Children attention deficit test method integrating gamification tasks

Abstract

The invention discloses a child attention deficit test method integrating a gamification task, and relates to the technical field of child physical examination, and the method comprises the steps: presenting a series of interactive digital games with cognitive load to a tested individual by using a self-adaptive task generation engine; behavior response signals, physiological electric signals and kinematics signals generated in the process that the individuals participate in the interactive digital game are synchronously collected; calculating a dynamic cognitive state vector of the individual in real time according to the collected signals; and performing conjoint analysis on difficulty parameters adopted by the whole series of interactive digital games and dynamic cognitive state vectors fed back by the difficulty parameters to generate a final test report. According to the method, the defects of high subjectivity, single data and the like of a traditional evaluation method are effectively overcome through fusion of the self-adaptive game task and the multi-modal data; by capturing the dynamic change of the cognitive state of the child in real time, personalized accurate evaluation is realized.

Description

Technical Field

[0001] This invention relates to the field of children's physical examination technology, and in particular to a method for detecting attention deficit in children that integrates gamified tasks. Background Technology

[0002] Attention deficit hyperactivity disorder (ADHD) is a common chronic neurodevelopmental disorder that begins in childhood and can continue to affect adults. It can be comorbid with various neuropsychiatric disorders. The core symptoms of ADHD include inattention, hyperactivity, and impulsive behavior, which severely impact patients' learning, social interactions, and quality of life.

[0003] Currently, ADHD diagnosis primarily relies on behavioral observation and subjective rating, including physician interviews and behavioral rating scales completed by parents and teachers. Commonly used assessment tools include the SNAP-IV scale and the ADHD-RATING SCALE-IV. This method suffers from significant drawbacks such as diagnostic delays, high misdiagnosis rates, and considerable limitations. In recent years, gamified assessment methods have shown great potential due to their ability to simulate real-world environments, and virtual reality (VR) and serious games have been introduced into ADHD assessment and intervention. However, despite the potential shown by gamified assessment, existing technologies still have significant shortcomings: Insufficient data utilization: Most systems only use a limited number of behavioral data (such as accuracy and reaction time), failing to make full use of multimodal data for comprehensive judgment; Inadequate adaptation to individual differences: The difficulty and type of tasks are usually fixed, making it difficult to adapt to the assessment needs of children of different ages and symptom characteristics; Insufficient validation: Many systems lack large-scale clinical validation, and their diagnostic sensitivity and specificity need to be improved; The algorithm is limited: it mainly uses traditional statistical methods or simple machine learning algorithms, resulting in limited classification accuracy.

[0004] To address the aforementioned technical bottlenecks, this invention proposes to organically combine gamified tasks with multimodal assessment. Through adaptive task generation and deep learning analysis, it achieves objective and accurate assessment of ADHD, providing a novel technical solution for the detection of attention deficit disorder in children. Summary of the Invention

[0005] This invention provides a method for detecting attention deficit in children using integrated gamified tasks, comprising: Step S110: Using an adaptive task generation engine, present a series of interactive digital games with cognitive load to the test subjects; Step S120: Synchronously collect the behavioral response signals, physiological electrical signals, and kinematic signals generated by the individual during participation in the interactive digital game; Step S130: Calculate the dynamic cognitive state vector of the individual in real time based on the collected signals; Step S140: Perform joint analysis on the difficulty parameters used in the entire series of interactive digital games and the dynamic cognitive state vectors they reflect, and generate the final verification report.

[0006] The method for testing children's attention deficit using integrated gamified tasks, as described above, utilizes an adaptive task generation engine to present the test subject with a series of interactive digital games with cognitive load, specifically comprising the following sub-steps: The adaptive task generation engine is initialized based on the metadata of the tested individual to generate the first set of interactive digital games; When the current group of interactive digital games ends, the task difficulty of the next group of interactive digital games is dynamically adjusted based on the dynamic cognitive state vector fed back from step S130 using the hybrid decision unit. Render the next set of interactive digital games based on the adjusted task difficulty; The task difficulty adjustment and digital game rendering steps are repeated until the maximum task volume is reached.

