Method and device for assisting student in online class by behavior recognition

Abstract

The application discloses a behavior recognition method for assisting students in online classes. First, the head action signal of the student is acquired, wherein the head action signal of the student comprises the phase of the RFID electronic tag and the received signal strength indication; then, a trained action recognition model is constructed, and the head action signal of the student is input into the action recognition model so as to output the corresponding head action; finally, the output head action is analyzed according to the preset application scenario so as to execute the corresponding operation; thus, the head action signal of the student is recognized through RFID, and the corresponding operation is executed according to the head action in multiple application scenarios, so that the online class efficiency is improved while reducing the disclosure of the privacy of the student.

Description

Technical Field

[0001] This invention relates to the field of online teaching technology, and in particular to a behavior recognition method for assisting students in online classes, a computer-readable storage medium, a computer device, and a behavior recognition device for assisting students in online classes. Background Technology

[0002] Among related technologies, online teaching cannot guarantee students' efficient learning, such as doing other things while online classes are running, myopia or worsening of myopia due to close-range use of electronic products, and insufficient classroom interaction. Current solutions generally involve video surveillance and random roll call. However, video surveillance has the potential to infringe on students' portrait rights by overusing their images, and it may also make students feel monitored, leading to aversion to learning. Random roll call cannot ensure that students are paying attention throughout the class and cannot help students learn effectively through online classes. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in the aforementioned technologies. Therefore, one objective of this invention is to propose a behavior recognition method to assist students in online classes. This method uses RFID to identify students' head movement signals, enabling the execution of corresponding operations in multiple application scenarios based on these head movements. This reduces the exposure of student privacy while improving the efficiency of online classes.

[0004] A second objective of this invention is to provide a computer-readable storage medium.

[0005] The third objective of this invention is to provide a computer device.

[0006] The fourth objective of this invention is to provide a behavior recognition device to assist students in online classes.

[0007] To achieve the above objectives, a first aspect of the present invention proposes a behavior recognition method to assist students in online classes, comprising: acquiring student head movement signals, wherein the student's head movement signals include the phase of an RFID electronic tag and a received signal strength indication; constructing a trained action recognition model and inputting the student's head movement signals into the action recognition model to output corresponding head movements; and parsing the output head movements according to a preset application scenario to perform corresponding operations.

[0008] According to an embodiment of the present invention, a behavior recognition method for assisting students in online classes first acquires the student's head movement signal, wherein the student's head movement signal includes the phase of the RFID electronic tag and the received signal strength indication; then, a trained action recognition model is constructed, and the student's head movement signal is input into the action recognition model to output the corresponding head movement; finally, the output head movement is parsed according to a preset application scenario to execute the corresponding operation; thus, by recognizing the student's head movement signal through RFID, corresponding operations can be executed in multiple application scenarios based on the head movement, thereby reducing the exposure of student privacy while improving the efficiency of online classes.

[0009] In addition, the behavior recognition method for assisting students in online classes proposed in the above embodiments of the present invention may also have the following additional technical features:

[0010] Optionally, acquiring the student's head movement signal includes: placing an RFID electronic tag on the student's head and placing an RFID reader around the student so that the RFID reader can receive the head movement signal returned by the RFID electronic tag in real time.

[0011] Optionally, after acquiring the student's head movement signal, the head movement signal is preprocessed using nearest neighbor filling and Gaussian filtering.

[0012] Optionally, inputting the student's head movement signal into the action recognition model to output the corresponding head movement includes: inputting the student's head movement signal continuously collected within a preset time period into the action recognition model to determine whether the number of times the student's head movement signal continuously collected within the preset time period meets the preset condition reaches a preset threshold. If so, it is determined that the student's head has moved, and the corresponding head movement is output. The head movement includes tilting forward, tilting backward, shaking the head to the left, and shaking the head to the right.

[0013] Optionally, the phase of the RFID electronic tag in the student's head movement signal continuously collected within a preset time period is b{b1, b2, ..., b}. n The received signal strength indication is c{c1, c2, ..., c}. n The preset condition that is satisfied is |b i -b i-1 |≥d and|c i -c i-1 |≥1, where n represents the number of phase or signal strength indications of RFID electronic tags received within a preset time period, b i c represents the phase of the i-th RFID tag. i b represents the i-th signal strength indicator. i-1c represents the phase of the (i-1)th RFID tag. i This indicates the (i-1)th signal strength indication, and d represents the phase difference threshold.

