Method and system for evaluating and training attention of children

Abstract

The invention relates to a child attention evaluation and training method and system, and the method comprises the steps: obtaining a brain wave mode, an eyeball movement track, an emotion activation level and autonomic nervous system function data of a child in real time, and generating multi-dimensional biological signal data; based on the multi-dimensional biological signal data, generating evaluation task data; generating dynamic task parameters according to biological signal data and behavior performance data in the evaluation task data; generating an attention feedback signal based on the dynamic task parameters; according to the attention feedback signal, a training task integrating work memory, suppression control and cognitive flexibility is constructed, and cognitive function training data is generated; and based on the cognitive function training data, synchronously sharing the attention performance data of the children to the parent terminal and the teacher terminal, generating life situation intervention suggestions, and iteratively optimizing evaluation parameters according to a long-term effect evaluation result. Therefore, the accuracy of children attention evaluation and training can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, system, electronic device and non-transitory computer-readable storage medium for evaluating and training children's attention. Background Art

[0002] Attention is a core competency in children's cognitive development, significantly impacting learning efficiency, academic achievement, and social adaptability. Existing methods for assessing and training children's attention primarily include behavioral measures based on paper-and-pencil tests, computerized attention tasks (such as the Continuous Performance Test (CPT) and the Stroop test), and parent- or teacher-administered scale assessments (such as the Conners Attention Deficit Inventory).

[0003] However, paper-and-pencil tests and scale-based assessments are highly subjective and easily influenced by the assessor's subjective judgment or environmental factors, lacking objectivity and timeliness. Furthermore, traditional computer tasks often depart from children's real cognitive contexts, making it difficult to sustain their attention and resulting in low ecological validity. Summary of the Invention

[0004] The present invention addresses the technical problems existing in the prior art and provides a method, system, electronic device and non-transitory computer-readable storage medium for children's attention assessment and training, which can improve the accuracy of children's attention assessment.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: The present invention provides a method for evaluating and training children's attention, the method comprising: Acquire children's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; Based on the multidimensional biosignal data, constructing a virtual reality environment that matches the child's age, and embedding sustained, selective, distributed, and switching attention tasks to generate assessment task data; According to the biological signal data and behavioral performance data in the evaluation task data, the difficulty and interference intensity of each task are adjusted in real time to generate dynamic task parameters; Based on the dynamic task parameters, the biosignal data is converted into a real-time audiovisual feedback signal, and an attention feedback signal is generated through element responses and prompt signals in the virtual environment; constructing a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal to generate cognitive function training data; Based on the cognitive function training data, the child's attention performance data is synchronously shared with the parent terminal and the teacher terminal, life situation intervention suggestions are generated, and the evaluation parameters are iteratively optimized according to the long-term effect evaluation results.

[0006] Optionally, the real-time acquisition of the child's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data to generate multi-dimensional biosignal data includes: By integrating a micro electroencephalogram sensor, energy values ​​of alpha wave, beta wave and theta wave frequency bands in the frontal lobe and parietal lobe areas of the child are collected; The eye tracking module built into the glasses frame records the child's gaze point coordinates, scanning path length, and blink frequency; measuring a skin conductance response value of the child using a fingertip skin conductance response sensor, and generating an emotional activation level indicator based on the skin conductance response value; The heart rate variability monitor is used to calculate the interval standard deviation, and the autonomic nervous system function data is evaluated based on the interval standard deviation to obtain an evaluation result.

[0007] Optionally, based on the multi-dimensional biosignal data, a virtual reality environment is constructed that matches the child's age and embeds sustained, selective, distributed, and switching attention tasks, including: Build a virtual space containing floating animated objects for first-year children and embed sustained attention tasks, such as continuously tracking the movement trajectory of a designated color object; Construct learning scenarios for second-year children that include dynamic distractors and embed selective attention tasks, such as identifying target mathematical symbols against a flickering background; Constructing multi-role social scenarios for third-year children and embedding divided attention tasks, such as simultaneously processing conversational audio cues and visual cues; A rule switching task was set in all scenes, and a switching attention task was embedded in the scenes of the rule switching task.

[0008] Optionally, adjusting the difficulty and interference intensity of each task in real time based on the biological signal data and behavioral performance data in the assessment task data includes: When the ratio of the energy of the theta wave to the energy of the beta wave decreases by 15% and the task error rate is less than 5%, the complexity level of each task is increased; When the child's eye movement distraction exceeds a preset threshold, increasing the dynamic change frequency of the visual distraction elements to 120% of the threshold; Based on the ratio of low-frequency power to high-frequency power of heart rate variability, the auditory interference intensity is adjusted in real time to keep the task difficulty within the preset challenge range; When the peak value of skin conductance response continues to exceed the standard, a 90-second relaxation training module is automatically triggered.

[0009] Optionally, converting the biosignal data into a real-time audiovisual feedback signal includes: When it is detected that the power of the beta wave increases and the power of the theta wave decreases, controlling the task target object in the virtual environment to emit light and playing a reward sound effect; When the child's eye movement trajectory deviates from the task area and exceeds a preset timeout threshold, generating a pulse vibration prompt signal; In the intermediate stage of neurofeedback training, the feedback signal output is delayed by m seconds to enhance the ability to maintain attention; In the advanced stage, the audiovisual feedback intensity is attenuated to n% of the initial value, where m and n are both greater than 0.

[0010] Optionally, the training tasks include a working memory training task, an inhibitory control training task, and a cognitive flexibility training task, wherein: The working memory training task is used to train the child to memorize and reproduce the color sequence of moving objects in a virtual scene; The inhibitory control training task is used to train the child to inhibit responses to non-target shapes in a rapidly flashing stream of stimuli; The cognitive flexibility training task is used to train the child to switch between classification rules according to environmental prompts.

[0011] Optionally, synchronously sharing the child's attention performance data to a parent terminal and a teacher terminal based on the cognitive function training data includes: Converting the attention maintenance duration and task switching efficiency indicators into a daily training report displayed on the parent terminal; Based on the fluctuation pattern of classroom attention, push reminders of key teaching periods to the teacher's terminal; Generate life situation intervention suggestions, and when it is detected that the child's attention reaches its peak, suggest arranging important learning content; Push micro-training tasks based on real-life scenarios through mobile devices.