[0007] The method for testing children's attention deficit using integrated gamified tasks, as described above, involves simultaneously collecting behavioral response signals, electrophysiological signals, and kinematic signals generated by the individual during participation in the interactive digital game. This process is specifically divided into the following sub-steps: All acquisition devices are clock-synchronized through a unified main control unit; Starting with the pulse signal emitted by the main control unit, the raw data from each acquisition device is collected and buffered synchronously. The collected raw data is preprocessed and integrated to form a time-aligned multimodal feature matrix, and then labeled with the corresponding game event tags.

[0008] The method for detecting attention deficit in children using integrated gamified tasks, as described above, involves calculating the individual's dynamic cognitive state vector in real time based on the collected signals. This process is specifically divided into the following sub-steps: The multimodal feature matrix is ​​standardized and weighted. The components of the dynamic cognitive state vector are calculated in parallel based on the processed multimodal feature matrix. The calculated dynamic cognitive state vector is timestamped and marked with game events before being output to a separate vector pool for the tested individual.

[0009] The method for testing children's attention deficit using integrated gamified tasks, as described above, involves joint analysis of the difficulty parameters used in the entire series of interactive digital games and the dynamic cognitive state vectors they provide, generating a final test report. This process is divided into the following sub-steps: Using the difficulty parameters adopted by different groups of interactive digital games as rows and the dynamic cognitive state vector sequence fed back in the game as columns, a sensing matrix is ​​constructed; The induction matrix is ​​input into the attention deficiency detection model, and the deficiency judgment result is output. The test results are used to calculate the strength of the individual's cognitive abilities across various dimensions and generate a final test report.

[0010] The beneficial effects achieved by this invention are as follows: By integrating adaptive game tasks with multimodal data, it effectively overcomes the shortcomings of traditional assessment methods, such as strong subjectivity and single data; the system can capture the dynamic changes in children's cognitive state in real time, realize personalized and accurate assessment, and significantly improve the objectivity and accuracy of ADHD diagnosis; its gamified form greatly increases children's participation, providing an efficient and reliable solution for the early screening and intervention of children's attention deficit. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1 This is a flowchart of a method for detecting attention deficit in children that integrates gamified tasks, as provided in Embodiment 1 of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] Example 1

[0015] like Figure 1 As shown, Embodiment 1 of this application provides a method for detecting attention deficit in children by integrating gamified tasks, including: Step S110: Using an adaptive task generation engine, present a series of interactive digital games with cognitive load to the test subjects; The adaptive task generation engine can dynamically adjust the difficulty parameters of subsequent games based on the individual's performance in completed interactive digital games, in order to approximate the individual's cognitive ability threshold; its specific task generation process is as follows: Step S111: Initialize the adaptive task generation engine based on the metadata of the tested individual to generate the first set of interactive digital games; First, based on the individual's metadata (including age in months, gender, and past medical history), the system retrieves developmental assessment data (i.e. attention performance parameters) of children under the same conditions from a pre-set cognitive development norm database. The mean value is then used as an initial cognitive ability baseline (i.e., the assessment starting point). Then, based on this baseline, the corresponding initial task parameters are retrieved. Subsequently, based on the initial task parameters, the corresponding materials are retrieved from a multidimensional task material library, assembled into the first set of interactive digital games, and rendered.

[0016] The cognitive development norm database is a structured data warehouse that collects and integrates large-scale, de-identified child development assessment data from multiple medical institutions, including assessment records of children diagnosed with ADHD and children with typical development. The database includes a demographic norm table and a task parameter mapping table. The demographic norm table uses age, sex, and past medical history as key indexes to store attention performance parameters (such as average reaction time, accuracy, error type distribution, attention duration, and physiological signal baseline) of children of different ages on various core assessment tasks. The task parameter mapping table defines the correlation between initial task parameters and different attention performance levels (attention parameter ranges).

[0017] The multidimensional task asset library stores the basic elements that make up all interactive digital games, and defines the corresponding asset classification identifiers (such as character images, prompt sounds, etc.) and asset attributes (such as shape, color, spatial position, layout rules, etc.) for each element. The task parameters include the required material type, specific material attribute values, and the task difficulty that needs to be dynamically adjusted later. After retrieving the corresponding elements based on the task parameters, the adaptive task generation engine first loads the interactive digital game paradigm selected by the test subject (selected on the start interface, with multiple theme paradigms such as treasure hunt, spot the difference, and adventure). Then, it dynamically binds and instantiates the retrieved materials according to the spatial arrangement rules, interaction logic, and task difficulty in the task parameters of the selected game paradigm, and finally renders the first set of interactive digital games and presents them to the test subject.

