An intelligent classroom participation monitoring and teaching adjustment system

Abstract

The application discloses an intelligent classroom participation monitoring and teaching adjustment system, which comprises a monitoring camera and an analysis host. The monitoring camera is deployed in each corner of the classroom to capture the behaviors and expressions of teachers and students in real time. The camera has high resolution and wide-angle view, which can avoid blind area coverage. The analysis host is installed on the classroom podium, which is built-in with high-performance processors and special analysis software to process the data transmitted by the camera. The display screen is installed on the front side of the analysis host to display real-time participation data and teaching adjustment suggestions; the prompt loudspeaker is installed on the upper end to remind the teacher to pay attention to the participation change. The monitoring camera is connected with the controller, which uses advanced face recognition and emotion analysis algorithms to evaluate the participation of students in real time. The application realizes real-time monitoring and dynamic adjustment of classroom participation, has the advantages of simple working principle, high intelligent degree, remarkable implementation effect and the like, and can effectively improve the classroom teaching quality and student learning efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent classroom technology, specifically to an intelligent classroom participation monitoring and teaching adjustment system. Background Technology

[0002] The intelligent teaching system integrates the teaching resources and research results of frontline teachers and teaching experts across the country through internet-based computer simulation technology. It then conducts scientific analysis, intelligent judgment, and provides timely, effective, comprehensive, and targeted teaching.

[0003] Intelligent teaching systems can intelligently identify and eliminate blind spots in learning and teaching that are not easily noticed by students and teachers. This can reduce students' learning burden, improve teachers' teaching efficiency, and ultimately improve students' academic performance.

[0004] In traditional higher education classroom settings, teachers often employ a single teaching method (such as lecturing) for extended periods, which can lead to student distraction and poor learning outcomes. Currently, there is a lack of effective means to monitor student participation and teaching methods in real time, and to provide real-time feedback to teachers for adjustments when necessary. Therefore, it is necessary to design an intelligent classroom participation monitoring and teaching adjustment system. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent classroom participation monitoring and teaching adjustment system to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent classroom participation monitoring and teaching adjustment system, comprising a monitoring camera and an analysis host. The monitoring camera is deployed in various corners of the classroom to capture the behavior and expressions of teachers and students in real time. The analysis host is installed on the classroom podium, with a display screen installed on the front side of the analysis host and a notification speaker installed on the upper part of the analysis host. A controller is installed inside the analysis host, and the monitoring camera is connected to the controller.

[0007] The surveillance camera is connected to the emotion and behavior data acquisition layer, which is connected to the processing and analysis layer, the processing and analysis layer, the display and interaction layer, and the security control layer. The emotion and behavior data acquisition layer includes a storage unit and a storage backup unit. The processing and analysis layer includes an algorithm learning module, an emotion and behavior prediction module, and an early warning module. The display and interaction layer includes an analysis result presentation unit and an early warning reminder unit. The security control layer includes a storage encryption unit, an access authorization unit, and a transmission encryption unit.

[0008] Preferably, this application provides an intelligent classroom participation monitoring and teaching adjustment system, wherein the controller is equipped with a processor module, a video image acquisition unit, a video image processing unit, a behavior analysis unit, and a teaching adjustment prompting unit. The input end of the video image acquisition unit is connected to a monitoring camera, and the output end of the video image acquisition unit is connected to the processor module through the video image processing unit. The behavior analysis unit and the teaching adjustment prompting unit are respectively connected to the processor module. The video image acquisition unit is used to acquire classroom videos and facial expression images of teachers and students. The video image processing unit is used to filter and reduce noise in the acquired video images. The behavior analysis unit analyzes the data collected from the monitoring camera and uses machine learning algorithms to evaluate student participation. The teaching adjustment prompting unit is used to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

[0009] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application further includes a signal transmission unit, wherein the processor unit module is connected to the back-end server terminal through the signal transmission unit.

[0010] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application further includes a learning behavior analysis server and a learning behavior data acquisition server, wherein the learning behavior analysis server and the learning behavior data acquisition server are respectively connected to the processor module.

