MCI intervention system based on virtual reality cognitive motor training difficulty dynamic adjustment

Abstract

The application discloses a kind of MCI intervention systems based on virtual reality cognitive motor training difficulty dynamic adjustment, including upper limb movement task prototype module, upper limb movement task dynamic difficulty adjustment module, virtual cognitive task prototype module and virtual cognitive task dynamic difficulty adjustment;System introduces a kind of dynamic difficulty adjustment algorithm based on Pareto frontier, the relationship between task intensity and participant performance is modeled, from which the possible combination of a variety of task difficulties and their corresponding trade-offs are evaluated, thereby achieving dynamic optimization adjustment of task difficulty.Finally, through the randomized controlled study carried out in the cooperative hospital, the significant effect of the system in improving cognitive ability and upper limb motor function is verified.The application provides an innovative system that combines cognitive and motor training and provides personalized intervention through a dynamic difficulty adjustment mechanism, providing an effective path for health management and cognitive function improvement of the elderly.

Description

Technical Field

[0001] This invention relates to the field of virtual reality intervention technology for cognitive impairment in the elderly in non-pharmacological interventions, specifically an MCI intervention system based on dynamic adjustment of the difficulty of virtual reality cognitive motor training. Background Technology

[0002] Alzheimer's disease is a global challenge and economic burden. The number of people with Alzheimer's is rapidly increasing in aging societies. The World Health Organization has called on countries to develop strategies to reduce the risk of Alzheimer's, including promoting ongoing research to optimize brain health and specialized prevention of brain diseases. Fortunately, mounting evidence suggests that approximately 40% of Alzheimer's cases are attributable to lifestyle-related risk factors, therefore Alzheimer's is considered preventable, and reducing the risk now appears achievable.

[0003] Currently, in addition to traditional psychological and cognitive training and physical training, virtual reality technology, as an innovative adjunctive therapy, provides a more intuitive and engaging intervention for elderly patients with cognitive impairment by constructing multi-sensory, personalized, and interactive virtual environments, effectively enhancing patient participation. Recent studies have explored combining virtual environments with various non-pharmacological intervention strategies (such as cognitive games, memory therapy, and music therapy), and using devices like Microsoft Kinect, large screens, computers, seatbelts, and treadmills to simulate daily life and physical activities, aiming to improve patients' cognitive function and physical health. Although these studies have shown initial positive results, they have not yet been widely applied to MCI patients due to issues such as high training duration requirements, insufficient personalization, and complex equipment configuration. Furthermore, existing virtual reality intervention programs often adjust difficulty linearly based on participants' interactive performance, neglecting the possibility of enhancing participants' abilities through more challenging settings, resulting in a relatively simplistic dynamic task adjustment mechanism. Therefore, developing an intervention program with a flexible task difficulty adjustment mechanism, that is simple, efficient, highly personalized, and easily scalable to improve cognitive and physical function is of significant practical importance. Summary of the Invention

[0004] This invention proposes a virtual reality cognitive-motor intervention system based on dynamic difficulty adjustment. Through refined task design, real-time difficulty adjustment, and integration with portable devices, it enhances the intervention effect and adaptability to individual differences. This intervention system is designed for seated operation and has broad applicability in various scenarios such as home, community, and nursing homes.

[0005] The technical system of the present invention is as follows:

[0006] A virtual reality cognitive motor training difficulty dynamic adjustment MCI intervention system includes an upper limb motor task prototype module, an upper limb motor task dynamic difficulty adjustment module, a virtual cognitive task prototype module, and a virtual cognitive task dynamic difficulty adjustment module.

[0007] Upper limb movement task prototype module: Based on the requirements, the upper limb movement task is determined. The design process of this task covers upper limb movement action design, interaction method and virtual environment evaluation.

[0008] The upper limb motor task dynamic difficulty adjustment module adopts a dynamic difficulty adjustment algorithm based on Pareto optimality theory. It generates a set of Pareto optimal solutions by modeling the difficulty of the upper limb motor task (intervention intensity) and the participants' motor performance (intervention performance). Then, by analyzing the trade-off characteristics of each system in the generated solution set, the most suitable solution is selected so that the task parameters or difficulty can be adjusted accordingly.

[0009] Virtual cognitive task prototype module: Based on requirements, the virtual cognitive task is determined. The design process of this task covers cognitive domain task design, interaction methods and style layout evaluation.

[0010] The dynamic difficulty adjustment of virtual cognitive tasks adopts a dynamic difficulty adjustment algorithm based on Pareto optimality theory to improve the efficiency of difficulty adjustment of cognitive tasks. The algorithm differs only in the objective function in each cognitive task, while the rest of the operation process is consistent with that of upper limb motor tasks.

