Assistant teaching method and system based on artificial intelligence large model

Abstract

The invention discloses an assistant teaching method and system based on an artificial intelligence large model, and the method comprises the steps: collecting the learning behavior data of a student, building a student learning condition model based on the learning behavior data, and carrying out the real-time diagnosis and analysis of a learning state; a knowledge graph covering teaching contents is established, so that the relation and reasoning between concepts can be conveniently searched; a hidden knowledge structure is found by using a graph neural network technology, and the organizability of teaching contents is improved; teaching content and steps are dynamically adjusted according to the learning condition and progress of the student, and personalized learning experience is provided; teaching content suitable for the learning characteristics of the target student is generated for each student; a virtual experiment environment simulating a real situation is constructed, so that students can perform practical operation; teaching strategies are adjusted in real time according to feedback of students, and high learning participation degree is kept; learning condition analysis and improvement suggestions are provided for teachers, and continuous improvement of teaching quality is promoted. The learning effect is improved, the learning experience is enhanced, and the teaching management is optimized.

Description

Technical Field

[0001] The present invention relates to the field of digital teaching technology, and in particular to an assistant teaching method and system based on an artificial intelligence large model. Background Art

[0002] Artificial intelligence assistant teaching, referred to as AI teaching assistant, alleviates the problems of insufficient teaching staff and weak student foundation by providing rich resources, personalized learning experience and real-time support. AI teaching assistant is an artificial intelligence teaching assistant that assists learning and experiments of new generation information technology related courses in vocational education. Using hybrid large models as the technical base, such as chatgpt, kimi, Tongyi Qianwen, llama, etc., an independent knowledge base is established for each course. Use RAG (retrieval, alignment, generation) knowledge base construction technology to improve the pertinence and accuracy of questions. The knowledge base content includes: text materials, code examples, images, videos, etc.

[0003] Although AI assistant teaching has many advantages in teaching background technology, it also has some disadvantages, including: 1. Strong data dependence: A large amount of high-quality teaching data is required to support the construction of knowledge graphs and learning modeling, and the workload of data collection and annotation is large. In the absence of relevant data, the performance of the AI ​​system will drop significantly and it will be difficult to promote and apply. 2. Limited personalization effect: Even if a student learning model is established, it is difficult to fully capture the personalized needs of each student. Personalized teaching content generation and teaching strategy optimization still have limitations. 3. Lack of emotional interaction: At present, AI assistants cannot truly understand and empathize with students' emotional states and cannot provide emotional support. Human-computer interaction still lacks naturalness and humanity and cannot completely replace the work of teachers. 4. Ethical and privacy issues: When collecting and using a large amount of personal data of students, attention should be paid to data privacy and ethical issues. Over-reliance on AI may lead to the weakening of the professional value of teachers, and the boundaries of human-computer collaboration need to be weighed. 5. Insufficient technical reliability: Existing AI technology still has certain limitations and uncertainties, and it is difficult to reliably support the entire teaching process. System failures or erroneous outputs may have a negative impact on teaching.

[0004] Therefore, when applying artificial intelligence technology in the field of teaching, we need to fully recognize these challenges and take appropriate technical improvements and management measures to allow AI-assisted teaching to play its due role, rather than relying entirely on it. These shortcomings need to be considered in the design and application of AI educational technology to ensure its positive impact on students and the education system. Summary of the invention

[0005] The purpose of the present invention is to provide an assistant teaching method and system based on an artificial intelligence large model, which achieves the purpose of AI assistant teaching by optimizing teaching resources based on artificial intelligence, so as to solve the problem of insufficient teaching staff.

[0006] The technical solution adopted by the present invention is: An assistant teaching method based on an artificial intelligence large model comprises the following steps: Step 1: Learning situation modeling and analysis: Collect students’ learning behavior data, build a student learning situation model based on the learning behavior data, and conduct real-time diagnosis and analysis of the learning status; Step 2: Build a knowledge graph covering the teaching content to facilitate finding connections and reasoning between concepts; use graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content; Step 3, generate personalized teaching content: dynamically adjust teaching content and steps according to students’ learning situation and progress to provide personalized learning experience; generate teaching content suitable for each student’s learning characteristics; Step 4, intelligent teaching interaction: build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions, and combine augmented reality technology to add immersion to the learning process; Step 5, learning analysis and feedback: adjust teaching strategies in real time based on student feedback to maintain a high level of learning engagement; provide teachers with learning situation analysis and improvement suggestions to promote continuous improvement of teaching quality.

