Autistic child emotion regulation system integrating electroencephalogram feedback and art

Abstract

The invention discloses an autistic child emotion regulation system integrating electroencephalogram feedback and art, and relates to the technical field of medical intelligent rehabilitation. An emotional state decoding module; a dynamic generation type art interaction guiding module; a closed-loop feedback regulation and control module; and an adaptive optimization module. According to the method, deep fusion of physiological signal monitoring and artistic emotion expression is realized, scientificity and effectiveness of emotion regulation intervention of the autistic children are remarkably improved, participation willingness and compliance of the children are effectively improved, personalized iteration and accurate regulation of the intervention process are realized, limitation of traditional single-mode intervention is broken through, and the method is suitable for popularization and application. Not only is the objectivity of emotion recognition and the pertinence of art guidance enhanced, but also an individualized rehabilitation path is formed through long-term memory map construction, and an intelligent, quantifiable and sustainable new emotion regulation normal form is provided for autistic children.

Description

Technical Field

[0001] This invention relates to the field of medical intelligent rehabilitation technology, and in particular to an emotion regulation system for autistic children that integrates electroencephalography (EEG) feedback and art. Background Technology

[0002] With the continuous advancement of social technology and the increasing emphasis on mental health, intervention techniques for children's psychological and neurodevelopmental disorders are gradually developing towards intelligence, personalization, and multimodal integration. In recent years, EEG biofeedback technology has received widespread attention because it can monitor brain activity in real time and achieve neuroplasticity training. At the same time, art therapy, especially art activities, has been proven to have a positive effect on promoting emotional release and psychological adjustment in children with autism due to its natural advantages of non-verbal, creative, and emotional expression.

[0003] Currently, existing intervention techniques for emotion regulation in children with autism still suffer from a core deficiency: the lack of an effective mechanism for dynamically integrating real-time physiological feedback with emotional expression interventions in a closed loop. Current EEG feedback systems are mostly limited to single neurofeedback training, which is often monotonous, lacks interactivity, and fails to attract long-term participation from children with autism. Furthermore, they fail to organically combine changes in EEG activity with specific emotional expression processes. While traditional art therapy can promote emotional release, its process is highly subjective, lacking real-time guidance and quantitative assessment of objective physiological indicators, making it difficult to precisely control and continuously track treatment effects. These two approaches are often disconnected, preventing the intervention process from achieving a closed-loop optimization of physiological regulation, psychological expression, and feedback reinforcement. This deficiency severely restricts the personalization, scientific approach, and effectiveness of emotion regulation interventions. Summary of the Invention

[0004] In view of the problems existing in the current emotion regulation system for autistic children that integrates EEG feedback and art, this invention is proposed.

[0005] Therefore, the problem that this invention aims to solve is that in existing emotional regulation intervention techniques for children with autism, EEG biofeedback and art therapy are isolated from each other, lacking an effective mechanism for dynamically linking and regulating real-time physiological state with emotional expression behavior in a closed loop. This makes it difficult to achieve synergistic optimization of neurophysiological regulation, artistic emotional expression, and feedback reinforcement during the intervention process.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide an emotion regulation system for autistic children that integrates electroencephalogram (EEG) feedback and art, comprising, The multi-channel EEG acquisition module is used to acquire multi-channel EEG signals from the frontal and temporoparietal regions of children with autism, and combines motion artifact suppression algorithms to complete the acquisition of EEG data. The emotion state decoding module is used to preprocess the collected EEG data. The preprocessing includes frequency domain feature analysis and time domain feature analysis of the EEG data and extraction of neurophysiological indicators. The dynamic generative art interaction guidance module is used to receive the emotional state decoding results as the generation conditions, call the art content generation engine driven by the diffusion model, and render a visual guidance scene that conforms to the emotional characteristics of children. The closed-loop feedback control module is used to establish a temporal correlation model between neurophysiological indicators and the art content generation engine. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, calculating the emotion regulation efficacy index of children's emotional characteristics, dynamically updating art interaction guidance, generating EEG feedback reward thresholds, and scoring the visual guidance scene of children's emotional characteristics. The adaptive optimization module is used to classify visually guided scenarios based on the scoring, and to regulate the emotions of autistic children based on the classification results.

[0007] As a preferred embodiment of the autistic children's emotion regulation system integrating EEG feedback and art as described in this invention, the multi-channel EEG acquisition module includes a child-adaptive dry electrode array unit and a motion artifact real-time suppression unit. The emotion state decoding module includes a multi-scale EEG feature extraction unit, an individual baseline self-calibration unit, and an emotion discrimination and reasoning unit. The dynamic generative art interaction guidance module includes an emotion color mapping strategy library unit, a diffusion model-driven content generation unit, and a progressive task delivery unit. The closed-loop feedback control module includes a multimodal behavior feature extraction unit, an efficiency index calculation unit, and a dynamic parameter modulation unit; The adaptive optimization module includes a visually guided scene scoring and classification unit, a strategy evolution unit, and a memory graph construction unit.

