Teaching assistance system based on large model agent and database multi-technology fusion

Abstract

The application discloses a kind of teaching auxiliary systems based on big model Agent and database multi-technology fusion, at least including big model application design module, database information management module, system interactive design module, will be based on Retrieval Augmented Generation (RAG) technology and Low-Rank Adaptation (LoRA) technology is applied to teaching auxiliary, knowledge transmission and intelligent interaction, especially for the intelligent processing of educational resources and the implementation of personalized teaching, the system can be widely applied in the field of education, help teachers and students overcome the limitations of traditional teaching mode, better carry out the interaction of teaching and learning, promote the dissemination of knowledge and the improvement of skills, promote education modernization, and jointly march towards the future of intelligent education.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and is particularly suitable for intelligent teaching and learning assistance in the education industry. It mainly involves a teaching assistance system based on the fusion of large model agents and database technologies. Background Art

[0002] Although the advent of the information age has brought abundant learning resources, it has also increased the difficulty of screening effective information and placed higher demands on students' information processing capabilities.

[0003] By using intelligent technology to reduce teachers' workload and improve their work efficiency, and by providing personalized learning support and enriched learning experiences, students' learning interests can be stimulated and their independent learning abilities can be cultivated. This transformation will help build a more efficient, equitable, and vibrant educational ecosystem.

[0004] Large-scale pre-trained language models (LMLs) are deep neural network models derived through unsupervised or self-supervised learning on massive amounts of text data. Pre-training on these massive amounts of text data allows these models to acquire rich linguistic knowledge and patterns. These models possess powerful natural language understanding and generation capabilities, enabling them to handle a variety of complex language tasks, such as text generation, question-answering, translation, and sentiment analysis. These models possess strong adaptability, dynamically adjusting their output to meet diverse user needs, providing personalized services, and continuously optimizing their performance through continuous learning from user feedback and new data.

[0005] Because big models can analyze and understand user needs and generate content, they are increasingly being applied in the education sector. Using big models in teaching support scenarios can automatically generate teaching materials such as lesson plans, PowerPoint presentations, and exercises, saving teachers significant time. They can also provide personalized learning suggestions and resources based on students' learning history and performance, improving learning efficiency. Furthermore, intelligent question-and-answer systems can answer students' questions and provide timely assistance.

[0006] An intelligent agent is a general-purpose problem solver based on a large language model. It is a system or program with autonomous learning, decision-making, and execution capabilities, capable of automatically performing tasks in a specific environment and adapting to changes. Large-model-based intelligent agents are intelligent systems built using large, pre-trained models. These models possess powerful language understanding and generation capabilities, enabling them to excel in a variety of tasks. These agents are not only capable of handling complex conversations but also performing various functions, such as information retrieval, content generation, and data analysis. Due to the unique characteristics of intelligent agents, they can play a vital role in teaching assistance. They can provide personalized tutoring, help students answer difficult questions, and improve learning efficiency. They can also assist teachers in developing lesson plans and generating teaching materials, alleviating workloads. By analyzing students' learning data, intelligent agents can provide valuable learning advice and increase students' avenues for self-improvement.

[0007] Database technology is the key to our implementation of knowledge base systems and vector databases.

[0008] The knowledge base system can provide teachers with a platform for centralized management and sharing of various types of teaching materials (such as Word documents, PDF files, PPT presentations, etc.), solving the inconvenience caused by the scattered storage of materials; it can help teachers quickly find teaching resources that meet specific needs and improve work efficiency; it can also promote knowledge exchange and cooperation between teachers and students, allowing the sharing of personal notes and teaching materials; the knowledge base system that supports the uploading, review and updating of materials can also ensure that the teaching content can continue to iterate with the development of educational concepts and technologies, and always keep it up to date.

[0009] By vectorizing multimedia content like text, images, and audio, the vector database enables efficient similarity-based retrieval. With the teacher's guidance, it can automatically and quickly and accurately locate required teaching materials from massive amounts of data. This not only unifies the management of data in various formats (such as text, images, and audio), but also provides an efficient and consistent search experience. Combined with large model technology, the data in the vector database can be used to generate high-quality teaching documents. For example, RAG technology can be used to retrieve relevant information from the knowledge base and generate lesson plans or PPTs that meet teaching needs, significantly improving teaching efficiency and quality. Summary of the Invention

[0010] This invention addresses the challenges of existing technologies by providing a multi-technology teaching assistance system based on a large-scale agent and database. This solution prioritizes the educator experience, rather than simply answering student questions. This invention can facilitate resource exchange, reduce the burden on educators, and enrich educational resources with AI, thus providing practical social benefits.

