English classroom attention regulation and control method combined with brain wave detection

Abstract

The invention discloses an English classroom attention regulation and control method combined with brain wave detection, and relates to the technical field of English classroom attention regulation and control, and the method comprises the steps: obtaining a multi-channel brain wave signal of a student in English classroom learning through a brain wave collection device, collecting visual gazing track data through an eye tracker, and obtaining a brain wave signal; capturing a face image sequence through a camera; performing frequency band separation on the multi-channel electroencephalogram signal, extracting energy of a theta wave and a beta wave of a prefrontal lobe, and calculating a theta / beta power ratio; performing de-noising and clustering processing on the visual gaze track data, identifying an effective gaze interval, calculating a reciprocal of a gaze point distribution variance in unit time, generating a visual focusing stability parameter, performing action unit identification on a facial image sequence, extracting smile frequency, eyebrow intensity and blink period characteristics, and outputting a cognitive emotion state score; and constructing a multi-modal attention fusion evaluation model based on the theta / beta power ratio, the visual focusing stability parameter and the cognitive emotion state score.

Description

Technical Field

[0001] This invention relates to the field of English classroom attention regulation technology, and in particular to a method for English classroom attention regulation that combines electroencephalogram (EEG) detection. Background Technology

[0002] English classroom attention regulation technology refers to a type of intelligent educational technology that, during English teaching, collects students' physiological, behavioral, or cognitive signals to assess their attention levels in real time and automatically adjusts the presentation of teaching content accordingly. This aims to maintain students within their optimal cognitive range for efficient learning. Its core objective is to achieve personalized teaching intervention that is tailored to individual needs and provides real-time responses, thereby improving learning focus and information absorption efficiency. Therefore, how to utilize advanced technologies to improve the intelligence and security of English classroom attention regulation has become one of the most pressing issues to be addressed.

[0003] In the field of attention regulation in English classrooms, traditional methods mainly rely on teacher observation or simple behavioral records, lacking objective and continuous physiological data support. This makes it difficult to accurately identify students' true attention status, especially in large-class teaching where there are monitoring blind spots. Furthermore, existing audio playback systems mostly use a fixed speaking speed, which cannot dynamically adjust the pace according to students' actual cognitive load. This results in students with high attention levels feeling that the information is too slow and losing interest, while students with low attention levels cannot keep up due to the speaking speed being too fast. At the same time, single EEG or eye movement indicators are easily affected by noise interference and individual differences. Existing systems do not fully integrate multi-source information such as EEG, eye movement, and facial expressions, resulting in poor stability and a high misjudgment rate in attention assessment results. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for regulating attention in English classrooms that combines EEG detection. This addresses the problem that existing listening playback systems often use a fixed speaking speed, which cannot dynamically adjust the pace according to students' actual cognitive load. As a result, students with high attention levels feel that the information is too slow and their interest decreases, while students with low attention levels cannot keep up because the speaking speed is too fast. At the same time, single EEG or eye movement indicators are easily affected by noise interference and individual differences. Furthermore, existing systems do not fully integrate multi-source information such as EEG, eye movement, and facial expressions, resulting in poor stability and high misjudgment rate of attention assessment results.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for regulating attention in English classrooms by combining electroencephalogram (EEG) detection, comprising: The system acquires multi-channel EEG signals from students during English classroom learning using EEG acquisition equipment, collects visual gaze trajectory data using an eye tracker, and captures facial image sequences using a camera. Frequency band separation was performed on multi-channel EEG signals to extract the energy of theta and beta waves in the prefrontal cortex and to calculate the theta / beta power ratio. The visual gaze trajectory data is denoised and clustered to identify the effective gaze intervals. The inverse of the variance of the gaze point distribution per unit time is calculated to generate visual focus stability parameters. Action unit recognition is performed on facial image sequences to extract features of smile frequency, frown intensity and blink cycle, and output cognitive emotion state score. Based on the θ / β power ratio, visual focus stability parameters, and cognitive emotion state scores, a multimodal attention fusion evaluation model is constructed. The currently collected θ / β power ratio, visual focus stability parameters, and cognitive emotion state are input into the multimodal attention fusion evaluation model, and the fusion attention index is output. A first threshold and a second threshold are set, and the fusion attention index within a continuous time period is compared with the first threshold and the second threshold to obtain the playback speed adjustment command; Based on the speed adjustment command, the suppression ratio of the α band energy in the central region relative to the no-task period is extracted, and this ratio is used as a scaling factor to calculate the target playback speed, thereby dynamically adjusting the output rhythm of the English listening material.

