A teaching scene modeling method and system based on VR scene

Abstract

The present invention relates to the field of data processing, and more specifically, to a teaching scene modeling method and system based on VR scenes. The method comprises: obtaining the index value of pre-processed behavior data in a teacher sample, for the same teacher sample, taking any index value as the target index value, and taking the index value other than the target index value as the reference index value; taking the fluctuation degree of the data point in the calculated target index value as the first importance; taking the mean of the difference between the data point of the target index value and the data point of each reference index value as the second importance; calculating the comprehensive importance of the target index value, taking the comprehensive importance as the weight of the index value, and completing the teaching scene modeling through a dimensionality reduction algorithm. Through the technical solution of the present invention, the complexity of modeling can be reduced to achieve fast and realistic virtual experimental teaching component modeling and scene construction.

Description

Technical Field

[0001] The present invention relates to the field of data processing. More specifically, the present invention relates to a teaching scene modeling method and system based on VR scene. Background Art

[0002] Virtual reality technology can provide users with an immersive experience, which makes VR technology an important tool in education, training and teaching scenarios. By building a virtual three-dimensional teaching scene, students can learn in a highly simulated environment, breaking the limitations of traditional teaching methods. Not only can they learn theoretically, but they can also conduct interactive learning such as experimental operations and field trips. Especially in industries that require high precision and high simulation, such as medicine, engineering, and aerospace, VR has become an important teaching aid.

[0003] The existing Chinese patent application document with publication number CN113742886A discloses a PCA modeling evaluation method, device and electronic device based on fit. The method discretizes the hyperellipsoid corresponding to the PCA model into a series of grids of equal size; calculates the fit index between the training data and the PCA model; compares the calculated fit index with a preset threshold; and evaluates the effect of the constructed PCA model based on the comparison result, thereby avoiding the problem that the naked eye recognition method cannot solve the problem of excessive dimension of variables.

[0004] However, the above method ignores the situation that when the data set contains some less important but more discrete features, the result of the index value arrangement in the dimensionality reduction process tends to be these unimportant features with large variance, so that the reduced dimensionality data cannot effectively express the characteristics of the original data, resulting in modeling difficulties and difficulty in achieving fast and realistic virtual experimental teaching component modeling and scene construction. Summary of the invention

[0005] In order to solve the problem that it is difficult to achieve fast and realistic virtual experiment teaching component modeling and scene construction, the present invention proposes a teaching scene modeling method and system based on VR scene.

[0006] In a first aspect, the present invention discloses a teaching scene modeling method based on a VR scene, comprising: obtaining an index value of preprocessed behavior data in a teacher sample, wherein each index value includes multiple data points, and for the same teacher sample, taking any index value as a target index value, and taking index values ​​other than the target index value as reference index values; taking the fluctuation degree of the data points in the calculated target index value as a first importance degree; taking the mean of the difference between the data points of the target index value and the data points of each reference index value as a second importance degree; calculating the comprehensive importance degree of the target index value, taking the comprehensive importance degree as the weight of the index value, and completing the teaching scene modeling through a dimensionality reduction algorithm; the comprehensive importance degree satisfies the relationship:

[0007] ,in, Indicates The comprehensive importance of the index values, Indicates The first importance of the indicator value, Indicates The second most important indicator value is in the comprehensive importance relationship. The index value is the target index value.

[0008] By evaluating the fluctuation degree of the target indicator value data point (the first importance) and the mean difference between the target indicator value and other reference indicator value data points (the second importance), it can effectively reflect the influence of different indicators on the overall teaching behavior. This calculation method combines the intrinsic connection between data points and avoids the one-sidedness of relying solely on a certain indicator, thus providing a more accurate and meaningful weight distribution for the subsequent dimensionality reduction algorithm.

[0009] Preferably, the first importance level includes: constructing a coordinate system based on the data points in the target index value, calculating the coordinates of the center point of the coordinate system, and obtaining the center data point, wherein the center data point is the data point closest to the center point; respectively calculating the slope of the line connecting the center data point and each data point, and calculating the variance of all slopes; the first importance level satisfies the relationship:

[0010] ,in, Indicates The first importance of the indicator value, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Represents the normalization function. In the first importance relationship, The index value is the target index value.

[0011] It helps to fully understand the fluctuations of indicators, so that in the multi-dimensional and multi-indicator teaching behavior analysis, it is possible to more reasonably evaluate the impact of each indicator on the teaching scenario modeling, thereby improving the accuracy of the model and the effect of practical application.

[0012] Preferably, the first importance level also includes a relationship: constructing a coordinate system based on the data points in the target index value, calculating the coordinates of the center point of the coordinate system, and obtaining the center data point, wherein the center data point is the data point closest to the center point; respectively calculating the slope of the line connecting the center data point and each data point, and calculating the variance of all slopes;

[0013] ,in, Indicates The first importance of the indicator value, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The mean of the difference between the ordinates of two adjacent data points in the coordinate system constructed by the index values ​​is Represents the normalization function. In the first importance relationship, The index value is the target index value.

