A high school VR teacher training simulation teaching data quantification evaluation method and system

Abstract

The present application relates to the technical field of wisdom teaching, disclose a kind of university VR teacher training simulation teaching data quantification evaluation method and system, the method includes: the teaching behavior data of teacher is carried out multimodal feature fusion, obtains teaching behavior feature;Teaching behavior feature is carried out semantic network reconfiguration, obtains teaching behavior feature atlas;According to the node attribute of teaching behavior feature atlas, teaching behavior feature atlas is carried out feature dimension mapping, obtains teaching ability quantitative index;The dynamic evolution law of teaching ability quantitative index is analyzed, obtains the change trend of teaching ability quantitative index;Teaching ability quantitative index is carried out stage trajectory fitting, obtains teaching ability development trajectory;Integrate teaching ability quantitative index and teaching ability development trajectory, generate comprehensive quantitative evaluation index;The present application can improve the efficiency of a kind of university VR teacher training simulation teaching data quantification evaluation.

Description

Technical Field

[0001] This invention relates to the field of smart teaching technology, and in particular to a method and system for quantitative evaluation of simulated teaching data in VR teacher training for universities. Background Technology

[0002] In the field of quantitative evaluation of simulated teaching data for VR teacher training in universities, existing technologies have significant shortcomings in processing and extracting features from teaching behavior data. Current methods struggle to effectively fuse and semantically align multimodal teaching behavior data generated in VR scenarios, often resulting in incomplete feature extraction or failure to remove redundant features. This leads to the acquired teaching behavior features failing to comprehensively and accurately reflect the teacher's actual teaching performance. Furthermore, existing technologies lack the ability to perform semantic association analysis and network reconstruction of teaching behavior features, making it impossible to construct effective feature maps. This results in a lack of reliable data support for the subsequent calculation of quantitative indicators of teaching ability, compromising the accuracy and objectivity of the evaluation results.

[0003] Furthermore, existing technologies have significant shortcomings in the dynamic assessment and comprehensive indicator generation of teaching ability. Traditional assessment methods often focus on calculating static quantitative indicators, neglecting the dynamic evolution of teaching ability as training progresses. They fail to capture the changing trends and stage characteristics of indicators, making it difficult to generate the development trajectory of teachers' teaching abilities. Consequently, the assessment results only reflect the instantaneous teaching level and cannot provide a basis for long-term training effectiveness monitoring. Simultaneously, when integrating quantitative indicators and development trajectories to generate comprehensive assessment results, existing technologies do not scientifically handle the differences in dimensions and weight allocation, easily leading to distortion of comprehensive indicators. This makes it difficult to accurately match teaching ability assessment standards and meet the scientific and practical needs of VR teacher training in universities. Therefore, how to improve the accuracy, dynamism, and comprehensiveness of quantitative assessment of simulated teaching data in VR teacher training in universities has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for quantitative evaluation of simulated teaching data in VR teacher training for universities, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, this invention provides a method for quantitative evaluation of simulated teaching data in VR teacher training for universities, comprising:

[0006] S1. Perform multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data;

[0007] S2. Perform semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features;

[0008] S3. Based on the node attributes of the teaching behavior feature map, perform feature dimension mapping on the teaching behavior feature map to obtain the quantitative indicators of the teacher's teaching ability.

[0009] S4. Analyze the dynamic evolution of the quantitative indicators of teaching ability to obtain the changing trend of the quantitative indicators of teaching ability.

[0010] S5. Based on the key characteristics of the changing trend, perform stage trajectory fitting on the quantitative indicators of teaching ability to obtain the teacher's teaching ability development trajectory.

[0011] S6. Integrate the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate a comprehensive quantitative evaluation index for the teacher.

[0012] In a preferred embodiment, the step of performing multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data includes:

[0013] Obtain data on teachers' teaching behaviors;

[0014] Extract speech features from the original speech waveforms in the teaching behavior data;

[0015] Track the skeletal keypoint data of the teaching behavior data to obtain the teacher's posture characteristics;

[0016] The interaction frequency, response time, and interaction depth of the teaching behavior data are extracted to obtain the teacher's interaction characteristics;

[0017] Semantic alignment is performed on the speech features, gesture features, and interaction features to obtain the teacher's preliminary teaching behavior features;

[0018] Redundant features of the preliminary teaching behavior characteristics are removed to obtain the teaching behavior characteristics of the teaching behavior data.

[0019] In a preferred embodiment, the step of performing semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features includes:

[0020] Perform semantic association analysis on the teaching behavior features to generate a feature similarity matrix of the teaching behavior features;

[0021] Based on the correlation strength in the feature similarity matrix, when the correlation strength reaches a preset threshold, a connection relationship is established between the relevant features of the teaching behavior features;

[0022] Using the relevant features as nodes and the connection relationships as connecting edges, an initial feature map of the teaching behavior features is constructed;

[0023] Semantic relation enhancement is performed on the initial feature map to obtain an optimized feature map.

[0024] Verify the connectivity of the optimized feature map to confirm the teaching behavior feature map of the teaching behavior features.

[0025] In a preferred embodiment, the step of performing semantic association analysis on the teaching behavior features to generate a feature similarity matrix of the teaching behavior features includes:

[0026] The teaching behavior features are numerically processed while retaining their semantic information to obtain feature vectors.

[0027] Based on the distribution characteristics of the feature vectors, construct the semantic space framework of the feature vectors;

[0028] Within the semantic space framework, the relative positions and distribution patterns of the feature vectors are analyzed to obtain the similarity relationship data of the feature vectors.

[0029] The similarity relationship data is organized into a matrix structure to obtain the feature similarity matrix of the teaching behavior features.

[0030] In a preferred embodiment, the step of mapping the teaching behavior feature map to feature dimensions based on the node attributes of the teaching behavior feature map to obtain the teacher's quantitative teaching ability index includes:

[0031] Collect the node attribute parameters of the teaching behavior feature map;

[0032] Based on the semantic relevance of the node attribute parameters, the node attribute parameters are semantically associated and classified to obtain the dimensional grouping data of the node attribute parameters;

[0033] The dimensional grouped data is mapped into a vector space to obtain the dimensional feature vectors of the dimensional grouped data.

[0034] Based on the preset feature weight configuration, the quantization score of the dimensional feature vector is calculated, wherein the calculation formula for the quantization score is as follows: ;

[0035] In the formula, This represents the quantized score of the feature vector of the stated dimension. Indicates the first Weight coefficients of each dimension of the feature vector. The dimensional feature vector represents the first... Each component value This represents the Sigmoid activation function. Represents the dimensional feature vector of the th dimension Historical mean of each component, This represents the preset information entropy adjustment coefficient. Represents the dimensional feature vector Information entropy This represents the number of dimensions in the dimensional feature vector. This represents the summation operation. This represents the square root operation;

[0036] The quantitative score is mapped to a preset teaching ability assessment standard to obtain the teacher's quantitative teaching ability index.

[0037] In a preferred embodiment, analyzing the dynamic evolution of the quantitative indicators of teaching ability to obtain the changing trends of the quantitative indicators of teaching ability includes:

[0038] The quantitative indicators of teaching ability are organized sequentially to obtain a time-series indicator sequence of the quantitative indicators of teaching ability.

[0039] Dynamic pattern analysis is performed on the time series indicator sequence to obtain the trend pattern of the time series indicator sequence;

[0040] Based on the trend pattern, the quantitative indicators of teaching ability are synthesized to obtain the changing trend of the quantitative indicators of teaching ability.

