A Virtual Teaching Data Interaction Method and System Based on Digital Twin

Abstract

The present invention discloses a digital twin-based virtual teaching data interaction method and system. The method includes obtaining audio and video data; determining a fluctuation range based on the data to obtain a change type; clustering the data according to the change type to obtain a clustering data set and isolated digital information; constructing a digital twin virtual teaching model; simulating the isolated digital information to obtain an output change amount and performing parameter settings; determining the data abnormality degree and combining the prediction accuracy rate of the digital twin virtual teaching model to formulate a virtual teaching data interaction decision. This method can improve the accuracy of virtual teaching data interaction decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a virtual teaching data interaction method and system based on digital twin. Background Art

[0002] Currently, in the implementation of virtual teaching systems, to ensure the stable operation of the system, a large amount of teaching data needs to be collected, processed, and transmitted. These data interaction processes cover various software and hardware devices and communication protocols, constituting a key link for the stable operation of virtual teaching systems. However, with the rapid increase in the amount of educational data, the quality of data collection is affected by multiple factors such as the performance of collection devices and communication environments, resulting in a decline in data quality, which in turn affects the overall stability of the system.

[0003] In the prior art, although encryption algorithms are used to ensure data security, this often comes at the cost of sacrificing data transmission and processing speed. In addition, when dealing with virtual teaching data, the prior art fails to fully consider the impact of data change types and data abnormality degrees on the system, which limits the accuracy of virtual teaching data interaction decisions.

[0004] In summary, the prior art has deficiencies in data interaction methods, fails to fully consider the impact of data change types and abnormality degrees on the system, resulting in inaccurate data analysis and lack of accuracy in decision-making. Summary of the Invention

[0005] The present invention provides a virtual teaching data interaction method based on digital twin to improve the accuracy of virtual teaching data interaction decisions.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a virtual teaching data interaction method based on digital twin, including:

[0007] Obtain audio data and video data in teaching data;

[0008] Determine the fluctuation range according to the audio data and the video data;

[0009] Judge according to the fluctuation range and a preset standard fluctuation range, and determine the change type according to the judgment result;

[0010] Input digital information into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolated digital information;

[0011] Construct an initial digital twin virtual teaching model according to the clustering data set, and train the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model;

[0012] Virtual teaching simulation is performed on the isolated digital information to obtain an output change amount, and parameter settings are performed on the isolated digital information according to the output change amount;

[0013] Determine the data abnormality degree according to the isolated digital information after the parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model.

[0014] In an optional implementation manner, determining a fluctuation range according to the audio data and the video data includes:

[0015] Preprocess the audio data and video data;

[0016] Convert the preprocessed audio data into a waveform signal, and obtain the maximum value and the minimum value of the waveform signal;

[0017] Subtract the minimum value from the maximum value of the waveform signal to obtain the audio data fluctuation range;

[0018] Extract the fluctuation characteristics of the preprocessed video data;

[0019] Analyze the fluctuation characteristics to obtain the video data fluctuation range;

[0020] The fluctuation range includes the audio data fluctuation range and the video data fluctuation range.

[0021] In an optional implementation manner, judging according to the fluctuation range and a preset standard fluctuation range, and determining a change type according to the judgment result, including:

[0022] Judge whether the fluctuation range of the audio data exceeds the preset audio standard fluctuation range;

[0023] If it exceeds the preset audio standard fluctuation range, it is determined that the change type of the audio data is a sharp increase;

[0024] If it does not exceed the preset audio standard fluctuation range, it is determined that the change type of the audio data is stable;

[0025] Judge whether the fluctuation range of the video data exceeds the preset video standard fluctuation range;

[0026] If it exceeds the preset video standard fluctuation range, it is determined that the change type of the video data is a mutation;

[0027] If it does not exceed the preset video standard fluctuation range, it is determined that the change type of the video data is non-mutation.

[0028] In an alternative embodiment, inputting the audio data and video data into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolation digital information, including:

[0029] Selecting the corresponding digital information as the input data of the isolation forest model according to the change type;

[0030] The isolation forest model performs clustering processing on the input data by a method of constructing multiple isolation trees for recognition;

[0031] According to the clustering processing result, dividing the input data into the clustering data set and the isolation digital information.

[0032] In an alternative embodiment, inputting digital information into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolation digital information, wherein the training process of the isolation forest model includes:

[0033] Extracting waveform features from the digital information as the input data of the model;

[0034] Recursively selecting optimal features and split points for the input data, continuously splitting the input data into two subsets, and when each subset contains only one data sample, the initial construction of the isolation forest model is completed;

[0035] Randomly selecting one of the waveform features, sorting the data samples according to the value of the waveform feature from small to large to form training set data;

[0036] Calculating the average value of the training set data, randomly selecting two of the data samples as reference samples, and dividing the training set data into three categories: a sample set between the two reference samples, a sample set smaller than the smaller reference sample, and a sample set larger than the larger reference sample;

[0037] Training the isolation forest model, and judging whether the average path lengths of the three categories of sample sets in the isolation tree are all less than a preset threshold. If so, the training of the isolation forest model is completed; if not, the isolation forest model continues to be trained.

