Big data interactive teaching and training methods

Abstract

The present invention discloses a big data interactive teaching training method, which comprises the following steps: step one: constructing a teaching training platform on a cloud server, developing teacher review, student review, and interconnected teaching subsystems, and writing an AI algorithm; step two: the teacher inputs the course video in the subsystem, and the student views the video and scores it; step three: the teacher's review process of the student's homework is input into the system, the platform calls the algorithm, and the teacher's review process is trained and learned; step four: the platform trains a model, calls the AI ​​reference model to review the homework, the student makes the course notes, the system records the original author and includes it in the performance assessment, the AI, teachers and students score the notes, and the high-scoring and high-quality notes are provided for students to refer to; step five: the video and notes with high scores are pushed to the interconnected teaching subsystem by the platform for reference by teachers and students in various places. According to the present invention, it has the ability to change the traditional review mode of interactive teaching training and stimulate the teaching interaction between teachers and students.

Description

Technical Field

[0001] The present invention relates to the field of AI technology, and in particular to a big data interactive teaching and training method. Background Art

[0002] With the nationwide popularization of Internet of Things technology, the "teaching" and "learning" between teachers and students on campus are no longer limited to the classroom or offline. With the use of Internet of Things technology, many courses and practical training, and even related homework submission and correction, can be completed online. The "teaching" and "learning" between teachers and students in the same school or even different schools, and between students can also be carried out online. At present, with the gradual popularization of 5G technology and the vigorous development of AI intelligence, most teachers of the existing teaching and training systems on the market still mark homework in the traditional way. Teachers cannot mark a large number of students' homework in a short period of time, and give detailed answers to each homework question of each student's homework. If students have questions about courses, practical training content, and homework, teachers can only give simple answers to a large number of students' questions in a short period of time, and cannot answer a large number of questions quickly and in detail. If a student creates high-quality courses or practical training notes, other students are more likely to plagiarize, and teachers cannot distinguish between the original creators and plagiarists, and cannot bring any advantages in grades to the original students themselves, and cannot stimulate the interaction of "teaching" and "learning" between students and students, and between teachers and students. Therefore, it is necessary to design a big data interactive teaching training system that can use AI technology to review a large number of student assignments in a very short time, provide detailed step-by-step analysis for multiple assignments with different answer contents for students to refer to and review, and incorporate students' high-quality original course notes into grade assessment. Summary of the invention

[0003] The purpose of the present invention is to provide a big data interactive teaching and training system and method to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a big data interactive teaching training method, the method comprising the following steps:

[0005] Step 1: Build an interactive teaching training platform on the cloud server, establish a cloud database, develop a teacher teaching review subsystem, a student performance review subsystem, and an interconnected teaching subsystem, and write an AI text recognition algorithm;

[0006] Step 2: The teacher enters the course video in the teacher teaching review subsystem. The student selects to view all the course videos posted by the teacher to the system through the student performance review subsystem. After watching the course video, the student evaluates and rates the teacher's course video on the system.

[0007] Step 3: The teacher's review process and results of the student's course assignments or practical training content are all entered into the teacher teaching review subsystem. The subsystem feeds all the data back to the platform. The platform calls the AI ​​text recognition algorithm to train and learn the teacher's review process and results, and train and learn all the content described in step 2;

[0008] Step 4: After the interactive teaching training platform has trained the course model, when students submit course assignments or training tasks to the system, the platform calls AI to review the students' assignments with reference to the course model and gives a reasonable analysis of the students' assignments. Students take course notes, and AI, teachers, and classmates jointly evaluate the students' course notes.

[0009] Step 5: Highly rated teaching course videos and student course notes will be pushed to the Internet teaching subsystem by the interactive teaching training platform for reference by teachers and students around the world. Using the Internet teaching subsystem, users will give evaluations and ratings to course videos and notes, and high-quality courses and notes will be recommended on the Internet teaching subsystem first.