[0041] In a preferred embodiment, the step of fitting the quantitative indicators of teaching ability to a stage trajectory based on the key characteristics of the changing trend to obtain the teacher's teaching ability development trajectory includes:

[0042] Extract the key features of the changing trend;

[0043] Based on the time distribution and feature intensity of the key features, the teaching ability quantitative index is serialized into a state sequence to obtain the evolution state sequence of the teaching ability quantitative index.

[0044] Based on the logical associations between states in the evolution state sequence, establish the connection relationships between the states;

[0045] Using the states in the evolution state sequence as trajectory nodes and the connection relationships as connecting edges, a basic trajectory framework for the quantitative indicators of teaching ability is constructed.

[0046] Segmented trajectory interpolation is performed on the basic trajectory framework to obtain segmented trajectory fragments of the basic trajectory framework;

[0047] The teacher's teaching ability development trajectory is obtained by smoothing the transition bands of the segmented trajectory segments.

[0048] In a preferred embodiment, the step of smoothing the transition bands of the segmented trajectory segments to obtain the teacher's teaching ability development trajectory includes:

[0049] Based on the connection point characteristics of the segmented trajectory segments, the transition zone region of the segmented trajectory segments is identified;

[0050] Curvature continuity optimization is performed on the trajectory points within the transition zone region to obtain the smooth trajectory of the segmented trajectory fragment;

[0051] Verify the smoothness of the smooth trajectory to confirm the teacher's teaching ability development trajectory.

[0052] In a preferred embodiment, the step of integrating the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate the comprehensive quantitative evaluation indicators for teachers includes:

[0053] Based on the target requirements of the teaching ability assessment standards, configure the weight coefficients of the quantitative indicators of teaching ability and the development trajectory of teaching ability;

[0054] Based on the weighting coefficients, the quantitative indicators of teaching ability and the development trajectory of teaching ability are fused to obtain the teacher's preliminary comprehensive indicators.

[0055] By eliminating the influence of the dimensions of the preliminary comprehensive indicators, the comprehensive quantitative evaluation indicators for the teachers are obtained.

[0056] To address the aforementioned problems, the present invention also provides a quantitative evaluation system for simulated teaching data in VR teacher training programs for higher education institutions, the system comprising:

[0057] The multimodal feature fusion module is used to perform multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data;

[0058] The semantic network reconstruction module is used to perform semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features;

[0059] The feature dimension mapping module is used to perform feature dimension mapping on the teaching behavior feature map based on the node attributes of the teaching behavior feature map to obtain the quantitative indicators of the teacher's teaching ability.

[0060] The dynamic evolution analysis module is used to analyze the dynamic evolution law of the quantitative indicators of teaching ability and obtain the changing trend of the quantitative indicators of teaching ability.

[0061] The stage trajectory fitting module is used to fit the stage trajectory of the quantitative indicators of teaching ability based on the key characteristics of the changing trend, so as to obtain the teaching ability development trajectory of the teacher.

[0062] The comprehensive evaluation index generation module is used to integrate the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate comprehensive quantitative evaluation indicators for teachers.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] 1. This invention utilizes multimodal feature fusion and semantic network reconstruction technology to comprehensively extract effective information from teachers' teaching behavior data and accurately generate teaching behavior feature maps. It integrates multi-dimensional features such as speech, posture, and interaction while eliminating redundant information, ensuring the completeness and accuracy of teaching behavior features. Simultaneously, it constructs closely related feature maps based on feature similarity matrices, providing reliable data support for quantitative indicators of teaching ability, significantly improving the matching degree between quantitative indicators and teachers' actual teaching abilities, and enhancing the objectivity and accuracy of evaluation results.

[0065] 2. This invention, through dynamic evolution analysis and stage trajectory fitting, can clearly present the changing trends and development trajectories of quantitative indicators of teaching ability, enabling dynamic monitoring and long-term tracking of teachers' teaching abilities. Furthermore, through scientific weighting and dimensional elimination processing, the indicators and trajectories are integrated to generate accurate comprehensive quantitative evaluation indicators. This not only intuitively reflects the process of teachers' ability improvement in VR training but also provides a clear direction for optimizing training programs, effectively enhancing the scientific rigor and practicality of VR teacher training evaluation in universities, and contributing to the efficient cultivation of high-quality teachers. Attached Figure Description

[0066] Figure 1 A flowchart illustrating a method for quantitative evaluation of simulated teaching data in VR teacher training at universities, provided as an embodiment of the present invention;

[0067] Figure 2 A functional module diagram of a VR teacher training simulation teaching data quantitative evaluation system for universities, provided in an embodiment of the present invention;

[0068] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0069] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0070] This application provides a method for quantitatively evaluating simulated teaching data in VR teacher training for universities. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for quantitatively evaluating simulated teaching data in VR teacher training for universities can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0071] Reference Figure 1 The diagram shown is a flowchart illustrating a method for quantitatively evaluating simulated teaching data in VR teacher training for universities, according to an embodiment of the present invention. In this embodiment, the method includes:

[0072] S1. Perform multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data;

[0073] In this embodiment of the invention, the step of performing multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data includes:

[0074] Obtain data on teachers' teaching behaviors;

[0075] Extract speech features from the original speech waveforms in the teaching behavior data;

[0076] Track the skeletal keypoint data of the teaching behavior data to obtain the teacher's posture characteristics;

[0077] The interaction frequency, response time, and interaction depth of the teaching behavior data are extracted to obtain the teacher's interaction characteristics;

[0078] Semantic alignment is performed on the speech features, gesture features, and interaction features to obtain the teacher's preliminary teaching behavior features;

[0079] Redundant features of the preliminary teaching behavior characteristics are removed to obtain the teaching behavior characteristics of the teaching behavior data.

[0080] When acquiring teachers' teaching behavior data, the built-in data acquisition module of the university VR teacher training simulation teaching system captures all behavior-related data of teachers in the VR teaching scene in real time, including voice data, body movement data and interaction data with virtual teaching objects or virtual teaching scenes generated by teachers during the teaching process. This data is stored in the system database in a structured format to ensure that the teaching behavior data required for subsequent processing is complete and accessible.

[0081] When extracting speech features from the raw speech waveforms in teaching behavior data, the stored raw speech waveform data is first preprocessed to remove background noise. Then, the speech waveforms are processed frame by frame using a speech signal analysis tool to extract features such as frequency, amplitude, speech rate, and speech pause intervals for each frame. These extracted features are then integrated to form the teacher's speech features and stored in the feature database.

[0082] When tracking skeletal key point data of teaching behavior to obtain the teacher's posture characteristics, the motion capture equipment equipped in the VR system is used to locate the key skeletal nodes of the teacher's body in real time, including nodes such as head, neck, shoulders, elbows, wrists, hips, knees, and ankles. The three-dimensional coordinate changes of each key node in the VR scene are recorded. Based on these coordinate changes, the teacher's limb movement range, movement continuity, and body language expression state are analyzed, and these analysis results are integrated to form the teacher's posture characteristics.

[0083] When extracting features from the interaction frequency, response time, and interaction depth of teaching behavior data to obtain the teacher's interaction characteristics, the interaction frequency is determined by first counting the number of times the teacher interacts with virtual teaching objects or virtual teaching scenarios per unit of time; then, the time interval from when the virtual teaching scenario or virtual teaching object issues an interaction request to when the teacher responds is recorded, and the average response time is calculated; at the same time, the completeness of the content of each teacher's interaction, the degree to which the interaction request is met, and the guidance in the interaction process are analyzed to determine the interaction depth. The relevant data of interaction frequency, response time, and interaction depth are integrated to form the teacher's interaction characteristics.