[0038] In an alternative embodiment, constructing an initial digital twin virtual teaching model according to the clustering data set and training the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model, including:

[0039] Extracting teaching-related feature information from the clustering data set;

[0040] Constructing an initial digital twin virtual teaching model according to the feature information;

[0041] Classify the digital information according to the change type and iteratively adjust the digital twin virtual teaching model according to the classification result;

[0042] Obtain the error between the output result of the digital twin virtual teaching model and the preset teaching result;

[0043] Train the digital twin virtual teaching model through error feedback according to the error;

[0044] When the preset error standard is reached, determine that the training is completed and obtain the digital twin virtual teaching model.

[0045] In an alternative embodiment, perform virtual teaching simulation on the isolated digital information to obtain an output change amount, and set parameters for the isolated digital information according to the output change amount, including:

[0046] Input the isolated digital information into the digital twin virtual teaching model to simulate a virtual teaching scenario;

[0047] Obtain the actual output amount of the digital twin virtual teaching model and calculate the difference from the preset output amount to obtain the output change amount;

[0048] Set relevant parameters in the isolated digital information according to the output change amount.

[0049] In an alternative embodiment, determine the data abnormality degree according to the isolated digital information after parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy of the digital twin virtual teaching model, including:

[0050] Calculate the data abnormality degree of the isolated digital information after parameter adjustment;

[0051] Obtain the prediction accuracy of the digital twin virtual teaching model;

[0052] Formulate a virtual teaching data interaction decision in combination with the data abnormality degree and the prediction accuracy.

[0053] In a second aspect, the present invention provides a virtual teaching data interaction system based on digital twins, including:

[0054] A data acquisition module for acquiring audio data and video data in teaching data;

[0055] A fluctuation range determination module for determining a fluctuation range according to the audio data and the video data;

[0056] A change type judgment module for judging according to the fluctuation range and a preset standard fluctuation range to determine the change type;

[0057] A clustering module, configured to cluster the audio data and video data according to the change type to obtain a clustering data set and isolated digital information;

[0058] A model construction and training module, configured to construct an initial digital twin virtual teaching model according to feature information, classify the digital information according to the change type, iteratively adjust the digital twin virtual teaching model according to the classification result, obtain the error between the output result of the digital twin virtual teaching model and a preset teaching result, train the digital twin virtual teaching model through error feedback according to the error, and determine that the training is completed when a preset error standard is reached, thereby obtaining the digital twin virtual teaching model;

[0059] A simulation and parameter setting module, configured to perform virtual teaching simulation on the isolated digital information to obtain an output change amount, and perform parameter setting on the isolated digital information according to the output change amount;

[0060] A decision-making module, configured to determine the data abnormality degree according to the isolated digital information after parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model.

[0061] In a third aspect, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, it controls a device where the computer-readable storage medium is located to execute any one of the above-mentioned methods for virtual teaching data interaction based on digital twins.

[0062] Compared with the prior art, the present invention has the following beneficial effects: By means of a method for virtual teaching data interaction based on digital twins, the present invention improves the accuracy of virtual teaching data interaction decisions, and enhances the stability and security of the system. First, a data acquisition module is used to obtain audio data and video data in real time, and then a feature extraction module extracts features from these data and performs analysis to determine the fluctuation range, and identifies the change type of the data by comparing it with a preset standard fluctuation range. The data is clustered and analyzed by means of an isolation forest model to accurately distinguish a clustering data set and isolated digital information. The model construction and training module trains a digital twin virtual teaching model to simulate a real teaching environment, performs virtual teaching simulation on the isolated digital information, obtains an output change amount, and performs parameter optimization setting on the isolated digital information according to the output change amount. The decision-making module comprehensively considers the data abnormality degree of the isolated digital information after parameter setting and the prediction accuracy rate of the digital twin virtual teaching model, and formulates a reasonable virtual teaching data interaction decision.

[0063] In summary, the present invention provides a virtual teaching data interaction method based on digital twins, which realizes precise management of virtual teaching operations, saves educational resources, improves teaching efficiency, and can significantly reduce decision-making errors caused by inaccurate data interaction and operating costs during long-term operation. At the same time, it improves the efficiency and effectiveness of teaching resource management, and has important social value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 FIG. 6 is a schematic flowchart of a virtual teaching data interaction method based on digital twins provided by the first embodiment of the present invention;

[0065] Figure 2 FIG. 10 is a schematic structural diagram of a virtual teaching data interaction system based on digital twins provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] Referring to Figure 1 , the first embodiment of the present invention provides a virtual teaching data interaction method based on digital twins, including the following steps:

[0068] S11, obtaining audio data and video data in teaching data;

[0069] S12, determining a fluctuation range according to the audio data and the video data;

[0070] S13, judging according to the fluctuation range and a preset standard fluctuation range, and determining a change type according to the judgment result;

[0071] S14, inputting digital information into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolated digital information;

[0072] S15, constructing an initial digital twin virtual teaching model according to the clustering data set, and training the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model;

[0073] S16, performing virtual teaching simulation on the isolated digital information to obtain an output change amount, and setting parameters for the isolated digital information according to the output change amount;

[0074] S17. Determine the data abnormality degree based on the isolated digital information after the parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model.

