An english classroom attention regulation method based on brain wave feedback

Abstract

The application discloses an English classroom attention regulation method based on brain wave feedback, and relates to the technical field of intelligent human-computer interaction, which comprises the following steps: guiding students to complete standardized concentration tasks and relaxation tasks before classes, collecting brain waves, eye movements and heart rate variability data, and establishing individualized attention baseline; collecting brain wave signals, facial expressions, eye movement characteristics and heart rate variability data of all students in real time during English classroom teaching; performing cross-modal fusion analysis based on the individualized attention baseline and the collected multi-modal data, and determining the current attention state category of each student; matching and executing corresponding individualized intervention measures from a preset intervention strategy library according to the attention state category, the individual characteristics of students and the current teaching content type; and dynamically evaluating the intervention effect according to the state change of students after the intervention, and adjusting the subsequent intervention strategy to form a closed-loop regulation.

Description

Technical Field

[0001] This invention relates to the field of intelligent human-computer interaction technology, and in particular to a method for regulating attention in English classrooms based on electroencephalogram (EEG) feedback. Background Technology

[0002] Intelligent human-computer interaction technology is a cutting-edge interdisciplinary field that integrates artificial intelligence, computer science, cognitive psychology, design, and human factors engineering. It aims to build a more natural, efficient, intelligent, and human-centered two-way interaction between users and intelligent systems. This technology not only focuses on traditional input / output interfaces but also emphasizes the system's understanding and response to implicit information such as user intent, emotions, and cognitive states. Through multimodal channels such as voice, gestures, eye tracking, facial expressions, and EEG, it achieves human-centered adaptive interaction and is widely applied in education, healthcare, intelligent manufacturing, and autonomous driving, driving the evolution of the human-machine relationship from a "tool-using" relationship to a "collaborative" one.

[0003] In traditional classroom teaching, teachers rely on experience or simple behavioral observations to judge students' attention status, making it difficult to accurately, in real time, and quantitatively identify the cognitive engagement level of individuals or groups. Moreover, existing classroom interventions often use uniform instructions, which cannot dynamically match appropriate intervention strategies according to students' real-time attention status, learning style, and type of teaching content, resulting in limited intervention effects or even interference. Summary of the Invention

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

[0005] Therefore, this invention provides an English classroom attention regulation method based on EEG feedback. This solves the problem that in traditional classroom teaching, teachers rely on experience or simple behavioral observation to judge students' attention status, making it difficult to accurately, in real time, and quantitatively identify the cognitive engagement level of individuals or groups. Furthermore, existing classroom interventions often use uniform instructions and cannot dynamically match and adapt intervention strategies according to students' real-time attention status, learning style, and teaching content type, resulting in limited intervention effects or even interference.

[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 based on electroencephalogram (EEG) feedback, comprising: Before class, students are guided to complete standardized focus and relaxation tasks, and brainwave, eye movement and heart rate variability data are collected to establish a personalized attention baseline. During English classroom teaching, the brainwave signals, facial expressions and eye movement characteristics, as well as heart rate variability data of all students are collected in real time and synchronously. Based on the personalized attention baseline and the collected multimodal data, cross-modal fusion analysis is performed to determine the current attention state category of each student; Based on the attention state category, individual student characteristics, and current teaching content type, match and execute corresponding personalized intervention measures from the preset intervention strategy library; The effectiveness of the intervention is dynamically assessed based on changes in students' status after the intervention is implemented, and subsequent intervention strategies are adjusted to form a closed-loop control. Based on the aforementioned attention state categories, a class attention heatmap is generated. Combined with the teaching progress, teaching decision suggestions are pushed to the teacher's terminal, and teachers are supported in triggering collaborative intervention operations.

