Interactive teaching management system and method for smart classroom

Abstract

The invention discloses an interactive teaching management system and method for a smart classroom, relates to the technical field of teaching management, and solves the technical problems that in the prior art, teaching activities are performed through intelligent multimedia, the actual classroom condition of students is not considered, and after-class homework of the students is difficult to set according to the actual condition of the students. Comprising a central processing module, a data acquisition module, a display control terminal and a database, the central processing module is used for generating an acquisition instruction based on the teacher voice information; acquiring a student image according to the acquisition instruction, and inputting the student image into a concentration degree model to obtain the time period concentration degree of the student; generating a reminding signal and after-class homework based on the time period concentration degree and a concentration degree threshold value; the teacher can conveniently adjust the teaching mode and the teaching progress according to the class states of the students; according to the invention, corresponding types of questions can be set according to the class attending states of different knowledge points during class attending of students, which is more suitable for learning conditions of the students, so that the students can have learning resources suitable for themselves.

Description

Technical Field

[0001] This application belongs to the technical field of teaching management, involving teaching management technology, specifically an interactive teaching management system and method for a smart classroom. Background Art

[0002] With the help of advanced information technology, the smart classroom has realized the digitization, intelligence, and Internetization of the teaching process, enabling teachers to monitor students' learning status in real time, accurately understand students' classroom status, and then adjust teaching content in a timely manner; the smart classroom provides a variety of interactive means, making the classroom content more vivid and interesting, which is conducive to improving students' concentration.

[0003] The prior art (a patent for invention with the publication number CN109754653B) discloses a personalized teaching system that can output corresponding personalized content through an output interface according to the results of face recognition, gesture recognition, or emotion recognition. Teachers conduct personalized teaching in the classroom based on the personalized content. The above technology does not consider the actual performance of students in the classroom and is difficult to set students' after-class homework according to the actual situation of students, which may lead to polarization among students. Therefore, the present invention provides an interactive teaching management system and method for a smart classroom. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes an interactive teaching management system and method for a smart classroom, which is used to solve the technical problem that in the prior art, teaching activities are carried out through intelligent multimedia without considering the actual classroom situation of students and it is difficult to set students' after-class homework according to the actual situation of students. This application solves the above problems by obtaining the real-time concentration of students during class to remind teachers to adjust the teaching method and progress, and at the same time generating teaching homework according to the period concentration.

[0005] To achieve the above object, the first aspect of this application provides an interactive teaching management system and method for a smart classroom, including: A central processing module, and a data acquisition module, a display control terminal, and a database connected thereto; Data acquisition module: Obtain teachers' voice information, video information, and students' images through data acquisition devices; Central processing module: Obtain teachers' voice information, generate acquisition instructions based on the teachers' voice information; Acquire students' images according to the acquisition instructions, input the students' images into the concentration model to obtain the period concentration of students; Generate a reminder signal and after-class homework based on the period concentration and the concentration threshold; among them, the concentration model is obtained by training with an artificial intelligence model; The display control terminal includes a teacher terminal and student terminals; among them, the teacher terminal is used to display the status of students during class, etc.; the student terminals are used to display the teaching content of the teacher, etc. Database: used to store historical data, teaching content, student status, etc.

[0006] This application generates a collection instruction according to the teacher's voice information, collects student images according to the collection instruction, obtains the current period of concentration of the students through the student images, and generates a reminder signal in a timely manner according to the period of concentration, facilitating the teacher to adjust the teaching method and teaching progress according to the students' class status; at the same time, generates teaching assignments according to the period of concentration, and can set corresponding types of questions according to the students' listening status of different knowledge points during class, which is more suitable for the learning situation of the students, enabling the students to have learning resources suitable for themselves.

[0007] Preferably, the generating the collection instruction based on the teacher's voice information includes: Obtain the teacher's voice information in real time and convert the teacher's voice information into text information; Detect whether key words appear in the text information; If yes, generate text key words according to the text information, and at the same time generate a collection instruction; If no, continuously obtain the teacher's voice information, convert the teacher's voice information into text information, and detect the text information; among them, the key words include chapter key words, knowledge point key words, and specific key words.

[0008] During the actual class, when the teacher mentions some key knowledge points, the concentration of the students in class may change. If student images are collected throughout the class, it will lead to a large amount of computational effort in subsequent image processing. In an actual classroom, it is only necessary to focus on some special times for image collection and processing; this application collects and analyzes the teacher's voice information, and generates a collection instruction according to the key words in the teacher's voice information. The collection instruction is an instruction to collect student images in real time; enabling this application to flexibly collect student images according to the teacher's class situation, facilitating the reduction of real-time computational effort.

[0009] Preferably, the central processing module is further used to expand the teaching content through the cloud platform, including: Extract the chapter key words and knowledge point key words from the text key words; Search for the corresponding chapter content and knowledge point content in the cloud platform; And send the chapter content and knowledge point content to the teacher terminal for screening to obtain the teaching content; send the teaching content to the student terminals; Screening the chapter content and knowledge point content to obtain the teaching content includes a current affairs mode and a classic mode; The current affairs mode sorts the chapter content and / or knowledge point content in the order from the most recent to the oldest, and filters out the chapter content and / or knowledge point content with higher rankings. The classic mode sorts the chapter content and / or knowledge point content in the order from the most views and / or the highest content score to the least, and filters out the chapter content and / or knowledge point content with higher rankings.

[0010] This application obtains the chapter content and knowledge point content through the cloud platform, and sends the chapter content and knowledge point content as supplementary content for teaching to the student terminal; it is convenient for students to obtain the content related to the chapter keywords and knowledge point keywords, and thus convenient for students to understand and learn the relevant chapters and knowledge points.