[0007] As a preferred embodiment of the English classroom attention regulation method combined with EEG detection described in this invention, the steps of acquiring multi-channel EEG signals of students during English classroom learning through an EEG acquisition device, acquiring visual gaze trajectory data through an eye tracker, and capturing facial image sequences through a camera are as follows: During classroom teaching, wearable EEG acquisition devices worn on students' heads continuously record raw EEG signals from multiple electrode channels in the prefrontal cortex and central region. Simultaneously, an eye-tracking device installed on the edge of the display uses an infrared light source and a high-speed imaging sensor to capture the changes in the position of the student's pupils in real time, generating a two-dimensional coordinate sequence and forming a visual gaze trajectory data stream; At the same time, a near-infrared camera placed in front of the teaching terminal captures video of the student's facial area, obtaining a continuous sequence of facial images; All three types of signals are transmitted to the central processing unit via wired or wireless means for timestamp alignment, ensuring that multimodal data is synchronized with millisecond-level precision.

[0008] As a preferred embodiment of the English classroom attention regulation method combined with EEG detection described in this invention, the specific steps of performing frequency band separation on multi-channel EEG signals, extracting the energy of prefrontal cortex theta and beta waves, and calculating the theta / beta power ratio are as follows: Preprocessing operations are performed on the received raw EEG signals, including notch filtering to remove power frequency interference, independent component analysis (ICA) denoising to eliminate motion artifacts, and low-pass filtering to suppress high-frequency noise. The cleaned signal is segmented and processed according to a fixed time window. Within each time window, a Fast Fourier Transform (FFT) is performed on the signal in the prefrontal electrode channel to obtain the frequency domain power spectral density distribution. Based on the international 10-20 system positioning standard, the integrated power values ​​in the θ band and β band are extracted respectively, and denoted as θ energy and β energy; Divide the θ energy within the current time window by the β energy to obtain the θ / β power ratio at that moment; This ratio, as a primary neural indicator reflecting students' cognitive load and alertness level, is labeled and stored.

[0009] As a preferred embodiment of the English classroom attention regulation method combined with EEG detection described in this invention, the steps include: denoising and clustering the visual gaze trajectory data, identifying effective gaze intervals, calculating the reciprocal of the variance of gaze point distribution per unit time to generate visual focus stability parameters, performing action unit recognition on facial image sequences, extracting smile frequency, frown intensity, and blink cycle features, and outputting a cognitive emotional state score. Spatial filtering and velocity threshold discrimination are performed on the raw coordinate sequence output by the eye tracker to remove abnormal jump points caused by blinking or micro-head movements, thus completing data denoising; A sliding window clustering algorithm is used to group the cleaned fixation points and identify fixation clusters that remain in the same semantic region for more than a preset time, which are then determined to be valid fixation intervals. The number of effective fixation intervals per unit time and their spatial distribution dispersion are statistically analyzed. The covariance matrix of the fixation point coordinates is calculated, and its trace is used as a quantitative indicator of the distribution variance. The reciprocal of this variance is taken as the visual focus stability parameter. The higher the value, the more focused the gaze and the stronger the attention. Gray-level normalization and key point localization are performed on facial image sequences to extract the change trends of action units (AU) in the eyebrow, corner of mouth and eyelid regions; Based on the AU intensity change curve, the frequency of smiling, the peak intensity of frowning, and the blink interval period were statistically analyzed per unit time. The above three features are weighted and fused to generate a comprehensive score, called the cognitive-emotional state score, which is used to characterize students' level of interest and cognitive tension.

[0010] As a preferred embodiment of the English classroom attention regulation method combined with EEG detection described in this invention, wherein: the above.