[0075] It should be noted that S11 to S17 constitute a complete process for formulating a virtual teaching data interaction decision. The audio data and video data in the teaching process are captured in real time by sensors, providing a data basis for subsequent feature extraction and analysis. The collected audio data and video data are preprocessed, converting the audio signal and video signal into waveform signals, and obtaining the maximum and minimum values of the waveform from them to calculate the fluctuation range. The fluctuation range is compared with the preset standard fluctuation range, and the type of data change is determined according to the comparison result. This classification helps to identify different dynamics in the teaching process. According to the determined type of change, the digital information is input into a pre-trained isolation forest model, which evaluates the isolation degree of data points by constructing multiple isolation trees, thereby distinguishing the clustering data set and the isolated digital information. The feature information in the clustering data set is used to construct an initial digital twin virtual teaching model, which simulates the real teaching environment and uses the classification result of the type of change for iterative adjustment. In the model training stage, the error between the model output and the expected teaching result is calculated and fed back to optimize the model parameters. When the error drops to the preset error standard, the training is completed, and a digital twin virtual teaching model is obtained to provide simulation and decision support for virtual teaching. The isolated digital information is simulated in virtual teaching, the difference between the actual output and the expected output of the model is calculated, that is, the output change amount, and the isolated digital information is parameter-set according to the output change amount. The data abnormality degree is determined based on the isolated digital information after the parameter setting, and a virtual teaching data interaction decision is formulated in combination with the prediction accuracy rate of the digital twin virtual teaching model.

[0076] It should be noted that the present invention demonstrates an efficient process for formulating virtual teaching data interaction decisions. Through intelligent data analysis and model optimization, the accuracy of interaction decisions in virtual teaching has been significantly improved. This method first extracts key feature information related to teaching activities from the clustering dataset, such as student interaction frequency, teaching content coverage, and learning progress. Then, using this feature information, a preliminary digital twin virtual teaching model is constructed, which aims to simulate the real teaching environment and learning process. Subsequently, according to the change types of teaching data, the digital information is classified, and the digital twin virtual teaching model is iteratively adjusted based on the classification results. This process involves calculating the error between the model output result and the preset teaching result, and training the model through an error feedback mechanism. When the error of the model is reduced to the preset error standard, the training is completed, and an optimized digital twin virtual teaching model is obtained. This model can provide accurate simulation and decision support for virtual teaching, thereby improving teaching quality and learning experience. At the same time, it also helps to reduce the waste of teaching resources, improve the automation level of teaching management, and bring significant economic and social benefits to the education field.

[0077] In step S11, audio data and video data in the teaching data are acquired.

[0078] It should be noted that in the virtual teaching environment, intelligent sensors are deployed on key teaching devices and interaction platforms to collect audio data and video data in real time. The audio data is obtained by real-time monitoring of the microphones installed in the classroom, which reflects the sound dynamics during the teaching process, including teacher explanations, student questions, and classroom discussions, and is a key indicator for evaluating teaching interaction and student participation. The video data is captured in real time by the cameras in the classroom, recording the visual information in the classroom, such as student expressions, movements, and teacher demonstrations. These data are used to analyze teaching activities and student responses. The audio data and video data collected in real time by intelligent sensors in step S11 can comprehensively and accurately grasp the progress of teaching activities and changes in the classroom environment, providing reliable data support for subsequent virtual teaching data interaction and decision-making.

[0079] In step S12, the fluctuation range is determined according to the audio data and the video data, including:

[0080] Preprocess the audio data and video data;

[0081] Convert the preprocessed audio data into a waveform signal, and obtain the maximum value and the minimum value of the waveform signal;

[0082] Subtract the minimum value from the maximum value of the waveform signal to obtain the audio data fluctuation range;

[0083] Extract the fluctuation features of the preprocessed video data;

[0084] Analyze the fluctuation features to obtain the video data fluctuation range;

[0085] The fluctuation range includes the audio data fluctuation range and the video data fluctuation range.

[0086] It should be noted that first, preprocessing is performed on the audio data and video data collected from the intelligent sensor. This step includes noise reduction, echo cancellation, volume normalization, image enhancement, and frame rate adjustment, aiming to improve the quality of the signal and the image. Subsequently, the preprocessed audio data is converted into a waveform signal, while the video data is converted into a series of frames. The maximum and minimum values of the fluctuation features are identified within a specific time window. These extreme values reveal the change amplitude of the teaching activity during this time period. By calculating the difference between the maximum and minimum values of these waveform signals and fluctuation features, the fluctuation range is obtained. This range reflects the dynamic changes of the teaching activity within a specific time. In the audio data, a larger fluctuation range indicates the intensity of the classroom discussion, while in the video data, it indicates the change in student participation. These fluctuation ranges are key data for analyzing the types of teaching activity changes and constructing the digital twin model, providing data support for virtual teaching data interaction, thereby enhancing the accuracy of teaching decisions and the quality of teaching interaction.

