Multimedia teaching courseware generation method based on AIGC

Abstract

The invention discloses an AIGC-based multimedia teaching courseware generation method, relates to the technical field of data processing, and mainly solves the problems of low efficiency, single courseware content and low courseware quality. The AIGC-based multimedia teaching courseware generation method comprises the implementation steps of collecting demand data of teaching courseware; processing and analyzing the received demand data; creating a detailed teaching courseware outline and a teaching courseware content structure; generating multimedia elements and courseware contents in the teaching courseware; integrating and editing the content generated by the AIGC tool; multimedia teaching courseware is previewed and detected and exported and iteratively managed, and a teaching target and student data are analyzed through a dynamic analysis algorithm, so that the courseware generation efficiency is improved; by adopting the multimedia material content, the diversification of the courseware content is improved; and the generated media material contents are fused through an information fusion algorithm, so that the courseware quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for generating multimedia teaching courseware based on AIGC. Background Art

[0002] With the advancement of educational informatization, multimedia teaching has become an important means of education and teaching. AIGC, or artificial intelligence generated content, has become an important breakthrough in the field of educational technology. The huge demand of the education market and the thirst for high-quality teaching resources provide AIGC with broad application prospects. With the maturity of computer technology, AIGC can be applied to the automatic generation of multimedia teaching content, which not only improves the personalization of teaching resources, but also greatly enriches the teaching form, making the acquisition and use of educational resources more convenient. However, the traditional teaching courseware generation method still has problems such as low generation efficiency, single courseware content and low courseware quality.

[0003] Therefore, the present invention provides a multimedia teaching courseware generation method based on AIGC, which analyzes teaching objectives and student data through a dynamic analysis algorithm, thereby improving the generation efficiency of courseware; by adopting multimedia material content, the diversification of courseware content is improved; and by integrating the generated media material content through an information fusion algorithm, the quality of courseware is improved. Summary of the invention

[0004] The purpose of the present invention is to solve the problems of low generation efficiency, single courseware content and low courseware quality in the prior art, and to propose a multimedia teaching courseware generation method based on AIGC.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for generating multimedia teaching courseware based on AIGC comprises the following steps:

[0007] S1. Collect teaching courseware demand data, including teaching objectives, teaching content, teaching methods, students’ knowledge background and learning preferences;

[0008] S2. Process and analyze the received demand data to extract key information of the courseware;

[0009] S3. Create a detailed teaching courseware outline and teaching courseware content structure;

[0010] S4. Select AIGC tools and generate multimedia elements and courseware content in teaching courseware;

[0011] S5. Integrate and edit the content generated by AIGC tools;

[0012] S6. Preview and test multimedia teaching courseware and export them, and perform iterative management based on feedback data;

[0013] The steps include a data collection module, a data analysis module, a courseware structure design module, a content generation module, an integrated editing module and a courseware management module; the data collection module transmits the teaching objectives, teaching resources, students' knowledge background and learning preference data information to the data analysis module to be converted into executable information; the data analysis module directs the processed and analyzed data to the courseware structure design module to provide a basis for courseware outline design and teaching content framework; after the courseware structure design is completed, multimedia courseware content is generated according to content requirements and the content generation module; the generated multimedia courseware content is screened, combined and optimized by the integrated editing module; the edited courseware is imported into the courseware management module for preview, detection, upload and management.

[0014] As a further description of the above technical solution, the data collection module includes a teaching research unit, a student information unit and a data integration unit. The teaching research unit collects teaching objectives, teaching content and teaching methods through questionnaires; the student information unit collects students' knowledge background and learning preferences through the learning management system LMS; and the data integration unit collects external teaching resources related to the teaching content through web crawlers.

[0015] As a further description of the above technical solution, the data analysis module includes a data preprocessing unit, an adaptive analysis unit and a decision support unit. The data preprocessing unit removes duplicate data, processes missing values ​​and standardizes data formats on the collected data through data cleaning, conversion and formatting; the adaptive analysis unit analyzes teaching objectives and student data through a dynamic analysis algorithm, and provides the analysis data to the decision support unit for formulating courseware generation strategies; the decision support unit provides strategic support for the generation of teaching courseware through decision trees and data analysis results.

