English auxiliary teaching virtual reality equipment and use method thereof

Abstract

The invention discloses an English auxiliary teaching virtual reality device and a use method thereof, and particularly relates to the technical field of education, and the method comprises the following steps: recording the starting and ending time of auxiliary teaching, calculating the total time length, analyzing the effectiveness of teaching design, obtaining the use information of a user, and carrying out the abnormality analysis. Teaching content quality indexes and teaching task quality indexes are obtained, comprehensive use quality coefficients are evaluated, high-quality and low-quality auxiliary teaching is divided, and for low-quality auxiliary teaching, the direction is optimized through fuzzy reasoning decision making; the method can timely discover the hidden danger of insufficient effectiveness in teaching design, ensure that the teaching content and tasks can effectively meet the requirements of students, improve the teaching quality, accurately identify high-quality and low-quality auxiliary teaching based on the analysis of the comprehensive use quality coefficient, provide a specific optimization direction for low-quality teaching, and improve the teaching efficiency. The effect of personalized teaching support is improved, the learning interest and enthusiasm of students are stimulated, and the overall learning effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and more specifically, to an English-assisted teaching virtual reality device and a method for using the device. Background Art

[0002] English-assisted teaching virtual reality equipment is an educational tool that uses virtual reality (VR) technology to enhance and optimize the English learning experience. This system allows learners to participate in various real or simulated scenarios through an immersive virtual environment, such as talking with virtual characters, carrying out tasks or adventures in the virtual world, etc., thereby improving the interactivity and fun of language learning. This can not only help students better understand and use the language, but also enhance learning effects through real-time feedback and interaction.

[0003] Virtual reality devices for English-assisted teaching are usually equipped with a variety of teaching resources and activities, such as virtual classrooms, pronunciation exercises, vocabulary games, etc., which are designed to comprehensively improve students' listening, speaking, reading and writing abilities. These systems can provide personalized teaching content and exercises based on students' individual needs and learning progress, thereby more effectively promoting language acquisition. With the help of VR technology, students can break free from the limitations of traditional classrooms and conduct immersive learning anytime and anywhere, greatly improving the flexibility and efficiency of learning.

[0004] In the design and use of virtual reality devices for English-assisted teaching, there are often problems such as unbalanced teaching content and task quality, which leads to insufficient student participation and low utilization of educational resources. How to judge the design deficiencies during personalized user use and optimize them in order to achieve the expected use effect is a problem that needs to be faced. Therefore, a virtual reality device for English-assisted teaching and a method of using it are proposed. Summary of the invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An English-assisted teaching virtual reality device, comprising an assisted teaching time calculation module, a hidden danger analysis module, an abnormality analysis module, a comprehensive analysis module, and a decision-making module;

[0007] When the target user uses the auxiliary teaching time calculation module, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time, and the difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use;

[0008] The hidden danger analysis module analyzes the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target user is using it;

[0009] The abnormal analysis module is used to obtain the usage information of the target users when there is a hidden danger of insufficient effectiveness in the teaching design, and then conduct abnormal analysis to obtain the teaching content quality index and the teaching task quality index;

[0010] The comprehensive analysis module evaluates the usage quality of target users based on the teaching content quality index and the teaching task quality index to obtain a comprehensive usage quality coefficient;

[0011] The decision-making module divides the target users' usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient, and makes decisions on the direction that needs to be optimized for low-quality auxiliary teaching.

[0012] In a preferred embodiment, the hidden danger analysis module performs analysis based on the total duration of a single auxiliary teaching use to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target user uses it, which refers to:

[0013] Obtain the total duration of each auxiliary teaching use under a fixed window, and the corresponding standard total duration of the auxiliary teaching preset, and then calculate the usage time ratio of each auxiliary teaching. The usage time ratio is obtained by dividing the total duration of each auxiliary teaching use by the corresponding standard total duration of the auxiliary teaching preset. A normal usage range value is preset. If the usage time ratio falls within the normal usage range, the auxiliary teaching is marked as normal use. If the usage time ratio does not fall within the normal usage range, the auxiliary teaching is marked as abnormal use. The total number of auxiliary teaching marked as normal use and the total number of auxiliary teaching marked as abnormal use are counted, and the usage quality ratio value of the target user is calculated. The usage quality ratio value of the target user is obtained by dividing the total number of auxiliary teaching marked as abnormal use by the total number of auxiliary teaching marked as normal use. A usage quality ratio threshold is preset. If the usage quality ratio value of the target user is less than or equal to the usage quality ratio threshold, it is judged that there is no hidden danger of insufficient effectiveness of the teaching design. If the usage quality ratio value of the target user is greater than the usage quality ratio threshold, it is judged that there is a hidden danger of insufficient effectiveness of the teaching design.

