Teacher teaching auxiliary system based on artificial intelligence and teaching file generation and optimization method thereof

Abstract

The invention provides a teacher teaching auxiliary system based on an artificial intelligence large language model and a teaching file generation and optimization method thereof. The system comprises an input module, a teaching file generation module based on a large language model, an intelligent test question generation and auditing module, a course content optimization module and a teaching file management module. The system automatically generates teaching files, such as a teaching outline, a talent training scheme, a teaching calendar and the like, by receiving basic course information and teaching targets input by a teacher and utilizing a large language model; meanwhile, the system automatically generates and audits the test questions according to the course target, and ensures the rationality and coverage rate of the test questions. The system can also provide teaching content optimization suggestions by analyzing classroom feedback and student performance, and dynamically adjust a teaching calendar according to actual teaching progress. In addition, the system provides a multi-version teaching file management function, which is convenient for teachers to edit, share and control versions of files. According to the invention, the teaching file generation and management efficiency is improved, the teaching content and process are optimized through an intelligent function, the workload of teachers is reduced, and the teaching quality is improved.

Description

Technical Field

[0001] The present invention relates to the fields of educational technology and artificial intelligence, and in particular to a teacher teaching assistance system based on an artificial intelligence large language model and a teaching file generation and optimization method thereof, which are used to help teachers automatically generate teaching files, intelligently generate and review test questions, and optimize teaching content and progress management. Background Art

[0002] In university teaching, teachers need to write and manage a large number of teaching documents, such as syllabus, talent training program, teaching manual, teaching calendar, etc. The writing of these documents usually takes a lot of time, and it is necessary to ensure that they are consistent with school requirements and course objectives. In addition, test question generation and review also require teachers to complete them manually according to teaching objectives, which increases the workload. Although the existing system has certain teaching assistance functions, it still has deficiencies in automation and intelligence, especially the lack of intelligent support for content generation, review and optimization. In recent years, with the development of large language models, the model has shown strong capabilities in text generation, semantic understanding, etc. Introducing large language models into teaching assistance systems can greatly improve the automation level of the system, help teachers quickly generate high-quality teaching documents, generate and review test questions, and optimize teaching content and calendars based on classroom feedback, thereby reducing the workload of teachers and improving teaching efficiency. 。 Summary of the invention

[0003] The purpose of the present invention is to provide a teacher teaching assistance system based on an artificial intelligence large language model and a teaching file generation and optimization method thereof, which can intelligently generate teaching files that meet format requirements, automatically generate and review test questions, analyze classroom feedback and provide optimization suggestions, and ultimately realize the intelligent and automated management of teaching files and adjustment of teaching content.

[0004] To achieve the above object, the present invention provides the following technical solutions: Teacher teaching assistance system based on large language model, including: Input module: used to receive basic course information, teaching objectives and related requirements input by teachers; Teaching document generation module based on large language model: Based on the text generation capability of the large language model and preset templates, it automatically generates teaching documents, including teaching syllabus, talent training plan, teaching calendar, teaching manual, and course content and goal docking report; Intelligent test question generation and review module: automatically generates test questions that meet the requirements based on course objectives and teaching content, and uses a large language model to review the rationality and difficulty of the test questions; Course content optimization module: Analyzes teaching feedback, classroom performance and teaching progress through a large language model, provides teaching optimization suggestions, and dynamically adjusts the teaching calendar and course schedule; Teaching file management module: used to manage and store generated teaching files, supporting version control, sharing and historical version recovery functions.

[0005] The method for automatically generating and optimizing teaching documents comprises the following steps: obtaining course information and teaching objectives input by teachers; generating teaching documents through a large language model; automatically generating and reviewing test questions; optimizing teaching content and adjusting the teaching calendar based on feedback. Beneficial Effects

[0006] The present invention has the following advantages: Intelligent teaching document generation: The system can generate complete and formatted teaching documents based on a small amount of input through a large language model, greatly reducing the workload of teachers.

[0007] Automatic test question generation and review: Generate and review test questions through a large language model to ensure that the test questions are consistent with the course objectives and provide semantic rationality checks.

[0008] Teaching optimization and feedback: By analyzing classroom performance and student feedback, the system can automatically optimize teaching content, dynamically adjust the teaching calendar, and improve teaching effectiveness and flexibility.

[0009] File management function: The system supports version control and sharing of teaching files, making it convenient for teachers to manage and modify them. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 :Schematic diagram of the system architecture of the teacher teaching assistance system based on the large language model.

[0011] Figure 2 :Flowchart of teaching file generation and optimization.

[0012] Figure 3 :Flowchart of intelligent test question generation and review. DETAILED DESCRIPTION

[0013] Example 1: Teaching file generation.

[0014] The teacher inputs the basic information of the course, such as the course name, class schedule, and teaching objectives, through the input module. The teaching document generation module based on the large language model automatically expands this information into a syllabus, talent training program, and teaching calendar that meet the school's requirements. The large language model uses its powerful natural language processing capabilities to convert simple course information into detailed course content descriptions and arrangements. For example, when the teacher inputs "the course goal is to cultivate students' numerical simulation capabilities for material forming", the system can automatically generate a complete syllabus, including course objectives, teaching plans, assessment methods, and other content.