[0011] The system and the prototype of the upper limb movement task: The upper limb movement task includes elbow flexion and extension, upper limb elevation and shoulder rotation; the elbow flexion and extension is performed in a four-beat cycle, while the upper limb elevation and shoulder rotation are designed in an eight-beat cycle.

[0012] The system described above, specifically the dynamic difficulty adjustment of upper limb motor tasks, defines two decision objective functions: intervention intensity and intervention performance. Intervention intensity is related to the difficulty of the task, while intervention performance is closely related to the participant's motor performance. By optimizing these two objectives, effective adaptation and improvement of the participant's abilities are achieved. The intervention intensity formula is:

[0013]

[0014] Among them, I i Let v be the standardized value of the intensity of the i-th intervention. xi v yi and v zi Let I represent the velocities of the ball in the x, y, and z axes respectively at the i-th time, and let min(I) and max(I) represent the minimum and maximum intervention intensities respectively. i The higher the value, the greater the difficulty;

[0015] The intervention performance formula is:

[0016] P i =1-[λ×(1-Accuracy)] i )+(1-λ)×Time i ]

[0017] Among them, P i For the i-th intervention, Accuracy i and Time i P represents the participant's accuracy and standardized time in the i-th upper limb task, respectively. i The higher the value, the better the participant's performance;

[0018] Secondly, a set of candidate solutions is generated in the search space by using a random algorithm. Each candidate solution is a point in the search space, consisting of a set of values ​​for decision variables.

[0019] Next, for each candidate solution, its mapping value in the definition of the objective function is calculated. Meanwhile, during the practice phase before each intervention, the intervention intensity generated by each candidate solution is applied to the participants' practice to generate the target value of the intervention performance.

[0020] Then, to ensure the effectiveness of the solution sorting within the Pareto front and reduce computational complexity, an efficient non-dominated sorting is introduced. In this process, all solutions in the feasible solution set are sorted in ascending order based on the intervention strength of the first objective value. If two or more solutions have the same first objective value, they are sorted in ascending order based on the intervention performance of the second objective value. If all objective values ​​of two or more solutions are the same, their sorting can be arbitrary. Through this sorting process, the efficient non-dominated sorting can gradually allocate solutions to the Pareto front, thereby optimizing the decision-making process.

[0021] Finally, a method for measuring the trade-off information of a pair of non-dominated solutions is introduced. By calculating the trade-off information of each solution on the frontier, one of the solutions is selected as the new game level. The formula is as follows:

[0022]

[0023] Among them, F m (v i ) and F m (v j These are solutions for system v. i and v j The value of the m-th objective function is obtained. and These are the maximum and minimum values ​​of the m-th objective function in the candidate solution system;

[0024] Furthermore, relative to other solutions on the optimal frontier in the non-dominant solution set S, any solution v i The trade-off value can be given by the following formula:

[0025]

[0026] Among them, v i and v j It is a solution in the non-dominant solution set S that is mutually indomitable, μ(v i ,S) indicates using v i Replace any solution v in the solution set S j The minimum improvement resulting from a decrease in a certain indicator.

[0027] The virtual cognitive task includes three virtual cognitive tasks: the bin test, used to train executive function; the working memory test, used to improve memory ability; and the depth perception test, used to train spatial localization ability.

[0028] Bin Test: Participants are required to move a specified number of virtual blocks from one compartment to another, with their hands passing through the partition in the middle. The test has two extended versions: the first requires participants to place the virtual blocks they grab into the corresponding areas according to their colors; the second requires participants to place the blocks they grab into the white areas row by row in sequence, thereby improving their task organization and execution capabilities.

[0029] Working Memory Test: This task aims to assess a participant's ability to process, manipulate, and store information in a short period of time. Participants first need to memorize the locations of a series of objects. These objects then disappear, and the system randomly presents one of the objects. Participants must accurately place it back in its original position. This process is repeated until all objects are correctly placed. If a participant's error rate exceeds 2 / 3 in three consecutive tests, the test will be terminated.

[0030] Depth Perception Test: This test stimulates the subject's spatial localization and executive abilities through multiple white balls in a virtual environment. Participants must click the balls in either a near-far or near-far order, and the system records the clicking order and reaction time. The reaction time consists of the interval between each click and is ultimately used to assess the subject's cognitive performance.