[0008] As a preferred embodiment of the emotion regulation system for autistic children that integrates EEG feedback and art as described in this invention, the child-adaptive dry electrode array unit is used to distribute the Fp1 and Fp2 positions in the frontal region and the T3, T4, and Cz positions in the temporoparietal region. The motion artifact real-time suppression unit is used to integrate a triaxial accelerometer and an adaptive notch filter to eliminate high-frequency interference caused by head micro-movements by modeling motion signal covariates. The multi-scale EEG feature extraction unit is used to perform wavelet packet decomposition on the preprocessed EEG data to obtain the energy ratios of the five frequency bands δ, θ, α, β, and γ. The individual baseline self-calibration unit is used to record the EEG baseline of children in a resting state with their eyes open and closed for 2 minutes each, and dynamically adjust the reference baseline in the alpha band. The emotion discrimination reasoning unit is used to employ a lightweight spatiotemporal convolutional neural network model, inputting multidimensional EEG feature vectors and outputting emotion labels.

[0009] As a preferred embodiment of the emotion regulation system for autistic children that integrates EEG feedback and art as described in this invention, the emotion color mapping strategy library unit is used to store a set of rules for the association between emotion and color, and the set of rules for the association between emotion and color includes main color selection, saturation gradient and brightness adjustment parameters. The diffusion model-driven content generation unit is used to generate a path guided by an abstract graphical base, with the emotional state decoding result as a conditional input. The progressive task delivery unit is used to break down visual content into phased drawing tasks, and guide children to complete their creations through a three-stage mode of outline prompts, color filling, and free extension via a touch interface. The multimodal behavior feature extraction unit is used to capture brush pressure, movement speed, pause frequency, number of color switching times, and image area coverage entropy during the painting process. The performance index calculation unit is used to construct an LSTM fusion network and output a visually guided scene score. The dynamic parameter modulation unit is used to adjust the EEG feedback reward threshold according to the visual guidance scene score. The visual guidance scene scoring and classification unit is used to rate the quality of the generated visual guidance scene based on the visual guidance scene score and the child completion index, and classify it into three categories: high response, medium response and low response. The strategy evolution unit is used to perform cross-iteration of parameter combinations corresponding to low-response scenarios using a swarm intelligence-based optimization algorithm. The memory mapping building unit is used to accumulate a database of response patterns that integrate EEG, behavior, and art, and to deploy memory maps.

[0010] As a preferred embodiment of the autistic children's emotion regulation system integrating EEG feedback and art as described in this invention, the child-adaptive dry electrode array unit includes an electrode contact impedance monitoring subunit, which is used to measure the impedance value of the electrode-skin interface of each channel and transmit the impedance abnormality signal to the motion artifact real-time suppression unit to trigger the operation of the adaptive notch filter to avoid misjudgment. The motion artifact real-time suppression unit includes a micro-motion pattern recognition subunit, which is used to identify the type of head micro-motion based on a triaxial accelerometer and feed back the intentional action marker information to the emotion state decoding module to shield non-physiological signal interference segments. The multi-scale EEG feature extraction unit includes a frequency band coupling analysis subunit, which is used to calculate the phase-amplitude coupling strength of α and γ across frequency bands, and inputs the coupling feature data into the emotion discrimination inference unit as an additional input dimension of the classification model; The individual baseline self-calibration unit includes a resting state determination subunit, which is used to analyze the alpha wave power variation coefficient in open and closed eye states, and synchronize the effective baseline parameters to the dynamic generative art interaction guidance module for initializing the generation of the first guidance scene. The emotion discrimination reasoning unit includes a confidence assessment subunit, which is used to evaluate the probability entropy of the emotion label output and feed back the low confidence judgment result to the multi-channel EEG acquisition module to instruct to improve the sampling resolution.

[0011] As a preferred embodiment of the emotion regulation system for autistic children that integrates EEG feedback and art as described in this invention, the emotion color mapping strategy library unit includes a dynamic weight adjustment subunit, which is used to update the color rule weight parameters corresponding to each emotion according to the emotion regulation efficacy index. The diffusion model-driven content generation unit includes a semantic control subunit, which is used to introduce controllable perturbations when generating the abstract graph base and write the generation parameter log into the memory graph construction unit for subsequent strategy backtracking. The progressive task delivery unit includes a task completion prediction subunit, which is used to transmit data to the dynamic parameter modulation unit to adjust the EEG feedback reward threshold. The multimodal behavior feature extraction unit includes a brushstroke dynamics modeling subunit, which is used to construct a three-dimensional dynamic vector of pressure-velocity-acceleration and stream the dynamic features to the performance index calculation unit for fusion modeling. The performance index calculation unit includes a cross-session normalization subunit, which processes the performance score and sends it to the visual guidance scene scoring classification unit of the adaptive optimization module for quality rating.

[0012] As a preferred embodiment of the emotional regulation system for autistic children that integrates EEG feedback and art as described in this invention, the dynamic parameter modulation unit includes a feedback delay compensation subunit, which is used to predict the emotional state in the next 0.5 seconds based on the system delay, and write the corrected EEG feedback reward threshold into the incentive triggering mechanism of the multi-channel EEG acquisition module. The visually guided scene scoring and classification unit includes an abnormal pattern detection subunit, which is used to identify the parameter features of continuous low response scenes and synchronize the list of avoidance strategy combinations to the generation constraints of the diffusion model driven content generation unit. The strategy evolution unit includes a knowledge transfer subunit, which is used to derive the parameter combinations that have been successfully optimized in high-response individuals and inject them into the initial population generation process of the strategy evolution unit corresponding to other children; The memory graph construction unit includes a pattern similarity retrieval subunit, which is used to compare the matching degree between the current session baseline data and the historical response graph, and load the optimal initial strategy configuration into the dynamically generated art interaction guidance module.