[0010] According to the above technical solution, the steps of building an interactive teaching training platform on a cloud server, establishing a cloud database, developing a teacher teaching review subsystem, a student performance review subsystem, and an interconnected teaching subsystem, and writing an AI text recognition algorithm include:

[0011] Build an interactive teaching and training platform on the cloud server;

[0012] Establish a cloud database on the SQL Server database;

[0013] Developed within the system:

[0014] Teacher teaching review subsystem and student performance review subsystem;

[0015] The two subsystems are mainly used by teachers and students on the same campus;

[0016] Developing interconnected teaching subsystems within the system;

[0017] The system is mainly used by users around the world;

[0018] The above three subsystems are deployed on mobile APP and PC;

[0019] Write AI text recognition algorithm on the interactive teaching and training platform;

[0020] The algorithm follows the course content and coursework content stored in the database;

[0021] Continuous training in learning courses and coursework texts;

[0022] The AI ​​text recognition algorithm then identifies and compares students’ homework texts based on the trained model.

[0023] According to the above technical solution, the teacher records the course video in the teacher teaching review subsystem, and the students watch the course video and evaluate and score it through the student performance review subsystem, including:

[0024] Campus teachers enter the courses or training courses through the teacher teaching review subsystem;

[0025] Students use the APP to view all teaching course videos on the interactive teaching training platform;

[0026] After students finish watching the teaching course video on the APP;

[0027] The system automatically pops up a teaching course video evaluation and rating pop-up window;

[0028] Students rate the teaching course video entered by the teacher in the pop-up window;

[0029] judge:

[0030] The completeness of the video's explanation of the course content Q, the degree to which the video analyzes the course knowledge points W, the attractiveness of the video content to students E, the wonderfulness of the course explanation R, whether the course can cultivate students' interest T, and students' rating of the course video Y;

[0031] Students' evaluation and rating of teaching course videos are included in their regular performance assessment.

[0032] According to the above technical solution, the teacher's review process and review results of student course assignments or practical training content are all entered into the teacher teaching review subsystem. The subsystem feeds back all data to the platform. The platform calls the AI ​​text recognition algorithm to train the teacher's review process and review results, and train the teacher's explanation process of the course content, including:

[0033] Students upload and submit course assignments or practical training tasks assigned by teachers in the system;

[0034] Teachers can view the course assignments or practical training tasks submitted by students on the system through the teacher teaching review subsystem;

[0035] Teachers review course assignments or practical training tasks and give review results;

[0036] At the same time, the teacher teaching review subsystem records the teacher's review process and results for each course assignment or practical training task.

[0037] According to the above technical solution, the platform calls the AI ​​text recognition algorithm to train the learning teacher's review process and review results, and trains the learning teacher's explanation process of the course content, including:

[0038] The interactive teaching and training platform uses AI text recognition algorithms;

[0039] According to the data stored in the data table, the AI ​​text recognition algorithm is trained and learned, and the teacher explains the course content, explains the knowledge points, and cultivates students' learning interests;

[0040] Through repeated training of the "annealing algorithm", learn from the teacher's teaching course video;

[0041] Gradually train a course knowledge point analysis model;

[0042] Teacher administrators select the best training results model through the interactive teaching and training platform and store it in the "Course Model Data Table";

[0043] Similarly, AI calls the teacher's marking process and marking result data of the homework in the "Course Assignment Data Table";

[0044] Through the annealing algorithm, the learning model is repeatedly trained to gradually train the analysis and correction model of course assignments and practical training tasks;

[0045] A large number of models are trained, and the administrator selects the best model and stores it in the "Course Model Data Table".

