Management teaching information processing method and system based on digital twinning

Abstract

The invention discloses a management teaching information processing method and system based on digital twinning, which can construct a personalized knowledge graph according to a digital twinning learning model, and accurately identify knowledge blind spots and weak links existing in the learning process of students by analyzing a pre-repair relationship and learning dependence between knowledge points. By utilizing the information, the presentation sequence of the learning path and the content can be further optimized, so that the students can be ensured to master each knowledge point according to the most suitable learning sequence. And meanwhile, performing learning influence weight analysis on each personalized learning content, calculating the actual influence of the personalized learning content on the learning effect of the student, and preferentially arranging the most critical content for improving the learning effect of the student for learning according to the analysis results. Through the optimization and adjustment, the learning efficiency of the students can be improved, the overall learning effect can be effectively improved, and the students are helped to solve learning difficulties in a more targeted manner.

Description

Technical Field

[0001] The present invention belongs to the field of management teaching information, and specifically, relates to a management teaching information processing method and system based on digital twins. Background Art

[0002] With the development of information technology, the field of education is gradually transforming towards digitalization and intelligence, giving rise to more data-driven teaching innovations. However, traditional teaching models often face many challenges such as insufficient personalization, difficulty in real-time feedback, and lack of accurate data support. In traditional classrooms, teachers mainly rely on experience and intuition to teach, and it is difficult to understand the learning status and needs of each student in real time, resulting in the inability to implement targeted teaching and dynamically adjust teaching content, especially the difficulty in quickly responding to students' immediate problems and learning bottlenecks during the teaching process. In addition, although the popularity of online education platforms provides students with rich learning resources and flexible learning methods, due to the lack of refined management and personalized support for the learning process, it is impossible to make dynamic adjustments based on students' learning progress and understanding, and students' learning effects are still uneven. This one-size-fits-all teaching method often ignores individual differences among students, fails to effectively meet the needs of different learners, and therefore cannot fully tap the potential and effectiveness of education.

[0003] In view of this, the present invention is proposed. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a management teaching information processing method and system based on digital twins, which solves the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0006] A management teaching information processing method based on digital twins includes the following steps:

[0007] Obtain students' multimodal data through the interactive teaching platform and digitize the acquired multimodal data to build an initial digital twin learning model;

[0008] Use the digital twin learning model to analyze students’ learning characteristics and current status and generate multiple personalized learning contents based on the analysis results, adjusting teaching resources and content according to the needs of different students;

[0009] Monitor students’ learning status data in real time during the teaching process and update the digital twin learning model based on real-time data;

[0010] Based on the updated digital twin learning model, build students' personalized knowledge graph and use the knowledge graph to optimize learning content and paths;

[0011] Conduct a learning impact weight analysis on each personalized learning content, calculate its impact weight on students’ learning outcomes, and optimize students’ learning paths and the order of teaching content based on the weight analysis results;

[0012] Based on the learning data of previous and current courses, intelligent teaching analysis is carried out to identify the difficulties and high error rate parts in learning, and then the analysis results are fed back to teachers to help them adjust subsequent teaching content and strategies.

[0013] Optionally, when constructing the initial digital twin learning model, first, integrate the acquired data and clean and preprocess the data, and convert the preprocessed data into key indicators that can reflect students' learning behavior. Then, screen and evaluate the key indicators. Next, integrate the screened and evaluated data into a data set and divide the data set into a training set and a test set. Then, select a decision tree to establish a digital twin learning model. After the digital twin model is established, train the model with the training set and adjust the parameters and structure of the digital twin learning model. After the model training is completed, use the test set to verify the digital twin learning model. Finally, deploy the verified and optimized model to the interactive teaching platform.

[0014] Optionally, the steps of analyzing students’ learning characteristics and current status based on the digital twin learning model and generating multiple personalized learning contents according to the analysis results and adjusting teaching resources and contents according to the needs of different students are as follows:

[0015] Use the digital twin learning model to analyze students’ learning data to identify their learning characteristics and current learning status, determine their understanding of the current teaching content, and then determine each student’s personalized learning needs based on the analysis results of the students’ learning characteristics and current status;

[0016] Based on the determined personalized learning needs, multiple personalized learning contents are generated, and after the personalized learning contents are generated, the corresponding teaching resources and contents are adjusted. Finally, the personalized learning contents and adjusted teaching resources are pushed to students for learning, and the students' progress and performance are continuously monitored during the learning process. The personalized content is dynamically adjusted and optimized based on real-time feedback.