[0013] Secondly, embodiments of the present invention provide a method for emotion regulation in children with autism that integrates EEG feedback and art, comprising: Multichannel EEG signals from the frontal and temporoparietal regions of children with autism were acquired, and the EEG data were collected by combining a motion artifact suppression algorithm. The collected EEG data is preprocessed, including frequency domain feature analysis and time domain feature analysis of the EEG data, and neurophysiological indicators are extracted. The system receives the emotional state decoding result as the generation condition, calls the art content generation engine driven by the diffusion model, and renders a visual guidance scene that conforms to the emotional characteristics of children. A temporal correlation model between neurophysiological indicators and art content generation engine is established. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, calculating the emotion regulation efficacy index of children's emotional characteristics, dynamically updating art interaction guidance, generating EEG feedback reward threshold, and scoring the visual guidance scene of children's emotional characteristics. Based on the visual guidance scenarios after scoring, the emotions of autistic children are regulated according to the classification results; The formula for calculating the emotion regulation efficacy index of children's emotional characteristics is as follows: in, Indicates at a point in time The calculated change in the frontal alpha wave asymmetry index relative to the baseline period. Represents the hyperbolic tangent function. Shannon entropy represents the color selection process during painting. Indicates a single intervention cycle Inner screen area coverage volume The standard deviation of the pen stroke speed. , , as well as All are dynamic weighting coefficients. This represents the index of emotion regulation effectiveness.

[0014] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step of the above-mentioned emotion regulation system for autistic children that integrates EEG feedback and art.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the above-described system for regulating the emotions of autistic children by integrating EEG feedback and art.

[0016] The beneficial effects of this invention are as follows: By constructing a closed-loop control mechanism of EEG perception, art guidance, and feedback optimization, this invention achieves a deep integration of physiological signal monitoring and artistic emotional expression, significantly improving the scientific nature and effectiveness of emotion regulation intervention for children with autism. The system utilizes multi-channel real-time EEG acquisition and individualized emotion decoding technology to accurately capture changes in children's emotional states. Through a dynamically generated art interaction guidance module, it outputs personalized visual creation tasks that match their physiological states, making the abstract neural feedback process concrete and interesting, effectively improving children's willingness to participate and compliance. The closed-loop feedback control and adaptive optimization mechanism integrates and analyzes EEG indicators and painting behavior characteristics, quantitatively assesses the regulatory efficacy of each intervention, and dynamically adjusts subsequent guidance strategies and feedback thresholds, achieving personalized iteration and precise control of the intervention process. This invention breaks through the limitations of traditional single-mode intervention, not only enhancing the objectivity of emotion recognition and the pertinence of art guidance, but also forming an individualized rehabilitation path through the construction of a long-term memory map, providing a new paradigm of intelligent, quantifiable, and sustainable emotion regulation for children with autism. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of an emotion regulation system for autistic children that integrates EEG feedback and art, provided as an embodiment of the present invention.

[0018] Figure 2 The flowchart illustrates a method for an emotion regulation system for autistic children that integrates EEG feedback and art, as provided in an embodiment of the present invention.

[0019] Figure 3 This is a schematic diagram of the structure of a medium for an emotion regulation system for autistic children that integrates EEG feedback and art, as provided in an embodiment of the present invention.

[0020] Figure 4 This is a schematic diagram of a computing device that provides an emotion regulation system for autistic children that integrates EEG feedback and art, as provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0024] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0025] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0026] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0027] Example Reference Figures 1-4This is the first embodiment of the present invention, which provides an emotion regulation system for autistic children that integrates EEG feedback and art, comprising: S110: Multi-channel EEG acquisition module, used to acquire multi-channel EEG signals from the frontal and temporoparietal regions of children with autism, combined with motion artifact suppression algorithm to complete the acquisition of EEG data.

[0028] S210: Emotional state decoding module, used to preprocess the collected EEG data. Preprocessing includes frequency domain feature analysis and time domain feature analysis of the EEG data, and extraction of neurophysiological indicators.

[0029] S310: Dynamically Generative Art Interaction Guidance Module, used to receive the emotional state decoding results as generation conditions, call the art content generation engine driven by the diffusion model, and render a visual guidance scene that conforms to the emotional characteristics of children.

[0030] S410: Closed-loop feedback control module, used to establish a temporal correlation model between neurophysiological indicators and the art content generation engine. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, to calculate the emotion regulation efficacy index of children's emotional characteristics, dynamically update art interaction guidance, generate EEG feedback reward thresholds, and score the visual guidance scene of children's emotional characteristics.

[0031] S510: Adaptive optimization module, used to classify visually guided scenarios based on scores, and to regulate the emotions of autistic children based on the classification results.

