DETAILED DESCRIPTION
[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.
[0021] The specific embodiments of the present application will be described in detail below with reference to the drawings.
[0022] Figure 1 is a flow chart schematically showing a training method for upper limb rehabilitation training according to an embodiment of the present application;
[0023] In the prior art, when training the upper limbs, the patient is asked to perform some simple and single actions according to the assessment by the rehabilitation therapist or the treating doctor, which cannot fully adjust to the specific condition of the patient, resulting in a general training effect.
[0024] To this end, in a first aspect, the present application provides a training method for upper limb rehabilitation training. As shown in the accompanying drawings, the method of the present application comprises the following steps. Figure 1
[0025] Before the training, the user needs to wear 3D glasses (in an optional embodiment, AR glasses can also be used), through which the user can see a virtual scene generated by the system, in which the user can see virtual training graphics. It should be noted that the upper limb training device can be an existing device as shown in Figure 3
[0026] S101, collecting the activity angle value of the joint when the user performs a plurality of preset actions.
[0027] In this embodiment, the key joints involved in the upper limbs include the shoulder joint, the elbow joint, the ulnar joint and the wrist joint. The user can select one or more joints to be evaluated according to actual needs. If not selected, the above four joints are evaluated by default.
[0028] In response to receiving the evaluation instruction, the evaluation actions corresponding to the joints selected by the user (hereinafter referred to as the joints to be evaluated) are displayed (after the user performs the wearing preparation, the user performs these evaluation actions in sequence). Each joint corresponds to a set of evaluation actions and a normal range of motion corresponding to the evaluation action. Specifically, a set of evaluation actions includes a plurality of evaluation actions, and each evaluation action corresponds to a normal range of motion (the range of motion of the joint when a normal person performs the evaluation action can be obtained by a hospital system, etc.).
[0029] Take the shoulder joint as an example for specific description. The evaluation actions corresponding to the shoulder joint can include: forward flexion (corresponding to a normal range of motion of 70°-90°), forward flexion and elevation (corresponding to a normal range of motion of 150°-170°), abduction (corresponding to a normal range of motion of 80°-90°), adduction (corresponding to a normal range of motion of 20°-40°), internal rotation (corresponding to a normal range of motion of 45°-70°), and external rotation (corresponding to a normal range of motion of 45°-60°), etc.
[0030] After the user performs the displayed evaluation action, the activity angle value (taking the maximum value) of the joint to be evaluated when the user performs the evaluation action is collected. Thus, a plurality of angle activity values of each joint to be evaluated are obtained.
[0031] In one embodiment, the method of the present application further comprises: drawing and displaying the activity space of each joint to be evaluated of the user according to the activity angle values of the joint to be evaluated by the user (which can be displayed separately, i.e. one joint to be evaluated corresponds to one activity space, or can be combined into one activity space representing all joints to be evaluated), which represents the range of the joint to be evaluated of the user (e.g. the activity space shown). Figure 2
[0032] In the present embodiment, the activity space is displayed in a virtual form through 3D glasses, so that the user can intuitively and explicitly know the range of the joint to be evaluated. In an alternative embodiment, a normal activity space (i.e. the activity space corresponding to a normal person) can also be added, and the two activity spaces can be displayed in the same space, wherein the activity space of the user can be displayed in solid line, and the activity space corresponding to the normal person can be displayed in dotted line. By displaying the activity spaces of the user and the normal person, the user can further explicitly know the restriction of the joint to be evaluated in a certain direction (the greater the distance between the corresponding positions of the activity space in solid line and the activity space in dotted line, the more serious the restriction of the joint to be evaluated in the direction).
[0033] In an alternative embodiment, the activity space described above can also be displayed in the form of a report, which can be displayed in the form of a table or a two-dimensional graph.
[0034] S102, determining the target joint to be trained and the target activity angle value.
[0035] In one embodiment, the user can select one or more joints to be trained (i.e. the target joint) and the activity angle value to be improved (i.e. the target activity angle value, corresponding to an evaluation action) according to the actual needs based on the activity space or the report displayed above.