[0031] The system and the dynamic difficulty adjustment of the virtual cognitive task: During the intervention process of the virtual cognitive task, the dynamic adjustment of the task difficulty is similar to that of the upper limb motor task, and both need to be optimized in real time according to the individual performance of the participants; a dynamic difficulty adjustment algorithm based on Pareto optimality theory is adopted to improve the efficiency of difficulty adjustment of the cognitive task. The algorithm differs only in the objective function in each cognitive task, and the rest of the operation process is consistent with that of the upper limb motor task.

[0032] The system described above sets objective functions for three cognitive tasks, including objective functions for virtual bin testing, working memory testing, and depth perception testing.

[0033] The objective function of the virtual bin test in the aforementioned system is:

[0034] In this task, participants must move a specified number of blocks from one side of a cubicle to the other as efficiently as possible without a time limit. The number of blocks in the task will be dynamically adjusted based on the participants' completion time in the previous task to ensure the difficulty matches their ability level. Therefore, the objective function is defined as:

[0035]

[0036] in, Let be the number of blocks dragged and dropped in the i-th iteration, with a value ranging from [30, 31, ..., 80]. and Let be the initial and end times of the i-th drag-and-drop operation.

[0037] The system described above, and the objective function of the working memory test described above:

[0038] In this task, the intervention intensity was defined as a composite measure of the number of items and the correlation between items; meanwhile, intervention performance was evaluated based on two key performance indicators: the participants' item recall accuracy and task completion time; the objective function was defined as:

[0039]

[0040] in, Let be the number of items in the i-th iteration, with values ​​ranging from [3, 4, ..., 8]. For the correlation between items in the i-th iteration, N i To correctly recall the number of items, Let i be the standardized time for the i-th item recall.

[0041] The system described above, and the objective function of the depth perception test described above:

[0042] In this task, adjustments to the ball density and depth directly affect the difficulty level for participants searching for and selecting balls in the virtual environment; meanwhile, intervention performance is evaluated based on accuracy and completion time; therefore, the objective function is defined as:

[0043]

[0044] in, Let be the number of balls in the i-th iteration, with values ​​ranging from [3, 4, ..., 8]. Let be the depth distance at the i-th time, with a value range of [10, 11, ..., 60]. For the accuracy of clicking the ball, Standardize the time for clicking the ball.

[0045] The beneficial effects of this invention are:

[0046] This invention proposes a virtual reality cognitive-motor intervention strategy based on dynamic difficulty adjustment, aiming to improve intervention effectiveness and enhance adaptability to individual differences. This strategy combines three cognitive training exercises with three upper limb motor tasks to comprehensively train the cognitive and motor functions of the elderly. By introducing a dynamic difficulty adjustment algorithm based on Pareto optimality theory, the intervention process can be comprehensively evaluated based on participant performance and intervention intensity, dynamically optimizing the training system and selecting the optimal system from the Pareto optimal solution set. This method effectively achieves personalized adjustment of training difficulty, enhancing participant enthusiasm and participation while maximizing intervention effectiveness. The results of this invention provide important reference for the prevention and management of cognitive impairment in the elderly, demonstrating the application potential of personalized intervention in improving the well-being of the elderly. Attached Figure Description

[0047] Figure 1 This is a schematic diagram illustrating the collaborative design and development process of the intervention system of this invention;

[0048] Figure 2 This is a schematic diagram illustrating the decomposition and execution sequence of upper limb movements based on a seated posture according to the present invention.

[0049] Figure 3 These are schematic diagrams of virtual environments based on different styles according to the present invention; (a) urban environment; (b) hospital environment; (c) natural environment; (d) fitness environment;

[0050] Figure 4 This is a schematic diagram of the Pareto-based dynamic difficulty adjustment algorithm of the present invention; (a) defining the objective function; (b) generating a candidate solution set; (c) evaluating the objective function; (d) non-dominated sorting; (e) weighing the value of non-dominated solutions;

[0051] Figure 5 The diagrams show three different arrangements of the target area for the test based on the bins in this invention: (a) 4×4 arrangement; (b) 3×3 arrangement; (c) 2×2 arrangement.

[0052] Figure 6 The diagram illustrates the performance of participants on different tasks during a 12-week intervention using the intervention system proposed in this invention; (a) elbow flexion and extension; (b) upper limb elevation; (c) shoulder circling; (d) box test; (e) working memory; (f) depth perception. Detailed Implementation

[0053] The present invention will be described in detail below with reference to specific embodiments.

