Intelligent teaching auxiliary system based on large language model

Abstract

The invention discloses an intelligent teaching auxiliary system based on a large language model, which relates to the technical field of intelligent teaching and comprises a progress management module, a resource management module, a teaching service module, a test question test module, a consultation evaluation module and a result auditing module. According to the intelligent teaching auxiliary system based on the large language model, the authenticity of the reflected learning condition of the student is judged according to the matching degree of the test question test result of the student and the input information, and the score record is corrected through manual analysis and auditing by a human teacher in allusion to the condition that the test score is not matched with the evaluation score; therefore, the system can adjust the teaching arrangement according to the real mastering degree of the teaching content of the students, can effectively avoid the improper teaching arrangement caused by the misjudgment of the conditions of the students, and facilitates the improvement of the teaching effect and the learning experience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent teaching technology, and in particular to an intelligent teaching auxiliary system based on a large language model. Background Art

[0002] Intelligent teaching refers to the use of artificial intelligence (AI) technology to provide students with personalized and intelligent teaching services. This teaching model uses in-depth analysis and mining of students' learning behaviors, grades and other data, combined with intelligent algorithms and big data technology, to accurately identify and meet students' personalized needs. Intelligent teaching emphasizes the flexibility and adaptability of the teaching process, and can automatically adjust teaching content, methods and rhythm according to the learning characteristics, progress and interests of different students.

[0003] Intelligent teaching assistance system, commonly known as computer-assisted instruction system (CAI), is an innovative teaching tool that uses computer and network technology to improve teaching efficiency and students' learning experience. Its development has benefited from the rapid progress of information technologies such as artificial intelligence, big data, cloud computing, and the Internet of Things. These technologies have provided strong support for the digital transformation of the education field, enabling intelligent teaching assistance systems to analyze students' learning data more accurately and provide more personalized teaching services. At the same time, with the continuous development of technologies such as virtual reality (VR) and augmented reality (AR), intelligent teaching assistance systems can also create a more immersive learning experience for students and improve the fun and interactivity of learning. In general, intelligent teaching assistance systems play an important role in intelligent teaching. They provide teachers and students with a more efficient and convenient teaching and learning environment through personalized learning, rich teaching resources, teaching effect evaluation, continuous feedback and guidance, and teaching management and monitoring.

[0004] However, in the actual teaching process, although the interactive function of the intelligent teaching system is improved compared with the traditional CAI, it still lacks a natural and smooth communication channel between students and computers. The system mainly judges the degree of mastery by the information input by the students. It cannot judge the real situation of the students through natural communication and observation like human teachers. As a result, it may lead to improper teaching arrangements due to misjudgment of the student situation, affecting the teaching effect and learning experience.

[0005] Therefore, it is urgent to improve this shortcoming. The present invention studies and improves the existing technology and its shortcomings, and provides an intelligent teaching auxiliary system based on a large language model. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent teaching assistance system based on a large language model to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: an intelligent teaching auxiliary system based on a large language model, comprising:

[0008] Progress management module, resource management module, teaching service module, test question module, consultation and evaluation module, and result review module;

[0009] The progress management module is responsible for developing personalized teaching plans, monitoring students' learning trajectories, automatically updating students' learning progress, and adjusting teaching content and rhythm;

[0010] The resource management module is responsible for managing various teaching resources including textbooks, courseware, videos, and exercises, and provides appropriate teaching resources for the teaching service module according to the teaching plan and the personalized needs of students, ensuring that the provided teaching resources are in line with the current learning progress and meet the learning needs of students in a targeted manner;

[0011] The teaching service module is responsible for providing teaching services directly to students, including knowledge explanation, Q&A, and learning guidance, etc. It uses a large language model to generate natural and fluent text or voice responses, simulating the communication method of human teachers;

[0012] The test module is responsible for automatically generating test questions of appropriate difficulty according to the students' learning progress and teaching content, testing the students' mastery of knowledge points, and automatically correcting the test papers after the test, giving the test scores and detailed analysis;