[0012] Optionally, the iterative optimization of evaluation parameters according to the long-term effect evaluation results includes: Adjust the sensitivity threshold of the dynamic difficulty algorithm based on task performance improvement data; Optimize the weight distribution of cognitive function training tasks based on learning ability improvement data; Update the distribution of task types and distraction intensities in a virtual reality environment based on long-term academic performance change data.

[0013] Optionally, also include: In a multi-person collaborative mode for evaluating multiple children, automatically matching training partners based on EEG coherence analysis results of the multiple children; A collaborative task requiring joint attention was constructed, requiring a team of at least two children to synchronously control the balance of a virtual object. When an abnormally elevated skin conductance response is detected in one of the children in the evaluation group, a peer assistance prompting mechanism is automatically triggered; The joint attention maintenance duration of all children in the evaluation group in the social scene is recorded, and a social attention coordination index is generated based on the joint attention maintenance duration.

[0014] The present invention also provides a system for evaluating and training children's attention, the system comprising: The first generation module is used to obtain children's brain wave patterns, eye movement trajectories, emotional activation levels and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; a second generation module, configured to construct a virtual reality environment that matches the child's age based on the multi-dimensional biosignal data, and embed sustained, selective, distributed, and switching attention tasks to generate assessment task data; A third generation module is used to adjust the difficulty and interference intensity of each task in real time based on the biological signal data and behavioral performance data in the evaluation task data to generate dynamic task parameters; a fourth generating module, configured to convert the biosignal data into a real-time audiovisual feedback signal based on the dynamic task parameters, and generate an attention feedback signal through element responses and prompt signals in the virtual environment; A training data module, configured to construct a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal, and generate cognitive function training data; The evaluation optimization module is used to synchronously share the child's attention performance data to the parent terminal and the teacher terminal based on the cognitive function training data, generate life situation intervention suggestions, and iteratively optimize the evaluation parameters according to the long-term effect evaluation results.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing a method for evaluating and training children's attention as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements a method for evaluating and training children's attention as described above.

[0017] The beneficial effects of the present invention are: This invention addresses the "one-size-fits-all" problem of traditional attention training through personalized intervention driven by multimodal data. Furthermore, through an immersive VR environment and dynamic adaptive mechanisms, it significantly improves the ecological validity of training and child engagement. Its family-school linkage model and long-term effect evaluation system further ensure the sustainability of intervention results, providing a scientific, efficient, and practical solution for children's attention development. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for evaluating and training children's attention provided by the present invention; Figure 2 A schematic diagram of the structure of a system for evaluating and training children's attention provided by the present invention; Figure 3 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 4 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0021] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0022] See also Figure 1 , provides a flowchart of a method for evaluating and training children's attention of the present invention, comprising the following steps: Step 201: Acquire the child's brain wave pattern, eye movement trajectory, emotional activation level, and autonomic nervous system function data in real time to generate multi-dimensional biosignal data.

[0023] In specific implementations, a micro EEG sensor integrated into a comfortable headband worn on the child's head can collect real-time energy values ​​in the alpha, beta, and theta wave bands in the frontal and parietal regions. Simultaneously, an eye-tracking module built into the eyeglass frame records gaze coordinates, saccade path length, and blink frequency for analysis of attention distribution. A fingertip skin conductance response (GSR) sensor measures changes in skin conductance to quantify emotional activation levels. Furthermore, a heart rate variability (HRV) monitor calculates the standard deviation of RR intervals to assess the functional state of the autonomic nervous system. Together, these data form a multidimensional biosignal dataset reflecting the child's current psychological and physiological state.

[0024] In some embodiments, step 201 may include: By integrating a miniature EEG sensor, the energy values ​​of the alpha, beta and theta wave frequency bands in the frontal and parietal regions of children are collected; The eye tracking module built into the glasses frame records the children's gaze coordinates, scanning path length, and blink frequency; The skin conductance response value of the child is measured by a fingertip skin conductance response sensor, and an emotional activation level index is generated based on the skin conductance response value; The standard deviation of the intervals was calculated using a heart rate variability monitor, and the autonomic nervous system function data were evaluated based on the standard deviation of the intervals to obtain the assessment results.

[0025] In one specific embodiment, a comfortable and lightweight headband with integrated micro-EEG sensors is specifically designed to collect real-time brain activity in a child's frontal and parietal regions. This sensor accurately captures the energy levels of the alpha (8-12Hz), beta (13-30Hz), and theta (4-7Hz) frequency bands. Energy changes in these specific frequency bands directly reflect the characteristics of brain activity in different states. For example, higher beta wave energy is typically associated with high concentration and alertness, while increased theta wave energy may indicate a state of relaxation or distraction. By analyzing the energy distribution of these waveforms, a child's current attention level and its fluctuations can be accurately assessed.

[0026] Furthermore, a high-precision eye tracking module is embedded in the glasses frame. This module can continuously record key parameters such as the child's gaze coordinates, saccade path length, and blink frequency without affecting the wearer's visual experience. The precise measurement of the gaze coordinates helps to understand the location and time distribution of the child's gaze focus, the saccade path length provides information about the range of eye movement, and changes in blink frequency are often an important indicator of fatigue. Combining this data, the system can construct a heat map of the child's attention distribution during the task, and then identify factors that may cause distraction.

[0027] To quantify children's emotional activation levels, fingertip skin conductance response (GSR) sensors are used for real-time monitoring. GSR sensors detect changes in skin electrical resistance, reflecting sweat gland activity, an indirect marker of sympathetic nervous system activity. As emotional tension or excitement increases, sweat gland secretion increases, leading to an increase in skin conductance. Based on the collected skin conductance response values, the system calculates a standardized emotional activation index to measure the intensity of children's emotional reactions to different types of stimuli. This metric is crucial for understanding how emotions influence cognitive processes.

[0028] In addition, a heart rate variability (HRV) monitor is used to calculate the standard deviation of the RR interval to assess the functional state of the autonomic nervous system. HRV refers to the slight difference in the time interval between heartbeats. It reflects the heart's ability to adapt to changes in the external environment and is one of the important parameters for evaluating the balance of the autonomic nervous system. Specifically, the HRV monitor obtains continuous heartbeat data through non-invasive means and uses an algorithm to calculate the standard deviation of the RR interval. Lower HRV values ​​usually indicate weakened parasympathetic nerve activity or overactive sympathetic nerves, which may be a manifestation of stress or anxiety; conversely, higher HRV values ​​mean better self-regulation ability and a healthier physiological state. Based on this result, the system can provide in-depth insights into the child's overall health status and guide adjustments to subsequent training plans.

