Personalized virtual-real interaction cognitive game system based on AI adaptive brain cognitive enhancement

Abstract

The invention discloses a personalized virtual-real interaction cognitive game system based on AI adaptive brain cognitive enhancement, comprising: a cognitive game design module for designing a plurality of cognitive tasks corresponding to attention, memory, execution function and perception function based on a dynamic difficulty adjustment algorithm according to user characteristics; the dynamic difficulty adjustment algorithm is used for dynamically adjusting the difficulty of a specific level task according to the behavior state and the psychological state of the user; the cognitive task guiding module interacts with the user through a multi-mode guiding mechanism to guide the user to complete a cognitive task; the data tracking analysis module is used for recording the performance and growth trajectory of the user in the completion process of each cognitive task; the instant feedback module provides feedback based on an instant feedback generation algorithm; the cognitive competence evaluation report module is used for generating a corresponding cognitive competence evaluation report according to the performance and data tracking analysis algorithm; and the data storage module is used for storing behavior data, emotion records and cognitive competence evaluation reports of the user.

Description

Technical Field

[0001] The present invention relates to the interdisciplinary fields of AI adaptation, brain science, and cognitive training, and more particularly to a personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement. Background Art

[0002] Adolescence is a crucial stage in an individual's cognitive development, and cognitive training during this period has a profound impact on a person's future development. Psychological research shows that adolescents experience rapid cognitive development during this period, particularly in key cognitive skills such as attention, memory, executive function, and perception. However, while traditional cognitive training methods, such as classroom lectures and cognitive training software, can be helpful to a certain extent, they are often limited and fail to stimulate adolescent interest and engagement, and suffer from the following shortcomings:

[0003] 1. Most cognitive training games lack systematic cognitive psychology design and cannot effectively guide teenagers in cognitive training;

[0004] 2. Lack of personalized feedback mechanism, unable to provide targeted guidance based on players' behavior and psychological state;

[0005] 3. The difficulty is fixed and cannot adapt to the cognitive level and psychological state of different players. Summary of the Invention

[0006] The purpose of this invention is to provide a personalized virtual-reality interactive cognitive gaming system based on AI-adaptive brain cognitive enhancement. Specifically, it is a system for improving adolescent brain cognitive skills and abilities based on scenario-based game design. This system utilizes structured task design, a graded difficulty system, and a standardized assessment mechanism, incorporating principles from cognitive psychology. Through game level design, task guidance, instant feedback, data tracking, and evaluation reporting, the system provides players with a personalized cognitive training experience, helping adolescents improve cognitive skills such as attention, memory, executive function, and perception in a relaxed and enjoyable environment.

[0007] The purpose of the present invention is to provide a personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement, comprising:

[0008] A cognitive game design module is configured to design, based on user characteristics and a dynamic difficulty adjustment algorithm, multiple specific level tasks, each corresponding to a cognitive task related to training one or more of attention, memory, executive function, and perception, with the cognitive task forming a mapping to one or more of attention, memory, executive function, and perception. The user characteristics include the user's behavioral and psychological state. The dynamic difficulty adjustment algorithm is configured to dynamically adjust the difficulty of the specific level tasks based on the user's behavioral and psychological state to ensure the challenging and adaptable nature of the specific level tasks.

[0009] A cognitive task guidance module, which interacts with the user through a multimodal guidance mechanism to guide the user to complete the cognitive task;

[0010] Data tracking and analysis module, used to record the user's performance and growth trajectory in the process of completing various cognitive tasks;

[0011] An instant feedback module provides instant feedback based on the user's performance in completing the cognitive task and based on an instant feedback generation algorithm, thereby helping the user understand their own cognitive ability;

[0012] A cognitive ability assessment reporting module, configured to generate a cognitive ability assessment report corresponding to a user's performance based on the user's performance and a data tracking and analysis algorithm, the cognitive ability assessment report also including personalized cognitive training recommendations for the user; wherein the data tracking and analysis algorithm is based on time series analysis and generates a detailed cognitive ability assessment report by analyzing the user's cognitive ability change trends, wherein the cognitive ability assessment report includes task completion status, cognitive ability change trends, and personalized training recommendations;

[0013] The data storage module is used to store the user's behavior data, emotion records and cognitive ability assessment report so that the user's upstream and downstream stakeholders can refer to and analyze them.

[0014] Preferably, the algorithm of the dynamic difficulty adjustment algorithm is: establishing a multi-objective optimization model based on reinforcement learning, and performing real-time parameter adjustment based on the multi-objective optimization model;

[0015] The input parameters of the multi-objective optimization model include:

[0016] (1) Behavioral state, which is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments;

[0017] (2) Psychological state, which is characterized by: EEG concentration index, eye movement anxiety frequency and heart rate variability HRV.

[0018] Preferably, the task design workflow of the cognitive game design module includes:

[0019] S1, based on the data acquisition and fusion layer, implements data acquisition, data processing, and data fusion. The data includes behavioral state and psychological state, wherein the behavioral state is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments; the psychological state is characterized by EEG concentration index, eye movement restlessness value, eye movement restlessness frequency, and heart rate variability (HRV);

[0020] S2, based on the data after data fusion, uses the reinforcement learning model to evaluate the current state of the user; the reinforcement learning model calculates the current state value S of the user based on formula (1):

[0021] (1);

[0022] Where T is the task completion time, E is the error rate, F is the operation frequency, α, β, and γ are the weight coefficients of task completion time, error rate, and operation frequency, respectively (for example, α = 0.4, β = 0.3, γ = 0.3);

[0023] S3, obtaining a generated difficulty coefficient K based on a dynamic difficulty adjustment algorithm, thereby representing the difficulty of the specific level task dynamically adjusted according to the user's behavioral state and psychological state, and adjusting the difficulty of the specific level task according to the user's current state value S to ensure the challenge and adaptability of the specific level task;