[0014] In a preferred embodiment, the logic for obtaining the teaching content quality index is:

[0015] Under the fixed window, feature extraction is performed on the learning time, learning feedback score, test score, and class participation rate of each auxiliary teaching use, and the collected feature data is standardized to obtain the standardized learning time, learning feedback score, test score, and class participation rate. The standardized data is constructed into a matrix X using the principal component analysis method, and then the covariance matrix Σ of the data matrix is ​​calculated: N is the number of samples, Xi is the i-th sample, μ is the eigenmean vector, T represents the transpose operation of the matrix, and the eigenvalue and eigenvector of the covariance matrix are calculated: ∑v = λv; λ is the eigenvalue, and v is the corresponding eigenvector; the first k eigenvectors are selected in descending order of eigenvalue as the basis vectors of the principal component to form a projection matrix W, and the original data is projected into the principal component space to obtain the data after dimensionality reduction;

[0016] Use MLP to train and predict the reduced-dimensional data, define the input layer, hidden layer, and output layer, the number of nodes in the input layer is equal to the number of principal components, the output layer is 1 node, randomly initialize the weights and biases, perform forward propagation to calculate the output, use the mean square error as the loss function, use the gradient descent method for optimization, perform back propagation to adjust the weights and biases, adjust the weights and biases through multiple iterations until the loss function converges, use the trained MLP model to predict the content quality performance of each auxiliary teaching, obtain the content quality score of each auxiliary teaching, and calculate the average of the content quality scores of all auxiliary teaching as the teaching content quality index.

[0017] In a preferred embodiment, the logic for obtaining the teaching task quality index is:

[0018] Under the fixed window, the task completion rate, task completion time, task difficulty score, and task feedback score of each auxiliary teaching are extracted, and the collected feature data are standardized to ensure that data of different dimensions can be compared. The standardized task completion rate, standardized task completion time, standardized task difficulty score, and standardized task feedback score are obtained and combined to obtain the combined data points. K-means clustering analysis is performed on the standardized data to identify the pattern of task performance. K cluster centers are randomly selected, and the distance from each data point to all cluster centers is calculated. Each data point is assigned to the nearest cluster center, and the mean of all data points assigned to each cluster is calculated and used as the new cluster center. The data point assignment and cluster center update are repeated until the cluster centers converge. After clustering, each data point obtains a cluster label and is then substituted into the pre-trained random forest regression model. Each tree in the random forest regression model predicts the test data, and the prediction results of all trees are averaged as the final result to obtain the teaching task quality score. The average value of the teaching task quality score of all auxiliary teaching uses is calculated as the teaching task quality index.

[0019] In a preferred embodiment, the comprehensive analysis module evaluates the usage quality of the target users based on the teaching content quality index and the teaching task quality index, and obtains the comprehensive usage quality coefficient, which means: substituting the teaching content quality index and the teaching task quality index into a pre-trained machine learning model for comprehensive analysis to generate a comprehensive usage quality coefficient.

[0020] In a preferred embodiment, the decision module divides the target user's usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient, which means:

[0021] Obtain a comprehensive usage quality coefficient, preset a standard comprehensive usage quality reference threshold, compare the comprehensive usage quality coefficient with the preset standard comprehensive usage quality reference threshold, if the comprehensive usage quality coefficient is greater than or equal to the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as high-quality auxiliary teaching; if the comprehensive usage quality coefficient is less than the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as low-quality auxiliary teaching.

[0022] In a preferred embodiment, for low-quality auxiliary teaching, making decisions on the direction that needs to be optimized refers to:

[0023] The teaching content quality index, teaching task quality index and comprehensive use quality coefficient are obtained respectively, fuzzy reasoning is applied, the teaching content quality index, teaching task quality index and comprehensive use quality coefficient are defined as input variables, the output variables are defined as the optimization direction, the input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets, the output variables are fuzzified and the output variables are converted into fuzzy sets, fuzzy rules are formulated to describe the optimization requirements under different data type combinations, the fuzzified input variables are inferred through fuzzy rules, and the direction that needs to be optimized is determined.