[0018] Step S112: When the current group of interactive digital games ends, use the hybrid decision unit to dynamically adjust the task difficulty of the next group of interactive digital games based on the dynamic cognitive state vector fed back in step S130. A real-time dynamic cognitive state vector is extracted from the individual vector pool of the tested individual. This dynamic cognitive state vector sequence, which marks the current group of game events, is input into the hybrid decision unit to determine the task difficulty of the next group of interactive digital games. The specific workflow of the hybrid decision unit is as follows: ① Use a state fuzzy inference engine to determine the current comprehensive cognitive state score of the tested individual; Substituting the real-time dynamic cognitive state vector V(t)=[A(t),I(t),F(t),E(t),C(t)] into the formula:

[0019] In this process, a comprehensive cognitive state score is obtained for the individual being tested. Where A(t) is the attention stability coefficient, I(t) is the impulse control coefficient, F(t) is the task switching fluency coefficient, E(t) is the physiological fatigue level, and C(t) is the cognitive consistency coefficient. , , , These are the weights for judging attention, impulse control, task switching, and cognitive consistency, respectively. 'a' represents the penalty index for small fluctuations in attention, and 'e' represents the penalty index for fatigue. The threshold for impulsivity is set, and k is an adjustable parameter. is the global inhibition coefficient of fatigue, representing the weakening effect of fatigue on all other cognitive abilities.

[0020] ② Use short-term performance predictors to predict an individual's likely performance score on the next more difficult task; The dynamic cognitive state vector sequence, labeled with the current set of game events, is input into the short-term performance predictor, which outputs the individual's possible performance score for the next difficulty task. .

[0021] This embodiment sets five task difficulties, each bound to different difficulty parameters. These parameters have three dimensions: time pressure, with adjustable parameters including stimulus presentation duration (e.g., the time it takes for key information to be displayed on the screen), reaction time window, stimulus interval (the time between two consecutive stimuli), and task pace; perception and distraction, with adjustable parameters including target-distractor similarity, number of distractors, visual complexity, and background noise level; and cognitive load, with adjustable parameters including working memory load (the number of units that need to be memorized simultaneously), rule complexity (the number of independent rules that need to be followed simultaneously or the depth of rule nesting), and response choice complexity (e.g., a choice between four or two). If the current game difficulty has reached the highest task difficulty, the next task difficulty will also be the highest task difficulty.

[0022] The core of the short-term performance predictor is a simplified gated recurrent unit (GRU) with an added temporal attention layer. Its training data is extracted from a large number of historical test sessions. For each training sample, the input sequence is a dynamic cognitive state vector sequence, and the prediction target is the comprehensive cognitive state score of the next trial after that sequence.

[0023] ③Based on a comprehensive assessment of current performance and predictions of future performance, generate and implement strategies to adjust task difficulty; The state fuzzy inference returned The short-term performance predictor returned Input to policy generation function In the process, the generated adjustment strategy code is returned, where , This represents the upper and lower thresholds of the standard cognitive state score. This represents the current task completion rate in the game. This is the task completion rate threshold. If the test subject is in a good current state, performs well on the next difficult task, and has achieved the target completion rate, then return 1, i.e., initiate the exploration strategy; if If the test subject's current state is at a normal level, or the task completion rate is below standard, then return 2, i.e., activate the consolidation strategy; if If the test result indicates that the individual's current state is poor or that their performance on the next difficulty task will be very poor, then return 3, which means that the compensation strategy will be activated. The exploration strategy refers to increasing the difficulty of a task, the consolidation strategy refers to keeping the difficulty of the next set of interactive digital games unchanged, and the compensation strategy refers to decreasing the difficulty of a task. If the difficulty of a task is already at its lowest, then it is not necessary to decrease it.

[0024] Step S113: Render the next set of interactive digital games based on the adjusted task difficulty; Based on the new task difficulty determined by the engine, the internal task difficulty parameters are updated, and the materials are recombined according to the new task difficulty parameter set to generate the next set of interactive digital games in real time.

[0025] Step S114: Repeat steps S112 and S113 until the maximum task volume is reached.