[0029] Through this method, the present invention achieves comprehensive monitoring of children's multi-dimensional physiological and psychological states, providing a solid data foundation for personalized attention assessment and training. These detailed biosignals not only reveal individual differences but also provide a basis for developing more precise and effective intervention strategies.

[0030] Step 202: Based on the multi-dimensional biosignal data, a virtual reality environment that matches the child's age is constructed, and sustained, selective, distributed, and switching attention tasks are embedded to generate evaluation task data.

[0031] In specific implementations, the system can customize virtual reality (VR) environments for children of different age groups based on the multi-dimensional biosignal data collected above. For example, for children aged 3-5, a space containing floating animated objects is created, and they are required to continuously track the movement of objects of a specific color to test their sustained attention. Children aged 6-9 face learning scenes with dynamic distractors, identifying target mathematical symbols against a flashing background to exercise selective attention. Children aged 10-12 participate in multi-role social situations, processing voice prompts and visual cues simultaneously to enhance distributed attention. Rule switching tasks are set up in all environments, such as adjusting operation rules according to changes in scene color to examine conversion attention.

[0032] In some embodiments, step 202 may include: Build a virtual space containing floating animated objects for first-year children and embed sustained attention tasks, such as continuously tracking the movement trajectory of a designated color object; Construct learning scenarios for second-year children that include dynamic distractors and embed selective attention tasks, such as identifying target mathematical symbols against a flickering background; Constructing multi-role social scenarios for third-year children and embedding divided attention tasks, such as simultaneously processing conversational audio cues and visual cues; A rule switching task was set in all scenes, and a switching attention task was embedded in the rule switching task scenes.

[0033] Specifically, for children in the first age group (3-5 years old), the system has designed an interesting and interactive virtual space. This space contains floating animated objects that move slowly and regularly in the air, attracting children's attention and stimulating their curiosity. For example, the system can generate a series of brightly colored balloons or small animal images in various shapes, floating along a specific path. To embed a sustained attention task, children are required to continuously track the movement of objects of a specified color. In this way, not only can children's ability to focus on a single target be assessed, but they can also help them develop basic visual tracking skills. This simple and intuitive task setting is ideal for children of this age, as their cognitive abilities and attention spans are limited and they need specific, easy-to-understand goals to maintain their interest.

[0034] For children in the second age group (6-9 years old), the system constructs a more complex learning scenario with dynamic distractors, which is designed to challenge and improve their selective attention. In this scenario, the background will constantly flash and change, and multiple mathematical symbols or other learning elements will appear at the same time. The child's task is to accurately identify specific target mathematical symbols, such as the number "5" or the plus sign "+", under these distractions. This task design helps to train children's ability to filter important information under information overload, simulating situations they may encounter in actual classroom environments. By adjusting the number and frequency of distractors, the system can adjust the difficulty of the task in real time according to each child's performance to ensure moderate challenge and promote the best learning effect.

[0035] For children in the third age group (10-12 years old), the system creates a multi-role social scene to encourage them to engage in more complex interactive learning. In this scene, children will face multiple virtual characters, each with its own dialogue content or visual clues. In order to complete the distributed attention task, children need to process information from different sources at the same time, such as listening to the voice prompts of one character while observing the visual clues displayed by another character. For example, in a virtual cooperative game, two characters may provide different instructions respectively, and the child needs to make correct responses based on these two instructions. This method not only improves children's information processing efficiency, but also promotes the development of their teamwork and social interaction skills.

[0036] Regardless of the age group, the system will set up rule-switching tasks in the virtual scenes to cultivate children's switching attention. For example, in the floating animated object scene of the first age group, after the children successfully track it for a period of time, the system will suddenly change the rules and require them to track objects of another color or shape; in the learning scene of the second age group, the originally flashing background may become static, but the color or size of the target symbol will change; and in the social scene of the third age group, the rules of interaction between characters may also change at any time, such as switching from auditory instructions to visual signals. Through these rule-switching tasks, the system encourages children to quickly adapt to new task requirements, thereby effectively improving their flexibility and adaptability.

[0037] Through this method, the present invention not only achieves customized VR environments and attention tasks tailored to the cognitive development characteristics of children of different age groups, but also dynamically adjusts task parameters to ensure that each child receives the most appropriate challenge within their "zone of proximal development." This not only enhances the effectiveness and interest of training, but also provides strong support for personalized education.

[0038] Step 203: Based on the biological signal data and behavioral performance data in the evaluation task data, the difficulty and interference intensity of each task are adjusted in real time to generate dynamic task parameters.

[0039] In practice, the system leverages biosignals (such as theta / beta wave ratio) and behavioral performance (such as error rate) derived from assessment tasks to adjust task difficulty in real time. If a decrease in theta wave energy and an increase in beta wave energy are detected, indicating a high state of focus, the task complexity is appropriately increased. Conversely, if eye movement dispersion exceeds a set threshold, indicating a loss of attention, more distractions are introduced or the task requirements are reduced. This ensures that every child is challenged within their "zone of proximal development," promoting optimal learning outcomes.

[0040] In some embodiments, step 203 may include: When the ratio of theta wave energy to beta wave energy drops by 15% and the task error rate is less than 5%, the complexity level of each task is increased; When the child's eye movement distraction exceeds the preset threshold, the dynamic change frequency of the visual distraction elements is increased to 120% of the threshold; Based on the ratio of low-frequency power to high-frequency power of heart rate variability, the auditory interference intensity is adjusted in real time to keep the task difficulty within the preset challenge range; When the peak value of skin conductance response continues to exceed the standard, a 90-second relaxation training module is automatically triggered.

