CN113919987A - Vocational education network teaching system based on artificial intelligence - Google Patents

Vocational education network teaching system based on artificial intelligence Download PDF

Info

Publication number
CN113919987A
CN113919987A CN202111227662.9A CN202111227662A CN113919987A CN 113919987 A CN113919987 A CN 113919987A CN 202111227662 A CN202111227662 A CN 202111227662A CN 113919987 A CN113919987 A CN 113919987A
Authority
CN
China
Prior art keywords
student
module
students
value
questions
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202111227662.9A
Other languages
Chinese (zh)
Inventor
高馨
徐会友
陈小青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202111227662.9A priority Critical patent/CN113919987A/en
Publication of CN113919987A publication Critical patent/CN113919987A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
    • G09B5/10—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations all student stations being capable of presenting the same information simultaneously
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
    • G09B5/14—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations with provision for individual teacher-student communication

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an artificial intelligence-based network teaching system for vocational education, and relates to the technical field of network teaching; the system comprises a class distribution module, an image acquisition module, a data analysis module, a live broadcast teaching module and a processor; the class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning, so that the purpose of teaching according to the factors is realized, and the teaching quality is improved; the image acquisition module is used for shooting the learning condition of the student through a camera of the network control student end after the authentication is successful, and acquiring real-time video information of the student; the data analysis module is used for receiving the real-time video information and analyzing the real-time video information to obtain attendance information and a vague value of the student and prompt the student to take class seriously in time; the live broadcast teaching module is used for synchronizing live broadcast video data of the teacher end to the student end; the invention can avoid repeated uploading of the same problem, improve the answering efficiency, strengthen the interaction with students and further improve the teaching quality.