[0014] Optionally, the output head movements are parsed according to a preset application scenario to execute corresponding operations, including: determining the type of the preset application scenario, wherein the preset application scenario includes myopia, listening, and answering; if the preset application scenario is myopia, then the head movements are used to determine whether the head is too close to the screen, and if so, a warning is issued; if the preset application scenario is listening, then the head movements are used to determine whether the student is listening attentively, and if not, a warning is issued; if the preset application scenario is answering, then the head movements are converted into corresponding answer responses, so that the answer responses are scored according to pre-set accurate answers to obtain the student's answer performance.

[0015] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium storing a behavior recognition program for assisting students in online classes. When executed by a processor, the behavior recognition program for assisting students in online classes implements the behavior recognition method for assisting students in online classes as described above.

[0016] According to an embodiment of the present invention, a computer-readable storage medium stores a behavior recognition program for assisting students in online classes, so that when the processor executes the behavior recognition program for assisting students in online classes, it implements the behavior recognition method for assisting students in online classes as described above. Thus, by recognizing students' head movement signals through RFID, corresponding operations can be performed in multiple application scenarios based on the head movements, thereby reducing the exposure of students' privacy while improving the efficiency of online classes.

[0017] To achieve the above objectives, a third aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the behavior recognition method for assisting students in online classes as described above.

[0018] According to the computer device of the present invention, a behavior recognition program for assisting students in online classes is stored in a memory, so that when the processor executes the behavior recognition program for assisting students in online classes, the behavior recognition method for assisting students in online classes described above is implemented. Thus, by recognizing the student's head movement signal through RFID, corresponding operations can be performed in multiple application scenarios based on the head movement, thereby reducing the exposure of student privacy while improving the efficiency of online classes.

[0019] To achieve the above objectives, a fourth aspect of the present invention provides a behavior recognition device to assist students in online classes, comprising an acquisition module for acquiring student head movement signals, wherein the student's head movement signals include the phase of an RFID electronic tag and a received signal strength indication; a behavior recognition module for constructing a trained action recognition model and inputting the student's head movement signals into the action recognition model to output corresponding head movements; and a judgment and processing module for parsing the output head movements according to a preset application scenario to execute corresponding operations.

[0020] According to an embodiment of the present invention, a behavior recognition device for assisting students in online classes acquires students' head movement signals through an acquisition module. These head movement signals include the phase of an RFID tag and the received signal strength indication. A trained action recognition model is constructed through the behavior recognition module, and the students' head movement signals are input into the model to output corresponding head movements. A judgment and processing module analyzes the output head movements according to a preset application scenario to execute corresponding operations. Thus, by recognizing students' head movement signals using RFID, corresponding operations can be executed in multiple application scenarios based on the head movements, thereby reducing the exposure of student privacy while improving the efficiency of online classes. Attached Figure Description

[0021] Figure 1 A flowchart illustrating a behavior recognition method for assisting students in online classes according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart illustrating a process for supervising students' attentive listening in class, according to an embodiment of the present invention.

[0023] Figure 3 A schematic diagram illustrating a process for prompting students to prevent myopia according to an embodiment of the present invention;

[0024] Figure 4 This is a flowchart illustrating a process to facilitate classroom interaction for students according to an embodiment of the present invention;

[0025] Figure 5 This is a block diagram of a behavior recognition device for assisting students in online classes according to an embodiment of the present invention. Detailed Implementation

[0026] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0027] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the invention to those skilled in the art.

[0028] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0029] Figure 1 This is a flowchart illustrating a behavior recognition method for assisting students in online classes according to an embodiment of the present invention, as shown below. Figure 1 As shown, the behavior recognition method for assisting students in online classes includes the following steps:

[0030] S101, acquire the student's head movement signal, wherein the student's head movement signal includes the phase of the RFID electronic tag and the received signal strength indication.

[0031] As one example, acquiring a student's head movement signal includes: placing an RFID electronic tag on the student's head and placing an RFID reader around the student so that the RFID reader can receive the head movement signal returned by the RFID electronic tag in real time.

