CN114299767A - Intelligent teaching demonstration system and method based on artificial intelligence - Google Patents
Intelligent teaching demonstration system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN114299767A CN114299767A CN202111505183.9A CN202111505183A CN114299767A CN 114299767 A CN114299767 A CN 114299767A CN 202111505183 A CN202111505183 A CN 202111505183A CN 114299767 A CN114299767 A CN 114299767A
- Authority
- CN
- China
- Prior art keywords
- demonstration
- student
- area
- students
- unit
- 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- Withdrawn
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent teaching demonstration system and method based on artificial intelligence, which comprises the following steps: teaching information collection module, data processing center, initial demonstration sets up the module, demonstration obstacle test module and teaching demonstration control module, gather student's basic information and learning information through teaching information collection module, all information of gathering through data processing center storage, set up the module through initial demonstration and adjust the teaching demonstration mode according to the study progress, monitor unusual situation at the demonstration in-process through demonstration obstacle test module, whether can shelter from the demonstration key region through image analysis personnel's ambulation, estimate student's sight focus position simultaneously, the degree is absorbed in the listening of analysis student, adjust the demonstration picture through teaching demonstration control module, remind the student to notice the listening and speaking, teaching efficiency is improved, student's study effect difference has been reduced when improving student's whole study efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent teaching demonstration, in particular to an intelligent teaching demonstration system and method based on artificial intelligence.
Background
At present, in the education industry, many colleges and universities set up courses in aspects of intelligent robots and the like to adapt to the development of artificial intelligence technology, the set-up of robot programming courses can shape the programming thinking of students and train the logic and abstract thinking ability of the students, and robot course teaching needs teachers to perform teaching demonstration to help the students to better understand learning contents;
however, the existing teaching demonstration mode has a plurality of problems: firstly, because each step of demonstration operation in the course demonstration process of robot programming is crucial and has connectivity, the prior art cannot timely process the phenomenon that abnormal demonstration pictures are blocked, so that the demonstration operation seen by students is interrupted, and the teaching efficiency is reduced; secondly, the learning conditions of the students cannot be monitored in real time in the process of demonstrating the teaching contents by the teacher, and the attention concentration states of the students cannot be mastered in time, so that the difference of the learning effects of different students is enlarged, and the centralized improvement of the learning abilities of the students is not facilitated; finally, the difficulty degree of teaching demonstration contents is different, proper contents cannot be selected according to the learning progress of students for demonstration and playing, and the students cannot master courses as soon as possible.
Therefore, there is a need for an intelligent teaching demonstration system and method based on artificial intelligence to solve the above problems.
Disclosure of Invention
The invention aims to provide an intelligent teaching demonstration system and method based on artificial intelligence, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the utility model provides an intelligence teaching demonstration system based on artificial intelligence which characterized in that: the system comprises: the system comprises a teaching information acquisition module, a data processing center, an initial demonstration setting module, a demonstration obstacle testing module and a teaching demonstration control module;
the teaching information acquisition module is used for acquiring basic information of students and learning progress and state information of the students; the data processing center is used for storing all the acquired information; the initial demonstration setting module is used for calling the learning progress and state information of students, analyzing the learning progress of different students and adjusting the teaching demonstration mode according to the learning progress; the demonstration obstacle testing module is used for monitoring abnormal conditions in the demonstration process, monitoring whether a person walks during demonstration, shooting images of the person walking, judging whether the person walks to block a demonstration key area through image analysis, and if so, adjusting a demonstration picture by using the teaching demonstration control module; through demonstration obstacle test module estimates student's sight focus position, analyzes student's listening and speaking and concentrates on the degree, through teaching demonstration control module reminds student's attention to listening and speaking.
Furthermore, the teaching information acquisition module comprises a learning information acquisition unit and a basic information acquisition unit, and the learning information acquisition unit is used for acquiring the learning progress and the learning state data of students; the basic information acquisition unit is used for acquiring height and seat height information of students and storing all acquired information into the data processing center.
Further, the initial demonstration setting module comprises a learning progress analyzing unit and a demonstration step adjusting unit, wherein the learning progress analyzing unit is used for analyzing the learning progress conditions of different students according to the acquired learning progress and state data of the students; the demonstration step adjusting unit is used for adjusting the demonstration mode of the teaching content according to the learning progress of different students.