[0084] When semantically aligning speech features, posture features, and interaction features, a unified semantic reference system is first established to clarify the semantic correspondence between the three features in the description of teaching behavior. For example, the semantic association between "questioning tone" in speech features and "gesture pointing action" in posture features, and "interaction in response to questions" in interaction features is established. Then, based on this semantic reference system, the time dimension and descriptive dimension of the three features are adjusted to ensure that the three features are consistent in terms of time nodes and semantic expression, thus forming the teacher's preliminary teaching behavior features.

[0085] When eliminating redundant features in the preliminary teaching behavior characteristics, first analyze the correlation between the features in the preliminary teaching behavior characteristics, identify features that repeatedly describe the same teaching behavior and features that have no substantial impact on the assessment of teaching ability. For example, if the preliminary characteristics contain both "hand raising range" and "upper limb raising range" and the descriptions of the two are highly overlapping, then retain the more representative "upper limb raising range" feature and delete the "hand raising range" feature. After screening, the teaching behavior characteristics of the teaching behavior data are obtained.

[0086] Acquire teachers' teaching behavior data, including skeletal key point trajectory data, raw voice waveform data, and interactive behavior record data collected in VR teaching scenarios, including the number of interaction triggers, response time, and interaction content relevance score.

[0087] Speech features were extracted from the raw speech waveforms in the teaching behavior data, including speech rate, logical pause intervals, volume fluctuation amplitude, and speech intelligibility score, and were calculated using Mel-frequency cepstral coefficients. These speech features directly reflect the teacher's language expression and classroom communication abilities. For example, a speech rate that is stable at 50 to 70 words per minute and a logical pause interval that matches the knowledge point division with a degree of no less than 80% indicates good teaching language organization skills.

[0088] By tracking skeletal key point data of teaching behavior, with core nodes including the head, neck, shoulders, elbows, wrists, hips, knees, and ankles, and calculating the changes in the three-dimensional coordinates of these nodes, the continuity of movement, and the accuracy of pointing, the teacher's postural characteristics are obtained. These postural characteristics directly reflect the teacher's body expression and classroom demonstration ability. For example, when demonstrating experimental operations, if the fluctuation range of the hand nodes does not exceed 5 degrees and the pointing deviation angle does not exceed 3 degrees, it indicates that the teaching operation demonstration meets the standard.

[0089] The interaction frequency, response time, and interaction depth of teaching behavior data are used to extract teacher interaction characteristics. These characteristics directly reflect the teacher's classroom interaction and emergency response capabilities. For example, an interaction frequency of no less than 0.5 times / minute within 10 minutes, an average response time of no more than 2 seconds, and an interaction depth score of no less than 7 points indicate a strong ability to guide teaching interaction.

[0090] Semantic alignment is performed on speech features, posture features, and interaction features. Based on the timestamp synchronization of the collection nodes of the three types of features, a semantic association mapping table of speech, posture, and interaction is established to obtain the preliminary teaching behavior features of teachers.

[0091] A feature filtering algorithm based on mutual information is used to remove redundant features with mutual information values ​​of not less than 0.8 from the preliminary teaching behavior features, i.e. features that repeatedly reflect the same teaching ability, to obtain the teaching behavior features of the teaching behavior data.

[0092] Taking the VR teacher training course "University Physics Experiment - Circuit Connection" in colleges and universities as an example, teaching behavior data of Teacher A was collected. Regarding skeletal data, the 3D coordinate changes of key points in the hand, wrist, and fingertips did not exceed 4 degrees, the motion continuity coefficient was 0.92, and the deviation angle pointing to circuit components did not exceed 2 degrees, corresponding to a posture feature quantification value of 8.6 points, reflecting a high level of experimental operation demonstration ability. Regarding voice data, the speech rate was 62 words / minute, the average logical pause interval was 1.1 seconds, perfectly matching the circuit connection steps, the volume fluctuation did not exceed 3dB, and the voice clarity score was 9.1 points, corresponding to a voice feature quantification value of 8.8 points, reflecting good language expression clarity and logical organization ability. Regarding interaction data, the teacher initiated 7 interactions within 10 minutes, with an interaction frequency of 0.7 times / minute, an average response time of 1.6 seconds to answer virtual student questions, an interaction depth score of 8.3 points, and 80% of responses guided students to correct operational deviations, corresponding to an interaction feature quantification value of 8.2 points, reflecting strong interactive guidance and emergency feedback capabilities. After semantic alignment and redundancy removal, the teaching behavior characteristics of Teacher A were finally obtained, which included three categories of directly assessable teaching abilities: core quantitative experimental operation demonstration ability, language expression and communication ability, and classroom interaction and emergency feedback ability.

[0093] The beneficial effect is that through the above-mentioned multi-step implementation, speech features, posture features, and interaction features can be extracted comprehensively and accurately from teachers' teaching behavior data. By semantic alignment and redundant feature removal, complete, accurate, and non-redundant teaching behavior features are obtained, providing a high-quality data foundation for the subsequent construction of teaching behavior feature maps and the generation of quantitative indicators of teaching ability, ensuring the reliability and accuracy of subsequent evaluation processes.

[0094] S2. Perform semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features;

[0095] In this embodiment of the invention, the step of performing semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features includes:

[0096] Perform semantic association analysis on the teaching behavior features to generate a feature similarity matrix of the teaching behavior features;

[0097] Based on the correlation strength in the feature similarity matrix, when the correlation strength reaches a preset threshold, a connection relationship is established between the relevant features of the teaching behavior features;

[0098] Using the relevant features as nodes and the connection relationships as connecting edges, an initial feature map of the teaching behavior features is constructed;

[0099] Semantic relation enhancement is performed on the initial feature map to obtain an optimized feature map.

[0100] Verify the connectivity of the optimized feature map to confirm the teaching behavior feature map of the teaching behavior features.

[0101] The step of performing semantic association analysis on the teaching behavior features to generate a feature similarity matrix of the teaching behavior features includes:

[0102] The teaching behavior features are numerically processed while retaining their semantic information to obtain feature vectors.

[0103] Based on the distribution characteristics of the feature vectors, construct the semantic space framework of the feature vectors;

[0104] Within the semantic space framework, the relative positions and distribution patterns of the feature vectors are analyzed to obtain the similarity relationship data of the feature vectors.

[0105] The similarity relationship data is organized into a matrix structure to obtain the feature similarity matrix of the teaching behavior features.

[0106] When quantifying teaching behavior features while preserving semantic information to obtain feature vectors, firstly, set corresponding quantification rules for the attributes of each teaching behavior feature. For example, convert speech rate into specific values ​​according to "words per minute" and action amplitude into specific values ​​according to "range of limb movement angles". At the same time, label each quantified value with a corresponding semantic description to ensure that the semantic information of the feature is preserved after quantification. Store each processed teaching behavior feature in the form of a vector containing quantified values ​​and semantic annotations to obtain the feature vector of the teaching behavior feature.

[0107] When constructing a semantic space framework based on the distribution characteristics of feature vectors, we first statistically analyze the distribution range and frequency of each dimension of all feature vectors to determine the feature performance of each feature vector in the numerical dimension. Then, based on the semantic annotations of each feature vector, feature vectors with the same or similar semantic types are grouped into the same semantic category. For example, feature vectors with semantic annotations such as "speech rate" and "speech pause interval" are grouped into the "speech semantic category", and feature vectors with semantic annotations such as "action amplitude" and "action continuity" are grouped into the "gesture semantic category". Based on these semantic categories and the numerical distribution of feature vectors, a spatial structure containing semantic category dimensions and numerical distribution dimensions is constructed to form the semantic space framework of feature vectors.