[0016] As a further description of the above technical solution, the implementation steps of the dynamic analysis algorithm are:

[0017] (1) Extract characteristic information of teaching objectives, teaching content, teaching methods, students’ knowledge background, and learning preferences, including grades, participation, learning time, and homework completion;

[0018] (2) Model training is performed on feature data using a random forest-based machine learning model;

[0019] (3) The model parameters are tuned by adjusting the function to improve the accuracy, and new data are continuously collected for updating the model. The formula expression of the adjustment function is:

[0020]

[0021] In formula (1), T represents the adjustment function, m represents the number of data to be analyzed, k represents the depth of the tree in the random forest model, and α i represents the data to be analyzed, i represents the order of the data to be analyzed, Indicates the data analysis value to be tuned. Indicates the maximum number of features to be adjusted;

[0022] (4) Deploy the trained model to the decision support system to ensure that the model can receive data and generate analysis results in real time;

[0023] (5) Regularly evaluate the performance of the model through the detection function. When the performance deteriorates, retrain the model to adjust the analysis strategy in real time based on student behavior and TensorFlow. The formula of the detection function is expressed as:

[0024]

[0025] In formula (2), M represents the detection function, ρ represents the detection function factor, β represents the data included in the data collection module in the model, γ represents the model performance comparison value, and i represents the order of the data to be detected;

[0026] (6) Use the data visualization tool Matplotlib to present the analysis results.

[0027] As a further description of the above technical solution, the courseware structure design module includes an outline preparation unit, a module division unit and a learning path planning unit. The outline preparation unit generates the outline structure of the courseware through the Tiangong AI model to build a knowledge framework for the generation of the courseware; the module division unit subdivides the outline structure into different modules through cluster analysis to generate the content layout of the courseware; the learning path planning unit sorts the learning order of the courseware content through reinforcement learning to carry out systematic course teaching.

[0028] As a further description of the above technical solution, the content generation module includes a text generation unit, a multimedia creation unit, an interaction unit and an assessment unit. The text generation unit generates handout text in the courseware through natural language generation NLG, including knowledge point explanation, principle analysis, review and summary; the multimedia creation unit generates pictures, audio and video materials in the courseware through ChatGpt and Keling AI tools based on the generated text content; the interaction unit conducts case analysis, simulation experiments and problem discussions through interactive whiteboards, online simulation laboratories and AI robots to enhance students' learning experience; the assessment unit conducts in-class tests on students through test questions to evaluate students' mastery.

[0029] As a further description of the above technical solution, the integrated editing module includes a content fusion unit, an editing and modification unit and a layout optimization unit. The content fusion unit integrates the text, multimedia materials, interactive content and assessment methods generated by the content generation module into the designed courseware structure through an information fusion algorithm to form a complete and coherent courseware; the editing and modification unit checks and modifies the grammatical, format and logical errors of the courseware content through natural language processing NLP and computer vision CV; the layout optimization unit adjusts the visual presentation of the courseware through Canva to ensure that the information hierarchy is clear, beautiful and easy to read.

[0030] As a further description of the above technical solution, the implementation steps of the information fusion algorithm are:

[0031] a. Identify and classify the content through the type recording function, analyze the input text, pictures and videos to identify their types and attributes. The formula expression of the type recording function is:

[0032]

[0033] In formula (3), P represents the type record function, θ i represents the content data value to be classified, ξ represents the classification threshold of the type record function, i represents the order of the content data value to be classified, Indicates the attribute value of the input text, image, and video;

[0034] b. Conduct a needs analysis of teaching objectives and student learning to determine what types of content and interactive elements the courseware needs to include;

[0035] c. Based on the results of the needs analysis, map different types of content to the corresponding parts of the teaching courseware objectives;