[0024] In a preferred embodiment, a method for using a virtual reality device for English-assisted teaching comprises the following steps:

[0025] When the target user uses it, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time. The difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use;

[0026] Analyze the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target users are using it;

[0027] When there is a hidden danger of insufficient effectiveness in the teaching design, the usage information of the target users is obtained, and then abnormal analysis is performed to obtain the teaching content quality index and the teaching task quality index;

[0028] Based on the teaching content quality index and teaching task quality index, the target users' usage quality is evaluated to obtain the comprehensive usage quality coefficient;

[0029] Based on the comprehensive usage quality coefficient, the usage quality of target users is divided into high-quality auxiliary teaching and low-quality auxiliary teaching. For low-quality auxiliary teaching, decisions are made on the direction that needs to be optimized.

[0030] Technical effects and advantages of the present invention:

[0031] The present invention accurately calculates and analyzes the total duration of a single auxiliary teaching session, timely discovers the lack of effectiveness in the teaching design, ensures that the teaching content and tasks can effectively meet the needs of students, and improves the teaching quality; uses the teaching content quality index and the teaching task quality index to comprehensively evaluate the usage quality of the target users, generates a comprehensive usage quality coefficient, provides a scientific basis for the level of teaching quality, and optimizes the direction through fuzzy reasoning decisions, and formulates targeted improvement measures.

[0032] Based on the comprehensive analysis of the quality coefficient, the present invention can accurately identify high-quality and low-quality auxiliary teaching, provide specific optimization directions for low-quality teaching, and improve the effect of personalized teaching support; by timely optimizing the teaching content and task design, it can improve students' satisfaction and participation, stimulate students' learning interest and enthusiasm, and improve the overall learning effect; the present invention can monitor and analyze various data in the teaching process in real time, discover and solve problems in the teaching design, avoid waste of resources, and improve the utilization efficiency of teaching resources; the system can collect and analyze teaching data in real time, quickly feedback teaching effects, help educators to adjust teaching strategies and content in time, and ensure continuous improvement of teaching quality; through the comprehensive evaluation of the quality coefficient, a systematic teaching management tool is provided to help education managers fully understand the teaching effect, scientifically plan and optimize the allocation of teaching resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0034] Figure 1 The figure is a schematic diagram of a virtual reality device for English-assisted teaching in the present invention.

[0035] Figure 2 The present invention is a schematic diagram of a method for using a virtual reality device for English-assisted teaching. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Reference Figure 1 - Figure 2 The following embodiments are obtained:

[0038] Embodiment 1: An English-assisted teaching virtual reality device, comprising an auxiliary teaching time calculation module, a hidden danger analysis module, an abnormality analysis module, a comprehensive analysis module, and a decision-making module;

[0039] When the target user uses the auxiliary teaching time calculation module, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time, and the difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use;

[0040] The hidden danger analysis module analyzes the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target user is using it;

[0041] The abnormal analysis module is used to obtain the usage information of the target users when there is a hidden danger of insufficient effectiveness in the teaching design, and then conduct abnormal analysis to obtain the teaching content quality index and the teaching task quality index;

[0042] The comprehensive analysis module evaluates the usage quality of target users based on the teaching content quality index and the teaching task quality index to obtain a comprehensive usage quality coefficient;

[0043] The decision-making module divides the target users' usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient, and makes decisions on the direction that needs to be optimized for low-quality auxiliary teaching.

[0044] The hidden danger analysis module analyzes the total duration of a single auxiliary teaching session to determine whether there are hidden dangers of insufficient effectiveness of the teaching design when the target users are using it. These are:

[0045] Obtain the total duration of each auxiliary teaching use under a fixed window, and the corresponding standard total duration of the auxiliary teaching preset, and then calculate the usage time ratio of each auxiliary teaching. The usage time ratio is obtained by dividing the total duration of each auxiliary teaching use by the corresponding standard total duration of the auxiliary teaching preset. A normal usage range value is preset. If the usage time ratio falls within the normal usage range, the auxiliary teaching is marked as normal use. If the usage time ratio does not fall within the normal usage range, the auxiliary teaching is marked as abnormal use. The total number of auxiliary teaching marked as normal use and the total number of auxiliary teaching marked as abnormal use are counted, and the usage quality ratio value of the target user is calculated. The usage quality ratio value of the target user is obtained by dividing the total number of auxiliary teaching marked as abnormal use by the total number of auxiliary teaching marked as normal use. A usage quality ratio threshold is preset. If the usage quality ratio value of the target user is less than or equal to the usage quality ratio threshold, it is judged that there is no hidden danger of insufficient effectiveness of the teaching design. If the usage quality ratio value of the target user is greater than the usage quality ratio threshold, it is judged that there is a hidden danger of insufficient effectiveness of the teaching design.

