A classroom student behavior analysis system based on edge computing

Abstract

The embodiment of the present invention discloses a classroom student behavior analysis system based on edge computing, which relates to the field of edge computing technology. The system includes: a camera, which is set at the height of the teacher's podium, and is used to collect classroom images of all students in the classroom during class in real time; an edge computing module, which is connected to the camera, and is used to identify students with abnormal behavior in the current classroom image according to the classroom image through a preset abnormal behavior recognition algorithm, and identify the students with abnormal behavior as target students; a client, which is used to display the identification of the target student determined by the current edge computing module. The present invention can intelligently and automatically identify the abnormal behavior of students in class and issue an alarm in time.

Description

Technical Field

[0001] The present invention belongs to the field of edge computing technology, and in particular relates to a classroom student behavior analysis system based on edge computing. Background Art

[0002] First of all, class can help students remember (memorize) the teaching content required by the syllabus, and secondly, help students understand the required teaching content, such as through pictures, examples, introducing other people's views, etc.; further, in class, teachers can explain the ins and outs, development status, future trends, advantages and disadvantages, application status, existing problems, solutions, etc. of the required teaching content, thereby effectively improving students' ability to master and learn knowledge.

[0003] However, during class, some students often lose focus and need to be reminded in time. Existing methods of monitoring student behavior mainly rely on teachers on the podium. When teachers find students under the podium have abnormal behaviors, such as distraction, lowering their heads, sleeping, etc., they will give timely reminders. However, the energy of teachers on the podium is limited. On the one hand, they need to pay attention to the knowledge points being explained, and on the other hand, they need to observe the students' class status, which consumes a lot of teachers' energy and affects the quality of teaching. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a classroom student behavior analysis system based on edge computing, which is used to solve the problem that the existing student behavior monitoring method consumes a lot of teachers' energy. The present invention can intelligently and automatically identify the abnormal behavior of students in class and issue an alarm in time through the abnormal behavior recognition algorithm of the edge computing module.

[0005] An embodiment of the present invention provides a classroom student behavior analysis system based on edge computing, including:

[0006] The camera is installed at the height of the teacher's platform and is used to collect classroom images of all students in the classroom in real time during class;

[0007] an edge computing module connected to the camera, and configured to identify students with abnormal behaviors in the current classroom image according to the classroom image by using a preset abnormal behavior recognition algorithm, and determine the students with abnormal behaviors as target students;

[0008] The client is used to display the identity of the target student determined by the current edge computing module.

[0009] In an optional embodiment, the identifier of the target student is the seat number of the target student in the classroom.

[0010] In an optional embodiment, the edge analysis module includes:

[0011] An identification unit is used to identify students with abnormal behavior in the current classroom image according to the classroom image by using a preset abnormal behavior identification algorithm, determine the students with abnormal behavior as target students, and send the seat number of the target student to the client;

[0012] The recording unit is used to record the duration of each target student's abnormal behavior, update the recorded number of times each target student has abnormal behavior in history, obtain the pre-stored distance between the target student's seat number and the podium, and send a data analysis instruction for the target student to the data analysis unit, or, when the recording unit confirms in the feedback message sent by the client that the target student does not have abnormal behavior, add 1 to the recorded number of times the target student has been mistakenly determined to have abnormal behavior in history;

[0013] The data analysis unit is used to determine the historical naughtiness value of the target student according to the historical abnormal behavior data of the target student recorded by the recording unit when receiving the data analysis instruction of the target student; wherein the historical abnormal behavior data at least includes: the duration of each abnormal behavior of the target student in history, the number of abnormal behaviors of the target student in history, and the number of times the target student was mistakenly determined to have abnormal behavior in history; the historical naughtiness value is used to characterize the degree of abnormal behavior of the target student in history;

[0014] A sending unit, used for sending the correspondence between the historical naughtiness level value and the seat number of the target student and the distance between the seat number of the target student and the podium to the client;

[0015] The client is also used to provide the teacher with the seat number of the target student who has abnormal behavior in the inquiry message mode, receive the teacher's feedback message on the inquiry message and send it to the edge computing module; the client is also used to display the seat number of the target student according to the historical naughtiness value of the target student and the distance value between the seat number of the target student and the podium; wherein the feedback message includes the teacher's feedback on whether the target student does have abnormal behavior.