Description

Vocational education network teaching system based on artificial intelligence
Technical Field
The invention relates to the technical field of network teaching, in particular to an artificial intelligence-based network teaching system for vocational education.
Background
The network education is one of adult education calendars, is a teaching mode using transmission media such as televisions, internet and the like, breaks through the boundary of time and space, and is different from the traditional teaching mode of lodging in schools. Students using this teaching mode are typically amateur repairmers; the student can attend classes anytime and anywhere because the student does not need to attend classes at a specific place. Students can also learn with the help of different channels such as TV broadcasting, Internet, tutoring special line, lesson and research society, and face-to-face (letter) etc. The method is a new concept generated after the modern information technology is applied to education, namely education developed by using network technology and environment. The student-attracting object is not limited by age and previous scholars, and the opportunity of promoting the scholars is provided for broad masses who step into the society.
The existing network teaching management system basically provides recorded and broadcast videos, teachers record and upload the videos in advance, students download the videos or watch the videos online for learning, and the teachers are not reasonably distributed according to knowledge base of the students, so that the purpose of teaching according to the factors is realized; moreover, all students cannot learn on time, and the opportunities of asking questions and answering questions cannot be given to the students, so that the network teaching mode is very inconvenient for teachers and students, and is not favorable for providing a good learning platform for the students.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an artificial intelligence-based network teaching system for vocational education.
The purpose of the invention can be realized by the following technical scheme: an artificial intelligence-based network teaching system for vocational education comprises a class distribution module, an authentication module, an image acquisition module, a data analysis module, a live broadcast teaching module, a recorded broadcast module, a courseware on-demand module, a processor and a database;
the class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning; the authentication module is used for verifying login requests of a teacher end and a student end; the authentication mode is fingerprint identification;
the image acquisition module is used for controlling the camera of the student end to shoot the learning condition of the student through a network after the authentication is successful, and acquiring real-time video information of the student; sending the real-time video information to a data analysis module; the data analysis module is used for receiving real-time video information and analyzing the real-time video information, and comprises the following specific steps:
v1: processing the real-time video information to obtain student face image information, and matching the captured face image information with standard student face image information stored in a database; obtaining attendance information of students;
v2: judging the disappearance time of facial image information; when the disappearance time of the facial image information of the student is greater than a preset time value T1, judging that the student is in a vague state;
counting the times of the student in the vague state and marking as vague frequency C1; accumulating the time of the student in the vague state to form a vague total duration, and marking as C2;
obtaining the vague value ZS of the student by using the formula ZS as C1 × a3+ C2 × a 4; wherein a3 and a4 are proportionality coefficients;
comparing the vague nerve value ZS with a vague nerve threshold;
if the vague value ZS is larger than the vague threshold value, generating a reminding signal; simultaneously marking the corresponding student end as a reminding terminal;
the data analysis module is used for sending a reminding signal and a reminding terminal to the processor, and the processor is used for sending the reminding signal and the reminding terminal to the reminding module and driving and controlling the reminding module to send reminding information to the reminding terminal;
the live broadcast teaching module is used for synchronizing live broadcast video data of the teacher end to the student end.
Further, the specific working steps of the class assignment module are as follows:
the method comprises the following steps: students log in a teaching platform by inputting account numbers and passwords through student terminals, and complete personal information is required to be input when the students log in for the first time; the personal information comprises a name, an identification card number, an age, an address and a study calendar;
step two: the class distribution module performs score verification according to personal information input by students; the method specifically comprises the following steps:
s21: the class distribution module is used for distributing corresponding examination questions according to the study calendar input by the students;
s22: the students answer the questions according to the examination questions issued by the class allocation module and send the answers to the class allocation module; the class distribution module is used for matching answers of students with examination question standard answers; obtaining the score of the student;
step three: the class allocation module performs class allocation according to the scores of the students and assigns corresponding teachers to perform online teaching; the teacher logs in the teaching platform through a teacher end; the method specifically comprises the following steps:
s31: marking the examination question score corresponding to the student as K1; wherein the examination questions are divided into 100 points;
s32: acquiring student's academic information, dividing the academic information into five grades of high school, special subject, basic subject, master and doctor, and setting a corresponding grade value for each academic grade; matching the student's academic calendar information with all the academic calendar grades to obtain corresponding grade values, and marking the grade values as K2; wherein the grade value corresponding to the high school < the grade value corresponding to the special department < the grade value corresponding to the present department < the grade value corresponding to the master < the grade value corresponding to the doctor;
s33: using the formula ZK ═ K (K1 × a1+ K2 × a2)(a1+a2)Acquiring a comprehensive score ZK corresponding to the student; wherein a1 and a2 are proportionality coefficients;
s34: comparing the composite score ZK to a score threshold; the scoring thresholds include P1, P2; wherein P1 and P2 are preset values, and P1 is more than P2;
if ZK > P2, assigning the student to a senior class;
if the ZK is more than P1 and less than or equal to P2, the student is assigned to the middle class;
if ZK ≦ P1, the student is assigned to the primary class.
Further, the attendance information comprises attendance normal and attendance abnormal; the method specifically comprises the following steps:
if the captured facial image information is matched with the standard facial image information of the students stored in the database; the student normally attendance;
and if the captured facial image information is not matched with the standard facial image information of the students stored in the database, the students are abnormal in attendance.