[0014] The distance between the center point of the coordinate system and the data point determines the distribution characteristics of the data point, while the slope variance reveals the degree of change between the data points. Secondly, by calculating the mean of the ordinate difference between adjacent data points, the local change trend between the data points can be captured. Combining this mean with the ratio of the ordinate range makes the volatility and trend change of the indicator more comprehensively reflect the stability and variability of the target indicator.

[0015] Preferably, the difference between the ordinates of two adjacent data points on the abscissa is calculated.

[0016] Preferably, obtaining the central data point includes: constructing a coordinate system of the target indicator value with the time when the data point was acquired as the horizontal axis and the normalized value of the data point as the vertical axis; taking the average of the horizontal coordinates of the first data point and the last data point in the coordinate system as the horizontal coordinate of the central point, and taking the average of the vertical coordinates of the first data point and the last data point in the coordinate system as the vertical coordinate of the central point to obtain the coordinates of the central point; respectively calculating the Euclidean distance between the central point and each data point, and taking the data point with the smallest Euclidean distance as the central data point.

[0017] The acquisition of center point data can help grasp the core features of the data set more accurately, provide a clearer and more robust understanding of data fluctuations and time series changes, and thus improve the accuracy of calculating the importance of indicators.

[0018] Preferably, the difference includes: constructing a coordinate system for the data points in the reference index value, and calculating the difference between the data points of the target index value and the data points of the reference index value:

[0019] ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is represents the normalization function. In the difference relation, The index value is the target index value.

[0020] Preferably, the difference also includes the relationship:

[0021] ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is Indicates The vertical coordinate difference sequence of the index value and the The similarity of the vertical coordinate difference sequence of the reference index values, represents the normalization function. In the difference relation, The index value is the target index value.

[0022] It avoids the limitations of single-dimensional measurement, makes the calculation of differences more comprehensive and accurate, and provides a more accurate quantification of the actual relationship between the target indicator and the reference indicator, thereby improving the accuracy and reliability of subsequent dimensionality reduction modeling.

[0023] Preferably, the ordinate difference sequence includes: calculating the ordinate difference between two adjacent data points in a coordinate system constructed with the same index value, and constructing all the differences into a ordinate difference sequence.

[0024] In a second aspect, the present invention discloses a teaching scene modeling system based on a VR scene, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned teaching scene modeling method based on a VR scene.

[0025] Beneficial effects of the present invention:

[0026] The present invention extracts the comprehensive importance of each indicator value through in-depth analysis of teacher behavior data, and uses this importance to model the teaching scene. In the process, by quantifying the fluctuation degree of the target indicator value and the difference with the reference indicator value, a weight is assigned to each indicator, and the teaching scene is modeled in combination with the dimensionality reduction algorithm, which optimizes the dynamic display effect in the teaching process.

[0027] By calculating the fluctuation degree of the target index value data point and its difference from the reference index value, the present invention can deeply explore the key behavioral characteristics in the teaching process, making the model more refined in describing teaching activities and revealing the intrinsic correlation between different teaching elements. Combined with the dimensionality reduction algorithm, the model will be able to effectively process high-dimensional teaching data, and then present a more reasonable and accurate teaching environment in the VR scene. At the same time, by calculating the comprehensive importance of each indicator, the rationality of the teaching scene modeling and the emphasis on key indicators are further guaranteed, so that the entire teaching process can more intuitively and effectively reflect the teacher's behavior pattern and its impact on learners. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0029] Figure 1 It is a flow chart of a teaching scene modeling method based on a VR scene according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0032] The present invention provides a teaching scene modeling method based on VR scene. Figure 1 As shown, a teaching scene modeling method based on VR scene includes steps S1 to S4, which are described in detail below.

[0033] S1, obtain the indicator values ​​of the preprocessed behavioral data in the teacher sample.

[0034] In one embodiment, the index value of the pre-processed behavior data in the teacher sample is obtained. For example, the index value of the behavior data is the interactive operation of the teacher in the virtual scene, including click, drag, voice command, gesture operation, etc. Each index value contains multiple data points.

[0035] The preprocessing of the indicator values ​​of behavioral data includes: importing the collected data into the Python environment and saving it in the form of a data frame through the Pandas library, where each teacher corresponds to a data frame, each row of the data frame represents the time corresponding to the teacher's behavioral data, and each column represents each data type. Finally, these data are saved in a file with a custom name for subsequent calls.

[0036] According to the distribution characteristics of the data, the data is cleaned. The data is visualized by calling the Matplotlib library, outliers are detected by drawing box plots, and the outliers are replaced by the average value of the same type of data as the outliers. Interpolation is used to fill in missing values ​​in the data frame and delete duplicate values.