[0087] In step S13, based on the judgment of the fluctuation range and the preset standard fluctuation range, the change type is determined according to the judgment result, including:

[0088] Judge whether the fluctuation range of the audio data exceeds the preset audio standard fluctuation range;

[0089] If it exceeds the preset audio standard fluctuation range, it is determined that the change type of the audio data is a sharp increase;

[0090] If it does not exceed the preset audio standard fluctuation range, it is determined that the change type of the audio data is stable;

[0091] Judge whether the fluctuation range of the video data exceeds the preset video standard fluctuation range;

[0092] If it exceeds the preset video standard fluctuation range, it is determined that the change type of the video data is a mutation;

[0093] If it does not exceed the preset video standard fluctuation range, it is determined that the change type of the video data is non-mutation.

[0094] It should be noted that for audio data, a preset standard fluctuation range is set. This range is determined based on specific conditions of the audio data and the teaching environment to identify the normal fluctuations of the audio signal. Then, the fluctuation range of the audio data calculated in step S12 is compared with this preset standard fluctuation range. If the fluctuation range of the audio data exceeds the preset audio standard fluctuation range, it indicates that there is a significant change in the audio signal, and its change type is determined as a steep increase. Such a steep increase indicates certain important events in the teaching process, such as the teacher suddenly increasing the volume and group discussions among students. If the fluctuation range of the audio data does not exceed the preset audio standard fluctuation range, the change type of the audio data is determined as stable, meaning that the audio signal is within an acceptable fluctuation range and the teaching environment is relatively stable. For video data, a similar method is adopted. First, a standard fluctuation range is preset, and then the fluctuation range of the video data obtained in step S12 is compared with this preset standard fluctuation range. If the fluctuation range of the video data exceeds the preset video standard fluctuation range, the change type of the video data is determined as a sudden change, reflecting significant changes in classroom activities, such as sudden movements of students and dynamic demonstrations by the teacher. If the fluctuation range of the video data does not exceed the preset video standard fluctuation range, the change type of the video data is determined as non-sudden, indicating that the video content is within the normal fluctuation range and the teaching activities are proceeding smoothly.

[0095] It is worth noting that through this step, the key dynamic changes in the teaching process can be accurately identified, providing an important basis for constructing a digital twin virtual teaching model and formulating virtual teaching data interaction decisions, which helps to optimize the allocation of teaching resources and improve the quality of teaching interaction.

[0096] In step S14, according to the change type, the audio data and video data are input into a pre-trained isolation forest model to obtain a clustering data set and isolation digital information, including:

[0097] Select the corresponding digital information as the input data of the isolation forest model according to the change type;

[0098] The isolation forest model performs clustering processing on the input data by a method of constructing multiple isolation trees for identification;

[0099] According to the clustering processing result, the input data is divided into the clustering data set and the isolation digital information.

[0100] According to the change type, the digital information is input into a pre-trained isolation forest model to obtain a clustering data set and isolation digital information. Among them, the training process of the isolation forest model includes:

[0101] Extract waveform features from the digital information as the input data of the model;

[0102] Recursively select the optimal features and splitting points for the input data, continuously split the input data into two subsets. When each subset contains only one data sample, the initial construction of the isolation forest model is completed;

[0103] Randomly select one of the waveform features, sort the data samples in ascending order according to the value of the waveform feature to form the training set data;

[0104] Calculate the average value of the training set data, randomly select two data samples as reference samples, and divide the training set data into three categories: the sample set between the two reference samples, the sample set smaller than the smaller reference sample, and the sample set larger than the larger reference sample;

[0105] Train the isolation forest model, and determine whether the average path lengths of the three types of sample sets in the isolation tree are all less than the preset threshold. If so, the training of the isolation forest model is completed; if not, the isolation forest model continues to be trained.

[0106] It should be noted that corresponding digital information is selected as the input data of the isolation forest model according to the change type. The isolation forest model performs clustering processing on the input data through a method of constructing multiple isolation trees. The construction process of the isolation tree involves recursively selecting the optimal features and splitting points for the input data, continuously splitting the input data into two subsets until each subset contains only one data sample, thereby completing the initial construction of the isolation forest model. During the training process of the isolation forest model, first, waveform features are extracted from the digital information as the input data of the model. Next, a waveform feature is randomly selected, and the data samples are sorted in ascending order according to the feature value to form the training set data. Calculate the average value of the training set data, and randomly select two data samples from it as reference samples. Divide the training set data into three categories: the sample set between the two reference samples, the sample set smaller than the smaller reference sample, and the sample set larger than the larger reference sample. Finally, train the isolation forest model to evaluate whether the average path lengths of the three types of sample sets in the isolation tree are all less than the preset threshold. If the condition is met, the model training is considered completed. If the condition is not met, continue to train the model until the requirements are met. Based on the clustering processing results, the input data is divided into a clustering data set and isolated digital information. The clustering data set contains data points in the normal mode, while the isolated digital information represents abnormal and special events. In this way, the model can identify the abnormal points in the data, and these abnormal points indicate special events or problems in the teaching process, such as the abnormal behavior of students and the failure of teaching equipment.