[0024] S4, through the task selector, select cognitive function goals based on the generation difficulty coefficient K and the rehabilitation goal; wherein, the cognitive function goal selection includes adjusting the target tracking task parameters based on the attention training goal, expanding the matrix memory complexity based on the memory training goal, increasing the rule conversion frequency based on the executive function training goal, and improving the fuzzy recognition noise based on the perceptual function training; then, based on the generation difficulty coefficient K as a benchmark, the number of task elements is generated based on the parameterized formula (2), and the formula (2) is:

[0025] (2);

[0026] The dynamic difficulty adjustment algorithm is parameterized by the formula Generate task parameters, where N is the number of task elements, α' is the scope scaling factor, β' is the cognitive load nonlinearity coefficient, and K is the generation difficulty coefficient;

[0027] S5, generating a personalized level JSON and cognitive tasks based on the cognitive function target selection, and loading the cognitive tasks through the Unity engine;

[0028] S6, updating the model parameters of the reinforcement learning model once every fixed time period to adapt to the long-term progress of the user.

[0029] Preferably, the data processing includes:

[0030] A. Cross-modal adaptive processing to support multi-device compatibility between brain-computer interfaces and VR controllers / eye control;

[0031] B. performing anti-fatigue adaptive processing, including: automatically switching to a low-intensity task when the standard deviation of the heart rate variability (HRV) is greater than 50 ms;

[0032] C. Signal synchronization processing, including: sampling the behavioral state at a period of 100 ms and the psychological state at a frequency of 256 Hz, aligning the timestamps of the behavioral state data with the timestamps of the psychological state data to form a synchronization signal;

[0033] D. Perform signal abnormality processing, including inserting a 3-minute deep breathing guidance task when the eye movement restlessness value is detected to be greater than 0.7.

[0034] Preferably, the data fusion includes weighted fusion of the operation trajectory accuracy and the EEG concentration index.

[0035] Preferably, the personalized level JSON and cognitive tasks of S4 are dynamically constructed by a programmatic content generation algorithm, including the following steps:

[0036] (1) Input seed parameters: user cognitive ability index V and training target weight W;

[0037] (2) Execute the generated rule set:

[0038] Spatial layout rule: Map=Voronoi_partition(V 1.2 );

[0039] Task complexity rules: ;

[0040] Output personalized level instances: Ensure that each generated cognitive challenge is unique.

[0041] Preferably, the S4 further includes:

[0042] A long-term adaptive mechanism for automatically increasing the proportion of executive function tasks based on weekly training data to insert the target number of the rehabilitation goals; and if the accuracy rate of the cognitive function target selection is less than 30% for two consecutive times, triggering a dynamic degradation mechanism for emergency intervention, wherein the dynamic degradation mechanism includes reducing the generation difficulty coefficient K to K×0.6 as the new generation difficulty coefficient.

[0043] Preferably, the working process of the cognitive task guidance module includes:

[0044] S1. Interact with the user based on a multimodal guidance mechanism, wherein the multimodal guidance mechanism includes a combination of one or more methods including cognitive task prompts, cognitive task multiple-choice questions, cognitive task guidance text input boxes, or cognitive task guidance image input boxes; wherein the cognitive task prompts include: dynamically generating AR visual markers superimposed on VR scenes; the cognitive task multiple-choice questions include: providing a cognitive task selector through voice broadcasts and screen options, wherein the number of options in the voice broadcasts and the screen dynamically increases or decreases with the numerical value of the generation difficulty coefficient K; the cognitive task guidance text input box or the cognitive task guidance image input box includes: performing functional training through handwritten formula recognition or performing perceptual training through noise image annotation.

[0045] S2, starting and executing the guidance logic engine, wherein the task type is used to determine whether it is an attention task. If so, the target is guided by an AR arrow. If not, it is determined whether it is a memory task. If so, a step-by-step voice prompt of the memory strategy is provided. If not, the graphic instruction decomposition rules are determined. When the guidance logic engine is executed, the eye movement trajectory is monitored in real time, and a reinforcement prompt is triggered when the gaze deviates for more than 3 seconds.

[0046] S3, dynamic difficulty adaptation in cognitive task guidance, including: enabling layered guidance when the error rate is greater than 40%, the layered guidance ranging from text prompts to animation demonstrations to simplified task practice; when the EEG concentration (θ / β) is less than 0.5, switching to voice motivation guidance;

[0047] S4, feeding back the user interaction data to the guidance logic engine to form a data closed loop, thereby optimizing subsequent guidance strategies; wherein the user interaction data includes response delay and / or input accuracy.

[0048] Preferably, the working method of the data tracking and analysis module includes:

[0049] Collecting data for tracking and analysis, including: collecting historical behavioral data and cognitive ability assessment results of the user;

[0050] Performing cognitive ability change trend analysis includes: extracting cognitive ability change trend using a time series analysis model, wherein the time series analysis model calculates the trend value T based on the following formula (4):

[0051] (4);

[0052] Among them, S i is the score of the i-th evaluation, is the average score, N is the number of evaluations;

[0053] Preferably, the instant feedback generation algorithm is based on natural language processing technology, generates personalized feedback content according to the user's performance, and combines cognitive psychology theory to help the user understand their cognitive ability and provide improvement suggestions; wherein, the instant feedback generation algorithm includes:

[0054] Conduct real-time data analysis: Analyze users' task completion status and extract key indicators, including completion time and error rate;

[0055] Generate immediate feedback: Integrate cognitive psychology theory to generate positive motivation and improvement suggestions;

[0056] Adjust the tone of feedback: Adjust the tone of feedback based on the user’s emotional state;

[0057] Generate natural language: Use a pre-trained language model to generate natural and fluent personalized feedback content.