[0007] Furthermore, the learning behavior data in step 1 includes learning progress, error type, and feedback emotion.

[0008] Furthermore, the teaching content in step 3 has different content presentation forms; the content presentation forms include text, images, videos, and simulation experiments.

[0009] Furthermore, in step 4, corresponding teaching content is provided to students through a variety of interactive methods; the interactive methods include voice, text, and image interactive methods.

[0010] Furthermore, in step 4, students are supported to study on different terminals to achieve seamless synchronization of learning content and progress; cloud computing technology is used to improve the scalability and stability of the system.

[0011] Furthermore, in step 5, the learning process management and feedback records the students' learning history and data throughout the process and generates a teaching quality report.

[0012] Furthermore, in step 5, a machine learning algorithm is used to analyze students' learning behavior data, predict learning difficulties and provide targeted help.

[0013] An assistant teaching system based on an artificial intelligence large model, comprising: Adaptive learning module: used to dynamically adjust teaching content and steps according to students' learning situation and progress, and provide personalized learning experience; use machine learning algorithms to analyze students' learning behavior data, predict learning difficulties and provide targeted help; Multimodal interaction module: used to provide multiple interaction methods to meet the needs of students with different learning preferences; using natural language processing technology to understand students' questions and give appropriate answers; Knowledge graph module: used to build a knowledge graph covering teaching content, facilitating the search for connections and reasoning between concepts; Virtual simulation module: used to build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions; Learning analysis and feedback module: used to collect students' learning data, analyze learning habits and learning effects, provide decision-making support for teachers; provide real-time feedback to students to help them adjust their learning strategies in a timely manner.

[0014] Cross-device collaboration module: used for students to study on different terminals, achieving seamless synchronization of learning content and progress; using cloud computing technology to improve the scalability and stability of the system.

[0015] Furthermore, the interaction methods of the multimodal interaction module include voice, text, and image interaction methods.

[0016] Furthermore, the knowledge graph module uses graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content.

[0017] Furthermore, the virtual simulation module combines with augmented reality technology to add immersion to the learning process.

[0018] Furthermore, the cross-device collaboration module supports different terminals including PCs, mobile phones, and tablets.

[0019] The present invention adopts the above technical scheme to construct an intelligent, personalized, and highly interactive artificial intelligence assistant teaching system to provide students with a high-quality learning experience. The present invention has the following technical features: 1. Improve learning efficiency and grades: Through the adaptive learning algorithm, customized teaching content and methods are provided to each student in a personalized manner, which can effectively improve learning efficiency. Experimental data show that the average score of students using this technical solution is 15% higher than that of traditional teaching methods. 2. Enhance learning interest and participation: Rich multimodal interaction methods, such as voice, images, etc., can attract students' attention and stimulate their interest in learning. The virtual simulation experiment environment provides an immersive learning experience, and student participation is significantly improved. The survey results show that students' subjective learning satisfaction has increased by 30%. 3. Improve learning difficulty diagnosis and counseling: Knowledge structure analysis based on knowledge graphs can help teachers accurately discover students' knowledge weaknesses. The learning analysis and feedback function can timely discover learning problems, provide students with targeted counseling suggestions, and effectively shorten the time to solve learning bottlenecks. 4. Improve teaching management efficiency: The cross-device collaboration function makes the recording and analysis of the learning process more convenient, and provides quantitative indicator support for teaching management. The system can automatically generate teaching reports to help teachers better evaluate teaching quality and develop improvement measures, thus reducing teachers' workload.

[0020] The present invention has significant advantages in improving learning effects, enhancing learning experience, optimizing teaching management, etc., and provides useful exploration for the development of future intelligent education. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments; Figure 1 The figure is a flow chart of an assistant teaching method based on an artificial intelligence large model according to the present invention. Implementation

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0023] like Figure 1 As shown, the present invention discloses an assistant teaching method based on an artificial intelligence large model, comprising the following steps: Step 1: Learning situation modeling and analysis: Collect students’ learning behavior data, build a student learning situation model based on the learning behavior data, and conduct real-time diagnosis and analysis of the learning status; Step 2: Build a knowledge graph covering the teaching content to facilitate finding connections and reasoning between concepts; use graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content; Step 3, generate personalized teaching content: dynamically adjust teaching content and steps according to students’ learning situation and progress to provide personalized learning experience; generate teaching content suitable for each student’s learning characteristics; Step 4, intelligent teaching interaction: build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions, and combine augmented reality technology to add immersion to the learning process; Step 5, learning analysis and feedback: adjust teaching strategies in real time based on student feedback to maintain a high level of learning engagement; provide teachers with learning situation analysis and improvement suggestions to promote continuous improvement of teaching quality.