[0107] It should be noted that this process not only improves the sensitivity to changes in teaching activities, but also optimizes the response to emergencies in the virtual teaching environment through the efficient clustering ability of the isolation forest model. By analyzing the clustering results and isolated information, teaching strategies can be adjusted more precisely, thereby improving teaching quality and learning experience.

[0108] In step S15, constructing an initial digital twin virtual teaching model according to the clustering data set and training the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model includes:

[0109] Extracting the teaching-related feature information in the clustering data set;

[0110] Constructing an initial digital twin virtual teaching model according to the feature information;

[0111] Classifying the digital information according to the change type and iteratively adjusting the digital twin virtual teaching model according to the classification result;

[0112] Obtaining the error between the output result of the digital twin virtual teaching model and the preset teaching result;

[0113] Training the digital twin virtual teaching model through error feedback according to the error;

[0114] When the preset error standard is reached, it is determined that the training is completed, and the digital twin virtual teaching model is obtained.

[0115] It should be noted that feature information closely related to teaching activities is extracted from the clustering dataset. These features include student engagement, course content complexity, and teaching interaction frequency, which can comprehensively reflect the teaching environment and learner behavior. Using this feature information, an initial digital twin virtual teaching model is constructed. This model is a preliminary framework designed to simulate the real teaching environment and learning process, including teachers' teaching behaviors, students' learning behaviors, and the display and interaction of teaching content. Next, the data is classified according to the change types of audio data and video data. Then, based on these classification results, the digital twin virtual teaching model is iteratively adjusted to ensure that the model can accurately reflect the behaviors and results in different teaching scenarios. After the model is adjusted, the output results of the digital twin virtual teaching model are obtained and compared with the preset teaching results, and the error between the two is calculated. This error evaluation is a key step in the model training process. It helps us understand the accuracy of the model prediction and guides the subsequent optimization direction. According to the calculated error, the digital twin virtual teaching model is trained through an error feedback mechanism, which includes adjusting model parameters and adding more training data to reduce the error. Finally, when the error between the model output result and the preset teaching result drops to the preset error standard, it is determined that the model training is completed. At this time, an optimized digital twin virtual teaching model is obtained, which can accurately simulate and predict various situations in the teaching process, providing data support and decision-making basis for virtual teaching.

[0116] In step S16, virtual teaching simulation is performed on the isolated digital information to obtain an output change amount, and parameter settings are performed on the isolated digital information according to the output change amount, including:

[0117] Input the isolated digital information into the digital twin virtual teaching model to simulate a virtual teaching scenario;

[0118] Obtain the actual output amount of the digital twin virtual teaching model and calculate the difference from the preset output amount to obtain an output change amount;

[0119] According to the output change amount, set the relevant parameters in the isolated digital information.

[0120] It should be noted that by inputting isolated digital information into a trained digital twin virtual teaching model to simulate a virtual teaching scenario, the isolated digital information refers to those data points that are identified as anomalies and significantly different from most data points during the clustering process. They represent special events and situations in the teaching process. During the simulation of the virtual teaching scenario, the digital twin virtual teaching model generates actual output quantities based on the input isolated digital information, which includes simulating students' understanding levels, participation degrees, and learning outcomes. Then, the actual output quantities of the digital twin virtual teaching model are obtained and compared with the preset output quantities, and the difference between the two is calculated to obtain the output change quantity. The preset output quantity is the expected result set according to the input data and teaching objectives, while the actual output quantity is the predicted result obtained by model simulation. The output change quantity reflects the deviation between the model prediction and the actual teaching objectives. Finally, based on the calculated output change quantity, relevant parameters in the isolated digital information are set, which involves adjusting the difficulty of teaching content, changing teaching methods, and adjusting the allocation of teaching resources. Through parameter setting, the isolated digital information can be optimized.

[0121] It is worth noting that by inputting isolated digital information into the digital twin virtual teaching model to simulate the teaching scenario, the actual output quantity of the model is obtained. Subsequently, this actual output quantity is compared with the preset expected output quantity, and the output change quantity is calculated. This change quantity shows the deviation between the model prediction and the teaching objectives. Based on this output change quantity, relevant parameters of the isolated digital information are adjusted to optimize these information points to make them more in line with the teaching objectives and improve the teaching effect. This process helps to understand and improve the factors that lead to abnormal teaching results, and then make more targeted teaching decisions in the virtual teaching environment.