Furthermore, the data analysis module is used for sending attendance information and the vague value ZS of the student to the processor, and the processor is used for fusing the attendance information and the vague value ZS of the student and stamping a timestamp to form an attendance record of the student and sending the attendance record of the student to the database for storage.
Furthermore, the live broadcast teaching module comprises an authority setting unit and a student questioning unit; the authority setting unit is used for granting the student end question asking authority; the student questioning unit is used for receiving the questions edited and uploaded by the student end and sending the corresponding questions to the teacher end; the method comprises the following specific steps:
q1: after a teacher live broadcasts and teaches for a period of time, the teacher grants the student end with question asking authority through the authority setting unit; the method specifically comprises the following steps:
marking the moment when the authority setting unit grants the questioning authority to the student end as the authority granting moment;
calculating the time difference between the permission granting moment and the current time of the system to obtain permission granting duration, and marking the permission granting duration as QT;
when the authority granting duration QT reaches the granting duration threshold, the authority setting unit closes the student end questioning authority;
q2: after the student side is granted with the questioning authority, the student edits and uploads the questions through the student side, and the questions edited and uploaded by the student side are audited and filtered by the student questioning unit and then transmitted to the teacher side; the method comprises the following specific steps:
q21: extracting keywords of all uploaded problems, and when the keyword coincidence degree of the two uploaded problems is larger than or equal to a preset coincidence degree lambda%, considering the two uploaded problems as the same problem; wherein lambda is a preset value;
q22: performing a preferred value analysis on the uploaded problems which are considered to be the same problem; selecting the problem with the largest preferred value as a selected problem; the method specifically comprises the following steps:
q221: acquiring students who upload problems and marking the students as uploading students; marking the vague value of the uploading student in the live broadcasting teaching process as L1;
marking the number of times of the student end uploading problems corresponding to the uploading students as L2;
q222: evaluating the richness of the question content to obtain a richness value L3;
q223: obtaining a preferred value YQ of the corresponding problem by using a formula YQ (L2 × b1+ L3 × b2)/(L1 × b3), wherein b1, b2 and b3 are all proportional coefficients;
q224: selecting the problem with the largest preferred value as a selected problem;
q23: counting the number of questions considered as the same question and marking as the number of questions of the selected question; marking the number of questioners selecting the question as R1;
using the formula DT ═ YQ × b4+ R1 × b5(b4+b5)Obtaining an effect-increasing value DT of the selected problem; wherein b4 and b5 are proportionality coefficients;
q24: sorting the selected problems according to the size of the extraction value DT; transmitting the selected problems in the top five ranks to a teacher end through a processor according to the sequence of the selected problems;
q3: after the teacher end receives the selected questions, the teacher answers the selected questions in sequence.
Furthermore, the recording and playing module is used for synchronously recording the live broadcast teaching of the teacher by the teaching platform; after the live broadcasting teaching is finished, the recorded broadcast video is transmitted to a courseware on-demand module by the recorded broadcast module; the student calls out the recorded and broadcast video for watching through the courseware on-demand module.
Further, in the step Q222, the richness of the question content is evaluated, so as to obtain a richness value L3; the method comprises the following specific steps:
DD 1: acquiring corresponding pictures and character descriptions in the question content;
if the problem content includes a picture, making Pc equal to 1, and if the problem content does not include a picture, making Pc equal to 0; if the question content contains the word description, setting Wc to 1, and if the question content does not contain the word description, setting Wc to 0;
DD 2: marking the number of pictures in the question content as Ps, and marking the text size of the character description as Ws;
DD 3: the richness value L3 of the question content is obtained by using the formula L3 ═ Pc + Wc) × (Ps × d1+ Ws × d2), where d1 and d2 are both proportionality coefficients.
The invention has the beneficial effects that:
1. the class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning; students log in a teaching platform by inputting account numbers and passwords through student terminals, and a class distribution module issues corresponding examination questions according to the students' input study calendar; the students answer the questions to obtain scores of the students; combining the scores and the grade values corresponding to the academic calendars to obtain corresponding comprehensive scores; the class allocation module performs class allocation according to the comprehensive scores corresponding to the students and assigns corresponding teachers to perform online teaching, so that the purpose of teaching according to the material is realized, and the teaching quality is improved;
2. the data analysis module is used for receiving the real-time video information and analyzing the real-time video information; acquiring facial image information of students, and matching the captured facial image information with standard facial image information of the students stored in a database to acquire attendance information of the students; judging the disappearance time of facial image information; combining the vagal frequency and the total vagal duration to obtain a vagal value of the student; if the vague value ZS is larger than the vague threshold, the processor drives and controls the reminding module to send reminding information to the student terminal to remind the student of attending classes seriously; meanwhile, the attendance information of the students and the vague value ZS are fused to form attendance records of the students, and the attendance records of the students are sent to a database to be stored; a teacher can log in a teaching platform to inquire attendance records of students from a database;
3. the live broadcast teaching module is used for synchronizing live broadcast video data of the teacher end to the student end; after a teacher live broadcasts and teaches for a period of time, the teacher grants the student end with question asking authority through the authority setting unit; after the student side is granted with the questioning authority, the student edits and uploads the questions through the student side, the questions edited and uploaded by the student side are audited and filtered through the student questioning unit, and the uploaded questions which are considered to be the same question are subjected to optimal value analysis; selecting the problem with the largest preferred value as a selected problem; repeated uploading of the same problem is avoided, and the answering efficiency is improved; then sorting the selected problems according to the size of the extraction value DT; transmitting the selected problems in the top five ranks to a teacher end through a processor according to the sequence of the selected problems; after the teacher receives the selected questions, the teacher answers the selected questions in sequence, the answering efficiency is improved, interaction between the teacher and the students is enhanced, and therefore teaching quality is improved.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a block diagram of the system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an artificial intelligence-based network teaching system for vocational education comprises a class assignment module, an authentication module, an image acquisition module, a data analysis module, a live broadcast teaching module, a recorded broadcast module, a courseware on-demand module, a processor and a database;