[0032] In other words, students can wear hats with RFID tags attached or attach the RFID tags directly to the back of their heads, and place an RFID reader behind or next to the student so that the RFID reader can receive the RFID tag phase and corresponding signal strength indication returned by the RFID tag in real time.

[0033] As an example, after acquiring the student's head motion signal, nearest neighbor filling and Gaussian filtering are used to preprocess the head motion signal.

[0034] In other words, nearest neighbor filling solves the problem of missing data, and Gaussian filtering solves the problem of data noise.

[0035] It should be noted that the reliability of the collected head motion signals is improved by performing noise reduction and normalization.

[0036] S102, construct the trained action recognition model, and input the student's head action signal into the action recognition model so as to output the corresponding head action.

[0037] It should be noted that the action recognition model integrates convolutional neural networks and long short-term memory neural networks. The attention mechanism is used in the long short-term memory neural network to increase the weight of key features and decrease the weight of interference features. The convolutional neural network is used to capture spatial dimension features in a fine-grained manner, and the long short-term memory neural network is used to capture temporal dimension features in a fine-grained manner, thereby improving the recognition accuracy of the deep model.

[0038] As an example, the student's head movement signal is input into the action recognition model to output the corresponding head movement. This includes: inputting the student's head movement signal continuously collected within a preset time period into the action recognition model to determine whether the number of times the student's head movement signal continuously collected within the preset time period meets the preset conditions reaches a preset threshold. If so, it is determined that the student's head has moved, and the corresponding head movement is output. The head movement includes tilting forward, tilting backward, shaking the head to the left, and shaking the head to the right.

[0039] In other words, a time period, conditions, and number of times are preset. If the number of times the preset conditions are met among all the head motion signals collected within the preset time period reaches a preset threshold, it is determined that the head has moved. If the threshold is not reached, it is determined that the head has not moved.

[0040] It should be noted that the phase difference can be determined by the phase of the RFID electronic tag and the corresponding signal strength indication, thereby obtaining the corresponding head movement. Within a preset time period, the head movement that occurs most frequently among the head movements corresponding to each phase difference is the head movement output by the action recognition model.

[0041] In addition, the number of times is initially a specified number, but it is not fixed and will change accordingly based on the adjustment of the model.

[0042] As an example, the phase of the RFID electronic tag in the student's head movement signal continuously collected within a preset time period is b{b1, b2, ..., b}. n The received signal strength indication is c{c1, c2, ..., c}. n The preset condition that is satisfied is |b i -b i-1 |≥d and|c i -c i-1 |≥1, where n represents the number of phase or signal strength indications of RFID electronic tags received within a preset time period, b i c represents the phase of the i-th RFID tag. i b represents the i-th signal strength indicator. i-1 c represents the phase of the (i-1)th RFID tag. i This indicates the (i-1)th signal strength indication, and d represents the phase difference threshold.

[0043] It should be noted that, taking the state of a certain time point E as the "zero axis", the time segments t before and after that time point E are considered together, and it is determined whether the above conditions are met N times within 2t. If N are met, it is considered that the head has performed a certain action.

[0044] S103, parse the output head movements according to the preset application scenario in order to perform the corresponding operation.

[0045] As an example, such as Figure 2-4 As shown, the output head movements are parsed according to preset application scenarios to execute corresponding operations, including: determining the type of preset application scenario, which includes nearsightedness, listening, and answering; if the preset application scenario is nearsightedness, the head movements are used to determine whether the head is too close to the screen, and if so, a warning is issued; if the preset application scenario is listening, the head movements are used to determine whether the student is listening attentively, and if not, a warning is issued; if the preset application scenario is answering, the head movements are converted into corresponding answers so that the answers can be scored according to pre-set accurate answers to obtain the student's answer status.

[0046] In other words, if a student leans forward during a preset time period, a nearsightedness warning is issued; if they maintain the same head position during the preset time period, a warning for not paying attention is issued. Multiple-choice answers are pre-entered into the system. When a teacher presents a multiple-choice question, students answer using four head movements (leaning forward for A, tilting back for B, shaking left for C, and shaking right for D). The deep learning model identifies the data and converts the student's head movements into A, B, C, and D. The system compares these answers with the pre-entered ones, scores the student's responses, and the teacher receives feedback on the student's performance.

