Intelligent teaching method, device and equipment based on AI cooperation and medium

Abstract

The invention relates to an intelligent teaching method, device and equipment based on AI cooperation and a medium, and belongs to the field of intelligent teaching. The method comprises the steps of uploading a teaching theme, traversing whole network data through an AI automatic search technology, and obtaining a matched teaching video through cross-modal retrieval; a matched teaching video is projected in a classroom through a three-dimensional holographic projection technology for cooperating with teaching work; student concentration detection is carried out based on artificial intelligence, a student concentration judgment model is constructed, student concentration judgment information is output, and the student concentration judgment information comprises student high concentration information and student low concentration information; and acquiring a student position corresponding to the output student low-concentration information, and performing three-dimensional holographic projection on the matched teaching video to the student position until the student concentration judgment model outputs the student high-concentration information, thereby realizing cooperation of teaching work through AI, reducing workload of teachers, improving teaching work efficiency, increasing classroom interestingness, and improving teaching experience. And the interest of students in classes is improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent teaching technology, and specifically relates to an intelligent teaching method, device, equipment and medium based on AI cooperation. Background Art

[0002] With the development of the times, the education industry has also changed, and society has paid more and more attention to the comprehensive growth of students. However, most students are lively, active, and easily influenced by new things, which causes students to lose concentration in class, reduces teaching efficiency, and consumes teachers' energy, resulting in teaching results that do not meet expectations. In recent years, intelligent teaching has gradually been widely used, but the intelligent classrooms created are still relatively boring and mainly rely on the unilateral output of teachers. Teachers not only need to complete teaching tasks and ensure the quality of the class, but also need to pay attention to whether students are distracted in real time, which leads to excessive burdens on teachers. At present, there is an urgent need for an intelligent teaching method that can highly cooperate with artificial intelligence and teachers and reduce the burden of teachers paying attention to students at the same time. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides an intelligent teaching method, device, equipment and medium based on AI cooperation.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] An intelligent teaching method based on AI cooperation, the implementation of the intelligent teaching method comprises the following steps:

[0006] S1: Upload the teaching topic, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end;

[0007] S2: Projecting the matching teaching video in the classroom through three-dimensional holographic projection technology to assist teaching work;

[0008] S3: Perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information, wherein the student concentration judgment information includes student high concentration information and student low concentration information;

[0009] S4: Obtain the student position corresponding to the output of the student's low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student's high concentration information.

[0010] Preferably, the step S3 specifically includes:

[0011] S301: Preset a concentration detection cycle, obtain a classroom real-time image set through a camera according to the concentration detection cycle, and obtain a unified face detection frame set of the classroom real-time image set through face detection;

[0012] S302: obtaining the student's head deflection angle based on the unified face detection frame set, and constructing a suspicious concentration capture model and outputting suspicious concentration capture information, wherein the suspicious concentration capture information includes the student's suspicious concentration information and the student's credible concentration information;

[0013] S303: When the suspicious concentration capture model outputs the student concentration suspicious information, the student concentration judgment model is constructed through the student concentration judgment index and the student concentration judgment information is output, wherein the student concentration judgment information includes the student high concentration information and the student low concentration information.

[0014] Preferably, the step S301 specifically includes:

[0015] S301-1: Performing face detection on the classroom real-time image set and obtaining a face detection frame;

[0016] S301-2: extracting the face detection frame and obtaining a face detection frame set;

[0017] S301 - 3 : Preset a uniform frame size, scale the face detection frame to the uniform frame size and obtain the uniform face detection frame set.

[0018] Preferably, the step S302 specifically includes:

[0019] S302-1: Locate facial feature points, where the facial feature points include a nose tip feature point, a nose root feature point, a left eye outer feature point, and a right eye outer feature point;

[0020] S302-2: Acquire facial feature point vectors, the facial feature point vectors including a first facial feature point vector, a second facial feature point vector, and a third facial feature point vector, the first facial feature point vector is a vector connecting the nose tip feature point to the nasal root feature point, the second facial feature point vector is a vector connecting the nose tip feature point to the left eye outer feature point, and the third facial feature point vector is a vector connecting the nose tip feature point to the right eye outer feature point;

[0021] S302-3: Calculate the student's head deflection angle based on the facial feature point vector, and the calculation formula is:

[0022]

[0023] Among them, α is the deflection angle of the student's head, is the angle between the first facial feature point vector and the second facial feature point vector, is the angle between the first facial feature point vector and the third facial feature point vector, is the first facial feature point vector, is the second facial feature point vector, is the third facial feature point vector;

[0024] S302-4: Preset a student head deflection angle threshold, construct the suspicious concentration capture model by comparing the student head deflection angle and the student head deflection angle threshold, and output the suspicious concentration capture information, wherein the suspicious concentration capture information includes student concentration suspicious information and student concentration credible information.