[0007] As a preferred embodiment of the English classroom attention regulation method based on EEG feedback described in this invention, the specific steps for establishing a personalized attention baseline are as follows: Before class, students are asked to complete standardized focus tasks and standardized relaxation tasks in sequence. During the execution of standardized focus tasks, EEG signals, eye movement trajectory data, and heart rate variability data are collected simultaneously to form a physiological dataset of focus state. During the standardized relaxation task, brainwave signals, eye movement trajectory data, and heart rate variability data were collected simultaneously to form a physiological dataset of the relaxation state. Frequency domain analysis was performed on the physiological dataset of focused state to extract the average power values ​​of the θ band from 4 Hz to 8 Hz and the average power values ​​of the β band from 13 Hz to 30 Hz. A time-domain analysis was performed on the physiological dataset of focused state to count the number of blinks per unit time, thus obtaining the blink frequency under focused state. The standard deviation of adjacent normal heartbeat intervals was calculated from the heart rate interval sequences in the physiological dataset of focused state to obtain the heart rate variability index under focused state. The frequency and time domain processing procedures of the relaxed physiological dataset were repeated to obtain the average power value of the θ band, the average power value of the β band, the blink rate and the heart rate variability index in the relaxed state, respectively. The eight indicators are combined into an ordered vector, which serves as the student's personalized attention baseline.

[0008] As a preferred embodiment of the English classroom attention regulation method based on EEG feedback described in this invention, the specific steps of the cross-modal fusion analysis to determine the current attention state category of each student are as follows: During English classroom teaching, the brainwave signals, facial video streams, and heart rate interval sequences of each student are acquired in real time at a fixed sampling frequency. Bandpass filtering and segmented windowing are applied to the EEG signal to calculate the average power values ​​of the θ and β bands within the current window; Facial key points are detected frame by frame in the facial video stream to identify the opening and closing state of the eyelids and count the number of blinks per unit time. Calculate the standard deviation of adjacent normal heartbeat intervals within the current window for the heart rate interval sequence to obtain the current heart rate variability index; The four real-time indicators were normalized with the personalized attention baseline to eliminate the influence of individual physiological differences. The normalized four-dimensional feature vector is input into the multimodal attention state discrimination model; The multimodal attention state discrimination model adopts a gated cross-attention mechanism, expressed as: ; in, Represents the EEG feature vector, Represents visual feature vectors. A vector representing the embedded heart rate variability feature scalar; This represents a vector concatenation operation; , , , All are learnable parameter matrices; Use the Sigmoid activation function; This indicates element-wise multiplication; By dynamically adjusting the contribution weights of different modal features through a gating mechanism, a fused feature vector is generated. ; Will Input a fully connected classification layer and output the probability distribution of six attention state categories; The category with the highest probability is selected as the current attention state judgment result; The six categories of attention states include high focus, normal focus, slight inattentiveness, deep inattentiveness, cognitive confusion, and fatigue.

[0009] As a preferred embodiment of the English classroom attention regulation method based on EEG feedback described in this invention, the specific steps of matching and executing corresponding personalized intervention measures according to attention state category, student individual characteristics, and current teaching content type are as follows: Obtain the type identifier of the current teaching content, wherein the type identifier is selected from one of four categories: listening training, speaking practice, reading comprehension, or grammar explanation; The corresponding intervention strategy sub-library is invoked based on the type identifier; Retrieve a set of intervention rules that match the current attention state category from the intervention strategy sub-library; Each rule in the intervention rule set consists of two parts: a precondition and an action instruction. The precondition is composed of the attention state category and the student's historical response record. Select the action command with the highest historical response success rate from the set of matched intervention rules; The action command includes at least one of the following: The student terminal highlights keywords, plays auxiliary voice prompts, pushes interactive micro-lesson videos, triggers wristband vibration reminders, and generates instant Q&A questions. Send the selected action command to the target student's terminal and record the command execution time and type.

[0010] As a preferred embodiment of the English classroom attention regulation method based on EEG feedback described in this invention, the specific steps of dynamically evaluating the intervention effect and adjusting subsequent intervention strategies based on changes in student state after the intervention are as follows: The effect evaluation window is launched after the action command is executed, and the window lasts for ten seconds; Continuously monitor changes in the target students' attention status categories within the assessment window; If at least one instance of attention shifting to a higher level of focus occurs within the assessment window, the current intervention is deemed effective. If the attention state category does not shift positively at the end of the assessment window, the current intervention is deemed ineffective. When an intervention is deemed ineffective, a suboptimal action instruction is selected from the same intervention strategy sub-library and re-executed. If two consecutive interventions are ineffective, the student will be marked as requiring manual intervention, and a high-priority prompt message will be generated on the teacher's terminal. At the same time, automatic intervention for the student will be suspended until the teacher confirms the action or the student's condition recovers naturally.