[0041] In this implementation, the system monitors the energy ratio of theta waves (4-7Hz) to beta waves (13-30Hz) in the frontal and parietal regions of children's electroencephalogram (EEG) signals in real time. When the ratio of theta waves to beta waves decreases by 15% and the task error rate falls below 5%, the system determines that the child is currently in a state of high concentration and capable of taking on higher challenges. At this point, the system automatically increases the complexity of the current task. For example, in a virtual reality environment, the speed of the target object's movement may be increased, additional distracting elements may be introduced, or task response time may be shortened. This mechanism ensures that training tasks remain within the child's "zone of proximal development," promoting the continuous improvement of attentional skills.

[0042] The system uses the eye tracking module built into the glasses frame to record the coordinates of the child's gaze point in real time and calculate the degree of gaze dispersion, that is, the degree of deviation between the current gaze point and the core area of ​​the task. When the eye gaze dispersion exceeds the preset threshold (for example, the standard deviation is greater than 1.5° visual angle), the system determines that the child's attention has begun to decline. In order to increase the challenge of the task and stimulate attention recovery, the system increases the dynamic change frequency of visual interference elements to 120% of the original set frequency. For example, adding an interfering pattern with a higher flickering frequency to the background, or speeding up the movement of irrelevant objects. This dynamic adjustment mechanism helps guide children to refocus on the task goals while enhancing their selective attention ability.

[0043] The system collects children's RR interval data using a heart rate variability (HRV) monitor and calculates the ratio of low-frequency power (LF, 0.04-0.15Hz) to high-frequency power (HF, 0.15-0.4Hz) as an indicator of the balance between the sympathetic and parasympathetic nervous systems. When the LF / HF ratio increases, it indicates that the child is in a state of high arousal, suitable for increasing the challenge of the task; conversely, when the LF / HF ratio decreases, it indicates decreased attention or fatigue. Based on this ratio, the system dynamically adjusts the intensity of auditory interference, for example by changing the volume, rhythm, or complexity of background noise, to maintain the overall difficulty of the task within a preset challenge range (e.g., 70%-85% of the optimal attention range). This mechanism helps maintain children's attention stability and training motivation.

[0044] The system continuously monitors children's emotional activation levels using fingertip galvanic skin response (GSR) sensors. When the GSR peak value consistently exceeds a preset safety threshold (e.g., 150% of the baseline value for more than 30 seconds), the system determines that the child is in a state of emotional overactivation or stress. To prevent attention fatigue or emotional breakdown, the system automatically triggers a 90-second relaxation training module. This module includes guided deep breathing exercises, transitions to virtual nature scenes (e.g., a forest or beach), soft background music, and visual biofeedback (e.g., simultaneous display of heart rate waveforms). This mechanism maintains training intensity while also ensuring the child's psychological comfort and sustainability.

[0045] In summary, this example achieves precise perception and personalized intervention of children's attentional states through real-time analysis of multimodal biosignals and dynamic adjustment of task difficulty and interference intensity. This method not only enhances the scientific nature and effectiveness of training but also provides technical support for systematic intervention of children's attention disorders.

[0046] Step 204: Based on the dynamic task parameters, the biological signal data is converted into a real-time audio-visual feedback signal, and an attention feedback signal is generated through the element response and prompt signal in the virtual environment.

[0047] In specific implementation, once the dynamic task parameters are determined, the system converts biosignals into intuitive audiovisual feedback. For example, when a significant increase in beta wave power and a decrease in theta wave power are detected, the target object in the virtual environment will light up and play positive sound effects to encourage high attention levels. If the eye movement trajectory deviates from the task area for more than a specified time, a pulsed vibration reminder will be triggered to help refocus. This immediate feedback mechanism helps to reinforce positive behavior while correcting distractions.

[0048] In some embodiments, step 204 may include: When the power of the beta wave is detected to increase and the power of the theta wave is detected to decrease, the task target object in the virtual environment is controlled to light up and a reward sound effect is played; When the child's eye movement trajectory deviates from the task area and exceeds the preset timeout threshold, a pulse vibration prompt signal is generated; In the intermediate stage of neurofeedback training, the feedback signal output is delayed by m seconds to enhance the ability to maintain attention; In the advanced stage, the audiovisual feedback intensity is attenuated to n% of the initial value, where m and n are both greater than 0.

[0049] In one specific embodiment, the system monitors EEG signals in the frontal and parietal regions of children in real time, paying particular attention to changes in the power of beta waves (13-30 Hz) and theta waves (4-7 Hz). When an increase in beta wave power and a decrease in theta wave power are detected, this generally indicates that the child is in a state of high concentration. At this point, the system immediately responds in the virtual environment, controlling the task target object to light up and playing reward sound effects. For example, in a virtual treasure hunt game, if a child successfully tracks down a hidden treasure, the treasure will emit a bright light and be accompanied by cheerful music as recognition and encouragement of their high state of attention. This immediate positive feedback helps to reinforce positive behavior patterns and motivates children to maintain their focus.

[0050] In addition, the system uses the eye tracking module built into the glasses frame to record in real time the coordinates of the child's gaze point and its position changes relative to the core task area. When the eye movement trajectory deviates from the task area for more than a preset timeout threshold (for example, 5 seconds), the system determines that the child's attention is beginning to wander. To help them refocus, the system generates a pulsed vibration prompt signal. Specifically, this vibration can be achieved through a wearable bracelet or a vibration device integrated into the seat, providing a short but intense tactile stimulation. The frequency and intensity of the vibration can be adjusted according to individual differences to ensure that it attracts attention without causing excessive interference. This mechanism effectively reminds children to return to the current task and prevents long-term loss of attention.

[0051] As training progresses into the intermediate stage, the system introduces a new feedback strategy to further enhance children's ability to sustain attention: delayed feedback signal output for m seconds (m>0). During this period, even if a desirable brainwave pattern (such as rising beta waves or falling theta waves) is detected, the system will not immediately provide a visual or auditory reward. Instead, the system will trigger the reward after a delay of m seconds. This delay is designed to cultivate children's internal perception and regulation of their own attention state, reducing their reliance on external rewards. For example, if m is set to 3 seconds, then the child will only receive the corresponding reward feedback if they maintain a high level of attention for at least 3 consecutive seconds. This approach helps train children to maintain their focus even without immediate external motivation.