[0011] Preferably, the concentration model is obtained through training with an artificial intelligence model, including: Obtain a number of student status images and their corresponding concentration scores; integrate the student status images and their corresponding concentration scores into training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model; obtain a concentration model with the input being the student image and the output being the time period concentration score. Among them, the time period concentration score is denoted as the time period concentration; the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0012] Preferably, generating a reminder signal based on the time period concentration of students includes: Obtain the time period concentration corresponding to the student images collected by a number of students under the same collection instruction, and the concentration threshold corresponding to each student; Obtain all students with a concentration less than the corresponding concentration threshold, and mark them as target personnel; mark the time period concentration of the target personnel as SZi, and mark the corresponding concentration threshold as YZi; where i is the number of the target personnel, and i = 1, 2, 3, …, n; n is the total number of target personnel in this collection instruction. Calculate the signal value XH corresponding to this collection instruction through the formula XH = ∑[(YZi - SZi) / YZi]; When the signal value XH is greater than the signal value threshold and not equal to the total number of target personnel, an interaction instruction is generated; When the signal value XH is greater than the signal value threshold and equal to the total number of target personnel, a rest instruction is generated; When the signal value XH is less than the signal value threshold; a marking information is generated; where the reminder signal includes an interaction instruction, a rest instruction, and a marking information; the interaction instruction includes small games and jokes related to the course, etc., for the teacher to interact with the students, which is convenient for improving the concentration of students.

[0013] This application generates reminder signals based on the time - period concentration level to remind teachers to make reasonable teaching arrangements, thereby improving students' learning efficiency. At the same time, it facilitates teachers to pay attention to a small number of students who are inattentive in class, so as to solve the problem that the learning effect of certain knowledge points is poor due to a small number of students being distracted in class.

[0014] Preferably, generating after - class homework based on the time - period concentration level of students and the concentration - level threshold includes: Obtain all key words in this class; extract chapter - related key words and knowledge - point key words from the key words, and divide this class into several teaching time - periods according to the chapter - related key words and knowledge - point key words; obtain the time - period concentration level and the corresponding concentration - level threshold of each student for each teaching time - period; Judge whether the time - period concentration level is greater than the concentration - level threshold; if yes, mark the time - period homework of the corresponding student as examination homework; if not, mark the time - period homework of the corresponding student as teaching homework; among them, examination homework includes homework items; teaching homework includes teaching videos and guiding homework, and the guiding homework is homework questions for explaining knowledge points; When the time - period homework of a student is examination homework, set the homework items according to the difference between the time - period concentration level and the concentration - level threshold, and adjust the homework items according to the historical homework items and historical correct - rate of the corresponding student; When the time - period homework of a student is teaching homework, judge whether the time - period concentration level of the corresponding student is lower than the unlearned threshold; if yes, set the teaching homework of the corresponding student as a teaching video; if not, set the teaching homework of the corresponding student as guiding homework; Integrate all the time - period homework of this class to generate after - class homework.

[0015] Preferably, setting the homework items according to the difference between the time - period concentration level and the concentration - level threshold includes: Obtain the time - period concentration level and the concentration - level threshold; calculate the difference between the time - period concentration level and the concentration - level threshold; when the difference is less than the medium threshold, set the corresponding homework type as simple homework; when the difference is greater than the medium threshold and less than the high threshold, set the corresponding homework type as medium - level homework; when the difference is greater than the high threshold, set the corresponding homework type as difficult homework; among them, the homework items include homework type and the number of homework; the medium threshold and the high threshold are set by experience, and the high threshold is greater than the medium threshold, for example, the medium threshold is 5% of the concentration - level threshold, and the high threshold is 10% of the concentration - level threshold, etc.

[0016] This application generates homework items based on the student's period concentration and adjusts the homework items according to the historical correct rate, making the after-class homework more suitable for the student's current state, facilitating the student to review and strengthen the content taught in class. Setting different levels of homework items according to the student's class state can stimulate the student's learning motivation, avoid problems such as overly difficult questions that dampen the student's enthusiasm and overly simple questions that prevent the student from delving deeper into learning.

[0017] Preferably, the concentration threshold is determined comprehensively by the difficulty of the teaching subject, the teaching quality of the teaching teacher, and the student's concentration, including: Obtain the teaching quality scores of each teacher through the cloud platform and mark them as JS; obtain the difficulty score of the teaching subject and mark it as KM; The database obtains the mode of several historical concentrations corresponding to the teaching subject with the highest student exam score and records it as the standard concentration, marked as BZ; the standard concentration can be understood as the most suitable concentration, which can be understood as the concentration at which the corresponding student has the highest learning efficiency; mark the difficulty score of the teaching subject with the highest student exam score as BK; mark the teaching quality score of the corresponding subject's teaching teacher as BJ; Calculate the concentration threshold ZY for the corresponding student under the teaching of the corresponding teacher in the corresponding teaching subject through the formula ZY = [α1 × exp((JS - BJ) / MJ) + α2 × exp((KM - BK) / MK)] × BZ; where MJ is the full score of the teaching quality score, the higher the teaching quality score, the higher the teaching level of the teacher and the higher the student's concentration in class; MK is the full score of the difficulty score of the teaching subject, the higher the difficulty score of the teaching subject, the greater the learning difficulty of the corresponding teaching subject and the higher the concentration required by the student; α1 and α2 are weight coefficients.