[0122] In step S17, based on the isolated digital information after parameter setting, the data abnormality degree is determined, and combined with the prediction accuracy of the digital twin virtual teaching model, a virtual teaching data interaction decision is formulated, including:

[0123] Calculate the data abnormality degree of the isolated digital information after parameter adjustment;

[0124] Obtain the prediction accuracy of the digital twin virtual teaching model;

[0125] Combined with the data abnormality degree and the prediction accuracy, formulate a virtual teaching data interaction decision.

[0126] It should be noted that calculating the data abnormality of isolated digital information after parameter adjustment involves quantitative analysis of the isolated digital information after parameter setting to evaluate its deviation from normal data. The data abnormality is an index to measure the difference between a data point and the rest of the data set, which is obtained by calculating the deviation between the data point and the model prediction value. Then, obtain the prediction accuracy of the digital twin virtual teaching model. The prediction accuracy reflects the degree of coincidence between the prediction result and the actual result of the model in the simulated teaching environment. The higher the accuracy, the more reliable the prediction of the model and the more realistically it can reflect the teaching activities. Finally, combining the data abnormality and the prediction accuracy, formulate a virtual teaching data interaction decision. This decision-making process includes deciding whether it is necessary to adjust the teaching activities, whether additional teaching resource support is needed, and whether the current teaching strategy should be continued. When the data abnormality is high and the prediction accuracy is low, corresponding teaching intervention measures need to be taken, such as changing the teaching method, providing additional tutoring, and adjusting the difficulty of the teaching content.

[0127] It is worth noting that through this process, it can be ensured that virtual teaching activities can be optimized according to real-time data and model predictions, thereby improving teaching quality and learning efficiency. This decision-making method based on data and model predictions provides an automated and precise teaching management means for virtual teaching, which helps to improve the quality of teaching.

[0128] To facilitate the understanding of the present invention, some preferred embodiments of the present invention will be further described below.

[0129] In this embodiment, a virtual teaching data interaction decision is made for an online course, where the teacher teaches through video conferencing software, and at the same time, students participate in classroom discussions through audio and video.

[0130] The working process is as follows:

[0131] Step 1: Obtain the audio data and video data in the teaching data. At the beginning of the course, intelligent sensors and data acquisition interfaces capture the teacher's explanatory audio and students' video interactions in real time, and these data are transmitted to the data processing center.

[0132] Step 2: Determine the fluctuation range according to the audio data and the video data. Preprocess these original audio data and video data, extract key features, such as the volume change in the audio and the body language of students in the video. Then, calculate the maximum and minimum values of these features to determine the fluctuation range.

[0133] Step 3: Make a judgment based on the fluctuation range and the preset standard fluctuation range, and determine the change type according to the judgment result. Compare the calculated fluctuation range with the preset standard fluctuation range. When the audio fluctuation range exceeds the preset range, it indicates that the classroom discussion is extremely active. When the video fluctuation range exceeds the preset range, it indicates a sudden change in students' behavior.

[0134] Step 4: Input the digital information into a pre-trained Isolation Forest model according to the change type to obtain a clustering data set and isolated digital information. According to the change type, input the data into the Isolation Forest model, which identifies and differentiates normal and abnormal teaching interaction patterns and outputs a clustering data set and isolated digital information.

[0135] Step 5: Construct an initial digital twin virtual teaching model based on the clustering data set, and train the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model. Use the feature information in the clustering data set to construct an initial digital twin virtual teaching model to simulate the real classroom environment. Then, use teaching data to train and optimize this model.

[0136] Step 6: Conduct virtual teaching simulation on the isolated digital information to obtain an output change amount, and set parameters for the isolated digital information according to the output change amount. Conduct virtual teaching simulation on the isolated digital information, compare the predicted output of the model with the actual output, and calculate the output change amount. Adjust the parameters of the isolated digital information according to this change amount to better conform to the expected teaching effect.

[0137] Step 7: Determine the data abnormality degree based on the isolated digital information after parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy of the digital twin virtual teaching model. Evaluate the data abnormality degree of the isolated digital information after adjusting the parameters, and formulate a teaching decision in combination with the prediction accuracy of the model. When the data abnormality degree is low and the prediction accuracy is high, it is decided to continue the current teaching strategy. When the data abnormality degree is high and the prediction accuracy is low, it is necessary to adjust the teaching method and resource allocation.

[0138] In summary, the present invention provides a virtual teaching data interaction method based on digital twins. It intelligently manages data interaction in the virtual teaching environment, optimizes teaching resource allocation, and improves the accuracy and efficiency of teaching interaction. First, intelligent sensors are used to capture audio data and video teaching data in real time, which reflect the real situation of teaching activities. Then, the collected data is preprocessed and its fluctuation range is calculated to provide a basis for analyzing teaching dynamics. By comparing the data fluctuation range with a preset standard, the change types of teaching activities, such as stable and sudden changes, are identified. Next, the Isolation Forest model is used to cluster the data of the change types to distinguish normal and abnormal teaching interaction modes. A digital twin virtual teaching model is constructed based on the clustering data set, and the model is iteratively optimized by inputting data to improve the prediction accuracy. Virtual teaching simulation is carried out on isolated digital information, and the parameters are adjusted according to the output change amount to meet the expected teaching goals. Finally, combining the data abnormality degree of the isolated digital information with the parameter adjustment and the prediction accuracy rate of the model, an accurate virtual teaching data interaction decision is formulated. The present invention improves the decision-making accuracy of virtual teaching, makes teaching management more scientific and precise, reduces the waste of teaching resources through intelligent means, improves resource utilization efficiency, enhances the real-time nature of teaching interaction, and thus optimizes the learning experience and teaching effect.