[0011] In order to achieve the above purpose, the technical solution adopted by the present invention is: a teaching auxiliary system based on the fusion of large model agent and database multi-technology, which at least includes a large model application design module, a database information management module, and a system interaction design module.

[0012] The large model application design module is as follows: a dedicated "Wenwu" large model is designed, which is based on a powerful neural network and processes natural language data or image data. After fine-tuning the relevant data of the teaching materials, it can accurately answer the professional knowledge questions input by teachers and students, and can also organize a large amount of knowledge to generate the content of teaching materials; the agent personalized calls the "Wenwu" large model and completes intelligent marking and judgment, and generates teaching material files based on the output of the large model.

[0013] The database information management module is used to manage user identity and authority information and teaching material information, maintain the user's identity information and other basic information, the basic information of the teaching material and the review status information, accept the operation information of the system interaction design module to update the data table in real time, and provide the URL of the teaching material to be downloaded to the system interaction design module for subsequent user operations; it is divided into private teaching material library and public teaching material library according to the open permission of the teaching material, and stores accessible user information and related teaching material information, and accepts the permission operation of the system interaction design module user to update the library access permission.

[0014] The system interaction design module designs system visualization and interaction functions, including user application or consent to private library access operations, administrator review of uploaded teaching materials operations, user information display and interface interaction beautification, etc., in order to facilitate user interaction, obtain various user operations and transmit the operation results to the large model application design module and database information management module.

[0015] As an improvement of the present invention, the large model application design module can be divided into a knowledge question answering submodule, a teaching material generation submodule and a large model adjustment management submodule:

[0016] The knowledge question answering submodule: A user, such as a teacher or student, inputs their own questions. The "Wenwu" model first determines whether the question is relevant to the knowledge in the knowledge base. If so, it performs search-augmented generation (RAG) in the knowledge base to output the answer. If not, it directly outputs the answer based on the user's "learned knowledge";

[0017] The teaching material generation submodule: users who are teachers can upload various types of teaching materials and ask the "Wenwu" model to generate corresponding other types of teaching materials based on the files of specific teaching materials. They can also input handwritten mathematical expressions and other contents in image format to obtain corresponding LaTeX codes to assist in editing teaching materials;

[0018] The large model adjustment management submodule includes preview command function, save training parameter and load training parameter function, start fine-tuning and interrupt fine-tuning function, supports large model selection (provides a list of popular open source large models, and the local large model can enter the model path), fine-tuning dataset selection (supports dataset preview, supports constructing new datasets from local), training parameter and LoRA parameter settings, output directory settings, real-time viewing of progress, loss curve and training log during the fine-tuning process, and supports loading checkpoint path and conducting question and answer tests after fine-tuning.

[0019] As another improvement of the present invention, the database information management module can be divided into a teaching material management submodule and a rights management submodule:

[0020] The teaching material management submodule receives the pass or fail operation result from the content review management submodule and updates the review status of the existing teaching materials in the teaching material database in real time. Users can upload various types of teaching materials to private or public teaching material databases, and can also download teaching materials from private, shared or authorized private teaching material databases. Teaching materials generated using existing materials are automatically stored as new teaching materials in the private teaching material database.

[0021] The authority management submodule receives the identity information of the user requesting access, provides the user requesting access with operation result information based on whether the user of the private library is allowed to access the private library, and updates the opening authority of the relevant teaching material library.

[0022] As another improvement of the present invention, the system interaction design module specifically includes a content review submodule and a permission operation submodule:

[0023] The content review submodule: A user who is an administrator receives all teaching material contents from the teaching material management module, reviews the rationality and legality of the material contents by checking and downloading, and makes a pass or fail operation and returns the operation result to the teaching material management submodule;

[0024] The permission operation submodule: the user can send application information to the private library user through the application access operation; the user who receives the application access information can choose whether to agree, and the access result information will be synchronously transmitted to the user who applied for access.