[0046] According to the above technical solution, after the interactive teaching training platform trains the course model, when students submit course assignments or training tasks to the system, the platform calls AI to refer to the course model to mark the students' assignments and gives a reasonable analysis of the students' assignments. Students make course notes, and AI, teachers, and classmates jointly evaluate the students' course notes. The excellent course notes are provided for students to study, refer to, and discuss together, including the following steps:

[0047] The interactive teaching and training platform has a reference model;

[0048] Afterwards, when students submit coursework or practical training tasks to the system;

[0049] Teachers can still manually mark assignments for students and give marking results;

[0050] The interactive teaching and training platform uses AI text recognition algorithms to automatically grade students' homework, give graded results, and provide detailed explanations of homework or training tasks;

[0051] After students submit their homework or practical training tasks;

[0052] The platform calls the AI ​​text recognition algorithm;

[0053] The algorithm makes a detailed comparison between the trained model and the homework or practical training tasks submitted by the students;

[0054] The algorithm calls all the data in the model library and compares each point in the homework or training task one by one;

[0055] if:

[0056] AI recognizes and analyzes that the student has completed the homework correctly and the steps are perfect. AI marks the knowledge points used in this homework, which is convenient for students to review later;

[0057] if:

[0058] AI recognized and analyzed that the student only answered the questions correctly, but the steps were incomplete. AI marked the knowledge points and detailed solution steps for this homework.

[0059] if:

[0060] AI identifies and analyzes the homework questions that students have answered incorrectly. AI marks the questions as wrong and gives the correct solution steps and knowledge points used.

[0061] if:

[0062] AI recognition and analysis shows that students did not do the questions, but only used them to search for questions. AI does not make any analysis to prevent students from using the system to plagiarize homework;

[0063] After AI finishes marking students' homework, it calculates the score for each student's homework based on the "analysis and correction model of course homework and practical training tasks";

[0064] Students make course or practical notes based on their understanding of the course;

[0065] Teachers and other students will rate and evaluate the student's notes based on how clearly the notes describe the course knowledge points, how clear the problem-solving ideas are, and how clear the practical training steps are explained;

[0066] Notes with higher scores will be recommended to other students first;

[0067] AI calls the data in the model library and compares the knowledge points described in the notes;

[0068] Score your notes based on how thoroughly they explain the knowledge points;

[0069] The course notes or practical training notes made by students are also included in the assessment of their regular grades.

[0070] According to the above technical solution, the teaching course videos and student course notes with high scores will be pushed to the Internet teaching subsystem by the interactive teaching training platform for reference by teachers and students around the world. Using the Internet teaching subsystem, users give evaluation and ratings to course videos and notes. The steps of giving priority to recommending high-quality courses and notes on the Internet teaching subsystem include:

[0071] In the data table, the platform filters the teaching course videos and course notes under the same course from high to low according to the ratings;

[0072] The interactive teaching and training platform selects videos and notes with high ratings;

[0073] Open data to the interconnected teaching subsystem;

[0074] Teachers and students around the world have access to only the high-scoring videos and notes selected by the platform through the interconnected teaching subsystem;

[0075] After teachers and students around the world have viewed the teaching course videos and course notes;

[0076] Rating course videos and notes in the subsystem;

[0077] The course videos and notes connected to the Internet teaching subsystem are screened again to determine their ratings;

[0078] Those with high scores will be recommended by the platform in the Internet teaching subsystem for reference, study and discussion by teachers and students around the world.

[0079] According to the above technical solution, the teacher teaching review subsystem includes:

[0080] Teaching video recording module, used by teachers to synchronously input teaching content into the system;

[0081] The teaching video evaluation module is used by teachers to view students' evaluation and rating of their recorded lessons, and teachers can adjust the course content based on the evaluation;

[0082] Review and correction module, used by teachers to review students' course assignments and practical training tasks;

[0083] The teacher-student interaction module is used for teachers and students to exchange course knowledge points.

[0084] According to the above technical solution, the student performance evaluation subsystem includes:

[0085] Teaching video viewing module, used for students to view teaching course videos;

[0086] Teaching video evaluation module, used for students to evaluate and rate course videos;

[0087] Assignment submission module, used by students to submit course assignments and practical training tasks;

[0088] Homework grading module, which is used by students to view the grading records of their homework by teachers or AI;

[0089] The course notes module is used for students to publish their learning experience or notes on courses and practical training.