[0037] The data were normalized to ensure that variables of different dimensions were more comparable during the analysis.

[0038] According to the above operation, the data in the data frame corresponding to each teacher in the city after preprocessing is obtained, which is recorded as the original data. Among them, the Pandas library and Matplotlib library, box plot, interpolation method, normalization processing, etc. in the Python environment are all existing technologies and will not be repeated here.

[0039] S2, taking the fluctuation degree of the data points in the calculated target index value as the first importance degree.

[0040] In one embodiment, for the same teacher sample, any indicator value is used as the target indicator value, and the indicator values ​​other than the target indicator value are used as reference indicator values.

[0041] Construct a coordinate system based on the data points in the target indicator value, calculate the coordinates of the center point of the coordinate system, and obtain the center data point. Obtaining the center data point includes:

[0042] A coordinate system for the target indicator value is constructed with the time when the data points were obtained as the horizontal axis and the normalized values ​​of the data points as the vertical axis; the coordinates of the center point are obtained by taking the average of the horizontal coordinates of the first and last data points in the coordinate system as the horizontal coordinate of the center point and the average of the vertical coordinates of the first and last data points in the coordinate system as the vertical coordinate of the center point; the Euclidean distance between the center point and each data point is calculated respectively, and the data point with the smallest Euclidean distance is taken as the center data point.

[0043] Calculate the slope of the line connecting the central data point and each data point separately, and calculate the variance of all slopes.

[0044] The first importance level satisfies the relationship:

[0045] ,in, Indicates The first importance of the indicator value, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Represents the normalization function. In the first importance relationship, The index value is the target index value.

[0046] The distance relationship between the center point of the constructed coordinate system and the data points reveals the distribution characteristics of the data, while the calculated slope variance further quantifies the degree of data fluctuation, reflecting the change pattern between data points. The range of the ordinate captures the span of the data points in the vertical direction. By normalizing these metrics, the influence of different data ranges can be eliminated, making the results more universal and comparable. Finally, the calculation of the first importance combines the slope variance and the ordinate range, reflecting the stability and range of change of the target indicator value, thereby providing a more accurate weight distribution for the subsequent calculation of the comprehensive importance.

[0047] It helps to fully understand the fluctuations of indicators, so that in the multi-dimensional and multi-indicator teaching behavior analysis, it is possible to more reasonably evaluate the impact of each indicator on the teaching scenario modeling, thereby improving the accuracy of the model and the effect of practical application.

[0048] In another embodiment, the first importance level further includes the relationship:

[0049] ,in, Indicates The first importance of the indicator value, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The mean of the difference between the ordinates of two adjacent data points in the coordinate system constructed by the index values ​​is Represents the normalization function. In the first importance relationship, The index value is the target index value.

[0050] By further introducing the mean of the ordinate difference between adjacent data points and the ratio of the ordinate range, the assessment of the volatility and trend of the target indicator value data is enhanced.

[0051] Among them, for the target indicator value, the horizontal axis is time, each moment corresponds to a normalized value of a data point, and calculating the difference between the vertical coordinates of two adjacent data points is to calculate the difference between the vertical coordinates of two adjacent data points on the horizontal axis.

[0052] For example, the value corresponding to the first moment is 0.3, the value corresponding to the second moment is 0.8, the value corresponding to the third moment is 0.9, the value corresponding to the fourth moment is 0.4, and the value corresponding to the fifth moment is 0.9. Then the difference between the vertical coordinates of two adjacent data points is -0.5, -0.1, 0.5, and -0.5 respectively.

[0053] S3, taking the mean of the difference between the data point of the target index value and the data point of each reference index value as the second importance.

[0054] It should be noted that the effect of considering the differences between indicator values ​​is: on the one hand, considering the changes in each indicator value alone will ignore the impact of other indicator values. By comparing with other indicator values, the relative importance of each indicator value in the overall impact can be more clearly seen; on the other hand, there may be interactions or correlations between different indicator values. By comparing the changes in different indicator values, the mutual influence between indicator values ​​can be reflected, thereby more accurately evaluating their contribution to the final result.

[0055] In one embodiment, according to step S2, a coordinate system is constructed for the data points in the reference index value, and the difference between the data points of the target index value and the data points of the reference index value is calculated:

[0056] ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is represents the normalization function. In the difference relation, The index value is the target index value.

[0057] In another embodiment, in a coordinate system constructed with the same index value, the vertical coordinate difference between two adjacent data points is calculated, and all the differences are constructed into a vertical coordinate difference sequence.

[0058] The differences also include the relationship:

[0059] ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is Indicates The vertical coordinate difference sequence of the index value and the The similarity of the vertical coordinate difference sequence of the reference index values, represents the normalization function. In the difference relation, The index value is the target index value.