[0011] As a preferred embodiment of the English classroom attention regulation method combining EEG detection described in this invention, the specific steps for constructing a multimodal attention fusion evaluation model based on the θ / β power ratio, visual focus stability parameters, and cognitive emotional state scores are as follows: Historical sample data of multiple students under different attention tasks were collected, including their θ / β power ratio, visual focus stability parameters, and cognitive emotional state scores in states such as focused reading, listening comprehension, and daydreaming. The actual attention levels were then labeled by teachers or behavior coders. Using the labeled attention level as the label and the above three features as input variables, a multimodal fusion model under a supervised learning framework is constructed. The multimodal fusion model structure contains three parallel nonlinear mapping paths, which correspond to the normalization processing of three modal features respectively. For the θ / β power ratio, an sigmoid function is used to map it to the [0,1] interval; For the visual focus stability parameter, a hyperbolic tangent function is used for compression transformation; For cognitive emotion state ratings, a truncated linear function is used to limit its output range; The output of each pathway is multiplied by an adjustable weight coefficient, and the sum is used to obtain the overall attention evaluation value. By minimizing the prediction error, the gradient descent algorithm is used to optimize the weight coefficients, making the model output approximate the real attention label. After training is complete, the optimal weight parameters are embedded in the model to form an attention evaluation engine suitable for individuals or groups.

[0012] As a preferred embodiment of the English classroom attention regulation method combining EEG detection described in this invention, the steps of inputting the currently collected θ / β power ratio, visual focus stability parameters, and cognitive emotional state into the multimodal attention fusion evaluation model and outputting a fusion attention index are as follows: During the real-time operation phase, the θ / β power ratio extracted within the current time window is... Visual focus stability parameters Cognitive Emotional State Score Input the pre-trained multimodal attention fusion evaluation model sequentially; The model first performs normalization on each feature: right Applying the Sigmoid function ,in, Shape adjustment factor; right Applying the hyperbolic tangent function ; right Applying the truncation function This ensures that its value range is limited; Then, the normalized results are multiplied by predetermined weighting coefficients. , , And sum them up, the expression is: ; in, This is the current fusion attention index; the higher the value, the higher the level of attention.

[0013] As a preferred embodiment of the English classroom attention regulation method combining EEG detection described in this invention, the steps of setting a first threshold and a second threshold, comparing the fusion attention index over a continuous time period with the first and second thresholds to obtain a playback speed adjustment command, are as follows: During the system initialization phase, two attention reference thresholds are set: the first threshold... This represents the threshold of low attention, the second threshold. This indicates the critical point for highly focused attention, satisfying... ; Fusion attention index over multiple consecutive time windows Perform a moving average process to eliminate the risk of misjudgment caused by instantaneous fluctuations; After moving average Persistently below If the preset time length is exceeded, a command to reduce the playback speed will be generated; when consistently higher If the preset time length is exceeded, a command to increase playback speed is generated; The speed adjustment command is sent to the audio control module, triggering the next stage of the playback rhythm adjustment process.

[0014] As a preferred embodiment of the English classroom attention regulation method combined with EEG detection described in this invention, the steps of extracting the inhibition ratio of the central alpha band energy relative to the task-free state period based on speed adjustment commands, using this ratio as a factor to calculate the target playback speed, and dynamically adjusting the output rhythm of the English listening material are as follows: In response to the playback speed adjustment command, the central zone alpha wave energy monitoring process is initiated; During the task-free rest period before the course began, EEG signals were collected from students in a relaxed state with their eyes closed for a sustained period of time. The mean energy of the alpha band at the central electrodes was extracted and denoted as [missing value]. As a baseline reference; During the teaching process, the average energy of the α band in the same region is extracted in real time and denoted as... ; The alpha wave suppression ratio is calculated using the following expression: ; This ratio reflects the degree of active attention invested by the brain; the more pronounced the inhibition, the higher the level of attention. The larger; The ratio is then normalized using a sliding window method to eliminate absolute power differences between individuals, resulting in a standardized attention intensity index. ; Will Substituting into the playback speed control model, the expression is: ; in, The preset standard playback speed, To adjust the gain coefficient, As the attention baseline threshold, The ultimate goal is playback speed; when hour, The system speeds up audio playback; when hour, The system slows down the playback. The audio playback module is based on The decoding rate is adjusted in real time to achieve adaptive output of English listening materials.