[0052] In the advanced training stage, to further challenge children's attention control ability, the system gradually attenuates the intensity of audiovisual feedback to n% of the initial value (n>0). For example, if the task target object emits a strong flash and plays a high-volume reward sound effect under the initial setting, then in the advanced stage, the intensity of these feedback signals will be weakened to 30% of the original intensity (i.e., n=30). This means that children need to rely more on their own internal feelings to judge their attention state, rather than relying solely on strong signals provided by the outside world. By gradually reducing external assistance, the system encourages children to develop stronger self-monitoring and regulation abilities, ultimately achieving the goal of effectively maintaining attention without external intervention.

[0053] In summary, this invention precisely analyzes children's multimodal biosignal data and dynamically adjusts the audiovisual feedback mechanism in the virtual environment accordingly. This not only instantly responds to children's attentional state but also gradually increases the difficulty level based on training progress, promoting the development of attention maintenance and self-regulation skills. This personalized, adaptive training method provides a scientific and effective solution to children's attention problems.

[0054] Step 205: Based on the attention feedback signal, construct a training task that integrates working memory, inhibitory control, and cognitive flexibility to generate cognitive function training data.

[0055] In practice, a series of tasks designed to enhance core cognitive skills can be designed based on attention feedback signals. For example, children might be asked to memorize and reproduce the color sequence of moving objects in a virtual space to strengthen working memory; ignore irrelevant information in a rapidly presented stream of stimuli to cultivate inhibitory control; and flexibly switch between different classification rules based on environmental sound cues to improve cognitive flexibility. The duration of each task is dynamically adjusted based on individual indicators such as prefrontal EEG asymmetry to ensure a personalized training experience.

[0056] In some embodiments, step 205 may include: The training tasks include working memory training tasks, inhibitory control training tasks and cognitive flexibility training tasks, among which: A working memory training task was used to train children to memorize and reproduce the color sequence of moving objects in a virtual scene; The inhibitory control training task was used to train children to inhibit responses to non-target shapes in a rapidly flashed stream of stimuli; The cognitive flexibility training task was used to train children to switch between classification rules according to environmental cues.

[0057] In this embodiment, the working memory training task is used to train children's short-term storage and operation capabilities for dynamic information. Specifically, the system generates multiple objects that move along a specific path in a virtual scene, and each object has a different color. During the training process, the system first shows the child a sequence of objects of multiple colors, and then the sequence disappears, requiring the child to reproduce the color arrangement seen in order within a certain period of time. For example, in a "color train" training task, the child needs to remember the color sequence of a train car as it passes by in sequence, and correctly arrange these colors in the subsequent selection interface. This task gradually increases the working memory load by constantly changing the number of objects and the presentation time, thereby effectively training children's ability to encode, retain and retrieve information while concentrating their attention.

[0058] To train children's ability to inhibit irrelevant stimuli in a complex information environment, the system sets up an inhibitory control training task. This task requires children to respond only to target shapes in a stream of rapidly flashing visual stimuli, while inhibiting responses to non-target shapes. For example, in a "target shape recognition" task, a circle, triangle, and square flash on the screen in sequence at high speed. The system prompts the child to press a button only when the circle is seen, while ignoring other shapes. The frequency and similarity of the distracting items introduced in the task can be dynamically adjusted to match the child's current attention level. Through this task, children learn to maintain selective attention in distracting situations, improving their ability to resist distractions in real life.

[0059] Cognitive flexibility training tasks are designed to enhance children's ability to flexibly switch between different rules. In this embodiment, the system guides children to adjust their classification or operation rules in real time according to changes in external cues through task design in a virtual environment. For example, in a "rule switching maze" task, children need to switch between two classification rules based on environmental cues (such as tones of different frequencies): when a high-pitched tone is heard, objects are classified by shape; when a low-pitched tone is heard, objects are classified by color. The system will randomly change the cues, requiring children to quickly adjust their response strategies. This task not only trains children's attention control ability, but also promotes the development of their cognitive flexibility, helping them to quickly adapt to new rules in complex and changing learning and social environments.

[0060] In summary, this invention achieves systematic training of children's executive functions by constructing working memory, inhibitory control, and cognitive flexibility training tasks within a virtual reality environment. This training system, combined with a multimodal biosignal feedback mechanism, dynamically adjusts task difficulty and content based on individual performance, thereby improving children's overall attention and cognitive regulation abilities. This system has promising educational applications and clinical intervention value.

[0061] Step 206: Based on the cognitive function training data, the child's attention performance data is synchronously shared with the parent terminal and the teacher terminal, life situation intervention suggestions are generated, and the evaluation parameters are iteratively optimized according to the long-term effect evaluation results.

[0062] In practice, a child's attention performance throughout the training process can be summarized into an easy-to-understand report and sent to parents and teachers' mobile devices. This includes daily training summaries, classroom attention fluctuation trends, and specific suggestions for daily routines (such as conducting important learning activities at 10 a.m.). In addition, the system will regularly conduct comprehensive assessments of short-term, medium-term, and long-term effects and update evaluation parameters accordingly, such as adjusting the color contrast of VR scenes or introducing new brain-computer interface technologies, to continuously optimize the entire training process.

[0063] In some embodiments, step 206 may include: Convert the attention span and task switching efficiency indicators into daily training reports displayed on the parent terminal; Based on the fluctuation pattern of classroom attention, reminders of key teaching periods are pushed to teachers' terminals; Generate life situation intervention suggestions and suggest arranging important learning content when it is detected that the child's attention reaches its peak; Push micro-training tasks based on real-life scenarios through mobile devices.

[0064] In this embodiment, the system collects and analyzes the child's attention performance data generated during each training session, including attention span (i.e., the duration of the child's focused state during a task) and task switching efficiency (i.e., the time and accuracy required for the child to switch between different task rules). This data is normalized and converted into easy-to-understand indicators, and a daily training report is presented in the form of charts on a parent's terminal (such as a smartphone or tablet). For example, the report may include content such as "Today's Focus Time," "Task Switching Success Rate Trend," and "Peak Attention Hours," allowing parents to intuitively understand their child's attention development and adjust their home learning arrangements accordingly.

[0065] The system further incorporates patterns of attention fluctuations exhibited by children during training, such as how concentration levels change throughout the day, to construct a personalized attention curve model. Based on this model, the system identifies periods when children's attention levels are highest (e.g., 10:00-11:00 AM) and pushes "key teaching period reminders" through the teacher's terminal (e.g., a teaching management platform or mobile device). For example, the system might prompt the teacher: "It is recommended to schedule the presentation of new math knowledge points between 10:00-11:00 AM today to match students' peak attention." This mechanism helps teachers optimize the teaching rhythm, improve classroom efficiency, and align teaching content with students' cognitive states.