[0025] Preferably, the student's head deflection angle is determined, and when the student's head deflection angle is greater than or equal to the student's head deflection angle threshold, the suspicious concentration capture model outputs the student's suspicious concentration information;

[0026] When the student's head deflection angle is less than the student's head deflection angle threshold, the suspicious concentration capture model outputs the student's concentration credible information.

[0027] Preferably, the step S303 specifically includes:

[0028] S303-1: Obtaining student concentration data through artificial intelligence, the student concentration data includes the distance between the center of the eyebrows and the lower frame, the angle of the eyes, the ratio of the mouth area, the face area, the pupil diameter variation coefficient, and the emotion index. The pupil diameter variation coefficient is the ratio of the pupil diameter standard deviation to the pupil diameter average value. When the student expresses negative emotions, the emotion index takes a value of 0.5, and when the student expresses positive emotions, the emotion index takes a value of 1. The negative emotions include anger, fear, sadness, and disgust, and the positive emotions include happiness, surprise, enthusiasm, interest, and excitement.

[0029] S303-2: Obtaining student concentration judgment data through the student concentration data, the student concentration judgment data is the ratio of the student concentration data of the previous unified face detection frame to the student concentration data of the next unified face detection frame, and the student concentration judgment data includes the ratio of the distance between the center of the eyebrows and the lower frame, the ratio of the eye angle, the ratio of the mouth area ratio, the ratio of the face area, the ratio of the pupil diameter variation coefficient, and the ratio of the emotion index;

[0030] S303-3: Calculate the student concentration judgment index based on the student concentration judgment data and establish the student concentration judgment model. The calculation formula of the student concentration judgment index is:

[0031]

[0032] Among them, θ is the student concentration judgment index, M is the ratio of the distance between the eyebrow center and the lower border, β z is the ratio of eye angle, Zu is the ratio of mouth area, S t is the face area ratio, P cv is the coefficient of variation of pupil diameter, Q L is the sentiment index ratio;

[0033] S303-4: Preset a student concentration judgment threshold, and obtain the student concentration judgment information by comparing the student concentration judgment index and the student concentration judgment threshold, wherein the student concentration judgment information includes student high concentration information and student low concentration information.

[0034] Preferably, the student concentration judgment index is judged, and when the student concentration judgment index is greater than or equal to the student concentration judgment threshold, the student concentration judgment model outputs the student low concentration information;

[0035] When the student concentration judgment index is less than the student concentration judgment threshold, the student concentration judgment model outputs the student high concentration information.

[0036] An AI-based intelligent teaching device, used to execute the intelligent teaching method described above, characterized in that it includes a teaching video acquisition module, a video projection module, and a concentration detection module;

[0037] The teaching video acquisition module is used to upload teaching topics, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end;

[0038] The video projection module is used to project the matching teaching video in the classroom through three-dimensional holographic projection technology to cooperate with teaching work;

[0039] The concentration detection module is used to perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information at the same time, the student concentration judgment information includes student high concentration information and student low concentration information, obtain the student position corresponding to the output of the student low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student high concentration information.

[0040] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned intelligent teaching method when executing the program.

[0041] A storage medium containing computer executable instructions, which are used to execute the intelligent teaching method described above when executed by a computer processor.

[0042] The beneficial effects of the present invention are:

[0043] (1) Through the cooperation between artificial intelligence and the teaching process, an intelligent classroom is constructed. With the help of modern information equipment, the difficult-to-understand and relatively boring content in the textbooks can be presented in an interesting way, which can enhance students' interest in teaching and enable students to actively follow the teacher's pace and complete classroom tasks step by step. At the same time, it can reduce the workload and burden of teachers and greatly improve teaching efficiency.