[0032] The multi-channel EEG acquisition module includes a child-adaptive dry electrode array unit and a motion artifact suppression unit. Furthermore, the child-adaptive dry electrode array unit includes an electrode contact impedance monitoring subunit, which measures the impedance value of the electrode-skin interface of each channel and transmits the impedance abnormality signal to the motion artifact real-time suppression unit to trigger the operation of the adaptive notch filter to avoid misjudgment. The real-time motion artifact suppression unit includes a micro-motion pattern recognition subunit, which is used to identify the type of head micro-motion based on a triaxial accelerometer and feed back the intentional action marker information to the emotion state decoding module to shield non-physiological signal interference segments; The multi-scale EEG feature extraction unit includes a frequency band coupling analysis subunit, which is used to calculate the phase-amplitude coupling strength of α and γ across frequency bands, and inputs the coupling feature data into the emotion discrimination inference unit as an additional input dimension of the classification model; The individual baseline self-calibration unit includes a resting state determination subunit, which is used to analyze the alpha wave power variation coefficient under open and closed eye states, and synchronize the effective baseline parameters to the dynamic generative art interaction guidance module for initializing the generation of the first guidance scene; The emotion discrimination reasoning unit includes a confidence assessment subunit, which is used to evaluate the probability entropy of the emotion label output and feed back the low confidence judgment result to the multi-channel EEG acquisition module to improve the sampling resolution.

[0033] The emotion state decoding module includes a multi-scale EEG feature extraction unit, an individual baseline self-calibration unit, and an emotion discrimination reasoning unit; The dynamic generative art interaction guidance module includes an emotion color mapping strategy library unit, a diffusion model-driven content generation unit, and a progressive task delivery unit. Furthermore, the emotion color mapping strategy library unit is used to store the emotion and color association rule set, which includes the main color selection, saturation gradient and brightness adjustment parameters; The diffusion model-driven content generation unit is used to generate a path guided by an abstract graphical base, with the result of emotional state decoding as a conditional input. The progressive task delivery unit is used to break down visual content into phased drawing tasks, and guides children to complete their creations through a three-stage mode of outline prompts, color filling, and free extension via a touch interface; The multimodal behavioral feature extraction unit is used to capture brush pressure, movement speed, pause frequency, number of color switching times, and image area coverage entropy during the painting process; The performance index calculation unit is used to construct the LSTM fusion network and output a visually guided scene score; The dynamic parameter modulation unit is used to adjust the EEG feedback reward threshold based on the visually guided scene score; The Visual Guidance Scene Scoring and Classification Unit is used to rate the quality of the generated visual guidance scenes based on the visual guidance scene scoring and children's completion indicators, and classifies them into three categories: high response, medium response, and low response. The strategy evolution unit is used to perform cross-iteration of parameter combinations corresponding to low-response scenarios using swarm intelligence-based optimization algorithms; The memory mapping building unit is used to accumulate a database of response patterns that integrate EEG, behavior, and art, and to deploy memory maps.

[0034] The closed-loop feedback control module includes a multimodal behavior feature extraction unit, an efficiency index calculation unit, and a dynamic parameter modulation unit; The adaptive optimization module includes a visually guided scene scoring and classification unit, a strategy evolution unit, and a memory map construction unit.

[0035] Furthermore, the emotion color mapping strategy library unit includes a dynamic weight adjustment subunit, which is used to update the color rule weight parameters corresponding to each emotion based on the emotion regulation efficacy index. The diffusion model-driven content generation unit includes a semantic control subunit, which is used to introduce controllable perturbations when generating the abstract graph base and write the generation parameter log to the memory graph construction unit for subsequent strategy backtracking. The progressive task delivery unit includes a task completion prediction subunit, which is used to transmit data to the dynamic parameter modulation unit to adjust the EEG feedback reward threshold. The multimodal behavior feature extraction unit includes a brushstroke dynamics modeling subunit, which is used to construct a three-dimensional dynamic vector of pressure-velocity-acceleration and stream the dynamic features to the performance index calculation unit for fusion modeling; The performance index calculation unit includes a cross-session normalization subunit, which processes the performance score and sends it to the visual guidance scene scoring classification unit of the adaptive optimization module for quality rating.

[0036] Furthermore, the child-adaptive dry electrode array unit is used to distribute Fp1 and Fp2 in the forehead region and T3, T4, and Cz in the temporoparietal region; The real-time motion artifact suppression unit integrates a triaxial accelerometer and an adaptive notch filter to eliminate high-frequency interference caused by head micro-movements by modeling motion signal covariates. The multi-scale EEG feature extraction unit is used to perform wavelet packet decomposition on the preprocessed EEG data to obtain the energy ratios of the five frequency bands δ, θ, α, β, and γ. The individual baseline self-calibration unit is used to record the EEG baseline of children in a resting state with their eyes open and closed for 2 minutes each, and dynamically adjust the reference baseline in the alpha band; The emotion discrimination reasoning unit uses a lightweight spatiotemporal convolutional neural network model, takes a multidimensional EEG feature vector as input, and outputs an emotion label.

[0037] Preferably, the multi-scale EEG feature extraction unit performs wavelet packet decomposition on the preprocessed EEG data and uses the Daubechies wavelet basis for multi-level analysis of the signal, dividing the 0-64 Hz EEG spectrum into fine sub-bands and integrating them into five core frequency bands (δ, θ, α, β, γ) according to internationally accepted standards. The system calculates the total energy of each frequency band within a specific time window and further normalizes it to obtain its proportion of the total energy of the entire frequency band, forming a stable spectral energy distribution characteristic. Experimental data show that in the Fp1 and Fp2 channels of the prefrontal cortex, when children are in a resting, closed-eye state, the proportion of α-band energy is significantly increased, averaging over 42%, significantly higher than the approximately 28% in the open-eye, relaxed state, exhibiting typical α-wave inhibition and recovery phenomena. This feature provides a reliable basis for individual baseline self-calibration. Simultaneously, during the emotion regulation task, the β-band energy ratio increases by an average of over 18% when children exhibit anxiety or alertness, while the γ-band energy ratio increases by approximately 23% when focusing on drawing or perceiving guided images, reflecting enhanced neural activity in higher cognitive and emotional processing. These energy ratio changes, which have clear physiological significance, provide high-resolution, quantifiable, multi-dimensional input indicators for the accurate decoding of subsequent emotional states.