[0090] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by setting up a teaching training platform on a cloud server, develops teacher review, student review, and interconnected teaching subsystems, writes AI algorithms, teachers enter course videos in the subsystem, students view videos and score them, the teacher's review process of student assignments is entered into the system, the platform calls the algorithm, trains and learns the teacher's review process, the platform trains a model, calls the AI ​​reference model to review assignments, students make course notes, the system records the original author and includes it in the performance assessment, AI, teachers and students score the notes, high-scoring and high-quality notes are provided for students to refer to, and high-scoring videos and notes are pushed to the interconnected teaching subsystem by the platform for reference by teachers and students from all over the country, so that the existing system's teacher reviewing homework method during big data interactive teaching training is separated from the traditional method, AI reviews a large amount of homework in a very short time and makes a detailed analysis of each question at the same time, records the students who publish high-quality notes, recommends high-quality courses and notes to the interconnected system, greatly improves the efficiency of reviewing homework, and establishes a better teaching interactive relationship for teachers and students in the same school or different schools. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0092] Figure 1 A flowchart of a big data interactive teaching training method provided in the first embodiment of the present invention;

[0093] Figure 2 A schematic diagram of the module composition of a big data interactive teaching and training system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0094] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0095] Embodiment 1: Figure 1This is a flowchart of a big data interactive teaching training system provided in Example 1 of the present invention. This embodiment can be applied to any teaching scenario. The method can be executed by a big data interactive teaching training system provided in this embodiment. Figure 1 As shown, the method specifically comprises the following steps:

[0096] Step 1: Build an interactive teaching training platform on the cloud server, establish a cloud database, develop a teacher teaching review subsystem, a student performance review subsystem, and an interconnected teaching subsystem, and write an AI text recognition algorithm;

[0097] In an embodiment of the present invention, an interactive teaching training platform is constructed on a cloud server, a cloud database is established on a SQL Server, a teacher teaching review subsystem and a student performance review subsystem are developed within the system, and the two subsystems are mainly used by teachers and students in the same campus. An interconnected teaching subsystem is developed within the system, and the system is mainly used by users around the world. The above three subsystems are deployed on mobile APP and PC, and an AI text recognition algorithm is written on the platform. The algorithm continuously trains and learns courses and course assignments according to the course content and course assignments stored in the database, and the training results model is stored in the database. The AI ​​text recognition algorithm then identifies and compares students' homework texts based on the trained model.

[0098] Step 2: The teacher enters the course video in the teacher teaching review subsystem, and the student chooses to view all the course videos, and evaluates and rates the course videos after watching them;

[0099] S21: In an embodiment of the present invention, campus teachers enter classes or training courses through the teacher teaching review subsystem, and students use the APP to view all teaching course videos on the interactive teaching training platform. After the students finish watching the teaching course videos, the student performance review subsystem automatically pops up a teaching course video evaluation and scoring pop-up window, and students evaluate and score the course video in the pop-up window to judge: the completeness of the video's explanation of the course content Q, the degree of analysis of the course knowledge points W by the video, the degree of attractiveness of the video content to students E, the degree of excitement of the course explanation R, whether the course can cultivate students' interest T, and the student's score for the course video Y. The student's evaluation and scoring of the course video is included in the student's regular performance assessment to maintain the interactive relationship between teachers and students on campus.

[0100] Step 3: The teacher's review process and results of the student's course assignments or practical training content are all entered into the teacher teaching review subsystem. The subsystem feeds all the data back to the platform. The platform calls the AI ​​text recognition algorithm to train and learn the teacher's review process and results, and train and learn all the content described in step 2;

[0101] In an embodiment of the present invention, students upload and submit course assignments or practical training tasks on the student performance review subsystem, and teachers review the course assignments or practical training tasks and give review results. At the same time, the teacher's review process and review results of the course assignments or practical training tasks are entered into the teacher's teaching review subsystem. The interactive teaching training platform calls the AI ​​text recognition algorithm to train the learning teacher's explanation process of the course content, the elaboration of knowledge points, and the cultivation of students' learning interest. The teacher's teaching course video is repeatedly trained through the "annealing algorithm" to gradually train the course knowledge point analysis model. The teacher administrator selects the best training result model through the interactive teaching training platform and stores it in the "course model data table". Similarly, AI calls the teacher's review process and review result data of the homework in the "course homework data table", repeatedly trains the learning model through the annealing algorithm, and gradually trains the analysis and correction model of the course assignments and practical training tasks. Among the large number of trained models, the administrator selects the best model and stores it in the data table.