[0011] As a preferred embodiment of the English classroom attention regulation method based on EEG feedback described in this invention, the specific steps for generating the class attention heatmap are as follows: Obtain the current attention state category results for all students; The physical seating arrangement in the classroom is mapped to a two-dimensional plane coordinate system, with each student corresponding to a unique coordinate position; Six attention state categories were assigned color codes, with warm colors used for high focus and normal focus, and cool colors used for the other four categories. In a two-dimensional coordinate system, each student's corresponding position is filled with the color corresponding to their current attention state category; The filled image is then smoothed and interpolated to generate a class attention heatmap with continuous color levels. The heat map is displayed in real time on the monitoring interface of the teacher terminal.

[0012] As a preferred solution of the English classroom attention regulation method based on brain wave feedback described in the present invention, wherein: the step of pushing teaching decision-making suggestions to the teacher terminal in combination with the teaching progress is as follows: Obtain the progress identifier of the current teaching session, and the progress identifier includes an introduction stage, a new knowledge explanation stage, a consolidation exercise stage or a summary feedback stage; Count the number of students in a non-concentrated state, and the non-concentrated state includes four categories: slight distraction, deep distraction, cognitive confusion and fatigue; Calculate the proportion of non-concentrated students, denoted as , and set a dynamic threshold , and the dynamic threshold is adjusted according to the progress identifier of the current teaching session: In the new knowledge explanation stage takes a lower value, and in the consolidation exercise stage takes a higher value; When the condition is satisfied, the system automatically generates teaching decision-making suggestions; The teaching decision-making suggestions include at least one of the following: Insert group discussion activities, switch to a fun quiz session, slow down the speech rate and repeat key content, or temporarily group for differentiated teaching; Send the generated teaching decision-making suggestions together with the class attention heat Figure 1 map and push them to the teacher terminal; The teacher can choose to adopt the suggestions and trigger collaborative intervention operations, and the collaborative intervention operations include broadcasting a prompt sound to the whole class, starting a collective relaxation training or adjusting the teaching rhythm.

[0013] As a preferred solution of the English classroom attention regulation method based on brain wave feedback described in the present invention, wherein: after the teacher triggers the collaborative intervention operation, the system executes a whole-class linkage response mechanism, and the specific steps are as follows: Receive the collaborative intervention instruction sent by the teacher terminal, and the collaborative intervention instruction includes one of three categories: collective prompt, rhythm reset or group switching; If the collaborative intervention instruction is a collective prompt, synchronously play a preset voice prompt to all student terminals, and highlight the current teaching keywords on the main display screen of the classroom; If the collaborative intervention instruction is a rhythm reset, automatically pause the playback of the current teaching content, insert a breathing regulation guiding audio with a duration of 30 seconds, and at the same time close the input functions of all student terminals to force a short silent state; If the collaborative intervention instruction is group switching, then the learning groups are reorganized according to each student's current attention status category and historical learning performance; The re-division of learning groups adopts an optimized clustering strategy, with the objective function being to minimize the variance of attention states within groups and maximize the complementarity of cognitive abilities between groups. The newly generated group assignment results are pushed to the teacher's terminal for confirmation, and the collaboration interface on the student's terminal is updated simultaneously. During the implementation of the collaborative intervention, physiological data of all students were continuously collected to evaluate the overall effectiveness of the collaborative intervention. When the overall attention level of the class is detected to have recovered to or above the preset threshold, the collaborative intervention mode will automatically exit and the normal teaching process will resume.

[0014] 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 based on EEG feedback as described in the first aspect of the present invention.

[0015] 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 control method based on EEG feedback as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By integrating multimodal physiological and behavioral data such as EEG, eye movement, heart rate variability, and facial expressions, a dynamic attention recognition and regulation system based on individual student differences is constructed, realizing a shift in teaching paradigm from uniform instruction to precise intervention. It can not only identify the fine-grained attention state of each student in the English classroom in real time, but also automatically match personalized intervention strategies based on the type of teaching content, and continuously optimize the intervention effect through a closed-loop feedback mechanism. Simultaneously, the class attention heatmap and intelligent teaching decision suggestions generated by the system enhance teachers' ability to perceive the overall cognitive load of the classroom, supporting their rapid implementation of collaborative interventions, thereby effectively extending students' effective focus time, reducing the incidence of cognitive confusion, and improving the efficiency of English classroom teaching and learning participation. Attached Figure Description

[0017] 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.