[0038] The lightweight spatiotemporal convolutional neural network model first uses a 1×1 convolutional layer to perform spatial feature fusion and channel expansion on multi-channel EEG feature vectors, enhancing the collaborative representation ability of neural activities between electrodes. Then, a depthwise separable temporal convolutional block is introduced, using a one-dimensional convolutional kernel to extract local time-frequency patterns on the time axis, and cross-channel information integration is achieved through pointwise convolution. Batch normalization and ReLU activation functions are combined to improve nonlinear expression capabilities, while residual connections are used to alleviate the gradient degradation problem of deep networks. Finally, global average pooling is used to compress the time dimension, outputting low-dimensional, time-independent high-order features, which are then mapped to five emotion state labels—calm, anxiety, pleasure, irritability, and focus—via a small fully connected layer, enabling real-time discrimination of individual emotional states. The entire network, through parameter simplification and knowledge distillation optimization, ensures small model size and low inference latency, achieving millisecond-level response on edge computing devices, meeting the stringent requirements of the EEG-art closed-loop feedback system for real-time and stability of emotion recognition.

[0039] Furthermore, the dynamic parameter modulation unit includes a feedback delay compensation subunit, which is used to predict the emotional state in the next 0.5 seconds based on the system delay, and write the corrected EEG feedback reward threshold into the incentive triggering mechanism of the multi-channel EEG acquisition module. Preferably, the 0.5-second prediction window used in the feedback delay compensation subunit is based on the measured analysis of the system's end-to-end signal delay and the comprehensive calibration results of children's neural response characteristics. By tracking millisecond-level timestamps in each stage, including EEG signal acquisition, transmission, feature extraction, emotional state decoding, art content generation, and visual feedback presentation, the average system delay from the occurrence of EEG changes to the actual update of the visual guidance image was measured to be 480 milliseconds, concentrated in the range of 460 to 510 milliseconds. At the same time, combined with clinical research data on neural conduction velocity in children with autism, it was found that the re-response latency of their sensorimotor cortex to visual feedback is generally between 300 and 400 milliseconds. Too short a prediction window cannot effectively cover the closed-loop delay, while too long a prediction is prone to misjudgment due to state drift. Through multiple rounds of cross-validation experiments, in a test group including 32 children with autism, setting a prospective prediction window of 0.5 seconds improved the spatiotemporal matching accuracy between EEG feedback reward signals and the children's actual neural activity state to 89.7%, significantly higher than the matching effect of 0.3 seconds or 0.7 seconds. Therefore, setting the prediction window to 0.5 seconds can effectively compensate for the inherent delay of the system and accurately align with the trend of neural dynamic changes, ensuring the timeliness and physiological consistency of feedback regulation.

[0040] The visually guided scene scoring and classification unit includes an abnormal pattern detection subunit, which is used to identify the parameter features of continuous low response scenes and synchronize the list of avoidance strategy combinations to the generation constraints of the diffusion model driven content generation unit. The strategy evolution unit includes a knowledge transfer subunit, which is used to derive the parameter combinations that have been successfully optimized in high-response individuals and inject them into the initial population generation process of the strategy evolution unit corresponding to other children; The memory graph construction unit includes a pattern similarity retrieval subunit, which is used to compare the matching degree between the current session baseline data and the historical response graph, and load the optimal initial strategy configuration into the dynamically generated art interaction guidance module.

[0041] The Visual Guidance Scene Scoring and Classification Unit is used to rate the quality of the generated visual guidance scenes based on the visual guidance scene scoring and children's completion indicators, and classifies them into three categories: high response, medium response, and low response. The strategy evolution unit is used to perform cross-iteration of parameter combinations corresponding to low-response scenarios using swarm intelligence-based optimization algorithms; The memory mapping construction unit is used to accumulate a database of response patterns integrating EEG, behavior, and art, and then deploy the memory map. A comparison of this invention with existing technologies is shown in Table 1 below: Table 1. Comparison of the present invention with the prior art Table 1 describes how this invention fundamentally solves the core problem of the disconnect between EEG feedback and art therapy, and the lack of closed-loop regulation. By constructing an integrated mechanism of "EEG perception - art guidance - feedback optimization," it achieves dynamic synergy between physiological state and emotional expression. The system not only significantly improves the personalization, objectivity, and real-time nature of intervention, but also enhances children's compliance by dynamically generating fun art tasks. Furthermore, by leveraging the quantifiable assessment of effectiveness and adaptive optimization capabilities, it supports long-term, sustainable emotion regulation training, comprehensively overcoming the shortcomings of traditional methods such as strong subjectivity, insufficient quantification, and poor adaptability.