[0108] When analyzing the relative positions and distribution patterns of feature vectors within a semantic space framework to obtain similarity relationship data, each feature vector is first mapped to its corresponding position within the semantic space framework. By observing the attribution of different feature vectors in the semantic category dimension and their distance in the numerical distribution dimension, the degree of correlation between feature vectors is determined. For example, if two feature vectors belong to the same "speech semantic category" and their distance in the numerical distribution dimension is less than a preset distance range, they are considered to have high similarity. If two feature vectors belong to different semantic categories and their numerical distribution distance is large, they are considered to have low similarity. The similarity determination results between all feature vectors are organized in the form of paired records to obtain the similarity relationship data of feature vectors.

[0109] When organizing similarity relationship data into a matrix structure to obtain a feature similarity matrix, first determine that the rows and columns of the matrix correspond to the feature vectors of all teaching behavior features, and each element position in the matrix corresponds to a pair of feature vectors. Then, fill the similarity results of each pair of feature vectors in the similarity relationship data into the corresponding element positions in the matrix. For example, if feature vector A corresponds to the first row of the matrix and feature vector B corresponds to the second column of the matrix, then fill the similarity results of A and B into the element of the first row and second column of the matrix. Fill all similarity relationship data into the matrix one by one in this way to form the feature similarity matrix of teaching behavior features.

[0110] When generating a feature similarity matrix by performing semantic association analysis on teaching behavior features, the process first executes the entire workflow described above: quantifying the teaching behavior features to obtain feature vectors, constructing a semantic space framework, analyzing the similarity of feature vectors to obtain similarity relationship data, and organizing the matrix structure to obtain the feature similarity matrix. This workflow fully explores the semantic associations between teaching behavior features and ultimately generates a feature similarity matrix that reflects the strength of the associations between each feature.

[0111] When establishing a connection between related features based on the correlation strength in the feature similarity matrix, if the correlation strength reaches a preset threshold, the correlation strength value corresponding to each element in the feature similarity matrix is ​​first read and compared with the preset correlation strength threshold. If the correlation strength value corresponding to a certain element is greater than or equal to the preset threshold, the two teaching behavior features corresponding to that element are determined to be related features. Then, a connection record representing the correlation relationship is established between the two related features. The record contains the identifiers of the two related features and the corresponding correlation strength information, thus completing the establishment of the connection relationship.

[0112] When constructing an initial feature graph of teaching behavior features using relevant features as nodes and connection relationships as connecting edges, all teaching behavior features identified as relevant features are first treated as independent nodes. Each node is labeled with its corresponding feature name and core attributes. Then, the previously established connection relationships are used as connecting edges. The two relevant feature nodes corresponding to each connecting edge are connected, and the corresponding association strength information is labeled on the connecting edges. According to this correspondence between nodes and edges, nodes and connecting edges are added one by one on the graph construction platform to form an initial feature graph that can intuitively display the association relationships between teaching behavior features. When enhancing the semantic relationships of the initial feature map to obtain the optimized feature map, the semantic annotations and attributes of each node in the initial feature map are first analyzed to identify potential indirect semantic relationships between nodes. For example, if node A is directly connected to node B, node B is directly connected to node C, and nodes A and C are semantically related to "interaction-related features", then a supplementary connection edge representing the indirect relationship is added to nodes A and C. At the same time, the semantic basis of the indirect relationship is supplemented and annotated. Then, the completeness of the association strength annotation of the connection edge in the initial map is checked, and missing or inaccurate annotations are corrected. After supplementing the association and correcting the annotations, the optimized feature map of the initial feature map is obtained.

[0113] When verifying the connectivity of the optimized feature graph to confirm the teaching behavior feature graph, first check whether all nodes in the optimized feature graph can form a connected whole through connecting edges. That is, starting from any node, by traversing along the connecting edges, all other nodes in the graph can be reached. If an isolated node that cannot be connected is found, the correlation strength between the isolated node and other nodes is analyzed. If the correlation strength between the isolated node and a certain node is close to a preset threshold, the correlation between the two is re-evaluated and attempts are made to add connecting edges. If the isolated node does not have any correlation features that meet the threshold, it is marked separately and the reason is recorded. If all nodes can form a connected structure or the isolated nodes have been properly handled, the optimized feature graph is confirmed as the final teaching behavior feature graph.

[0114] The beneficial effect is that, through the above specific implementation process, the semantic network reconstruction of teaching behavior features can be completed systematically and accurately. From feature vector generation and similarity matrix construction to connection relationship establishment, graph construction and optimization, each step fully explores the semantic associations of teaching behavior features, and finally obtains a teaching behavior feature graph with good connectivity and clear associations. This graph can intuitively present the association strength between various teaching behavior features, providing structured and high-quality graph data support for the subsequent extraction of quantitative indicators of teaching ability based on node attributes, and ensuring the accuracy and reliability of subsequent evaluation links.

[0115] S3. Based on the node attributes of the teaching behavior feature map, perform feature dimension mapping on the teaching behavior feature map to obtain the quantitative indicators of the teacher's teaching ability.

[0116] In this embodiment of the invention, the step of mapping the teaching behavior feature map to feature dimensions based on the node attributes of the teaching behavior feature map to obtain the quantitative indicators of the teacher's teaching ability includes:

[0117] Collect the node attribute parameters of the teaching behavior feature map;

[0118] Based on the semantic relevance of the node attribute parameters, the node attribute parameters are semantically associated and classified to obtain the dimensional grouping data of the node attribute parameters;

[0119] The dimensional grouped data is mapped into a vector space to obtain the dimensional feature vectors of the dimensional grouped data.

[0120] Based on the preset feature weight configuration, the quantization score of the dimensional feature vector is calculated, wherein the calculation formula for the quantization score is as follows:

[0121] ;

[0122] In the formula, This represents the quantized score of the feature vector of the stated dimension. Indicates the first Weight coefficients of each dimension of the feature vector. The dimensional feature vector represents the first... Each component value This represents the Sigmoid activation function. Represents the dimensional feature vector of the th dimension Historical mean of each component, This represents the preset information entropy adjustment coefficient. Represents the dimensional feature vector Information entropy This represents the number of dimensions in the dimensional feature vector. This represents the summation operation. This represents the square root operation;

[0123] The quantitative score is mapped to a preset teaching ability assessment standard to obtain the teacher's quantitative teaching ability index.

[0124] When collecting node attribute parameters of the teaching behavior feature map, it is necessary to identify the attribute information corresponding to each node in the teaching behavior feature map one by one. This attribute information includes the type description of the teaching behavior feature represented by the node, the frequency of the feature in the teaching process, the specific numerical performance of the feature, and the correlation strength between the feature and other nodes. These attribute information of each node are recorded and organized one by one to form a set of node attribute parameters of the teaching behavior feature map, ensuring that the attribute parameters of each node are complete and accurately correspond to the node itself.

[0125] When classifying node attribute parameters based on their semantic relevance to obtain dimensional grouping data, the semantic description of each node attribute parameter is first analyzed to determine its corresponding teaching ability dimension. For example, parameters containing semantic descriptions such as "speech rate" and "speech pause interval" are all related to the teaching ability dimension of "teacher's language expression ability," and these parameters are grouped into the same group. Parameters containing semantic descriptions such as "motion amplitude" and "motion continuity" are all related to the teaching ability dimension of "teacher's body expression ability," and are grouped into another group. Parameters containing semantic descriptions such as "interaction frequency" and "response time" are all related to the teaching ability dimension of "teacher's classroom interaction ability," and are grouped into a third group. Following this semantic association judgment method, all node attribute parameters are divided into different teaching ability dimension groups, and each group is the dimensional grouping data of the node attribute parameters.