Furthermore, the demonstration obstacle testing module comprises a demonstration shielding testing unit, a scene change monitoring unit, a shielding range analyzing unit, a sight line focus estimating unit and a key factor analyzing unit, wherein the demonstration shielding testing unit is used for testing whether demonstration contents are shielded in the demonstration process and shooting shielding images; the scene change monitoring unit is used for monitoring the walking condition of people in the demonstration environment; if the demonstration content is shielded, analyzing whether a shielded area covers a demonstration key area or not by the shielded area analyzing unit; the sight focusing estimation unit is used for analyzing sight focuses of students when the staff walks; the key factor analysis unit is used for analyzing the sight focus of the student and judging the area in which the sight focus is concentrated.
Furthermore, the teaching demonstration control module comprises a display control unit, a demonstration adjusting unit and an abnormity reminding unit, wherein the display control unit is used for controlling demonstration contents to demonstrate according to the adjusted teaching demonstration mode; the demonstration adjusting unit is used for adjusting the position of a demonstration picture when the demonstration key area is covered by the re-shielding area; the abnormity reminding unit is used for judging whether the overall attention of the student is concentrated according to the sight focus of the student and reminding a teacher of paying attention to the learning condition of the student when the overall attention of the student is not concentrated.
An intelligent teaching demonstration method based on artificial intelligence is characterized in that: the method comprises the following steps:
s11: collecting the learning progress, the learning state and corresponding basic information of a student;
s12: analyzing the learning progress of the student according to the learning progress and the learning state information of the student, and adjusting a demonstration mode;
s13: testing whether a demonstration picture is shielded or not, shooting a demonstration image when the demonstration picture is shielded, analyzing whether a shielding area covers a demonstration key area or not after the image is processed, and if so, adjusting a demonstration position;
s14: and estimating the sight line focusing position of the student, judging whether the attention of the student is concentrated, and if the attention of the student is not concentrated, performing abnormal reminding.
Further, in steps S11-S12: the height information and the seat height information of the students are acquired by the basic information acquisition unit, the demonstration contents are arranged into I sections according to the difficulty degree of mastering, and the difficulty coefficient set of the demonstration contents acquired by the learning information acquisition unit is set as { 2%0*M，21*M，...，2I-1M, where M represents a basic difficulty coefficient, a set of learning degree coefficients of a random student for I-segment contents is Q ═ { Q1, Q2.., QI }, and a set of times corresponding to the I-segment contents listened to by the student is M ═ M1, M2.., mI }, and a learning ability coefficient Pi of the random student for a random segment of demonstration contents is calculated according to the following formula:
therein, 2iM represents the difficulty coefficient of a random section of demonstration content, Qi represents the mastering degree coefficient of a random student to a corresponding section of demonstration content, mi represents the times of listening and speaking the corresponding section of content by the corresponding student, the learning ability coefficient set of the demonstration content by the corresponding student is obtained as P ═ P1, P2,i-1m: if Pi is greater than or equal to 2i-1M, judging that the corresponding students can master the corresponding section of demonstration content, counting the number of the students which can learn to master the corresponding section of demonstration content to be K, and if K is equal to K>2k/3, the display control unit is used for controlling the display of corresponding demonstration contents for k students, the more difficult the demonstration contents are, the more the students listen and talk, and the lower the mastering degree, the lower the learning ability of the corresponding demonstration contents is, the difficulty of the demonstration contents, the listening and speaking times of the students and the mastering degree of the students on different demonstration contents are combined to calculate the learning ability coefficient of the students, and the purpose of comprehensively judging the mastering degree of the students on different teaching contents is achieved, the selection of proper teaching contents for demonstration is facilitated, so that most students can quickly master courses, and the learning efficiency of most students is improved in a centralized manner.
Further, in step S13: whether a person walks in a demonstration environment is monitored by using a scene change monitoring unit, a shooting person walks on a sheltered image formed on a demonstration picture, a sheltered area outline is obtained after the image is subjected to boundary processing, ellipse fitting is carried out on the sheltered area outline, and a sheltered area outline curve equation obtained after fitting is as follows:
drawing and demonstrating the key area as an ellipse to obtain a key area curve equation as follows:
assuming that the occlusion area covers the demonstration key area, calculating the area S of the occlusion area covering the demonstration key area according to the following formula:
wherein, p and q represent the abscissa of two nodical points of sheltering from region and demonstration key area, and q > p, utilize and shelter from the analysis unit of scope and whether shelter from the region and cover demonstration key area: if S is equal to 0, the coverage area does not exist, and the occlusion area is judged not to cover the demonstration key area; if S is not equal to 0, it is indicated that the coverage area exists, the fact that the shielding area covers the demonstration key area is judged, the demonstration key area position is adjusted through the demonstration adjusting unit, the image processing technology in artificial intelligence is utilized, when the demonstration picture is shielded due to the fact that people walk, the image is shot, the outline of the shielding area is extracted, the overlapping area of the shielding area and the demonstration key area can be rapidly calculated through a mode of determining integral points, whether the shielding area covers the demonstration key content or not is judged, the key degree of the demonstration area is different, the content being demonstrated is the key area, the key area is selected when the overlapping area is calculated, the whole demonstration area is not selected, and unnecessary operation of adjusting the demonstration position is reduced.