[0046] In the process of virtual reality teaching of English, the lack of effectiveness of teaching design will lead to the following problems:

[0047] Poor learning outcomes: Overly complex or inappropriate task design may confuse and frustrate students. Tasks and activities in a VR environment should be adapted to the students’ language level and gradually increase in difficulty to ensure that students can gradually improve through challenges. If the task design is unreasonable and the difficulty is too high or too low, students may feel too much pressure or lack of challenge, which will affect their learning outcomes.

[0048] Individualized learning needs cannot be met: The lack of individualized learning paths and targeted exercises may result in students being unable to learn effectively according to their own learning progress and needs. An important advantage of virtual reality technology is that it can provide a personalized learning experience, but if the teaching design fails to fully utilize this and fails to adjust and optimize according to the individual needs of students, the students' learning effect may be limited. For example, different students may have different strengths and weaknesses in listening, speaking, reading, and writing. If the teaching design cannot provide personalized tutoring based on these differences, the improvement of students' comprehensive language ability will be affected.

[0049] The necessity of judging hidden dangers: Ensure the effectiveness of teaching design: The effectiveness of teaching design directly affects students' learning outcomes. Through regular monitoring and analysis, problems can be discovered and solved in a timely manner to ensure the effectiveness and adaptability of teaching design. Improve student satisfaction: When the teaching design meets students' learning needs and is effective, students' satisfaction and learning experience will increase. This is very important for students' continuous learning and progress. Data-driven decision-making: By analyzing students' learning time and usage, scientific decisions can be made based on data, and teaching design and teaching strategies can be improved, thereby improving the overall teaching quality. Responding to diverse learning needs: Students' learning methods and learning progress are different. Through monitoring and analysis, the learning needs of different students can be identified, and personalized support and assistance can be provided to ensure that every student can receive effective teaching.

[0050] The logic for obtaining the teaching content quality index is:

[0051] Under a fixed window, such as weekly or monthly, feature extraction is performed on the learning time, learning feedback score, test score, and class participation rate each time auxiliary teaching is used, and the collected feature data is standardized, such as using the Z-Score standardization method to obtain the standardized learning time, learning feedback score, test score, and class participation rate. The standardized data is constructed into a matrix X using the principal component analysis method, where each row represents a data sample (such as the data of a student in a fixed window), each column represents a feature, and the corresponding feature mean is subtracted from each column of the data matrix X to obtain the centralized data matrix X. c ;X c =X i -μ; then calculate the covariance matrix Σ of the data matrix: It can also be expressed as: N is the number of samples, X i is the ith sample, μ is the eigenmean vector, T represents the transpose operation of the matrix, and the eigenvalue and eigenvector of the covariance matrix are calculated: Σv=λv; λ is the eigenvalue, and v is the corresponding eigenvector; the first k eigenvectors are selected in descending order of the eigenvalue as the basis vectors of the principal component to form the projection matrix W, and the original data are projected into the principal component space to obtain the reduced-dimensional data: T=XW; Y is the projected data matrix, and W is the projection matrix; learning time: the total learning time used for each auxiliary teaching; learning feedback score: the student's feedback score for each teaching; test score: the student's test score after each auxiliary teaching, and classroom participation: the student's participation in the classroom (such as the number of virtual interactions, the number of questions answered, etc.).