[0126] When performing vector space mapping on dimensional grouped data to obtain dimensional feature vectors, firstly, a corresponding vector dimension is set for each dimensional group, with the number of dimensions matching the number of node attribute parameters within that group. Then, the numerical representation of each node attribute parameter within each group is used as a component value of the vector. These component values ​​are arranged sequentially according to a preset order to form an ordered numerical sequence. This numerical sequence is the dimensional feature vector corresponding to that dimensional group, ensuring that each dimensional group can be accurately transformed into a unique corresponding dimensional feature vector.

[0127] When calculating the quantization score of a dimensional feature vector based on a preset feature weight configuration, the weights corresponding to each component of the dimensional feature vector in the preset feature weight configuration are first obtained. Then, the difference between each component value and its historical mean is calculated. Each difference is substituted into the Sigmoid activation function for processing to obtain the normalized result corresponding to each component. Next, each normalized result is multiplied by the weight of the corresponding component. All multiplication results are added together to obtain the sum of the numerators. Then, the sum of the squares of all component weights is calculated and the square root is taken to obtain the first part of the denominator. Then, the information entropy of the dimensional feature vector is calculated. The information entropy is multiplied by a preset information entropy adjustment coefficient and then 1 is added to obtain the second part of the denominator. The first part of the denominator is multiplied by the second part to obtain the final denominator. Finally, the sum of the numerators is divided by the final denominator to obtain the quantization score of the dimensional feature vector.

[0128] The weight coefficients of the dimensional eigenvectors are determined using the analytic hierarchy process (AHP), with the following steps: First, a weight judgment matrix is ​​established. A review panel composed of three university teaching experts, two VR technology experts, and two teacher training managers compares and scores the importance of three dimensions—language expression, physical demonstration, and interactive guidance—based on the core objectives of VR teaching scenarios (e.g., experimental courses emphasize operational demonstrations, while theoretical courses emphasize verbal expression). A 1-9 scale is used to obtain the judgment matrix. Second, a consistency check is performed. The consistency index (CI) and consistency ratio (CR) of the judgment matrix are calculated. If CR is less than 0.1, the judgment matrix meets the consistency requirements; otherwise, the scores are recalculated. Third, weight calculation is performed. The eigenvectors of the judgment matrix are calculated using eigenvalue decomposition and normalized to obtain the weight coefficients for each dimension.

[0129] For the VR training course "University Physics Experiment - Circuit Connection," the core objective is to improve experimental operation demonstration and interactive guidance capabilities. The review panel determined the weighting coefficients after analysis using the Analytic Hierarchy Process (AHP). The physical demonstration dimension corresponds to experimental operation demonstration ability, with a weighting coefficient of 0.40. This is based on the fact that standardized operation demonstration is a core teaching objective in experimental courses and directly impacts the development of students' practical skills, thus it has the highest weight. The interactive guidance dimension corresponds to classroom interaction and emergency feedback capabilities, with a weighting coefficient of 0.35. This is based on the fact that experimental classes require timely responses to students' operational questions, and interactive ability directly determines the effectiveness of teaching, thus it has the second highest weight. The verbal expression dimension corresponds to verbal expression and communication skills, with a weighting coefficient of 0.25. This is based on the fact that language is a tool to assist in operation demonstrations; it must ensure clear expression but not supersede the operation, thus it has the third highest weight.

[0130] The formula for calculating the quantitative score is as follows: This represents the quantized score of the feature vector of the stated dimension, which, after normalization, ranges from 0 to 1. Indicates the first Weight coefficients of each dimension of the feature vector. The dimensional feature vector represents the first... Each component value This represents the Sigmoid activation function, used to normalize component values ​​to the interval between 0 and 1. Represents the dimensional feature vector of the th dimension The historical average of each component was obtained based on statistics from over 1000 sets of similar VR teaching data. This represents the preset information entropy adjustment coefficient, with a value range of 0.5 to 1.0 and a default of 0.8. Represents the dimensional feature vector Information entropy reflects the uniformity of feature distribution. This indicates the number of dimensions in the dimensional feature vector.

[0131] Using Teacher A's case, Equals 3, Equals 0.8, physical demonstration dimension It is 0.40. It is 8.6. It is 7.5. reduce It equals 1.1. Equals 0.750, Interactive Guidance Dimension It is 0.35. It is 8.2. It is 6.8. reduce It equals 1.4. Equals 0.802, Language Expression Dimension It is 0.25. It is 8.8. It is 7.2. reduce It equals 1.6. The result is 0.833; the numerator is calculated as 0.40 × 0.750 + 0.35 × 0.802 + 0.25 × 0.833, which gives 0.300 + 0.2807 + 0.2083 = 0.789; the denominator is calculated by first calculating the sum of squares of the weights, which gives 0.345; the square root of the sum of squares of the weights is approximately 0.587; information entropy. The entropy value of the probability distribution of the dimensional feature vector was calculated, and the result was 1.2, reflecting good uniformity of the feature distribution; the adjustment term was 0.8 × 1.2 + 1 = 1.96; the final denominator value was 0.587 × 1.96 ≈ 1.151; the quantized score was... It equals 0.789 divided by 1.151, which is approximately 0.686. After normalization, it is converted to a percentage score of 68.6.

[0132] The core logic of mapping quantitative scores to pre-defined teaching ability assessment standards to obtain quantitative indicators of teachers' teaching abilities is "determining thresholds based on big data statistical patterns → matching scores to levels → linear transformation to calculate indicators." First, it clarifies the teaching ability levels and specific quantitative indicators corresponding to different score ranges in the pre-defined teaching ability assessment standards. For example, the assessment standards stipulate that a quantitative score of 80-100 points corresponds to an "Excellent" level, with a corresponding quantitative indicator of 90-100 points; 60-79 points corresponds to a "Good" level, with a corresponding quantitative indicator of 70-89 points; and 40-59 points corresponds to a "Pass" level, with a corresponding quantitative indicator of 70-89 points. The quantitative indicator is 50-69 points; below 40 points corresponds to the "unqualified" level. The corresponding quantitative indicator for teaching ability is 0-49 points. Then, check the range of the calculated quantitative score to find the range of the quantitative indicator for teaching ability. Determine the final quantitative indicator value for teaching ability based on the specific position of the quantitative score within the range. For example, if the quantitative score is 85 points, which is in the 80-100 point range and corresponds to the "excellent" level, and if the quantitative score within this range is linearly mapped to the quantitative indicator for teaching ability at a ratio of 1.10, then the quantitative indicator for teaching ability corresponding to 85 points is 93.5 points. This value is determined as the teacher's quantitative indicator for teaching ability.

[0133] The threshold for the teaching ability assessment standard is determined based on the statistical distribution of over 1000 sets of VR teacher training sample data. The sample data conforms to a normal distribution, and the threshold is calculated as the mean plus or minus one standard deviation. The specific mapping rules are as follows: a quantitative score of 80 to 100 corresponds to an excellent level. The quantitative indicator for teaching ability is equal to... The formula ×100×1.10 is based on the scientific principle that the quantitative indicators of excellent teachers in the sample range from 90 to 100 points, conforming to the right-tail characteristic of a normal distribution. The 1.10-fold mapping is based on the statistical calibration results of the sample within this range. A quantitative score of 60 to 79 points corresponds to a "good" level, and the quantitative indicator of teaching ability is equal to... The formula ×100×1.05 is based on the scientific principle that the quantitative index distribution range of good teachers in the sample is 70 to 89 points, corresponding to the middle high-density area of ​​a normal distribution. A 1.05-fold mapping corresponds to the ability gradient differences among teachers of this level. A quantitative score of 40 to 59 points corresponds to a passing grade, and the quantitative index of teaching ability is equal to... The formula ×100×0.95 is based on the scientific principle that the quantitative indicators of qualified teachers in the sample range from 50 to 69 points, which conforms to the left-tail transition zone of a normal distribution. A 0.95-fold mapping corrects for the systematic bias in this range. A quantitative score below 40 points corresponds to an unqualified grade. The quantitative indicator of teaching ability is equal to... ×100×0.80, the scientific basis is that the quantitative indicators of unqualified teachers in the sample are distributed in the range of 0 to 49 points, which corresponds to the low-density area of ​​the left tail of the normal distribution. 0.80 times mapping highlights the quantitative differences in the ability to highlight shortcomings.