[0139] Referring to Figure 2 , the present invention provides a virtual teaching data interaction system based on digital twins, including:

[0140] A data acquisition module for acquiring audio data and video data in teaching data;

[0141] A fluctuation range determination module for determining the fluctuation range according to the audio data and the video data;

[0142] A change type judgment module for judging according to the fluctuation range and a preset standard fluctuation range to determine the change type;

[0143] A clustering module for clustering the audio data and video data according to the change type to obtain a clustering data set and isolated digital information;

[0144] A model construction and training module for constructing an initial digital twin virtual teaching model according to feature information, classifying the digital information according to the change type, iteratively adjusting the digital twin virtual teaching model according to the classification result, obtaining the error between the output result of the digital twin virtual teaching model and the preset teaching result, training the digital twin virtual teaching model through error feedback according to the error, and determining that the training is completed when the preset error standard is reached to obtain the digital twin virtual teaching model;

[0145] A simulation and parameter setting module for performing virtual teaching simulation on the isolated digital information to obtain an output change amount, and setting parameters for the isolated digital information according to the output change amount;

[0146] A decision-making module for determining the data abnormality degree according to the isolated digital information after parameter setting, and formulating a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model.

[0147] In summary, the present invention provides a virtual teaching data interaction system based on digital twins. It optimizes the allocation of teaching resources and improves the accuracy and efficiency of teaching interaction by intelligently managing data interaction in the virtual teaching environment. First, intelligent sensors are used to capture audio data and video teaching data in real time, which reflect the real situation of teaching activities. Then, the collected data is preprocessed, and its fluctuation range is calculated to provide a basis for analyzing teaching dynamics. By comparing the data fluctuation range with a preset standard, the change types of teaching activities, such as stable and sudden changes, are identified. Next, the Isolation Forest model is used to cluster the data of the change types to distinguish normal and abnormal teaching interaction modes. A digital twin virtual teaching model is constructed based on the clustering data set, and the model is iteratively optimized by inputting data to improve the prediction accuracy. Virtual teaching simulation is performed on the isolated digital information, and the parameters are adjusted according to the output change amount to meet the expected teaching goals. Finally, an accurate virtual teaching data interaction decision is made by combining the data abnormality degree of the isolated digital information after parameter adjustment and the prediction accuracy rate of the model. The present invention improves the decision-making accuracy of virtual teaching, makes teaching management more scientific and precise, reduces the waste of teaching resources through intelligent means, improves resource utilization efficiency, and enhances the real-time nature of teaching interaction, thereby optimizing the learning experience and teaching effect.

[0148] It should be noted that the virtual teaching data interaction system based on digital twins provided in the embodiments of the present invention is used to execute all the process steps of the virtual teaching data interaction method based on digital twins in the above embodiments. Their working principles and beneficial effects correspond one by one, and thus will not be elaborated here.

[0149] The embodiments of the present invention also provide an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a virtual teaching data interaction program based on digital twins. When the processor executes the computer program, it implements the steps in the embodiments of the above various virtual teaching data interaction methods based on digital twins, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above device embodiments, such as the decision-making module.

[0150] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0151] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0152] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and circuits.

[0153] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and invoking the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, the image playback function, etc.); the data storage area can store the data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0154] Among them, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0155] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0156] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A virtual teaching data interaction method based on digital twin, characterized in that, Executed by a computer, including: Obtain audio data and video data in teaching data; Determine the fluctuation range according to the audio data and the video data; Make a judgment based on the fluctuation range and a preset standard fluctuation range, and determine the change type according to the judgment result; Input digital information into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolated digital information; Construct an initial digital twin virtual teaching model according to the clustering data set, and train the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model; Conduct virtual teaching simulation on the isolated digital information to obtain an output change amount, and perform parameter setting on the isolated digital information according to the output change amount; Determine the data abnormality degree according to the isolated digital information after parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy of the digital twin virtual teaching model; Among them, inputting the audio data and video data into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolated digital information includes: Select corresponding digital information as the input data of the isolation forest model according to the change type; The isolation forest model performs clustering processing on the input data through a method of constructing multiple isolation trees for identification; According to the clustering processing result, divide the input data into the clustering data set and the isolated digital information; Among them, inputting digital information into a pre-trained isolation forest model according to the change type to obtain a clustering data set and isolated digital information, where the training process of the isolation forest model includes: Extract waveform features from the digital information as the input data of the model; Recursively select the optimal feature and splitting point for the input data, and continuously split the input data into two subsets. When each subset contains only one data sample, the initial construction of the isolation forest model is completed; Randomly select one of the waveform features, sort the data samples according to the value of the waveform feature from small to large to form training set data; Calculate the average value of the training set data, randomly select two data samples as reference samples, and divide the training set data into three categories: a sample set between the two reference samples, a sample set smaller than the smaller reference sample, and a sample set larger than the larger reference sample; Train the isolation forest model, and judge whether the average path lengths of the three sample sets in the isolation tree are all less than a preset threshold. If so, the training of the isolation forest model is completed; if not, the isolation forest model continues to be trained.