[0026] Step S120: Synchronously collect the behavioral response signals, physiological electrical signals, and kinematic signals generated by the individual during participation in the interactive digital game; By integrating multiple sensors, multimodal signals generated by the tested individuals during the execution of interactive digital games are collected synchronously, providing a data foundation for cognitive state analysis. This process is divided into the following sub-steps: Step S121: Synchronize the clock of all acquisition devices through a unified main control unit; The data acquisition equipment includes a high-precision touchscreen for acquiring an individual's behavioral response signals (including touch coordinates, pressure, and timestamps); a portable electroencephalogram (EEG) for acquiring the individual's physiological electrical signals, i.e., raw EEG signals; an inertial measurement unit (IMU) for acquiring the individual's kinematic signals (including acceleration and angular acceleration data at the wearing site); and an infrared eye tracker, also for acquiring the individual's kinematic signals (including fixation point and pupil data). After the device is fitted by the individual, all acquisition devices are synchronized via a unified main control unit.

[0027] Step S122: Starting from the pulse signal issued by the main control unit, synchronously collect and buffer the raw data of each acquisition device; At the start of the game, the main control unit synchronously sends a pulse signal to the acquisition device to start acquisition. After receiving the pulse signal, the acquisition device begins to acquire data, and the acquired raw data is cached in a circular buffer.

[0028] Step S123: Preprocess the collected raw data, integrate it to form a time-aligned multimodal feature matrix, and mark it with the corresponding game event tags; The raw data in the buffer is preprocessed in parallel, including: extracting the θ and β band power and P300 features of the physiological electrical signals; calculating the head motion index, wrist range of motion, gaze stability and pupillary change rate based on the kinematic signals; and calculating the reaction time, accuracy and number of impulsive trials (i.e., the number of clicks when the pressure value is greater than the threshold) based on the behavioral response signals.

[0029] After preprocessing, the extracted features are integrated along a unified time axis to form a time-aligned multimodal feature matrix X, and the feature matrix is ​​associated with the corresponding game event markers for querying.

[0030] Step S130: Calculate the dynamic cognitive state vector of the individual in real time based on the collected signals; The dynamic cognitive state vector V(t) is calculated in real time based on the preprocessed multimodal feature matrix X. The specific calculation process is divided into the following sub-steps: Step S131: Standardize and weight the multimodal feature matrix; Z-socre normalization is performed on each feature in the multimodal feature matrix X to eliminate the influence of dimensions, resulting in the matrix. Then, using an association analysis model, the weighted matrix W of the multimodal feature matrix is ​​determined based on the correlation between features and attention deficits; subsequently, the matrix... Multiplying it by the weighting matrix W yields the processed modal feature matrix. The weighting is used to amplify the main signal in the feature matrix and suppress secondary signals and noise.

[0031] Step S132: Calculate each component of the dynamic cognitive state vector in parallel based on the processed multimodal feature matrix; The formula for calculating the attention stability coefficient is as follows:

[0032] in This is the current reaction time. The optimal reaction time for this age group is obtained based on a cognitive development norm database. The accuracy rate within the sliding window (window size is the last 10 trials). Let Variance be the fixation point location. for Bandwidth power, for Bandwidth power, The preset stability assessment factor, , It is a smoothing factor used to prevent division by zero errors; The formula for calculating the impulse control coefficient is as follows:

[0033] in The impulse trial rate within the sliding window (the proportion of impulse trials with a response time < 200 ms). Head movement index, It is a characteristic of P300. The rate of change of pupil diameter. These are preset impulse assessment factors; The formula for calculating the task switching smoothness coefficient is as follows:

[0034] in The task switching cost refers to the difference in accuracy between the two windows before and after the task switch (e.g., the previous task was "sort by color", and the switch is "sort by shape"). It is the accuracy rate within the current sliding window. This represents the increase in reaction time for each task switch trial, specifically the difference in reaction time between the first trial after the task switch and the last trial of the previous task. For eye saccade speed, It is a preset smoothness evaluation factor; The formula for calculating physiological fatigue is as follows:

[0035] in express The increase in bandwidth power relative to the baseline, The rate of change of blink frequency. This shows the trend of head movement over time. The slope of the reaction time as the test progresses. These are preset fatigue assessment factors; The formula for calculating the cognitive consistency coefficient is as follows:

[0036] in This indicates the real-time correlation between features in the behavioral dimension (i.e., features extracted from behavioral response signals) and features in the physiological dimension (i.e., features extracted from physiological electrical signals); This represents the variance between different features within the same dimension. This is a preset consistency evaluation factor.