[0025] As another improvement of the present invention, the large model application design module includes large model LoRA fine-tuning technology and large model Agent technology:

[0026] Large-model LoRA fine-tuning technology: Large-model LoRA fine-tuning technology is an efficient parameter adjustment method that reduces the number of parameters that need to be trained by decomposing model weights into the product of two low-rank matrices. This technology is used to customize large models for teaching assistants to adapt to specific teaching tasks, such as generating PPT content from course outlines, converting handwritten mathematical expressions into LaTeX code, and automatically generating and grading subject exercises. The specific implementation steps include downloading and formatting the dataset, selecting an appropriate large model, decomposing the model weights into the product of two low-rank matrices, and performing fine-tuning.

[0027] The large model agent technology described above: The agent calls the large model and uses the output of the large model to provide further support to teachers and students by combining the four major elements of planning, memory, tool use and execution. When a teacher needs to generate a lesson plan or PPT, the agent first understands this need and breaks it down into a series of steps, such as retrieving relevant materials and generating a document framework. Then, the agent uses the information in the knowledge base and text generation tools to create teaching materials that meet the requirements. In addition, the agent can also process images, such as converting handwritten formulas into LaTeX code, thereby helping teachers prepare course content more efficiently. Throughout the process, the agent will continuously optimize the service based on the user's historical interaction records and personal preferences to ensure that the teaching resources provided are more in line with actual needs.

[0028] As another improvement of the present invention, the large model application design module has preset the "Wenwu" examination and grading model obtained by fine-tuning the Qwen large model using the MR-Ben dataset and LoRA technology, such as Figure 4 As shown:

[0029] The fine-tuning process of the test-taking and grading model first prepared and parsed the MR-Ben dataset, which is specifically adapted for test-taking and grading tasks. Then, based on the LoRa core formula h = W0x + ΔWx = W0x + BAx, while keeping most of the pre-trained model parameters unchanged, low-rank matrix updates were introduced only for specific layers. Through a carefully designed training process, including data preprocessing, defining LoRA settings, and iterative optimization, the Qwen model was adapted to this complex reasoning and evaluation task.

[0030] The described grading model architecture: The model's input format is a structured text sequence, including but not limited to the question description, the candidate's answer process and step-by-step instructions. Specifically, each input instance is constructed into a composite structure containing instructions, context, questions and candidate answers; for the output format, the model generates a scoring result and corresponding comments. The scoring result is a quantitative assessment of the accuracy and completeness of the candidate's answers, usually presented in numerical form; the comments are a qualitative analysis of the problem-solving process, pointing out the strengths and weaknesses, and proposing improvement suggestions.

[0031] As another improvement of the present invention, the teaching material management module supports uploading of teaching materials including but not limited to teaching syllabuses, teaching requirements, lesson plans, study guides, teaching PPTs, and after-class exercises.

[0032] In order to achieve the above object, the present invention also adopts a technical solution: a method for using the system includes the following steps:

[0033] S1, Registration and Login: When using this system for the first time, users need to fill in the necessary system information including identity, user name, account number, password, name, ID number and national real-name system information. When it is not the first time to use this system, users can log in with their account number and password. The system will enter different main interfaces according to the identity information of the account.

[0034] S2, intelligent question answering: users input their own questions, and the large model first determines whether the questions are related to the knowledge in the knowledge base. If so, it performs retrieval-enhanced generation (RAG) in the knowledge base to output the answer. If not, it directly outputs the answer based on the user's "learned knowledge".

[0035] S3, intelligent generation: When generating teaching material files, the user who is a teacher first uploads a certain type of teaching material as the knowledge base of the large model retrieval enhanced generation (RAG), and then enters the requirements, that is, what type of corresponding teaching material the large model needs to generate; when generating LaTeX code, the user who is a teacher first enters handwritten mathematical expressions and other content in image format, and then obtains the corresponding LaTeX code, which can be previewed and, if necessary, manually modified online.

[0036] S4, Smart Search: Users who are teachers or students can click on the "Smart Search" function area in the main interface to perform search operations. By entering keywords in the input box, the system can retrieve all files containing keywords from public libraries and accessible private libraries and display them for users to download and review.