[0018] Preferably, the central processing module is also used to determine whether the student has an abnormality through the period concentration, including: Obtain the period concentration and determine whether the period concentration is less than the abnormal concentration threshold; the abnormal concentration threshold is set by experience, such as 5% of the corresponding student's concentration threshold; If so, increment the abnormal parameter by one. When the abnormal parameter is greater than the abnormal parameter threshold, generate an abnormal instruction and send it to the teacher terminal; where the abnormal parameter represents the number of times the period concentration is continuously less than the abnormal concentration threshold; the abnormal parameter threshold is set as a positive integer by experience and can be 3; otherwise, continue to determine whether the next period concentration is less than the concentration threshold; If not, clear the abnormal parameter; continue to determine whether the next period concentration is less than the concentration threshold.

[0019] In the actual teaching process, there are some students who are not good at communicating, have physical problems or are in a low mood during class, and the teacher cannot be informed in time. Moreover, physical problems of students will affect their concentration in class. This application determines whether a student is abnormal by the abnormal number of times of the student's concentration during a period, and generates an abnormal instruction in time to remind the teacher to pay attention to the student's status, which is convenient for establishing a good relationship between the teacher and the student.

[0020] The second aspect of this application provides an interactive teaching management method for a smart classroom, including the following steps: Step 1: Obtain the teacher's voice information and generate a collection instruction according to the teacher's voice information. Step 2: Collect and obtain student images according to the collection instruction. Step 3: Input the student image into the concentration model to obtain the student's concentration during a period. Step 4: Generate a reminder signal according to the concentration during a period and the concentration threshold. Step 5: Generate after-class homework based on the concentration during a period and the concentration threshold.

[0021] Compared with the prior art, the beneficial effects of this application are as follows: 1. This application generates a collection instruction according to the teacher's voice information, collects student images according to the collection instruction, obtains the student's concentration during a period through the student images, and generates a reminder signal in time according to the concentration during a period, which is convenient for the teacher to adjust the teaching method and teaching progress according to the student's class status. At the same time, generating teaching homework according to the concentration during a period can set corresponding types of questions according to the student's listening status of different knowledge points during class, which is more suitable for the student's learning situation, enabling the student to have learning resources suitable for himself.

[0022] 2. This application determines whether a student is abnormal by the abnormal number of times of the student's concentration during a period, and generates an abnormal instruction in time to remind the teacher to pay attention to the student's status, which is convenient for establishing a good relationship between the teacher and the student. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a schematic diagram of the principle of this application; Figure 2 It is a method step diagram of this application; Figure 3 It is one of the diagrams of the status bar of a single student in this application; Figure 4 One of the status bar diagrams of a single student in this application; Figure 5 One of the status bar diagrams of a single student in this application. Specific implementation manner

[0025] Next, the technical solutions of this application will be described clearly and completely in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0026] Please refer to Figures 1 - 2 , the interactive teaching management system and method of the smart classroom provided by the first aspect embodiment of this application include: A central processing module, and a data acquisition module, a display control terminal, and a database connected thereto; Data acquisition module: Obtain teacher voice information, video information, and student images through data acquisition devices; The data acquisition devices include recorders and high-definition cameras, etc.; The teacher voice information is the content recorded by the recorder when the teacher speaks in class; The video information includes teaching video information and student video information. The teaching video information is the recorded video of the teacher's class; The student video information is the status video of each student during class; Central processing module: Obtain teacher voice information, generate a collection instruction based on the teacher voice information; Collect and obtain student images according to the collection instruction, input the student images into the concentration model to obtain the student's time period concentration; Generate a reminder signal and after-class homework based on the time period concentration and the concentration threshold; Among them, the concentration model is obtained through artificial intelligence model training; The display control terminal includes a teacher terminal and a student terminal; Among them, the teacher terminal is used to display the status of students during class, teaching content, etc.; The student terminal is used to display the teaching content of the teacher, etc.; As Figures 3 - 5 , for the status bar diagram of a single student, the status bar diagram of the student includes: student name, student time period concentration, concentration threshold, and abnormal status; Among them, when the student's time period concentration is 0, the corresponding student status bar will be displayed in red; When the student's time period concentration is less than the corresponding concentration threshold, the corresponding student status bar will be displayed in yellow; When the student's time period concentration is greater than or equal to the corresponding concentration threshold, the corresponding student status bar will be displayed in green; When the time period concentration is less than the concentration threshold, it is judged that the abnormal status of the corresponding student is yes, otherwise, it is judged that the abnormal status of the student is no; It should be noted that the overall student status diagram displayed on the teaching terminal is updated in real time according to the time period concentration of each student obtained by the acquisition instruction; and the update time is marked; It can be understood that when a student's physical condition deteriorates, it will cause the value of their time period concentration to decrease, and this will also be shown to the corresponding teacher through the student status bar; Database: used to store historical data, teaching content, student status, etc.

[0027] This application generates an acquisition instruction based on the teacher's voice information, acquires student images according to the acquisition instruction, obtains the student's time period concentration at this time through the student images, and generates a reminder signal in a timely manner according to the time period concentration, facilitating the teacher to adjust the teaching method and teaching progress according to the student's class status; at the same time, generates teaching assignments according to the time period concentration, and can set corresponding types of questions according to the listening status of different knowledge points during class, which is more suitable for the learning situation of students, enabling students to have learning resources suitable for themselves.