Further, in step S14: estimating the sight focus of the student when the person walks by using a sight focus estimation unit: establishing a two-dimensional coordinate system by taking the bottom edge of a demonstration screen as an x axis, acquiring the height information of students facing the demonstration screen by using a basic information acquisition unit, acquiring the height set of the students as H ═ H1, H2,. and hn }, wherein n represents the number of the students facing the demonstration screen, setting the position coordinate of the original sight focus of one random student on the demonstration screen as (Xi, (hi-H)), wherein hi represents the sitting height of the corresponding student, H represents the height difference between the student seat and the bottom edge of the demonstration screen, acquiring the left and right deflection angles of the head of the corresponding student as alpha i when the person walks, and respectively calculating the horizontal coordinate Xi 'and the vertical coordinate Yi' of the sight focus on the demonstration screen when the person walks according to the following formula:
Xi'＝Xi±(hi-H)cos(π/2-αi)；
Yi'＝(hi-H)-(hi-H)sin(π/2-αi)；
when a student who is right at the demonstration picture walks, the coordinate set of the sight line focus on the demonstration screen is (X ', Y') { (X1 ', Y1'), (X2 ', Y2'), (Xn ', Yn') }, the sight line focus of the student is estimated when the student walks through the head movement data of the student, and the purpose of calculating the coordinate of the sight line focus on the demonstration screen is to analyze the sight line concentration area of the student, so that the subsequent judgment of the overall attention concentration degree of the student is facilitated.
Further, a genetic algorithm is utilized to obtain the area of the minimum region covering the sight focus as s, the area of the overlapping region of the minimum region and the demonstration key region as s', p points in the minimum region are counted, and the attention concentration coefficient W is calculated according to the following formula:
setting the attention concentration coefficient threshold value as W ', and comparing W with W': if W is larger than W', the comprehensive attention degree of the student exceeds a threshold value; if W is less than or equal to W', the comprehensive attention degree of the students does not exceed the threshold value, the situation that the overall attention of the students is not concentrated exists, the abnormal reminding unit is used for reminding the teachers of paying attention to the learning situation of the students, the genetic algorithm is a method for seeking the optimal solution, the genetic algorithm is used for solving the derivation problem of the minimum coverage circle, the accurate minimum area can be obtained, compared with some conventional optimization algorithms, the result can be obtained quickly and well, the smaller the number of points in the minimum area is, the smaller the area of the overlapping area is, the less the overall attention of the students is, and the attention concentration coefficient is calculated by combining the overlapping area of the minimum area and the demonstration key area and the number of the points of the content of the minimum area.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, by using an artificial intelligence technology, when a person walks to shield the demonstration content in the demonstration process, the image is shot, the boundary processing is carried out on the image, the outline of the shielded area is extracted, the overlapping area of the shielded area and the demonstration key area is calculated, whether the shielded area covers the demonstration key content is judged, and the problem that the teaching efficiency is reduced because the abnormal demonstration picture is not shielded in time in the prior art and the demonstration operation seen by a student is interrupted is solved; the sight line focus coordinate of the student is estimated through the head movement data of the student when the student walks, a relatively accurate sight line focus concentration area, namely the minimum area, is obtained through the sight line focus coordinate and a genetic algorithm, the attention concentration coefficient is calculated through the minimum area and the overlapping area of the demonstration key area and the number of points of the minimum area content, the accuracy of a calculation result is improved, and the problem that in the prior art, a teacher cannot timely master the attention concentration state of the student, and the difference of learning effects of different students is enlarged is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an artificial intelligence based intelligent teaching demonstration system of the present invention;
FIG. 2 is a flow chart of an intelligent teaching demonstration method based on artificial intelligence.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Referring to fig. 1-2, the present invention provides a technical solution: the utility model provides an intelligence teaching demonstration system based on artificial intelligence which characterized in that: the system comprises: the teaching demonstration system comprises a teaching information acquisition module S1, a data processing center S2, an initial demonstration setting module S3, a demonstration obstacle testing module S4 and a teaching demonstration control module S5;
the teaching information acquisition module S1 is used for acquiring the basic information of students and the learning progress and state information thereof; the data processing center S2 is used for storing all the collected information; the initial demonstration setting module S3 is used for calling the learning progress and state information of students, analyzing the learning progress of different students and adjusting the teaching demonstration mode according to the learning progress; the demonstration obstacle testing module S4 is used for monitoring abnormal conditions in the demonstration process, monitoring whether a person walks during the demonstration, shooting images of the person walking, judging whether the walking of the person can block a demonstration key area through the image analysis, and if the walking can block the key area, adjusting the demonstration picture by using the teaching demonstration control module S5; the sight line focusing position of the student is estimated through the demonstration obstacle testing module S4, the listening and speaking concentration degree of the student is analyzed, and the student is reminded to pay attention to listening and speaking through the teaching demonstration control module S5.