[0017] Optionally, the steps of real-time monitoring of students' learning status data during the teaching process and updating the digital twin learning model based on the real-time data are:

[0018] During the teaching process, the interactive teaching platform collects students’ learning status data in real time and updates the original features based on the new data. The updated feature data is then used to adjust the parameters of the digital twin learning model. Finally, the dynamically updated digital twin learning model generates new personalized learning suggestions and feedback based on the students’ latest learning status and monitors students’ responses to these adjustments.

[0019] Optionally, based on the updated digital twin learning model, the steps of building a personalized knowledge graph for students and using the knowledge graph to optimize learning content and paths are:

[0020] Extract key knowledge points and learning relationships related to the student’s learning process from the updated digital twin learning model, and calculate the initial importance score K of each knowledge point i , and then construct the student's preliminary knowledge graph based on the extracted knowledge points and learning relationships. After constructing the preliminary knowledge graph, according to the updated digital twin learning model, use the formula Personalize the knowledge graph and use the personalized knowledge graph to optimize students' learning content and paths. During the learning process, continuously monitor students' progress and performance and further dynamically adjust the knowledge graph and learning path based on real-time feedback. i ′ is the importance score of knowledge point i after personalized adjustment. K i is the initial importance score of knowledge point i in the updated digital twin learning model. λ1 is the basic weight, which controls the influence of the initial importance score in the adjustment process. R i is the set of knowledge points that have a direct learning relationship with knowledge point i. ij K is the learning relationship weight of knowledge point j to knowledge point i, reflecting the influence of j on i. j is the importance score of knowledge point j. μ is the learning progress feedback coefficient, which controls the impact of learning progress feedback on the adjustment of knowledge point importance. i Q is the learning progress feedback of students for knowledge point i during the learning process, and η is the error rate adjustment coefficient, which reflects the impact of students’ error feedback on the adjustment of knowledge point importance. i is the error rate of students on knowledge point i during the learning process.

[0021] Optionally, when personalizing the knowledge graph, first, highlight the knowledge points that students have mastered well based on the student characteristics analyzed by the digital twin learning model, mark the weak links that students need to strengthen, and rearrange the order of learning content based on the sequence of knowledge points in the knowledge graph and the students' mastery level.

[0022] Collect data related to the students' learning process, and then extract features that can reflect the students' learning effects from the data. Based on the extracted features, use the formula Calculate the impact weight of each personalized learning content on the student’s learning effect. Finally, calculate the impact weight W of each learning content. i Then sort all the learning contents, with the contents with high priority at the front, among which W i is the influence weight of learning content i, T i is the time students spend studying content i, T avg is the average learning time of students on all learning contents, C i C is the number of clicks that students make on learning content i total is the total number of clicks by students on all learning contents, S i is the correct rate of students answering questions on learning content i, E i is the student’s error rate on learning content i, S max is the highest correct answer rate of students in all learning contents. α, β, γ are weight coefficients, which are used to adjust the influence of each feature on the total weight, and α+β+γ=1.

[0023] Optionally, collect students' learning data in previous courses and current courses, then extract features from the acquired learning data to generate key indicators for teaching analysis, and then perform intelligent analysis on the extracted feature data to identify the difficulty coefficient D in learning. i and error rate E i , where the difficulty coefficient E i and error rate E i Calculated by formula (1) and formula (2) respectively, after completing the analysis, the analysis results are organized into a detailed teaching feedback report, and finally the generated feedback report is sent to the teacher, who adjusts the subsequent teaching content and strategy according to these analysis results;

[0024]

[0025] Where D i is the difficulty coefficient of knowledge point i, T i is the average learning time of students on knowledge point i, T avg is the average learning time of all knowledge points, N i is the total number of exercises for knowledge point i, N total is the total number of exercises for all knowledge points, δ,∈ is the weight coefficient, which is used to adjust the influence of learning time and number of exercises on the difficulty coefficient, and δ+∈=1, E i is the error rate of knowledge point i, W i is the student's practice weight on knowledge point i, Si is the correct answer rate of students on knowledge point i.