[0044] (2) Use AI automatic search technology to search for videos that match the teaching topic, and project them using 3D holographic projection technology to increase the fun of the class, make knowledge easier to understand, and reduce the workload of teachers in pre-class preparation;

[0045] (3) A suspicious concentration capture model is constructed based on the student's head deflection angle and suspicious concentration capture information is output. If it is detected that the student may have low concentration, the next step of concentration detection is performed, thereby reducing the workload of AI processing and improving efficiency;

[0046] (4) The student concentration during the teaching process can be judged by a variety of student concentration data, which makes the judgment more comprehensive and the results more credible. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0048] Figure 1 The present invention is a flowchart of the steps of an intelligent teaching method based on AI cooperation. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0050] The working principle and use process of the present invention:

[0051] See also Figure 1 , an intelligent teaching method based on AI cooperation, including:

[0052] S1: Upload the teaching topic, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end;

[0053] S2: Projecting the matching teaching video in the classroom through three-dimensional holographic projection technology to assist teaching work;

[0054] S3: Perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information, wherein the student concentration judgment information includes student high concentration information and student low concentration information;

[0055] S4: Obtain the student position corresponding to the output of the student's low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student's high concentration information.

[0056] In this embodiment, the student concentration detection is performed based on artificial intelligence and a student concentration judgment model is constructed, and the student concentration judgment information is output at the same time. The student concentration judgment information includes student high concentration information and student low concentration information. It can be implemented by the following steps:

[0057] S301: Preset a concentration detection cycle, obtain a classroom real-time image set through a camera according to the concentration detection cycle, and obtain a unified face detection frame set of the classroom real-time image set through face detection;

[0058] S302: Based on the unified face detection frame set, the student's head deflection angle is obtained, and at the same time, a suspicious concentration capture model is constructed and suspicious concentration capture information is output, wherein the suspicious concentration capture information includes suspicious student concentration information and credible student concentration information. If it is detected that the student may have low concentration, the next step of concentration detection is performed, thereby reducing the workload of AI processing and improving efficiency;

[0059] S303: When the suspicious concentration capture model outputs the student concentration suspicious information, the student concentration judgment model is constructed through the student concentration judgment index and the student concentration judgment information is output, wherein the student concentration judgment information includes the student high concentration information and the student low concentration information.

[0060] In this embodiment, a concentration detection cycle is preset, a classroom real-time image set is obtained through a camera according to the concentration detection cycle, and a unified face detection frame set of the classroom real-time image set is obtained through face detection, which can be specifically implemented by the following steps:

[0061] S301-1: Performing face detection on the classroom real-time image set and obtaining a face detection frame;

[0062] S301-2: Extract the face detection frame and obtain a face detection frame set;

[0063] S301 - 3 : Preset a uniform frame size, scale the face detection frame to the uniform frame size and obtain the uniform face detection frame set.

[0064] In this embodiment, the student's head deflection angle is obtained based on the unified face detection frame set, and a suspicious concentration capture model is constructed and suspicious concentration capture information is output. The suspicious concentration capture information includes suspicious student concentration information and credible student concentration information. The specific implementation can be performed by the following steps:

[0065] S302-1: Locate facial feature points, where the facial feature points include a nose tip feature point, a nose root feature point, a left eye outer feature point, and a right eye outer feature point;

[0066] S302-2: Acquire facial feature point vectors, the facial feature point vectors including a first facial feature point vector, a second facial feature point vector, and a third facial feature point vector, the first facial feature point vector is a vector connecting the nose tip feature point to the nasal root feature point, the second facial feature point vector is a vector connecting the nose tip feature point to the left eye outer feature point, and the third facial feature point vector is a vector connecting the nose tip feature point to the right eye outer feature point;

[0067] S302-3: Calculate the student's head deflection angle based on the facial feature point vector, and the calculation formula is:

[0068]

[0069] Among them, α is the deflection angle of the student's head, is the angle between the first facial feature point vector and the second facial feature point vector, is the angle between the first facial feature point vector and the third facial feature point vector, is the first facial feature point vector, is the second facial feature point vector, is the third facial feature point vector;

[0070] S302-4: Preset a student head deflection angle threshold, build the suspicious concentration capture model by comparing the student head deflection angle and the student head deflection angle threshold, and output the suspicious concentration capture information, wherein the suspicious concentration capture information includes student concentration suspicious information and student concentration credible information;

[0071] Determine the deflection angle of the student's head, and when the deflection angle of the student's head is greater than or equal to the student's head deflection angle threshold, the suspicious concentration capture model outputs the student's suspicious concentration information;

[0072] When the student's head deflection angle is less than the student's head deflection angle threshold, the suspicious concentration capture model outputs credible information about the student's concentration. At this time, the student is relatively focused and no subsequent concentration detection is required.