[0036] d. Detect potential conflicts between different contents, including duplicate information and logical inconsistencies, through a decision function, and resolve conflicts by adjusting the order of the contents and merging similar contents. The formula expression of the decision function is:

[0037]

[0038]

[0039] In formulas (4)-(5), N i represents repeated information detection, ω represents the detection coefficient of repeated information detection, γ i Indicates the data to be detected for repeated information detection, Φ i Indicates the comparison value of the data to be detected for duplicate information detection, i indicates the order of duplicate information detection, N 2irepresents logic detection, μ represents the logic detection coefficient, υ i It indicates the data to be tested for logic testing, and T indicates the order of logic testing;

[0040] e. Test the integrated courseware and collect user feedback. Continuously iterate the courseware content based on the test results and feedback to improve quality and effectiveness.

[0041] As a further description of the above technical solution, the courseware management module includes a preview detection unit, an export unit, a feedback unit and a maintenance unit. The preview detection unit previews and runs the courseware by simulating the actual usage environment; the export unit saves the courseware in PPT format and uploads it to the LMS for online viewing; the feedback unit collects user feedback information through an integrated online feedback system for subsequent courseware optimization; the maintenance unit updates the content information of the courseware according to the received user feedback information and teaching needs, the output end of the preview detection unit is connected to the input end of the export unit, the output end of the export unit is connected to the input end of the feedback unit, and the output end of the feedback unit is connected to the input end of the maintenance unit.

[0042] Other advantages, objectives and features of the present invention will be described in part in the following description; and in part, will be apparent to those skilled in the art based on an examination of the following; or, may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to understand and grasp the technical solution more intuitively and clearly, when describing the embodiments of the present invention or the prior art, drawings are often used to supplement and illustrate. It should be noted that the drawings are only one way of expressing the embodiments of the present invention or the prior art. In fact, the technical solution can also have other implementation methods and changes, which all fall within the protection scope of the present invention. Therefore, technicians can design other drawings as needed to implement the technical solution of the present invention, among which,

[0044] Figure 1 The figure is a general flow chart of the steps of the present invention.

[0045] Figure 2 It is a structural schematic diagram of the data analysis module of the present invention.

[0046] Figure 3 The figure is a flow chart of the steps of the dynamic analysis algorithm of the present invention.

[0047] Figure 4 It is a structural schematic diagram of the content generation module of the present invention.

[0048] Figure 5It is a flow chart of the steps of the information fusion algorithm of the present invention.

[0049] Figure 6 It is a structural diagram of the courseware management module of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of this invention through the accompanying drawings in the embodiments of this invention. Obviously, the described embodiments are only part of the embodiments of this invention, not all of the embodiments. At the same time, the description of well-known structures and technologies is omitted in the following description to avoid unnecessary confusion of the concepts of the present invention.

[0051] like Figure 1-Figure 6 As shown, a method for generating multimedia teaching courseware based on AIGC includes the following steps:

[0052] S1. Collect teaching courseware demand data, including teaching objectives, teaching content, teaching methods, students’ knowledge background and learning preferences;

[0053] S2. Process and analyze the received demand data to extract key information of the courseware;

[0054] S3. Create a detailed teaching courseware outline and teaching courseware content structure;

[0055] S4. Select AIGC tools and generate multimedia elements and courseware content in teaching courseware;

[0056] S5. Integrate and edit the content generated by AIGC tools;

[0057] S6. Preview and test multimedia teaching courseware and export them, and perform iterative management based on feedback data;

[0058] The steps include a data collection module, a data analysis module, a courseware structure design module, a content generation module, an integrated editing module and a courseware management module; the data collection module transmits the teaching objectives, teaching resources, students' knowledge background and learning preference data information to the data analysis module to be converted into executable information; the data analysis module directs the processed and analyzed data to the courseware structure design module to provide a basis for courseware outline design and teaching content framework; after the courseware structure design is completed, multimedia courseware content is generated according to content requirements and the content generation module; the generated multimedia courseware content is screened, combined and optimized by the integrated editing module; the edited courseware is imported into the courseware management module for preview, detection, upload and management.