[0011] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application includes a Zigbee communication module as the signal transmission unit. The Zigbee communication module includes a Zigbee module and a WIFI module. The Zigbee module is connected to a first clock module, a WIFI module, and a power management module. The power management module is connected to the WIFI module and a power interface. The WIFI module is also connected to a storage module and a second clock module. The Zigbee module and the WIFI module are also connected to an antenna interface.

[0012] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application includes a behavior analysis unit consisting of a SIMAM module. The SIMAM module enhances the accuracy and stability of student classroom behavior detection. The specific implementation process of the SIMAM module can be divided into the following steps: First, the input feature map is assumed to be...

[0013]

[0014] Where C is the number of channels, and H and W are the height and width of the feature map, respectively; then, global mean pooling is performed on the input feature map X to obtain channel-level global features. Next, the feature importance of each spatial location is calculated by comparing each spatial location in the feature map (X) with the global feature X. gp The difference S = |XX gp |, among which The spatial information map S is represented; then, it is normalized to ensure that its values ​​are within a reasonable range. Where ∈ is a very small number to prevent division by zero; next, the attention weights are calculated using the normalized spatial information graph S. Where σ represents the Sigmoid function. This is the final attention weight map; finally, the attention weight A is applied to the original feature map X to obtain the final weighted feature map Y = X⊙A, where ⊙ represents element-level multiplication.

[0015]

[0016] This is the final weighted feature map. Through the above steps, SIMAM enhances the focus on key regions based on the original feature map, suppresses interference from background and irrelevant regions, and more accurately captures important behavioral features, thereby improving the accuracy and stability of the detection task.

[0017] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application includes the following steps in its usage:

[0018] A. Surveillance cameras deployed in various corners of the classroom capture real-time video images of the behavior and expressions of teachers and students;

[0019] B. The acquired video image signal is transmitted to the video image processing unit for noise reduction and filtering.

[0020] C. The processed video images are transmitted to the processor module, which triggers the behavior analysis unit to analyze the data collected from the surveillance camera and use machine learning algorithms to evaluate student participation.

[0021] D. The teaching adjustment prompt unit is used by the system to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

[0022] Preferably, the intelligent classroom participation monitoring and teaching adjustment system provided in this application includes a video image processing unit that processes data as follows:

[0023] a. Input the acquired image data into the template generation module, and use a 1×7 neighborhood template to process the row data of the image, processing the odd-numbered row image data and the even-numbered row image data respectively;

[0024] b. The median filtering module performs median filtering on the 7 rows of original image data and noise variance generated by the template generation module, calculates the median of the original image data under four step sizes of 1, 1×2, 3×4, and 5×6, and the corresponding median noise variance, and outputs the results to the data analysis selection module.

[0025] c. Calculate the range of the image signal at each step size based on the image data and the corresponding noise variance at different step sizes, and select the optimal step size based on this range;

[0026] d. Finally, output the denoised video image.

[0027] Preferably, in the intelligent classroom participation monitoring and teaching adjustment system provided in this application, step D specifically comprises:

[0028] a. Teachers conduct multi-dimensional learning behavior analysis and visualization of student learning behavior data;

[0029] b. The learning behavior analysis server classifies each student terminal into several categories, such as high motivation / low motivation and effective learning / inefficient learning, based on the various behavioral data generated by each student terminal accessing the teaching resource server, knowledge point test server, and Q&A interaction server collected by the learning behavior data collection server. Teachers dynamically adjust teaching content and carry out personalized teaching design for students based on the student learning behavior analysis results output by the learning behavior analysis server.

[0030] c. Teachers publish knowledge review quizzes to the knowledge point testing server through their teacher terminals, and students complete the tests by accessing the knowledge point testing server through their student terminals. This is used to assess the effectiveness of classroom teaching. The learning behavior data collection server further collects student behavior data for the purpose of evaluating and improving teaching effectiveness.

[0031] Compared with the prior art, the beneficial effects of the present invention are:

[0032] (1) This invention has a simple working principle and a high degree of intelligence. When low participation is detected, it can automatically remind teachers to adjust their teaching strategies through the display screen and speaker, such as introducing group discussions and interactive Q&A activities. The teacher interface provides intuitive participation data and visualization, helping teachers understand the classroom dynamics in real time and make corresponding adjustments. The system also includes security measures such as data encryption and access control to ensure the privacy of teachers and students and data security. This invention integrates intelligent cameras and analysis software to realize real-time monitoring and dynamic adjustment of classroom participation. It has the advantages of simple working principle, high degree of intelligence, and significant implementation effect, and can effectively improve the quality of classroom teaching and students' learning efficiency.