[0015] Embodiment 2: Intelligent test question generation and review.

[0016] Before the final exam, teachers can request a set of final exam questions through the system. The intelligent question generation and review module uses a large language model to automatically generate various types of questions based on teaching objectives and course content, including multiple-choice questions, short-answer questions, and case analysis. The system uses semantic analysis and difficulty matching algorithms to review the rationality of the generated questions, ensuring that the questions cover all teaching objectives and avoid duplication and deviation. Finally, the system will generate a set of questions that meet the requirements and provide an analysis report on the difficulty and coverage of the questions.

[0017] Example 3: Teaching content optimization and calendar adjustment.

[0018] During the teaching process, the system collects students' class participation, homework submission and test scores in real time. The course content optimization module analyzes this data through the large language model and provides teaching optimization suggestions. For example, if students have difficulty understanding a certain chapter, the system will suggest that teachers increase the explanation time in subsequent courses. In addition, the system dynamically adjusts the teaching calendar according to the actual teaching progress and feedback, such as adding additional review classes or adjusting the final exam date. The entire process provides accurate and personalized teaching optimization suggestions through the analysis and reasoning functions of the large language model.

[0019] Embodiment 4: Teaching file management.

[0020] All automatically generated teaching files are stored in the teaching file management module. The system supports file version control. Teachers can review and restore historical versions at any time and edit the generated files online. Teachers can also share teaching files with colleagues through the system, or adjust and modify them according to review opinions. This module makes the management of teaching files more efficient and orderly.

Claims

1. A teacher teaching assistance system based on artificial intelligence large language model, characterized by The system includes: an input module: used to receive basic course information, teaching objectives and related requirements input by teachers; a teaching file generation module based on a large language model: used to automatically generate teaching files according to preset templates and the generation capability of the large language model, including but not limited to teaching syllabuses, talent training plans, teaching calendars, teaching manuals, and reports on the connection between course objectives and content; an intelligent test question generation and review module: generates adaptive test questions according to course objectives and large language models, and automatically reviews the difficulty, coverage and rationality of the test questions to ensure that the test questions are highly matched with the course objectives; a course content optimization module: analyzes teaching progress, student feedback and classroom performance through a large language model, provides suggestions for optimizing teaching content, and dynamically adjusts the teaching calendar and course schedule; a teaching file management module: used to manage automatically generated teaching files, and provides version control, file sharing and review functions to facilitate teachers to adjust and update files.

2. The system according to claim 1, characterized in that The teaching document generation module based on the large language model can automatically expand the small amount of information input by the teacher into a complete teaching document that meets the format requirements, and make reasonable filling and content suggestions based on the course objectives.

3. The system according to claim 1, characterized in that The intelligent test question generation and review module can generate various types of test questions that are consistent with teaching objectives through a large language model, including but not limited to multiple-choice questions, short-answer questions, and case analysis, and review the rationality and difficulty distribution of the test questions through semantic analysis.

4. The system according to claim 1, characterized in that The course content optimization module can optimize teaching content and teaching methods based on classroom feedback, student performance data and teaching improvement suggestions provided by the large language model, and dynamically adjust the teaching calendar according to actual progress.

5. The system according to claim 1, characterized in that The teaching file management module supports multi-version storage and management of files. Teachers can quickly view, edit and share various teaching files through the system, and can review files and restore historical versions.

6. A method for generating and optimizing teaching files based on the system of claim 1, characterized in that The following steps are included: obtaining input information: receiving course information and teaching objectives input by teachers through the input module; generating teaching documents: using the large language model and preset templates to automatically generate teaching documents that meet the requirements, including but not limited to talent training programs, teaching syllabuses, and teaching manuals; generating and reviewing test questions: generating test questions that match the course objectives through the large language model, and automatically reviewing their coverage and difficulty; providing teaching optimization suggestions: by analyzing classroom performance and feedback, and based on the analysis results of the large language model, providing teaching content and calendar adjustment suggestions; dynamically adjusting the teaching calendar: automatically adjusting the teaching calendar according to actual teaching progress and optimization suggestions to ensure that the teaching plan is consistent with the course objectives.

7. The method according to claim 6, characterized in that In the step of generating teaching files, the system generates standardized files that meet the requirements of the teaching syllabus, teaching calendar and other file formats based on the small amount of information input, and provides content expansion and suggestions through a large language model.

8. The method according to claim 6, characterized in that The test question generation and review steps automatically detect the accuracy and difficulty distribution of the test questions through the semantic analysis function of the large language model, ensuring that the test questions are highly relevant to the teaching objectives.

9. The method according to claim 6, characterized in that The teaching optimization suggestions analyze students' classroom participation, homework completion and test performance through a large language model, automatically generate suggestions for optimizing teaching content and provide teaching calendar adjustment plans.

Images