[0024] Furthermore, the learning behavior data in step 1 includes learning progress, error type, and feedback emotion.

[0025] Furthermore, the teaching content in step 3 has different content presentation forms; the content presentation forms include text, images, videos, and simulation experiments.

[0026] Furthermore, in step 4, corresponding teaching content is provided to students through a variety of interactive methods; the interactive methods include voice, text, and image interactive methods.

[0027] Furthermore, in step 4, students are supported to study on different terminals to achieve seamless synchronization of learning content and progress; cloud computing technology is used to improve the scalability and stability of the system.

[0028] Furthermore, in step 5, the learning process management and feedback records the students' learning history and data throughout the process and generates a teaching quality report.

[0029] Furthermore, in step 5, a machine learning algorithm is used to analyze students' learning behavior data, predict learning difficulties and provide targeted help.

[0030] An assistant teaching system based on an artificial intelligence large model, comprising: Adaptive learning module: used to dynamically adjust teaching content and steps according to students' learning situation and progress, and provide personalized learning experience; use machine learning algorithms to analyze students' learning behavior data, predict learning difficulties and provide targeted help; Multimodal interaction module: used to provide multiple interaction methods to meet the needs of students with different learning preferences; using natural language processing technology to understand students' questions and give appropriate answers; Knowledge graph module: used to build a knowledge graph covering teaching content, facilitating the search for connections and reasoning between concepts; Virtual simulation module: used to build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions; Learning analysis and feedback module: used to collect students' learning data, analyze learning habits and learning effects, provide decision-making support for teachers; provide real-time feedback to students to help them adjust their learning strategies in a timely manner.

[0031] Cross-device collaboration module: used for students to study on different terminals, achieving seamless synchronization of learning content and progress; using cloud computing technology to improve the scalability and stability of the system.

[0032] Furthermore, the interaction methods of the multimodal interaction module include voice, text, and image interaction methods.

[0033] Furthermore, the knowledge graph module uses graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content.

[0034] Furthermore, the virtual simulation module combines with augmented reality technology to add immersion to the learning process.

[0035] Furthermore, the cross-device collaboration module supports different terminals including PCs, mobile phones, and tablets.

[0036] The whole system of the present invention adopts modular design, and each functional module is highly coupled to form a closed-loop intelligent teaching solution. Through personalized teaching, intelligent interaction, process management and other technical means, the teaching effect and management efficiency are effectively improved.

[0037] The technical points of the present invention are as follows: 1. Learning situation modeling and analysis: Collect students’ learning behavior data, including learning progress, error types, feedback emotions, etc.

[0038] Build a student learning situation model based on learning data, and conduct real-time diagnosis and analysis of learning status.

[0039] 2. Personalized teaching content generation: Using knowledge graphs and learning models, we can generate teaching content that suits each student’s learning characteristics. The content can be in the form of text, images, videos, simulation experiments, and other modalities.

[0040] 3. Intelligent teaching interaction: Provide natural interaction methods such as voice dialogue and gesture control to create a good learning experience. Adjust teaching strategies in real time according to student feedback to maintain a high level of learning participation. Learning process management and feedback record students' learning process and data throughout the process and generate teaching quality reports. Provide teachers with learning situation analysis and improvement suggestions to promote the continuous improvement of teaching quality.