[0033] (2) This invention has a real-time feedback function, which allows teachers to obtain feedback on student participation in an instant and adjust their teaching strategies accordingly.

[0034] (3) This invention enhances learning effectiveness by continuously optimizing teaching methods and classroom activities to improve students' learning efficiency and results.

[0035] (4) The present invention has an adaptive teaching effect. The system supports teachers to flexibly adjust the teaching plan according to the actual classroom situation to meet the learning needs of different students. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the structure of the present invention;

[0037] Figure 2 This is a system architecture diagram of the present invention;

[0038] Figure 3 This is a block diagram illustrating the working principle of the present invention;

[0039] Figure 4 This is a block diagram of the signal transmission unit of the present invention;

[0040] Figure 5 This is a flowchart of the workflow of the present invention;

[0041] In the diagram: 1. Surveillance camera; 2. Analysis host; 3. Display screen; 4. Alarm speaker; 5. Processor module; 6. Video image acquisition unit; 7. Video image processing unit; 8. Behavior analysis unit; 9. Teaching adjustment prompt unit; 10. Signal transmission unit; 11. Backend server terminal; 12. Zigbee module; 13. WIFI module; 14. First clock module; 15. Power management module; 16. Power interface; 17. Storage module; 18. Second clock module; 19. Antenna interface; 20. Learning behavior analysis server; 21. Learning behavior data acquisition server; 22. Emotion and behavior data acquisition layer; 23. Processing and analysis layer; 24. Display and interaction layer; 25. Security control layer; 26. Storage unit; 27. Storage backup unit; 28. Algorithm learning module; 29. ​​Emotion and behavior prediction module; 30. Early warning module; 31. Analysis result presentation unit; 32. Early warning reminder unit; 33. Storage encryption unit; 34. Access authorization unit; 35. Transmission encryption unit. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly set on the other component; when a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to the other component.

[0044] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0045] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" or "several" means two or more, unless otherwise explicitly specified.

[0046] It should be understood that the structures, proportions, sizes, etc., illustrated in the accompanying drawings are merely for illustrative purposes to aid those skilled in the art and are not intended to limit the scope of this application. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effectiveness or purpose of this application, should still fall within the scope of the technical content disclosed in this application. Furthermore, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are merely for clarity and are not intended to limit the scope of this application. Changes or adjustments to their relative relationships, without substantially altering the technical content, should also be considered within the scope of this application.

[0047] Please see Figure 1-5 The present invention provides a technical solution: an intelligent classroom participation monitoring and teaching adjustment system, including a monitoring camera 1 and an analysis host 2. The monitoring camera 1 is deployed in various corners of the classroom to capture the behavior and expressions of teachers and students in real time. The analysis host 2 is installed on the classroom podium. A display screen 3 is installed on the front of the analysis host 2. A notification speaker 4 is installed on the upper part of the analysis host 2. A controller is installed inside the analysis host 2. The monitoring camera 1 is connected to the controller.

[0048] The surveillance camera 1 is connected to the emotion and behavior data acquisition layer 22, which is connected to the processing and analysis layer 23, which is connected to the display and interaction layer 24, and the display and interaction layer 24 is connected to the security control layer 25. The emotion and behavior data acquisition layer 22 includes a storage unit 26 and a storage backup unit 27. The processing and analysis layer 23 includes an algorithm learning module 28, an emotion and behavior prediction module 29, and an early warning module 30. The display and interaction layer 24 includes an analysis result presentation unit 31 and an early warning reminder unit 32. The security control layer 25 includes a storage encryption unit 33, an access authorization unit 34, and a transmission encryption unit 35.