[0036] In an alternative embodiment, the system can also automatically select. Specifically, if the user only evaluates one joint, the joint is directly taken as the target joint, and all the activity angle values out of the normal activity range (abnormal activity angle values) are taken as the target activity angle values when determining the target activity angle values. If the user evaluates multiple joints, the ratio of the number of abnormal activity angle values to the total number of activity angle values can be calculated (for example, the evaluation actions of the shoulder joint have 10, of which 5 evaluation actions do not meet the standard / activity restriction, and the ratio is 0.5), and then the joint corresponding to the largest ratio is taken as the target joint, and the abnormal activity angle values of the joint are taken as the target activity angle values; or the two joints with the largest ratio are taken as the target joints, and the abnormal activity angle values of the two joints are taken as the target activity angle values; or the above two situations are output for the user to select.
[0037] S103, generating a training graph for the user to draw based on the target joint and the target activity angle value.
[0038] According to the evaluation action corresponding to the target joint and the target activity angle value, a target graph suitable for the user is found from a preset graph database according to a set condition. In this embodiment, the set condition includes: condition one: the user uses the target joint when drawing the target graph, and makes a similar or same action as the evaluation action; condition two: if the user trains only one joint, the target graph is found from a two-dimensional graph; if the user trains multiple joints, the target graph is found from a three-dimensional graph. That is, the graph that meets the above two conditions is found from the graph database.
[0039] In one embodiment, the data structure in the graph database can be as shown in the following table.
[0040] Joint name Evaluation action Figure number Shoulder joint Evaluation action 1 Figure 1, Figure 2, Figure 5, Figure 8 Shoulder joint Evaluation action 2 Figure 1, Figure 3, Figure 5 Shoulder joint Evaluation action 3 Figure 3, Figure 5, Figure 9, Figure 12, Figure 22 Elbow joint Evaluation action 1 Figure 1, Figure 7, Figure 6 ... ... ...
[0041] According to the above table, one graph can train multiple joints and multiple evaluation actions can be made when drawing the graph, for example, the graph 1 in the above table. Figure 1 In this embodiment, the training graph can include a circle, a sphere, a pentagram, a cuboid, a moon in different periods, etc.
[0042] By matching the target graph according to the target joint and the target activity angle value, it can be ensured that the user can fully train the target joint when drawing the target graph, and the activity degree of the target joint in the corresponding direction can be improved, thereby improving the efficiency of rehabilitation; at the same time, by using the drawing graph, the enthusiasm of the user in training can be mobilized.
[0043] In one embodiment, if multiple target graphs are matched, they can be displayed in the interface, and the user can select one according to actual needs, or the system selects the target graph with the lowest drawing difficulty from the multiple target graphs, wherein the drawing difficulty can be determined according to the time, shape or structure required for drawing the target graph; for example, the more time required, the greater the drawing difficulty; the more complex the shape or structure, the greater the drawing difficulty, for example, the drawing difficulty of the pentagram is greater than that of the square; if only one target graph is matched, the target graph is directly used as the training graph required by the user in subsequent training.
[0044] In other optional embodiments, a mapping relationship between joints and graphs can also be established (for example, the shoulder joint corresponds to the two-dimensional graph 1, the shoulder joint + elbow joint corresponds to the three-dimensional graph 3, etc.), and then the shape and dimension of the target graph are determined according to the mapping relationship. In addition, the user can also select the graph to be trained by himself.
[0045] Further, after obtaining the target figure, the size of the target figure is adjusted according to the target angle activity value (in optional embodiments, the angle can also be adjusted), so as to obtain a training figure used by the user in subsequent training. Specifically, the target activity angle value (the direction of the upper limb activity when performing the evaluation action) is classified into horizontal direction, vertical direction and depth direction, and the minimum value of the three directions is taken as the length of the horizontal direction, the length of the vertical direction and the length of the width direction of the target figure respectively (if it is a two-dimensional figure, only the minimum value of the horizontal direction and the vertical direction is taken as the length of the horizontal direction and the length of the vertical direction of the target figure respectively). For example, the abduction and elevation of the shoulder joint (evaluation action) corresponds to the vertical direction, so the activity angle value of the abduction and elevation should be classified into the vertical direction.