[0013] The consulting and evaluation module is responsible for receiving the personal learning situation (such as study notes, self-evaluation, etc.) automatically input by students, analyzing and evaluating it using natural language processing technology, and providing evaluation scores and personalized learning suggestions;

[0014] The result review module is responsible for comprehensively analyzing the test scores and assessment scores, judging the students' actual learning situation and level, and based on the analysis results, providing feedback to the teaching service module on the students' learning progress, difficulties and error-prone points, providing decision support for subsequent teaching arrangements, and guiding the optimization and personalized adjustment of teaching services;

[0015] The teaching service module receives information from the progress management module and the result review module, adjusts the teaching strategy and content, and interacts with the test question test module and the consulting and evaluation module to obtain students' learning feedback and further improve the teaching effect.

[0016] Furthermore, the progress management module specifically includes the following submodules:

[0017] Task statistics submodule: responsible for collecting and counting students' learning plan tasks, which may come from the teacher's syllabus, the learning path recommended by the system, or the learning content selected by students, and recording basic information such as the name, type (such as video learning, exercise practice, reading materials, etc.), and expected completion time of each task;

[0018] Catalog formulation submodule: responsible for dividing the learning tasks into different progress nodes based on the information provided by the task statistics submodule, and formulating a detailed learning progress catalog based on this information. The learning progress catalog should clearly show the learning objectives, main tasks and expected results of each stage;

[0019] Progress tracking submodule: responsible for real-time tracking of students' learning progress, specifically evaluating their learning progress through their online learning behaviors (such as video viewing time, exercise completion status, homework submission time, etc.), and generating progress reports;

[0020] Progress update submodule: responsible for automatically updating the learning progress catalog based on the real-time progress information of students provided by the progress tracking submodule; when it is found that the student's progress is ahead or behind, this submodule can automatically adjust the difficulty of subsequent tasks or recommend supplementary learning resources to maintain the continuity and effectiveness of the learning progress.

[0021] Furthermore, the progress management module specifically includes the following submodules:

[0022] Resource download submodule: responsible for automatically downloading the teaching resources required for the upcoming learning session in the learning progress directory from the cloud resource library and storing them in the local resource library. This submodule ensures that students can obtain the required learning materials in a timely manner during the learning process without manual search or waiting, thereby improving the continuity and efficiency of learning; the resource download submodule supports the breakpoint resume function. If an interruption occurs during the download process, the download will continue after reconnection;

[0023] Compression upload submodule: responsible for compressing the teaching resources that have been learned, no longer frequently used or have expired in the local resource library, and uploading them to cloud storage. This submodule helps to free up local storage space, while maintaining long-term backup of teaching resources in the cloud, facilitating subsequent management and reuse; the compression upload submodule supports incremental upload function for partially uploaded resources, and only uploads the newly added or modified parts, reducing upload time and traffic consumption.

[0024] Furthermore, the workflow of the resource download submodule is as follows:

[0025] Analyze the learning progress catalog: Analyze the current learning progress catalog to determine the upcoming learning links and corresponding teaching resource requirements;

[0026] Cloud resource retrieval: According to the needs, search for corresponding teaching resources in the cloud resource library, including video tutorials, e-books, exercise books, etc.;

[0027] Resource download and verification: Download the retrieved resources and perform integrity verification to ensure the integrity and correctness of the resources;

[0028] Local storage: Store the downloaded and verified resources in the local resource library for students to use in subsequent learning.

[0029] Furthermore, the workflow of the compression upload submodule is as follows:

[0030] Resource screening: Filter out the resources that need to be compressed and uploaded according to preset rules (such as learning completion time, access frequency, etc.);

[0031] Resource compression: compress the selected resources to reduce the file size for easy storage and transmission;

[0032] Cloud upload: upload the compressed resources to the cloud resource library and ensure the accessibility of the resources in the cloud after successful upload;

[0033] Local cleanup: After confirming that the resources have been successfully uploaded to the cloud, delete the corresponding resource files from the local resource library to free up storage space.