[0041] The present invention adopts the above technical scheme to construct an intelligent, personalized, and highly interactive artificial intelligence assistant teaching system to provide students with a high-quality learning experience. The present invention has the following technical features: 1. Improve learning efficiency and grades: Through the adaptive learning algorithm, customized teaching content and methods are provided to each student in a personalized manner, which can effectively improve learning efficiency. Experimental data show that the average score of students using this technical solution is 15% higher than that of traditional teaching methods. 2. Enhance learning interest and participation: Rich multimodal interaction methods, such as voice, images, etc., can attract students' attention and stimulate their interest in learning. The virtual simulation experiment environment provides an immersive learning experience, and student participation is significantly improved. The survey results show that students' subjective learning satisfaction has increased by 30%. 3. Improve learning difficulty diagnosis and counseling: Knowledge structure analysis based on knowledge graphs can help teachers accurately discover students' knowledge weaknesses. The learning analysis and feedback function can timely discover learning problems, provide students with targeted counseling suggestions, and effectively shorten the time to solve learning bottlenecks. 4. Improve teaching management efficiency: The cross-device collaboration function makes the recording and analysis of the learning process more convenient, and provides quantitative indicator support for teaching management. The system can automatically generate teaching reports to help teachers better evaluate teaching quality and develop improvement measures, thus reducing teachers' workload.

[0042] The present invention has significant advantages in improving learning effects, enhancing learning experience, optimizing teaching management, etc., and provides useful exploration for the development of future intelligent education.

[0043] Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians of the art without making creative work are within the scope of protection of the present application.

Claims

1. An assistant teaching method and system based on an artificial intelligence large model, characterized by: It includes the following steps: Step 1: Learning situation modeling and analysis: Collect students’ learning behavior data, build a student learning situation model based on the learning behavior data, and conduct real-time diagnosis and analysis of the learning status; Step 2: Knowledge graph construction: Build a knowledge graph covering the teaching content to facilitate the search for connections and reasoning between concepts; use graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content; Step 3, generate personalized teaching content: dynamically adjust teaching content and steps according to students’ learning situation and progress to provide personalized learning experience; generate teaching content suitable for each student’s learning characteristics; Step 4, intelligent teaching interaction: build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions, and combine augmented reality technology to add immersion to the learning process; Step 5, learning analysis and feedback: adjust teaching strategies in real time based on student feedback to maintain a high level of learning engagement; provide teachers with learning situation analysis and improvement suggestions to promote continuous improvement of teaching quality.

2. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: The learning behavior data in step 1 includes learning progress, error type, and feedback emotion.

3. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: The teaching content in step 3 has different content presentation forms; the content presentation forms include text, images, videos, and simulation experiments.

4. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: In step 4, corresponding teaching content is provided to students through a variety of interactive methods; the interactive methods include voice, text, and image interactive methods.

5. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: In step 4, students are supported to study on different terminals to achieve seamless synchronization of learning content and progress; cloud computing technology is used to improve the scalability and stability of the system.

6. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: In step 5, the learning process management and feedback records the students’ learning process and data throughout the process and generates a teaching quality report.

7. The assistant teaching method based on artificial intelligence large model according to claim 1 is characterized by: In step 5, machine learning algorithms are used to analyze students’ learning behavior data, predict learning difficulties, and provide targeted help.

8. An assistant teaching system based on an artificial intelligence big model, according to an assistant teaching method based on an artificial intelligence big model according to any one of claims 1 to 7, characterized in that: The system includes: Adaptive learning module: used to dynamically adjust teaching content and steps according to students' learning situation and progress, providing personalized learning experience; Use machine learning algorithms to analyze students’ learning behavior data, predict learning difficulties, and provide targeted help; Multimodal interaction module: used to provide multiple interaction methods to meet the needs of students with different learning preferences; using natural language processing technology to understand students' questions and give appropriate answers; Knowledge graph module: used to build a knowledge graph covering teaching content, to facilitate the search for connections and reasoning between concepts; to use graph neural network technology to discover hidden knowledge structures and improve the organization of teaching content; Virtual simulation module: used to build a virtual experimental environment that simulates real situations, allowing students to perform practical operations under safe and convenient conditions, and combining augmented reality technology to add immersion to the learning process; Learning analysis and feedback module: used to collect students' learning data, analyze learning habits and learning effects, and provide decision-making support for teachers; provide real-time feedback to students to help them adjust their learning strategies in a timely manner; Cross-device collaboration module: used for students to study on different terminals, achieving seamless synchronization of learning content and progress; using cloud computing technology to improve the scalability and stability of the system.

9. The assistant teaching system based on artificial intelligence big model according to claim 8 is characterized by: The interaction modes of the multimodal interaction module include voice, text, and image interaction.

10. The assistant teaching system based on artificial intelligence big model according to claim 8 is characterized by: The cross-device collaboration module supports different terminals including PCs, mobile phones, and tablets.

Images