[0026] A management teaching information processing system based on digital twins, characterized by comprising:

[0027] A data acquisition module, which is used to obtain students' multimodal data through an interactive teaching platform and digitize the obtained multimodal data;

[0028] A digital twin learning model construction module, which is used to construct an initial digital twin learning model using the data acquisition module;

[0029] Personalized learning content generation module: The personalized learning content generation module analyzes students’ learning characteristics and current status based on the digital twin learning model, generates personalized learning content for students, and adjusts teaching resources and content according to needs;

[0030] Real-time monitoring and model updating module: The real-time monitoring and model updating module is responsible for real-time monitoring of students’ learning status during the teaching process, and dynamically updating the digital twin learning model based on real-time data;

[0031] Personalized knowledge graph construction and optimization module: The personalized knowledge graph construction and optimization module builds students' personalized knowledge graphs based on the updated digital twin learning model, and uses the knowledge graph to optimize learning content and paths;

[0032] The learning impact weight analysis and path optimization module is used to analyze the learning impact weight of each personalized learning content, calculate its impact weight on students' learning effects, and optimize the learning path and teaching content sequence;

[0033] Intelligent teaching analysis and feedback module,The intelligent teaching analysis and feedback module is used to conduct intelligent teaching analysis based on the learning data of previous and current courses, identify the difficult points and high error rate parts in learning, and feed back the analysis results to the teacher.

[0034] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all the advantages described below at the same time:

[0035] The present invention can construct a personalized knowledge graph based on the digital twin learning model, and accurately identify the knowledge blind spots and weak links of students in the learning process by analyzing the chronological relationship and learning dependency between knowledge points. Using this information, the presentation order of the learning path and content can be further optimized to ensure that students can master each knowledge point in the most suitable learning order. At the same time, each personalized learning content is subjected to a learning impact weight analysis, and its actual impact on the students' learning effect is calculated. According to these analysis results, the content that is most critical to improving the students' learning effect is given priority for learning. Through such optimization and adjustment, not only can the students' learning efficiency be improved, but also the overall learning effect can be effectively improved, helping students to solve learning difficulties more targetedly.

[0036] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described below are only some embodiments. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] In the figure:

[0039] Figure 1 This is a flow chart of the teaching information processing method.

[0040] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but are intended to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0041] The present invention will now be described in further detail with reference to the accompanying drawings.

[0042] See also Figure 1 As shown, in this embodiment, a management teaching information processing method based on digital twin is provided, comprising the following steps:

[0043] Obtain students' multimodal data through the interactive teaching platform and digitize the acquired multimodal data to build an initial digital twin learning model;

[0044] Use the digital twin learning model to analyze students’ learning characteristics and current status and generate multiple personalized learning contents based on the analysis results, adjusting teaching resources and content according to the needs of different students;

[0045] Monitor students’ learning status data in real time during the teaching process and update the digital twin learning model based on real-time data;

[0046] Based on the updated digital twin learning model, build students' personalized knowledge graph and use the knowledge graph to optimize learning content and paths;

[0047] Conduct a learning impact weight analysis on each personalized learning content, calculate its impact weight on students’ learning outcomes, and optimize students’ learning paths and the order of teaching content based on the weight analysis results;

[0048] Based on the learning data of previous and current courses, intelligent teaching analysis is carried out to identify the difficulties and high error rate parts in learning, and then the analysis results are fed back to teachers to help them adjust subsequent teaching content and strategies.