[0028] Generating an acquisition instruction based on the teacher's voice information includes: Obtaining the teacher's voice information in real time and converting the teacher's voice information into text information; Detecting whether key words appear in the text information; If so, generating text key words according to the text information and generating an acquisition instruction at the same time; If not, continuously obtain the teacher's voice information, convert the teacher's voice information into text information, and detect the text information; among them, the key words include chapter key words, knowledge point key words, and specific key words; the chapter key words, knowledge point key words, and specific key words are all set by experience; for example, the chapter key words of the mathematics subject can be "Section 1: Length Units", "Section 1", "Length Units", etc.; the knowledge point key words can be "What is a unit", "What is a length unit", etc.; the specific key words can be "The following is the key point", "Frequently tested points", "Difficult points", and "Error-prone", etc.; among them, the chapter key words and knowledge point key words change according to the different chapters or subjects of the class, and the chapter key words, knowledge point key words, and specific key words can also be obtained through big data statistics; Specifically, obtain the course data of different teachers on the same chapter, identify the words with higher frequencies of occurrence in different course data, and classify these words to obtain chapter key words, knowledge point key words, and specific key words; among them, the chapter key words are the words related to this chapter; the knowledge point key words are the words related to each knowledge point within this chapter, and the specific key words are the words that are not related to this chapter and each knowledge point within the chapter but have a higher frequency of occurrence.

[0029] During the actual teaching process, when the teacher mentions some key knowledge points, the students' concentration in class may change. If student images are collected throughout the entire class, it will lead to a huge computational load for subsequent image processing. In an actual classroom, it is only necessary to focus on some special times for image collection and processing. This application collects and analyzes the teacher's voice information, generates a collection instruction based on the key words in the teacher's voice information, and the collection instruction is an instruction to collect student images in real time, enabling this application to flexibly collect student images according to the teacher's teaching situation, which helps to reduce the computational load.

[0030] The central processing module is also used to expand teaching content through the cloud platform, including: Extracting chapter keywords and knowledge point keywords from the important words in the text; uploading the chapter keywords and knowledge point keywords to the cloud platform; searching for the corresponding chapter content of the chapter keywords and the corresponding knowledge point content of the knowledge point keywords in the cloud platform; the chapter content can be text information, video information, image information, etc. Sending the chapter content and knowledge point content to the teacher terminal for screening to obtain teaching content; sending the teaching content to the student terminal. The screening of the chapter content and knowledge point content to obtain teaching content includes a current affairs mode and a classic mode. The current affairs mode is to sort the chapter content and / or knowledge point content obtained from the cloud platform in the order from the nearest to the farthest in time, and screen out the chapter content and / or knowledge point content with the top rankings. The classic mode is to sort the chapter content and / or knowledge point content obtained from the cloud platform in the order from the most to the least in terms of the number of views and / or content scores, and screen out the chapter content and / or knowledge point content with the top rankings. It can be understood that the top rankings are set by the teacher, and the chapter content and / or knowledge point content ranked first, third, fifth, etc. can be obtained.

[0031] It should be noted that in this embodiment, the teacher can also perform secondary screening on the chapter content and / or knowledge point content with the top rankings to obtain the chapter content and / or knowledge point content finally recognized by the teacher, and then integrate the corresponding chapter content and / or knowledge point content to generate teaching content, which is convenient for selecting the chapter content and / or knowledge point content suitable for the teacher's teaching for recommendation, increasing the fit between this system and the corresponding teacher's teaching. At the same time, this system will record the publishers corresponding to the chapter content and / or knowledge point content for which the teacher performs secondary screening. When expanding teaching content later, the chapter content and / or knowledge point content with the top rankings will be sorted again, and the relevant chapter content and / or knowledge point content of the corresponding publisher will be ranked first, which is convenient for the teacher to perform secondary screening.

[0032] This application obtains chapter content and knowledge point content through a cloud platform, and sends the chapter content and knowledge point content to student terminals as supplementary teaching content, facilitating students to obtain content related to chapter keywords and knowledge point keywords, and thus facilitating students to understand and learn relevant chapters and knowledge points.

[0033] The concentration model is obtained through training with an artificial intelligence model and includes: Obtain a number of student status images and their corresponding concentration scores; the concentration scores are given by professionals based on the student status images. For example, if a student lies down to rest, the concentration is recorded as 0 points. Integrate the student status images and their corresponding concentration scores into a number of training data and a number of test data; among them, the ratio of the number of training data to the number of test data is 7:3. Use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model. Specifically, input the student status images in the test data into the trained artificial intelligence model to obtain the time period concentration score. Compare the time period concentration score with the corresponding concentration score in the test data. When the difference between the two is within the threshold (the threshold is obtained based on experience), no parameter adjustment is required, and the next set of test data is detected; if it is not within the threshold, the corresponding parameters are adjusted until the output time period concentration score is within the threshold of the concentration score, and then the next set of test data is detected. Among them, the corresponding threshold is set based on experience; when the number of test data with the output time period concentration score within the threshold accounts for 90% or more of the total amount of test data, that is, when 90% of the test data passes the detection; a concentration model with student images as input and time period concentration scores as output is obtained; this model supports the multi-input multi-output mode, that is, multiple student images are input simultaneously, and multiple corresponding time period concentration scores can be output simultaneously. Among them, the time period concentration score is denoted as the time period concentration; the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0034] Generate a reminder signal based on the time period concentration of students, including: Obtain the time period concentration corresponding to the student images collected by a number of students under the same collection instruction, and the concentration threshold corresponding to each student. Obtain all students with a concentration less than the corresponding concentration threshold, and mark them as target personnel; mark the time period concentration of the target personnel as SZi, and mark their corresponding concentration threshold as YZi; where i is the number of the target personnel, and i = 1, 2, 3,..., n; n is the total number of target personnel in this collection instruction. The signal value XH corresponding to the current acquisition instruction is calculated by the formula XH = ∑[(YZi - SZi) / YZi]; When the signal value XH is greater than the signal value threshold and not equal to the total number of target personnel; it means that most students are not listening attentively, then an interaction instruction is generated; the signal value threshold is greater than zero and less than the total number of target personnel; When the signal value XH is greater than the signal value threshold and equal to the total number of target personnel; that is, when the time period concentration of multiple students is zero, there will be a situation where the signal value XH is greater than the signal value threshold and equal to the total number of target personnel. This situation means that multiple students are lying down and resting and not attending class. At this time, a rest instruction is generated; the signal value threshold is set by experience, and the value of the signal value threshold is less than the value of the total number of target personnel; When the signal value XH is less than the signal value threshold; it means that a few students are not listening attentively; then a marking information is generated; among them, the reminder signal includes an interaction instruction, a rest instruction, and a marking information; the interaction instruction includes small games and jokes related to the course, etc., which are used for interaction between teachers and students to improve students' concentration; the rest instruction is used to let students rest for a certain period of time to relieve fatigue, which helps to improve the concentration of students in subsequent learning; the marking information is used to mark the corresponding students for subsequent teaching.