[0058] Beneficial effects of the system of the present invention:

[0059] Through a series of scenario-based game tasks, combined with dynamic difficulty adjustment algorithms, instant feedback generation algorithms, and data tracking and analysis algorithms, we help young players improve their brain cognitive skills such as attention, memory, executive function, and perception during the game. The specific beneficial effects are reflected in:

[0060] (1) The dynamic difficulty adjustment algorithm is based on the reinforcement learning model. By analyzing the user's behavioral data (such as task completion time, error rate, operation frequency) and emotional state (such as concentration and stress level), the game difficulty is dynamically adjusted to ensure that players train at an appropriate challenge level.

[0061] (2) “Psychological-behavioral double closed-loop feedback” forms a closed-loop feedback regulation effect in dynamic difficulty adjustment, which is closer to the real cognitive interaction situation.

[0062] (3) The interactive cognition is quantitatively described through the mathematical expression of the “parametric generation formula for cognitive tasks”, making the operation of the game system more reasonable.

[0063] (4) By forming a "real-time fusion of multimodal data" architecture, the technical effect of personalized adaptation can be achieved.

[0064] (5) Deep integration of scenario-based game design and cognitive tasks: Through carefully designed game scenarios and task guidance, the principles of cognitive psychology are deeply integrated with scenario-based game design. Game scenarios such as "Ball Tour", "Lemon Match" and "Guard the Lighthouse" are not only visually attractive, but also help teenagers gradually improve their cognitive abilities during the game process through task guidance and immediate feedback.

[0065] (6) Dynamic Difficulty Adjustment Algorithm: The system includes a dynamic difficulty adjustment algorithm that dynamically adjusts the game difficulty based on the player's behavior and psychological state. This design ensures the game's challenging and adaptable nature, allowing players of all levels to play at a difficulty level that suits them. For example, in the "Rolling Ball Journey" level, players' task completion time was reduced by an average of 23% and the error rate was reduced by 18%.

[0066] (7) Instant feedback generation algorithm: The system provides instant feedback and evaluation based on the player's performance in the game and generates an evaluation report. The feedback not only includes the completion status of the task, but also analyzes the player's cognitive ability based on the principles of cognitive psychology and provides targeted suggestions. For example, in the "Lemon Match" level, the player's accuracy rate increased by an average of 28%, and the task completion time was shortened by 15%.

[0067] (8) Data tracking and analysis algorithm: The system uses a data tracking and analysis algorithm to record the player's performance and growth trajectory in each level and generate an evaluation report. This report can help players better understand their cognitive development and also provide a reference for parents and educators. For example, the adoption rate of training suggestions has increased by 35%. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in related technologies, the following briefly introduces the drawings required for use in the specific embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0069] Figure 1 A schematic diagram of a task design workflow of a cognitive game design module according to an embodiment of the present invention;

[0070] Figure 2 A schematic diagram of a data flow architecture of a cognitive game design module provided according to an embodiment of the present invention;

[0071] Figure 3 This is a workflow diagram taking the attention task and memory task of the guidance logic engine provided in an embodiment of the present invention as an example. DETAILED DESCRIPTION

[0072] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0073] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0074] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0075] This embodiment provides a personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement, including:

[0076] (1) a cognitive game design module, configured to design a plurality of specific level tasks based on a dynamic difficulty adjustment algorithm according to user characteristics, wherein the plurality of specific level tasks respectively correspond to cognitive tasks related to training of one or more of attention, memory, executive function, and perceptual function, and the cognitive tasks form a mapping with one or more of attention, memory, executive function, and perceptual function; wherein the user characteristics include the user's behavioral state and psychological state; and the dynamic difficulty adjustment algorithm is configured to dynamically adjust the difficulty of the specific level tasks according to the user's behavioral state and psychological state, thereby ensuring the challenging and adaptable nature of the specific level tasks;

[0077] In this embodiment, the core of the dynamic difficulty adjustment algorithm is: establishing a multi-objective optimization model based on reinforcement learning, and performing real-time parameter adjustment based on the multi-objective optimization model; the dynamic difficulty adjustment algorithm stabilizes the task success rate at 65%-80% (the golden training range) to achieve precise matching.

[0078] The input parameters of the multi-objective optimization model include:

[0079] (1) Behavioral state, which is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments;

[0080] (2) Psychological state, which is characterized by: EEG concentration index (EEG θ / β wave ratio), eye movement frequency (EM) and heart rate variability (HRV).

[0081] The algorithm flow of the dynamic difficulty adjustment algorithm is as follows:

[0082] def DDA_Algorithm(user_state, task_history):

[0083] # 1. Capability Assessment Model

[0084] skill_level = α * (0.6*accuracy + 0.2*speed + 0.2*EEG_focus) - β* EM_stress

[0085] # 2. Dynamic difficulty coefficient generation

[0086] if skill_level > threshold_high:

[0087] difficulty = base_difficulty * (1 + γ * tanh(skill_level)) #Increase the challenge

[0088] elif skill_level < threshold_low:

[0089] difficulty = base_difficulty * (1 - δ * (1 - sigmoid(skill_level))) # Reduce difficulty

[0090] else:

[0091] difficulty = base_difficulty

[0092] # 3. Real-time parameter tuning (based on reinforcement learning)

[0093] reward = calculate_reward(accuracy, EEG_focus)

[0094] difficulty += η * (reward - expected_reward) # η is the learning rate

[0095] return clamp(difficulty, min=0.1, max=0.9) # Limit difficulty range

[0096] As a preferred embodiment, the mapping of the cognitive task with one or more of attention, memory, executive function and perceptual function includes the mapping relationship between the cognitive task and one or more of attention, memory, executive function and perceptual function as shown in Table 1 below.