[0016] In an optional embodiment, the data analysis unit is specifically used to calculate the historical naughtiness level value of the target student according to the first formula;

[0017] Among them, the first formula is:

[0018]

[0019] In the first formula, P(i) represents the historical mischievousness value of the i-th target student; T(i_a) represents the duration of the a-th abnormal behavior of the i-th target student; N(i) represents the number of abnormal behaviors of the i-th target student; and n(i) represents the number of times the i-th target student has been mistakenly identified as having abnormal behavior.

[0020] In an optional embodiment, the client is specifically used to control the font size of the seat number of the corresponding target student when it is displayed according to the historical naughtiness value of the target student and the distance between the seat number of the target student and the podium.

[0021] In an optional embodiment, the recording unit is further configured to record the initial moment when the identification unit identifies that the target student has abnormal behavior when it is confirmed in the feedback message sent by the client that the target student does have abnormal behavior;

[0022] The edge computing module further includes:

[0023] A sorting module is used to determine the sorting priority value of each target student according to the initial moment of identifying the abnormal behavior of each target student, the distance between the seat number of the target student and the podium, and the historical naughtiness value of the target student when the recognition unit identifies multiple target students in the current classroom image and the feedback message sent by the client confirms that the multiple target students do have abnormal behaviors;

[0024] The sending unit is further used to send the corresponding relationship between the ranking priority values ​​and seat numbers of the multiple target students identified this time to the client;

[0025] The client is specifically used to sort and display the seat numbers of multiple current target students according to the sorting priority values ​​of the target students.

[0026] In an optional embodiment, the client is specifically used to control the font size of the seat number of the target student when it is displayed according to the second formula; the client is also specifically used to sort and display the seat numbers of multiple target students from high to low according to the sorting priority values ​​of the target students;

[0027] The ranking module is specifically used to determine the ranking priority value of each target student according to the third formula;

[0028] Wherein, the second formula is:

[0029]

[0030] The third formula is:

[0031]

[0032] In the second and third formulas, h(i) represents the font size of the seat number of the i-th target student when displayed; S[Z(i)] represents the distance between the seat number of the i-th target student and the podium; S0 represents a preset unit distance value; h0 represents the predetermined minimum font size that can be controlled and displayed on the client; h M represents the predetermined maximum font size that can be controlled and displayed on the client; L(t_i) represents the sorting priority value of the i-th target student at time t; t(i) represents the initial time when the i-th target student is identified to have abnormal behavior; t represents the current time.

[0033] In an optional embodiment, the client is a mobile client

[0034] The present invention provides a classroom student behavior analysis system based on edge computing. First, classroom images of all students in the classroom are collected during class. Then, based on the classroom images, students with abnormal behaviors in the current classroom images are identified through an abnormal behavior recognition algorithm preset by an edge computing module. Finally, the identification of students with abnormal behaviors is sent to a client for display. The present invention can intelligently and automatically identify abnormal behaviors of students in class and issue an alarm in a timely manner through the abnormal behavior recognition algorithm of the edge computing module. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A schematic diagram of the structure of a classroom student behavior analysis system based on edge computing provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0038] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Figure 1 A schematic diagram of the structure of a classroom student behavior analysis system based on edge computing provided by an embodiment of the present invention. Figure 1 , the system comprises:

[0040] Camera 1 is installed at the height of the teacher's platform and is used to collect classroom images of all students in the classroom in real time during class;

[0041] The edge computing module 2 is connected to the camera 1 and is used to identify students with abnormal behaviors in the current classroom image according to the classroom image by using a preset abnormal behavior recognition algorithm, and determine the students with abnormal behaviors as target students;

[0042] Client 3 is used to display the identifier of the target student determined by the current edge computing module 2.

[0043] The beneficial effects of the above technical solution are as follows: the classroom student behavior analysis system based on edge computing provided by the embodiment of the present invention first collects classroom images of all students in the classroom during class, and then identifies students with abnormal behavior in the current classroom image through the abnormal behavior recognition algorithm preset by the edge computing module based on the classroom image, and finally sends the identification of the students with abnormal behavior to the client for display. The present invention can intelligently and automatically identify the abnormal behavior of students in class and issue an alarm in time through the abnormal behavior recognition algorithm of the edge computing module, thereby realizing real-time detection of the status of students in class.