[0073] In this embodiment, when the suspicious concentration capture model outputs the student concentration suspicious information, the student concentration judgment model is constructed through the student concentration judgment index and the student concentration judgment information is output, and the student concentration judgment information includes the student high concentration information and the student low concentration information, which can be specifically implemented by the following steps:

[0074] S303-1: Obtain student concentration data through artificial intelligence, the student concentration data includes the distance between the center of the eyebrows and the lower frame, the angle of the eyes, the ratio of the mouth area, the face area, the pupil diameter variation coefficient, and the emotion index. The pupil diameter variation coefficient is the ratio of the pupil diameter standard deviation to the pupil diameter average value. When the student expresses negative emotions, the emotion index takes a value of 0.5, and when the student expresses positive emotions, the emotion index takes a value of 1. The negative emotions include but are not limited to anger, fear, sadness, and disgust, and the positive emotions include but are not limited to happiness, surprise, enthusiasm, interest, and excitement. The judgment is more comprehensive and the result is more credible;

[0075] S303-2: Obtaining student concentration judgment data through the student concentration data, the student concentration judgment data is the ratio of the student concentration data of the previous unified face detection frame to the student concentration data of the next unified face detection frame, and the student concentration judgment data includes the ratio of the distance between the center of the eyebrows and the lower frame, the ratio of the eye angle, the ratio of the mouth area ratio, the ratio of the face area, the ratio of the pupil diameter variation coefficient, and the ratio of the emotion index;

[0076] S303-3: Calculate the student concentration judgment index based on the student concentration judgment data and establish the student concentration judgment model. The calculation formula of the student concentration judgment index is:

[0077]

[0078] Among them, θ is the student concentration judgment index, M is the ratio of the distance between the eyebrow center and the lower border, β z is the ratio of eye angle, Zu is the ratio of mouth area, S t is the face area ratio, P cv is the coefficient of variation of pupil diameter, Q L is the sentiment index ratio;

[0079] S303-4: Preset a student concentration judgment threshold, and obtain the student concentration judgment information by comparing the student concentration judgment index and the student concentration judgment threshold, wherein the student concentration judgment information includes student high concentration information and student low concentration information;

[0080] Determine the student concentration determination index, and when the student concentration determination index is greater than or equal to the student concentration determination threshold, the student concentration determination model outputs the student low concentration information;

[0081] When the student concentration judgment index is less than the student concentration judgment threshold, the student concentration judgment model outputs the student high concentration information.

[0082] An intelligent teaching device based on AI cooperation includes a teaching video acquisition module, a video projection module, and a concentration detection module.

[0083] The teaching video acquisition module is used to upload teaching topics, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end;

[0084] The video projection module is used to project the matching teaching video in the classroom through three-dimensional holographic projection technology to cooperate with teaching work;

[0085] The concentration detection module is used to perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information at the same time, the student concentration judgment information includes student high concentration information and student low concentration information, obtain the student position corresponding to the output of the student low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student high concentration information.

[0086] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0087] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0088] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0089] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An intelligent teaching method based on AI cooperation, characterized in that: The implementation of the intelligent teaching method comprises the following steps: S1: Upload the teaching topic, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end; S2: Projecting the matching teaching video in the classroom through three-dimensional holographic projection technology to assist teaching work; S3: Perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information, wherein the student concentration judgment information includes student high concentration information and student low concentration information; S4: Obtain the student position corresponding to the output of the student's low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student's high concentration information.

2. The intelligent teaching method according to claim 1, characterized in that: The step S3 specifically includes: S301: Preset a concentration detection cycle, obtain a classroom real-time image set through a camera according to the concentration detection cycle, and obtain a unified face detection frame set of the classroom real-time image set through face detection; S302: obtaining the student's head deflection angle based on the unified face detection frame set, and constructing a suspicious concentration capture model and outputting suspicious concentration capture information, wherein the suspicious concentration capture information includes the student's suspicious concentration information and the student's credible concentration information; S303: When the suspicious concentration capture model outputs the student concentration suspicious information, the student concentration judgment model is constructed through the student concentration judgment index and the student concentration judgment information is output, wherein the student concentration judgment information includes the student high concentration information and the student low concentration information.

3. The intelligent teaching method according to claim 2, characterized in that: The step S301 specifically includes: S301-1: Performing face detection on the classroom real-time image set and obtaining a face detection frame; S301-2: Extract the face detection frame and obtain a face detection frame set; S301 - 3 : Preset a uniform frame size, scale the face detection frame to the uniform frame size and obtain the uniform face detection frame set.