[0037] S5, Knowledge Base Viewing: Users who are teachers or students can click "My Knowledge Base" in the main interface function area to enter their personal private knowledge base to view all uploaded files, including the file's review status, upload time and other information. They can also click the "Upload" button to continue uploading local teaching materials to the knowledge base for management and choose whether to make them public as public library files; users can enter the account of the user they want to access in the input box to apply for access to the user's private knowledge base. For the knowledge base that passes the application, all file contents in the knowledge base can be directly viewed.

[0038] S6, large model tuning: users with the administrator identity need to first select the large model, then select the fine-tuning dataset (the dataset can be previewed before selection), set the training parameters and LoRA parameters and the output directory, and then click the "Start" button to start fine-tuning. At the end of fine-tuning, select the output directory of the just fine-tuned model in the checkpoint path, and then enter the chat area for question-and-answer testing.

[0039] S7, Data Review: Users with the administrator identity can view all files in all libraries, review and judge the content of the files, and make "pass / fail" operations to change the file review status. The system automatically publishes relevant information to notify the user to whom the file belongs.

[0040] Compared to existing technologies, this invention offers significant advantages: It combines, for the first time, database technologies from personal and public knowledge bases with multiple large-scale models to create a platform for global educators to share educational resources. The system not only allows users to create their own knowledge bases but also allows them to choose to make portions of them public. Users can also retrieve publicly available content, enabling the exchange of educational resources. Users can download these files or select content, which the system then uses to create teaching materials such as lesson plans, PowerPoint presentations, and exams, alleviating the burden on educators.

[0041] In addition, the present invention also introduces an intelligent grading system that recognizes handwritten content, converts it into characters, and uploads it to a large model for correctness judgment. This can greatly facilitate educators and realize a full AI process from question setting to grading. Moreover, for user convenience, the system has added a tool library that integrates commonly used functions, allowing all teaching tasks to be completed in one system.

[0042] Compared to other large-scale teaching assistance models, the system of this invention focuses more on the experience with educators rather than simply answering students' questions. This invention can promote the exchange of resources, reduce the burden on educators, and enrich educational resources with AI, with practical social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1This is a structural diagram of the system of the present invention;

[0044] Figure 2 This is a structural diagram of each submodule of the system of the present invention;

[0045] Figure 3 A flowchart of the steps of the method for using the system of the present invention;

[0046] Figure 4 This is the large model architecture diagram of the "Wenwu" system of the present invention;

[0047] Figure 5 This is a schematic diagram of the interface after a user with the user identity of Example 2 of the present invention logs in;

[0048] Figure 6 This is a schematic diagram of the interface after a user with administrator identity logs in according to Example 3 of the present invention. DETAILED DESCRIPTION

[0049] The present invention will be further explained below with reference to the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention.

[0050] Example 1

[0051] The teaching auxiliary system based on the fusion of large model agent and database multi-technology is characterized by at least including a large model application design module, a database information management module, and a system interaction design module.

[0052] The large model application design module is as follows: a dedicated "Wenwu" large model is designed, which is based on a powerful neural network and processes natural language data or image data. After fine-tuning the relevant data of the teaching materials, it can accurately answer the professional knowledge questions input by teachers and students, and can also organize a large amount of knowledge to generate the content of teaching materials; the agent personalized calls the "Wenwu" large model and completes intelligent marking and judgment, and generates teaching material files based on the output of the large model.

[0053] The database information management module is used to manage user identity and authority information and teaching material information, maintain the user's identity information and other basic information, the basic information of the teaching material and the review status information, accept the operation information of the system interaction design module to update the data table in real time, and provide the URL of the teaching material to be downloaded to the system interaction design module for subsequent user operations; it is divided into private teaching material library and public teaching material library according to the open permission of the teaching material, and stores accessible user information and related teaching material information, and accepts the permission operation of the system interaction design module user to update the library access permission.

[0054] The system interaction design module designs system visualization and interaction functions, including user application or consent to private library access operations, administrator review of uploaded teaching materials operations, user information display and interface interaction beautification, etc., in order to facilitate user interaction, obtain various user operations and transmit the operation results to the large model application design module and database information management module.