[0066] To facilitate the transfer of attention training effects from virtual environments to real life, the system generates personalized intervention suggestions based on attention monitoring data. For example, if the system detects that a child's attention peaks around 10:00 a.m., it will generate a suggestion: "It is recommended to schedule important learning content, such as reading comprehension or math word problem practice, during this period to improve learning efficiency." Furthermore, the system can also combine the child's learning habits and sleep schedule to recommend appropriate learning methods, such as "It is recommended to use the 'Pomodoro' learning method, taking a 5-minute break every 25 minutes to maintain stable attention." To further enhance the generalizability of attention training, the system delivers real-world mini-training tasks via mobile devices (such as smartphones used by parents or children). These tasks are short and concise, typically lasting 2-5 minutes, and are embedded in children's daily lives. For example, while shopping in a supermarket, the system delivers a "Product Search Challenge" task, requiring children to find and remember three specific colored items within a time limit; while on the way to and from school, the system delivers an "Environmental Observation Task," requiring children to notice and repeat specific signs or numbers they see along the way. Through these real-world mini-training tasks, children practice attention control skills in real environments, improving the transferability and practicality of their attention.

[0067] In summary, this invention transforms children's attention performance data into visual reports, combines them with personalized analysis results, provides teaching suggestions to parents and teachers, and makes attention training a daily and ecological process through micro-training tasks in real-life scenarios. This system has built a multimodal children's attention training ecosystem that integrates data collection, analysis, feedback, and intervention. This system not only improves the scientific nature and personalization of training, but also provides effective support for collaborative education between families and schools.

[0068] In some embodiments, step 206 may further include: Adjust the sensitivity threshold of the dynamic difficulty algorithm based on task performance improvement data; Optimize the weight distribution of cognitive function training tasks based on learning ability improvement data; Update the distribution of task types and distraction intensities in a virtual reality environment based on long-term academic performance change data.

[0069] In this embodiment, the system regularly evaluates the child's performance improvement in various attention tasks, including indicators such as task completion speed and reduction in error rate. When it detects that the task performance improvement data reaches a preset standard (for example, the task completion speed improvement rate exceeds 15% for three consecutive weeks), the system determines that the child has adapted to the current difficulty level. At this time, the system automatically adjusts the sensitivity threshold of the dynamic difficulty algorithm to increase the response sensitivity to changes in task difficulty. For example, the threshold for changes in the EEG theta / beta wave ratio that triggers an increase in difficulty is reduced from 15% to 10%, allowing the system to identify the state of focused attention earlier and increase the complexity of the task accordingly. This mechanism ensures that training is always within the child's "zone of proximal development" and promotes the continuous improvement of attention ability.

[0070] The system further collects and analyzes data on children's learning ability improvement, such as changes in standardized attention test scores, growth in working memory capacity, and other mid-term effect indicators. When the mid-term improvement rate is lower than the preset target (for example, <10%), the system activates the task parameter reorganization algorithm to optimize the weight distribution of cognitive function training tasks. Specifically, if data analysis shows that children are making slow progress in inhibitory control, the system will increase the proportion of inhibitory control training tasks in the overall training plan; conversely, if working memory has been significantly improved, the duration of related tasks will be appropriately reduced, and the proportion of cognitive flexibility training will be increased. Through this dynamic weight adjustment mechanism, the system can accurately strengthen individual shortcomings and improve training efficiency.

[0071] In order to evaluate the long-term educational value of training, the system continuously tracks the long-term academic performance change data of children, including subject test scores, classroom participation, and the quality of homework completion. When the system identifies a significant improvement in long-term academic performance (for example, an improvement of ≥10% in math scores) or an improvement in the score on the social skills assessment scale, it is regarded as a verification of the effectiveness of the training. Based on this result, the system updates the task types and interference intensity distribution in the virtual reality environment. For example, more challenging multi-task parallel processing scenarios are introduced, or the spatial density and dynamic frequency distribution of visual interference elements are adjusted to simulate higher-level learning environment requirements. In addition, the system can also introduce a new brain-computer interface control paradigm to enhance the immersion and feedback accuracy of human-computer interaction, and further improve the ecological validity of the training.

[0072] In summary, this invention achieves closed-loop optimization of evaluation parameters by establishing a three-tiered assessment model: short-term, mid-term, and long-term. This model combines multi-dimensional data such as task performance, learning ability, and academic achievement. This mechanism not only ensures the scientific and adaptable nature of the training program but also ensures the effective transfer of attention training results to real-life learning and life scenarios, possessing significant educational application value and promising clinical applications.

[0073] In some embodiments, the present invention may further include: In the multi-person collaborative mode for evaluating multiple children, training partners are automatically matched based on the EEG coherence analysis results of multiple children; A collaborative task requiring joint attention was constructed, requiring a team of at least two children to synchronously control the balance of a virtual object. When an abnormally elevated skin conductance response is detected in one child in the evaluation group, the peer assistance prompting mechanism is automatically triggered; The joint attention duration of all children in the evaluation group in social scenarios was recorded, and a social attention coordination index was generated based on the joint attention duration.

[0074] In a multi-person collaborative mode for assessing and training the attention of multiple children, the system uses a miniature electroencephalogram (EEG) sensor integrated into the child's headband to collect each child's brainwave signals in real time while performing the task, focusing specifically on alpha, beta, and theta wave activity in the frontal and parietal regions. The system further analyzes EEG coherence between different children, i.e., the degree of synchronization between brain signals of different individuals within the same frequency range. EEG coherence is widely used to measure interpersonal neural synchronization and is an important indicator for predicting collaborative efficiency and social compatibility.

[0075] Based on this analysis, the system automatically matches children using a clustering algorithm, prioritizing individuals with high EEG coherence for evaluation. For example, if two children exhibit strong alpha wave coherence in their prefrontal cortex while performing an attention task, this indicates a high degree of consistency in their cognitive rhythm and attention regulation, making them well-suited to collaborative tasks requiring synchronized attention. This mechanism helps improve collaborative efficiency and enhances the natural flow of social interactions.