[0054] A Multi-Level Intervention (MCI) system based on dynamic adjustment of cognitive motor training difficulty in virtual reality is characterized by comprising a needs assessment module, an upper limb motor task prototype design module, a virtual cognitive task prototype design module, and a field research module. The overall process is as follows: Figure 1 As shown.

[0055] In order to design easy-to-implement and efficient intervention tasks, this invention delves into intervention training programs suitable for older adults with cognitive decline, their psychology, and their acceptance and preference for virtual reality interaction methods from the perspectives of task requirements and system requirements.

[0056] The specific steps of step A1 are as follows:

[0057] A11. Task Requirements.

[0058] In exploring the cognitive domain, the research team emphasized the significant advantages of virtual reality technology over traditional devices (such as tablets, smartphones, and large-screen displays) in spatial perception and executive function training, particularly in providing a more realistic and intuitive interactive experience. Experts in human-computer interaction suggest migrating cognitive tasks to virtual environments to offer older adults a more immersive and realistic training experience. Meanwhile, clinical observations by neurologists show that many older patients (whether in outpatient clinics or nursing homes) often lack motivation for physical exercise and experience discomfort with high-intensity activity. To address this issue, the research focuses on designing seated upper limb movement tasks to create a safe and comfortable training environment for older adults, reducing injury risks and increasing their engagement and sustainability.

[0059] A12. System Requirements.

[0060] Based on extensive clinical experience with the elderly population, specific expectations for the system are proposed: First, the task design should be simple and clear, ensuring that users can easily understand and operate it; second, the system should be highly accessible so that elderly users can use it easily; third, the system's engagement should be enhanced by integrating visual, auditory, and tactile feedback and reward mechanisms to optimize the user experience; finally, the intervention content should broadly cover cognitive and motor training, aiming to comprehensively improve the rehabilitation outcomes of the elderly.

[0061] A2 is an upper limb movement task based on defined needs. The design process of this task includes upper limb movement design, interaction methods and virtual environment evaluation, as well as dynamic difficulty adjustment of the upper limb movement task.

[0062] The specific steps of step A2 are as follows:

[0063] A21. Upper limb movement design.

[0064] The upper limb movement tasks were designed to target specific upper limb movements, ensuring that the tasks effectively activate key muscle groups and cover a sufficient range of motion, thereby enhancing training effectiveness. Suitable upper limb movement patterns for a seated posture were identified. For example... Figure 2 As shown, the designed upper limb movements include elbow flexion and extension, upper limb elevation, and shoulder rotation. These movements are carefully designed, with elbow flexion and extension performed in a four-beat cycle, while upper limb elevation and shoulder rotation use an eight-beat cycle to ensure the scientific nature of the movement rhythm and the effectiveness of the training.

[0065] A22. Evaluation of interaction methods and virtual environment.

[0066] A pilot evaluation of the system prototype was conducted based on selected upper limb movement training, involving 15 elderly participants from two nursing homes and two community hospitals. The experiment was carried out in a spacious indoor space, with participants seated in chairs with their hands naturally at their sides, performing specific upper limb movement tasks as instructed. To minimize potential side effects, each virtual reality exposure session was limited to no more than 20 minutes. The evaluation covered two interaction methods: one was interaction through touching virtual objects, and the other was simulating grasping actions by pressing buttons. Furthermore, the study explored the impact of virtual environment style on participant preferences, providing a variety of environment options such as cities, hospitals, natural landscapes, and fitness settings. Figure 3 As shown.

[0067] A23. Dynamic difficulty adjustment of upper limb movement tasks.

[0068] In upper limb motor tasks, dynamic difficulty adjustment is considered a bi-objective optimization problem, the core of which is balancing the two objective functions of intervention intensity and intervention performance. To this end, this invention proposes a dynamic difficulty adjustment algorithm based on Pareto optimality theory, such as... Figure 4 As shown, the algorithm generates a set of Pareto optimal solutions by modeling the difficulty (intervention intensity) of the upper limb motor task and the participants' motor performance (intervention performance). Then, by analyzing the trade-offs of each system in the generated solution set, the most suitable solution system is selected to adjust the task parameters or difficulty accordingly. First, the two decision objective functions are defined as intervention intensity and intervention performance, respectively. Intervention intensity reflects the difficulty level of the task, while intervention performance represents the participants' motor performance in the task. The formula for intervention intensity is:

[0069]

[0070] Among them, I iLet v be the standardized value of the intensity of the i-th intervention. xi v yi and v zi Let I represent the velocities of the ball in the x, y, and z axes respectively at the i-th time, and let min(I) and max(I) represent the minimum and maximum intervention intensities respectively. i The higher the value, the greater the difficulty.