[0047] The results of comparing the students' chosen answers are shown in Table 1 below:

[0048] 1 2 3 4 5 6 7 8 9 10 accuracy Answer A A C B A D C C B D Student A A A C B A C C C B D 90％ Student B A A C D A D C A B D 80％ Student C A A C B A D C C B D 100％

[0049] In summary, the behavior recognition method for assisting students in online classes according to embodiments of the present invention replaces video surveillance for recognizing students' head movements with RFID behavior recognition technology, thus protecting students' privacy; it eliminates the need for additional hardware devices, allowing students to complete multiple-choice questions based on four head movements, thereby assessing the effectiveness of their classes; it helps students develop correct and good sitting posture, reducing the likelihood of myopia or its progression; and it uses fewer labels and a faster convergence model, which not only improves recognition accuracy but also reduces costs.

[0050] To implement the above embodiments, this invention also proposes a computer-readable storage medium storing a behavior recognition program for assisting students in online classes. When executed by a processor, the behavior recognition program for assisting students in online classes implements the behavior recognition method for assisting students in online classes as described above.

[0051] According to an embodiment of the present invention, a computer-readable storage medium stores a behavior recognition program for assisting students in online classes, so that when the processor executes the behavior recognition program for assisting students in online classes, it implements the behavior recognition method for assisting students in online classes as described above. Thus, by recognizing students' head movement signals through RFID, corresponding operations can be performed in multiple application scenarios based on the head movements, thereby reducing the exposure of students' privacy while improving the efficiency of online classes.

[0052] To implement the above embodiments, this invention proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the behavior recognition method for assisting students in online classes as described above.

[0053] According to the computer device of the present invention, a behavior recognition program for assisting students in online classes is stored in a memory, so that when the processor executes the behavior recognition program for assisting students in online classes, the behavior recognition method for assisting students in online classes described above is implemented. Thus, by recognizing the student's head movement signal through RFID, corresponding operations can be performed in multiple application scenarios based on the head movement, thereby reducing the exposure of student privacy while improving the efficiency of online classes.

[0054] To achieve the above embodiments, this invention proposes a behavior recognition device to assist students in online classes, such as... Figure 5 As shown, the behavior recognition device that assists students in taking online classes includes: an acquisition module 10, a behavior recognition module 20, and a judgment and processing module 30.

[0055] The acquisition module 10 is used to acquire the student's head movement signal, which includes the phase of the RFID electronic tag and the received signal strength indication; the behavior recognition module 20 is used to construct a trained action recognition model and input the student's head movement signal into the action recognition model to output the corresponding head movement; the judgment and processing module 30 is used to parse the output head movement according to the preset application scenario in order to execute the corresponding operation.

[0056] It should be noted that the above regarding Figure 1 The description of the behavior recognition method for assisting students in online classes also applies to the behavior recognition device for assisting students in online classes, and will not be repeated here.

[0057] In summary, the behavior recognition device for assisting students in online classes according to embodiments of the present invention acquires students' head movement signals through an acquisition module, wherein the students' head movement signals include the phase of the RFID electronic tag and the received signal strength indication; a trained action recognition model is constructed through the behavior recognition module, and the students' head movement signals are input into the action recognition model to output corresponding head movements; the judgment and processing module parses the output head movements according to preset application scenarios to execute corresponding operations; thus, by recognizing students' head movement signals through RFID, corresponding operations can be executed in multiple application scenarios based on the head movements, thereby reducing the exposure of students' privacy while improving the efficiency of online classes.