[0052] Use MLP to train and predict the reduced-dimensional data, define the input layer, hidden layer, and output layer, the number of nodes in the input layer is equal to the number of principal components, the output layer is 1 node, randomly initialize the weights and biases, perform forward propagation to calculate the output, use the mean square error as the loss function, use the gradient descent method for optimization, perform back propagation to adjust the weights and biases, adjust the weights and biases through multiple iterations until the loss function converges, use the trained MLP model to predict the quality performance of the content used in each auxiliary teaching, obtain the content quality score of each auxiliary teaching, and calculate the average of the content quality scores of all auxiliary teaching as the teaching content quality index, specifically:

[0053] Define the network structure: Input layer: The number of nodes is equal to the number of principal components (assuming it is k). Hidden layer: Contains several hidden layers, each layer contains several nodes (assuming the first layer contains n (l) Nodes). Output layer: 1 node, used to output content quality scores.

[0054] Randomly initialize weights and biases: Weight matrix: Randomly initialize the weight matrix W of each layer (l) ; Bias vector: Randomly initialize the bias vector b of each layer (l) .

[0055] Forward propagation: input layer to hidden layer: Z (l) =W (l) X+b (l) ; A (1) =f(Z (l) ); X is the input data matrix (data after dimensionality reduction), with a dimension of N×k, W (l) is the weight matrix from the input layer to the first hidden layer, with dimension n (l) *j,b (l) is the bias vector of the first hidden layer, with dimension n (l) *1, Z (l) is the linear combination result of the first hidden layer, A (1) is the activation output of the first hidden layer, and f is the activation function (such as ReLU or Sigmoid).

[0056] Hidden layer to hidden layer (taking the lth layer as an example): Z (l) =W (l) A (l-1) +b (l) ; A (l) =f(Z (l) );W (l) is the weight matrix from layer l-1 to layer l, with dimension n (l) *n (l-1) , b (l) is the bias vector of the lth layer, with dimension n(l) *1, Z (l) is the linear combination result of the lth layer, A (l) is the activation output of layer l.

[0057] Hidden layer to output layer: Z (L) =W (L) A (L-1) +b (L) ; W (L) It is the weight matrix from the last layer to the output layer, with a dimension of 1*n (L)-1) ; b (L) is the bias vector of the output layer, with a dimension of 1*1, Z (L) is the linear combination result of the output layer, is the predicted value of the output layer (content quality score).

[0058] Use the trained MLP model to predict the quality of the content used in each auxiliary teaching, and get the content quality score of each auxiliary teaching The average of all auxiliary teaching content quality scores is calculated as the teaching content quality index. The size of the teaching content quality index (TCQI) directly reflects the overall quality and effectiveness of the teaching content. It is used to evaluate the performance of the teaching content in multiple dimensions. TCQI close to 0 indicates that the teaching content performs poorly in all dimensions. For example, students have a short learning time, low feedback scores, unsatisfactory test scores, and low class participation. Students are less satisfied with the teaching content, which may be reflected in the feedback scores. Students may find the course boring, too difficult or too low, or it does not meet their expectations. The current teaching methods and strategies may not be suitable for students' learning needs and need to be adjusted and optimized. For example, it may be necessary to increase interactive links, adjust the difficulty of course content, improve assessment methods, etc. Teaching resources (such as time, equipment, teacher input, etc.) have not been effectively utilized, resulting in unsatisfactory teaching results.

[0059] The logic for obtaining the teaching task quality index is as follows: within a fixed window, feature extraction is performed on the task completion rate, task completion time, task difficulty score, and task feedback score for each auxiliary teaching use. Task completion rate: the completion percentage of each auxiliary teaching task; Task completion time: the completion time of each auxiliary teaching task; Task difficulty score: the student's subjective score on the difficulty of each auxiliary teaching task; Task feedback score: the student's overall feedback score on each auxiliary teaching task; The collected feature data are standardized to ensure that data of different dimensions can be compared, and the standardized task completion rate, standardized task completion time, standardized task difficulty score, and standardized task feedback score are obtained and combined to obtain the combined data points. K-means cluster analysis is performed on the standardized data to identify the pattern of task performance, and K cluster centers are randomly selected to calculate the distance from each data point to all cluster centers. Euclidean distance can be used as the distance measurement method. Each data point is assigned to the nearest cluster center, the mean of all data points assigned to each cluster is calculated, and it is used as the new cluster center. The data point assignment and cluster center update are repeated. The assignment rule is: assign each data point to the nearest cluster center; update the cluster center: calculate the mean of all data points assigned to each cluster, and use it as the new cluster center until the cluster center converges, that is, the cluster center no longer changes or changes very little. After clustering, each data point gets a cluster label, and then substitutes it into the pre-trained random forest regression model. Specifically, the features and cluster labels of each data point (task) are substituted into the pre-trained random forest regression model. Each tree in the random forest regression model predicts the test data. The prediction results of all trees are averaged as the final result to obtain the teaching task quality score. The average of the teaching task quality scores for each auxiliary teaching is calculated as the teaching task quality index. The teaching task quality index (TTQ TTQ I) is an indicator used to evaluate the overall quality and effectiveness of teaching tasks. Assuming that the range of TTQ I is 0 to 1, the closer TTQ I is to 0, the lower the quality of the teaching task. If TTQ I is close to 0, it may mean that students have a low completion rate in auxiliary teaching tasks. Students may fail to complete the task or only partially complete the task. TTQ I close to 0 may mean that students spend too long on the task and exceed the expected time. The task design may be too complicated or students have difficulties in completing the task. Students give high difficulty scores for the task, indicating that they find the task difficult and difficult to complete. This may reflect that the task design is unreasonable and beyond the ability of students. Students give low feedback scores on the task, indicating that they are not satisfied with the task and may find the task boring, irrelevant or too difficult.