the class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning; the method comprises the following specific steps:
the method comprises the following steps: students log in a teaching platform by inputting account numbers and passwords through student terminals, and complete personal information is required to be input when the students log in for the first time; the personal information comprises name, identification card number, age, address and academic calendar;
step two: the class distribution module performs score verification according to personal information input by students; the method specifically comprises the following steps:
s21: the class distribution module is used for distributing corresponding examination questions according to the study calendar input by the students;
s22: the students answer the questions according to the examination questions issued by the class allocation module and send the answers to the class allocation module; the class distribution module is used for matching the answers of the students with the examination question standard answers; obtaining the score of the student;
step three: the class allocation module performs class allocation according to the scores of the students and assigns corresponding teachers to perform online teaching; a teacher logs in a teaching platform through a teacher end; the method specifically comprises the following steps:
s31: marking the examination question score corresponding to the student as K1; wherein the examination questions are divided into 100 points;
s32: acquiring student's academic information, dividing the academic information into five grades of high school, special subject, basic subject, master and doctor, and setting a corresponding grade value for each academic grade; matching the student's academic calendar information with all the academic calendar grades to obtain corresponding grade values, and marking the grade values as K2; wherein the grade value corresponding to the high school < the grade value corresponding to the special department < the grade value corresponding to the present department < the grade value corresponding to the master < the grade value corresponding to the doctor;
s33: using the formula ZK ═ K (K1 × a1+ K2 × a2)(a1+a2)Acquiring a comprehensive score ZK corresponding to the student; wherein a1 and a2 are proportionality coefficients; for example, a1 takes on the value 0.57, a2 takes on the value 0.98;
s34: comparing the composite score ZK to a score threshold; scoring thresholds include P1, P2; wherein P1 and P2 are preset values, and P1 is more than P2;
if ZK > P2, assigning the student to a senior class;
if the ZK is more than P1 and less than or equal to P2, the student is assigned to the middle class;
if ZK is less than or equal to P1, the student is assigned to the primary class;
the authentication module is used for verifying login requests of the teacher end and the student end; the authentication mode is fingerprint identification;
the image acquisition module is used for shooting the learning condition of the student through a camera of the network control student end after the authentication is successful, and acquiring real-time video information of the student; sending the real-time video information to a data analysis module; the data analysis module is used for receiving the real-time video information and making analysis, and comprises the following specific steps:
v1: processing the real-time video information to obtain student face image information, and matching the captured face image information with standard student face image information stored in a database; obtaining attendance information of students; attendance information comprises attendance normal and attendance abnormal; the method specifically comprises the following steps:
if the captured facial image information is matched with the standard facial image information of the students stored in the database; the student normally attendance;
if the captured facial image information is not matched with the standard facial image information of the students stored in the database, the students are abnormal in attendance;
v2: judging the disappearance time of facial image information; when the disappearance time of the facial image information of the student is greater than a preset time value T1, judging that the student is in a vague state;
counting the times of the student in the vague state and marking as vague frequency C1; accumulating the time of the student in the vague state to form a vague total duration, and marking as C2;
obtaining the vague value ZS of the student by using the formula ZS as C1 × a3+ C2 × a 4; wherein a3 and a4 are proportionality coefficients; for example, a3 takes on a value of 0.11, a4 takes on a value of 0.38;
comparing the vague nerve value ZS with a vague nerve threshold;
if the vague value ZS is larger than the vague threshold value, generating a reminding signal; simultaneously marking the corresponding student end as a reminding terminal;
the data analysis module is used for sending the reminding signal and the reminding terminal to the processor, and the processor is used for sending the reminding signal and the reminding terminal to the reminding module and driving and controlling the reminding module to send reminding information to the reminding terminal so as to remind students to attend classes seriously;
the data analysis module is used for sending attendance information and the vague value ZS of the student to the processor, and the processor is used for fusing the attendance information and the vague value ZS of the student, stamping a timestamp to form attendance records of the student and sending the attendance records of the student to the database for storage; a teacher can log in a teaching platform to inquire attendance records of students from a database;
the live broadcast teaching module is used for synchronizing live broadcast video data of the teacher end to the student end; the live broadcast teaching module comprises an authority setting unit and a student questioning unit; the authority setting unit is used for granting the student end with question asking authority; the student questioning unit is used for receiving the questions edited and uploaded by the student end and sending the corresponding questions to the teacher end; the method comprises the following specific steps:
q1: after a teacher live broadcasts and teaches for a period of time, the teacher grants the student end with question asking authority through the authority setting unit; the method specifically comprises the following steps:
marking the moment when the authority setting unit grants the questioning authority to the student end as the authority granting moment;
calculating the time difference between the permission granting moment and the current time of the system to obtain permission granting duration, and marking the permission granting duration as QT;
when the authority granting duration QT reaches the granting duration threshold, the authority setting unit closes the student end questioning authority;
q2: after the student side is granted with the questioning authority, the student edits and uploads the questions through the student side, and the questions edited and uploaded by the student side are audited and filtered by the student questioning unit and then transmitted to the teacher side; repeated uploading of the same problem is avoided, and the answering efficiency is improved; the method comprises the following specific steps:
q21: extracting keywords of all uploaded problems, and when the keyword coincidence degree of the two uploaded problems is larger than or equal to a preset coincidence degree lambda%, considering the two uploaded problems as the same problem; wherein lambda is a preset value; for example, λ takes the value 95;
q22: performing a preferred value analysis on the uploaded problems which are considered to be the same problem; selecting the problem with the largest preferred value as a selected problem; the method specifically comprises the following steps:
q221: acquiring students who upload problems and marking the students as uploading students; marking the vague value of the uploading student in the live broadcasting teaching process as L1;
marking the number of times of the student end uploading problems corresponding to the uploading students as L2;
q222: evaluating the richness of the question content to obtain a richness value L3;
q223: obtaining a preferred value YQ of the corresponding problem by using a formula YQ (L2 × b1+ L3 × b2)/(L1 × b3), wherein b1, b2 and b3 are all proportional coefficients; for example, b1 takes the value of 0.22, b2 takes the value of 0.51, and b3 takes the value of 0.63; the more serious the student who uploads the question gets on class, the more the number of questions asked and the more detailed the question description, the greater the preference value of the corresponding question, i.e. the greater the possibility that the question is answered by the teacher, and meanwhile, the student is encouraged to take class seriously and ask questions actively;
q224: selecting the problem with the largest preferred value as a selected problem;
q23: counting the number of questions considered as the same question and marking as the number of questions of the selected question; for example: when five uploaded questions are regarded as the same question, the number of the questions to be asked is five; marking the number of questioners selecting the question as R1;
using the formula DT ═ YQ × b4+ R1 × b5(b4+b5)Obtaining an effect-increasing value DT of the selected problem; wherein b4 and b5 are proportionality coefficients; for example, b4 takes the value 0.33, b5 takes the value 0.58;
q24: sorting the selected problems according to the size of the extraction value DT; transmitting the selected problems in the top five ranks to a teacher end through a processor according to the sequence of the selected problems;
q3: after the teacher receives the selected questions, the teacher answers the selected questions in sequence, so that the answering efficiency is improved, and the interaction between the teacher and the students is enhanced, so that the teaching quality is improved;
the recording and broadcasting module is used for synchronously recording the live broadcasting teaching of the teacher by the teaching platform; after the live broadcasting teaching is finished, the recorded broadcast video is transmitted to a courseware on-demand module by the recorded broadcast module; the students call the recorded and broadcast video out for watching through the courseware on-demand module, review is carried out, and course understanding is enhanced;
evaluating the richness of the question content in the step Q222 to obtain a richness value L3; the method comprises the following specific steps:
DD 1: acquiring corresponding pictures and character descriptions in the question content;
if the problem content includes a picture, making Pc equal to 1, and if the problem content does not include a picture, making Pc equal to 0; if the question content contains the word description, setting Wc to 1, and if the question content does not contain the word description, setting Wc to 0;
DD 2: marking the number of pictures in the question content as Ps, and marking the text size of the character description as Ws;
DD 3: obtaining a richness value L3 of the question content by using a formula L3 ═ Pc + Wc) × (Ps × d1+ Ws × d2), wherein d1 and d2 are proportionality coefficients; for example, d1 takes on a value of 0.44 and d2 takes on a value of 0.58.
The working principle of the invention is as follows:
when the network teaching system works, a class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning; students log in a teaching platform by inputting account numbers and passwords through student terminals, and a class distribution module issues corresponding examination questions according to the students' input study calendar; the students answer the questions to obtain scores of the students; combining the scores and the grade values corresponding to the academic calendars to obtain corresponding comprehensive scores; the class allocation module performs class allocation according to the comprehensive scores corresponding to the students and assigns corresponding teachers to perform online teaching, so that the purpose of teaching according to the material is realized, and the teaching quality is improved;
the authentication module is used for verifying login requests of the teacher end and the student end; after the authentication is successful, the image acquisition module controls a camera at the student end to shoot the learning condition of the student through a network, and real-time video information of the student is obtained; the data analysis module is used for receiving the real-time video information and analyzing the real-time video information; acquiring facial image information of students, and matching the captured facial image information with standard facial image information of the students stored in a database to acquire attendance information of the students; judging the disappearance time of facial image information; combining the vagal frequency and the total vagal duration to obtain a vagal value of the student; if the vague value ZS is larger than the vague threshold, the processor drives and controls the reminding module to send reminding information to the student terminal to remind the student of attending classes seriously; meanwhile, the attendance information of the students and the vague value ZS are fused to form attendance records of the students, and the attendance records of the students are sent to a database to be stored; a teacher can log in a teaching platform to inquire attendance records of students from a database;
the live broadcast teaching module is used for synchronizing live broadcast video data of the teacher end to the student end; after a teacher live broadcasts and teaches for a period of time, the teacher grants the student end with question asking authority through the authority setting unit; after the student side is granted with the questioning authority, the student edits and uploads the questions through the student side, and after the questions edited and uploaded by the student side are audited and filtered by the student questioning unit, the uploaded questions which are considered to be the same question are subjected to optimal value analysis; selecting the problem with the largest preferred value as a selected problem; repeated uploading of the same problem is avoided, and the answering efficiency is improved; then sorting the selected problems according to the size of the extraction value DT; transmitting the selected problems in the top five ranks to a teacher end through a processor according to the sequence of the selected problems; after the teacher receives the selected questions, the teacher answers the selected questions in sequence, the answering efficiency is improved, interaction between the teacher and the students is enhanced, and therefore teaching quality is improved.
The formula and the proportionality coefficient are both obtained by collecting a large amount of data to perform software simulation and performing parameter setting processing by corresponding experts, and the formula and the proportionality coefficient which are consistent with real results are obtained.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims (5)