[0035] This application generates a reminder signal based on the time period concentration to remind teachers to make reasonable teaching arrangements, thereby improving students' learning efficiency. At the same time, it is convenient for teachers to pay attention to a few students who are not focused in class to solve the problem that the learning effect of a certain knowledge point is poor due to a few students being distracted in class.

[0036] Generate after-class assignments based on the time period concentration of students and the concentration threshold, including: Obtain all key words in this class; extract chapter key words and knowledge point key words from the key words, and divide this class into several teaching time periods according to the chapter key words and knowledge point key words; obtain the time period concentration and the corresponding concentration threshold corresponding to each student in each teaching time period; Judge whether the time period concentration is greater than the concentration threshold; if so, mark the time period assignment of the corresponding student as an examination assignment; if not, mark the time period assignment of the corresponding student as a teaching assignment; among them, the examination assignment includes assignment items; the teaching assignment includes teaching videos and guiding assignments, and the guiding assignment is an assignment question for explaining knowledge points; When the time period assignment of a student is an examination assignment, set the assignment items according to the difference between the time period concentration and the concentration threshold, and adjust the assignment items according to the historical assignment items and historical correct rates of the corresponding student; When the period assignment of a student is a teaching assignment, determine whether the period concentration of the corresponding student is lower than the unlearned threshold. If so, set the teaching assignment of the corresponding student as a teaching video; if not, set the teaching assignment of the corresponding student as a guiding assignment; Integrate all the period assignments of this class to generate after-class assignments.

[0037] It should be noted that in this embodiment, the teaching video information is divided according to teaching periods to generate different period teaching videos, which are integrated to generate teaching videos.

[0038] Set the assignment items according to the difference between the period concentration and the concentration threshold, including: Obtain the period concentration and the concentration threshold; calculate the difference between the period concentration and the concentration threshold; when the difference is less than the medium threshold, set the corresponding assignment type as a simple assignment; when the difference is greater than the medium threshold and less than the high threshold, set the corresponding assignment type as a medium assignment; when the difference is greater than the high threshold, set the corresponding assignment type as a difficult assignment; where the assignment items include assignment type and assignment quantity; the medium threshold and the high threshold are set by experience, and the high threshold is greater than the medium threshold, for example, the medium threshold is 5% of the concentration threshold, and the high threshold is 10% of the concentration threshold, etc.; This application generates assignment items through the student's period concentration and adjusts the assignment items according to the historical correct rate, making the after-class assignments more suitable for the student's current state, facilitating the student to review and strengthen the content of the class. Setting different levels of assignment items according to the student's class state can stimulate the student's learning motivation, avoid problems such as the difficulty of the questions being too high and hitting the student's enthusiasm, and the questions being too simple for the student to conduct in-depth learning.

[0039] Among them, a simple assignment is an assignment that examines knowledge points; a medium assignment is an assignment that examines the expansion of knowledge points; a difficult assignment is an assignment that examines the integration of knowledge points; the assignment type corresponding to the questions can be set according to experience, and the assignment types include simple assignments, medium assignments, and difficult assignments.

[0040] Obtain the historical data of the previous after-class assignment through the database; extract the historical assignment items in the historical data and the historical correct rate corresponding to the historical assignment type in each historical assignment item; When the assignment type in the current left and right items is a simple assignment; determine whether the historical assignment meets the following conditions: The historical assignment items include simple assignments, and the historical correct rate corresponding to the simple assignment is greater than the first upgrade threshold; The historical assignment items include medium assignments, and the historical correct rate corresponding to the medium assignment is greater than the second upgrade threshold; The items in the history homework include difficult homework, and the historical correct rate corresponding to the difficult homework is greater than the upgrade threshold three; When the history homework meets any one of the above three conditions: then upgrade a set number of questions in the current simple homework to medium homework; otherwise, keep the current homework type as simple homework; among them, the set number is set by experience, and the number of homework is set by experience; the set number of questions can be 50% of the number of homework.

[0041] When the homework type in the current left and right items is medium homework; determine whether the history homework meets the following conditions: The history homework items include medium homework, and the historical correct rate corresponding to the medium homework is greater than the upgrade threshold two; The history homework items include difficult homework, and the historical correct rate corresponding to the difficult homework is greater than the upgrade threshold three; When the history homework meets any one of the above two conditions: then upgrade a set number of questions in the current medium homework to difficult homework; among them, the set number of questions can be 30% of the number of homework; otherwise, when the historical correct rate corresponding to the medium homework is less than the upgrade threshold four, then downgrade a set number of questions in the current medium homework to simple homework; among them, the set number of questions can be 30% of the number of homework.