The teaching information acquisition module S1 comprises a learning information acquisition unit and a basic information acquisition unit, wherein the learning information acquisition unit is used for acquiring the learning progress and the learning state data of students; the basic information acquisition unit is used for acquiring the height and seat height information of the students and storing all the acquired information into the data processing center S2.
The initial demonstration setting module S3 comprises a learning progress analysis unit and a demonstration step adjustment unit, wherein the learning progress analysis unit is used for analyzing the learning progress conditions of different students according to the acquired learning progress and state data of the students; the demonstration step adjusting unit is used for adjusting the demonstration mode of the teaching content according to the learning progress of different students.
The demonstration obstacle testing module S4 comprises a demonstration shielding testing unit, a scene change monitoring unit, a shielding range analyzing unit, a sight line focus estimating unit and a key factor analyzing unit, wherein the demonstration shielding testing unit is used for testing whether demonstration contents are shielded in the demonstration process and shooting shielding images; the scene change monitoring unit is used for monitoring the walking condition of people in the demonstration environment; if the demonstration content is shielded, analyzing whether the shielded area covers the demonstration key area or not by using a shielded range analysis unit; the sight focusing estimation unit is used for analyzing sight focuses of students when the staff walks; the key factor analysis unit is used for analyzing the sight focus of the student and judging the area in which the sight focus is concentrated.
The teaching demonstration control module S5 comprises a display control unit, a demonstration adjusting unit and an abnormity reminding unit, wherein the display control unit is used for controlling demonstration contents to demonstrate according to the adjusted teaching demonstration mode; the demonstration adjusting unit is used for adjusting the position of a demonstration picture when the demonstration key area is covered by the re-shielding area; the abnormity reminding unit is used for judging whether the overall attention of the student is concentrated according to the sight focus of the student and reminding a teacher of paying attention to the learning condition of the student when the overall attention of the student is not concentrated.
An intelligent teaching demonstration method based on artificial intelligence is characterized in that: the method comprises the following steps:
s11: collecting the learning progress, the learning state and corresponding basic information of a student;
s12: analyzing the learning progress of the student according to the learning progress and the learning state information of the student, and adjusting a demonstration mode;
s13: testing whether a demonstration picture is shielded or not, shooting a demonstration image when the demonstration picture is shielded, analyzing whether a shielding area covers a demonstration key area or not after the image is processed, and if so, adjusting a demonstration position;
s14: and estimating the sight line focusing position of the student, judging whether the attention of the student is concentrated, and if the attention of the student is not concentrated, performing abnormal reminding.
In steps S11-S12: the height information and the seat height information of the students are acquired by the basic information acquisition unit, the demonstration contents are arranged into I sections according to the difficulty degree of mastering, and the difficulty coefficient set of the demonstration contents acquired by the learning information acquisition unit is set as { 2%0*M，21*M，...，2I-1M, where M represents a basic difficulty coefficient, a set of learning degree coefficients of a random student for I-segment contents is Q ═ { Q1, Q2.., QI }, and a set of times corresponding to the I-segment contents listened to by the student is M ═ M1, M2.., mI }, and a learning ability coefficient Pi of the random student for a random segment of demonstration contents is calculated according to the following formula:
therein, 2iM represents the difficulty coefficient of a random section of demonstration content, Qi represents the mastery degree system of a random student to the corresponding section of demonstration contentAnd mi represents the frequency of listening and speaking the corresponding section of content by the corresponding student, the learning ability coefficient set of the corresponding student to the demonstration content is obtained as P ═ P1, P2i-1M: if Pi is greater than or equal to 2i-1M, judging that the corresponding students can master the corresponding section of demonstration content, counting the number of the students which can learn to master the corresponding section of demonstration content to be K, and if K is equal to K>2k/3, k represents the student total number, utilizes the control of display control unit to show corresponding section demonstration content to k students, combines the degree of difficulty of demonstration content, the number of times that the student listened to and the degree of mastering of student to different demonstration contents to calculate the student's learning ability coefficient's aim at judge the student to the degree of mastering of different teaching contents synthetically, is convenient for select suitable teaching content to demonstrate to guarantee that most students can master the course fast, can concentrate improvement most students ' learning efficiency.