[0037] What needs to be explained is It is obtained by calculating the Spearman rank correlation coefficients between each feature of the behavioral dimension and each feature of the physiological dimension within a sliding window, and then taking the average.

[0038] Step S133: After adding a timestamp and game event marker to the calculated dynamic cognitive state vector, output it to the individual's separate vector pool; The system creates a separate vector pool for each individual to store the dynamic cognitive state vectors generated in the game, and adds timestamps and game event markers for easy retrieval.

[0039] Step S140: Perform joint analysis on the difficulty parameters used in the entire series of interactive digital games and the dynamic cognitive state vectors they reflect, and generate the final verification report. The multi-dimensional data generated throughout the testing process is integrated and analyzed, and an objective and accurate test report is generated through a rigorously trained attention deficit detection model. The specific implementation process is as follows: Step S141: Construct a sensing matrix using the difficulty parameters used in different groups of interactive digital games as rows and the dynamic cognitive state vector sequence fed back in the game as columns; If the lengths of the dynamic cognitive state vector sequences from different game feedback groups are inconsistent, then interpolation is needed to unify all sequences to a fixed length.

[0040] Step S142: Input the sensing matrix into the attention deficiency detection model and output the deficiency judgment result; The attention deficit detection model is a multi-channel deep neural network, consisting of a three-layer architecture: an input layer, a feature fusion and classification layer, and an output layer. The input layer receives the standardized induction matrix M and has two feature extraction channels. Temporal feature channel: A bidirectional gated recurrent unit (Bi-GRU) layer is used to capture the long-term dependencies and contextual information of dynamic cognitive states as task difficulty changes; a self-attention mechanism is also introduced after the Bi-GRU layer, which allows the model to focus on key time segments and features most relevant to ADHD diagnosis. Local pattern channel: A one-dimensional convolutional neural network (1D-CNN) layer is used to extract local correlation patterns at different time scales in the sensing matrix using convolutional kernels of different sizes; The feature fusion and classification layer is used to concatenate the temporal features output from the Bi-GRU channel and the local features output from the CNN channel; then, it is passed through a fully connected layer for nonlinear transformation and feature fusion. Finally, a three-class probability distribution is generated through a Softmax output layer, which is the defect judgment result: [typical development, ADHD-attention deficit dominant type, ADHD-hyperactivity and impulsivity dominant type].

[0041] Step S143: Statistically assess the individual's ability strength across various cognitive dimensions, and combine the results to generate the final test report; First, the mean of each component in the dynamic cognitive state vector of the individual's feedback throughout the entire series of games is calculated. This mean is compared with the norm data of children of the same age to form a standard score. Then, the standard scores of each component are visualized in the form of a radar chart, i.e., an ability profile, to show the individual's strength and weakness in each cognitive dimension. The classification result with the highest confidence in the defect judgment results is taken as the individual's primary defect. If the difference between the second highest confidence and the highest confidence is less than a preset threshold, the second highest classification result is taken as the individual's secondary defect; otherwise, no secondary defect is set. The above results are integrated into a standardized report, which includes basic information (individual information, test time), core conclusions (primary defect, secondary defect), and the ability profile.

[0042] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor for running one or more program instructions to perform a method for testing attention deficit in children that integrates gamified tasks.

[0043] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are executed by a processor to provide a method for detecting attention deficit in children that integrates gamified tasks.

[0044] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions that, when executed on a computer, cause the computer to perform the aforementioned method for detecting attention deficit in children by integrating gamified tasks.

[0045] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0046] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0047] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0048] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0049] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0050] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0051] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0052] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for detecting attention deficit in children using integrated gamified tasks, characterized in that, include: Step S110: Using an adaptive task generation engine, present a series of interactive digital games with cognitive load to the test subjects; Step S120: Synchronously collect the behavioral response signals, physiological electrical signals, and kinematic signals generated by the individual during participation in the interactive digital game; Step S130: Calculate the dynamic cognitive state vector of the individual in real time based on the collected signals; Step S140: Perform joint analysis on the difficulty parameters used in the entire series of interactive digital games and the dynamic cognitive state vectors they reflect, and generate the final verification report.