[0055] Example 2

[0056] Based on the teaching auxiliary system of large model agent and database multi-technology integration, the user identity in this embodiment is the user, and the function can be realized through the user main interface. Figure 5 This embodiment includes a large model application design module, a database information management module, and a system interaction design module. Figure 1 shown.

[0057] (1) When teachers need to use the intelligent question-and-answer function, they click to enter the "intelligent question-and-answer" function area, enter the code or question in the question area, and can select "code modification" or "knowledge question-and-answer" to allow the big model to make more professional and more in line with the needs of the answer. If further questions are needed, they can directly "reference" the previous chat records to "activate" the memory of the big model and conduct multiple rounds of dialogue. During the process of the big model streaming output of the answer, they can also stop answering at any time and put forward the need for improvement in the question area;

[0058] (2) When teachers need to use the data search function, they can click to enter the "Data Search" function area, enter a complete or partial keyword, and then retrieve a list of all the data related to the keyword in the public knowledge base and their own personal knowledge base, and save it to the local computer for viewing;

[0059] (3) When teachers need to use the intelligent generation of teaching materials function, they click to enter the "Intelligent Generation" function area, check "Yes" for "Add to Knowledge Base", click the "Upload File" button, select other types of materials related to the teaching materials they want to generate locally, upload them to the system to serve as the knowledge base for large model retrieval enhancement generation, then select "Generate File Type", and finally enter the detailed requirements for the generated materials and click the "Send" button. After the materials are successfully generated, a file download box will pop up on the page. Click Download to save the materials locally.

[0060] (4) When teachers need to use the intelligent generation of teaching materials function, they click to enter the "Intelligent Generation" function section, then click the "Handwritten Formula to LaTeX Formula" button, and then select and upload a picture of handwritten mathematical expressions and other content locally to obtain the corresponding LaTeX code. They can preview it online and manually modify the LaTeX code online if necessary;

[0061] (5) When teachers need to use the functions related to the personal knowledge base, they can click to enter the "My Knowledge Base" function area, where they can view the review status of the materials they have uploaded, click "Download" to obtain the materials in the personal knowledge base that have passed the review, and click the "Upload File" button to select new materials from the local computer to upload;

[0062] (6) When teachers need to use the tool library, they can click to enter the "My Tool Library" function area and choose tools such as professional calculator, library collection query, CNKI search, Markdown editor, MySQL database tool, idiom dictionary, etc.

[0063] Example 3

[0064] Based on the teaching assistance system of large model agent and database multi-technology integration, the user identity in this embodiment is the administrator, and the functions can be realized through the administrator main interface. Figure 6 This embodiment includes a large model application design module, a database information management module, and a system interaction design module. Figure 1 shown.

[0065] (1) The administrator clicks on the "Home Page" on the left to enter the system management module. In this section, the administrator can see the number of registered users on the platform, the number of knowledge base files, the number of online users on the platform, the cumulative income, today's income, etc.

[0066] (2) The administrator can click on "Data Review" on the left to enter the content review management module. The administrator can see the files uploaded by users for the first time and review whether they violate the rules. The administrator can see all files marked as "unreviewed" on this interface. The administrator can click the download button and select "Approve" or "Reject" to mark the file after reading it.

[0067] (3) If the administrator wants to check the knowledge base, he can click "Knowledge Base Management". The administrator can see the file name, uploader, download address, file status, whether the file belongs to the public knowledge base or private knowledge base, and other related information. The administrator can click the download button to download the file, or click "Approved" or "Failed" to directly modify the file status.

[0068] (4) If the administrator wants to operate on the large model, he can click "Large Model Management" to enter the large model management page. The administrator can click "Upload" and select a file or knowledge base to upload from the local computer to adjust the parameters of the large model.

[0069] (5) If you are a root administrator, you can click "Permission Management" to enter the permission management module. The root administrator can see other administrator accounts and click "Audit Permissions", "View Knowledge Base Permissions", and "Large Model Adjustment Permissions" behind the administrator account to assign these permissions to other administrators.

[0070] It should be noted that the above content merely illustrates the technical idea of ​​the present invention and cannot be used to limit the scope of protection of the present invention. For ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications all fall within the scope of protection of the claims of the present invention.