[0015] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the English classroom attention regulation method combined with electroencephalogram detection as described in the first aspect of the present invention.

[0016] Thirdly, the present invention provides 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 English classroom attention regulation method combined with EEG detection as described in the first aspect of the present invention.

[0017] The beneficial effects of this invention are as follows: By integrating multimodal physiological signals such as the EEG theta / β power ratio, visual focus stability, and facial emotional state, an individualized attention fusion assessment model is constructed to achieve dynamic and accurate identification of students' classroom attention levels. Based on the degree of central alpha wave inhibition, an adaptive audio control mechanism is designed to transform neurophysiological feedback into playback speed adjustment instructions for English listening materials, forming a perception-evaluation-response closed-loop control. This not only improves the objectivity and real-time nature of attention monitoring but also optimizes the learning load through personalized rhythm adjustment, enhancing students' information reception efficiency and concentration duration. This effectively solves the problems of fixed playback rhythm and lack of individualized feedback in traditional English listening teaching. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0019] Figure 1 This is a flowchart of the English classroom attention regulation method combined with EEG detection in Example 1. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] 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.

[0022] 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.

[0023] Example 1, referring to Figure 1 This embodiment of the invention provides a method for regulating attention in English classrooms by combining electroencephalogram (EEG) detection, comprising the following steps: S1. Acquire multi-channel EEG signals of students during English classroom learning through EEG acquisition equipment, collect visual gaze trajectory data through eye tracker, and capture facial image sequences through camera; Furthermore, during classroom teaching, wearable EEG acquisition devices worn on students' heads continuously record raw EEG signals from multiple electrode channels in the prefrontal cortex and central region. Simultaneously, an eye-tracking device installed on the edge of the display uses an infrared light source and a high-speed imaging sensor to capture the changes in the position of the student's pupils in real time, generating a two-dimensional coordinate sequence and forming a visual gaze trajectory data stream; At the same time, a near-infrared camera placed in front of the teaching terminal captures video of the student's facial area, obtaining a continuous sequence of facial images; All three types of signals are transmitted to the central processing unit via wired or wireless means for timestamp alignment to ensure that multimodal data is synchronized with millisecond-level precision. It should be noted that the synchronous acquisition and timestamp alignment mechanism of multimodal data ensures the consistency of EEG, eye movement and facial expression signals in the time dimension, avoids feature misalignment due to device sampling delay, provides an accurate time reference for subsequent cross-modal correlation analysis, and significantly improves the spatiotemporal reliability of the input data of the fusion evaluation model.

[0024] S2. Perform frequency band separation on the multi-channel EEG signal, extract the energy of the theta wave and beta wave in the prefrontal cortex, and calculate the theta / beta power ratio; Furthermore, preprocessing operations are performed on the received raw EEG signals, including notch filtering to remove power frequency interference, independent component analysis (ICA) denoising to eliminate motion artifacts, and low-pass filtering to suppress high-frequency noise. The cleaned signal is segmented and processed according to a fixed time window. Within each time window, a Fast Fourier Transform (FFT) is performed on the signal in the prefrontal electrode channel to obtain the frequency domain power spectral density distribution. Based on the international 10-20 system positioning standard, the integrated power values ​​in the θ band and β band are extracted respectively, and denoted as θ energy and β energy; Divide the θ energy within the current time window by the β energy to obtain the θ / β power ratio at that moment; This ratio, as a primary neural indicator reflecting students' cognitive load and alertness level, is labeled and stored; It should be noted that the calculation of the θ / β power ratio is based on frequency domain analysis of the prefrontal cortex, which is closely related to executive function and attention regulation. Combining ICA denoising and FFT transformation can effectively extract rhythmic features with neurophysiological significance, making the θ / β ratio a sensitive indicator reflecting changes in students' alertness and cognitive load.