[0102] Step 4: After the interactive teaching training platform trains the course model, students submit course assignments or training tasks to the system. The platform calls AI to mark students' assignments with reference to the course model and gives reasonable analysis to students' assignments. Students make course notes, and AI, teachers, and classmates jointly evaluate students' course notes.

[0103] S41: In the embodiment of the present invention, the interactive teaching and training platform has a reference model. After that, when students submit course assignments or training tasks to the system, teachers can still manually mark the assignments for students and give marking results. What's more, it is also a feature of this system: the interactive teaching and training platform calls the AI ​​text recognition algorithm to automatically mark the assignments for students, give marking results, and make detailed explanations for the assignments or training tasks. The platform calls the AI ​​text recognition algorithm, and the algorithm compares the trained model with the assignments or training tasks submitted by students in detail. The algorithm calls all the data in the model library and compares each point in the assignments or training tasks one by one. The AI ​​text recognition algorithm analyzes each point in each assignment.

[0104] S42: If: AI recognizes and analyzes that the student has done the homework correctly and the steps are complete, AI will mark the knowledge points used for this homework; if: AI recognizes and analyzes that the homework steps are incomplete, AI will mark the knowledge points for this homework and mark the detailed problem-solving steps; if: AI recognizes and analyzes that the student has done the homework wrong, AI will add a wrong question mark to this question and give the correct problem-solving steps and the knowledge points used; if: AI recognizes and analyzes that the student has not done the question and is just searching for questions, AI will not make any analysis to prevent students from using the system to plagiarize homework; after AI has reviewed the students' homework, it will calculate the score for each student's homework according to the "analysis and correction model of course homework and practical training tasks";

[0105] S43: Students make course or practical training notes in the system according to their understanding of the course. Teachers and other classmates rate and evaluate the student's notes according to the clarity of the description of course knowledge points, the clarity of problem-solving ideas, and the clarity of the practical training steps. Notes with higher scores are recommended to other students. AI calls the data in the model library, compares the knowledge points explained in the notes, and rates the notes according to the comprehensiveness of the knowledge points. The course or practical training notes made by students are also included in the assessment of regular grades to maintain teaching interaction between students and between students and teachers. Excellent notes are provided for campus teachers and students to study and discuss together.

[0106] Step 5: Highly rated teaching course videos and student course notes will be pushed to the Internet teaching subsystem by the interactive teaching training platform for reference by teachers and students around the world. Using the Internet teaching subsystem, users will give evaluation and ratings to course videos and notes. High-quality courses and notes will be recommended on the Internet teaching subsystem first.

[0107] In the embodiment of the present invention, the platform screens the teaching course videos and course notes under the same course in the data table according to the scores from high to low. The interactive teaching training platform screens out the videos and notes with high scores, and opens the data to the interconnected teaching subsystem. Teachers and students from all over the world have the right to access only the high-scoring videos and notes screened by the platform through the interconnected teaching subsystem. While protecting the intellectual property rights of the campus, it also shares high-quality educational resources for users from all over the world. After viewing the teaching course videos and course notes, teachers and students from all over the world evaluate and score the course videos and notes in the subsystem, and screen the course videos and notes connected to the interconnected teaching subsystem again. The platform gives priority to recommending the high-scoring videos and notes in the interconnected teaching subsystem for reference, study and discussion by teachers and students from all over the world.