[0049] The present invention can construct a personalized knowledge graph based on the digital twin learning model, and accurately identify the knowledge blind spots and weak links of students in the learning process by analyzing the chronological relationship and learning dependency between knowledge points. Using this information, the presentation order of the learning path and content can be further optimized to ensure that students can master each knowledge point in the most suitable learning order. At the same time, each personalized learning content is subjected to a learning impact weight analysis, and its actual impact on the students' learning effect is calculated. According to these analysis results, the content that is most critical to improving the students' learning effect is given priority for learning. Through such optimization and adjustment, not only can the students' learning efficiency be improved, but also the overall learning effect can be effectively improved, helping students to solve learning difficulties more targetedly.

[0050] In this embodiment, when constructing the initial digital twin learning model, first, the acquired data is integrated, cleaned and preprocessed, and the preprocessed data is converted into key indicators that can reflect students' learning behavior. Then, the key indicators are screened and evaluated. Next, the screened and evaluated data are integrated into a data set and the data set is divided into a training set and a test set. Then, a decision tree is selected to establish a digital twin learning model. After the digital twin model is established, the model is trained with the training set and the parameters and structure of the digital twin learning model are adjusted. After the model training is completed, the digital twin learning model is verified using the test set. Finally, the verified and optimized model is deployed to the interactive teaching platform.

[0051] In this embodiment, the steps of analyzing the learning characteristics and current status of students based on the digital twin learning model and generating multiple personalized learning contents according to the analysis results, and adjusting teaching resources and contents according to the needs of different students are as follows:

[0052] The digital twin learning model is used to analyze students' learning data to identify their learning characteristics and current learning status, determine their understanding of the current teaching content, and then determine each student's personalized learning needs based on the analysis results of the students' learning characteristics and current status. For example, for students who learn slowly, more basic content and repeated exercises need to be provided; for students who have a good grasp of certain knowledge points but have gaps in certain specific knowledge points, intensive exercises and supplementary materials for these knowledge points need to be provided. By accurately positioning each student's learning needs, a clear direction can be provided for subsequent content generation.

[0053] Based on the determined personalized learning needs, multiple personalized learning contents are generated, and after the personalized learning contents are generated, the corresponding teaching resources and contents are adjusted. Finally, the personalized learning contents and adjusted teaching resources are pushed to students for learning, and the students' progress and performance are continuously monitored during the learning process. The personalized content is dynamically adjusted and optimized based on real-time feedback. For example, the difficulty of the questions is adjusted according to the students' answering performance, and the content display order is adjusted according to the students' learning habits to ensure that each student can learn in the best way. This process is a cycle, and through continuous feedback and adjustment, the personalized learning experience of students can be continuously optimized.

[0054] In this embodiment, the steps of real-time monitoring of students' learning status data during the teaching process and updating the digital twin learning model based on the real-time data are as follows:

[0055] During the teaching process, the interactive teaching platform collects students' learning status data in real time and updates the original features based on the new data. Then, the updated feature data is used to adjust the parameters of the digital twin learning model. Finally, the dynamically updated digital twin learning model will generate new personalized learning suggestions and feedback based on the students' latest learning status and monitor the students' response to these adjustments. Feature update refers to recalculating or adjusting existing feature values ​​based on new learning data, such as updating students' correct answer rate or page dwell time. Feature extraction refers to extracting new features from real-time data, such as identifying students' attention change patterns or emotional reactions. These newly extracted features can provide richer input information for the digital twin learning model and enhance the analytical capabilities of the digital twin learning model. Through continuous feedback and adjustment, the optimal state of students' learning paths can be maintained to ensure the effectiveness and flexibility of personalized teaching.

[0056] In this embodiment, the steps of constructing a personalized knowledge graph for students and optimizing learning content and paths using the knowledge graph are as follows:

[0057] Extract key knowledge points and learning relationships related to the student’s learning process from the updated digital twin learning model, and calculate the initial importance score K of each knowledge point i , and then construct the student's preliminary knowledge graph based on the extracted knowledge points and learning relationships. After constructing the preliminary knowledge graph, according to the updated digital twin learning model, use the formula Personalize the knowledge graph and use the personalized knowledge graph to optimize students' learning content and paths. During the learning process, continuously monitor students' progress and performance and further dynamically adjust the knowledge graph and learning path based on real-time feedback. i ′ is the importance score of knowledge point i after personalized adjustment. K i is the initial importance score of knowledge point i in the updated digital twin learning model. λ1 is the basic weight, which controls the influence of the initial importance score in the adjustment process. R i is the set of knowledge points that have a direct learning relationship with knowledge point i. ij K is the learning relationship weight of knowledge point j to knowledge point i, reflecting the influence of j on i. j is the importance score of knowledge point j. μ is the learning progress feedback coefficient, which controls the impact of learning progress feedback on the adjustment of knowledge point importance. i Q is the learning progress feedback of students for knowledge point i during the learning process, and η is the error rate adjustment coefficient, which reflects the impact of students’ error feedback on the adjustment of knowledge point importance. i The error rate of students for knowledge point i during the learning process. Knowledge points include various concepts, skills and information units that students come into contact with during the learning process. Learning relationships refer to the correlation between knowledge points, such as prerequisite relationships (some knowledge points are the prerequisite for understanding other knowledge points), similarities (similar or complementary knowledge points) and application relationships (some knowledge points need to be combined for application). Extracting this information can lay the foundation for building a personalized knowledge graph. According to the student characteristics analyzed by the digital twin learning model (such as learning speed, knowledge mastery, and learning style), the knowledge points that students have mastered well are highlighted, and the weak links that students need to strengthen are marked. For example, if the digital twin learning model shows that the student has a weak grasp of a certain knowledge point, the knowledge point will be highlighted on the knowledge graph, and its connection with other related knowledge points and learning paths will be marked. Through these personalized adjustments, the knowledge graph can more accurately reflect the learning status and needs of students.

[0058] Specifically, The initial importance score of knowledge point i and the influence of other knowledge points j that have a direct learning relationship with it are combined to ensure that the weight of each knowledge point is not only based on its own importance, but also takes into account the role of neighboring knowledge points. Subsequently, the adjustment factor (1+μ·Fi ) Based on the student's learning progress feedback on knowledge point i i , dynamically adjust the importance of knowledge points so that the knowledge graph can better reflect the actual learning status of students. Finally, the adjustment factor (1+η·E i ) Based on the student's error rate E on knowledge point i i , further adjust the importance of knowledge points and ensure that more attention is paid to difficult knowledge.

[0059] The order of learning content is rearranged according to the order of knowledge points in the knowledge graph and the students' mastery level to ensure that students have fully mastered the basic knowledge before learning new knowledge. For example, if a student has weak basic knowledge in a certain field, relevant basic courses are given priority to strengthen the student's understanding of basic knowledge. On the contrary, if the student has mastered a certain knowledge point, the learning progress is accelerated and more advanced content is introduced. In this way, the learning content and path are dynamically optimized to meet the personalized learning needs of students.

[0060] A knowledge graph is a graphical structure in which nodes represent knowledge points and edges represent the relationships between knowledge points. For example, a graph can be constructed that contains all the knowledge points that students have learned and their relationships, such as which knowledge points are core foundations, which are extended knowledge, and which are application cases. This preliminary knowledge graph can intuitively display the students' knowledge structure and learning path.

[0061] In this embodiment, when the knowledge graph is personalized, first, the knowledge points that students have mastered well are highlighted based on the student characteristics analyzed by the digital twin learning model, and the weak links that students need to strengthen are marked, and the order of learning content is rearranged according to the prerequisite relationship of the knowledge points in the knowledge graph and the students' mastery level.

[0062] Collect data related to the students' learning process, and then extract features that can reflect the students' learning effects from the data. Based on the extracted features, use the formula Calculate the impact weight of each personalized learning content on the student’s learning effect. Finally, calculate the impact weight W of each learning content. i Then sort all the learning contents, with the contents with high priority at the front, among which W i is the influence weight of learning content i, T i is the time students spend studying content i, T avg is the average learning time of students on all learning contents, C i C is the number of clicks that students make on learning content i total is the total number of clicks by students on all learning contents, S i is the correct rate of students answering questions on learning content i, Ei is the student’s error rate on learning content i, S max is the highest correct answer rate of students in all learning contents. α, β, γ are weight coefficients, which are used to adjust the influence of each feature on the total weight, and α+β+γ=1.