In step S13: whether a person walks in a demonstration environment is monitored by using a scene change monitoring unit, a shooting person walks on a sheltered image formed on a demonstration picture, a sheltered area outline is obtained after the image is subjected to boundary processing, ellipse fitting is carried out on the sheltered area outline, and a sheltered area outline curve equation obtained after fitting is as follows:
drawing and demonstrating the key area as an ellipse to obtain a key area curve equation as follows:
assuming that the occlusion area covers the demonstration key area, calculating the area S of the occlusion area covering the demonstration key area according to the following formula:
wherein, p and q represent the abscissa of two nodical points of sheltering from region and demonstration key area, and q > p, utilize and shelter from the analysis unit of scope and whether shelter from the region and cover demonstration key area: if S is equal to 0, the coverage area does not exist, and the occlusion area is judged not to cover the demonstration key area; if S is not equal to 0, the coverage area exists, the occlusion area is judged to cover the demonstration key area, and the demonstration key area is adjusted by the demonstration adjusting unit.
In step S14: estimating the sight focus of the student when the person walks by using a sight focus estimation unit: establishing a two-dimensional coordinate system by taking the bottom edge of a demonstration screen as an x axis, acquiring the height information of students facing the demonstration screen by using a basic information acquisition unit, acquiring the height set of the students as H ═ H1, H2,. and hn }, wherein n represents the number of the students facing the demonstration screen, setting the position coordinate of the original sight focus of one random student on the demonstration screen as (Xi, (hi-H)), wherein hi represents the sitting height of the corresponding student, H represents the height difference between the student seat and the bottom edge of the demonstration screen, acquiring the left and right deflection angles of the head of the corresponding student as alpha i when the person walks, and respectively calculating the horizontal coordinate Xi 'and the vertical coordinate Yi' of the sight focus on the demonstration screen when the person walks according to the following formula:
Xi'＝Xi±(hi-H)cos(π/2-αi)；
Yi'＝(hi-H)-(hi-H)sin(π/2-αi)；
when a student who is right at the demonstration picture moves, the coordinate set of the sight line focus on the demonstration screen is (X ', Y') { (X1 ', Y1'), (X2 ', Y2'), (Xn ', Yn') }, the sight line focus of the student when the student moves is estimated through the head movement data of the student, and the purpose of calculating the coordinate of the sight line focus on the demonstration screen is to analyze the sight line concentration area of the student, so that the attention concentration degree of the whole student can be conveniently judged in the follow-up process.
Obtaining the area of the minimum area covering the sight focus as s by utilizing a genetic algorithm, obtaining the area of the overlapping area of the minimum area and the demonstration key area as s', counting p points in the minimum area, and calculating the attention concentration coefficient W according to the following formula:
setting the attention concentration coefficient threshold value as W ', and comparing W with W': if W is larger than W', the comprehensive attention degree of the student exceeds a threshold value; if W is less than or equal to W', the comprehensive attention degree of the students does not exceed the threshold value, the situation that the overall attention of the students is not concentrated exists, the abnormal reminding unit is used for reminding the teachers to pay attention to the study situation of the students, the minimum coverage circle derivation problem is solved through the genetic algorithm, the relatively accurate minimum area can be quickly obtained, the attention concentration coefficient is calculated by combining the overlapping area of the minimum area and the demonstration key area and the number of points of the content of the minimum area, and the accuracy of the calculation result can be improved.