[0108] Compared with other systems available on the market, this big data interactive teaching and training system innovatively introduces AI text recognition algorithms. AI continuously and repeatedly trains and learns teachers' explanations of course knowledge points and the process of marking homework or training tasks. Ultimately, the system can automatically mark homework for students and explain all the knowledge points corresponding to each homework question to students. In this way, the system can mark homework for a large number of students in a very short time and analyze the detailed problem-solving steps, problem-solving ideas, and knowledge points used for each question. This is something that traditional teaching and training systems cannot achieve. At the same time, it saves teachers a lot of time in marking homework and helps them improve their English. During the time when students are answering questions, teachers have more energy to devote to scientific research or other aspects; this big data interactive teaching training system also innovatively introduces the course note sharing function. Students share their learning experience and summary notes, which can improve their own regular grades and stimulate their interest in learning. Students, teachers, and AI can all participate in the evaluation, scoring and discussion of teaching courses and course notes. In the system, the three parties can discuss and exchange experiences with each other, which can well establish interactive relationships between students and between students and teachers, and continuously consolidate the interactive relationships in an incentive way to ensure that the system can run for a long time.

[0109] Embodiment 2: Embodiment 2 of the present invention provides a big data interactive teaching training system. Figure 2 A schematic diagram of the module composition of a big data interactive teaching and training system provided in the second embodiment of the present invention is shown in FIG. Figure 2 As shown, the system includes:

[0110] The cloud database is used to store various data generated in the system. A data table is established in the cloud database to classify and store various data;

[0111] AI text recognition algorithm is used to repeatedly train and learn teaching course videos and the process and results of teachers' review of students' homework or practical training tasks, so as to train the best course knowledge point model and course homework or practical training task analysis and correction model, which is used to analyze and review students' homework, provide students with problem-solving ideas, problem-solving steps, and knowledge points needed to solve problems, and score students' homework, course videos, and students' course notes;

[0112] Interactive teaching and training platform, used to provide functional interface services for other modules and subsystems, calling various subsystems and submodules within the system to achieve the purpose of processing the overall data of the system;

[0113] The teacher teaching review subsystem is used for teachers to record teaching course videos, review students' course assignments, review practical training tasks, evaluate and score students' course notes or practical training notes, and interact and discuss with students;

[0114] The student performance review subsystem is used for students to view teaching course videos, submit course assignments, submit practical training tasks, evaluate and score teaching course videos, view the review of their homework by teachers or AI, write course or practical training experience or notes, and interact with teachers and other students;

[0115] The interconnected teaching subsystem is used by teachers and students around the world to view teaching course videos, course notes, and practical training notes, communicate and discuss with other users, and evaluate and rate course videos and notes;

[0116] In some embodiments of the present invention, the teacher teaching review subsystem includes:

[0117] Teaching video recording module, used by teachers to synchronously input teaching content into the system;

[0118] The teaching video evaluation module is used by teachers to view students' evaluation and rating of their recorded lessons, and teachers can adjust the course content based on the evaluation;

[0119] Review and correction module, used by teachers to review students' course assignments and practical training tasks;

[0120] Teacher-student interaction module, used for teachers and students to exchange course knowledge points and practical training content;

[0121] In some embodiments of the present invention, the student performance review subsystem includes:

[0122] Teaching video viewing module, used for students to view teaching course videos;

[0123] Teaching video evaluation module, used for students to evaluate and rate course videos;

[0124] Assignment submission module, used by students to submit course assignments and practical training tasks;

[0125] Homework grading module, which is used by students to view the grading records of their homework by teachers or AI;

[0126] The course notes module is used for students to publish their learning experience or notes on courses and practical training.