[0018] Figure 1This is a flowchart of the English classroom attention regulation method based on EEG feedback in Example 1. Detailed Implementation

[0019] 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.

[0020] 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.

[0021] 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.

[0022] Example 1, referring to Figure 1 As one embodiment of the present invention, this embodiment provides a method for regulating attention in an English classroom based on electroencephalogram (EEG) feedback, comprising the following steps: S1. Before class, guide students to complete standardized focus and relaxation tasks, collect EEG, eye movement and heart rate variability data, and establish a personalized attention baseline.

[0023] Furthermore, before class, students are arranged to complete standardized focus tasks and standardized relaxation tasks in sequence; During the execution of standardized focus tasks, EEG signals, eye movement trajectory data, and heart rate variability data are collected simultaneously to form a physiological dataset of focus state. During the standardized relaxation task, brainwave signals, eye movement trajectory data, and heart rate variability data were collected simultaneously to form a physiological dataset of the relaxation state. Frequency domain analysis was performed on the physiological dataset of focused state to extract the average power values ​​of the θ band from 4 Hz to 8 Hz and the average power values ​​of the β band from 13 Hz to 30 Hz. A time-domain analysis was performed on the physiological dataset of focused state to count the number of blinks per unit time, thus obtaining the blink frequency under focused state. The standard deviation of adjacent normal heartbeat intervals was calculated from the heart rate interval sequences in the physiological dataset of focused state to obtain the heart rate variability index under focused state. The frequency and time domain processing procedures of the relaxed physiological dataset were repeated to obtain the average power value of the θ band, the average power value of the β band, the blink rate and the heart rate variability index in the relaxed state, respectively. The eight indicators are combined into an ordered vector, which serves as the student's personalized attention baseline.

[0024] It should be noted that by guiding students to complete standardized focus and relaxation tasks before class and simultaneously collecting multi-dimensional physiological data to construct a personalized attention baseline, the interference of individual physiological differences on subsequent attention judgment can be effectively eliminated, the accuracy and adaptability of attention state recognition can be improved, and a data foundation can be laid for truly individualized instruction.

[0025] S2. Real-time synchronous collection of brainwave signals, facial expressions and eye movement characteristics, and heart rate variability data of all students during English classroom teaching.

[0026] Furthermore, the system synchronously collects EEG signals, facial expressions and eye movement characteristics, and heart rate variability data from all students in real time. The specific steps are as follows: In the classroom environment, each student is equipped with a wearable physiological signal acquisition device, which includes an electroencephalogram (EEG) acquisition module and a heart rate monitoring module. By continuously capturing facial video streams of all students through high-definition infrared cameras deployed at the front of the classroom, the high-definition infrared cameras have low light adaptability, ensuring stable acquisition of facial images under different classroom lighting conditions. The EEG acquisition module continuously records the multi-channel EEG signals of each student at a sampling frequency of no less than 250 Hz, and transmits the signals to the edge computing node in real time via wireless transmission. The heart rate monitoring module continuously measures the heart rate interval sequence of each student using photoplethysmography (PPG) technology and uploads it synchronously to the edge computing node. Real-time frame extraction is performed on the facial video stream output by the high-definition infrared camera, extracting no less than 15 frames per second; In the edge computing node, face detection and key point localization are performed on each frame of image to identify the opening and closing of the eyes, the position of the pupils and the head posture angle. The number of blinks per unit time is statistically analyzed based on the opening and closing state of both eyes, serving as the core indicator of eye movement characteristics; The brainwave signals, blink count, head posture angle, and heartbeat interval sequences are aligned according to a unified timestamp to form a structured multimodal physiological behavior data stream; A sliding window segmentation process is implemented on the multimodal physiological behavior data stream, with a window length of five seconds and a step size of one second, to support the continuous discrimination of subsequent attention states.

[0027] It should be noted that by deploying wearable devices and non-invasive visual acquisition systems in a real classroom environment, low-latency and high-synchronization acquisition of multimodal signals such as EEG, eye movement, facial expressions, and heart rate variability is achieved. This not only ensures the integrity and timeliness of the data but also avoids interference with students' normal learning behavior, ensuring that the entire control process is naturally integrated into the teaching process.