[0063] In this embodiment, the learning data of students in the previous course and the current course are collected, and then the features of the acquired learning data are extracted to generate key indicators for teaching analysis. Then, the extracted feature data are intelligently analyzed to identify the difficulty coefficient D in learning. i and error rate E i , where the difficulty coefficient E i and error rate E i Calculated by formula (1) and formula (2) respectively, after completing the analysis, the analysis results are organized into a detailed teaching feedback report, and finally the generated feedback report is sent to the teacher, who adjusts the subsequent teaching content and strategy according to these analysis results;

[0064]

[0065] Where D i is the difficulty coefficient of knowledge point i, T i is the average learning time of students on knowledge point i, T avg is the average learning time of all knowledge points, N i is the total number of exercises for knowledge point i, N total is the total number of exercises for all knowledge points, δ,∈ is the weight coefficient, which is used to adjust the influence of learning time and number of exercises on the difficulty coefficient, and δ+∈=1, E i is the error rate of knowledge point i, W i is the student's practice weight on knowledge point i, S i is the correct answer rate of students on knowledge point i.

[0066] By calculating the difficulty coefficient D i and error rate E i , which can identify the difficult points and parts with high error rates in learning. These data reflect which knowledge points students need more attention and additional teaching support on. The teaching feedback report includes the difficulty coefficient, error rate, and possible learning bottlenecks and misunderstandings for each knowledge point. Teachers can rearrange the course progress based on the suggestions in the report, increase the explanation and practice of knowledge points with high error rates, or adjust the teaching methods to better meet the learning needs of students. For example, if a certain knowledge point has a high difficulty coefficient and error rate, the teacher can choose to increase the discussion and interaction of the knowledge point in class, or provide more practice opportunities to strengthen students' understanding.

[0067] It should be noted that multimodal data includes voice interaction data, answer feedback data, video viewing data, etc. Learning status data includes page dwell time, answer accuracy rate, etc. The key indicators are to extract intonation and emotional features from voice data, facial expressions and viewing time from video data, click frequency and page dwell time from interaction logs, etc. Learning data includes students' learning speed, answer accuracy, error types, learning behavior patterns (such as page dwell time, video viewing times), etc. Learning characteristics include learning speed, mastery of different knowledge points, preferred learning methods, etc. Personalized learning content can include customized video explanations, targeted exercises, interactive simulation exercises, supplementary reading materials, etc. Personalized learning content is tailored to students' learning characteristics and current status, aiming to improve students' learning efficiency and effectiveness, and provide each student with unique learning paths and resources based on different learning needs.

[0068] A management teaching information processing system based on digital twins, comprising:

[0069] A data acquisition module, which is used to obtain students' multimodal data through an interactive teaching platform and to digitally process the obtained multimodal data;

[0070] A digital twin learning model construction module, which is used to construct an initial digital twin learning model using the data acquisition module;

[0071] Personalized learning content generation module: The personalized learning content generation module analyzes students’ learning characteristics and current status based on the digital twin learning model, generates personalized learning content for students, and adjusts teaching resources and content according to needs;

[0072] Real-time monitoring and model updating module: The real-time monitoring and model updating module is responsible for real-time monitoring of students’ learning status during the teaching process, and dynamically updating the digital twin learning model based on real-time data;

[0073] Personalized knowledge graph construction and optimization module: The personalized knowledge graph construction and optimization module builds students' personalized knowledge graphs based on the updated digital twin learning model, and uses the knowledge graph to optimize learning content and paths;

[0074] The learning impact weight analysis and path optimization module is used to analyze the learning impact weight of each personalized learning content, calculate its impact weight on students' learning effects, and optimize the learning path and teaching content sequence;

[0075] Intelligent teaching analysis and feedback module,The intelligent teaching analysis and feedback module is used to conduct intelligent teaching analysis based on the learning data of previous and current courses, identify the difficult points and high error rate parts in learning, and feed back the analysis results to the teacher.

[0076] The present invention is not limited to the above-mentioned embodiments. Anyone should be aware that any structural changes made under the enlightenment of the present invention, and any technical solutions that are the same or similar to the present invention, fall within the protection scope of the present invention. The technology, shape, and structural parts not described in detail in the present invention are all well-known technologies.