[0034] Furthermore, before outputting the score results, the test question test module and the consulting and evaluation module both convert the scores into percentages using a conversion formula, and the conversion formula is:

[0035]

[0036] Furthermore, the result review module specifically includes the following submodules:

[0037] Score calculation submodule: responsible for calculating the consistency rate between the test score and the evaluation score, receiving the test score given by the test question test module and the evaluation score given by the consultation and evaluation module, and then using the formula to calculate the degree of consistency between the two, and outputting the consistency rate between the test score and the evaluation score;

[0038] Matching judgment submodule: Based on the matching rate between the test scores and the evaluation scores, it is responsible for judging the authenticity of the students’ learning situation reflected by the test results and the evaluation results;

[0039] Manual review submodule: When the match determination submodule determines that the test score and the evaluation score do not match, a manual teacher is invited to participate in the review process to review the test score and the evaluation score. The manual teacher determines whether the score is accurate based on his or her professional knowledge and experience, and makes necessary adjustments or corrections;

[0040] Result analysis submodule: responsible for in-depth test scores and evaluation scores to extract detailed information about students' learning situation, considering factors such as students' strengths, weaknesses, learning progress, and mastery, and output a comprehensive learning evaluation report, including learning outcomes, existing problems, and improvement suggestions.

[0041] Furthermore, the matching rate calculation formula of the score calculation submodule is:

[0042]

[0043] Among them, CR represents the matching rate, Score1 represents the test score output by the test question test module, and Score1 represents the evaluation score output by the consultation evaluation module.

[0044] Furthermore, the judgment condition of the match determination submodule is "CR ≥ 95%?", and the corresponding instructions of the judgment result are as follows: if CR ≥ 95%, it is considered that the test score and the evaluation score are consistent, and the student learning situation reflected is true, and the result analysis submodule is directly triggered; otherwise, CR < 95%, it is considered that the test score and the evaluation score are inconsistent, and there are errors in the student learning situation reflected, and the manual review submodule is triggered.

[0045] Furthermore, the workflow of the manual review submodule is: receiving instructions and related data from the match determination submodule, assigning review tasks to appropriate manual teachers, the manual teachers review the test scores and evaluation scores, and give review opinions, and then updating the score records based on the review opinions.

[0046] The present invention provides an intelligent teaching auxiliary system based on a large language model, which has the following beneficial effects:

[0047] 1. The present invention determines the authenticity of the student's learning situation reflected by the degree of match between the student's test results and the input information, and corrects the score records through manual analysis and review by human teachers in the case of inconsistency between the test scores and the evaluation scores, so as to obtain a more realistic and accurate student learning situation, thereby enabling the system to adjust the teaching arrangements according to the students' actual mastery of the teaching content, which can effectively avoid improper teaching arrangements caused by misjudgment of the student's situation, and help improve the teaching effect and learning experience.

[0048] 2. The present invention is designed with a teaching resource loading control mechanism, which can load subsequent teaching resources in appropriate amounts according to the students' learning progress, ensuring that the teaching resources are sufficient to support the students' learning progress, and effectively avoiding the problem of affecting the device's operating speed due to loading too many teaching resources at one time. For expired teaching resources, they are compressed and uploaded to the cloud, further reducing device resource usage and improving the operating speed of intelligent teaching equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A logic block diagram of an intelligent teaching auxiliary system based on a large language model of the present invention;

[0050] Figure 2 The present invention is a schematic diagram showing the operation flow of a progress management module of an intelligent teaching auxiliary system based on a large language model;

[0051] Figure 3 The present invention is a schematic diagram of the operation flow of a result review module of an intelligent teaching assistance system based on a large language model. DETAILED DESCRIPTION

[0052] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0053] like Figure 1-Figure 3 As shown, an intelligent teaching auxiliary system based on a large language model includes:

[0054] Progress management module: formulate personalized teaching plans, monitor students' learning trajectories, automatically update students' learning progress, and adjust teaching content and rhythm; the progress management module specifically includes the following sub-modules:

[0055] Task statistics submodule: collects and counts students' learning plan tasks, which may come from the teacher's syllabus, the learning path recommended by the system, or the learning content selected by students. It also records basic information such as the name, type (such as video learning, exercise practice, reading materials, etc.), and expected completion time of each task.