[0044] As an optional embodiment, the identifier of the target student is the seat number of the target student in the classroom.

[0045] The beneficial effect of the above technical solution is: the seat number of the student with abnormal behavior is sent to the client for display, which can facilitate the teacher to quickly locate the position of the student with abnormal behavior.

[0046] As an optional embodiment, the edge analysis module 2 includes:

[0047] The recognition unit is used to identify students with abnormal behavior in the current classroom image according to the classroom image by using a preset abnormal behavior recognition algorithm, determine the students with abnormal behavior as target students, and send the seat number of the target student to the client 3;

[0048] The recording unit is used to record the duration of each target student's abnormal behavior, update the recorded number of times each target student has abnormal behavior in history, obtain the pre-stored distance value between the target student's seat number and the podium, and send a data analysis instruction for the target student to the data analysis unit, or, when the recording unit confirms in the feedback message sent by the client 3 that the target student does not have abnormal behavior, add 1 to the recorded number of times the target student has been mistakenly determined to have abnormal behavior;

[0049] The data analysis unit is used to determine the historical naughtiness value of the target student according to the historical abnormal behavior data of the target student recorded by the recording unit when receiving the data analysis instruction of the target student; wherein the historical abnormal behavior data at least includes: the duration of each abnormal behavior of the target student in history, the number of abnormal behaviors of the target student in history, and the number of times the target student was mistakenly determined to have abnormal behavior in history; the historical naughtiness value is used to characterize the degree of abnormal behavior of the target student in history;

[0050] A sending unit, used for sending the correspondence between the historical naughtiness level value of the target student and the seat number and the distance between the seat number of the target student and the podium to the client 3;

[0051] Client 3 is also used to provide the teacher with the seat number of the target student who has abnormal behavior in this time in an inquiry message mode, receive the teacher's feedback message on this inquiry message and send it to the edge computing module; the client is also used to display the seat number of the target student according to the historical naughtiness value of the target student and the distance value between the target student's seat number and the podium; wherein the feedback message includes the teacher's feedback on whether the target student does have abnormal behavior.

[0052] The beneficial effect of the above technical solution is: when there is a student with abnormal behavior (i.e., the target student) in the current classroom image, the historical naughtiness level of the target student is determined according to the duration of each abnormal behavior of the target student in history, the number of abnormal behaviors of the target student in history, and the number of times the target student has been mistakenly determined as having abnormal behavior. This level objectively reflects the historical abnormal behavior of the target student and also objectively reflects the possible current abnormal behavior of the target student. The correspondence between the historical naughtiness level of the target student and the seat number and the distance between the target student's seat number and the podium are sent to the client for display, so that the teacher can have a more comprehensive understanding of the abnormal behavior of the target student.

[0053] As an optional embodiment, the data analysis unit is specifically used to calculate the historical naughtiness level value of the target student according to the first formula;

[0054] Among them, the first formula is:

[0055]

[0056] In the first formula, P(i) represents the historical mischievousness value of the i-th target student; T(i_a) represents the duration of the a-th abnormal behavior of the i-th target student; N(i) represents the number of abnormal behaviors of the i-th target student; and n(i) represents the number of times the i-th target student has been mistakenly identified as having abnormal behavior.

[0057] The beneficial effect of the above technical solution is: using the first formula (1) to obtain the historical naughtiness value of the student according to the duration of each abnormal behavior of the target student, the number of abnormal behaviors of the target student, and the number of times the target student was mistakenly determined as having abnormal behavior, the student's historical naughtiness value is quantified, thereby improving the efficiency of the system.

[0058] As an optional embodiment, the client is specifically used to control the font size of the seat number of the corresponding target student when it is displayed according to the historical naughtiness value of the target student and the distance between the seat number of the target student and the podium.

[0059] The beneficial effect of the above technical solution is: according to the historical naughtiness value of the target student and the distance between the target student's seat number and the podium, the font size of the corresponding target student's seat number when displayed is controlled. When the historical naughtiness value is larger, the font size is set larger, thereby giving a reminder to the teacher.