[0058] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0060] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0062] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0063] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0064] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0065] In the description of this invention, it should be understood that 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 indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0066] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0067] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0068] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms should not be construed as necessarily referring to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0069] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A behavior recognition method to assist students in online classes, characterized in that, Includes the following steps: Acquire student head movement signals, wherein the student head movement signals include the phase of the RFID electronic tag and the received signal strength indication; A trained action recognition model is constructed, and the student's head action signal is input into the action recognition model to output the corresponding head action. The output head movements are parsed according to a preset application scenario in order to execute the corresponding operation; The process of inputting the student's head movement signal into the action recognition model to output the corresponding head movement includes: The student's head movement signals collected continuously within a preset time period are input into the action recognition model to determine whether the number of times the student's head movement signals collected continuously within the preset time period meet the preset conditions reaches a preset threshold. If so, it is determined that the student's head has moved and the corresponding head movement is output. The head movement includes tilting forward, tilting backward, shaking the head to the left, and shaking the head to the right. Among them, the phase of the RFID electronic tag in the student's head movement signal continuously collected within a preset time period is b{b1,b2,…,b n The received signal strength indication is c{c1,c2,…,c n The preset condition that is satisfied is |b i -b i-1 |≥d and|c i -c i-1 |≥1, where n represents the number of phase or signal strength indications of RFID electronic tags received within a preset time period, b i c represents the phase of the i-th RFID tag. i b represents the i-th signal strength indicator. i-1 c represents the phase of the (i-1)th RFID tag. i This indicates the (i-1)th signal strength indication, and d represents the phase difference threshold. The output head movements are parsed according to a preset application scenario in order to execute corresponding operations, including: Determine the type of the preset application scenario, wherein the preset application scenario includes myopia, listening to lectures, and answering questions; If the preset application scenario is a myopia situation, then the system will determine whether the head is too close to the screen based on the head movement. If so, a warning will be issued. If the preset application scenario is a class listening situation, then the head movement is used to determine whether the student is listening attentively; if not, a warning is issued. If the preset application scenario is a question-and-answer situation, the head movement is converted into the corresponding answer so that the answer can be scored according to the preset accurate answer to obtain the student's answer status.

2. The behavior recognition method for assisting students in online classes as described in claim 1, characterized in that, Acquire student head movement signals, including: An RFID tag is attached to the student's head, and RFID readers are placed around the student so that the RFID readers can receive head movement signals returned by the RFID tag in real time.

3. The behavior recognition method for assisting students in online classes as described in claim 2, characterized in that, After acquiring the student's head movement signal, the head movement signal is preprocessed using nearest neighbor filling and Gaussian filtering.

4. A computer-readable storage medium, characterized in that, It stores a behavior recognition program that assists students in taking online classes. When the processor executes the behavior recognition program that assists students in taking online classes, it implements the behavior recognition method for assisting students in taking online classes as described in any one of claims 1-3.

5. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the behavior recognition method for assisting students in online classes as described in any one of claims 1-3.

6. A behavior recognition device to assist students in online classes, characterized in that, include The acquisition module is used to acquire the student's head movement signal, wherein the student's head movement signal includes the phase of the RFID electronic tag and the received signal strength indication; The behavior recognition module is used to construct a trained action recognition model and input the student's head action signal into the action recognition model so as to output the corresponding head action. The judgment and processing module is used to parse the output head action according to a preset application scenario so as to perform the corresponding operation; The process of inputting the student's head movement signal into the action recognition model to output the corresponding head movement includes: The student's head movement signals collected continuously within a preset time period are input into the action recognition model to determine whether the number of times the student's head movement signals collected continuously within the preset time period meet the preset conditions reaches a preset threshold. If so, it is determined that the student's head has moved and the corresponding head movement is output. The head movement includes tilting forward, tilting backward, shaking the head to the left, and shaking the head to the right. Among them, the phase of the RFID electronic tag in the student's head movement signal continuously collected within a preset time period is b{b1,b2,…,b n The received signal strength indication is c{c1,c2,…,c n The preset condition that is satisfied is |b i -b i-1 |≥d and|c i -c i-1 |≥1, where n represents the number of phase or signal strength indications of RFID electronic tags received within a preset time period, b i c represents the phase of the i-th RFID tag. i b represents the i-th signal strength indicator. i-1 c represents the phase of the (i-1)th RFID tag. i This indicates the (i-1)th signal strength indication, and d represents the phase difference threshold. The output head movements are parsed according to a preset application scenario in order to execute corresponding operations, including: Determine the type of the preset application scenario, wherein the preset application scenario includes myopia, listening to lectures, and answering questions; If the preset application scenario is a myopia situation, then the system will determine whether the head is too close to the screen based on the head movement. If so, a warning will be issued. If the preset application scenario is a class listening situation, then the head movement is used to determine whether the student is listening attentively; if not, a warning is issued. If the preset application scenario is a question-and-answer situation, the head movement is converted into the corresponding answer so that the answer can be scored according to the preset accurate answer to obtain the student's answer status.

Images