[0046] In one embodiment, after determining the length (size) of each direction, the training figure with the drawing direction prompt is generated according to the size. In other optional embodiments, the drawing direction prompt can also not be displayed.
[0047] S104, output the training figure to assist the user in training the target joint.
[0048] In one embodiment, the output training figure needs to be limited within the activity space of the user (the size of the figure cannot exceed the size of the activity space), so as to avoid safety problems caused by excessive activity of the user during training.
[0049] The user can clearly see the shape, size and drawing order of the training figure through the 3D glasses, and then starts drawing from the starting point. When the entire figure is drawn, it is recorded as one time of training completion. Through the drawing of the training figure, the target joint of the user can be trained specifically, so as to improve the rehabilitation efficiency of the training.
[0050] In one embodiment, the method of the present application further comprises: recording the completion time of the user drawing the training figure, and adjusting the drawing difficulty of the training figure according to the completion time. Specifically, the completion time of the user drawing the figure is recorded (recorded by the mechanical arm, the mechanical arm can record the trajectory drawn by the user, so as to determine the completion time of the drawing), and the reference time is determined according to the training figure; it is judged whether the completion time is less than the reference time, if yes, the drawing difficulty of the training figure is increased; if not, the current drawing difficulty of the training figure is maintained.
[0051] In one embodiment, in addition to manual setting, the method for determining the reference time can also be automatically generated: first, obtain the completion time of a normal person drawing each reference graphic (the size is pre-set), and use the completion time as the reference time of the corresponding reference graphic, thereby establishing a mapping relationship between the reference graphic and the reference time (that is, the training graphic corresponds to a reference time). Then, calculate the size difference between the reference graphic and the training graphic, multiply the size difference by the reference graphic reference time to obtain the user's final reference time. For example, the user's training graphic is a two-dimensional graphic with a vertical length of H2 and a horizontal length of W2. The corresponding reference graphic has a vertical length of H1 and a horizontal length of W1. The reference time corresponding to the reference graphic is t2. Then, the calculation expression for the user's final reference time t1 is:
[0052]
[0053] It should be noted that the horizontal length refers to the distance from the leftmost end point to the rightmost end point of the figure (such as Figure 4 Similarly, the vertical length refers to the distance from the top end to the bottom end of the figure (such as Figure 4 Y shown); the length in the depth direction refers to the distance from the front end point to the end of the figure. In addition, the shape of the reference figure is consistent with the shape of the user's training figure, or the training figure can be obtained by changing the horizontal length, vertical length and / or width length of the reference figure.
[0054] If the user's drawing time is less than the benchmark time, it indicates that the current drawing difficulty is low and the user cannot receive effective training. Therefore, the drawing difficulty of the training pattern can be appropriately increased to ensure that the user always trains within the appropriate difficulty level. In one embodiment, the training difficulty can be increased by changing the shape (i.e., changing the training pattern) or size of the training pattern.
[0055] Specifically, if multiple target graphics are found in S103, a graphic with a greater drawing difficulty than the current training graphic is searched from these target graphics as a new training graphic (only the shape is changed, the size remains unchanged). If multiple target graphics are not found, the training difficulty is changed by adjusting the size of the training graphic. Specifically, if the user's training graphic is a two-dimensional graphic, the size of the training graphic can be increased according to the set length. For example, if the user's training graphic is a rectangle, the length and width of the rectangle can be increased by 10 cm (the set length).
[0056] If the user's training graph is a three-dimensional graph, record the horizontal direction (x direction) completion time (the total time of the mechanical arm drawing in the horizontal direction according to the motion trajectory), the vertical direction (y direction) completion time, and the depth direction (z direction) completion time; determine whether the horizontal direction completion time is less than the corresponding reference time (i.e., the horizontal direction reference time, which can be artificially set or generated by the system), if yes, increase the length of the training graph in the horizontal direction; if no, keep the current length of the training graph in the horizontal direction; similarly, determine whether the vertical direction completion time is less than the corresponding reference time, if yes, increase the length of the training graph in the vertical direction; if no, keep the current length of the training graph in the vertical direction; similarly, determine whether the depth direction completion time is less than the corresponding reference time, if yes, increase the length of the training graph in the depth direction; if no, keep the current length of the training graph in the depth direction.