[0056] Catalog development submodule: The information provided by the task statistics submodule is used to divide the learning tasks into different progress nodes, and a detailed learning progress catalog is developed accordingly. The learning progress catalog should clearly display the learning objectives, main tasks and expected results of each stage;

[0057] Progress Tracking Submodule: real-time tracking of students’ learning progress, specifically evaluating their learning progress through their online learning behaviors (such as video viewing time, exercise completion, homework submission time, etc.), and generating progress reports;

[0058] Progress update submodule: automatically updates the learning progress directory based on the real-time progress information of students provided by the progress tracking submodule; when it is found that the student's progress is ahead or behind, this submodule can automatically adjust the difficulty of subsequent tasks or recommend supplementary learning resources to maintain the continuity and effectiveness of the learning progress;

[0059] Resource management module: manages various teaching resources including textbooks, courseware, videos, exercises, etc., provides appropriate teaching resources for the teaching service module according to the teaching plan and students' personalized needs, ensures that the provided teaching resources are in line with the current learning progress, and specifically meet students' learning needs; the progress management module specifically includes the following sub-modules:

[0060] Resource download submodule: automatically downloads the teaching resources required for the upcoming learning session in the learning progress directory from the cloud resource library and stores them in the local resource library. This submodule ensures that students can obtain the required learning materials in a timely manner during the learning process without manual search or waiting, which improves the continuity and efficiency of learning; the resource download submodule supports the breakpoint resume function. If the download process is interrupted, the download will continue after reconnection;

[0061] Compression upload submodule: compresses the teaching resources that have been learned, no longer frequently used or expired in the local resource library and uploads them to the cloud storage. This submodule helps to free up local storage space while maintaining long-term backup of teaching resources in the cloud, which is convenient for subsequent management and reuse. The compression upload submodule supports incremental upload for partially uploaded resources, uploading only the newly added or modified parts, reducing upload time and traffic consumption.

[0062] Among them, the workflow of the resource download submodule is as follows:

[0063] Analyze the learning progress catalog: Analyze the current learning progress catalog to determine the upcoming learning links and corresponding teaching resource requirements;

[0064] Cloud resource retrieval: According to the needs, search for corresponding teaching resources in the cloud resource library, including video tutorials, e-books, exercise books, etc.;

[0065] Resource download and verification: Download the retrieved resources and perform integrity verification to ensure the integrity and correctness of the resources;

[0066] Local storage: Download and verify resources and store them in the local resource library for students to use in subsequent learning;

[0067] Among them, the workflow of the compression upload submodule is as follows:

[0068] Resource screening: Filter out the resources that need to be compressed and uploaded according to preset rules (such as learning completion time, access frequency, etc.);

[0069] Resource compression: compress the selected resources to reduce the file size for easy storage and transmission;

[0070] Cloud upload: upload the compressed resources to the cloud resource library and ensure the accessibility of the resources in the cloud after successful upload;

[0071] Local cleanup: After confirming that the resources have been successfully uploaded to the cloud, delete the corresponding resource files from the local resource library to free up storage space;

[0072] Teaching service module: directly provides teaching services to students, including knowledge explanation, Q&A, and learning guidance, etc. It uses a large language model to generate natural and fluent text or voice responses, simulating the communication method of human teachers. The teaching service module receives information from the progress management module and the result review module, adjusts teaching strategies and content, and interacts with the test module and the consulting and evaluation module to obtain students' learning feedback and further improve teaching effectiveness.

[0073] Test module: automatically generates test questions of appropriate difficulty according to students' learning progress and teaching content to test students' mastery of knowledge points. After the test, the test paper is automatically graded and the test score and detailed analysis are given.