2. The virtual teaching data interaction method based on digital twin according to claim 1, wherein Determine the fluctuation range according to the audio data and the video data, including: Preprocess the audio data and video data; Convert the preprocessed audio data into a waveform signal, and obtain the maximum value and the minimum value of the waveform signal; Subtract the minimum value from the maximum value of the waveform signal to obtain the audio data fluctuation range; Extract the fluctuation features of the preprocessed video data; Analyze the fluctuation features to obtain the video data fluctuation range; The fluctuation range includes the audio data fluctuation range and the video data fluctuation range.

3. The virtual teaching data interaction method based on digital twin according to claim 2, wherein, Judging according to the fluctuation range and a preset standard fluctuation range, and determining the change type according to the judgment result, including: Judging whether the fluctuation range of the audio data exceeds the preset audio standard fluctuation range; If it exceeds the preset audio standard fluctuation range, it is determined that the change type of the audio data is a sharp increase; If it does not exceed the preset audio standard fluctuation range, it is determined that the change type of the audio data is stable; Judging whether the fluctuation range of the video data exceeds the preset video standard fluctuation range; If it exceeds the preset video standard fluctuation range, it is determined that the change type of the video data is a mutation; If it does not exceed the preset video standard fluctuation range, it is determined that the change type of the video data is non-mutation.

4. The virtual teaching data interaction method based on digital twin according to claim 3, wherein Constructing an initial digital twin virtual teaching model according to the clustering data set, and training the initial digital twin virtual teaching model to obtain a digital twin virtual teaching model, including: Extracting the teaching-related feature information in the clustering data set; Constructing an initial digital twin virtual teaching model according to the feature information; Classifying the digital information according to the change type and iteratively adjusting the digital twin virtual teaching model according to the classification result; Obtaining the error between the output result of the digital twin virtual teaching model and the preset teaching result; Training the digital twin virtual teaching model through error feedback according to the error; When the preset error standard is reached, it is determined that the training is completed, and the digital twin virtual teaching model is obtained.

5. The virtual teaching data interaction method based on digital twin according to claim 1, characterized in that Performing virtual teaching simulation on the isolated digital information to obtain an output change amount, and setting parameters for the isolated digital information according to the output change amount, including: Inputting the isolated digital information into the digital twin virtual teaching model to simulate a virtual teaching scenario; Obtaining the actual output amount of the digital twin virtual teaching model and calculating the difference from the preset output amount to obtain the output change amount; Setting relevant parameters in the isolated digital information according to the output change amount.

6. The virtual teaching data interaction method based on digital twin according to claim 1, characterized in that Determining the data abnormality degree according to the isolated digital information after parameter setting, and formulating a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model, including: Calculating the data abnormality degree of the isolated digital information after parameter adjustment; Obtaining the prediction accuracy rate of the digital twin virtual teaching model; Formulating a virtual teaching data interaction decision in combination with the data abnormality degree and the prediction accuracy rate.

7. A virtual teaching data interaction system based on digital twin, characterized in that For implementing the virtual teaching data interaction method based on digital twin as described in any one of claims 1 to 6, including: A data acquisition module for acquiring audio data and video data in teaching data; A fluctuation range determination module for determining a fluctuation range according to the audio data and the video data; A change type judgment module for judging according to the fluctuation range and a preset standard fluctuation range to determine the change type; A clustering module for clustering the audio data and video data according to the change type to obtain a clustering data set and isolated digital information; A model construction and training module, configured to construct an initial digital twin virtual teaching model according to feature information, classify the digital information according to the change type, iteratively adjust the digital twin virtual teaching model according to the classification result, obtain the error between the output result of the digital twin virtual teaching model and the preset teaching result, train the digital twin virtual teaching model through error feedback according to the error, and determine that the training is completed and obtain the digital twin virtual teaching model when the preset error standard is reached; A simulation and parameter setting module, configured to perform virtual teaching simulation on the isolated digital information to obtain an output change amount, and perform parameter setting on the isolated digital information according to the output change amount; A decision-making module, configured to determine the data abnormality degree according to the isolated digital information after parameter setting, and formulate a virtual teaching data interaction decision in combination with the prediction accuracy rate of the digital twin virtual teaching model.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute a virtual teaching data interaction method based on digital twin as described in any one of claims 1 to 6.

Images