[0057] After the user completes each drawing, the drawing difficulty of the training graph is adjusted according to the completion time of the drawing, ensuring that the user always performs effective training within a suitable training difficulty, thereby improving the efficiency of the user's rehabilitation.
[0058] Figure 5 is a schematic structural block diagram of a training system for upper limb rehabilitation training according to the present embodiment.
[0059] In a second aspect, the present application also provides a training system for upper limb rehabilitation training. As shown in Figure 5 The training system includes a processor and a memory, and the memory stores computer program instructions which, when executed by the processor, implement a robot inspection method for a static scene according to the first aspect of the present application.
[0060] The training system also includes a communication interface and other components well known to those skilled in the art, the settings and functions of which are known in the art, and thus will not be described here.
[0061] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise retained by such a computer-readable medium.
[0062] In this specification, "multiple" means at least two, such as two, three, or more, unless otherwise specifically defined. Furthermore, the steps of the above method are divided for clarity of description only. During implementation, they can be combined into a single step, or some steps can be split into multiple steps, as long as they share the same logical relationship.
[0063] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.
Claims
1. A training method for upper limb rehabilitation training, applied to upper limb rehabilitation training equipment, characterized in that: include: Collect the joint angle values when the user performs multiple preset evaluation actions; Determine the target joints and target activity angles that need to be trained; Based on the target joint and the target activity angle value, generating a training graphic for the user to draw; The training graphic is output to assist the user in training the target joint.
2. The training method for upper limb rehabilitation training according to claim 1, characterized in that: Based on the target joint and the target activity angle value, a training graphic for the user to draw is generated, including: Searching a target graphic that meets set conditions from a preset graphic database, wherein the set conditions include: when drawing the target graphic, the user needs to use the target joint and an action that is similar to or the same as the evaluation action corresponding to the target activity angle value; The size of the target pattern is adjusted according to the target activity angle value to obtain the training pattern.
3. The training method for upper limb rehabilitation training according to claim 2, characterized in that: The setting condition further includes: if the target joint is one joint, searching the target graph from a two-dimensional graph; if the target joint is multiple joints, searching the target graph from a three-dimensional graph.
4. The training method for upper limb rehabilitation training according to claim 1, characterized in that: The training process also includes: recording the completion time of the user drawing the training graphic, and adjusting the drawing difficulty of the training graphic according to the completion time.
5. The training method for upper limb rehabilitation training according to claim 4, characterized in that: Adjusting the drawing difficulty of the training graphic according to the completion time includes: determining a benchmark time according to the training graph; In response to the completion time being less than the reference time, the size of the training pattern is increased, or the training pattern is modified.
6. The training method for upper limb rehabilitation training according to claim 5, characterized in that: Matching a reference time according to the training pattern includes: Determining the reference time according to a preset mapping relationship between a reference pattern and a reference time; The reference time is adjusted according to the size difference between the training pattern and the reference pattern, and the reference time is positively correlated with the size difference.
7. The training method for upper limb rehabilitation training according to claim 5, characterized in that: When the training graph is a three-dimensional graph, the reference time includes a horizontal reference time, and the completion time includes a horizontal completion time; In response to the completion time being less than the reference time, increasing the size of the training pattern; including: if the horizontal completion time is less than the horizontal reference time, increasing the horizontal length of the training pattern.
8. The training method for upper limb rehabilitation training according to claim 1, characterized in that: After the activity angle value is collected, the method further includes: generating an activity space of the user according to the activity angle value, where the activity space represents a range within which the user can move.
9. The training method for upper limb rehabilitation training according to claim 1, characterized in that: Also includes: In response to the end of the training, a training report is generated, the training report including the activity angle value, the evaluation object, and the training graph.
10. A training system for upper limb rehabilitation training, characterized in that: It comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the training method for upper limb rehabilitation training according to any one of claims 1 to 9 is implemented.