[0074] Consultation and evaluation module: receives students' automatically input personal learning information (such as study notes, self-evaluation, etc.), uses natural language processing technology to analyze and evaluate, and provides evaluation scores and personalized learning suggestions;

[0075] Before outputting the score results, the test module and the consulting and evaluation module convert the scores into percentages through the conversion formula:

[0076]

[0077] Results review module: Comprehensively analyze test scores and assessment scores to determine students’ actual learning situation and level, and based on the analysis results, provide feedback to the teaching service module on students’ learning progress, difficulties and error-prone points, provide decision support for subsequent teaching arrangements, and guide the optimization and personalized adjustment of teaching services; and the results review module specifically includes the following sub-modules:

[0078] Score calculation submodule: calculates the matching rate between the test score and the evaluation score, receives the test score given by the test question test module and the evaluation score given by the consultation evaluation module, then uses the formula to calculate the matching degree between the two, and outputs the matching rate between the test score and the evaluation score; the matching rate calculation formula is: Among them, CR represents the matching rate, Score1 represents the test score output by the test question test module, and Score2 represents the evaluation score output by the consultation evaluation module.

[0079] Matching judgment submodule: Based on the matching rate between the test score and the evaluation score, the authenticity of the student learning situation reflected by the test result and the evaluation result is judged; the judgment condition of the matching judgment submodule is "CR ≥ 95%?", and the corresponding instructions of the judgment result are as follows: If CR ≥ 95%, it is considered that the test score and the evaluation score are consistent, and the student learning situation reflected is true, and the result analysis submodule is directly triggered; on the contrary, if CR < 95%, it is considered that the test score and the evaluation score are inconsistent, and the student learning situation reflected is wrong, and the manual review submodule is triggered;

[0080] Manual review submodule: When the match determination submodule determines that the test score and the evaluation score do not match, invite a manual teacher to participate in the review process to review the test score and the evaluation score. The manual teacher determines whether the score is accurate based on his / her professional knowledge and experience, and makes necessary adjustments or corrections. The workflow of the manual review submodule: receives the instructions and relevant data from the match determination submodule, assigns the review task to the appropriate manual teacher, and the manual teacher reviews the test score and the evaluation score, gives review opinions, and then updates the score record based on the review opinions.

[0081] Result analysis submodule: In-depth test scores and assessment scores to extract detailed information about students' learning situation, considering factors such as students' strengths, weaknesses, learning progress, and mastery, and output a comprehensive learning evaluation report, including learning outcomes, existing problems, and improvement suggestions.

[0082] The embodiments of the present invention are given for the purpose of illustration and description, and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. An intelligent teaching assistance system based on a large language model, characterized in that: include: Progress management module, resource management module, teaching service module, test question module, consultation and evaluation module, and result review module; The progress management module is responsible for developing personalized teaching plans, monitoring students' learning trajectories, automatically updating students' learning progress, and adjusting teaching content and rhythm; The resource management module is responsible for managing various teaching resources including textbooks, courseware, videos, and exercises, and provides appropriate teaching resources according to the teaching plan and students' personalized needs to ensure that the provided teaching resources are in line with the current learning progress; The teaching service module is responsible for providing teaching services directly to students, using a large language model to generate natural and fluent text or voice responses, simulating the communication method of human teachers; The test module is responsible for automatically generating test questions of appropriate difficulty for testing according to the students' learning progress and teaching content, and automatically correcting the test papers after the test, giving the test scores and detailed analysis; The consulting and evaluation module is responsible for receiving the personal learning situation automatically input by the students, analyzing and evaluating it using natural language processing technology, and providing evaluation scores and personalized learning suggestions; The result review module is responsible for comprehensively analyzing the test scores and assessment scores, judging the students' actual learning situation and level, and based on the analysis results, providing feedback to the teaching service module on the students' learning progress, difficulties and error-prone points, providing decision support for subsequent teaching arrangements, and guiding the optimization and personalized adjustment of teaching services; The teaching service module receives information from the progress management module and the result review module, adjusts the teaching strategy and content, and interacts with the test question test module and the consulting and evaluation module to obtain students' learning feedback and further improve the teaching effect.

2. The intelligent teaching auxiliary system based on a large language model according to claim 1, characterized in that: The progress management module specifically includes the following submodules: Task statistics submodule: responsible for collecting and counting students' learning plan tasks and recording basic information of each task; Catalog making submodule: It is responsible for dividing the learning tasks into different progress nodes based on the information provided by the task statistics submodule, and making a detailed learning progress catalog accordingly; Progress tracking submodule: responsible for real-time tracking of students' learning progress, specifically evaluating their learning progress through their online learning behaviors and generating progress reports; Progress update submodule: responsible for automatically updating the learning progress catalog based on the real-time progress information of students provided by the progress tracking submodule; when it is found that the student's progress is ahead or behind, it automatically adjusts the difficulty of subsequent tasks or recommends additional learning resources.