[0060] For example, the similarity can be cosine similarity, Euclidean distance, Manhattan distance, etc. The present invention adopts cosine similarity. 0.00001 is to avoid the denominator being 0.

[0061] S4, calculate the comprehensive importance of the target indicator value, use the comprehensive importance as the weight of the indicator value, and complete the teaching scenario modeling through the dimensionality reduction algorithm.

[0062] In one embodiment, the comprehensive importance of the target indicator value is calculated:

[0063] ,in, Indicates The comprehensive importance of the index values, Indicates The first importance of the indicator value, Indicates The second most important indicator value is in the comprehensive importance relationship. The index value is the target index value.

[0064] The comprehensive importance is used as the weight of the index value, and data modeling is completed through a dimensionality reduction algorithm. For example, the dimensionality reduction algorithm can use principal component analysis, linear discriminant analysis, singular value decomposition, and local linear embedding.

[0065] An embodiment of the present invention further discloses a teaching scene modeling system based on a VR scene, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a teaching scene modeling method based on a VR scene according to the present invention is implemented.

[0066] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0067] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0068] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0069] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A teaching scene modeling method based on VR scene, characterized in that: include: Obtaining the index values ​​of the preprocessed behavior data in the teacher sample, wherein each index value includes multiple data points, and for the same teacher sample, taking any index value as the target index value, and taking the index values ​​other than the target index value as the reference index value; The fluctuation degree of the data points in the calculated target index value is taken as the first importance degree; The mean of the difference between the target index value data point and each reference index value data point is taken as the second importance level; Calculate the comprehensive importance of the target indicator value, use the comprehensive importance as the weight of the indicator value, and complete the teaching scenario modeling through the dimensionality reduction algorithm; The comprehensive importance satisfies the relationship: ,in, Indicates The comprehensive importance of the index values, Indicates The first importance of the indicator value, Indicates The second most important indicator value is in the comprehensive importance relationship. The index value is the target index value; The first level of importance includes: A coordinate system is constructed based on the data points in the target index value, and the coordinates of the center point of the coordinate system are calculated to obtain the center data point, wherein the center data point is the data point closest to the center point; Calculate the slope of the line connecting the central data point and each data point respectively, and calculate the variance of all slopes; The first importance level satisfies the relationship: ,in, Indicates The first importance of the indicator value, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Represents the normalization function. In the first importance relationship, The indicator value is the target indicator value; or, The first importance level satisfies the relationship: ,in, Indicates The mean of the difference between the ordinates of two adjacent data points in the coordinate system constructed by the index values.

2. A teaching scene modeling method based on VR scene according to claim 1, characterized in that: Calculate the difference between the vertical coordinates of two adjacent data points on the horizontal axis.

3. A teaching scene modeling method based on VR scene according to claim 1 or 2, characterized in that: The obtaining of the central data point comprises: The coordinate system of the target indicator value is constructed with the time when the data point is obtained as the horizontal axis and the normalized value of the data point as the vertical axis; The mean of the horizontal coordinates of the first data point and the last data point in the coordinate system is used as the horizontal coordinate of the center point, and the mean of the vertical coordinates of the first data point and the last data point in the coordinate system is used as the vertical coordinate of the center point to obtain the coordinates of the center point; Calculate the Euclidean distance between the center point and each data point respectively, and take the data point with the smallest Euclidean distance as the center data point.

4. The teaching scene modeling method based on VR scene according to claim 1 is characterized in that: The differences include: Construct a coordinate system for the data points in the reference index value, and calculate the difference between the data points of the target index value and the data points of the reference index value: ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is represents the normalization function. In the difference relation, The index value is the target index value.

5. The teaching scene modeling method based on VR scene according to claim 1, characterized in that: The differences also include the relationship: ,in, Indicates The data points of the indicator value and The difference of the data points of the reference index values, Indicates The variance of the normalized slope in the coordinate system constructed by the index values, Indicates In the coordinate system constructed by the index value, the range of the vertical coordinates of all data points is Indicates The variance of the normalized slope in the coordinate system constructed by the reference index value, Indicates The range of the vertical coordinates of all data points in the coordinate system constructed by the reference index value is Indicates The vertical coordinate difference sequence of the index value and the The similarity of the vertical coordinate difference sequence of the reference index values, represents the normalization function. In the difference relation, The index value is the target index value.

6. A teaching scene modeling method based on VR scene according to claim 5, characterized in that: The vertical coordinate difference sequence includes: In the coordinate system constructed with the same indicator value, the vertical coordinate difference between two adjacent data points is calculated, and all the differences are constructed into a vertical coordinate difference sequence.

7. A teaching scene modeling system based on VR scene, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a teaching scene modeling method based on a VR scene according to any one of claims 1 to 6.

Images