[0059] In a specific embodiment, the data collection module includes a teaching research unit, a student information unit and a data integration unit. The teaching research unit deeply explores the teaching objectives of teachers through questionnaires, refines the teaching content, and explores innovative teaching methods. These data not only reflect the core needs of teaching, but also provide a basis for subsequent teaching adjustments; the student information unit uses the learning management system LMS to fully capture the students' knowledge background, understand their learning preferences, and pave the way for data analysis of learning behavior patterns in the later stage. Deeply understanding students' learning habits enables educators to formulate personalized teaching plans for different students and improve teaching quality; the data integration unit connects internal teaching resources with external interconnected resource data, and collects external teaching resources closely related to the teaching content through web crawler technology, including professional literature, online courses and research reports, etc., to expand the scope of educational resources and the diversity of course content. The three units work together to form a closed-loop data ecology. The teaching research unit clarifies the direction, the student information unit provides a customized perspective, and the data integration unit incorporates more educational resources, which not only greatly improves teaching efficiency, but also provides a solid foundation for educational research and innovation.

[0060] In a specific embodiment, the data analysis module includes a data preprocessing unit, an adaptive analysis unit and a decision support unit. The data preprocessing unit removes redundant and repeated information through a data cleaning process to ensure the purity of the data; fills in the blanks with filling technology for missing fields in the data to make the data more complete; and lays a solid foundation for subsequent analysis through a unified data format; the adaptive analysis unit uses a dynamic analysis algorithm to conduct an in-depth analysis of teaching objectives and student data to capture the learning characteristics and potential needs of each student. The dynamic analysis algorithm accurately matches the teaching objectives with the students' actual learning situation to provide data support for subsequent personalized teaching strategies; the decision support unit uses a decision tree algorithm and comprehensive analysis results to provide strategic support for the generation of teaching courseware, effectively predict and respond to future education trends, and bring students a more personalized and efficient learning experience.

[0061] In a specific embodiment, the implementation steps of the dynamic analysis algorithm are:

[0062] (1) Extract characteristic information of teaching objectives, teaching content, teaching methods, students’ knowledge background, and learning preferences, including grades, participation, learning time, and homework completion;

[0063] (2) Model training is performed on feature data using a random forest-based machine learning model;

[0064] (3) The model parameters are tuned by adjusting the function to improve the accuracy, and new data are continuously collected for updating the model. The formula expression of the adjustment function is:

[0065]

[0066] In formula (1), T represents the adjustment function, m represents the number of data to be analyzed, k represents the depth of the tree in the random forest model, and α i represents the data to be analyzed, i represents the order of the data to be analyzed, Indicates the data analysis value to be tuned. Indicates the maximum number of features to be adjusted;

[0067] (4) Deploy the trained model to the decision support system to ensure that the model can receive data and generate analysis results in real time;

[0068] (5) Regularly evaluate the performance of the model through the detection function. When the performance deteriorates, retrain the model to adjust the analysis strategy in real time based on student behavior and TensorFlow. The formula of the detection function is expressed as:

[0069]

[0070] In formula (2), M represents the detection function, ρ represents the detection function factor, β represents the data included in the data collection module in the model, γ represents the model performance comparison value, and i represents the order of the data to be detected;

[0071] (6) Use the data visualization tool Matplotlib to present the analysis results.