The first embodiment is as follows: the demonstration contents are divided into I sections according to the arrangement of low to high difficulty degree of mastering, and the difficulty coefficient set of the demonstration contents acquired by the learning information acquisition unit is { 2%0*M，21*M，22M ═ 2, 4, 8 ═ 2, the set of grasping degree coefficients of a random student for I ═ 3 pieces of content is Q ═ Q1, Q2, Q3 ═ 4, 8, 6}, the set of times corresponding to students listening to and speaking 3 pieces of content is M ═ M1, M2, M3 ═ 2, 1, 3}, and the method is based on the formula
Obtaining a set of learning ability coefficients for the demonstration content corresponding to the student, P ═ { P1, P2, P3}, {1.9, 4.3, 7.8}, and comparing Pi and 2i-1*M：P1＜20*M，P2＞21*M，P3＜22M, judging that the corresponding students can master the 2 nd section of demonstration content, counting the number of the students which can learn to master the 2 nd section of demonstration content, wherein the number is K equal to 12, the total number of the students is K equal to 15, and if K is K, the number is K>2k/3, controlling to display the 2 nd section of demonstration content for 15 students by using a display control unit;
example two: whether a person walks in a demonstration environment is monitored by using a scene change monitoring unit, a shooting person walks on a sheltered image formed on a demonstration picture, a sheltered area outline is obtained after the image is subjected to boundary processing, ellipse fitting is carried out on the sheltered area outline, and a sheltered area outline curve equation obtained after fitting is as follows:
drawing and demonstrating the key area as an ellipse to obtain a key area curve equation as follows:
assuming that the shielding area covers the demonstration key area, according to the formula
And calculating the area S of the shielding area covering the demonstration key area, wherein S is approximately equal to 2.3, S is not equal to 0, indicating that the coverage area exists, judging that the shielding area covers the demonstration key area, and adjusting the position of the demonstration key area by using a demonstration adjusting unit.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides an intelligence teaching demonstration system based on artificial intelligence which characterized in that: the system comprises: the teaching demonstration system comprises a teaching information acquisition module (S1), a data processing center (S2), an initial demonstration setting module (S3), a demonstration obstacle testing module (S4) and a teaching demonstration control module (S5);
the teaching information acquisition module (S1) is used for acquiring basic information of students and learning progress and state information of the students; the data processing center (S2) is used for storing all the collected information; the initial demonstration setting module (S3) is used for calling the learning progress and state information of students, analyzing the learning progress of different students and adjusting the teaching demonstration mode according to the learning progress; the demonstration obstacle testing module (S4) is used for monitoring abnormal conditions in the demonstration process, monitoring whether a person walks during the demonstration, shooting images of the person during walking, and utilizing the teaching demonstration control module (S5) to adjust a demonstration picture if the person walks to block a demonstration key area through image analysis whether the person walks to block the demonstration key area; and estimating the sight line focusing position of the student through the demonstration obstacle testing module (S4), analyzing the listening and speaking concentration degree of the student, and reminding the student to pay attention to listening and speaking through the teaching demonstration control module (S5).
2. The artificial intelligence based intelligent teaching demonstration system of claim 1, wherein: the teaching information acquisition module (S1) comprises a learning information acquisition unit and a basic information acquisition unit, wherein the learning information acquisition unit is used for acquiring the learning progress and the learning state data of students; the basic information acquisition unit is used for acquiring height and seat height information of students and storing all the acquired information into the data processing center (S2).
3. The artificial intelligence based intelligent teaching demonstration system of claim 1, wherein: the initial demonstration setting module (S3) comprises a learning progress analysis unit and a demonstration step adjustment unit, wherein the learning progress analysis unit is used for analyzing the learning progress conditions of different students according to the collected learning progress and state data of the students; the demonstration step adjusting unit is used for adjusting the demonstration mode of the teaching content according to the learning progress of different students.
4. The artificial intelligence based intelligent teaching demonstration system of claim 1, wherein: the demonstration obstacle testing module (S4) comprises a demonstration shielding testing unit, a scene change monitoring unit, a shielding range analyzing unit, a sight line focusing estimating unit and a key factor analyzing unit, wherein the demonstration shielding testing unit is used for testing whether demonstration contents are shielded in the demonstration process and shooting shielding images; the scene change monitoring unit is used for monitoring the walking condition of people in the demonstration environment; if the demonstration content is shielded, analyzing whether a shielded area covers a demonstration key area or not by the shielded area analyzing unit; the sight focusing estimation unit is used for analyzing sight focuses of students when the staff walks; the key factor analysis unit is used for analyzing the sight focus of the student and judging the area in which the sight focus is concentrated.