[0042] In a preferred embodiment, a method for emotion regulation in autistic children that integrates EEG feedback and art includes: Multichannel EEG signals from the frontal and temporoparietal regions of children with autism were acquired, and the EEG data were collected by combining a motion artifact suppression algorithm. The collected EEG data were preprocessed, including frequency domain feature analysis and time domain feature analysis, and neurophysiological indicators were extracted. The system receives the emotional state decoding result as the generation condition, calls the art content generation engine driven by the diffusion model, and renders a visual guidance scene that conforms to the emotional characteristics of children. A temporal correlation model between neurophysiological indicators and the art content generation engine was established. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, the calculation of the emotion regulation efficacy index of children's emotional characteristics, the dynamic updating of art interaction guidance, the generation of EEG feedback reward threshold, and the scoring of visual guidance scenarios for children's emotional characteristics. Based on the visual guidance scenarios after scoring, the emotions of autistic children are regulated according to the classification results; The formula for calculating the emotion regulation efficacy index of children's emotional characteristics is: in, Indicates at a point in time The calculated change in the frontal alpha wave asymmetry index relative to the baseline period. Represents the hyperbolic tangent function. Shannon entropy represents the color selection process during painting. Indicates a single intervention cycle Inner screen area coverage volume The standard deviation of the pen stroke speed. , , as well as All are dynamic weighting coefficients. This represents the index of emotion regulation effectiveness.

[0043] The calculation formula for the motion artifact suppression algorithm is as follows: in, This represents denoised EEG signals. Represents raw brain electrical signals. This represents the adaptive filter weight vector. This represents the acceleration value of the head in the X-axis direction. This represents the acceleration value of the head in the Y-axis direction. This represents the acceleration value of the head in the Z-axis direction. The nonlinear coupling relationship representing the square term of the X-axis acceleration. The nonlinear coupling relationship representing the square term of the Y-axis acceleration. The nonlinear coupling relationship representing the square term of the Z-axis acceleration. It indicates the magnitude of acceleration.

[0044] The above-mentioned unit modules can be embedded in the processor of the computer device in hardware form or independent of it, or they can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0045] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0046] In summary, this invention, by constructing a closed-loop control mechanism integrating EEG perception, art guidance, and feedback optimization, achieves a deep integration of physiological signal monitoring and artistic emotional expression. This significantly enhances the scientific rigor and effectiveness of emotion regulation interventions for children with autism. The system utilizes multi-channel real-time EEG acquisition and individualized emotion decoding technology to accurately capture changes in children's emotional states. Through a dynamically generated art interaction guidance module, it outputs personalized visual creation tasks that match their physiological states, making the abstract neural feedback process concrete and engaging, effectively increasing children's willingness to participate and their compliance. The closed-loop feedback control and adaptive optimization mechanism integrates EEG indicators with drawing behavior characteristics for analysis, quantitatively assesses the regulatory efficacy of each intervention, and dynamically adjusts subsequent guidance strategies and feedback thresholds, achieving personalized iteration and precise control of the intervention process. This invention breaks through the limitations of traditional single-mode interventions, not only enhancing the objectivity of emotion recognition and the targeted nature of art guidance but also constructing an individualized rehabilitation path through long-term memory mapping, providing a new paradigm of intelligent, quantifiable, and sustainable emotion regulation for children with autism.

[0047] After introducing the method and system of exemplary embodiments of the present invention, the following references are made. Figure 3 A computer-readable storage medium according to exemplary embodiments of the present invention will be described, please refer to... Figure 3 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it implements the steps described in the above-described method implementation. For example, a multi-channel EEG acquisition module is used to acquire multi-channel EEG signals from the frontal and temporoparietal regions of autistic children, and combines a motion artifact suppression algorithm to complete the acquisition of EEG data; an emotion state decoding module is used to preprocess the acquired EEG data, including frequency domain feature analysis and time domain feature analysis of the EEG data, and extracting neurophysiological indicators; a dynamic generative art interaction guidance module is used to receive the emotion state decoding results as a generator. The system takes several steps: First, it invokes a diffusion-model-driven art content generation engine to render visually guided scenes that match children's emotional characteristics. Second, a closed-loop feedback control module establishes a temporal correlation model between neurophysiological indicators and the art content generation engine. This model integrates the engine's drawing speed, color selection entropy, and region coverage mode to calculate the emotion regulation efficacy index of children's emotional characteristics, dynamically updates the art interaction guidance, generates EEG feedback reward thresholds, and scores the visually guided scenes based on children's emotional characteristics. Third, an adaptive optimization module categorizes the scored visually guided scenes and adjusts the emotions of autistic children based on the classification results. The specific implementation details of each step are not repeated here.

[0048] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0049] After introducing the methods and media of exemplary embodiments of the present invention, the following references are made. Figure 4 A computational device for adaptive recovery of low-voltage power grid self-healing control according to an exemplary embodiment of the present invention.

[0050] Figure 4 A block diagram is shown of an exemplary computing device 40 suitable for implementing embodiments of the present invention. The computing device 40 may be a computer system or a server. Figure 4 The computing device 40 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0051] like Figure 4 As shown, the components of computing device 40 may include, but are not limited to: one or more processors or processing units 401, system memory 402, and bus 403 connecting different system components (including system memory 402 and processing unit 401).

[0052] The computing device 40 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 40, including volatile and non-volatile media, and removable and non-removable media.

[0053] System memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 4021 and / or cache memory 4022. Computing device 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 4023 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 4 (Not shown in the image, usually referred to as "hard drive"). Although not shown in... Figure 4The diagram illustrates that disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) can be provided. In these cases, each drive can be connected to bus 403 via one or more data media interfaces. System memory 402 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0054] A program / utility 4025 having a set (at least one) of program modules 4024 may be stored, for example, in system memory 402, and such program modules 4024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 4024 typically perform the functions and / or methods described in the embodiments of the present invention.