[0071] The intervention performance formula is:

[0072] P i =1-[λ×(1-Accuracy)] i )+(1-λ)×Time i ]

[0073] Among them, P i For the i-th intervention, Accuracy i and Time i P represents the participant's accuracy and standardized time in the i-th upper limb task, respectively. i The larger the value, the better the participants perform. In this experiment, the value of λ was 0.3.

[0074] Secondly, a set of candidate solutions is generated in the search space using a random algorithm. Each candidate solution corresponds to a point in the search space and is composed of the values ​​of several decision variables. Specifically, the velocities of the ball in the x, y, and z axes are used as decision variables, denoted by v. x v y v z This indicates that for each axis, a preset velocity range is defined. Taking the x-axis as an example, its velocity range is v. x ={1,2,...,8}, v y and v z The range of values ​​for v x Consistent. Subsequently, based on their respective velocity ranges, a certain number of feasible solutions are randomly generated, and the values ​​of these solutions range from the corresponding v. x v y v z The speed is randomly selected from the range.

[0075] Next, for each candidate solution, its mapping value in the definition of the objective function is calculated. Specifically, during the practice phase before each intervention, the intervention intensity generated by each candidate solution is applied to the participants' practice to generate the target value for intervention performance. Subsequently, the bi-objective function under each candidate solution is encapsulated into a two-dimensional objective function vector F. i =[I i ,P iSimultaneously, the previous intervention information (two-dimensional objective function vectors corresponding to different candidate solutions) will also be incorporated to construct a new objective function vector F = [F1, F2, ..., F...]. i [,...], to ensure that the algorithm gradually approaches the optimal solution or Pareto front when searching the solution space.

[0076] Then, to ensure the effectiveness of solution ranking within the Pareto front and reduce computational complexity, an efficient non-dominated ranking is introduced. In this approach, all solutions in the feasible solution set are ordered in ascending order based on their first objective value (intervention intensity). If two or more solutions have the same first objective value, they are ordered in ascending order based on their second objective value (intervention performance). If two or more solutions have the same objective value, their ranking can be arbitrary. Through this ranking process, the efficient non-dominated ranking can progressively allocate solutions to the Pareto front, thereby optimizing the decision-making process.

[0077] Finally, a method for measuring the trade-off information of a pair of non-dominated solutions is introduced. By calculating the trade-off information of each solution on the frontier, one of the solutions is selected as the new game level. The formula is as follows:

[0078]

[0079] Among them, F m (v i ) and F m (v j These are solutions for system v. i and v j The value of the m-th objective function is obtained. and These are the maximum and minimum values ​​of the m-th objective function in the candidate solution system.

[0080] Furthermore, relative to other solutions on the optimal frontier in the non-dominant solution set S, any solution v i The trade-off value can be given by the following formula:

[0081]

[0082] Among them, v i and v j It is a solution in the non-dominant solution set S that is mutually indomitable, μ(v i ,S) indicates using v i Replace any solution v in the solution set S j The minimum improvement resulting from a decrease in a certain indicator.

[0083] A3 is a virtual cognitive task based on defined needs. The design process of this task covers cognitive domain task design, interaction methods and style layout evaluation, and dynamic difficulty adjustment of the virtual cognitive task.

[0084] The specific steps of step A3 are as follows:

[0085] A31. Design of virtual cognitive domain tasks.

[0086] To better meet the cognitive training needs of older adults, three virtual cognitive tasks were identified: a bin test (for training executive function), a working memory test (for training memory), and a depth perception test (for training depth perception).

[0087] Bin Test: Participants must move a specified number of virtual blocks from one compartment to another, with their hands passing through the central partition. Upon successfully picking up a block, the controller vibrates to provide tactile feedback. In addition, two extended versions of the test were designed: The first extended version requires participants to place blocks in corresponding areas based on color matching—red blocks in red areas, yellow blocks in yellow areas, and so on. This version aims to enhance participants' spatial visual perception and test their ability to extract and retain categorical information. The second extended version requires participants to place the picked-up blocks row by row into white areas. If the first white area is empty, a block cannot be placed in the second white area. This aims to improve participants' precise control over their movements.

[0088] Working memory: Participants first need to memorize the locations of a series of objects. Then, all the objects temporarily disappear, and the system randomly presents one of the objects, requiring participants to return it to its original position. This process is repeated until all objects are correctly restored. The correctness of each location is displayed through visual feedback. If the error rate in restoring the object exceeds 2 / 3 in three consecutive tasks, the test terminates. This task aims to assess participants' cognitive abilities to process, manipulate, and store information in a short period, especially their decision-making abilities when performing multiple tasks simultaneously.