[0049] In this invention, the controller is equipped with a processor module 5, a video image acquisition unit 6, a video image processing unit 7, a behavior analysis unit 8, and a teaching adjustment prompting unit 9. The input end of the video image acquisition unit 6 is connected to a monitoring camera 1, and the output end of the video image acquisition unit 6 is connected to the processor module 5 through the video image processing unit 7. The behavior analysis unit 8 and the teaching adjustment prompting unit 9 are respectively connected to the processor module 5. The video image acquisition unit is used to acquire classroom videos and facial expressions of teachers and students. The video image processing unit is used to filter and reduce noise in the acquired video images. The behavior analysis unit analyzes the data collected from the monitoring camera and uses machine learning algorithms to evaluate student participation. The teaching adjustment prompting unit is used to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

[0050] The invention also includes a signal transmission unit 10, through which the processor module 5 is connected to the backend server terminal 11. The signal transmission unit 10 employs a Zigbee communication module, which includes a Zigbee module 12 and a WIFI module 13. The Zigbee module 12 is connected to a first clock module 14, the WIFI module 13, and a power management module 15. The power management module 15 is connected to the WIFI module 13 and a power interface 16. The WIFI module 13 is also connected to a storage module 17 and a second clock module 18. The Zigbee module 12 and the WIFI module 13 are also connected to an antenna interface 19. The Zigbee communication module used in the signal transmission unit of this invention is compatible with both WIFI and Zigbee modules, achieving a fusion connection between the WIFI and Zigbee modules, further improving the efficiency of backend monitoring. The invention also includes a learning behavior analysis server 20 and a learning behavior data acquisition server 21, which are respectively connected to the processor module 5.

[0051] In this invention, the behavior analysis unit 8 is equipped with a SIMAM module. The SIMAM module enhances the accuracy and stability of student classroom behavior detection. The specific implementation process of the SIMAM module can be divided into the following steps: First, the input feature map is assumed to be...

[0052]

[0053] Where C is the number of channels, and H and W are the height and width of the feature map, respectively; then, global mean pooling is performed on the input feature map X to obtain the channel-level global features. Next, the feature importance of each spatial location is calculated by comparing each spatial location in the feature map (X) with the global feature X.gp The difference S = |XX gp |, among which The spatial information map S is represented; then, it is normalized to ensure that its values ​​are within a reasonable range. Where ∈ is a very small number to prevent division by zero; next, the attention weights are calculated using the normalized spatial information graph S. Where σ represents the Sigmoid function. This is the final attention weight map; finally, the attention weight A is applied to the original feature map X to obtain the final weighted feature map Y = X⊙A, where ⊙ represents element-level multiplication.

[0054]

[0055] This is the final weighted feature map. Through the above steps, SIMAM enhances the focus on key regions based on the original feature map, suppresses interference from background and irrelevant regions, and more accurately captures important behavioral features, thereby improving the accuracy and stability of the detection task.

[0056] Working principle: The method of using this invention includes the following steps:

[0057] A. Surveillance cameras deployed in various corners of the classroom capture real-time video images of the behavior and expressions of teachers and students;

[0058] B. The acquired video image signal is transmitted to the video image processing unit for noise reduction and filtering.

[0059] C. The processed video images are transmitted to the processor module, which triggers the behavior analysis unit to analyze the data collected from the surveillance camera and use machine learning algorithms to evaluate student participation.

[0060] D. The teaching adjustment prompt unit is used by the system to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

[0061] The video image processing unit processes images as follows:

[0062] a. Input the acquired image data into the template generation module, and use a 1×7 neighborhood template to process the row data of the image, processing the odd-numbered row image data and the even-numbered row image data respectively;

[0063] b. The median filtering module performs median filtering on the 7 rows of original image data and noise variance generated by the template generation module, calculates the median of the original image data under four step sizes of 1, 1×2, 3×4, and 5×6, and the corresponding median noise variance, and outputs the results to the data analysis selection module.

[0064] c. Calculate the range of the image signal at each step size based on the image data and the corresponding noise variance at different step sizes, and select the optimal step size based on this range;

[0065] d. Finally, output the denoised video image.

[0066] The video image processing unit method used in this invention can reduce noise in the original image data, and has the characteristics of low implementation complexity and good noise reduction performance, thereby further improving the clarity of video images.