[0134] Teacher A's quantitative score is 68.6, which is considered good. The corresponding quantitative indicator for teaching ability is 68.6 × 1.05, which is approximately 72.0. Therefore, the final quantitative indicator for teaching ability is determined to be 72, which accurately reflects the comprehensive teaching ability level of teacher A in experimental operation demonstration, interactive guidance, and language expression.

[0135] The weighting coefficients are not assigned based on human experience, but rather through a combination of analytic hierarchy process (AHP) and mathematical verification. The scoring results from the review panel must pass a consistency check to ensure logical consistency. The final weighting coefficients are calculated using eigenvalue decomposition, strictly adhering to mathematical principles and avoiding subjective assumptions.

[0136] The quantitative score calculation process integrates multiple natural science models. The Sigmoid activation function utilizes nonlinear mapping characteristics to normalize the original data, eliminating extreme value interference and conforming to the mathematical laws of data processing; information entropy Based on the principles of probability and statistics, this reflects the uniformity of the characteristic distribution. The range of adjustment coefficients was calibrated using a large amount of experimental data to ensure the stability of the calculation results.

[0137] The grade thresholds for the teaching ability assessment standards are determined based on big data statistical patterns. By analyzing the quantitative results of more than 1,000 VR teacher training samples, it was found that they conform to the characteristics of a normal distribution. The grade thresholds are taken as the mean plus or minus 1 standard deviation, which makes the assessment standards statistically objective, rather than simply arbitrary.

[0138] The beneficial effects are that, through the detailed implementation process described above, node attribute parameters can be accurately collected from the teaching behavior feature map and semantically associated and classified. After forming dimensional grouped data, it is transformed into dimensional feature vectors. Then, combined with preset weight configuration, quantitative scores are obtained through standardized calculations, and finally mapped to quantitative indicators of teaching ability. The steps in the whole process are closely connected and the operation is clear. It not only makes full use of the multi-dimensional information of teaching behavior features, but also ensures the accuracy of quantitative indicators of teaching ability through reasonable calculation and mapping. At the same time, considering factors such as historical average and information entropy when calculating quantitative scores, the resulting quantitative indicators of teaching ability can reflect both the teacher's current teaching ability level and the stability and historical comparison of ability performance. This provides a scientific and reliable quantitative basis for the evaluation of teachers' teaching ability in VR teacher training in universities.

[0139] S4. Analyze the dynamic evolution of the quantitative indicators of teaching ability to obtain the changing trend of the quantitative indicators of teaching ability.

[0140] In this embodiment of the invention, analyzing the dynamic evolution of the quantitative indicators of teaching ability to obtain the changing trend of the quantitative indicators of teaching ability includes:

[0141] The quantitative indicators of teaching ability are organized sequentially to obtain a time-series indicator sequence of the quantitative indicators of teaching ability.

[0142] Dynamic pattern analysis is performed on the time series indicator sequence to obtain the trend pattern of the time series indicator sequence;

[0143] Based on the trend pattern, the quantitative indicators of teaching ability are synthesized to obtain the changing trend of the quantitative indicators of teaching ability.

[0144] When organizing the quantitative indicators of teaching ability into a time-series indicator sequence, the basis for dividing the time dimension should first be clarified. Considering the actual pace of VR teacher training in universities, the training cycle should be divided into several consecutive time units. Specifically, each VR simulation teaching training session can be considered a time unit, or each completed teaching module can be considered a time unit, ensuring that the division of time units fully covers the entire training process and is consistent. Next, the quantitative indicators of teacher teaching ability generated after each time unit are extracted from the teaching ability assessment data repository. These indicators cover specific values ​​for multiple dimensions such as communication skills, classroom management skills, and the ability to use VR teaching tools. Then, according to the chronological order of time units, the quantitative indicators of teaching ability for each dimension are arranged sequentially, and a corresponding time unit identifier is attached to each value, such as "1st VR simulation class - classroom control ability indicator 78", "2nd VR simulation class - classroom control ability indicator 82", "1st teaching module - VR teaching tool application ability indicator 80", etc., which finally forms a time-series indicator sequence of teaching ability quantitative indicators in chronological order, containing multi-dimensional indicator values ​​and time identifiers, ensuring that the sequence can fully reflect the specific situation of each dimension of teaching ability quantitative indicators at different time points.

[0145] When performing dynamic pattern analysis on time-series indicators to obtain trend patterns, the time-series indicator series is first split by dimension, and the indicator series of each dimension is analyzed separately to avoid interference between the changing patterns of indicators in different dimensions. During the analysis, the indicator values ​​of adjacent time units are compared one by one, the difference between adjacent values ​​is calculated, and it is determined whether the value is rising, falling, or remaining stable. At the same time, the magnitude of each change is recorded. For example, if an indicator of a certain dimension changes from 75 in the first time unit to 78 in the second time unit, the difference is +3, which is judged as a slight increase; if it changes from 78 in the second time unit to 85 in the third time unit, the difference is +7, which is judged as a significant increase. Subsequently, based on the changes over multiple consecutive time units, the overall trend is summarized. If the indicator values ​​show an upward trend for five consecutive time units, with each increase ranging from 3 to 8, and no obvious decline or stabilization phase, the trend pattern of the time series indicator sequence for that dimension is determined to be a "continuous upward pattern." If an indicator in a certain dimension first rises slowly over three time units, then remains stable over two time units, and then slowly declines over three time units, with both the increase and decrease being less than 5, it is determined to be a "rise-stabilize-decline pattern." If the indicator value fluctuates around a central value throughout the entire time period, with the fluctuation range always less than 3, and no obvious continuous upward or downward trend, it is determined to be a "stable fluctuation pattern." Through this analysis process, the trend pattern corresponding to the time series indicator sequence for each dimension is finally obtained.

[0146] When synthesizing trends from quantitative indicators of teaching ability based on trend patterns, the first step is to identify the key time points of indicator changes under each trend pattern. These points include trend start points, trend turning points, and trend peak points. For example, in the "rise-stabilize-fall pattern," the starting point of the rising phase, the turning point from rising to stabilizing, the turning point from stabilizing to falling, and the ending point of the falling phase are all key points. Next, in a coordinate system with time as the horizontal axis and the quantitative indicator values ​​of teaching ability as the vertical axis, the time and indicator values ​​corresponding to each key point are converted into coordinate points and marked. For example, if a key point corresponds to "3rd VR simulation lesson - indicator 85," then the coordinate point is marked at the intersection of the horizontal axis "3rd" and the vertical axis "85." Then, based on the changing patterns of the trend pattern, these coordinate points are connected sequentially with smooth lines. During the connection process, it is necessary to ensure that the lines accurately reflect the changing trends between adjacent nodes. For example, the lines in the rising phase should show an upward sloping trend, the lines in the stabilizing phase should remain horizontal, and the lines in the falling phase should show a downward sloping trend. Meanwhile, next to the generated trend lines, the trend pattern name and key change information corresponding to the dimension indicator are marked, such as "continuous upward pattern, from the 1st to the 6th simulation class, the indicator rose from 72 to 91, with a cumulative increase of 19". Through this synthesis process, the change trend of the quantitative indicators of teaching ability in each dimension is finally obtained, and the dynamic evolution of the indicators over time is fully presented.