[0060] As an optional embodiment, the recording unit is further configured to record the initial moment when the identification unit identifies that the target student has abnormal behavior when it is confirmed in the feedback message sent by the client that the target student does have abnormal behavior;

[0061] The edge computing module 2 further includes:

[0062] A sorting module is used to determine the sorting priority value of each target student according to the initial moment of identifying the abnormal behavior of each target student, the distance between the seat number of the target student and the podium, and the historical naughtiness value of the target student when the recognition unit identifies multiple target students in the current classroom image and the feedback message sent by the client confirms that the multiple target students do have abnormal behaviors;

[0063] The sending unit is further used to send the corresponding relationship between the ranking priority values ​​and seat numbers of the multiple target students identified this time to the client;

[0064] Client 3 is specifically used to sort and display the seat numbers of multiple current target students according to the sorting priority values ​​of the target students.

[0065] The beneficial effect of the above technical solution is that students with more abnormalities and closer time among the target students are displayed at the front position of the client, which is convenient for teachers to manage them quickly and efficiently.

[0066] As an optional embodiment, the client 3 is specifically used to control the font size of the seat number of the target student when it is displayed according to the second formula; and is also specifically used to sort and display the seat numbers of multiple target students from high to low according to the sorting priority values ​​of the target students;

[0067] The ranking module is specifically used to determine the ranking priority value of each target student according to the third formula;

[0068] Wherein, the second formula is:

[0069]

[0070] The third formula is:

[0071]

[0072] In the second and third formulas, h(i) represents the font size of the seat number of the i-th target student when displayed; S[Z(i)] represents the distance between the seat number of the i-th target student and the podium; S0 represents a preset unit distance value; h0 represents the predetermined minimum font size that can be controlled and displayed on the client; h M represents the predetermined maximum font size that can be controlled and displayed on the client; L(t_i) represents the sorting priority value of the i-th target student at time t; t(i) represents the initial time when the i-th target student is identified to have abnormal behavior; t represents the current time.

[0073] The beneficial effects of the above technical solution are as follows: using the second formula (2) to control the font size of the seat number in the corresponding binding mark data displayed on the teacher's mobile terminal according to the historical naughtiness value of the student in the binding mark data (i.e. the historical naughtiness value of the target student and the seat number of the student), thereby giving the teacher a reminder; then using the third formula (3) to intelligently sort the seat numbers of the students with abnormal behavior on the teacher's client 3 according to the initial moment when the student with abnormal behavior is detected and the binding mark data of the abnormal student, thereby arranging the students with more abnormal behaviors and more recent abnormal behaviors at the front to facilitate the teacher's management.

[0074] As an optional embodiment, the client 3 is a mobile client.

[0075] The beneficial effects of the above technical solution are: the mobile client is convenient for teachers to carry with them. When students with abnormal behavior appear, teachers can understand the situation in time through the mobile client they carry with them, thereby improving management efficiency.

[0076] From the content of the above embodiment, it can be known that the intelligent analysis degree of the monitoring screen (i.e., the classroom image of all students in the classroom during class) can be improved through the edge computing module 2, and intelligent judgment can be made on the status of students, such as normal, dazed, dozing, playing with mobile phones, etc., and students with abnormal behavior can be marked to remind teachers; specifically, when a student with abnormal behavior is detected in this class, the historical naughtiness value of the student is obtained according to the number of abnormal behaviors in the history of the student, the duration of each historical abnormal behavior, and the number of times the student is mistakenly determined as abnormal behavior. Then, the historical naughtiness value of the student and the student are compared and the historical naughtiness value of the student are compared. The student's seat number is bound and marked, and the binding mark data is sent to the teacher's mobile terminal. The teacher's mobile terminal will display the student's seat number in the binding mark data and control the font size of the seat number according to the student's historical naughtiness value in the binding mark data, so as to remind the teacher. If there are multiple students with abnormal behaviors in this class, the seat numbers of the abnormal students will be intelligently sorted on the teacher's mobile terminal according to the initial time when the abnormal behavior is detected and the binding mark data of the abnormal students, so as to put the students with more abnormal behaviors and closer time at the front, so as to facilitate the teacher's management.