[0042] When the history homework includes difficult homework, and the historical correct rate corresponding to the difficult homework is lower than the upgrade threshold five; then downgrade a set number of questions in the current difficult homework to medium homework; among them, the set number of questions can be 50% of the number of homework.

[0043] Specifically, the upgrade threshold one, upgrade threshold two, upgrade threshold three, upgrade threshold four, and upgrade threshold five are all set by experience; and the upgrade threshold one is greater than the upgrade threshold two, and the upgrade threshold two is greater than the upgrade threshold three; the upgrade threshold five is less than the upgrade threshold four; for example, the upgrade threshold one can be set to 90%, the upgrade threshold two to 80%, and the upgrade threshold three to 60%; the upgrade threshold four to 20%, and the upgrade threshold five to 10%; It should be noted that in this embodiment, obtaining the time period concentration corresponding to any student in each time period includes: Obtain the duration of each teaching time period, set an interception instruction according to the duration, and intercept the student image of the corresponding student in the video information according to the interception instruction; Input the student image into the concentration model to obtain the concentration corresponding to the corresponding student; number the corresponding concentration in the chronological order of the interception instruction, and mark the numbered concentration as ZZj; where j is the number, and j = 1, 2, 3,..., m The period concentration DZ is calculated by the formula DZ = ∑(αj × ZZj); where j = 1, 2, 3, …, m; m is the total number of serial numbers for numbering the corresponding concentration according to the time sequence of the interception instructions; αj is the weight coefficient; αj = j / ∑(j).

[0044] Specifically, according to the duration, interception instructions can be set. The duration can be divided into several interception periods, and an interception instruction is generated at the end of each interception period. For example, if the duration of a teaching period is 10 minutes, it is divided into 10 interception periods with a duration of 1 minute each. An interception instruction is generated at the last second of the first minute, the last second of the second minute,..., and the last second of the tenth minute of the corresponding teaching period; In this embodiment, 3 interception instructions are generated within a certain teaching period. The concentration ZZ1 corresponding to the first interception instruction is 69, the concentration ZZ2 corresponding to the second interception instruction is 60, and the concentration ZZ3 corresponding to the third interception instruction is 64; the period concentration DZ = 63.5 is calculated by the formula DZ = ∑(αj × ZZj).

[0045] The period concentration can also be generated according to the teacher's voice information in this embodiment, including: Obtain several segments of the teacher's voice information during the entire teaching period, and generate interception instructions according to the teacher's voice information; intercept the student images of the corresponding students in the video information according to the interception instructions; Input the student images into the concentration model to obtain the concentration corresponding to the corresponding students; number the corresponding concentrations according to the time sequence of the interception instructions or according to the duration of the teacher's voice information, and mark the numbered concentrations as ZZk; where k is the serial number; generate the period concentration according to the duration and characteristic words of the teacher's voice information, and the concentration; The period concentration DZ is calculated by the formula DZ = ∑(βk × ZZk); where k = 1, 2, 3, …, q; q is the total number of the serial number k; βk is the weight coefficient; Obtain the marked duration of the teacher's voice information as YSk; convert each segment of the teacher's voice information into text information, obtain and count the number of characteristic words in the text information and mark it as TSk; calculate the weight coefficient βk of the serial number k by the formula βk = γ1 × YSk / ∑(YSk) + γ2 × TSk / ∑(TSk); where k = 1, 2, 3, …, q; γ1 and γ2 are weight coefficients set by experience; In this embodiment, γ1 = 0.4 and γ2 = 0.6 are set. During a certain teaching period, 3 interception instructions are generated according to the teacher's voice information. The voice duration YS1 corresponding to the first interception instruction is 5 minutes, and the number of characteristic words TSk is 4. The voice duration YS1 corresponding to the second interception instruction is 10 minutes, and the number of characteristic words TSk is 5. The voice duration YS1 corresponding to the first interception instruction is 6 minutes, and the number of characteristic words TSk is 2. The concentration degree ZZ1 corresponding to the first interception instruction is 69. The concentration degree ZZ2 corresponding to the second interception instruction is 60. The concentration degree ZZ3 corresponding to the third interception instruction is 64. The period concentration degree DZ ≈ 63.71 is calculated by the formula DZ = ∑(βk × ZZk).

[0046] The concentration threshold is comprehensively determined by the difficulty of the teaching subject, the teaching quality of the teaching teacher, and the concentration degree of the students, including: The teaching quality score of each teacher is obtained through the cloud platform and marked as JS. The difficulty score of the teaching subject is obtained and marked as KM. The mode of several historical concentration degrees corresponding to the teaching subject with the highest exam score of the student is obtained from the database and marked as the standard concentration degree BZ. The standard concentration degree can be understood as the most suitable concentration degree, and it can be understood that the student has the highest learning efficiency when using this concentration degree. The difficulty score of the teaching subject with the highest exam score of the student is marked as BK. The teaching quality score of the teaching teacher corresponding to the subject is marked as BJ. The concentration threshold ZY of the corresponding student under the teaching of the corresponding teacher in the corresponding teaching subject is calculated by the formula ZY = [α1 × exp((JS - BJ) / MJ) + α2 × exp((KM - BK) / MK)] × BZ. Where MJ is the full score of the teaching quality score. The higher the teaching quality score, the higher the teaching level of the teacher, and the higher the concentration degree of the students in class. MK is the full score of the difficulty score of the teaching subject. The higher the difficulty score of the teaching subject, the greater the learning difficulty of the corresponding teaching subject, and the higher the concentration degree required by the students. α1 and α2 are weight coefficients.