Claims

1. A management teaching information processing method based on digital twins, characterized in that: The following steps are involved: Obtain students' multimodal data through the interactive teaching platform and digitize the acquired multimodal data to build an initial digital twin learning model; Use the digital twin learning model to analyze students’ learning characteristics and current status and generate multiple personalized learning contents based on the analysis results, adjusting teaching resources and content according to the needs of different students; Monitor students’ learning status data in real time during the teaching process and update the digital twin learning model based on real-time data; Based on the updated digital twin learning model, build students' personalized knowledge graph and use the knowledge graph to optimize learning content and paths; Conduct a learning impact weight analysis on each personalized learning content, calculate its impact weight on students’ learning outcomes, and optimize students’ learning paths and the order of teaching content based on the weight analysis results; Based on the learning data of previous and current courses, intelligent teaching analysis is carried out to identify the difficulties and high error rate parts in learning, and then the analysis results are fed back to teachers to help them adjust subsequent teaching content and strategies.

2. According to a digital twin-based management teaching information processing method according to claim 1, it is characterized in that: When constructing the initial digital twin learning model, first, integrate the acquired data and clean and preprocess the data, and convert the preprocessed data into key indicators that can reflect students' learning behavior. Then, screen and evaluate the key indicators. Next, integrate the screened and evaluated data into a data set and divide the data set into a training set and a test set. Then, select a decision tree to establish a digital twin learning model. After the digital twin model is established, train the model with the training set, and adjust the parameters and structure of the digital twin learning model. After the model training is completed, use the test set to verify the digital twin learning model. Finally, deploy the verified and optimized model to the interactive teaching platform.

3. According to a management teaching information processing method based on digital twins according to claim 1, it is characterized in that: Based on the digital twin learning model, the learning characteristics and current status of students are analyzed and multiple personalized learning contents are generated according to the analysis results. The steps to adjust teaching resources and content according to the needs of different students are as follows: Use the digital twin learning model to analyze students’ learning data to identify their learning characteristics and current learning status, determine their understanding of the current teaching content, and then determine each student’s personalized learning needs based on the analysis results of the students’ learning characteristics and current status; Based on the determined personalized learning needs, multiple personalized learning contents are generated, and after the personalized learning contents are generated, the corresponding teaching resources and contents are adjusted. Finally, the personalized learning contents and adjusted teaching resources are pushed to students for learning. During the learning process, the students' progress and performance are continuously monitored, and the personalized content is dynamically adjusted and optimized based on real-time feedback.

4. According to a digital twin-based management teaching information processing method according to claim 1, it is characterized in that: The steps to monitor students’ learning status data in real time during the teaching process and update the digital twin learning model based on real-time data are as follows: During the teaching process, the interactive teaching platform collects students’ learning status data in real time and updates the original features based on the new data. The updated feature data is then used to adjust the parameters of the digital twin learning model. Finally, the dynamically updated digital twin learning model generates new personalized learning suggestions and feedback based on the students’ latest learning status and monitors students’ responses to these adjustments.

5. The management teaching information processing method based on digital twin according to claim 1 is characterized in that: According to the updated digital twin learning model, the steps to build students' personalized knowledge graphs and use the knowledge graphs to optimize learning content and paths are as follows: Extract key knowledge points and learning relationships related to the student’s learning process from the updated digital twin learning model, and calculate the initial importance score K of each knowledge point i , and then construct the student's preliminary knowledge graph based on the extracted knowledge points and learning relationships. After constructing the preliminary knowledge graph, according to the updated digital twin learning model, use the formula Personalize the knowledge graph and use the personalized knowledge graph to optimize students' learning content and paths. During the learning process, continuously monitor students' progress and performance and further dynamically adjust the knowledge graph and learning path based on real-time feedback. i ′ is the importance score of knowledge point i after personalized adjustment, K i is the initial importance score of knowledge point i in the updated digital twin learning model, λ1 is the basic weight, which controls the influence of the initial importance score in the adjustment process, and R i is the set of knowledge points that have a direct learning relationship with knowledge point i, W ij is the learning relationship weight of knowledge point j to knowledge point i, reflecting the influence of j on i. K j is the knowledge point j The importance score of , μ is the learning progress feedback coefficient, which controls the impact of learning progress feedback on the adjustment of knowledge point importance, F i is the student’s learning progress feedback on knowledge point i during the learning process, η is the error rate adjustment coefficient, which reflects the impact of student error feedback on the adjustment of knowledge point importance, Q i is the error rate of students on knowledge point i during the learning process.