[0028] S3. Based on the personalized attention baseline and the collected multimodal data, perform cross-modal fusion analysis to determine the current attention state category of each student.

[0029] Furthermore, during English classroom teaching, the brainwave signals, facial video streams, and heart rate interval sequences of each student are acquired in real time at a fixed sampling frequency. Bandpass filtering and segmented windowing are applied to the EEG signal to calculate the average power values ​​of the θ and β bands within the current window; Facial key points are detected frame by frame in the facial video stream to identify the opening and closing state of the eyelids and count the number of blinks per unit time. Calculate the standard deviation of adjacent normal heartbeat intervals within the current window for the heart rate interval sequence to obtain the current heart rate variability index; The four real-time indicators were normalized with the personalized attention baseline to eliminate the influence of individual physiological differences. The normalized four-dimensional feature vector is input into the multimodal attention state discrimination model; The multimodal attention state discrimination model employs a gated cross-attention mechanism, expressed as follows: ; in, Represents the EEG feature vector, Represents visual feature vectors. A vector representing the embedded heart rate variability feature scalar; This represents a vector concatenation operation; , , , All are learnable parameter matrices; Use the Sigmoid activation function; This indicates element-wise multiplication; By dynamically adjusting the contribution weights of different modal features through a gating mechanism, a fused feature vector is generated. ; Will Input a fully connected classification layer and output the probability distribution of six attention state categories; The category with the highest probability is selected as the current attention state judgment result; The six categories of attention states include high focus, normal focus, slight inattentiveness, deep inattentiveness, cognitive confusion, and fatigue.

[0030] It should be noted that by normalizing real-time multimodal data based on personalized baselines and introducing a cross-modal fusion discrimination mechanism with dynamic weight allocation capabilities, the system can accurately distinguish subtle changes in attention and effectively identify complex states, including cognitive confusion and fatigue, thereby providing a high-confidence state basis for subsequent interventions.

[0031] S4. Based on the attention state category, individual student characteristics, and current teaching content type, match and execute corresponding personalized intervention measures from the preset intervention strategy library.

[0032] Furthermore, obtain the type identifier of the current teaching content, which is selected from one of four categories: listening training, speaking practice, reading comprehension, or grammar explanation; The corresponding intervention strategy sub-library is invoked based on the type identifier; Retrieve a set of intervention rules that match the current attention state category from the intervention strategy sub-library; Each rule in the intervention rule set consists of two parts: a precondition and a motor instruction. The precondition is composed of the attention state category and the student's historical response record. Select the action command with the highest historical response success rate from the set of matched intervention rules; Action instructions include at least one of the following: The student terminal highlights keywords, plays auxiliary voice prompts, pushes interactive micro-lesson videos, triggers wristband vibration reminders, and generates instant Q&A questions. Send the selected action command to the target student's terminal and record the command execution time and type.

[0033] It should be noted that by combining attention state categories with teaching content types and students' historical response behaviors, the optimal intervention action is intelligently matched from the structured strategy library. This achieves both content adaptability and form diversity of intervention measures, respecting the subject characteristics of English teaching while also taking into account students' individual acceptance preferences, thereby improving the acceptance and effectiveness of the intervention.

[0034] S5. Based on the changes in students' status after the intervention, dynamically assess the effectiveness of the intervention and adjust subsequent intervention strategies to form a closed-loop control.

[0035] Furthermore, an effect evaluation window is launched after the action command is executed, and the window lasts for ten seconds; Continuously monitor changes in the target students' attention status categories within the assessment window; If at least one instance of attention shifting to a higher level of focus occurs within the assessment window, the current intervention is deemed effective. If the attention state category does not shift positively at the end of the assessment window, the current intervention is deemed ineffective. When an intervention is deemed ineffective, a suboptimal action instruction is selected from the same intervention strategy sub-library and re-executed. If two consecutive interventions are ineffective, the student will be marked as requiring manual intervention, and a high-priority prompt message will be generated on the teacher's terminal. At the same time, automatic intervention for the student will be suspended until the teacher confirms the action or the student's condition recovers naturally.