[0076] To promote the development of joint attention among children, the system constructs collaborative VR tasks that require shared attention. For example, in a "virtual balancing ball" task, a team of at least two children is required to jointly control the balance of a virtual object (such as a floating ball) through their individual attention states. Each child's attention level (such as beta wave power) is converted into control force in the virtual control system. Only when all members maintain high concentration and coordinated attention states can the object be stabilized and prevented from falling.

[0077] This task not only trains the individual's attention regulation ability, but also promotes attention synchronization and collaboration awareness among children. It is an effective training method to improve social attention and teamwork ability.

[0078] During the collaborative task, the system continuously monitors each child's physiological signals, including indicators of emotional activation such as skin conductance response (GSR). If a child in the evaluation group experiences a significant increase in GSR (e.g., exceeding 150% of their baseline value and persisting for more than 30 seconds), the system determines that child is anxious, stressed, or distracted.

[0079] At this point, the system automatically triggers the peer assistance prompt mechanism, generating visual or auditory prompts in the virtual environment to guide other team members to provide assistance to the child. For example, in the virtual scene, it displays "Please encourage your partner" or plays a prompt "Your teammates need support", while reducing the delay in the child's task feedback, making it easier for them to regain their focus. In addition, the system can also suggest other team members to help them regain their attention through voice interaction or action coordination. This mechanism not only improves the inclusiveness and emotional support of collaborative training, but also helps to cultivate children's empathy and social responsiveness.

[0080] To assess children's attentional synchronization during collaborative tasks, the system records the duration of joint attention across all children in the group during social situations—that is, the length of time all members maintain simultaneous focus. This metric is calculated by integrating multi-dimensional data, including the EEG attention index, eye movement focus area overlap, and task response consistency.

[0081] Based on this joint attention duration, the system further generates a Social Attention Coordination Index (SACI), which serves as a quantitative indicator of attention synchronization and collaboration between team members. This index serves as an important reference for subsequent training grouping, task difficulty adjustment, and social skills development assessment.

[0082] For example, if the SACI value of a certain evaluation group continues to increase, it indicates that the attention coordination ability among its members has increased, and the system can match them with more challenging collaborative tasks; conversely, if the SACI value is low, an emotion regulation module can be added or the training partner combination can be adjusted to optimize the social interaction effect.

[0083] In summary, this example constructs a multi-person collaborative training system centered on attention coordination by using EEG coherence analysis to intelligently match training partners, construct collaborative tasks requiring shared attention, introduce a peer assistance prompt mechanism, and generate a social attention coordination index. This system not only improves children's ability to regulate attention in social situations but also provides a quantifiable and actionable technical path for the development of social skills, promising promising educational and clinical applications.

[0084] See also Figure 2 , Figure 2 This is a structural diagram of a system for evaluating and training children's attention provided by the present invention.

[0085] like Figure 2 As shown, a system for evaluating and training children's attention proposed in an embodiment of the present invention includes: The first generation module 301 is used to obtain the child's brain wave pattern, eye movement trajectory, emotional activation level and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; A second generating module 302 is configured to construct a virtual reality environment that matches the child's age based on the multi-dimensional biosignal data, embed sustained, selective, distributed, and switching attention tasks, and generate assessment task data; The third generation module 303 is used to adjust the difficulty and interference intensity of each task in real time according to the biological signal data and behavioral performance data in the evaluation task data to generate dynamic task parameters; a fourth generating module 304 for converting the biosignal data into a real-time audiovisual feedback signal based on the dynamic task parameters, and generating an attention feedback signal through element responses and prompt signals in the virtual environment; A training data module 305 is used to construct a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal to generate cognitive function training data; The evaluation optimization module 306 is used to synchronously share the child's attention performance data to the parent terminal and the teacher terminal based on the cognitive function training data, generate life situation intervention suggestions, and iteratively optimize evaluation parameters according to long-term effect evaluation results.

[0086] See also Figure 3 , Figure 3 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Acquire children's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; Based on the multidimensional biosignal data, constructing a virtual reality environment that matches the child's age, and embedding sustained, selective, distributed, and switching attention tasks to generate assessment task data; According to the biological signal data and behavioral performance data in the evaluation task data, the difficulty and interference intensity of each task are adjusted in real time to generate dynamic task parameters; Based on the dynamic task parameters, the biosignal data is converted into a real-time audiovisual feedback signal, and an attention feedback signal is generated through element responses and prompt signals in the virtual environment; constructing a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal to generate cognitive function training data; Based on the cognitive function training data, the child's attention performance data is synchronously shared with the parent terminal and the teacher terminal, life situation intervention suggestions are generated, and the evaluation parameters are iteratively optimized according to the long-term effect evaluation results.

[0087] See also Figure 4 , Figure 4 Schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Acquire children's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; Based on the multidimensional biosignal data, constructing a virtual reality environment that matches the child's age, and embedding sustained, selective, distributed, and switching attention tasks to generate assessment task data; According to the biological signal data and behavioral performance data in the evaluation task data, the difficulty and interference intensity of each task are adjusted in real time to generate dynamic task parameters; Based on the dynamic task parameters, the biosignal data is converted into a real-time audiovisual feedback signal, and an attention feedback signal is generated through element responses and prompt signals in the virtual environment; constructing a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal to generate cognitive function training data; Based on the cognitive function training data, the child's attention performance data is synchronously shared with the parent terminal and the teacher terminal, life situation intervention suggestions are generated, and the evaluation parameters are iteratively optimized according to the long-term effect evaluation results.

[0088] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0089] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0091] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system that is implemented in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0093] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0094] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for evaluating and training children's attention, characterized in that: The method comprises: Acquire children's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; Based on the multidimensional biosignal data, constructing a virtual reality environment that matches the child's age, and embedding sustained, selective, distributed, and switching attention tasks to generate assessment task data; According to the biological signal data and behavioral performance data in the evaluation task data, the difficulty and interference intensity of each task are adjusted in real time to generate dynamic task parameters; Based on the dynamic task parameters, the biosignal data is converted into a real-time audiovisual feedback signal, and an attention feedback signal is generated through element responses and prompt signals in the virtual environment; constructing a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal to generate cognitive function training data; Based on the cognitive function training data, the child's attention performance data is synchronously shared with the parent terminal and the teacher terminal, life situation intervention suggestions are generated, and the evaluation parameters are iteratively optimized according to the long-term effect evaluation results.