[0060] The comprehensive analysis module evaluates the usage quality of the target users based on the teaching content quality index and the teaching task quality index. Obtaining the comprehensive usage quality coefficient means: substituting the teaching content quality index and the teaching task quality index into a pre-trained machine learning model for comprehensive analysis to generate a comprehensive usage quality coefficient. The machine learning model is not specifically limited here. Any model that can perform a comprehensive analysis of the teaching content quality index and the teaching task quality index to generate a comprehensive usage quality coefficient is acceptable. In order to implement the technical solution of the present invention, the present invention provides a specific implementation method: k1 and k2 are both preset weight coefficients, both k1 and k2 are positive numbers, ZX represents the comprehensive usage quality coefficient, the larger the value is, the more the teaching content design and teaching task design when using the auxiliary teaching virtual reality equipment meet the usage needs of the target users, i.e. students, the higher the quality of the teaching content and teaching tasks, the more satisfied the students are with the usage effect.

[0061] The decision module divides the target user's usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient.

[0062] Obtain a comprehensive usage quality coefficient, preset a standard comprehensive usage quality reference threshold, compare the comprehensive usage quality coefficient with the preset standard comprehensive usage quality reference threshold, if the comprehensive usage quality coefficient is greater than or equal to the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as high-quality auxiliary teaching; if the comprehensive usage quality coefficient is less than the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as low-quality auxiliary teaching.

[0063] For low-quality auxiliary teaching, decision-making and judgment on the direction that needs to be optimized refers to:

[0064] Get the teaching content quality index, teaching task quality index, and comprehensive use quality coefficient respectively, apply fuzzy reasoning, define the teaching content quality index, teaching task quality index, and comprehensive use quality coefficient as input variables, define the output variable as the optimization direction, fuzzify the input variables, convert the values ​​of the input variables into fuzzy sets, fuzzify the output variables, convert the output variables into fuzzy sets, formulate fuzzy rules, describe the optimization requirements under different data types, and reason the fuzzified input variables through fuzzy rules to determine the direction that needs to be optimized. For example: collect the following input variables: teaching content quality index (TCQ I), teaching task quality index (TTQ I), comprehensive use quality coefficient, define the input variable fuzzy set: teaching content quality index (TCQ I): low, medium, high; teaching task quality index (TTQ I): low, medium, high; comprehensive use quality coefficient: low, medium, high; define the output variable fuzzy set: optimization direction: content optimization, task optimization, comprehensive optimization; fuzzification: convert the values ​​of the input variables into fuzzy sets. Assuming that the value range of each input variable is between 0 and 1, the membership function of the fuzzy set can be defined, for example: low: the membership function is a trigonometric function with a peak value at 0; medium: the membership function is a trigonometric function with a peak value at 0.5; high: the membership function is a trigonometric function with a peak value at 1. Fuzzy rules are formulated according to the optimization requirements under different data combinations. For example: if TCQI is low and TTQI is low and the comprehensive use quality coefficient is low, the optimization direction is comprehensive optimization. If TCQI is low and TTQI is medium or high and the comprehensive use quality coefficient is high, the optimization direction is content optimization. If TTQI is low and TCQI is medium or high and the comprehensive use quality coefficient is high, the optimization direction is task optimization. The fuzzified input variables are inferred through fuzzy rules to determine the direction that needs to be optimized.