[0127] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0128] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A big data interactive teaching training method, applied to a big data interactive teaching training system, characterized by: The method comprises the following steps: Step 1: Build an interactive teaching training platform on the cloud server, establish a cloud database, develop teacher teaching review, student performance review, and interconnected teaching subsystems, and write AI text recognition algorithms; Step 2: The teacher enters the course video in the teacher teaching review subsystem, and the students evaluate and score the course video through the student performance review subsystem. The teacher teaching review subsystem includes: Teaching video recording module, used by teachers to synchronously input teaching content into the system; The teaching video evaluation module is used by teachers to view students' evaluation and rating of their recorded lessons, and teachers can adjust the course content based on the evaluation; Review and correction module, used by teachers to review students' course assignments and practical training tasks; Teacher-student interaction module, used for teachers and students to exchange course knowledge points; The student performance review subsystem includes: Teaching video viewing module, used for students to view teaching course videos; Teaching video evaluation module, used for students to evaluate and rate course videos; Assignment submission module, used by students to submit course assignments and practical training tasks; Homework grading module, which is used by students to view the grading records of their homework by teachers or AI; The course notes module is used for students to publish their learning experience or notes on courses and practical training; Step 3: The teacher's review process and results of the student's course assignments or practical training content are all entered into the teacher teaching review subsystem. The subsystem feeds all data back to the platform. The platform calls the AI ​​text recognition algorithm to train and learn the teacher's review process and results, and train and learn the recorded course video described in step 2; Step 4: After the interactive teaching training platform has trained the course model, when students submit course assignments or training tasks to the system, the platform calls AI to refer to the course model to mark the students' assignments and give reasonable analysis to the students' assignments. Students make course notes, and AI, teachers, and classmates jointly evaluate the students' course notes. Excellent course notes are provided for students to study, refer to, and discuss together; Step 5: Highly rated teaching course videos and student course notes will be pushed to the Internet teaching subsystem by the interactive teaching training platform for reference by teachers and students around the world. Using the Internet teaching subsystem, users will give evaluation and ratings to course videos and notes. High-quality courses and notes will be recommended on the Internet teaching subsystem first. The steps of constructing an interactive teaching training platform on a cloud server, establishing a cloud database, developing teacher teaching review, student performance review, and interconnected teaching subsystems, and writing an AI text recognition algorithm include: constructing an interactive teaching training platform on a cloud server; Establish a cloud database on the SQL Server database; Developed within the system: Teacher teaching review subsystem and student performance review subsystem; Developing interconnected teaching subsystems within the system; The teacher teaching review subsystem, student performance review subsystem, and interconnected teaching subsystem are all deployed on mobile APP and PC; Write AI text recognition algorithm on the interactive teaching and training platform; The AI ​​text recognition algorithm follows the course content and coursework content stored in the database; Continuous training in learning courses and coursework texts; The AI ​​text recognition algorithm then identifies and compares students’ homework texts based on the trained model; The teacher records the course video in the teacher teaching review subsystem, and the student watches the course video and evaluates and scores it through the student performance review subsystem, including: the campus teacher records the class course or training course through the teacher teaching review subsystem; Students use the APP to view all teaching course videos on the interactive teaching training platform; After students have watched the teaching course video; The student performance review subsystem automatically pops up a pop-up window for evaluating and grading teaching course videos; Students rate the teaching course video in the pop-up window; judge: The completeness of the video’s explanation of the course content Q, the degree to which the video analyzes the course knowledge points W, the attractiveness of the video content to students E, the wonderfulness of the course explanation R, whether the course can cultivate students’ interest T, and students’ rating of the course video Y; Students' evaluation and rating of the teaching course videos recorded by teachers will be included in the students' regular performance assessment; The teacher's review process and review results of the student's course assignments or practical training content are all entered into the teacher teaching review subsystem. The subsystem feeds all data back to the platform. The platform calls the AI ​​text recognition algorithm to train the learning teacher's review process and review results, and train the learning teacher's explanation process of the course content, including: students upload and submit the course assignments or practical training tasks assigned by the teacher on the student performance review subsystem; Teachers pass the teacher teaching evaluation subsystem; View the coursework or practical training tasks submitted by students on the system; Teachers review course assignments or practical training tasks and give review results; At the same time, the teacher teaching