[0089] Depth Perception Test: In a virtual environment, multiple white spheres are randomly arranged. Participants are required to click on the spheres as quickly as possible, either in a forward or backward order. During the task, the system records the time interval between each click in real time and calculates the reaction time. This task primarily assesses participants' spatial perception, reaction speed, and executive control. By comprehensively analyzing the accuracy of reaction time and click order, it further explores the participants' cognitive strategies and their efficiency in spatial positioning and target selection.

[0090] A32. Evaluation of interaction methods and style layout.

[0091] To explore the interactive experience of older adults using virtual reality controllers for grasping operations, an interactive experiment was designed and implemented. During the experiment, participants interacted with various virtual objects (such as cubes, balls, cars, and vases) using Oculus Quest 2 controllers. The experiment consisted of two phases: for the first three minutes, participants performed a grasping operation by pressing the trigger button on the controller, and then switched to using the side-grip button to perform the same task. After the experiment, unstructured interviews were conducted to collect participants' subjective feedback on these two operation methods, covering aspects such as comfort, ease of use, and personal preferences.

[0092] In addition, to further explore the impact of different interactive layouts on the user experience, the experiment also introduced an extended bin test, using three different target area arrangements of 4×4, 3×3, and 2×2 to examine the impact of these arrangements on participants' perceptual experience. Figure 5 As shown.

[0093] A33. Dynamic difficulty adjustment for virtual cognitive tasks.

[0094] In the intervention process of virtual cognitive tasks, the dynamic adjustment of task difficulty is similar to that of upper limb motor tasks, both requiring real-time optimization based on participants' individual performance. Therefore, this study introduces a dynamic difficulty adjustment algorithm based on Pareto optimality theory to improve the efficiency of difficulty adjustment in cognitive tasks. It is worth noting that this algorithm differs only in its objective function across the various cognitive tasks; the remaining operational procedures are consistent with those for upper limb motor tasks. The objective function settings for the three cognitive tasks are described below.

[0095] Objective function for virtual bin testing:

[0096] In this task, participants must move a specified number of blocks from one side of a cubicle to the other as efficiently as possible, without a time limit. The number of blocks in the task will be dynamically adjusted based on the participants' completion time in the previous task to ensure the difficulty matches their ability level. Therefore, the objective function is defined as:

[0097]

[0098] in, Let be the number of blocks dragged and dropped in the i-th iteration, with a value ranging from [30, 31, ..., 80]. and Let be the initial and end times of the i-th drag-and-drop operation.

[0099] Objective function of working memory test

[0100] In this task, the intervention intensity was defined as a composite measure of the number of items and the correlation between items. Meanwhile, intervention performance was evaluated based on two key performance indicators: the participants' item recall accuracy and task completion time. Therefore, the objective function was defined as:

[0101]

[0102] in, Let be the number of items in the i-th iteration, with values ​​ranging from [3, 4, ..., 8]. For the correlation between items in the i-th iteration, N i To correctly recall the number of items, Let λ be the standardized time for the i-th item recall. In this experiment, λ1 and λ2 are set to 0.8 and 0.6, respectively.

[0103] Objective function of depth perception test

[0104] In this task, adjustments to the ball density and depth directly affect the difficulty level for participants searching for and selecting balls in the virtual environment. Meanwhile, intervention performance is evaluated based on accuracy and completion time. Therefore, the objective function is defined as:

[0105]

[0106] in, Let be the number of balls in the i-th iteration, with values ​​ranging from [3, 4, ..., 8]. Let be the depth distance at the i-th time, with a value range of [10, 11, ..., 60]. For the accuracy of clicking the ball, To standardize the time of the ball's click, λ3 and λ4 were set to 0.6 and 0.6 respectively in this experiment.

[0107] Field study: Thirty elderly participants were recruited from various sources, including community hospitals, clinics, and long-term care facilities, and randomly assigned to an intervention group and a control group. The intervention group received virtual reality-based cognitive and motor training for 12 weeks, while the control group received no intervention and maintained their daily living habits. Baseline assessments (such as cognitive ability screening tools, mini mental status tests, and the Montreal Cognitive Assessment Scale) were performed on both groups before the intervention and again after 12 weeks to compare the effects between the groups.