4. The intelligent teaching method according to claim 2, characterized in that: The step S302 specifically includes: S302-1: Locate facial feature points, where the facial feature points include a nose tip feature point, a nose root feature point, a left eye outer feature point, and a right eye outer feature point; S302-2: Acquire facial feature point vectors, the facial feature point vectors including a first facial feature point vector, a second facial feature point vector, and a third facial feature point vector, the first facial feature point vector is a vector connecting the nose tip feature point to the nasal root feature point, the second facial feature point vector is a vector connecting the nose tip feature point to the left eye outer feature point, and the third facial feature point vector is a vector connecting the nose tip feature point to the right eye outer feature point; S302-3: Calculate the student's head deflection angle based on the facial feature point vector, and the calculation formula is: Among them, α is the student head deflection angle, is the angle between the first facial feature point vector and the second facial feature point vector, is the angle between the first facial feature point vector and the third facial feature point vector, is the first facial feature point vector, is the second facial feature point vector, is the third facial feature point vector; S302-4: Preset a student head deflection angle threshold, construct the suspicious concentration capture model by comparing the student head deflection angle and the student head deflection angle threshold, and output the suspicious concentration capture information, wherein the suspicious concentration capture information includes student concentration suspicious information and student concentration credible information.

5. The intelligent teaching method according to claim 4, characterized in that: Determine the deflection angle of the student's head, and when the deflection angle of the student's head is greater than or equal to the student's head deflection angle threshold, the suspicious concentration capture model outputs the student's suspicious concentration information; When the student's head deflection angle is less than the student's head deflection angle threshold, the suspicious concentration capture model outputs the student's concentration credible information.

6. The intelligent teaching method according to claim 2, characterized in that: The step S303 specifically includes: S303-1: Obtaining student concentration data through artificial intelligence, the student concentration data includes the distance between the center of the eyebrows and the lower frame, the angle of the eyes, the ratio of the mouth area, the face area, the pupil diameter variation coefficient, and the emotion index. The pupil diameter variation coefficient is the ratio of the pupil diameter standard deviation to the pupil diameter average value. When the student expresses negative emotions, the emotion index takes a value of 0.5, and when the student expresses positive emotions, the emotion index takes a value of 1. The negative emotions include anger, fear, sadness, and disgust, and the positive emotions include happiness, surprise, enthusiasm, interest, and excitement. S303-2: Obtaining student concentration judgment data through the student concentration data, the student concentration judgment data is the ratio of the student concentration data of the previous unified face detection frame to the student concentration data of the next unified face detection frame, and the student concentration judgment data includes the ratio of the distance between the center of the eyebrows and the lower frame, the ratio of the eye angle, the ratio of the mouth area ratio, the ratio of the face area, the ratio of the pupil diameter variation coefficient, and the ratio of the emotion index; S303-3: Calculate the student concentration judgment index based on the student concentration judgment data and establish the student concentration judgment model. The calculation formula of the student concentration judgment index is: Among them, θ is the student concentration judgment index, M is the ratio of the distance between the eyebrow center and the lower border, β z is the ratio of eye angle, Zu is the ratio of mouth area, S t is the face area ratio, P cv is the coefficient of variation of pupil diameter, Q L is the sentiment index ratio; S303-4: Preset a student concentration judgment threshold, and obtain the student concentration judgment information by comparing the student concentration judgment index and the student concentration judgment threshold, wherein the student concentration judgment information includes student high concentration information and student low concentration information.

7. The intelligent teaching method according to claim 6, characterized in that: Determine the student concentration determination index, and when the student concentration determination index is greater than or equal to the student concentration determination threshold, the student concentration determination model outputs the student low concentration information; When the student concentration judgment index is less than the student concentration judgment threshold, the student concentration judgment model outputs the student high concentration information.

8. An intelligent teaching device based on AI cooperation, characterized in that: It includes teaching video acquisition module, video projection module and concentration detection module; The teaching video acquisition module is used to upload teaching topics, traverse the entire network through AI automatic search technology, obtain matching teaching videos through cross-modal retrieval and upload them to the teacher's end; The video projection module is used to project the matching teaching video in the classroom through three-dimensional holographic projection technology to cooperate with teaching work; The concentration detection module is used to perform student concentration detection based on artificial intelligence and build a student concentration judgment model, and output student concentration judgment information at the same time, the student concentration judgment information includes student high concentration information and student low concentration information, obtain the student position corresponding to the output of the student low concentration information, and three-dimensionally holographically project the matching teaching video at the student position until the student concentration judgment model outputs the student high concentration information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the intelligent teaching method as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the intelligent teaching method as described in any one of claims 1-7 when executed by a computer processor.

Images