[0067] Furthermore, in this invention, step D specifically includes:

[0068] a. Teachers conduct multi-dimensional learning behavior analysis and visualization of student learning behavior data;

[0069] b. The learning behavior analysis server classifies each student terminal into several categories, such as high motivation / low motivation and effective learning / inefficient learning, based on the various behavioral data generated by each student terminal accessing the teaching resource server, knowledge point test server, and Q&A interaction server collected by the learning behavior data collection server. Teachers dynamically adjust teaching content and carry out personalized teaching design for students based on the student learning behavior analysis results output by the learning behavior analysis server.

[0070] c. Teachers publish knowledge review quizzes to the knowledge point testing server through their teacher terminals, and students complete the tests by accessing the knowledge point testing server through their student terminals. This is used to assess the effectiveness of classroom teaching. The learning behavior data collection server further collects student behavior data for the purpose of evaluating and improving teaching effectiveness.

[0071] This invention provides real-time feedback, allowing teachers to receive immediate feedback on student engagement and adjust their teaching strategies accordingly.

[0072] This invention enhances learning outcomes by continuously optimizing teaching methods and classroom activities to improve students' learning efficiency and effectiveness.

[0073] This invention provides an adaptive teaching effect, allowing teachers to flexibly adjust their teaching plans based on actual classroom conditions to meet the learning needs of different students.

[0074] In summary, this invention features a simple working principle and a high degree of intelligence. By integrating intelligent cameras and analysis software, it monitors the behavior of teachers and students in the classroom and assesses student engagement in real time. When low engagement is detected, the system can automatically remind teachers to adjust their teaching strategies, such as changing teaching methods or introducing different teaching activities, to enhance student participation and learning efficiency.

[0075] The circuits, electronic components, and modules involved are all existing technologies, which can be fully implemented by those skilled in the art, and need not be elaborated upon. The scope of protection of this invention does not involve any improvement to the software and methods.

[0076] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A smart classroom participation monitoring and teaching adjustment system, comprising a monitoring camera (1) and an analysis host (2), characterized in that: The surveillance camera (1) is deployed in various corners of the classroom to capture the behavior and expressions of teachers and students in real time. The analysis host (2) is installed on the classroom podium. The analysis host (2) has a display screen (3) installed on the front side. The analysis host (2) has a notification speaker (4) installed on the upper part. The analysis host (2) has a controller installed inside. The surveillance camera (1) is connected to the controller. The surveillance camera (1) is connected to the emotion and behavior data acquisition layer (22), which is connected to the processing and analysis layer (23), which is connected to the display and interaction layer (24), and which is connected to the security control layer (25). The emotion and behavior data acquisition layer (22) is equipped with a storage unit (26) and a storage backup unit (27). The processing and analysis layer (23) is equipped with an algorithm learning module (28), an emotion and behavior prediction module (29), and an early warning module (30). The display and interaction layer (24) is equipped with an analysis result presentation unit (31) and an early warning reminder unit (32). The security control layer (25) is equipped with a storage encryption unit (33), an access authorization unit (34), and a transmission encryption unit (35).

2. The intelligent classroom participation monitoring and teaching adjustment system according to claim 1, characterized in that: The controller is equipped with a processor module (5), a video image acquisition unit (6), a video image processing unit (7), a behavior analysis unit (8), and a teaching adjustment prompt unit (9). The input end of the video image acquisition unit (6) is connected to the monitoring camera (1), and the output end of the video image acquisition unit (6) is connected to the processor module (5) through the video image processing unit (7). The behavior analysis unit (8) and the teaching adjustment prompt unit (9) are respectively connected to the processor module (5). The video image acquisition unit is used to acquire class videos and facial expression images of teachers and students. The video image processing unit is used to filter and reduce noise in the acquired video images. The behavior analysis unit analyzes the data collected from the monitoring camera and uses machine learning algorithms to evaluate student participation. The teaching adjustment prompt unit is used to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

3. The intelligent classroom participation monitoring and teaching adjustment system according to claim 1, characterized in that: It also includes a signal transmission unit (10), through which the processor module (5) is connected to the back-end server terminal (11).

4. The intelligent classroom participation monitoring and teaching adjustment system according to claim 1, characterized in that: It also includes a learning behavior analysis server (20) and a learning behavior data acquisition server (21), which are respectively connected to the processor module (5).