3. The intelligent teaching auxiliary system based on a large language model according to claim 1, characterized in that: The progress management module specifically includes the following submodules: Resource download submodule: responsible for automatically downloading the teaching resources required for the upcoming learning session in the learning progress directory from the cloud resource library, and storing them in the local resource library; the resource download submodule supports the breakpoint resume function. If an interruption occurs during the download process, the download will continue after reconnection; Compression upload submodule: responsible for compressing the teaching resources that have been learned, no longer frequently used or have expired in the local resource library, and uploading them to cloud storage; the compression upload submodule supports incremental upload function for partially uploaded resources, and only uploads the newly added or modified parts.

4. The intelligent teaching auxiliary system based on a large language model according to claim 3, characterized in that: The workflow of the resource download submodule is as follows: Analyze the learning progress catalog: Analyze the current learning progress catalog to determine the upcoming learning links and corresponding teaching resource requirements; Cloud resource retrieval: According to the needs, search for corresponding teaching resources in the cloud resource library, including video tutorials, e-books, and exercise books; Resource download and verification: Download the retrieved resources and perform integrity verification to ensure the integrity and correctness of the resources; Local storage: Store the downloaded and verified resources in the local resource library for students to use in subsequent learning.

5. The intelligent teaching auxiliary system based on a large language model according to claim 3, characterized in that: The workflow of the compression upload submodule is as follows: Resource screening: Filter out the resources that need to be compressed and uploaded according to preset rules; Resource compression: compress the selected resources to reduce the file size; Cloud upload: upload the compressed resources to the cloud resource library and ensure the accessibility of the resources in the cloud after successful upload; Local cleanup: After confirming that the resources have been successfully uploaded to the cloud, delete the corresponding resource files from the local resource library to free up storage space.

6. The intelligent teaching auxiliary system based on a large language model according to claim 1, characterized in that: Before outputting the score results, the test question test module and the consulting and evaluation module convert the scores into percentages through a conversion formula, which is:

7. The intelligent teaching auxiliary system based on a large language model according to claim 1, characterized in that: The result review module specifically includes the following submodules: Score calculation submodule: responsible for calculating the consistency rate between the test score and the evaluation score; Matching judgment submodule: Based on the matching rate between the test scores and the evaluation scores, it is responsible for judging the authenticity of the students’ learning situation reflected by the test results and the evaluation results; Manual review submodule: When the match determination submodule determines that the test score and the evaluation score do not match, a manual teacher is invited to participate in the review process to review the test score and the evaluation score and make necessary adjustments or corrections; Result analysis submodule: responsible for in-depth test scores and assessment scores to extract detailed information about students' learning situation and output a comprehensive learning evaluation report.

8. The intelligent teaching auxiliary system based on a large language model according to claim 7, characterized in that: The calculation formula of the matching rate of the score calculation submodule is: Among them, CR represents the matching rate, Score1 represents the test score output by the test question test module, and Score1 represents the evaluation score output by the consultation evaluation module.

9. The intelligent teaching auxiliary system based on a large language model according to claim 8, characterized in that: The judgment condition of the match determination submodule is "CR ≥ 95%?", and the corresponding instructions of the judgment result are as follows: if CR ≥ 95%, it is considered that the test score and the evaluation score are consistent, and the student learning situation reflected is true, and the result analysis submodule is directly triggered; on the contrary, CR < 95%, it is considered that the test score and the evaluation score are inconsistent, and there are errors in the student learning situation reflected, which triggers the manual review submodule.

10. The intelligent teaching auxiliary system based on a large language model according to claim 7, characterized in that: The workflow of the manual review submodule is as follows: receiving instructions and related data from the match determination submodule, assigning review tasks to appropriate manual teachers, the manual teachers review the test scores and evaluation scores, and give review opinions, and then updating the score records based on the review opinions.

Images