[0097] Table 1

[0098] Cognitive function Specific task name Mission Mechanism Difficulty Adjustment Parameter attention Dynamic target tracking Lock the color-changing target in the moving background Number of targets / movement speed / background interference complexity Interference Mitigation Challenges Ignore the flickering distractions and click on the designated icon Distractor density / effective target similarity memory Spatial Matrix Memory Memorize the flash grid sequence and then reproduce it Grid size (3x3→7x7) / sequence length Multimodal associative memory Paired sound-image-text combinations Number of pairs / distractor similarity Executive function Rule conversion task Switch classification rules based on color changes (e.g. red by shape / blue by number) Rule switching frequency / conflict item ratio Resource allocation decisions Distribute supplies to multiple target points within a limited time Time pressure / goal conflict Perception function Integration of time and space perception Estimate the arrival time of moving objects and intercept them Object velocity / trajectory nonlinearity Fuzzy pattern recognition Identifying hidden objects in noisy images Signal-to-noise ratio / feature blur

[0099] As shown in Figure 1, the task design workflow of the cognitive game design module includes:

[0100] S1, based on the data acquisition and fusion layer, implements data acquisition, data processing, and data fusion. The data includes behavioral state and psychological state, wherein the behavioral state is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments; the psychological state is characterized by EEG concentration index, eye movement restlessness value, eye movement restlessness frequency, and heart rate variability (HRV);

[0101] In this embodiment, the data processing includes:

[0102] A. Cross-modal adaptive processing to support multi-device compatibility between brain-computer interfaces (BCIs) and VR controllers / eye control;

[0103] B. performing anti-fatigue adaptive processing, including: automatically switching to a low-intensity task when the standard deviation of the heart rate variability (HRV) is greater than 50 ms;

[0104] C. Signal synchronization processing, including: sampling the behavioral state at a period of 100 ms and the psychological state at a frequency of 256 Hz, aligning the timestamps of the behavioral state data with the timestamps of the psychological state data to form a synchronization signal;

[0105] D. Perform signal abnormality processing, including inserting a 3-minute deep breathing guidance task when the eye movement restlessness value is detected to be greater than 0.7.

[0106] In this embodiment, the data fusion includes weighted fusion of the operation trajectory accuracy (measured value is 0.92) and the EEG concentration index (measured value is 0.78). Of course, weighted fusion of other data can also be performed, all within the scope of protection of the present invention.

[0107] S2, based on the data after data fusion, uses the reinforcement learning model to evaluate the current state of the user; the reinforcement learning model calculates the current state value S of the user based on formula (1):

[0108] (1);

[0109] Where T is the task completion time, E is the error rate, F is the operation frequency, α, β, and γ are the weight coefficients of task completion time, error rate, and operation frequency, respectively (for example, α = 0.4, β = 0.3, γ = 0.3);

[0110] S3, obtaining a generated difficulty coefficient K based on a dynamic difficulty adjustment algorithm, thereby representing the difficulty of the specific level task dynamically adjusted according to the user's behavioral state and psychological state, and adjusting the difficulty of the specific level task according to the user's current state value S to ensure the challenge and adaptability of the specific level task;

[0111] S4, through the task selector, select cognitive function goals based on the generation difficulty coefficient K and the rehabilitation goal; wherein, the cognitive function goal selection includes adjusting the target tracking task parameters based on the attention training goal, expanding the matrix memory complexity based on the memory training goal, increasing the rule conversion frequency based on the executive function training goal, and improving the fuzzy recognition noise based on the perceptual function training; then, based on the generation difficulty coefficient K as a benchmark, the number of task elements is generated based on the parameterized formula (2), and the formula (2) is:

[0112] (2);

[0113] The dynamic difficulty adjustment algorithm is parameterized by the formula Generate task parameters, where N is the number of task elements, α' is the scope scaling factor, β' is the cognitive load nonlinearity coefficient, and K is the generation difficulty coefficient.

[0114] This mathematical form is the core means to solve the technical problem of "personalized difficulty adaptation". As an example, the parameter relationship α'=5, β'=1.5 is used in the conventional application scenario of cognitive training, that is, formula (3):

[0115] The number of recovery targets = ceil(5*K 1.5 ) (3);

[0116] ceil(5*K 1.5 ) is a parameterized generation formula used to quantify the dynamic difficulty coefficient K into specific parameters of the game task (such as the number of targets, sequence length, etc.). Its mathematical meaning and technical logic are as follows:

[0117] Mathematical breakdown:

[0118] 1. K 1.5 (Non-linear amplification of difficulty)

[0119] K is the dynamic difficulty coefficient (usually ranging from 0.1 to 0.9);

[0120] The effect of index 1.5: When K is small (such as 0.2), K 1.5 =0.2 1.5 ≈0.089 → Suppresses difficulty growth;

[0121] When K is large (such as 0.8), K 1.5 =0.8 1.5 ≈0.716 → Accelerated difficulty increase;

[0122] Technical significance: Matches the "progressive challenge curve" of human cognitive ability (flat at low levels and steep at high levels).

[0123] 2.5*K 1.5 (Parameter range scaling)

[0124] The multiplier 5 normalizes K 1.5 Mapping to the actual task parameter range (such as the number of targets 1 to 15):

[0125] K=0.1→5×0.0316≈0.158;

[0126] K=0.9→5×0.853≈4.2655×0.853≈4.265;

[0127] 3. (Round up)

[0128] Make sure the output is an integer (e.g. the target quantity cannot be a decimal). For example:

[0129] ceil(0.158)=1ceil(0.158)=1;

[0130] ceil(4.265)=5ceil(4.265)=5.