[0025] S3. Denoise and cluster the visual gaze trajectory data, identify the effective gaze interval, calculate the reciprocal of the variance of gaze point distribution per unit time, generate visual focus stability parameters, perform action unit recognition on facial image sequences, extract smile frequency, frown intensity and blink cycle features, and output cognitive emotion state score. Furthermore, spatial filtering and velocity threshold discrimination are performed on the raw coordinate sequence output by the eye tracker to remove abnormal jump points caused by blinking or micro-head movements, thus completing data denoising. A sliding window clustering algorithm is used to group the cleaned fixation points and identify fixation clusters that remain in the same semantic region for more than a preset time, which are then determined to be valid fixation intervals. The number of effective fixation intervals per unit time and their spatial distribution dispersion are statistically analyzed. The covariance matrix of the fixation point coordinates is calculated, and its trace is used as a quantitative indicator of the distribution variance. The reciprocal of this variance is taken as the visual focus stability parameter. The higher the value, the more focused the gaze and the stronger the attention. Gray-level normalization and key point localization are performed on facial image sequences to extract the change trends of action units (AU) in the eyebrow, corner of mouth and eyelid regions; Based on the AU intensity change curve, the frequency of smiling, the peak intensity of frowning, and the blink interval period were statistically analyzed per unit time. The above three features are weighted and fused to generate a comprehensive score, called the cognitive emotional state score, which is used to characterize students’ level of interest and cognitive tension. It should be noted that the visual focus stability parameter is quantified by the inverse of the variance of the fixation point distribution, which can objectively characterize the spatial concentration of students' visual attention. Combined with the clustering identification of effective fixation intervals, it can distinguish between active attention and unconscious saccades, thereby improving the discriminative effectiveness of eye movement data in attention assessment.

[0026] S4. Based on the θ / β power ratio, visual focus stability parameters, and cognitive emotion state scores, construct a multimodal attention fusion evaluation model. Input the currently collected θ / β power ratio, visual focus stability parameters, and cognitive emotion state into the multimodal attention fusion evaluation model and output the fusion attention index. Furthermore, historical sample data of multiple students under different attention tasks were collected, including their θ / β power ratio, visual focus stability parameters, and cognitive emotional state scores in states such as focused reading, listening comprehension, and daydreaming. The actual attention levels were then labeled by teachers or behavior coders. Using the labeled attention level as the label and the above three features as input variables, a multimodal fusion model under a supervised learning framework is constructed. The multimodal fusion model structure contains three parallel nonlinear mapping paths, which correspond to the normalization processing of three modal features respectively; For the θ / β power ratio, an sigmoid function is used to map it to the [0,1] interval; For the visual focus stability parameter, a hyperbolic tangent function is used for compression transformation; For cognitive emotion state ratings, a truncated linear function is used to limit its output range; The output of each pathway is multiplied by an adjustable weight coefficient, and the sum is used to obtain the overall attention evaluation value. By minimizing the prediction error, the gradient descent algorithm is used to optimize the weight coefficients, making the model output approximate the real attention label. After training is completed, the optimal weight parameters are fixed in the model to form an attention evaluation engine suitable for individuals or groups; During the real-time operation phase, the θ / β power ratio extracted within the current time window is... Visual focus stability parameters Cognitive Emotional State Score Input the pre-trained multimodal attention fusion evaluation model sequentially; The model first performs normalization on each feature: right Applying the Sigmoid function ,in, Shape adjustment factor; right Applying the hyperbolic tangent function ; right Applying the truncation function This ensures that its value range is limited; Then, the normalized results are multiplied by predetermined weighting coefficients. , , And sum them up, the expression is: ; in, This is the fusion attention index at the current moment; the higher the value, the higher the level of attention. It should be noted that the multimodal attention fusion evaluation model uses a nonlinear function to normalize features of different dimensions and optimizes the weight coefficients through supervised learning, thereby achieving adaptive weighted fusion of EEG, eye movement and emotion features, making the output fused attention index more individualized and physiologically interpretable.