[0108] Figure 6 The participants' performance on different tasks during the 12-week intervention period is presented in box plot form, with the top numbers indicating the average scores for each week. In elbow flexion and extension movements ( Figure 6(a)) Participants performed poorly in the first week, with an average score of only 0.457, presumably due to excessively high training intensity assigned randomly. Table 1 shows that the average intensity in the first week was 0.617, which decreased to 0.503 in subsequent weeks, supporting this inference. Figure 6 (b) shows that performance in the upper limb elevation movement improved slightly from week two to week twelve, reflecting the participants' gradual adaptation to high-intensity training. Although outliers indicate poor performance in some participants, these were generally influenced by task-independent external factors. In the shoulder circling movement ( Figure 6 (c) The average score was best in the first week, reaching 0.547, but subsequently stabilized at a lower level. The randomly selected lower intensity may have led to excellent performance in the first week, but also triggered subsequent boredom. Therefore, the subsequent intervention adopted a dynamic difficulty adjustment strategy based on Pareto optimality theory, increasing the optimal average intensity to 0.731 (see Table 1). Although the overall performance declined slightly, the performance remained relatively consistent across weeks.

[0109] also, Figure 6 (d) through (f) demonstrate performance on three virtual cognitive tasks. In the virtual bin test, participants' average completion time significantly improved, decreasing from 114 seconds in the first week to 60-80 seconds. Table 1 shows that the optimal intensity for this task was 45 seconds, with a randomly selected average of 60 seconds, designed to balance task complexity and cognitive load to promote stable and efficient performance. For the working memory test ( Figure 6 (e) Although the performance did not change significantly before and after selecting the optimal intensity, the outliers in the first week indicated that the intervention intensity was too low, leading to exceptionally high performance. Table 1 further confirms this, showing that the average intensity in the first week was 0.742, while the optimal intensity in subsequent weeks increased to 0.814. Finally, Figure 6 The analysis in (f) shows that after the difficulty adjustment, the performance in subsequent weeks improved significantly compared to the first week, from 0.756 to 0.678, highlighting the effectiveness and adaptability of the difficulty adjustment strategy in the task execution process.

[0110] Table 1 shows the average intensity of different tasks during the 12-week intervention.

[0111]

[0112]

[0113] Table 2 presents the statistical analysis results of the intervention group and the control group on the baseline and post-test cognitive assessment scales. Data from the control group showed a significant improvement in scores on all tests in the post-test compared to baseline. This trend was also observed in the intervention group, with a more significant increase in scores. At baseline, the intervention and control groups had roughly equivalent scores on all tests, but in the post-test, the intervention group scored significantly higher than the control group. Furthermore, an independent samples t-test comparing baseline and post-test cognitive assessment scale scores revealed no statistically significant differences in any cognitive test scores in the control group (P>0.05), indicating that the group's cognitive status remained stable during the study period. In contrast, the intervention group showed significant improvements in all cognitive function tests except for long-term memory, orientation, abstract thinking, and judgment (P<0.05), indicating that the implemented intervention system had a positive impact on specific cognitive domains.

[0114] Table 2. Measurement results of cognitive assessment scales at baseline and post-test in the intervention and control groups.

[0115]

[0116] To assess the significance of the intervention effect, this invention conducted an analysis of covariance on continuous variables in the two groups before and after the intervention, and the results are shown in Table 3. Compared with the control group, the intervention group participants showed a significant improvement in their scores on the cognitive ability screening tool after the intervention (F = 201.571, p < 0.001, η² = 0.780), indicating the effectiveness of the intervention system in enhancing overall cognitive function. Except for long-term memory, abstract thinking, and judgment (P > 0.05), most cognitive domains showed significant improvement after the intervention (P < 0.05), suggesting that the intervention system had a positive impact on most cognitive domains, although there were some differences in the effects between different domains. In addition, the intervention group also significantly outperformed the control group in the Mini Mental State Examination score (F = 140.810, P < 0.001, η² = 0.712) and the Montreal Cognitive Assessment score (F = 94.834, p < 0.001, η² = 0.625), further confirming the effectiveness of the intervention system across a wide range of cognitive domains. Overall, the η² values ​​of the cognitive screening tool, the Mini Mental State Examination, and the Montreal Cognitive Assessment scores ranged from 0.625 to 0.780, reflecting a relatively high effect size, indicating that the cognitive function of the intervention group participants improved significantly after 12 weeks of intervention training.

[0117] Table 3. Effect size of the intervention system on cognitive function improvement

[0118]

[0119] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. An MCI intervention system based on virtual reality cognitive motor training difficulty dynamic adjustment, characterized in that, The virtual cognitive task prototype module comprises a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module.