[0072] The role of the dynamic analysis algorithm is to deeply understand teaching and student data, provide data-driven decision support for courseware generation strategies, solve the dynamic and personalized matching of teaching content and student needs, and ensure the appropriateness and attractiveness of courseware content. Dynamic analysis is achieved through a series of steps including feature extraction, model training, parameter tuning, model deployment, performance evaluation, and data visualization. The number of data to be analyzed m, the depth of the tree in the random forest model k, and the number of data to be analyzed α i , Data analysis value to be tuned and the maximum number of features to be adjusted Generate the adjustment function and tune the model parameters to improve accuracy; regularly evaluate the performance of the model by detecting the function factor ρ, the data β contained in the data collection module in the model, and the model performance comparison value γ, and retrain the model when the performance degrades to adjust the analysis strategy in real time according to the student behavior and TensorFlow; in the specific implementation process, use the random forest model for training and prediction, rely on Python, TensorFlow and other software environments for data processing, and use the cloud platform to carry out calculations and storage. In summary, the dynamic analysis algorithm realizes the prediction and analysis of student behavior through the random forest model, and uses various tools and cloud platforms in the Python ecosystem to achieve efficient and flexible courseware generation strategy formulation. The continuous optimization and deployment of the model ensures the precise matching of teaching content and student needs, and improves teaching effectiveness and student satisfaction. The differences between the traditional data analysis algorithm and the dynamic analysis algorithm are shown in Table 1:

[0073] Table 1 Differences between traditional data analysis algorithms and dynamic analysis algorithms

[0074]

[0075]

[0076] In summary, the dynamic analysis algorithm is superior to the traditional data analysis algorithm in three aspects: data extraction efficiency, data adjustment efficiency and data analysis efficiency. It can be seen that the dynamic analysis algorithm is the best choice for the present invention.

[0077] In a specific embodiment, the courseware structure design module includes an outline preparation unit, a module division unit and a learning path planning unit. The outline preparation unit generates the outline structure of the courseware through the Tiangong AI big model to construct a knowledge framework for the generation of the courseware. The core of the outline preparation unit is the Tiangong AI big model, which uses AIGC technology to accurately capture the core knowledge points of the course to automatically generate a logically rigorous and hierarchical courseware outline, which not only provides a clear knowledge framework for subsequent content filling, but also ensures the consistency and depth of the courseware in knowledge transmission; the module division unit subdivides the outline structure into different modules through cluster analysis to generate the content layout of the courseware, and further subdivides the outline prepared by the outline preparation unit through the cluster analysis algorithm to form independent and interrelated learning modules. At the same time, each module revolves around a specific theme, which not only ensures the depth of the content, but also facilitates students to systematically learn and master knowledge. It not only improves the readability of the courseware, but also greatly facilitates teachers' teaching and students' learning. The learning path planning unit sorts the learning order of the courseware content through reinforcement learning and students' learning habits, progress and feedback, ensuring that each step of learning is based on the knowledge already mastered, thereby realizing systematic teaching.

[0078] In a specific embodiment, the content generation module includes a text generation unit, a multimedia creation unit, an interactive unit and an assessment unit. The text generation unit automatically generates course handout texts through natural language generation (NLG). These texts not only cover knowledge point explanations and in-depth principle analysis, but also contain review materials and refined summaries to ensure that the learning content is comprehensive and profound. The multimedia creation unit converts static knowledge point text content into vivid images, sounds and videos based on the generated text content with the help of ChatGPT and Keling AI tools. The multimedia materials not only enrich the content of the courseware, but also enhance the students' visual and auditory experience, stimulating students' learning. learning interest; the interactive unit conducts case analysis and interaction with students in the classroom through an interactive whiteboard; the online simulation laboratory uses ChemSketch, ANSYS and MultisimLive online software to help students conduct online simulation experiments in the classroom and absorb knowledge content more vividly; through the intelligent question and answer function of the AI ​​robot, discuss problems with students to enhance the students' learning experience; the assessment unit conducts in-class tests on students by designing test questions, designs different types of questions such as multiple-choice questions, fill-in-the-blank questions and answer questions according to teaching objectives and knowledge points, and uses AI scoring technology to automatically evaluate students' answers.