Claims

1. A teaching assistance system based on the fusion of large model agents and database technologies, characterized by: At least including large model application design module, database information management module and system interaction design module, The large model application design module: designs a dedicated "Wenwu" large model based on a neural network to process natural language data or image data. After fine-tuning with the relevant data of the teaching materials, it can accurately answer the professional knowledge questions input by teachers and students, and organize a large amount of knowledge to generate the content of the teaching materials; the agent personalized calls the "Wenwu" large model, and completes intelligent examination and judgment, and generates teaching material files based on the output of the large model. The database information management module is used to manage user identity and authority information and teaching material information, maintain user identity information and other basic information, basic information of teaching materials and review status information, accept operation information of the system interactive design module to update the data table in real time, and provide the system interactive design module with the URL of the teaching material to be downloaded for subsequent user operations; it is divided into private teaching material database and public teaching material database according to the open authority of teaching materials, and stores accessible user information and related teaching material information, accepts the authority operation of the system interactive design module user to update the database access rights, The system interaction design module is used to design system visualization and interaction functions, including user application or consent to private library access operations, administrator review of uploaded teaching materials operations, user information display and interface interaction beautification, etc., to facilitate user interaction, obtain various user operations and transmit the operation results to the large model application design module and database information management module; The large model application design module is divided into a knowledge question answering submodule, a teaching material generation submodule and a large model adjustment management submodule. The knowledge question answering submodule: users, such as teachers or students, input their own questions. The "Wenwu" model first determines whether the question is relevant to the knowledge in the knowledge base. If so, it performs search enhancement and generation in the knowledge base to output the answer. If not, it directly outputs the answer based on the user's "learned knowledge"; The teaching material generation submodule: users with teacher identities upload various types of teaching materials, requiring The "Wenwu" model generates corresponding other types of teaching materials based on the files of specific teaching materials, or inputs the content of handwritten mathematical expressions in image format to obtain the corresponding LaTeX code to assist in the editing of teaching materials.

2. The teaching assistance system based on the integration of large model agent and database multi-technology according to claim 1 is characterized by: The large model adjustment management submodule includes preview command function, save training parameter and load training parameter function, start fine-tuning and interrupt fine-tuning function, supports large model selection, fine-tuning data set selection, training parameter and LoRA parameter setting, output directory setting, real-time viewing of progress, loss curve and training log during fine-tuning, and supports loading checkpoint path and question-and-answer test after fine-tuning.

3. The teaching assistance system based on the integration of large model agent and database multi-technology according to claim 1 is characterized by: The database information management module is divided into a teaching material management submodule and a rights management submodule. The teaching material management submodule receives the pass or fail operation result from the content review management submodule and updates the review status of the existing teaching materials in the teaching material database in real time. Users can upload various types of teaching materials to private or public teaching material databases, or download teaching materials from private, shared or authorized private teaching material databases. Teaching materials generated using existing materials are automatically stored as new teaching materials in the private teaching material database. The authority management submodule receives the identity information of the user requesting access, provides the user requesting access with operation result information based on whether the user of the private library is allowed to access the private library, and updates the opening authority of the relevant teaching material library.

4. The teaching assistance system based on the integration of large model agent and database multi-technology according to claim 1 is characterized by: The system interaction design module specifically includes a content review submodule and a permission operation submodule. The content review submodule: A user who is an administrator receives all teaching material contents from the teaching material management module, reviews the rationality and legality of the material contents by checking the download method, makes a pass or fail operation, and returns the operation result to the teaching material management submodule; The permission operation submodule: the user sends application information to the private library user through the access application operation; the user who receives the access application information chooses whether to agree, and the access result information will be synchronously transmitted to the user who applied for access.

5. The teaching assistance system based on the fusion of large model agent and database technology according to claim 2 is characterized by: The large model application design module includes large model LoRA fine-tuning technology and large model Agent technology. The large model LoRA fine-tuning technology: large model LoRA fine-tuning technology is an efficient parameter adjustment method. By decomposing the model weights into the product of two low-rank matrices, the specific implementation steps include downloading and formatting the dataset, selecting a suitable large model, decomposing the model weights into the product of two low-rank matrices, and performing fine-tuning. The large model agent technology described above: The agent calls the large model and uses the output of the large model to provide further support for teachers and students by combining the four major elements of planning, memory, tool use and execution. When a teacher needs to generate a lesson plan or PPT, the agent first understands this need and breaks it down into a series of steps, including retrieving relevant materials and generating a document framework. Then, the agent uses information in the knowledge base and text generation tools to create teaching materials that meet the requirements. The agent can also process images, including converting handwritten formulas into LaTeX code, thereby helping teachers prepare course content more efficiently. Throughout the process, the agent will continuously optimize services based on the user's historical interaction records and personal preferences to ensure that the provided teaching resources are more in line with actual needs.