[0131] Examples of technical effects are shown in Table 2 below (dynamic target tracking task)

[0132] User capability level (K) Calculation process Generate target quantity Cognitive load regulation logic Novice (K=0.2) <![CDATA[ceil(5×0.2 1.5 )=1]]> 1 goal Avoid attention overload Intermediate (K=0.5) <![CDATA[ceil(5×0.5 1.5 )=3]]> 3 goals Moderately challenge working memory capacity Advanced (K=0.8) <![CDATA[ceil(5×0.8 1.5 )=5]]> 5 goals Stimulate the multitasking potential of executive function

[0133] The basis for designing this quantitative formula:

[0134] 1. Cognitive psychology basis:

[0135] (1) Stevens Power Law: Human perception of stimulus intensity conforms to ψ(I)=kIn;

[0136] (2) The exponent n = 1.5 approximates the subjective intensity model of “visual attention load” (experimental fitting value).

[0137] 2. Algorithm Advantages

[0138] Anti-oscillation: avoid difficulty jumps (e.g., from 2 directly to 5);

[0139] Boundary control: constrain the parameter to the valid range (1-15) through ceil and multiplier 5;

[0140] Monotonicity: Ensure that the difficulty of the task increases strictly as K increases.

[0141] 3. Scalability (as an alternative)

[0142] Changing the multiplier (e.g., 5 to 8) to suit different mission types; and

[0143] Adjustment index (such as K for memory tasks) 2.0 ) matching functional characteristics.

[0144] The rehabilitation goal is used to dynamically assign weights to multiple training goals, thereby determining the training emphasis corresponding to different rehabilitation goals. For example, ADHD patients focus on attention training goals, so they are given a weight of 70%.

[0145] S5: Generate personalized level JSON and cognitive tasks based on the cognitive function target selection, and load the cognitive tasks through the Unity engine.

[0146] As a preferred embodiment, the personalized level JSON and cognitive tasks of S4 are dynamically constructed through a procedural content generation (PCG) algorithm, including the following steps:

[0147] (1) Input seed parameters: user cognitive ability index V and training target weight W;

[0148] (2) Execute the generated rule set:

[0149] Spatial layout rule: Map=Voronoi_partition(V 1.2 );

[0150] Task complexity rules: ;

[0151] Output personalized level instances: Ensure that each generated cognitive challenge is unique.

[0152] In this embodiment, the core concepts of the programmatic content generation algorithm include:

[0153] (1) "Procedural": refers to the automatic generation of content through predefined algorithmic rules (not manually designed); for example: Perlin noise algorithm generates terrain, L-system grammar generates vegetation

[0154] (2) "Content": includes digital assets such as game levels, missions, maps, textures, and story branches;

[0155] (3) "Generate": Dynamically create infinite variations (e.g. 1 algorithm → 1000 level configurations).

[0156] Based on the cognitive function target selection and procedural content generation algorithm or procedural content generation algorithm (PCG), a single task can generate more than 1,000 variants, achieving the technical goal of generating diversity.

[0157] S6, updating the model parameters of the reinforcement learning model once every fixed time period to adapt to the long-term progress of the user.

[0158] In this embodiment, the model parameters of the reinforcement learning model are updated every 10 seconds to adapt to the long-term progress of the user.

[0159] like Figure 2 As shown, the data flow architecture of the cognitive game design module is:

[0160] Starting from the user end, real-time data streams flow into the status monitoring module, which outputs preprocessing signals to the AI decision engine. At the same time, the user history database sends the transfer learning data to the AI decision engine. After that, the AI decision engine inputs difficulty instructions to the level generator and inputs evaluation reports to the therapist dashboard; then the level generator inputs task parameters to the game rendering engine, and the game rendering engine returns interactive feedback to the user end.

[0161] As a preferred embodiment, the S4 further includes:

[0162] A long-term adaptation mechanism is provided for automatically increasing the proportion of executive function tasks based on weekly training data (for example, +5% per week in this embodiment) to insert the target number of the rehabilitation goals; and if the accuracy rate of the cognitive function goal selection is less than 30% for two consecutive times, a dynamic degradation mechanism is triggered for emergency intervention, wherein the dynamic degradation mechanism includes reducing the generation difficulty coefficient K to K×0.6 as the new generation difficulty coefficient.

[0163] (2) A cognitive task guidance module that interacts with the user through a multimodal guidance mechanism to guide the user to complete the cognitive task;

[0164] As a preferred embodiment, the working process of the cognitive task guidance module includes:

[0165] S1. Interacting with the user based on a multimodal guidance mechanism, wherein the multimodal guidance mechanism includes a combination of one or more of cognitive task prompts, cognitive task multiple-choice questions, cognitive task guidance text input boxes, or cognitive task guidance image input boxes; wherein the cognitive task prompts include: dynamically generating AR visual markers (such as highlighted target areas) superimposed on the VR scene; the cognitive task multiple-choice questions include: providing a cognitive task selector through voice broadcast and screen options, wherein the number of options in the voice broadcast and the screen dynamically increases or decreases with the numerical value of the generation difficulty coefficient K; the cognitive task guidance text input box or the cognitive task guidance image input box includes: performing functional training through handwritten formula recognition or performing perceptual training through noise image annotation.

[0166] S2, starts and executes the boot logic engine, such as Figure 3 The following is a workflow diagram of the guidance logic engine, using attention tasks and memory tasks as examples. The diagram shows a task type that determines whether it is an attention task. If so, an AR arrow guides the target to move. If not, a determination is made as to whether it is a memory task. If so, a step-by-step voice prompt is provided for the memory strategy. If not, a graphic instruction decomposition rule is determined. When the guidance logic engine is executed, eye movement trajectories are monitored in real time, and a reinforcement prompt is triggered when gaze deviation exceeds 3 seconds.

[0167] S3, dynamic difficulty adaptation in cognitive task guidance, including: enabling layered guidance when the error rate is greater than 40%, the layered guidance ranging from text prompts to animation demonstrations to simplified task practice; when the EEG concentration (θ / β) is less than 0.5, switching to voice motivation guidance;

[0168] S4 feeds back user interaction data (response latency / input accuracy) to the guidance logic engine to form a data closed loop, thereby optimizing subsequent guidance strategies with an error convergence rate of >90%.