[0065] Embodiment 2: A method for using a virtual reality device for English-assisted teaching, comprising the following steps:

[0066] When the target user uses it, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time. The difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use;

[0067] Analyze the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target users are using it;

[0068] When there is a hidden danger of insufficient effectiveness in the teaching design, the usage information of the target users is obtained, and then abnormal analysis is performed to obtain the teaching content quality index and the teaching task quality index;

[0069] Based on the teaching content quality index and teaching task quality index, the target users' usage quality is evaluated to obtain the comprehensive usage quality coefficient;

[0070] Based on the comprehensive usage quality coefficient, the target users' usage quality is divided into high-quality auxiliary teaching and low-quality auxiliary teaching. For low-quality auxiliary teaching, decisions are made on the direction that needs to be optimized, and then adaptive optimization is performed according to the preset optimization strategy.

[0071] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0072] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0073] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A virtual reality device for English-assisted teaching, characterized in that: It includes auxiliary teaching time calculation module, hidden danger analysis module, abnormality analysis module, comprehensive analysis module and decision-making module; When the target user uses the auxiliary teaching time calculation module, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time, and the difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use; The hidden danger analysis module analyzes the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target user is using it; The abnormal analysis module is used to obtain the usage information of the target users when there is a hidden danger of insufficient effectiveness in the teaching design, and then conduct abnormal analysis to obtain the teaching content quality index and the teaching task quality index; The comprehensive analysis module evaluates the usage quality of target users based on the teaching content quality index and the teaching task quality index to obtain a comprehensive usage quality coefficient; The decision-making module divides the target users' usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient, and makes decisions on the direction that needs to be optimized for low-quality auxiliary teaching.

2. The English-assisted teaching virtual reality device according to claim 1, characterized in that: The hidden danger analysis module analyzes the total duration of a single auxiliary teaching session to determine whether there are hidden dangers of insufficient effectiveness of the teaching design when the target users are using it. These are: Obtain the total duration of each auxiliary teaching use under a fixed window, and the corresponding standard total duration of the auxiliary teaching preset, and then calculate the usage time ratio of each auxiliary teaching. The usage time ratio is obtained by dividing the total duration of each auxiliary teaching use by the corresponding standard total duration of the auxiliary teaching preset. A normal usage range value is preset. If the usage time ratio falls within the normal usage range, the auxiliary teaching is marked as normal use. If the usage time ratio does not fall within the normal usage range, the auxiliary teaching is marked as abnormal use. The total number of auxiliary teaching marked as normal use and the total number of auxiliary teaching marked as abnormal use are counted, and the usage quality ratio value of the target user is calculated. The usage quality ratio value of the target user is obtained by dividing the total number of auxiliary teaching marked as abnormal use by the total number of auxiliary teaching marked as normal use. A usage quality ratio threshold is preset. If the usage quality ratio value of the target user is less than or equal to the usage quality ratio threshold, it is judged that there is no hidden danger of insufficient effectiveness of the teaching design. If the usage quality ratio value of the target user is greater than the usage quality ratio threshold, it is judged that there is a hidden danger of insufficient effectiveness of the teaching design.

3. The English-assisted teaching virtual reality device according to claim 2, characterized in that: The logic for obtaining the teaching content quality index is: Under the fixed window, feature extraction is performed on the learning time, learning feedback score, test score, and class participation rate of each auxiliary teaching use, and the collected feature data is standardized to obtain the standardized learning time, learning feedback score, test score, and class participation rate. The standardized data is constructed into a matrix X using the principal component analysis method, and then the covariance matrix Σ of the data matrix is ​​calculated: N is the number of samples, X i is the i-th sample, μ is the eigenmean vector, T represents the transpose operation of the matrix, and the eigenvalue and eigenvector of the covariance matrix are calculated: ∑v = λv; λ is the eigenvalue, and v is the corresponding eigenvector; the first k eigenvectors are selected in descending order of eigenvalue as the basis vectors of the principal component to form a projection matrix W, and the original data is projected into the principal component space to obtain the data after dimensionality reduction; Use MLP to train and predict the reduced-dimensional data, define the input layer, hidden layer, and output layer, the number of nodes in the input layer is equal to the number of principal components, the output layer is 1 node, randomly initialize the weights and biases, perform forward propagation to calculate the output, use the mean square error as the loss function, use the gradient descent method for optimization, perform back propagation to adjust the weights and biases, adjust the weights and biases through multiple iterations until the loss function converges, use the trained MLP model to predict the content quality performance of each auxiliary teaching, obtain the content quality score of each auxiliary teaching, and calculate the average of the content quality scores of all auxiliary teaching as the teaching content quality index.