6. The teaching assistance system based on the integration of large model agent and database multi-technology according to claim 2 is characterized by: The large model application design module has been pre-installed with the "Wenwu" test-taking model obtained by fine-tuning the Qwen large model using the MR-Ben dataset and LoRA technology. The fine-tuning process of the test-taking and grading model involves first preparing and parsing the MR-Ben dataset, which is specifically adapted for test-taking and grading tasks. Then, based on the LoRa core formula h = W0x + ΔWx = W0x + BAx, while keeping most of the pre-trained model parameters unchanged, low-rank matrix updates are introduced only for specific layers. A carefully designed training process, including data preprocessing, defining LoRa settings, and iterative optimization steps, allows the Qwen model to adapt to this complex inference and evaluation task. The scoring model architecture: The model's input format is a structured text sequence, including the question description, the candidate's answer process, and step-by-step instructions. Specifically, each input instance is constructed into a composite structure containing instructions, context, question, and candidate answers. The model generates a scoring result and corresponding comments. The scoring result is a quantitative assessment of the accuracy and completeness of the candidate's answer, presented in numerical form. The comments are a qualitative analysis of the problem-solving process, pointing out the strengths and weaknesses and making suggestions for improvement.

7. The teaching assistance system based on the fusion of large model agent and database technology according to claim 3 is characterized by: The teaching material management submodule supports uploading of multiple types of teaching materials including teaching syllabus, teaching requirements, lesson plans, study guides, teaching PPTs, and after-class exercises.

8. The teaching assistance system based on the integration of large model agent and database multi-technology according to claim 3 is characterized by: The method for using the teaching auxiliary system includes the following steps: S1, Registration and Login: When using this system for the first time, users need to fill in the necessary system information including identity, user name, account number, password, name, ID number and national real-name system information. When using this system for the first time, users can log in with account number and password. The system will enter different main interfaces according to the identity information of the account. S2, intelligent question answering: users input their own questions, and the big model first determines whether the questions are relevant to the knowledge in the knowledge base. If so, it performs search enhancement and generation in the knowledge base to output the answer. If not, it directly outputs the answer based on the user's "learned knowledge". S3, intelligent generation: When generating teaching material files, the user who is a teacher first uploads a certain type of teaching material as the knowledge base for the large model retrieval enhancement generation, and then enters the requirements, that is, what type of corresponding teaching material the large model needs to generate; when generating LaTeX code, the user who is a teacher first enters the handwritten mathematical expression content in image format, obtains the corresponding LaTeX code, and then previews it. If necessary, the LaTeX code can be manually modified online. S4, Smart Search: Users who are teachers or students can click on the "Smart Search" function in the main interface to perform a search operation. By entering a keyword in the input box, all files containing the keyword will be retrieved from the system public library and accessible private library and displayed for users to download and review. S5, Knowledge Base View: Users who are teachers or students can click "My Knowledge Base" in the main interface function area to enter their personal private knowledge base to view all uploaded files, including the file's review status and upload time information, or click the "Upload" button to continue uploading local teaching materials to the knowledge base for management and choose whether to make them public. Users enter the user's account number in the input box to apply for access to the user's private knowledge base. For the knowledge base that is approved, users can directly view all the file contents in the knowledge base. S6, large model tuning: The user with the administrator identity needs to first select the large model, then select the fine-tuning dataset, set the training parameters and LoRA parameters and the output directory, and then click the "Start" button to start fine-tuning. At the end of fine-tuning, select the output directory of the just fine-tuned model in the checkpoint path, and then enter the chat area for question and answer testing. S7, Data Review: Users with the administrator identity can view all files in all repositories, review and judge the content of the files, and make "pass / fail" operations to change the file review status. The system automatically publishes relevant information to notify the user who owns the file.

Images