5. The artificial intelligence based intelligent teaching demonstration system of claim 1, wherein: the teaching demonstration control module (S5) comprises a display control unit, a demonstration adjusting unit and an abnormity reminding unit, wherein the display control unit is used for controlling demonstration contents to demonstrate according to the adjusted teaching demonstration mode; the demonstration adjusting unit is used for adjusting the position of a demonstration picture when the demonstration key area is covered by the re-shielding area; the abnormity reminding unit is used for judging whether the overall attention of the student is concentrated according to the sight focus of the student and reminding a teacher of paying attention to the learning condition of the student when the overall attention of the student is not concentrated.
6. An intelligent teaching demonstration method based on artificial intelligence is characterized in that: the method comprises the following steps:
s11: collecting the learning progress, the learning state and corresponding basic information of a student;
s12: analyzing the learning progress of the student according to the learning progress and the learning state information of the student, and adjusting a demonstration mode;
s13: testing whether a demonstration picture is shielded or not, shooting a demonstration image when the demonstration picture is shielded, analyzing whether a shielding area covers a demonstration key area or not after the image is processed, and if so, adjusting a demonstration position;
s14: and estimating the sight line focusing position of the student, judging whether the attention of the student is concentrated, and if the attention of the student is not concentrated, performing abnormal reminding.
7. The artificial intelligence based intelligent teaching demonstration method according to claim 6, wherein: in steps S11-S12: the height information and the seat height information of the students are collected by the basic information collection unit, the demonstration contents are divided into I sections according to the arrangement of the difficulty degree of mastering and the height, and the demonstration contents are collected by the learning information collection unitThe difficulty coefficient set of the content is {2 }0*M，21*M，...，2I-1M, where M represents a basic difficulty coefficient, a set of learning degree coefficients of a random student for I-segment contents is Q ═ { Q1, Q2.., QI }, and a set of times corresponding to the I-segment contents listened to by the student is M ═ M1, M2.., mI }, and a learning ability coefficient Pi of the random student for a random segment of demonstration contents is calculated according to the following formula:
therein, 2iM represents the difficulty coefficient of a random section of demonstration content, Qi represents the mastering degree coefficient of a random student to a corresponding section of demonstration content, mi represents the times of listening and speaking the corresponding section of content by the corresponding student, the learning ability coefficient set of the demonstration content by the corresponding student is obtained as P ═ P1, P2,i-1m: if Pi is greater than or equal to 2i-1M, judging that the corresponding students can master the corresponding section of demonstration content, counting the number of the students which can learn to master the corresponding section of demonstration content to be K, and if K is equal to K>And 2k/3, controlling to display corresponding sections of demonstration contents for k students by using the display control unit.
8. The artificial intelligence based intelligent teaching demonstration method according to claim 6, wherein: in step S13: whether a person walks in a demonstration environment is monitored by using a scene change monitoring unit, a shooting person walks on a sheltered image formed on a demonstration picture, a sheltered area outline is obtained after the image is subjected to boundary processing, ellipse fitting is carried out on the sheltered area outline, and a sheltered area outline curve equation obtained after fitting is as follows:
drawing and demonstrating the key area as an ellipse to obtain a key area curve equation as follows:
assuming that the occlusion area covers the demonstration key area, calculating the area S of the occlusion area covering the demonstration key area according to the following formula:
wherein, p and q represent the abscissa of two nodical points of sheltering from region and demonstration key area, and q > p, utilize and shelter from the analysis unit of scope and whether shelter from the region and cover demonstration key area: if S is equal to 0, the coverage area does not exist, and the occlusion area is judged not to cover the demonstration key area; if S is not equal to 0, the coverage area exists, the occlusion area is judged to cover the demonstration key area, and the demonstration key area is adjusted by the demonstration adjusting unit.
9. The artificial intelligence based intelligent teaching demonstration method according to claim 8, wherein: in step S14: estimating the sight focus of the student when the person walks by using a sight focus estimation unit: establishing a two-dimensional coordinate system by taking the bottom edge of a demonstration screen as an x axis, acquiring the height information of students facing the demonstration screen by using a basic information acquisition unit, acquiring the height set of the students as H ═ H1, H2,. and hn }, wherein n represents the number of the students facing the demonstration screen, setting the position coordinate of the original sight focus of one random student on the demonstration screen as (Xi, (hi-H)), wherein hi represents the sitting height of the corresponding student, H represents the height difference between the student seat and the bottom edge of the demonstration screen, acquiring the left and right deflection angles of the head of the corresponding student as alpha i when the person walks, and respectively calculating the horizontal coordinate Xi 'and the vertical coordinate Yi' of the sight focus on the demonstration screen when the person walks according to the following formula:
Xi'＝Xi±(hi-H)cos(π/2-αi)；
Yi'＝(hi-H)-(hi-H)sin(π/2-αi)；
when the student who faces the demonstration screen walks, the coordinate set of the gaze focus on the demonstration screen is (X ', Y') { (X1 ', Y1'), (X2 ', Y2'), (Xn ', Yn') }.