[0036] It should be noted that by setting an assessment window and automatically judging the effectiveness of intervention based on the dynamic evolution of attention status, a closed-loop control logic of execution-monitoring-feedback-optimization is formed. This not only avoids the repeated application of ineffective interventions, but also allows for timely transfer to teachers for intervention when necessary, balancing automation efficiency with educational humanistic care.

[0037] S6. Generate a class attention heatmap based on attention state categories, push teaching decision suggestions to the teacher's terminal in conjunction with the teaching progress, and support teachers to trigger collaborative intervention operations.

[0038] Furthermore, obtain the current attention state category results for all students; The physical seating arrangement in the classroom is mapped to a two-dimensional plane coordinate system, with each student corresponding to a unique coordinate position; Six attention state categories were assigned color codes, with warm colors used for high focus and normal focus, and cool colors used for the other four categories. In a two-dimensional coordinate system, each student's corresponding position is filled with the color corresponding to their current attention state category; The filled image is then smoothed and interpolated to generate a class attention heatmap with continuous color levels. The heat map is displayed in real time on the monitoring interface of the teacher's terminal; Obtain the progress indicators of the current teaching segment, including the introduction stage, the new knowledge explanation stage, the consolidation and practice stage, or the summary and feedback stage; The number of students currently in a state of inattention is counted. Inattention includes four categories: slight inattentiveness, deep inattentiveness, cognitive confusion, and fatigue. The percentage of non-focused students is calculated and denoted as . Set dynamic threshold Dynamic threshold Adjustments will be made based on the progress indicators of the current teaching segment: New knowledge explanation stage The value is relatively low, during the consolidation and practice phase. The value is relatively high; When the condition is met At that time, the system automatically generates teaching decision suggestions; Teaching decision recommendations include at least one of the following: Insert group discussion activities, switch to fun Q&A sessions, slow down the speaking speed to repeat key content, and temporarily divide into groups to implement differentiated teaching; The generated teaching decision suggestions, along with class attention heatmaps, will be used to... Figure 1 And push it to the teacher's terminal; Teachers can choose to adopt suggestions and trigger collaborative interventions, which may include broadcasting prompts to the whole class, initiating group relaxation training, or adjusting the pace of instruction.

[0039] It should be noted that by aggregating individual attentional states into a visual heatmap and combining it with the intelligent generation of actionable teaching decision-making suggestions at each teaching stage, teachers can intuitively grasp the distribution of cognitive load across the entire class and quickly respond to fluctuations in collective attention, thereby improving the overall quality of classroom participation and teaching effectiveness while maintaining the teaching rhythm.

[0040] This embodiment also provides a computer device applicable to the English classroom attention control method based on EEG feedback, 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 realize the English classroom attention control method based on EEG feedback as proposed in the above embodiment.

[0041] 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.

[0042] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the English classroom attention control method based on EEG feedback 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.

[0043] In summary, this invention integrates multimodal physiological and behavioral data, including EEG, eye movement, heart rate variability, and facial expressions, to construct a dynamic attention recognition and regulation system based on individual student differences. This enables a shift in teaching paradigms from uniform instruction to precise intervention. It not only identifies each student's fine-grained attention state in the English classroom in real time but also automatically matches personalized intervention strategies to the type of teaching content, continuously optimizing intervention effects through a closed-loop feedback mechanism. Simultaneously, the system-generated class attention heatmap and intelligent teaching decision suggestions enhance teachers' perception of the overall cognitive load in the classroom, supporting their rapid implementation of collaborative interventions. This effectively prolongs students' effective focus time, reduces the incidence of cognitive confusion, and improves the efficiency of English classroom teaching and learning participation.

[0044] 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 brain wave feedback-based English classroom attention regulation method, characterized in that: include: Before class, students are guided to complete standardized focus and relaxation tasks, and brainwave, eye movement and heart rate variability data are collected to establish a personalized attention baseline. During English classroom teaching, the brainwave signals, facial expressions and eye movement characteristics, as well as heart rate variability data of all students are collected in real time and synchronously. Based on the personalized attention baseline and the collected multimodal data, cross-modal fusion analysis is performed to determine the current attention state category of each student; Based on the attention state category, individual student characteristics, and current teaching content type, match and execute corresponding personalized intervention measures from the preset intervention strategy library; The effectiveness of the intervention is dynamically assessed based on changes in students' status after the intervention is implemented, and subsequent intervention strategies are adjusted to form a closed-loop control. Based on the aforementioned attention state categories, a class attention heatmap is generated. Combined with the teaching progress, teaching decision suggestions are pushed to the teacher's terminal, and teachers are supported in triggering collaborative intervention operations.