6. A management teaching information processing method based on digital twins according to claim 5, characterized in that: When personalizing the knowledge graph, first, based on the student characteristics analyzed by the digital twin learning model, the knowledge points that are easy for students to master are highlighted, the links where students need to master are marked, and the order of learning content is rearranged according to the sequence of knowledge points in the knowledge graph and the students' mastery level.

7. The management teaching information processing method based on digital twin according to claim 1 is characterized in that: Collect data related to the students' learning process, and then extract features that can reflect the students' learning effects from the data. Based on the extracted features, use the formula Calculate the impact weight of each personalized learning content on the student’s learning effect. Finally, calculate the impact weight W of each learning content. i Then sort all the learning contents, with the contents with high priority at the front, among which W i For learning content i The influence weight of T i For students in learning content i The learning time on avg is the average learning time of students on all learning contents, C i C is the number of clicks that students make on learning content i total is the total number of clicks by students on all learning contents, S i is the correct rate of students answering questions on learning content i, E i is the student’s error rate on learning content i, S max is the highest correct answer rate of students in all learning contents. α, β, γ are weight coefficients, which are used to adjust the influence of each feature on the total weight, and α+β+γ=1.

8. The management teaching information processing method based on digital twin according to claim 1 is characterized in that: Collect students' learning data in previous courses and current courses, then extract features from the acquired learning data to generate key indicators for teaching analysis. Then, perform intelligent analysis on the extracted feature data to identify the difficulty coefficient D in learning. i and error rate E i , where the difficulty coefficient E i and error rate E i Calculated by formula (1) and formula (2) respectively, after completing the analysis, the analysis results are organized into a detailed teaching feedback report, and finally the generated feedback report is sent to the teacher, who adjusts the subsequent teaching content and strategy according to these analysis results; Where D i is the difficulty coefficient of knowledge point i, T i is the average learning time of students on knowledge point i, T avg is the average learning time of all knowledge points, N i is the total number of exercises for knowledge point i, N total is the total number of exercises for all knowledge points, δ,∈ is the weight coefficient, which is used to adjust the influence of learning time and number of exercises on the difficulty coefficient, and δ+∈=1, E i is the error rate of knowledge point i, W i is the student's practice weight on knowledge point i, S i is the correct answer rate of students on knowledge point i.

9. A management teaching information processing system based on digital twins, characterized in that: include: A data acquisition module, which is used to obtain students' multimodal data through an interactive teaching platform and to digitally process the obtained multimodal data; A digital twin learning model construction module, which is used to construct an initial digital twin learning model using the data acquisition module; Personalized learning content generation module: The personalized learning content generation module analyzes students’ learning characteristics and current status based on the digital twin learning model, generates personalized learning content for students, and adjusts teaching resources and content according to needs; Real-time monitoring and model updating module: The real-time monitoring and model updating module is responsible for real-time monitoring of students’ learning status during the teaching process, and dynamically updating the digital twin learning model based on real-time data; Personalized knowledge graph construction and optimization module: The personalized knowledge graph construction and optimization module builds students' personalized knowledge graphs based on the updated digital twin learning model, and uses the knowledge graph to optimize learning content and paths; The learning impact weight analysis and path optimization module is used to analyze the learning impact weight of each personalized learning content, calculate its impact weight on students' learning effects, and optimize the learning path and teaching content sequence; Intelligent teaching analysis and feedback module,The intelligent teaching analysis and feedback module is used to conduct intelligent teaching analysis based on the learning data of previous and current courses, identify the difficult points and high error rate parts in learning, and feed back the analysis results to the teacher.

Images