[0147] The beneficial effects are that, through the detailed implementation process described above, scattered quantitative indicators of teaching ability can be transformed into an ordered and structured time-series indicator sequence, accurately analyzing the specific trend patterns of each dimension of indicators and synthesizing intuitive and clear trends. This not only fully preserves the details of indicator changes at different time points but also clearly presents the overall evolutionary pattern of the indicators. This provides a comprehensive and accurate trend basis for subsequent analysis of teachers' teaching ability development stages and fitting development trajectories, ensuring that the dynamic evaluation of teachers' teaching ability during VR teacher training is more scientific and targeted, and helping to accurately grasp the improvement of teachers' teaching ability.

[0148] S5. Based on the key characteristics of the changing trend, perform stage trajectory fitting on the quantitative indicators of teaching ability to obtain the teacher's teaching ability development trajectory.

[0149] In this embodiment of the invention, the step of fitting the quantitative indicators of teaching ability to a stage trajectory based on the key characteristics of the changing trend to obtain the teacher's teaching ability development trajectory includes:

[0150] Extract the key features of the changing trend;

[0151] Based on the time distribution and feature intensity of the key features, the teaching ability quantitative index is serialized into a state sequence to obtain the evolution state sequence of the teaching ability quantitative index.

[0152] Based on the logical associations between states in the evolution state sequence, establish the connection relationships between the states;

[0153] Using the states in the evolution state sequence as trajectory nodes and the connection relationships as connecting edges, a basic trajectory framework for the quantitative indicators of teaching ability is constructed.

[0154] Segmented trajectory interpolation is performed on the basic trajectory framework to obtain segmented trajectory fragments of the basic trajectory framework;

[0155] The teacher's teaching ability development trajectory is obtained by smoothing the transition bands of the segmented trajectory segments.

[0156] The process of smoothing the transition bands of the segmented trajectory segments to obtain the teacher's teaching ability development trajectory includes:

[0157] Based on the connection point characteristics of the segmented trajectory segments, the transition zone region of the segmented trajectory segments is identified;

[0158] Curvature continuity optimization is performed on the trajectory points within the transition zone region to obtain the smooth trajectory of the segmented trajectory fragment;

[0159] Verify the smoothness of the smooth trajectory to confirm the teacher's teaching ability development trajectory.

[0160] When extracting key features of the trend, it is necessary to comprehensively sort out the core elements of the trend of quantitative indicators of teaching ability, including the starting and ending points of the indicator's rise or fall to clarify the time range of the trend, capturing the specific time nodes and corresponding indicator values ​​when the trend turns to determine the key position of the change in trend direction, recording the highest and lowest values ​​reached by the indicator in the trend to lock in the extreme value characteristics, and statistically analyzing the change range of the indicator per unit time to clarify the change rate characteristics. These extracted elements, such as the starting and ending points, turning points, extreme value data, and change rate, are integrated to form the key features of the trend.

[0161] When serializing the state sequence of teaching ability quantitative indicators based on the time distribution and intensity of key features to obtain the evolution state sequence, firstly, all key features are arranged in chronological order to clarify their time distribution patterns. Then, intensity levels are divided according to the intensity of indicator changes reflected by the key features. Combining the time distribution and intensity levels, the state of teaching ability quantitative indicators in each time interval is defined. For example, if the indicator shows a rapid increase and a high intensity level in a certain time interval, it is defined as a rapid improvement state. If the indicator changes slowly and the intensity level is low in a certain time interval, it is defined as a stable development state. The states corresponding to all time intervals are arranged in chronological order to form the evolution state sequence of teaching ability quantitative indicators.

[0162] When establishing connections between states based on the logical relationships between states in the evolutionary state sequence, the attribute characteristics of adjacent states in the evolutionary state sequence are analyzed one by one to determine the transition logic from the previous state to the next state. If the previous state is a rapidly improving state and the next state is a stable development state, and there is a logical relationship of "becoming stable after improvement" between the two, then a one-way connection relationship from the rapidly improving state to the stable development state is established. If there is a two-way logical relationship of mutual influence between adjacent states, then a two-way connection relationship is established. All connections between adjacent states must clearly indicate their logical relationship basis to ensure the rationality of the connection relationship.

[0163] When constructing a basic trajectory framework for quantitative indicators of teaching ability using states in an evolutionary state sequence as trajectory nodes and connections as connecting edges, each state in the evolutionary state sequence is treated as an independent trajectory node. The time interval and core features corresponding to the state name are marked on the node. The previously established connections between states are then used as connecting edges. The trajectory nodes are connected sequentially through the connecting edges according to the time order of the evolutionary state sequence, forming a basic trajectory framework that can intuitively show the evolution path of quantitative indicators of teaching ability. The framework must clearly present the position of each node and the connection method between nodes.

[0164] When performing segmented trajectory interpolation on the basic trajectory framework to obtain segmented trajectory fragments, the entire framework is divided into several continuous segments according to the attribute changes of the state in the basic trajectory framework. Each segment contains a set of trajectory nodes and connecting edges with similar change characteristics. For each segment, the key time points and index values ​​corresponding to the trajectory nodes in that segment are selected. Several intermediate points are added between two adjacent trajectory nodes. The added intermediate points need to be reasonably set according to the index change rules of the preceding and following nodes to ensure that the index values ​​of the intermediate points can accurately reflect the gradual change process between nodes. Each segment forms an independent segmented trajectory fragment after being supplemented by intermediate points.

[0165] When obtaining the teacher's teaching ability development trajectory by smoothing the transition zone of segmented trajectory segments, the transition zone region is first identified based on the connection point characteristics of the segmented trajectory segments. Then, the curvature of the trajectory points within the transition zone region is continuously optimized to obtain a smooth trajectory. Finally, the smoothness of the smooth trajectory is verified to confirm the teaching ability development trajectory.

[0166] When identifying the transition zone region of segmented trajectory segments based on the connection point characteristics of segmented trajectory segments, carefully observe the trajectory direction and index changes at the connection point of two adjacent segmented trajectory segments. Find the area where the trajectory curvature changes significantly before and after the connection point. This area is the transition zone region. The range of the transition zone region extends from the connection point to the two segmented trajectory segments before and after it. The extension length should be sufficient to completely cover the area where the curvature changes to ensure the accuracy of the transition zone region.

[0167] When performing curvature optimization on trajectory points within the transition zone to obtain smooth trajectories of segmented trajectory segments, the curvature value of each trajectory point within the transition zone is analyzed one by one. The curvature differences between adjacent trajectory points are compared, and trajectory points with abrupt curvature changes are adjusted. The curvature value of the abrupt change point is corrected to a value that connects with the curvature of the trajectory points before and after it, so that the curvature of all trajectory points within the transition zone shows a continuous and gradual trend. After curvature optimization, adjacent segmented trajectory segments can naturally connect in the transition zone to form smooth trajectories.

[0168] When verifying the smoothness of a smooth trajectory to confirm the teacher's teaching ability development trajectory, the rate of curvature change between adjacent trajectory points is calculated sequentially along the smooth trajectory. It is then determined whether the rate of curvature change is within a preset reasonable range. If the rate of curvature change of all adjacent trajectory points is within a reasonable range and the entire trajectory has no obvious broken lines or abrupt changes, the smooth trajectory is determined to meet the smoothness requirements, and the smooth trajectory is confirmed as the teacher's teaching ability development trajectory. If there are parts that do not meet the smoothness requirements, the process is repeated to smooth the transition zone until the requirements are met.