4. The English-assisted teaching virtual reality device according to claim 3, characterized in that: The logic for obtaining the teaching task quality index is: Under the fixed window, feature extraction is performed on the task completion rate, task completion time, task difficulty score, and task feedback score of each auxiliary teaching use. The collected feature data is standardized to obtain the standardized task completion rate, standardized task completion time, standardized task difficulty score, and standardized task feedback score, and they are combined to obtain the combined data points. K-means clustering analysis is performed on the standardized data to identify the pattern of task performance. K cluster centers are randomly selected, and the distance from each data point to all cluster centers is calculated. Each data point is assigned to the nearest cluster center, and the mean of all data points assigned to each cluster is calculated and used as the new cluster center. The data point assignment and cluster center update are repeated until the cluster centers converge. After clustering, each data point obtains a cluster label and is then substituted into the pre-trained random forest regression model. Each tree in the random forest regression model predicts the test data, and the prediction results of all trees are averaged as the final result to obtain the teaching task quality score. The average value of the teaching task quality score for all auxiliary teaching uses is calculated as the teaching task quality index.

5. The English-assisted teaching virtual reality device according to claim 4, characterized in that: The comprehensive analysis module evaluates the usage quality of target users based on the teaching content quality index and the teaching task quality index to obtain a comprehensive usage quality coefficient, which means: substituting the teaching content quality index and the teaching task quality index into the pre-trained machine learning model for comprehensive analysis to generate a comprehensive usage quality coefficient.

6. The English-assisted teaching virtual reality device according to claim 5, characterized in that: The decision module divides the target user's usage quality into high-quality auxiliary teaching and low-quality auxiliary teaching based on the comprehensive usage quality coefficient. Obtain a comprehensive usage quality coefficient, preset a standard comprehensive usage quality reference threshold, compare the comprehensive usage quality coefficient with the preset standard comprehensive usage quality reference threshold, if the comprehensive usage quality coefficient is greater than or equal to the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as high-quality auxiliary teaching; if the comprehensive usage quality coefficient is less than the preset standard comprehensive usage quality reference threshold, then the usage quality of the target user is classified as low-quality auxiliary teaching.

7. The virtual reality device for English-assisted teaching according to claim 6, characterized in that: For low-quality auxiliary teaching, decision-making and judgment on the direction that needs to be optimized refers to: The teaching content quality index, teaching task quality index and comprehensive use quality coefficient are obtained respectively, fuzzy reasoning is applied, the teaching content quality index, teaching task quality index and comprehensive use quality coefficient are defined as input variables, the output variables are defined as the optimization direction, the input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets, the output variables are fuzzified and the output variables are converted into fuzzy sets, fuzzy rules are formulated to describe the optimization requirements under different data type combinations, the fuzzified input variables are inferred through fuzzy rules, and the direction that needs to be optimized is determined.

8. A method for using an English-assisted teaching virtual reality device, based on the English-assisted teaching virtual reality device according to any one of claims 1 to 7, characterized in that: The following steps are involved: When the target user uses it, the time of entering the auxiliary teaching is recorded as the start time, and the time of exiting the auxiliary teaching is recorded as the end time. The difference between the end time and the start time of each auxiliary teaching use is calculated to obtain the total duration of a single auxiliary teaching use; Analyze the total duration of a single auxiliary teaching session to determine whether there is a hidden danger of insufficient effectiveness of the teaching design when the target users are using it; When there is a hidden danger of insufficient effectiveness in the teaching design, the usage information of the target users is obtained, and then abnormal analysis is performed to obtain the teaching content quality index and the teaching task quality index; Based on the teaching content quality index and teaching task quality index, the target users' usage quality is evaluated to obtain the comprehensive usage quality coefficient; Based on the comprehensive usage quality coefficient, the usage quality of target users is divided into high-quality auxiliary teaching and low-quality auxiliary teaching. For low-quality auxiliary teaching, decisions are made on the direction that needs to be optimized.

Images