[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 An apparatus for the method specified in one or more blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 The method specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the method are specified in one or more boxes.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these changes and variations. The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A classroom student behavior analysis system based on edge computing, characterized in that: include: The camera is installed at the height of the teacher's platform and is used to collect classroom images of all students in the classroom in real time during class; an edge computing module connected to the camera, and configured to identify students with abnormal behaviors in the current classroom image according to the classroom image by using a preset abnormal behavior recognition algorithm, and determine the students with abnormal behaviors as target students; The client is used to display the identity of the target student determined by the current edge computing module; The identifier of the target student is the seat number of the target student in the classroom; Wherein, the edge computing module includes: An identification unit is used to identify students with abnormal behavior in the current classroom image according to the classroom image by using a preset abnormal behavior identification algorithm, determine the students with abnormal behavior as target students, and send the seat number of the target student to the client; The recording unit is used to record the duration of each target student's abnormal behavior, update the recorded number of times each target student has abnormal behavior in history, obtain the pre-stored distance between the target student's seat number and the podium, and send a data analysis instruction for the target student to the data analysis unit, or, when the recording unit confirms in the feedback message sent by the client that the target student does not have abnormal behavior, add 1 to the recorded number of times the target student has been mistakenly determined to have abnormal behavior in history; a data analysis unit, configured to determine a historical naughtiness value of the target student according to the historical abnormal behavior data of the target student recorded by the recording unit upon receiving a data analysis instruction of the target student; wherein the historical abnormal behavior data includes the duration of each abnormal behavior of the target student, the number of abnormal behaviors of the target student and the number of times the target student was mistakenly determined to have abnormal behavior; and the historical naughtiness value is used to characterize the degree of abnormal behavior of the target student in history; A sending unit, used for sending the correspondence between the historical naughtiness level value and the seat number of the target student and the distance between the seat number of the target student and the podium to the client; The client is also used to provide the teacher with the seat number of the target student with abnormal behavior in the inquiry message mode, receive the teacher's feedback message on the inquiry message and send it to the edge computing module; the client is also used to display the seat number of the target student according to the historical naughtiness value of the target student and the distance value between the seat number of the target student and the podium; wherein the feedback message includes the teacher's feedback on whether the target student does have abnormal behavior; The data analysis unit is specifically used to calculate the historical naughtiness level value of the target student according to the first formula; Among them, the first formula is: In the first formula, Indicates The historical naughtiness level of each target student; Indicates Target student history Duration of each episode of abnormal behavior; Indicates The number of times the target student has historically exhibited abnormal behavior; Indicates The historical number of times the target student was misidentified as having deviant behavior.

2. The classroom student behavior analysis system based on edge computing as claimed in claim 1, characterized in that: The client is specifically used to control the font size of the seat number of the corresponding target student when it is displayed according to the historical naughtiness value of the target student and the distance between the seat number of the target student and the podium.

3. The classroom student behavior analysis system based on edge computing as described in claim 2 is characterized in that: The recording unit is further configured to record the initial moment when the identification unit identifies that the target student has abnormal behavior, when it is confirmed in the feedback message sent by the client that the target student does have abnormal behavior; The edge computing module further includes: A sorting module is used to determine the sorting priority value of each target student according to the initial moment of identifying the abnormal behavior of each target student, the distance between the seat number of the target student and the podium, and the historical naughtiness value of the target student when the recognition unit identifies multiple target students in the current classroom image and the feedback message sent by the client confirms that the multiple target students do have abnormal behaviors; The sending unit is further used to send the corresponding relationship between the ranking priority values ​​and seat numbers of the multiple target students identified this time to the client; The client is specifically used to sort and display the seat numbers of multiple current target students according to the sorting priority values ​​of the target students.

4. The classroom student behavior analysis system based on edge computing as claimed in claim 3 is characterized in that: The client is specifically used to control the font size of the seat number of the target student when it is displayed according to the second formula; the client is also specifically used to sort and display the seat numbers of multiple target students from high to low according to the sorting priority values ​​of the target students; The ranking module is specifically used to determine the ranking priority value of each target student according to the third formula; Wherein, the second formula is: The third formula is: In the second and third formulas, Indicates The font size of the target student's seat number when displayed; Indicates The distance between the seat number of each target student and the podium; Indicates the preset unit distance value; Indicates the predetermined minimum font size that can be controlled and displayed on the client; Indicates the predetermined maximum font size that can be controlled and displayed on the client; express Moment The ranking priority value of each target student; Indicates the identification of The initial moment when the target student exhibits abnormal behavior; Indicates the current moment.

5. The classroom student behavior analysis system based on edge computing according to any one of claims 1 to 4, characterized in that: The client is a mobile client.

Images