2. The brainwave feedback-based English class attention regulation method according to claim 1, characterized in that: The specific steps for establishing a personalized attention baseline are as follows: Before class, students are asked to complete standardized focus tasks and standardized relaxation tasks in sequence. During the execution of standardized focus tasks, EEG signals, eye movement trajectory data, and heart rate variability data are collected simultaneously to form a physiological dataset of focus state. During the standardized relaxation task, brainwave signals, eye movement trajectory data, and heart rate variability data were collected simultaneously to form a physiological dataset of the relaxation state. Frequency domain analysis was performed on the physiological dataset of focused state to extract the average power values ​​of the θ band from 4 Hz to 8 Hz and the average power values ​​of the β band from 13 Hz to 30 Hz. A time-domain analysis was performed on the physiological dataset of focused state to count the number of blinks per unit time, thus obtaining the blink frequency under focused state. The standard deviation of adjacent normal heartbeat intervals was calculated from the heart rate interval sequences in the physiological dataset of focused state to obtain the heart rate variability index under focused state. The frequency and time domain processing procedures of the relaxed physiological dataset were repeated to obtain the average power value of the θ band, the average power value of the β band, the blink rate and the heart rate variability index in the relaxed state, respectively. The eight indicators are combined into an ordered vector, which serves as the student's personalized attention baseline.

3. The brainwave feedback-based English class attention regulation method according to claim 2, characterized in that: The cross-modal fusion analysis determines the current attention state category of each student, and the specific steps are as follows: During English classroom teaching, the brainwave signals, facial video streams, and heart rate interval sequences of each student are acquired in real time at a fixed sampling frequency. Bandpass filtering and segmented windowing are applied to the EEG signal to calculate the average power values ​​of the θ and β bands within the current window; Facial key points are detected frame by frame in the facial video stream to identify the opening and closing state of the eyelids and count the number of blinks per unit time. Calculate the standard deviation of adjacent normal heartbeat intervals within the current window for the heart rate interval sequence to obtain the current heart rate variability index; The four real-time indicators were normalized with the personalized attention baseline to eliminate the influence of individual physiological differences. The normalized four-dimensional feature vector is input into the multimodal attention state discrimination model; The multimodal attention state discrimination model adopts a gated cross-attention mechanism, expressed as: ； wherein, represents a brain electrical feature vector, represents a visual feature vector, represents a vector formed after embedding the heart rate variability feature scalar; represents a vector concatenation operation; , , , are all learnable parameter matrices; is a sigmoid activation function; represents an element-wise multiplication; The contribution weights of different modal features are dynamically adjusted through a gating mechanism to generate a fusion feature vector ; will be described below. input a fully connected classification layer, output a probability distribution of six attention state categories; The category with the highest probability is selected as the current attention state judgment result; The six categories of attention states include high focus, normal focus, slight inattentiveness, deep inattentiveness, cognitive confusion, and fatigue.

4. The brainwave feedback-based English class attention regulation method according to claim 3, characterized in that: The specific steps for matching and implementing corresponding personalized intervention measures based on attention state category, individual student characteristics, and current teaching content type are as follows: Obtain the type identifier of the current teaching content, wherein the type identifier is selected from one of four categories: listening training, speaking practice, reading comprehension, or grammar explanation; The corresponding intervention strategy sub-library is invoked based on the type identifier; Retrieve a set of intervention rules that match the current attention state category from the intervention strategy sub-library; Each rule in the intervention rule set consists of two parts: a precondition and an action instruction. The precondition is composed of the attention state category and the student's historical response record. Select the action command with the highest historical response success rate from the set of matched intervention rules; The action command includes at least one of the following: The student terminal highlights keywords, plays auxiliary voice prompts, pushes interactive micro-lesson videos, triggers wristband vibration reminders, and generates instant Q&A questions. Send the selected action command to the target student's terminal and record the command execution time and type.