1. An artificial intelligence-based network teaching system for vocational education is characterized by comprising a class distribution module, an authentication module, an image acquisition module, a data analysis module, a live broadcast teaching module, a recorded broadcast module, a courseware on-demand module, a processor and a database;
the class distribution module is used for performing learning gradient management on students and distributing the students to corresponding classes for learning; the image acquisition module is used for shooting the learning condition of the student after the authentication is successful, acquiring the real-time video information of the student and sending the real-time video information to the data analysis module; the data analysis module is used for receiving real-time video information and analyzing the real-time video information, and comprises the following specific steps:
processing the real-time video information to obtain student face image information, and matching the captured face image information with standard student face image information stored in a database; obtaining attendance information of students;
when the disappearance time of the facial image information of the student is greater than a preset time value T1, judging that the student is in a vague state; counting the number of times that the student is in the vague state to be C1; counting the time when the student is in the vague state as C2; obtaining the vague value ZS of the student by using the formula ZS as C1 × a3+ C2 × a 4; if the vague value ZS is larger than the vague threshold value, generating a reminding signal; simultaneously marking the corresponding student end as a reminding terminal;
the data analysis module is used for sending a reminding signal and a reminding terminal to the reminding module through the processor; the reminding module is used for sending reminding information to the reminding terminal.
2. The artificial intelligence based network teaching system for vocational education according to claim 1, wherein the specific working steps of the class assignment module are as follows:
the class distribution module is used for distributing corresponding examination questions according to the study calendar input by the students; matching the answers of the students with the standard answers of the examination questions; obtaining the score K1 of the student; acquiring student's calendar information, acquiring a grade value corresponding to the student's calendar information, and marking the grade value as K2; using the formula ZK ═ K (K1 × a1+ K2 × a2)(a1+a2)Acquiring a comprehensive score ZK corresponding to the student;if ZK > P2, assigning the student to a senior class; if the ZK is more than P1 and less than or equal to P2, the student is assigned to the middle class; if ZK ≦ P1, the student is assigned to the primary class.
3. The artificial intelligence based network teaching system for vocational education according to claim 1, wherein the direct broadcasting teaching module comprises an authority setting unit and a student questioning unit; the method comprises the following specific steps:
after the student side is granted with the questioning authority, the student side edits and uploads the questions, and the questions edited and uploaded by the student side are audited and filtered by the student questioning unit and then corresponding selected questions are transmitted to the teacher side;
the number of questions considered to be the same question is counted and labeled R1; using the formula DT ═ YQ × b4+ R1 × b5(b4+b5)Obtaining an effect-increasing value DT of the selected problem; sorting the selected problems according to the size of the extraction value DT; transmitting the selected problems in the top five ranks to a teacher end through a processor according to the sequence of the selected problems;
after the teacher end receives the selected questions, the teacher answers the selected questions in sequence.
4. The artificial intelligence based network teaching system for vocational education according to claim 3, wherein the specific method for auditing and filtering is as follows:
extracting keywords of all uploaded problems, and when the keyword coincidence degree of the two uploaded problems is larger than or equal to a preset coincidence degree lambda%, considering the two uploaded problems as the same problem; performing a preferred value analysis on the uploaded problems which are considered to be the same problem; the method specifically comprises the following steps:
marking the vague value of the uploaded students in the live broadcast teaching process as L1; marking the number of times of uploading questions of the student end corresponding to the uploading students as L2; evaluating the richness of the question content to obtain a richness value L3; obtaining a preferred value YQ of the corresponding problem by using a formula YQ (L2 × b1+ L3 × b2)/(L1 × b 3); and selecting the problem with the maximum preferred value as the selected problem.
5. The artificial intelligence based network teaching system for vocational education according to claim 4, wherein the evaluation of the richness of the question contents results in a richness value L3; the method comprises the following specific steps:
acquiring corresponding pictures and character descriptions in the question content; if the problem content includes a picture, making Pc equal to 1, otherwise making Pc equal to 0; if the question content contains the text description, making Wc be 1, otherwise making Wc be 0;
marking the number of pictures in the question content as Ps, and marking the text size of the character description as Ws; the richness value L3 of the question content is obtained using the formula L3 ═ (Pc + Wc) × (Ps × d1+ Ws × d 2).
CN202111227662.9A 2021-10-21 2021-10-21 Vocational education network teaching system based on artificial intelligence Withdrawn CN113919987A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111227662.9A CN113919987A (en) 2021-10-21 2021-10-21 Vocational education network teaching system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111227662.9A CN113919987A (en) 2021-10-21 2021-10-21 Vocational education network teaching system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN113919987A true CN113919987A (en) 2022-01-11