[0169] (3) Data tracking and analysis module, used to record the user's performance and growth trajectory in the process of completing various cognitive tasks;

[0170] As a preferred embodiment, the working method of the data tracking and analysis module includes:

[0171] Collecting data for tracking and analysis, including: collecting historical behavioral data and cognitive ability assessment results of the user;

[0172] Performing cognitive ability change trend analysis includes: extracting cognitive ability change trend using a time series analysis model, wherein the time series analysis model calculates the trend value T based on the following formula (4):

[0173] (4);

[0174] Among them, S i is the score of the i-th evaluation, is the average score, N is the number of evaluations;

[0175] (4) an immediate feedback module, which provides immediate feedback based on the immediate feedback generation algorithm according to the user's performance in completing the cognitive task, thereby helping the user understand his or her own cognitive ability;

[0176] As a preferred embodiment, the instant feedback generation algorithm is based on natural language processing technology to generate personalized feedback content based on the user's performance, combined with cognitive psychology theory to help users understand their cognitive abilities and provide improvement suggestions; wherein, the instant feedback generation algorithm includes:

[0177] Conduct real-time data analysis: Analyze users' task completion status and extract key indicators (such as completion time and error rate);

[0178] Generate immediate feedback: Integrate cognitive psychology theory to generate positive motivation and improvement suggestions;

[0179] Perform tone adjustments: Adjust the tone of feedback based on the user’s emotional state (e.g., stress level);

[0180] Generate natural language: Use a pre-trained language model to generate natural and fluent personalized feedback content.

[0181] (5) A cognitive ability assessment report module, which is used to generate a cognitive ability assessment report corresponding to the user's performance based on the user's performance and the data tracking and analysis algorithm, and the cognitive ability assessment report also includes personalized cognitive training recommendations for the user; wherein the data tracking and analysis algorithm is based on time series analysis, and generates a detailed cognitive ability assessment report by analyzing the user's cognitive ability change trend, wherein the cognitive ability assessment report includes task completion status, cognitive ability change trend and personalized training recommendations.

[0182] (6) A data storage module for storing the user's behavioral data, emotional records, and the cognitive ability assessment report so that the user's upstream and downstream stakeholders (e.g., parents and educators) can refer to and analyze the data.

[0183] Application Examples

[0184] 1. Game level design module

[0185] The game's level-designed module uses multiple level tasks to train attention, memory, executive function, and perception. Each level guides players through cognitive training through different tasks (such as the ball rolling challenge, lemon collision, and lighthouse defense). For example, the ball rolling challenge trains concentration and coordination by keeping the ball in the center of a ring; the lemon collision challenge trains adaptability by clicking lemon slices; and the lighthouse defense challenge trains attention allocation, coordination, and spatial perception by keeping the cursor in the target area.

[0186] 2. Dynamic Difficulty Adjustment Algorithm

[0187] The dynamic difficulty adjustment algorithm is based on a reinforcement learning model and dynamically adjusts the game difficulty by analyzing the player's behavioral data and emotional state. The specific implementation is as follows:

[0188] Input: Players’ behavioral data (e.g., task completion time, error rate, operation frequency) and emotional state (e.g., concentration, stress level);

[0189] Output: adjusted game difficulty parameters;

[0190] Algorithm steps:

[0191] (1) Data collection: Collect players’ behavioral data and emotional states in real time. For example, in the “Rolling Ball Journey” level, record the player’s operation frequency (number of operations per second) and error rate (number of times the ball deviates from the center of the ring);

[0192] (2) State evaluation: Use the reinforcement learning model to evaluate the player's current state. The model calculates the player's current state value S based on the following formula: ; Where T is the task completion time, E is the error rate, F is the operation frequency, α, β, γ are weight coefficients (for example, α=0.4, β=0.3, γ=0.3);

[0193] (3) Difficulty adjustment: Adjust the game difficulty according to the state value S. For example, when S>0.8, increase the game difficulty; when S<0.2, reduce the game difficulty;

[0194] (4) Model update: Model parameters are updated every 10 seconds to adapt to the long-term progress of players.

[0195] Technical Effect: Through dynamic difficulty adjustment, players' task completion time in the "Rolling Ball Journey" level was shortened by an average of 23% and the error rate was reduced by 18%.

[0196] 3. Instant Feedback Generation Algorithm

[0197] The instant feedback generation algorithm is based on natural language processing technology and generates personalized feedback content based on the player's performance. The specific implementation is as follows:

[0198] Input: Players’ task completion and cognitive ability assessment results;

[0199] Output: Personalized feedback content;

[0200] Algorithm steps:

[0201] (1) Data analysis: Analyze the player's task completion status and extract key indicators (such as completion time and error rate). For example, in the "Lemon Clash" level, record the player's click speed (number of clicks per second) and accuracy (percentage of correct clicks);

[0202] (2) Feedback generation: Incorporating cognitive psychology theory, it generates positive incentives and improvement suggestions. For example, when a player’s accuracy rate falls below 70%, the system will prompt: “Your adaptability needs to be improved. Try to identify the target faster!”

[0203] (3) Tone adjustment: Adjust the tone of feedback based on the player’s emotional state (e.g., stress level). For example, when a player is detected to be stressed, use a gentler tone: “You’re doing great, keep focusing!”

[0204] (4) Natural language generation: Use pre-trained language models to generate natural and fluent feedback content.

[0205] Technical Effect: Through immediate feedback, players’ accuracy in the “Lemon Clash” level increased by an average of 28%, and task completion time was reduced by 15%.