10. The artificial intelligence based intelligent teaching demonstration method according to claim 8, wherein: obtaining the area of the minimum area covering the sight focus as s by utilizing a genetic algorithm, obtaining the area of the overlapping area of the minimum area and the demonstration key area as s', counting p points in the minimum area, and calculating the attention concentration coefficient W according to the following formula:
setting the attention concentration coefficient threshold value as W ', and comparing W with W': if W is larger than W', the comprehensive attention degree of the student exceeds a threshold value; if W is less than or equal to W', the comprehensive attention degree of the students does not exceed the threshold value, the situation that the overall attention of the students is not concentrated exists, and the abnormity reminding unit is used for reminding the teacher to pay attention to the learning situation of the students.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111505183.9A CN114299767A (en) | 2021-12-10 | 2021-12-10 | Intelligent teaching demonstration system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111505183.9A CN114299767A (en) | 2021-12-10 | 2021-12-10 | Intelligent teaching demonstration system and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299767A true CN114299767A (en) | 2022-04-08 |
Family
ID=80967987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111505183.9A Withdrawn CN114299767A (en) | 2021-12-10 | 2021-12-10 | Intelligent teaching demonstration system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299767A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051328A (en) * | 2023-02-10 | 2023-05-02 | 深圳市纬亚森科技有限公司 | Remote management system and method for multimedia teaching based on Internet of things |
| CN116597680A (en) * | 2023-03-28 | 2023-08-15 | 北京知藏云道科技有限公司 | Line feasibility prediction system based on data analysis |
-
2021
- 2021-12-10 CN CN202111505183.9A patent/CN114299767A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051328A (en) * | 2023-02-10 | 2023-05-02 | 深圳市纬亚森科技有限公司 | Remote management system and method for multimedia teaching based on Internet of things |
| CN116051328B (en) * | 2023-02-10 | 2024-01-12 | 杨金峰 | Remote management system and method for multimedia teaching based on Internet of things |
| CN116597680A (en) * | 2023-03-28 | 2023-08-15 | 北京知藏云道科技有限公司 | Line feasibility prediction system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114299767A (en) | Intelligent teaching demonstration system and method based on artificial intelligence | |
| CN109657553B (en) | Student classroom attention detection method | |
| Thar et al. | A proposal of yoga pose assessment method using pose detection for self-learning | |
| Hu et al. | Research on abnormal behavior detection of online examination based on image information | |
| CN113706960A (en) | Nursing operation exercise platform based on VR technology and use method | |
| CN112489371B (en) | Swimming pool drowning prevention early warning system based on computer vision | |
| CN108229352B (en) | Standing detection method based on deep learning | |
| CN111507592B (en) | Evaluation method for active modification behaviors of prisoners | |
| CN106599821A (en) | Controller fatigue detection method and system based on BP neural network | |
| CN112200138B (en) | Classroom learning situation analysis method based on computer vision | |
| CN111563449A (en) | Real-time classroom attention detection method and system | |
| CN111553218A (en) | Intelligent medical skill teaching monitoring system based on human body posture recognition | |
| Lee et al. | A multisensor interface to improve the learning experience in arc welding training tasks | |
| CN107256375A (en) | Human body sitting posture monitoring method before a kind of computer | |
| CN113095260A (en) | Intelligent student self-learning state monitoring method | |
| CN109118512A (en) | A kind of classroom based on machine vision is come to work late and leave early detection method | |
| CN114285966B (en) | Method and system for processing monitoring data related to labor education | |
| CN116110091A (en) | Online learning state monitoring system | |
| CN108734612A (en) | A kind of Classroom Teaching device based on multi-aspect information acquisition | |
| CN111273232A (en) | Indoor abnormal condition judgment method and system | |
| Hwang et al. | Attentiveness assessment in learning based on fuzzy logic analysis | |
| Reddy et al. | Student live behaviour monitoring during virtual class using artificial intelligence | |
| Kunishima et al. | Gait Condition Assessment Methods for Visualizing Interventional Expertise by Means of Posture Detection | |
| CN113673856A (en) | 3D-based hospital sensory control simulation training and examination system | |
| CN113517052A (en) | Multi-perception man-machine interaction system and method in commercial fitness scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220408 |