5. The intelligent classroom participation monitoring and teaching adjustment system according to claim 3, characterized in that: The signal transmission unit (10) adopts a Zigbee communication module, which includes a Zigbee module (12) and a WIFI module (13). The Zigbee module (12) is connected to the first clock module (14), the WIFI module (13) and the power management module (15), respectively. The power management module (15) is connected to the WIFI module (13) and the power interface (16), respectively. The WIFI module (13) is also connected to the storage module (17) and the second clock module (18), respectively. The Zigbee module (12) and the WIFI module (13) are also connected to the antenna interface (19), respectively.

6. The intelligent classroom participation monitoring and teaching adjustment system according to claim 2, characterized in that: The behavior analysis unit (8) is equipped with a SIMAM module, which enhances the accuracy and stability of student classroom behavior detection. The specific implementation process of the SIMAM module can be divided into the following steps: First, the input feature map is assumed to be... Where C is the number of channels, and H and W are the height and width of the feature map, respectively; then, global mean pooling is performed on the input feature map X to obtain channel-level global features. Next, the feature importance of each spatial location is calculated by comparing each spatial location in the feature map (X) with the global feature X. gp The difference S = |XX gp |, among which The spatial information map S is represented; then, it is normalized to ensure that its values ​​are within a reasonable range. Where ∈ is a very small number to prevent division by zero; next, the attention weights are calculated using the normalized spatial information graph S. Where σ represents the Sigmoid function. This is the final attention weight map; finally, the attention weight A is applied to the original feature map X to obtain the final weighted feature map Y = X⊙A, where ⊙ represents element-level multiplication. This is the final weighted feature map. Through the above steps, SIMAM enhances the focus on key regions based on the original feature map, suppresses interference from background and irrelevant regions, and more accurately captures important behavioral features, thereby improving the accuracy and stability of the detection task.

7. A method for using the intelligent classroom participation monitoring and teaching adjustment system as described in claim 1, characterized in that: Its usage includes the following steps: A. Surveillance cameras deployed in various corners of the classroom capture real-time video images of the behavior and expressions of teachers and students; B. The acquired video image signal is transmitted to the video image processing unit for noise reduction and filtering. C. The processed video images are transmitted to the processor module, which triggers the behavior analysis unit to analyze the data collected from the surveillance camera and use machine learning algorithms to evaluate student participation. D. The teaching adjustment prompt unit is used by the system to automatically send teaching adjustment reminders to teachers based on the analysis results, including changing teaching activities, adopting different teaching methods, or conducting classroom interaction.

8. The method of using the intelligent classroom participation monitoring and teaching adjustment system according to claim 6, characterized in that: The video image processing unit processes the image as follows: a. Input the acquired image data into the template generation module, and use a 1×7 neighborhood template to process the row data of the image, processing the odd-numbered row image data and the even-numbered row image data respectively; b. The median filtering module performs median filtering on the 7 rows of original image data and noise variance generated by the template generation module, calculates the median of the original image data under four step sizes of 1, 1×2, 3×4, and 5×6, and the corresponding median noise variance, and outputs the results to the data analysis selection module. c. Calculate the range of the image signal at each step size based on the image data and the corresponding noise variance at different step sizes, and select the optimal step size based on this range; d. Finally, output the denoised video image.

9. The method of using the intelligent classroom participation monitoring and teaching adjustment system according to claim 6, characterized in that: Step D specifically involves: a. Teachers conduct multi-dimensional learning behavior analysis and visualization of student learning behavior data; b. The learning behavior analysis server classifies each student terminal into several categories, such as high motivation / low motivation and effective learning / inefficient learning, based on the various behavioral data generated by each student terminal accessing the teaching resource server, knowledge point test server, and Q&A interaction server collected by the learning behavior data collection server. Teachers dynamically adjust teaching content and carry out personalized teaching design for students based on the student learning behavior analysis results output by the learning behavior analysis server. c. Teachers publish knowledge review quizzes to the knowledge point testing server through their teacher terminals, and students complete the tests by accessing the knowledge point testing server through their student terminals. This is used to assess the effectiveness of classroom teaching. The learning behavior data collection server further collects student behavior data for the purpose of evaluating and improving teaching effectiveness.

Images