[0206] 4. Data tracking and analysis algorithm

[0207] The data tracking and analysis algorithm is based on time series analysis, and generates a detailed evaluation report by analyzing the changing trends of players' cognitive abilities. The specific implementation is as follows:

[0208] Input: Players’ historical behavioral data and cognitive ability assessment results;

[0209] Output: Cognitive ability change trend report;

[0210] Algorithm steps:

[0211] (1) Data collection: Collect players’ historical behavioral data and cognitive ability assessment results. For example, record the player’s attention allocation ability score (110 points) in the “Guard the Lighthouse” level;

[0212] (2) Trend analysis: A time series analysis model is used to extract the trend of cognitive ability changes. The model calculates the trend value T based on the following formula:

[0213] ;

[0214] Among them, S i is the score of the i-th evaluation, is the average score, N is the number of evaluations;

[0215] (3) Report generation: Generate a detailed evaluation report, including task completion status, cognitive ability change trends, and personalized training recommendations;

[0216] (4) Parent Reference: Provides reference for parents and educators to help them understand the cognitive development of players.

[0217] Technical Effect: Through data tracking and analysis, parents and educators can more accurately understand changes in players’ cognitive abilities, and the adoption rate of training suggestions has increased by 35%.

[0218] Game Examples

[0219] Level 1: Rolling Ball Journey (Concentration and Coordination)

[0220] (1) Game scenes and task guidance:

[0221] After players enter the rolling ball journey scene, the system guides them through task prompts to control the ball and keep it in the center of the ring. Players use the input box to record their actions. The system gradually unlocks the rolling ball journey scene based on the player's answers and provides instant feedback.

[0222] (2) Dynamic Difficulty Adjustment:

[0223] The system uses a dynamic difficulty adjustment algorithm to analyze the player's operation frequency and error rate, and adjust the ring's movement speed and complexity in real time. For example, if the player's operation frequency is less than 2 times / second, the system will reduce the ring's movement speed; if the operation frequency is more than 5 times / second, the system will increase the ring's complexity.

[0224] (3) Instant feedback and evaluation

[0225] After completing a task, players receive a "Concentration" badge, and the system provides immediate feedback, emphasizing the importance of concentration. For example, the system prompts the player: "Your concentration ability has improved. Keep it up!" This feedback mechanism helps players better understand their own cognitive abilities.

[0226] Level 2: Lemon Collision (Adaptability)

[0227] (1) Task design and goal setting:

[0228] Players can practice their adaptability by completing lemon-collision tasks. The system guides players to click on the lemon slices through task prompts and provides instant feedback based on their performance.

[0229] (2) Dynamic Difficulty Adjustment

[0230] The system uses a dynamic difficulty adjustment algorithm to analyze the player's click speed and accuracy, adjusting the frequency and location of lemon slices in real time. For example, if the player's click speed is less than 3 times per second, the system will reduce the frequency of lemon slices; if the click speed is more than 6 times per second, the system will increase the complexity of the lemon slices' locations.

[0231] (3) Instant feedback and evaluation

[0232] After completing a task, players receive a "resilience" badge, and the system emphasizes the importance of adaptability. For example, the system will prompt the player: "Your adaptability has improved. Keep it up!" This feedback mechanism helps players build self-confidence and improve cognitive abilities.

[0233] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement, characterized by: include: A cognitive game design module is configured to design, based on user characteristics and a dynamic difficulty adjustment algorithm, multiple specific level tasks, each corresponding to a cognitive task related to training one or more of attention, memory, executive function, and perception, with the cognitive task forming a mapping to one or more of attention, memory, executive function, and perception. The user characteristics include the user's behavioral and psychological state. The dynamic difficulty adjustment algorithm is configured to dynamically adjust the difficulty of the specific level tasks based on the user's behavioral and psychological state to ensure the challenging and adaptable nature of the specific level tasks. A cognitive task guidance module, which interacts with the user through a multimodal guidance mechanism to guide the user to complete the cognitive task; Data tracking and analysis module, used to record the user's performance and growth trajectory in the process of completing various cognitive tasks; An instant feedback module provides instant feedback based on the user's performance in completing the cognitive task and based on an instant feedback generation algorithm, thereby helping the user understand their own cognitive ability; A cognitive ability assessment reporting module, configured to generate a cognitive ability assessment report corresponding to a user's performance based on the user's performance and a data tracking and analysis algorithm, the cognitive ability assessment report also including personalized cognitive training recommendations for the user; wherein the data tracking and analysis algorithm is based on time series analysis and generates a detailed cognitive ability assessment report by analyzing the user's cognitive ability change trends, wherein the cognitive ability assessment report includes task completion status, cognitive ability change trends, and personalized training recommendations; The data storage module is used to store the user's behavior data, emotion records and cognitive ability assessment report so that the user's upstream and downstream stakeholders can refer to and analyze them.

2. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 1 is characterized in that: The algorithm of the dynamic difficulty adjustment algorithm is as follows: establishing a multi-objective optimization model based on reinforcement learning, and performing real-time parameter adjustment based on the multi-objective optimization model; The input parameters of the multi-objective optimization model include: (1) Behavioral state, which is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments; (2) Psychological state, which is characterized by: EEG concentration index, eye movement anxiety frequency and heart rate variability HRV.

3. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 2 is characterized in that: The task design workflow of the cognitive game design module includes: S1, based on the data acquisition and fusion layer, implements data acquisition, data processing, and data fusion. The data includes behavioral state and psychological state, wherein the behavioral state is characterized by task response time, accuracy, operation trajectory accuracy, and number of abandonments; the psychological state is characterized by EEG concentration index, eye movement restlessness value, eye movement restlessness frequency, and heart rate variability (HRV); S2, based on the data after data fusion, uses the reinforcement learning model to evaluate the current state of the user; the reinforcement learning model calculates the current state value S of the user based on formula (1): （1）； Where T is the task completion time, E is the error rate, F is the operation frequency, α, β, and γ are the weight coefficients of task completion time, error rate, and operation frequency, respectively (for example, α = 0.4, β = 0.3, γ = 0.3); S3, obtaining a generated difficulty coefficient K based on a dynamic difficulty adjustment algorithm, thereby representing the difficulty of the specific level task dynamically adjusted according to the user's behavioral state and psychological state, and adjusting the difficulty of the specific level task according to the user's current state value S to ensure the challenge and adaptability of the specific level task; S4, through the task selector, select cognitive function goals based on the generation difficulty coefficient K and the rehabilitation goal; wherein, the cognitive function goal selection includes adjusting the target tracking task parameters based on the attention training goal, expanding the matrix memory complexity based on the memory training goal, increasing the rule conversion frequency based on the executive function training goal, and improving the fuzzy recognition noise based on the perceptual function training; then, based on the generation difficulty coefficient K as a benchmark, the number of task elements is generated based on the parameterized formula (2), and the formula (2) is: （2）； The dynamic difficulty adjustment algorithm is parameterized by the formula Generate task parameters, where N is the number of task elements, α' is the scope scaling factor, β' is the cognitive load nonlinearity coefficient, and K is the generation difficulty coefficient; S5, generating a personalized level JSON and cognitive tasks based on the cognitive function target selection, and loading the cognitive tasks through the Unity engine; S6, updating the model parameters of the reinforcement learning model once every fixed time period to adapt to the long-term progress of the user.

4. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 3 is characterized in that: The data processing includes: A. Cross-modal adaptive processing to support multi-device compatibility between brain-computer interfaces and VR controllers / eye control; B. performing anti-fatigue adaptive processing, including: automatically switching to a low-intensity task when the standard deviation of the heart rate variability (HRV) is greater than 50 ms; C. Signal synchronization processing, including: sampling the behavioral state at a period of 100 ms and the psychological state at a frequency of 256 Hz, aligning the timestamps of the behavioral state data with the timestamps of the psychological state data to form a synchronization signal; D. Perform signal abnormality processing, including inserting a 3-minute deep breathing guidance task when the eye movement restlessness value is detected to be greater than 0.

7.

5. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 4 is characterized in that: The data fusion includes weighted fusion of the operation trajectory accuracy and the EEG concentration index.

6. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 5 is characterized in that: The personalized level JSON and cognitive tasks of the S4 are dynamically constructed through a programmatic content generation algorithm, including the following steps: (1) Input seed parameters: user cognitive ability index V and training target weight W; (2) Execute the generated rule set: Spatial layout rule: Map=Voronoi_partition(V 1.2 ); Task complexity rules: ; Output personalized level instances: Ensure that each generated cognitive challenge is unique.

7. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 6 is characterized in that: Said S4 further comprises: A long-term adaptive mechanism for automatically increasing the proportion of executive function tasks based on weekly training data to insert the target number of the rehabilitation goals; and if the accuracy rate of the cognitive function target selection is less than 30% for two consecutive times, triggering a dynamic degradation mechanism for emergency intervention, wherein the dynamic degradation mechanism includes reducing the generation difficulty coefficient K to K×0.6 as the new generation difficulty coefficient.

8. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 7 is characterized in that: The working process of the cognitive task guidance module includes: S1. Interacting with a user based on a multimodal guidance mechanism, wherein the multimodal guidance mechanism includes a combination of one or more of cognitive task prompts, cognitive task multiple-choice questions, a cognitive task guidance text input box, or a cognitive task guidance image input box; wherein the cognitive task prompt includes: dynamically generating an AR visual marker superimposed on a VR scene; the cognitive task multiple-choice question includes: providing a cognitive task selector through voice broadcast and on-screen options, wherein the number of options in the voice broadcast and on-screen options dynamically increases or decreases with the value of the generation difficulty coefficient K; the cognitive task guidance text input box or cognitive task guidance image input box includes: performing functional training through handwritten formula recognition or performing perceptual training through noise image annotation; S2, starting and executing the guidance logic engine, wherein the task type is used to determine whether it is an attention task. If so, the target is guided by an AR arrow. If not, it is determined whether it is a memory task. If so, a step-by-step voice prompt of the memory strategy is provided. If not, the graphic instruction decomposition rules are determined. When the guidance logic engine is executed, the eye movement trajectory is monitored in real time, and a reinforcement prompt is triggered when the gaze deviates for more than 3 seconds. S3, dynamic difficulty adaptation in cognitive task guidance, including: enabling layered guidance when the error rate is greater than 40%, the layered guidance ranging from text prompts to animation demonstrations to simplified task practice; when the EEG concentration (θ / β) is less than 0.5, switching to voice motivation guidance; S4, feeding back the user interaction data to the guidance logic engine to form a data closed loop, thereby optimizing subsequent guidance strategies; wherein the user interaction data includes response delay and / or input accuracy.

9. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 8, characterized in that: The working method of the data tracking and analysis module includes: Collecting data for tracking and analysis, including: collecting historical behavioral data and cognitive ability assessment results of the user; Performing cognitive ability change trend analysis includes: extracting cognitive ability change trend using a time series analysis model, wherein the time series analysis model calculates the trend value T based on the following formula (4): （4）； Among them, S i is the score of the i-th evaluation, is the average score, and N is the number of evaluations.

10. The personalized virtual-reality interactive cognitive game system based on AI adaptive brain cognitive enhancement according to claim 9 is characterized in that: The instant feedback generation algorithm is based on natural language processing technology and generates personalized feedback content based on the user's performance. It combines cognitive psychology theory to help users understand their cognitive abilities and provide improvement suggestions. The instant feedback generation algorithm includes: Conduct real-time data analysis: Analyze users' task completion status and extract key indicators, including completion time and error rate; Generate immediate feedback: Integrate cognitive psychology theory to generate positive motivation and improvement suggestions; Adjust the tone of feedback: Adjust the tone of feedback based on the user’s emotional state; Generate natural language: Use a pre-trained language model to generate natural and fluent personalized feedback content.

Images