5. The brainwave feedback-based English class attention regulation method according to claim 4, characterized in that: The specific steps for dynamically evaluating the intervention effect and adjusting subsequent intervention strategies based on changes in students' states after the intervention are as follows: The effect evaluation window is launched after the action command is executed, and the window lasts for ten seconds; Continuously monitor changes in the target students' attention status categories within the assessment window; If at least one instance of attention shifting to a higher level of focus occurs within the assessment window, the current intervention is deemed effective. If the attention state category does not shift positively at the end of the assessment window, the current intervention is deemed ineffective. When an intervention is deemed ineffective, a suboptimal action instruction is selected from the same intervention strategy sub-library and re-executed. If two consecutive interventions are ineffective, the student will be marked as requiring manual intervention, and a high-priority prompt message will be generated on the teacher's terminal. At the same time, automatic intervention for the student will be suspended until the teacher confirms the action or the student's condition recovers naturally.

6. The brainwave feedback-based English class attention regulation method according to claim 5, characterized in that: The specific steps for generating the class attention heatmap through aggregation are as follows: Obtain the current attention state category results for all students; The physical seating arrangement in the classroom is mapped to a two-dimensional plane coordinate system, with each student corresponding to a unique coordinate position; Six attention state categories were assigned color codes, with warm colors used for high focus and normal focus, and cool colors used for the other four categories. In a two-dimensional coordinate system, each student's corresponding position is filled with the color corresponding to their current attention state category; The filled image is then smoothed and interpolated to generate a class attention heatmap with continuous color levels. The heat map is displayed in real time on the monitoring interface of the teacher's terminal.

7. The brainwave feedback-based English class attention regulation method according to claim 6, characterized in that: The specific steps for pushing teaching decision suggestions to teachers' terminals in conjunction with the teaching progress are as follows: Obtain the progress indicator of the current teaching segment, which includes the introduction stage, the new knowledge explanation stage, the consolidation and practice stage, or the summary and feedback stage; The number of students currently in a state of inattention is counted. This state of inattention includes four categories: slight distraction, deep distraction, cognitive confusion, and fatigue. The percentage of non-focused students is calculated and denoted as . Set dynamic threshold The dynamic threshold Adjustments will be made based on the progress indicators of the current teaching segment: New knowledge explanation stage The value is relatively low, during the consolidation and practice phase. The value is relatively high; When the condition is met At that time, the system automatically generates teaching decision suggestions; The teaching decision suggestions include at least one of the following: Insert group discussion activities, switch to a fun quiz session, slow down the speaking speed to repeat key content, or conduct temporary grouping for differentiated teaching; Push the generated teaching decision suggestions together with the class attention heat map to the teacher terminal; The teacher can choose to adopt the suggestions and trigger collaborative intervention operations, which include broadcasting a reminder sound to the whole class, starting a collective relaxation training, or adjusting the teaching rhythm.

8. The English classroom attention regulation method based on EEG feedback as described in claim 7, characterized in that: After the teacher triggers the collaborative intervention operation, the system executes a whole-class linkage response mechanism, and the specific steps are as follows: Receive the collaborative intervention instruction sent by the teacher terminal, and the collaborative intervention instruction includes one of the three categories: collective reminder, rhythm reset, or grouping switch; If the collaborative intervention instruction is a collective reminder, synchronously play a preset voice reminder to all student terminals, and highlight the current teaching keywords on the main display screen of the classroom; If the collaborative intervention instruction is a rhythm reset, automatically pause the playback of the current teaching content, insert a 30-second breathing regulation guidance audio, and at the same time close the input functions of all student terminals to force a short silent state; If the collaborative intervention instruction is a grouping switch, re-divide the learning groups according to the current attention state category and historical learning performance of each student; The re-dividing of the learning groups adopts an optimized clustering strategy, and the objective function is to minimize the variance of the attention state within the group and maximize the complementarity of cognitive abilities between groups; Push the newly generated group assignment results to the teacher terminal for confirmation, and synchronously update the collaborative interface of the student terminals; During the execution of the collaborative intervention, continuously collect the physiological data of all students to evaluate the overall effectiveness of the collaborative intervention; When it is detected that the overall attention level of the class has recovered above the preset threshold, automatically exit the collaborative intervention mode and resume the normal teaching process.

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 based on brain wave feedback according to 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 English classroom attention regulation method based on brain wave feedback according to any one of claims 1 to 7.

Images