[0079] In a specific embodiment, the integrated editing module includes a content fusion unit, an editing and modification unit and a layout optimization unit. The content fusion unit integrates the text, multimedia materials, interactive content and assessment evaluation methods generated by the content generation module into the designed courseware structure through an information fusion algorithm; the editing and modification unit checks and modifies the grammatical, format and logical errors of the courseware content through natural language processing NLP and computer vision CV. The NLP technology can be used to detect grammatical errors, spelling errors and incoherent expressions in the text, while the CV technology can be used to check visual problems in multimedia materials, such as image clarity and video editing errors; the layout optimization unit adjusts the visual presentation of the courseware through Canva, taking into account the overall design of the courseware, including color matching, font selection, image usage, typeface layout, etc., to improve learners' reading experience and information absorption efficiency.

[0080] In a specific embodiment, the implementation steps of the information fusion algorithm are:

[0081] a. Identify and classify the content through the type recording function, analyze the input text, pictures and videos to identify their types and attributes. The formula expression of the type recording function is:

[0082]

[0083] In formula (3), P represents the type record function, θi represents the content data value to be classified, ξ represents the classification threshold of the type record function, i represents the order of the content data value to be classified, Indicates the attribute value of the input text, image, and video;

[0084] b. Conduct a needs analysis of teaching objectives and student learning to determine what types of content and interactive elements the courseware needs to include;

[0085] c. Based on the results of the needs analysis, map different types of content to the corresponding parts of the teaching courseware objectives;

[0086] d. Detect potential conflicts between different contents, including duplicate information and logical inconsistencies, through a decision function, and resolve conflicts by adjusting the order of the contents and merging similar contents. The formula expression of the decision function is:

[0087]

[0088]

[0089] In formulas (4)-(5), N i represents repeated information detection, ω represents the detection coefficient of repeated information detection, γ i Indicates the data to be detected for repeated information detection, Φ i Indicates the comparison value of the data to be detected for duplicate information detection, i indicates the order of duplicate information detection, N 2i represents logic detection, μ represents the logic detection coefficient, υ i Indicates the data to be tested for logical testing, and i indicates the order of logical testing;

[0090] e. Test the integrated courseware and collect user feedback. Continuously iterate the courseware content based on the test results and feedback to improve quality and effectiveness.

[0091] The function of the information fusion algorithm is to ensure that the teaching content is highly matched with the needs of students, and to enhance the attractiveness and teaching effect of the courseware; it solves the problem of overcoming content conflicts and logical confusion, and ensures the coherence and integrity of the courseware content; the information fusion algorithm is implemented through type identification, demand analysis, content mapping, conflict detection and iterative optimization steps, and integrates the text, multimedia materials, interactive content and assessment methods generated by the content generation module into the designed courseware structure to form a complete and coherent courseware, and the content data value θ to be classified is used to calculate the content of the courseware. i , the classification threshold ζ of the type record function, the attribute values ​​of the input text, pictures and videos Generate a recording function formula to identify and classify the content, analyze the input text, pictures and videos to identify their types and attributes; through the detection coefficient ω of repeated information detection, the data to be detected γ of repeated information detection i , the comparison value of the data to be detected for repeated information detection Φ i Get the duplicate information detection formula Detect repeated information between different contents, through the logical detection coefficient μ and the logical detection data v i Get the logical test formula Detect the logical consistency between different contents, use NLP and CV technology to identify and classify content, use decision tree algorithm to resolve conflicts, and use A / B testing to iterate and optimize. The difference between the traditional data fusion method and the information fusion algorithm is shown in Table 2:

[0092] Table 2 Differences between traditional data fusion methods and information fusion algorithms

[0093]

[0094] In summary, the information fusion algorithm is superior to the traditional data fusion method in terms of detection efficiency and fusion efficiency. It can be seen that the data fusion algorithm is the best choice for the present invention.