[0047] In this embodiment, the full score MJ of the teaching quality score is set to 100. The full score MK of the difficulty score of the teaching subject is set to 100. α1 = 0.6 and α2 = 0.4. The value ranges of the teaching quality score and the teaching difficulty score are both from 0 to 100. The standard concentration degree BZ = 80 corresponding to the teaching subject with the highest exam score of a certain student is obtained. The corresponding teaching subject is mathematics, the corresponding difficulty score BK = 70, and the teaching quality score BJ = 70 of the corresponding teaching teacher. The teaching subject the student is taking is physics, and the difficulty rating KM corresponding to the teaching subject is 85, and the teaching quality rating JS of the teacher in class is 80; The corresponding focus threshold ZY≈90.22 of the corresponding student under the teaching of the corresponding teacher in the teaching subject of physics is calculated by the formula ZY = [α1×exp((JS - BJ) / MJ)+α2×exp((KM - BK) / MK)]×BZ.

[0048] The central processing module is also used to determine whether a student has an abnormality through the time period focus, including: Obtain the time period focus and determine whether the time period focus is less than the abnormal focus threshold; the abnormal focus threshold is set by experience, such as 5% of the focus threshold of the corresponding student; If so, increment the abnormal parameter by one. When the abnormal parameter is greater than the abnormal parameter threshold, generate an abnormal instruction and send it to the teacher terminal; where the abnormal parameter represents the number of times the time period focus is continuously less than the abnormal focus threshold; the abnormal parameter threshold is set as a positive integer by experience and can be 3; otherwise, continue to determine whether the next time period focus is less than the focus threshold; If not, clear the abnormal parameter; continue to determine whether the next time period focus is less than the focus threshold.

[0049] In the actual teaching process, there are some students who are not good at communicating, have physical problems or are in a low mood during class, and the teacher cannot know in time; and the physical problems of the students will affect the students' concentration in listening to the class; this application determines whether a student is abnormal through the number of abnormalities in the student's time period focus, and generates an abnormal instruction in time to remind the teacher to pay attention to the student's status; it is convenient to establish a good relationship between the teacher and the student.

[0050] The central processing module is also used to generate reinforcement homework, including: Obtain the special example questions explained by the teacher in class, find the questions similar to the special example questions in the database, and divide them into simple questions, medium questions and difficult questions according to the correct rate; and according to the homework type in the student's homework items, extract a set number and type of questions from them to generate reinforcement homework; specifically, if the homework type in the homework item is simple homework, extract a set number of questions from the simple questions as reinforcement homework; if the homework type in the homework item is medium homework, extract a set number of questions from the medium questions as reinforcement homework; if the homework type in the homework item is difficult homework, extract a set number of questions from the difficult questions as reinforcement homework; it is also possible to adjust the question type of the reinforcement homework according to the student's historical homework items and historical correct rate, and the specific method is the same as the method of adjusting the homework items according to the student's historical homework items and historical correct rate.

[0051] The second aspect of the present application provides an interactive teaching management method for a smart classroom, including the following steps: Step 1: Obtain teacher voice information and generate a collection instruction based on the teacher voice information; Step 2: Collect student images according to the collection instruction; Step 3: Input the student images into the concentration model to obtain the period concentration of the students; Step 4: Generate a reminder signal based on the period concentration and the concentration threshold; Step 5: Generate after-class assignments based on the period concentration and the concentration threshold.

[0052] Some of the data in the above formula is the numerical value obtained after removing the dimension. The formula is a formula that is closest to the actual situation obtained through software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0053] The working principle of the present application: In this embodiment, by obtaining teacher voice information, generating a collection instruction based on the teacher voice information, and collecting student images according to the collection instruction; inputting the student images into the concentration model to obtain the period concentration of the students; comprehensively setting the concentration threshold according to the difficulty of the teaching subject, the teaching quality of the teaching teacher, and the concentration of the students; generating a reminder signal based on the period concentration and the concentration threshold; generating after-class assignments based on the period concentration and the concentration threshold; it is possible to set corresponding types of questions according to the listening status of students for different knowledge points during class, which is more suitable for the learning situation of students, so that students can have learning resources suitable for themselves.

[0054] The above embodiments are only used to illustrate the technical method of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present application.

Claims

1. Interactive teaching management system for smart classrooms, characterized in that, Including: A central processing module, a data acquisition module connected to the central processing module, a display control terminal, and a database; Among them, the data acquisition module: obtains teacher voice information, video information, and student images through data acquisition devices; The central processing module: is used to obtain teacher voice information, generate acquisition instructions based on the teacher voice information; acquire student images according to the acquisition instructions, input the student images into the concentration model to obtain the time period concentration of the students; generate reminder signals and after-class assignments based on the time period concentration and the concentration threshold; among them, the concentration model is obtained through training of an artificial intelligence model; The display control terminal includes a teacher terminal and a student terminal; among them, the teacher terminal is used to display the class status of the students; the student terminal is used to display the teaching content of the teacher; The database: is used to store historical data, teaching content, and student status.

2. The interactive teaching management system for an intelligent classroom according to claim 1, wherein The generating of the acquisition instructions based on the teacher voice information includes: Obtaining the teacher voice information in real time, and converting the teacher voice information into text information; Detecting whether key words appear in the text information; If yes, generate text key words according to the text information, and at the same time generate acquisition instructions; If no, continuously obtain the teacher voice information, convert the teacher voice information into text information, and detect the text information; among them, the key words include chapter key words, knowledge point key words, and specific key words.