review subsystem records the teacher's review process and review results for each course assignment or practical training task; The platform calls the AI ​​text recognition algorithm, trains the learning teacher's explanation process of the course content, and trains the learning teacher's review process and review results, including: the interactive teaching training platform calls the AI ​​text recognition algorithm; According to the data stored in the data table, the AI ​​text recognition algorithm is trained and learned, and the teacher explains the course content, explains the knowledge points, and cultivates students' learning interests; Through repeated training of "annealing algorithm", learn from the teacher's teaching course video; Gradually train a course knowledge point analysis model; Teacher administrators select training achievement models through the interactive teaching training platform and store them in the "Course Model Data Table"; Similarly, AI calls the teacher's review process and review result data of the homework in the "Course Assignment Data Table"; Through the annealing algorithm, the learning model is repeatedly trained to gradually train the analysis and correction model of course assignments and practical training tasks; A large number of models are trained, and the administrator selects the model and stores it in the "Course Model Data Table"; After the interactive teaching training platform trains the course model, when the student submits the course homework or training task to the system, the platform calls AI to mark the homework for the student with reference to the course model, and gives a reasonable analysis of the student's homework. The student makes course notes, and AI, teachers, and classmates jointly evaluate the student's course notes, including: the interactive teaching training platform has a reference model; Afterwards, when students submit coursework or practical training tasks to the system; Teachers still manually mark students' homework and give marking results; The interactive teaching and training platform uses AI text recognition algorithms to automatically grade students' homework, give graded results, and provide detailed explanations of homework or training tasks; After students submit their homework or practical training tasks; The platform calls the AI ​​text recognition algorithm; The AI ​​text recognition algorithm makes a detailed comparison between the trained model and the homework or practical training tasks submitted by students; The AI ​​text recognition algorithm calls all the data in the model library and compares each point in the homework or training task one by one; AI text recognition algorithm analyzes every point in each assignment; AI recognizes and analyzes that the student has completed the homework correctly and the steps are perfect, and AI marks the knowledge points used in this homework; AI recognized and analyzed that the student only answered the questions correctly, but the steps were not perfect. AI marked the knowledge points and detailed solution steps for the homework. AI identifies and analyzes the homework questions that students have answered incorrectly. AI marks the questions as wrong and gives the correct solution steps and knowledge points used. AI recognition and analysis shows that students did not do the questions, but only used them to search for questions. AI does not make any analysis to prevent students from using the system to plagiarize homework; After AI finishes marking students' homework, it calculates the score for each student's homework based on the "analysis and correction model of course homework and practical training tasks"; Students make course or practical notes based on their understanding of the course; Teachers and other students will rate and evaluate the student's notes based on how clearly the notes describe the course knowledge points, how clear the problem-solving ideas are, and how clear the practical training steps are explained; Notes with higher scores will be recommended to other students first; AI calls the data in the model library and compares the knowledge points described in the notes; Score your notes based on how thoroughly they explain the knowledge points; The course notes or practical training notes made by students are also included in the assessment of their regular grades; The teaching course videos and student course notes with high scores will be pushed to the Internet teaching subsystem by the interactive teaching training platform for reference by teachers and students around the world. Using the Internet teaching subsystem, users give evaluation scores to course videos and notes, and high-quality courses and notes are recommended on the Internet teaching subsystem in priority. The steps include: the platform selects teaching course videos and course notes under the same course from high to low according to the scores in the data table; The interactive teaching and training platform selects videos and notes with high ratings; Open data to the interconnected teaching subsystem; Teachers and students around the world have access to only the high-scoring videos and notes selected by the platform through the interconnected teaching subsystem; After teachers and students around the world have viewed the teaching course videos and course notes; Rating course videos and notes in the subsystem; The course videos and notes connected to the Internet teaching subsystem are screened again to determine their ratings; Those with high scores will be recommended by the platform in the Internet teaching subsystem for reference, study and discussion by teachers and students around the world; The system also includes: The AI ​​text recognition algorithm is used to repeatedly train and learn teaching course videos and the teacher's marking process and results of student homework or practical training tasks. The trained course knowledge point model and course homework or practical training task analysis and correction model are used to parse and mark student homework, provide students with problem-solving ideas, problem-solving steps, and knowledge points needed to solve problems, and score student homework, course videos, and student course notes.

Images