2. The method for evaluating and training children's attention according to claim 1, characterized in that: The real-time acquisition of the child's brain wave patterns, eye movement trajectories, emotional activation levels, and autonomic nervous system function data generates multi-dimensional biosignal data, including: By integrating a micro electroencephalogram sensor, energy values ​​of alpha wave, beta wave and theta wave frequency bands in the frontal lobe and parietal lobe areas of the child are collected; The eye tracking module built into the glasses frame records the child's gaze point coordinates, scanning path length, and blink frequency; measuring a skin conductance response value of the child using a fingertip skin conductance response sensor, and generating an emotional activation level indicator based on the skin conductance response value; The heart rate variability monitor is used to calculate the interval standard deviation, and the autonomic nervous system function data is evaluated based on the interval standard deviation to obtain an evaluation result.

3. The method for evaluating and training children's attention according to claim 2, characterized in that: The method comprises constructing a virtual reality environment that matches the child's age based on the multi-dimensional biosignal data and embedding sustained, selective, distributed, and switching attention tasks, including: Build a virtual space containing floating animated objects for first-year children and embed sustained attention tasks, such as continuously tracking the movement trajectory of a designated color object; Construct learning scenarios for second-year children that include dynamic distractors and embed selective attention tasks, such as identifying target mathematical symbols against a flickering background; Constructing multi-role social scenarios for third-year children and embedding divided attention tasks, such as simultaneously processing conversational audio cues and visual cues; A rule switching task was set in all scenes, and a switching attention task was embedded in the scenes of the rule switching task.

4. The method for evaluating and training children's attention according to claim 3, characterized in that: The step of adjusting the difficulty and interference intensity of each task in real time based on the biological signal data and behavioral performance data in the assessment task data includes: When the ratio of the energy of the theta wave to the energy of the beta wave decreases by 15% and the task error rate is less than 5%, the complexity level of each task is increased; When the child's eye movement distraction exceeds a preset threshold, increasing the dynamic change frequency of the visual distraction elements to 120% of the threshold; Based on the ratio of low-frequency power to high-frequency power of heart rate variability, the auditory interference intensity is adjusted in real time to keep the task difficulty within the preset challenge range; When the peak value of skin conductance response continues to exceed the standard, a 90-second relaxation training module is automatically triggered.

5. The method for evaluating and training children's attention according to claim 4, characterized in that: The converting of the biosignal data into a real-time audiovisual feedback signal comprises: When it is detected that the power of the beta wave increases and the power of the theta wave decreases, controlling the task target object in the virtual environment to emit light and playing a reward sound effect; When the child's eye movement trajectory deviates from the task area and exceeds a preset timeout threshold, generating a pulse vibration prompt signal; In the intermediate stage of neurofeedback training, the feedback signal output is delayed by m seconds to enhance the ability to maintain attention; In the advanced stage, the audiovisual feedback intensity is attenuated to n% of the initial value, where m and n are both greater than 0.

6. The method for evaluating and training children's attention according to claim 5, characterized in that: The training tasks include working memory training tasks, inhibitory control training tasks and cognitive flexibility training tasks, wherein: The working memory training task is used to train the child to memorize and reproduce the color sequence of moving objects in a virtual scene; The inhibitory control training task is used to train the child to inhibit responses to non-target shapes in a rapidly flashing stream of stimuli; The cognitive flexibility training task is used to train the child to switch between classification rules according to environmental prompts.

7. The method for evaluating and training children's attention according to claim 6, characterized in that: The synchronously sharing the child's attention performance data to the parent terminal and the teacher terminal based on the cognitive function training data includes: Converting the attention maintenance duration and task switching efficiency indicators into a daily training report displayed on the parent terminal; Based on the fluctuation pattern of classroom attention, push reminders of key teaching periods to the teacher's terminal; Generate life situation intervention suggestions, and when it is detected that the child's attention reaches its peak, suggest arranging important learning content; Push micro-training tasks based on real-life scenarios through mobile devices.

8. The method for evaluating and training children's attention according to claim 7, characterized in that: The iterative optimization of evaluation parameters based on the long-term effect evaluation results includes: Adjust the sensitivity threshold of the dynamic difficulty algorithm based on task performance improvement data; Optimize the weight distribution of cognitive function training tasks based on learning ability improvement data; Update the distribution of task types and distraction intensities in a virtual reality environment based on long-term academic performance change data.

9. The method for evaluating and training children's attention according to claim 8, characterized in that: Also includes: In a multi-person collaborative mode for evaluating multiple children, automatically matching training partners based on EEG coherence analysis results of the multiple children; A collaborative task requiring joint attention was constructed, requiring a team of at least two children to synchronously control the balance of a virtual object. When an abnormally elevated skin conductance response is detected in one of the children in the evaluation group, a peer assistance prompting mechanism is automatically triggered; The joint attention maintenance duration of all children in the evaluation group in the social scene is recorded, and a social attention coordination index is generated based on the joint attention maintenance duration.

10. A system for evaluating and training children's attention, characterized in that: The system comprises: The first generation module is used to obtain children's brain wave patterns, eye movement trajectories, emotional activation levels and autonomic nervous system function data in real time to generate multi-dimensional biosignal data; a second generation module, configured to construct a virtual reality environment that matches the child's age based on the multi-dimensional biosignal data, and embed sustained, selective, distributed, and switching attention tasks to generate assessment task data; A third generation module is used to adjust the difficulty and interference intensity of each task in real time based on the biological signal data and behavioral performance data in the evaluation task data to generate dynamic task parameters; a fourth generating module, configured to convert the biosignal data into a real-time audiovisual feedback signal based on the dynamic task parameters, and generate an attention feedback signal through element responses and prompt signals in the virtual environment; A training data module, configured to construct a training task integrating working memory, inhibitory control, and cognitive flexibility based on the attention feedback signal, and generate cognitive function training data; The evaluation optimization module is used to synchronously share the child's attention performance data to the parent terminal and the teacher terminal based on the cognitive function training data, generate life situation intervention suggestions, and iteratively optimize the evaluation parameters according to the long-term effect evaluation results.

Images