3. The interactive teaching management system for a smart classroom according to claim 2, wherein, The central processing module is also used to expand teaching content through a cloud platform, including: Extracting chapter key words and knowledge point key words from the text key words; Searching for corresponding chapter content and knowledge point content in the cloud platform; Sending the chapter content and knowledge point content to the teacher terminal for screening to obtain teaching content; Sending the teaching content to the student terminal.

4. The interactive teaching management system for a smart classroom according to claim 1, characterized in that, The concentration model is obtained through training of an artificial intelligence model, including: Obtaining a number of student status images, and the concentration scores respectively corresponding to each student status image; Integrating the student status images and the concentration scores corresponding to the student status images into training data and test data; using the training data to train the artificial intelligence model; using the test data to test the trained artificial intelligence model, when the test data passing the detection reaches 90%; obtaining a concentration model with the input being the student image and the output being the time period concentration score; among them, the time period concentration score is recorded as the time period concentration; the artificial intelligence model includes a BP neural network model or an RBF neural network model.

5. The interactive teaching management system for a smart classroom according to claim 1, wherein The reminder signals include interaction instructions, rest instructions, and marking information; Generating the reminder signals based on the time period concentration and the concentration threshold includes: Obtaining the time period concentration corresponding to the student images collected by a number of students under the same acquisition instruction, and the concentration threshold corresponding to each student; Marking all students with a time period concentration less than the corresponding concentration threshold as target persons; marking the time period concentration of the target persons as SZi, and marking the corresponding concentration threshold as YZi; where i is the number of the target person, and i = 1, 2, 3,..., n; n is the total number of target persons in this acquisition instruction; The signal value XH corresponding to the current acquisition instruction is calculated by the formula XH = ∑[(YZi - SZi) / YZi]; When the signal value XH is greater than the signal value threshold and not equal to the total number of target personnel, an interaction instruction is generated; When the signal value XH is greater than the signal value threshold and equal to the total number of target personnel, a rest instruction is generated; When the signal value XH is less than the signal value threshold, a marking information is generated; wherein, the interaction instruction includes small games and jokes related to the course.

6. The interactive teaching management system of the smart classroom according to claim 1, characterized in that The after-class assignment is generated based on the period concentration and the concentration threshold, including: Obtain all the key words in this class; extract the chapter key words and knowledge point key words in the key words; divide this class into several teaching periods according to the chapter key words and knowledge point key words; obtain the period concentration and the corresponding concentration threshold corresponding to each student in each teaching period; Judge whether the period concentration is greater than the concentration threshold; if so, mark the period assignment of the corresponding student as an examination assignment; otherwise, mark the period assignment of the corresponding student as a teaching assignment; wherein, the examination assignment includes assignment items; the teaching assignment includes teaching videos and guiding assignments; Integrate all the period assignments in this class to generate the after-class assignment.

7. The interactive teaching management system for an intelligent classroom according to claim 6, characterized in that, The assignment items are set according to the difference between the period concentration and the concentration threshold, including: Obtain the period concentration and the concentration threshold; calculate the difference between the period concentration and the concentration threshold; when the difference is less than the medium threshold, set the assignment type as a simple assignment; when the difference is greater than the medium threshold and less than the high threshold, set the assignment type as a medium assignment; when the difference is greater than the high threshold, set the assignment type as a difficult assignment; wherein, the assignment items include the assignment type and the number of assignments; the high threshold is greater than the medium threshold.

8. The interactive teaching management system for a smart classroom according to claim 6, wherein, The concentration threshold is comprehensively determined by the teaching subject, the teaching teacher and the students, including: Obtain the teaching quality scores of each teacher through the cloud platform and mark them as JS; obtain the difficulty score of the teaching subject and mark it as KM; The database obtains the mode of several historical concentrations corresponding to the teaching subject with the highest exam score of the student, and records it as the standard concentration and marks it as BZ; marks the difficulty score of the teaching subject with the highest exam score of the student as BK; marks the teaching quality score of the teaching teacher of the corresponding subject as BJ; The concentration threshold ZY of the corresponding student under the teaching of the corresponding teacher in the corresponding teaching subject is calculated by the formula ZY = [α1×exp((JS - BJ) / MJ) + α2×exp((KM - BK) / MK)]×BZ; wherein, MJ is the full score of the teaching quality score; MK is the full score of the difficulty score of the teaching subject; α1 and α2 are weight coefficients.

9. The interactive teaching management system for a smart classroom according to claim 1, characterized in that, The central processing module is also used to judge whether a student has an abnormality through the period concentration, including: Obtain the period concentration and judge whether the period concentration is less than the abnormal concentration threshold; If so, increment the exception parameter. When the exception parameter is greater than the exception parameter threshold, where the exception parameter represents the number of consecutive times the period concentration is less than the exception concentration threshold; the exception parameter threshold is a set positive integer; then generate an exception instruction and send it to the teacher terminal; otherwise, continue to determine whether the concentration in the next period is less than the concentration threshold. If not, reset the exception parameter to zero; continue to determine whether the concentration in the next period is less than the concentration threshold.

10. The interactive teaching management method for a smart classroom operates based on the interactive teaching management system for a smart classroom described in any one of claims 1 to 9, and is characterized in that, It includes the following steps: Step 1: Obtain the teacher's voice information and generate a collection instruction according to the teacher's voice information. Step 2: Collect the student's image according to the collection instruction. Step 3: Input the student's image into the concentration model to obtain the student's period concentration. Step 4: Generate a reminder signal according to the period concentration and the concentration threshold. Step 5: Generate after-class homework based on the period concentration and the concentration threshold.

Images