2. The method for detecting attention deficit in children using integrated gamified tasks according to claim 1, characterized in that, Using an adaptive task generation engine, a series of interactive digital games with cognitive load are presented to the test subjects, specifically in the following sub-steps: The adaptive task generation engine is initialized based on the metadata of the tested individual to generate the first set of interactive digital games; When the current group of interactive digital games ends, the task difficulty of the next group of interactive digital games is dynamically adjusted based on the dynamic cognitive state vector fed back from step S130 using the hybrid decision unit. Render the next set of interactive digital games based on the adjusted task difficulty; The task difficulty adjustment and digital game rendering steps are repeated until the maximum task volume is reached.

3. The method for detecting attention deficit in children using integrated gamified tasks according to claim 2, characterized in that, The adaptive task generation engine is initialized based on the metadata of the tested individual to generate the first set of interactive digital games, which is divided into the following sub-steps: Based on the metadata of the tested individual, the developmental assessment data of children under the same conditions were retrieved from the pre-set cognitive development norm database, and the mean value was used as an initial cognitive ability baseline. The corresponding initial task parameters are retrieved based on the initial cognitive ability baseline; Based on the initial task parameters, the corresponding materials are retrieved from the multi-dimensional task material library, assembled into the first set of interactive digital games, and rendered.

4. The method for detecting attention deficit in children using integrated gamified tasks according to claim 3, characterized in that, The Cognitive Development Norm Database is a structured data warehouse that collects and integrates large-scale, de-identified child development assessment data from multiple medical institutions, including assessment records of children diagnosed with ADHD and children with typical development. The database contains a demographic norm table and a task parameter mapping table. The demographic norm table uses age, sex, and past medical history as key indexes to store attention performance parameters of children of different ages on various core assessment tasks. The task parameter mapping table defines the correlation between initial task parameters and different attention performance levels.

5. The method for detecting attention deficit in children using integrated gamified tasks according to claim 3, characterized in that, The multidimensional task material library stores the basic elements that make up all interactive digital games and defines the corresponding material category identifier and material attributes for each element.

6. The method for detecting attention deficit in children using integrated gamified tasks according to claim 2, characterized in that, The specific workflow of the hybrid decision-making unit is as follows: Use a state fuzzy inference engine to determine the current comprehensive cognitive state score of the tested individual; Use short-term performance predictors to predict an individual's likely performance score on the next more difficult task; The strategy for adjusting the difficulty of the generated task is then implemented based on a comprehensive assessment of current performance and predictions of future performance.

7. The method for detecting attention deficit in children using integrated gamified tasks according to claim 1, characterized in that, The process of synchronously collecting behavioral response signals, physiological electrical signals, and kinematic signals generated by the individual during participation in the interactive digital game involves the following sub-steps: All acquisition devices are clock-synchronized through a unified main control unit; Starting with the pulse signal emitted by the main control unit, the raw data from each acquisition device is collected and buffered synchronously. The collected raw data is preprocessed and integrated to form a time-aligned multimodal feature matrix, and then labeled with the corresponding game event tags.

8. The method for detecting attention deficit in children using integrated gamified tasks according to claim 1, characterized in that, The dynamic cognitive state vector of the individual is calculated in real time based on the collected signals, which is specifically divided into the following sub-steps: The multimodal feature matrix is ​​standardized and weighted. The components of the dynamic cognitive state vector are calculated in parallel based on the processed multimodal feature matrix. The calculated dynamic cognitive state vector is timestamped and marked with game events before being output to a separate vector pool for the tested individual.

9. The method for detecting attention deficit in children using integrated gamified tasks according to claim 1, characterized in that, A joint analysis of the difficulty parameters used in the entire series of interactive digital games and the dynamic cognitive state vectors they reflect is conducted to generate a final verification report, which is specifically divided into the following sub-steps: Using the difficulty parameters adopted by different groups of interactive digital games as rows and the dynamic cognitive state vector sequence fed back in the game as columns, a sensing matrix is ​​constructed; The induction matrix is ​​input into the attention deficiency detection model, and the deficiency judgment result is output. The test results are used to calculate the strength of the individual's cognitive abilities across various dimensions and generate a final test report.

10. A computer storage medium, characterized in that, include: At least one memory and at least one processor; Memory, used to store one or more program instructions; A processor for running one or more program instructions to perform a method for testing attention deficit in children that integrates gamified tasks as described in any one of claims 1-9.

Images