[0055] The computing device 40 can also communicate with one or more external devices 404 (such as a keyboard, pointing device, display, etc.). This communication can be performed via the input / output (I / O) interface 405. Furthermore, the computing device 40 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 406. Figure 4 As shown, network adapter 406 communicates with other modules of computing device 40 (such as processing unit 401) via bus 403. It should be understood that, although... Figure 4 As not shown, it can be used in conjunction with computing device 40 with other hardware and / or software modules.

[0056] The processing unit 401 executes various functional applications and data processing by running programs stored in the system memory 402. For example, a multi-channel EEG acquisition module is used to acquire multi-channel EEG signals from the frontal and temporoparietal regions of autistic children, combining them with a motion artifact suppression algorithm to complete the acquisition of EEG data; an emotion state decoding module is used to preprocess the acquired EEG data, including frequency domain feature analysis and time domain feature analysis, and to extract neurophysiological indicators; a dynamic generative art interaction guidance module is used to receive the emotion state decoding results as generation conditions and call a diffusion model-driven... The system comprises four modules: an art content generation engine, which renders visually guided scenes that align with children's emotional characteristics; a closed-loop feedback control module, which establishes a temporal correlation model between neurophysiological indicators and the art content generation engine. This model integrates the drawing speed, color selection entropy, and region coverage patterns of the art content generation engine to calculate the emotion regulation efficacy index of children's emotional characteristics, dynamically update the art interaction guidance, generate EEG feedback reward thresholds, and score the visually guided scenes based on children's emotional characteristics; and an adaptive optimization module, which categorizes the scored visually guided scenes and adjusts the emotions of autistic children based on the classification results.

[0057] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0058] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0060] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0061] If the functionality is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0063] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0064] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An emotion regulation system for autistic children integrating EEG feedback and art, characterized in that: include, The multi-channel EEG acquisition module is used to acquire multi-channel EEG signals from the frontal and temporoparietal regions of children with autism, and combines motion artifact suppression algorithms to complete the acquisition of EEG data. The emotion state decoding module is used to preprocess the collected EEG data. The preprocessing includes frequency domain feature analysis and time domain feature analysis of the EEG data and extraction of neurophysiological indicators. The dynamic generative art interaction guidance module is used to receive the emotional state decoding results as the generation conditions, call the art content generation engine driven by the diffusion model, and render a visual guidance scene that conforms to the emotional characteristics of children. The closed-loop feedback control module is used to establish a temporal correlation model between neurophysiological indicators and the art content generation engine. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, calculating the emotion regulation efficacy index of children's emotional characteristics, dynamically updating art interaction guidance, generating EEG feedback reward thresholds, and scoring the visual guidance scene of children's emotional characteristics. The adaptive optimization module is used to classify visually guided scenarios based on the scoring, and to regulate the emotions of autistic children based on the classification results.

2. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 1, characterized in that: The multi-channel EEG acquisition module includes a child-adaptive dry electrode array unit and a motion artifact suppression unit. The emotion state decoding module includes a multi-scale EEG feature extraction unit, an individual baseline self-calibration unit, and an emotion discrimination and reasoning unit. The dynamic generative art interaction guidance module includes an emotion color mapping strategy library unit, a diffusion model-driven content generation unit, and a progressive task delivery unit. The closed-loop feedback control module includes a multimodal behavior feature extraction unit, an efficiency index calculation unit, and a dynamic parameter modulation unit; The adaptive optimization module includes a visually guided scene scoring and classification unit, a strategy evolution unit, and a memory graph construction unit.

3. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 2, characterized in that: The child-adaptive dry electrode array unit is used to distribute the Fp1 and Fp2 positions in the forehead region and the T3, T4, and Cz positions in the temporoparietal region. The motion artifact real-time suppression unit is used to integrate a triaxial accelerometer and an adaptive notch filter to eliminate high-frequency interference caused by head micro-movements by modeling motion signal covariates. The multi-scale EEG feature extraction unit is used to perform wavelet packet decomposition on the preprocessed EEG data to obtain the energy ratios of the five frequency bands δ, θ, α, β, and γ. The individual baseline self-calibration unit is used to record the EEG baseline of children in a resting state with their eyes open and closed for 2 minutes each, and dynamically adjust the reference baseline in the alpha band. The emotion discrimination reasoning unit is used to employ a lightweight spatiotemporal convolutional neural network model, inputting multidimensional EEG feature vectors and outputting emotion labels.

4. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 3, characterized in that: The emotion color mapping strategy library unit is used to store the emotion and color association rule set, which includes the main color selection, saturation gradient and brightness adjustment parameters. The diffusion model-driven content generation unit is used to generate a path guided by an abstract graphical base, with the emotional state decoding result as a conditional input. The progressive task delivery unit is used to break down visual content into phased drawing tasks, and guide children to complete their creations through a three-stage mode of outline prompts, color filling, and free extension via a touch interface. The multimodal behavior feature extraction unit is used to capture brush pressure, movement speed, pause frequency, number of color switching times, and image area coverage entropy during the painting process. The performance index calculation unit is used to construct an LSTM fusion network and output a visually guided scene score. The dynamic parameter modulation unit is used to adjust the EEG feedback reward threshold according to the visual guidance scene score. The visual guidance scene scoring and classification unit is used to rate the quality of the generated visual guidance scene based on the visual guidance scene score and the child completion index, and classify it into three categories: high response, medium response and low response. The strategy evolution unit is used to perform cross-iteration of parameter combinations corresponding to low-response scenarios using a swarm intelligence-based optimization algorithm. The memory mapping building unit is used to accumulate a database of response patterns that integrate EEG, behavior, and art, and to deploy memory maps.

5. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 4, characterized in that: The child-adaptive dry electrode array unit includes an electrode contact impedance monitoring subunit, which measures the impedance value of the electrode-skin interface of each channel and transmits the impedance abnormality signal to the motion artifact real-time suppression unit to trigger the operation of the adaptive notch filter to avoid misjudgment. The motion artifact real-time suppression unit includes a micro-motion pattern recognition subunit, which is used to identify the type of head micro-motion based on a triaxial accelerometer and feed back the intentional action marker information to the emotion state decoding module to shield non-physiological signal interference segments. The multi-scale EEG feature extraction unit includes a frequency band coupling analysis subunit, which is used to calculate the phase-amplitude coupling strength of α and γ across frequency bands, and inputs the coupling feature data into the emotion discrimination inference unit as an additional input dimension of the classification model; The individual baseline self-calibration unit includes a resting state determination subunit, which is used to analyze the alpha wave power variation coefficient in open and closed eye states, and synchronize the effective baseline parameters to the dynamic generative art interaction guidance module for initializing the generation of the first guidance scene. The emotion discrimination reasoning unit includes a confidence assessment subunit, which is used to evaluate the probability entropy of the emotion label output and feed back the low confidence judgment result to the multi-channel EEG acquisition module to instruct to improve the sampling resolution.

6. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 5, characterized in that: The emotion color mapping strategy library unit includes a dynamic weight adjustment subunit, which is used to update the color rule weight parameters corresponding to each emotion according to the emotion regulation efficacy index. The diffusion model-driven content generation unit includes a semantic control subunit, which is used to introduce controllable perturbations when generating the abstract graph base and write the generation parameter log into the memory graph construction unit for subsequent strategy backtracking. The progressive task delivery unit includes a task completion prediction subunit, which is used to transmit data to the dynamic parameter modulation unit to adjust the EEG feedback reward threshold. The multimodal behavior feature extraction unit includes a brushstroke dynamics modeling subunit, which is used to construct a three-dimensional dynamic vector of pressure-velocity-acceleration and stream the dynamic features to the performance index calculation unit for fusion modeling. The performance index calculation unit includes a cross-session normalization subunit, which processes the performance score and sends it to the visual guidance scene scoring classification unit of the adaptive optimization module for quality rating.

7. The emotion regulation system for autistic children integrating EEG feedback and art as described in claim 6, characterized in that: The dynamic parameter modulation unit includes a feedback delay compensation subunit, which is used to predict the emotional state in the next 0.5 seconds based on the system delay, and write the corrected EEG feedback reward threshold into the incentive triggering mechanism of the multi-channel EEG acquisition module. The visually guided scene scoring and classification unit includes an abnormal pattern detection subunit, which is used to identify the parameter features of continuous low response scenes and synchronize the list of avoidance strategy combinations to the generation constraints of the diffusion model driven content generation unit. The strategy evolution unit includes a knowledge transfer subunit, which is used to derive the parameter combinations that have been successfully optimized in high-response individuals and inject them into the initial population generation process of the strategy evolution unit corresponding to other children; The memory graph construction unit includes a pattern similarity retrieval subunit, which is used to compare the matching degree between the current session baseline data and the historical response graph, and load the optimal initial strategy configuration into the dynamically generated art interaction guidance module.

8. A method for emotion regulation in autistic children integrating EEG feedback and art, based on the emotion regulation system for autistic children integrating EEG feedback and art as described in any one of claims 1 to 7, characterized in that: include: Multichannel EEG signals from the frontal and temporoparietal regions of children with autism were acquired, and the EEG data were collected by combining a motion artifact suppression algorithm. The collected EEG data is preprocessed, including frequency domain feature analysis and time domain feature analysis of the EEG data, and neurophysiological indicators are extracted. The system receives the emotional state decoding result as the generation condition, calls the art content generation engine driven by the diffusion model, and renders a visual guidance scene that conforms to the emotional characteristics of children. A temporal correlation model between neurophysiological indicators and art content generation engine is established. The temporal correlation model refers to the fusion of the painting speed, color selection entropy value and regional coverage mode of the art content generation engine, calculating the emotion regulation efficacy index of children's emotional characteristics, dynamically updating art interaction guidance, generating EEG feedback reward threshold, and scoring the visual guidance scene of children's emotional characteristics. Based on the visual guidance scenarios after scoring, the emotions of autistic children are regulated according to the classification results; The formula for calculating the emotion regulation efficacy index of children's emotional characteristics is as follows: in, Indicates at a point in time The calculated change in the frontal alpha wave asymmetry index relative to the baseline period. Represents the hyperbolic tangent function. Shannon entropy represents the color selection process during painting. Indicates a single intervention cycle Inner screen area coverage volume The standard deviation of the pen stroke speed. , , as well as All are dynamic weighting coefficients. This represents the index of emotion regulation effectiveness.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the emotional regulation system for autistic children that integrates EEG feedback and art, as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the emotional regulation system for autistic children that integrates EEG feedback and art, as described in any one of claims 1 to 7.

Images