[0027] S5. Set a first threshold and a second threshold, compare the fusion attention index within a continuous time period with the first threshold and the second threshold, and obtain the playback speed adjustment command. Furthermore, during the system initialization phase, two attention reference thresholds are set: the first threshold... This represents the threshold of low attention, the second threshold. This indicates the critical point for highly focused attention, satisfying... ; Fusion attention index over multiple consecutive time windows Perform a moving average process to eliminate the risk of misjudgment caused by instantaneous fluctuations; After moving average Persistently below If the preset time length is exceeded, a command to reduce the playback speed will be generated; when consistently higher If the preset time length is exceeded, a command to increase playback speed is generated; The speed adjustment command is sent to the audio control module, triggering the next stage of the playback rhythm adjustment process; It should be noted that the introduction of moving average processing to smooth the fusion attention index effectively suppresses misjudgments caused by short-term noise fluctuations. Combined with the dual threshold comparison mechanism, stable state classification is achieved, which improves the robustness of playback speed adjustment command generation and the rationality of teaching intervention.

[0028] S6. Based on the speed adjustment command, extract the suppression ratio of the α band energy in the central area relative to the no-task state period, use it as a ratio factor to calculate the target playback speed, and dynamically adjust the output rhythm of the English listening material. Furthermore, in response to playback speed adjustment commands, the central zone alpha wave energy monitoring process is initiated; During the task-free rest period before the course began, EEG signals were collected from students in a relaxed state with their eyes closed for a sustained period of time. The mean energy of the alpha band at the central electrodes was extracted and denoted as [missing value]. As a baseline reference; During the teaching process, the average energy of the α band in the same region is extracted in real time and denoted as... ; The alpha wave suppression ratio is calculated using the following expression: ; This ratio reflects the degree of active attention invested by the brain; the more pronounced the inhibition, the higher the level of attention. The larger; The ratio is then normalized using a sliding window method to eliminate absolute power differences between individuals, resulting in a standardized attention intensity index. ; Will Substituting into the playback speed control model, the expression is: ; in, The preset standard playback speed, To adjust the gain coefficient, As the attention baseline threshold, The ultimate goal is playback speed; when hour, The system speeds up audio playback; when hour, The system slows down the playback. The audio playback module is based on Real-time adjustment of decoding rate enables adaptive output of English listening materials; It should be noted that the playback speed control model based on the central zone alpha wave inhibition ratio directly converts neural feedback into audio rhythm adjustment signals, forming a closed-loop control path. This not only achieves dynamic adaptation of the output rhythm of teaching content, but also maintains a high level of attention through appropriate acceleration stimulation, thereby enhancing the interactivity and adaptability of the learning process.

[0029] This embodiment also provides a computer device applicable to the English classroom attention regulation method combined with EEG detection, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the English classroom attention regulation method combined with EEG detection as proposed in the above embodiment.

[0030] 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.

[0031] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the English classroom attention regulation method combined with EEG detection as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0032] In summary, this invention integrates multimodal physiological signals such as EEG theta / β power ratio, visual focus stability, and facial emotional state to construct an individualized attention fusion assessment model. This model enables dynamic and accurate identification of students' classroom attention levels. Furthermore, based on the degree of central alpha wave inhibition, an adaptive audio control mechanism is designed to transform neurophysiological feedback into playback speed adjustment commands for English listening materials. This forms a perception-assessment-response closed-loop control, which not only improves the objectivity and real-time performance of attention monitoring but also optimizes the learning load through personalized rhythm adjustment, enhancing students' information reception efficiency and concentration duration. This effectively solves the problems of fixed playback rhythm and lack of individualized feedback in traditional English listening teaching.

[0033] 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. A method for regulating attention in English classrooms by combining electroencephalogram (EEG) detection, characterized in that: include: The system acquires multi-channel EEG signals from students during English classroom learning using EEG acquisition equipment, collects visual gaze trajectory data using an eye tracker, and captures facial image sequences using a camera. Frequency band separation was performed on multi-channel EEG signals to extract the energy of theta and beta waves in the prefrontal cortex and to calculate the theta / beta power ratio. The visual gaze trajectory data is denoised and clustered to identify the effective gaze intervals. The inverse of the variance of the gaze point distribution per unit time is calculated to generate visual focus stability parameters. Action unit recognition is performed on facial image sequences to extract features of smile frequency, frown intensity and blink cycle, and output cognitive emotion state score. Based on the θ / β power ratio, visual focus stability parameters, and cognitive emotion state scores, a multimodal attention fusion evaluation model is constructed. The currently collected θ / β power ratio, visual focus stability parameters, and cognitive emotion state are input into the multimodal attention fusion evaluation model, and the fusion attention index is output. A first threshold and a second threshold are set, and the fusion attention index within a continuous time period is compared with the first threshold and the second threshold to obtain the playback speed adjustment command; Based on the speed adjustment command, the suppression ratio of the α band energy in the central region relative to the no-task period is extracted, and this ratio is used as a scaling factor to calculate the target playback speed, thereby dynamically adjusting the output rhythm of the English listening material.

2. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 1, characterized in that: The specific steps are as follows: acquiring multi-channel EEG signals of students during English classroom learning through EEG acquisition equipment, acquiring visual gaze trajectory data through eye tracker, and capturing facial image sequences through camera. During classroom teaching, wearable EEG acquisition devices worn on students' heads continuously record raw EEG signals from multiple electrode channels in the prefrontal cortex and central region. Simultaneously, an eye-tracking device installed on the edge of the display uses an infrared light source and a high-speed imaging sensor to capture the changes in the position of the student's pupils in real time, generating a two-dimensional coordinate sequence and forming a visual gaze trajectory data stream; At the same time, a near-infrared camera placed in front of the teaching terminal captures video of the student's facial area, obtaining a continuous sequence of facial images; All three types of signals are transmitted to the central processing unit via wired or wireless means for timestamp alignment, ensuring that multimodal data is synchronized with millisecond-level precision.

3. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 2, characterized in that: The specific steps for performing frequency band separation on multi-channel EEG signals, extracting the theta and beta wave energies from the prefrontal cortex, and calculating the theta / beta power ratio are as follows: Preprocessing operations are performed on the received raw EEG signals, including notch filtering to remove power frequency interference, independent component analysis (ICA) denoising to eliminate motion artifacts, and low-pass filtering to suppress high-frequency noise. The cleaned signal is segmented and processed according to a fixed time window. Within each time window, a Fast Fourier Transform (FFT) is performed on the signal in the prefrontal electrode channel to obtain the frequency domain power spectral density distribution. Based on the international 10-20 system positioning standard, the integrated power values ​​in the θ band and β band are extracted respectively, and denoted as θ energy and β energy; Divide the θ energy within the current time window by the β energy to obtain the θ / β power ratio at that moment; This ratio, as a primary neural indicator reflecting students' cognitive load and alertness level, is labeled and stored.

4. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 3, characterized in that: The process involves denoising and clustering the visual gaze trajectory data, identifying effective gaze intervals, calculating the reciprocal of the variance of gaze point distribution per unit time to generate visual focus stability parameters, performing action unit recognition on facial image sequences, extracting features such as smile frequency, frown intensity, and blink cycle, and outputting a cognitive emotion state score. The specific steps are as follows: Spatial filtering and velocity threshold discrimination are performed on the raw coordinate sequence output by the eye tracker to remove abnormal jump points caused by blinking or micro-head movements, thus completing data denoising; A sliding window clustering algorithm is used to group the cleaned fixation points and identify fixation clusters that remain in the same semantic region for more than a preset time, which are then determined to be valid fixation intervals. The number of effective fixation intervals per unit time and their spatial distribution dispersion are statistically analyzed. The covariance matrix of the fixation point coordinates is calculated, and its trace is used as a quantitative indicator of the distribution variance. The reciprocal of this variance is taken as the visual focus stability parameter. The higher the value, the more focused the gaze and the stronger the attention. Gray-level normalization and key point localization are performed on facial image sequences to extract the change trends of action units (AU) in the eyebrow, corner of mouth and eyelid regions; Based on the AU intensity change curve, the frequency of smiling, the peak intensity of frowning, and the blink interval period were statistically analyzed per unit time. The above three features are weighted and fused to generate a comprehensive score, called the cognitive-emotional state score, which is used to characterize students' level of interest and cognitive tension.

5. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 4, characterized in that: The multimodal attention fusion evaluation model is constructed based on the θ / β power ratio, visual focus stability parameters, and cognitive emotion state scores. The specific steps are as follows: Historical sample data of multiple students under different attention tasks were collected, including their θ / β power ratio, visual focus stability parameters, and cognitive emotional state scores in states such as focused reading, listening comprehension, and daydreaming. The actual attention levels were then labeled by teachers or behavior coders. Using the labeled attention level as the label and the above three features as input variables, a multimodal fusion model under a supervised learning framework is constructed. The multimodal fusion model structure contains three parallel nonlinear mapping paths, which correspond to the normalization processing of three modal features respectively. For the θ / β power ratio, an sigmoid function is used to map it to the [0,1] interval; For the visual focus stability parameter, a hyperbolic tangent function is used for compression transformation; For cognitive emotion state ratings, a truncated linear function is used to limit its output range; The output of each pathway is multiplied by an adjustable weight coefficient, and the sum is used to obtain the overall attention evaluation value. By minimizing the prediction error, the gradient descent algorithm is used to optimize the weight coefficients, making the model output approximate the real attention label. After training is complete, the optimal weight parameters are embedded in the model to form an attention evaluation engine suitable for individuals or groups.

6. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 5, characterized in that: The steps for inputting the currently collected θ / β power ratio, visual focus stability parameters, and cognitive emotional state into the multimodal attention fusion evaluation model and outputting the fusion attention index are as follows: During the real-time operation phase, the θ / β power ratio extracted within the current time window is... R Visual focus stability parameters V Cognitive Emotional State Score E Input the pre-trained multimodal attention fusion evaluation model sequentially; The model first performs normalization on each feature: right R Applying the Sigmoid function Where α is the shape adjustment factor; right V Applying the hyperbolic tangent function ; right E Applying the truncation function This ensures that its value range is limited; Then, the normalized results are multiplied by predetermined weighting coefficients. , , And sum them up, the expression is: ； in, F This is the current fusion attention index; the higher the value, the higher the level of attention.

7. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 6, characterized in that: The steps for setting a first threshold and a second threshold, comparing the fusion attention index over a continuous time period with the first and second thresholds to obtain a playback speed adjustment command are as follows: During the system initialization phase, two attention reference thresholds are set: the first threshold... L This represents the threshold of low attention, the second threshold. H This indicates the critical point for high concentration of attention, satisfying... L <H ; Fusion attention index over multiple consecutive time windows F Perform a moving average process to eliminate the risk of misjudgment caused by instantaneous fluctuations; After moving average F consistently below L If the preset time length is exceeded, a command to reduce the playback speed will be generated; when F consistently higher H If the preset time length is exceeded, a command to increase playback speed is generated; The speed adjustment command is sent to the audio control module, triggering the next stage of the playback rhythm adjustment process.

8. The English classroom attention regulation method combined with electroencephalogram (EEG) detection as described in claim 7, characterized in that: The process of extracting the suppression ratio of the central α band energy relative to the no-task period based on speed adjustment commands, using this ratio as a scaling factor to calculate the target playback speed, and dynamically adjusting the output rhythm of the English listening material involves the following steps: In response to the playback speed adjustment command, the central zone alpha wave energy monitoring process is initiated; During the task-free rest period before the course began, EEG signals were collected from students in a relaxed state with their eyes closed for a sustained period of time. The mean energy of the alpha band at the central electrodes was extracted and denoted as [missing value]. P As a baseline reference; During the teaching process, the average energy of the α band in the same region is extracted in real time and denoted as... Q ; The alpha wave suppression ratio is calculated using the following expression: ； This ratio reflects the degree of active attention invested by the brain; the more pronounced the inhibition, the higher the level of attention. The larger; The ratio is then normalized using a sliding window method to eliminate absolute power differences between individuals, resulting in a standardized attention intensity index. ; Will Substituting into the playback speed control model, the expression is: ； in, S The preset standard playback speed, To adjust the gain coefficient, T As the attention baseline threshold, The ultimate goal is playback speed; when hour, The system speeds up audio playback; when hour, The system slows down playback; The audio playback module is based on The decoding rate is adjusted in real time to achieve adaptive output of English listening materials.

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 English classroom attention regulation method combined with EEG detection as described in any one of claims 1 to 8.

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 English classroom attention regulation method combined with EEG detection as described in any one of claims 1 to 8.

Images