Family

ID=79242168

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111227662.9A Withdrawn CN113919987A (en) 2021-10-21 2021-10-21 Vocational education network teaching system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN113919987A (en)

Similar Documents

Publication Publication Date Title
CN109670110B (en) Educational resource recommendation method, device, equipment and storage medium
Hart Understanding the media: A practical guide
CN109243226B (en) Multi-screen interactive teaching system and method
CN110070295B (en) Classroom teaching quality evaluation method and device and computer equipment
CN113781853B (en) Teacher-student remote interactive education platform based on terminal
CN111611434B (en) Online course interaction method and interaction platform
CN109817040A (en) A kind of processing system for teaching data
CN110706530A (en) Intelligent educational administration management system and method based on online live broadcast
CN110164213A (en) A kind of multiple terminals distance education and training system based on AI video analysis
CN103428234A (en) Education cloud computing platform
CN107316511B (en) Interactive video system based on web browser
CN114422820A (en) Education interactive live broadcast system and live broadcast method
CN110706534A (en) Remote education examination system based on cloud service
Lugo-Ortiz The academia, the media, and the ideal professional: a generalist-multimedia journalist
CN113919987A (en) Vocational education network teaching system based on artificial intelligence
CN115278272B (en) Education practice online guidance system and method
JP6829509B1 (en) Learning support system and learning support method
CN113516572A (en) Online learning statistics and evaluation system
KR20160111677A (en) Apparatus for providing pre-experience lecture and method for providing pre-experience lecture
CN117576604B (en) Classroom interaction method and device based on image recognition
KR100389808B1 (en) A bothway tutoring method and system based on the Internet
Giudici HYBRID VERSUS HYFLEX INSTRUCTION IN AN INTRODUCTORY FINANCE COURSE.
Mohamed et al. The Degree of Availability of E-Learning Competencies: A Survey Study Among the Faculty Staff Members at Jazan University-Saudi Arabia
CN116978265A (en) One-to-one teaching system based on Internet
KR20230165476A (en) Providing Method of Learning Services Based on Problem Solving Materials

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220111