[0095] In a specific embodiment, the courseware management module includes a preview detection unit, an export unit, a feedback unit and a maintenance unit. The preview detection unit uses virtual simulation technology to simulate a real teaching scene and conducts a comprehensive and detailed test on the courseware to be used, which not only covers the functional test of the courseware, such as the interaction fluency and the compatibility of multimedia elements, but also includes the accuracy and suitability evaluation of the content, to ensure that each courseware can play the best effect in actual teaching; the export unit saves the courseware in PPT format and uploads it to the LMS for online viewing. Before the course starts, the teacher will browse the courseware according to the LMS to prepare for the class. After the course ends, students and parents can browse and save the courseware online to consolidate the knowledge; the feedback unit collects user feedback information by integrating the online feedback system, invites teachers and students to share their experience and suggestions, and the collected valuable feedback will be directly used for the iterative upgrade of the courseware to ensure that the content of the courseware always meets the teaching needs; the maintenance unit updates the content information of the courseware according to the received user feedback information and teaching needs, regularly checks and analyzes user feedback, and makes necessary modifications and updates to the courseware in combination with the actual teaching situation.

[0096] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for generating multimedia teaching courseware based on AIGC, characterized in that: The steps include: S1. Collect teaching courseware demand data, including teaching objectives, teaching content, teaching methods, students’ knowledge background and learning preferences; S2. Process and analyze the received demand data to extract key information of the courseware; S3. Create a detailed teaching courseware outline and teaching courseware content structure; S4. Select AIGC tools and generate multimedia elements and courseware content in teaching courseware; S5. Integrate and edit the content generated by AIGC tools; S6. Preview and test multimedia teaching courseware and export them, and perform iterative management based on feedback data; The steps include a data collection module, a data analysis module, a courseware structure design module, a content generation module, an integration editing module and a courseware management module; the data collection module transmits teaching objectives, teaching resources, student knowledge background and learning preference data information to the data analysis module to convert them into executable information; The data analysis module directs the processed and analyzed data to the courseware structure design module to provide a basis for courseware syllabus design and teaching content framework; after the courseware structure design is completed, multimedia courseware content is generated according to content requirements and the content generation module; The generated multimedia courseware content is screened, combined and optimized by the integration editing module; The edited courseware is imported into the courseware management module for preview, detection, uploading and management.

2. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The data collection module includes a teaching research unit, a student information unit and a data integration unit. The teaching research unit collects teaching objectives, teaching content and teaching methods through questionnaires; the student information unit collects students' knowledge background and learning preferences through the learning management system LMS; and the data integration unit collects external teaching resources related to the teaching content through web crawlers.

3. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The data analysis module includes a data preprocessing unit, an adaptive analysis unit and a decision support unit. The data preprocessing unit removes duplicate data, processes missing values ​​and standardizes data formats on the collected data through data cleaning, conversion and formatting; The adaptive analysis unit analyzes the teaching objectives and student data through a dynamic analysis algorithm, and provides the analysis data to the decision support unit for formulating a courseware generation strategy; the decision support unit provides strategic support for the generation of teaching courseware through a decision tree and data analysis results.

4. The method for generating multimedia teaching courseware based on AIGC according to claim 3, characterized in that: The implementation steps of the dynamic analysis algorithm are: (1) Extract characteristic information of teaching objectives, teaching content, teaching methods, students’ knowledge background, and learning preferences, including grades, participation, learning time, and homework completion; (2) Model training is performed on feature data using a random forest-based machine learning model; (3) The model parameters are tuned by adjusting the function to improve the accuracy, and new data are continuously collected for updating the model. The formula expression of the adjustment function is: In formula (1), T represents the adjustment function, m represents the number of data to be analyzed, k represents the depth of the tree in the random forest model, and α i represents the data to be analyzed, i represents the order of the data to be analyzed, Indicates the data analysis value to be tuned. Indicates the maximum number of features to be adjusted; (4) Deploy the trained model to the decision support system to ensure that the model can receive data and generate analysis results in real time; (5) Regularly evaluate the performance of the model through the detection function. When the performance deteriorates, retrain the model to adjust the analysis strategy in real time based on student behavior and TensorFlow. The formula of the detection function is expressed as: In formula (2), M represents the detection function, ρ represents the detection function factor, β represents the data included in the data collection module in the model, γ represents the model performance comparison value, and i represents the order of the data to be detected; (6) Use the data visualization tool Matplotlib to present the analysis results.

5. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The courseware structure design module includes an outline preparation unit, a module division unit and a learning path planning unit. The outline preparation unit generates the outline structure of the courseware through the Tiangong AI model to build a knowledge framework for the generation of the courseware; the module division unit subdivides the outline structure into different modules through cluster analysis to generate the content layout of the courseware; The learning path planning unit arranges the learning sequence of the courseware contents through reinforcement learning so as to carry out systematic course teaching.

6. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The content generation module includes a text generation unit, a multimedia creation unit, an interaction unit and an assessment unit. The text generation unit generates the handout text in the courseware through natural language generation (NLG), including knowledge point explanation, principle analysis, review and summary; the multimedia creation unit generates pictures, audio and video materials in the courseware through ChatGpt and Keling AI tools based on the generated text content; the interaction unit conducts case analysis, simulation experiments and problem discussions through interactive whiteboards, online simulation laboratories and AI robots to enhance students' learning experience; the assessment unit conducts in-class tests on students through test questions to evaluate their mastery.

7. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The integrated editing module includes a content fusion unit, an editing and modification unit, and a layout optimization unit. The content fusion unit integrates the text, multimedia materials, interactive content, and assessment and evaluation methods generated by the content generation module into the designed courseware structure through an information fusion algorithm to form a complete and coherent courseware. The editing and modification unit checks and modifies the grammatical, formatting and logical errors of the courseware content through natural language processing NLP and computer vision CV; the layout optimization unit adjusts the visual presentation of the courseware through Canva to ensure that the information hierarchy is clear, beautiful and easy to read.

8. The method for generating multimedia teaching courseware based on AIGC according to claim 7, characterized in that: The implementation steps of the information fusion algorithm are: a. Identify and classify the content through the type recording function, analyze the input text, pictures and videos to identify their types and attributes. The formula expression of the type recording function is: In formula (3), P represents the type record function, θ i represents the content data value to be classified, ξ represents the classification threshold of the type record function, i represents the order of the content data value to be classified, Indicates the attribute value of the input text, image, and video; b. Conduct a needs analysis of teaching objectives and student learning to determine what types of content and interactive elements the courseware needs to include; c. Based on the results of the needs analysis, map different types of content to the corresponding parts of the teaching courseware objectives; d. Detect potential conflicts between different contents, including duplicate information and logical inconsistencies, through a decision function, and resolve conflicts by adjusting the order of the contents and merging similar contents. The formula expression of the decision function is: In formulas (4)-(5), N i represents repeated information detection, ω represents the detection coefficient of repeated information detection, Υ i Indicates the data to be detected for duplicate information detection, φ i Indicates the comparison value of the data to be detected for duplicate information detection, i indicates the order of duplicate information detection, N 2i represents logic detection, μ represents the logic detection coefficient, υ i Indicates the data to be tested for logical testing, and i indicates the order of logical testing; e. Test the integrated courseware and collect user feedback. Continuously iterate the courseware content based on the test results and feedback to improve quality and effectiveness.

9. The method for generating multimedia teaching courseware based on AIGC according to claim 1, characterized in that: The courseware management module includes a preview detection unit, an export unit, a feedback unit and a maintenance unit. The preview detection unit previews and runs the courseware by simulating the actual use environment; the export unit saves the courseware in PPT format and uploads it to the LMS for online viewing; The feedback unit collects user feedback information through an integrated online feedback system for subsequent optimization of courseware; the maintenance unit updates the content information of the courseware based on the received user feedback information and teaching needs, the output end of the preview detection unit is connected to the input end of the export unit, the output end of the export unit is connected to the input end of the feedback unit, and the output end of the feedback unit is connected to the input end of the maintenance unit.

Images