2. The system of claim 1, wherein, The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module.

3. The system of claim 1, wherein, The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. where I i is the normalized value of the intensity of the i-th intervention, v xi , v yi , and v zi are the velocities of the i-th ball in the x, y, and z axis directions, respectively, min(I) and max(I) are the minimum and maximum intervention intensities, respectively, and I i The greater the value, the more difficult the challenge. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. P i = 1 - [λ x (1 - Accuracy i ) + (1 - λ) x Time i ] where P i is the performance of the i-th intervention, Accuracy i and Time i are the accuracy and normalized time of the participant on the i-th upper limb task, respectively, and P i values are larger, the better the participant's performance. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an upper limb movement task prototype module, an upper limb movement task dynamic difficulty adjustment module, a virtual cognitive task prototype module and a virtual cognitive task dynamic difficulty adjustment module. The upper limb movement task prototype module comprises an where F m (v i ) and F m (v j ) are the values of the mth objective function of the candidate solution system v i and v j respectively. and are the maximum and minimum values of the mth objective function value of the candidate solution system. Furthermore, the trade-off value of any solution v i with respect to other solutions on the optimal frontier in the non-dominant set S can be given by the following formula: where v i and v j are non-dominated solutions in the set S, μ(v i , S) represents the minimum improvement in some objective that results from replacing any solution v i in the set S with v j .

4. The system of claim 1, wherein, The virtual cognitive task includes three virtual cognitive tasks, namely, a block test for training executive function, a working memory test for improving memory capacity, and a depth perception test for training spatial positioning capacity. The block test requires the participant to move a specified number of virtual blocks from one compartment to another compartment, with the hand passing through the middle partition. Two extended versions are designed: the first requires the participant to place the virtual blocks according to color matching in the corresponding area; the second requires the participant to place the blocks in the white area in order, thus improving their task organization and execution ability. The working memory test aims to assess the participant's ability to process, manipulate, and store information in a short period of time. The participant first needs to remember the location of a series of items, then these items will disappear, and the system will randomly appear one of them, which the participant needs to accurately place back to the initial position. The process is repeated until all items are correctly placed. If the participant's error rate exceeds 2 / 3 for three consecutive times, the test will be terminated. The depth perception test stimulates the spatial positioning and execution ability of the subject through multiple white balls in the virtual environment. The participant needs to click the balls in order of distance or proximity. The system records the click sequence and reaction time, which is composed of the interval time between each click. Finally, the reaction time is used to evaluate the cognitive performance of the subject.

5. The system of claim 1, wherein, The dynamic difficulty adjustment of the virtual cognitive task: During the intervention process of the virtual cognitive task, the dynamic adjustment of task difficulty is similar to the upper limb motor task, which needs to be optimized in real time according to the individual performance of the participant. A dynamic difficulty adjustment algorithm based on the Pareto optimization theory is used to improve the efficiency of difficulty adjustment of the cognitive task. The target function in each cognitive task is different, and the rest of the operation process is consistent with the upper limb motor task.

6. The system of claim 4, wherein, The target function settings of the three cognitive tasks include the target function of the virtual block test, the target function of the working memory test, and the target function of the depth perception test.

7. The system of claim 6, wherein, The target function of the virtual block test: In this task, the participant needs to move a specified number of blocks from one side of the compartment to the other side as efficiently as possible without time limit. The number of blocks in the task will be dynamically adjusted according to the completion time of the participant in the previous task to ensure that the difficulty matches the participant's ability level. Therefore, the target function is defined as: wherein, is the number of blocks for the ith drag-and-drop, taking values in the range [30, 31,..., 80], and is the initial and end time of the ith drag-and-drop.

8. The system of claim 6, wherein, The target function of the working memory test: In this task, the intervention intensity is defined as the composite measure of the number of items and the correlation between items. At the same time, the intervention performance is evaluated based on the accuracy of the participant's item recall and the task completion time. The target function is defined as: wherein, is the number of items for the ith trial, taking values in the range [3, 4,..., 8], is the inter-item correlation for the ith trial, N i is the number of items correctly recalled, is the item recall criterion normalized time for the ith trial.

9. The system of claim 6, wherein, The target function of the depth perception test: In this task, the adjustment of ball density and depth distance will directly affect the difficulty level of the participant's search and selection of balls in the virtual environment. At the same time, the evaluation of intervention performance is based on accuracy and completion time. Therefore, the target function is defined as: wherein, is the number of pellets for the i-th time, taking values in the range [3, 4,..., 8], is the depth distance for the i-th time, taking values in the range [10, 11,..., 60], is the click pellet accuracy, is the click pellet normalized time.

Images