[0169] The beneficial effects are that, through the above detailed and standardized implementation process, key features of changing trends can be accurately extracted and state serialization can be completed. A reasonable state connection relationship can be established to construct a basic trajectory framework. After segmented interpolation and transition smoothing, a smooth and accurate trajectory of teaching ability development can be obtained. This fully presents the stage evolution path of teachers' teaching ability in the VR teacher training process, providing comprehensive and reliable trajectory data support for the subsequent integration and generation of comprehensive quantitative evaluation indicators. This ensures that the evaluation of teachers' teaching ability is more dynamic and scientific, and helps to accurately grasp the development law of teachers' teaching ability.

[0170] S6. Integrate the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate a comprehensive quantitative evaluation index for the teacher.

[0171] In this embodiment of the invention, the step of integrating the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate the comprehensive quantitative evaluation indicators for teachers includes:

[0172] Based on the target requirements of the teaching ability assessment standards, configure the weight coefficients of the quantitative indicators of teaching ability and the development trajectory of teaching ability;

[0173] Based on the weighting coefficients, the quantitative indicators of teaching ability and the development trajectory of teaching ability are fused to obtain the teacher's preliminary comprehensive indicators.

[0174] By eliminating the influence of the dimensions of the preliminary comprehensive indicators, the comprehensive quantitative evaluation indicators for the teachers are obtained.

[0175] When configuring the weighting coefficients for quantitative indicators of teaching ability and the development trajectory of teaching ability according to the target requirements of the teaching ability assessment standards, the core objectives of each assessment dimension in the teaching ability assessment standards should be clarified first. For example, if the assessment standard takes the teacher's current teaching ability level as the core objective, the weighting of the quantitative indicators of teaching ability should be increased; if the core objective is the teacher's long-term potential for improvement in teaching ability, the weighting of the development trajectory of teaching ability should be increased. Subsequently, an assessment team composed of university teaching experts, VR technology application experts, and teacher training managers should be formed. Combining the target requirements of the assessment standards, the team should score the importance of the quantitative indicators of teaching ability and the development trajectory of teaching ability through collective discussion. The average score results should be taken, and the weighting coefficients of the two should be determined in percentage form to ensure that the sum of the weighting coefficients is 100% and that they accurately match the target orientation of the assessment standards.

[0176] When merging quantitative indicators of teaching ability and the development trajectory of teaching ability based on weighted coefficients to obtain a teacher's preliminary comprehensive index, the specific values ​​of the quantitative indicators of teaching ability and the corresponding quantitative scores of the development trajectory of teaching ability are first obtained. The quantitative scores of the development trajectory of teaching ability need to be converted into specific values ​​according to the characteristics of ability improvement and stability reflected by the trajectory, referring to the preset trajectory scoring rules. Next, according to the configured weighted coefficients, the values ​​of the quantitative indicators of teaching ability are multiplied by their corresponding weighted coefficients, and the quantitative scores of the development trajectory of teaching ability are multiplied by their corresponding weighted coefficients. The two products are then added together, and the sum is the teacher's preliminary comprehensive index. During the calculation process, the accuracy of the numerical calculations must be ensured to avoid affecting the reliability of the preliminary comprehensive index due to calculation errors.

[0177] To eliminate the dimensional influence of the preliminary comprehensive indicators and obtain the comprehensive quantitative evaluation indicators for teachers, the preliminary comprehensive indicator data of all teachers participating in VR teacher training are first collected, and the maximum and minimum values ​​of these data are calculated. Then, each teacher's preliminary comprehensive indicator is standardized using a fixed formula: the minimum value of all preliminary comprehensive indicator data is subtracted from the teacher's preliminary comprehensive indicator value, and then divided by the difference between the maximum and minimum values ​​of all preliminary comprehensive indicator data, resulting in the standardized value. Finally, the standardized value is mapped and transformed according to a preset scoring range. The transformed value is the comprehensive quantitative evaluation indicator after eliminating the dimensional influence, ensuring that the comprehensive quantitative evaluation indicators of different teachers are within the same dimensional system and that horizontal comparisons are feasible.

[0178] The beneficial effect is that, through the above steps, weight coefficients can be accurately configured according to the evaluation criteria and objectives, realizing the scientific integration of quantitative indicators of teaching ability and development trajectory. After dimension elimination processing, a comprehensive quantitative evaluation indicator with unified comparison standards is obtained, which not only reflects the current teaching ability level of teachers, but also reflects their ability development potential. This provides a comprehensive, objective and comparable result for the evaluation of the effectiveness of VR teacher training in universities, helping to accurately judge the effectiveness of teacher training and optimize training programs.

[0179] like Figure 2 The diagram shown is a functional module diagram of a VR teacher training simulation teaching data quantitative evaluation system for universities, provided by an embodiment of the present invention.

[0180] The VR teacher training simulation teaching data quantitative evaluation system 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the VR teacher training simulation teaching data quantitative evaluation system 100 may include a multimodal feature fusion module 101, a semantic network reconstruction module 102, a feature dimension mapping module 103, a dynamic evolution analysis module 104, a stage trajectory fitting module 105, and a comprehensive evaluation index generation module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0181] In this embodiment, the functions of each module / unit are as follows:

[0182] The multimodal feature fusion module 101 is used to perform multimodal feature fusion on the teacher's teaching behavior data to obtain the teaching behavior features of the teaching behavior data;

[0183] The semantic network reconstruction module 102 is used to perform semantic network reconstruction on the teaching behavior features to obtain a teaching behavior feature map of the teaching behavior features;

[0184] The feature dimension mapping module 103 is used to perform feature dimension mapping on the teaching behavior feature map according to the node attributes of the teaching behavior feature map to obtain the quantitative index of the teacher's teaching ability.

[0185] The dynamic evolution analysis module 104 is used to analyze the dynamic evolution law of the quantitative indicators of teaching ability and obtain the changing trend of the quantitative indicators of teaching ability.

[0186] The stage trajectory fitting module 105 is used to perform stage trajectory fitting on the quantitative indicators of teaching ability based on the key characteristics of the changing trend, so as to obtain the teacher's teaching ability development trajectory.

[0187] The comprehensive evaluation index generation module 106 is used to integrate the quantitative indicators of teaching ability and the development trajectory of teaching ability to generate the comprehensive quantitative evaluation index of the teacher.

[0188] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0189] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0190] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0191] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0192] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A high school VR teacher training simulation teaching data quantification evaluation method, characterized in that, The method comprises: S1, the teaching behavior data of the teacher is fused with multi-modal characteristics, and the teaching behavior characteristics of the teaching behavior data are obtained; S2, the teaching behavior characteristics are reconfigured by a semantic network, and a teaching behavior characteristic map of the teaching behavior characteristics is obtained, comprising: performing semantic correlation analysis on the teaching behavior characteristics to generate a feature similarity matrix of the teaching behavior characteristics; according to the correlation strength in the feature similarity matrix, when the correlation strength reaches a preset threshold, a connection relationship is established between the related features of the teaching behavior characteristics; the related features are taken as nodes, and the connection relationship is taken as a connection edge to construct an initial feature map of the teaching behavior characteristics; the initial feature map is enhanced by a semantic relationship to obtain an optimized feature map of the initial feature map; verify the connectivity of the optimized feature map to confirm the teaching behavior characteristic map of the teaching behavior characteristics; S3, according to the node attribute of the teaching behavior characteristic map, the feature dimension mapping of the teaching behavior characteristic map is carried out, and the teaching ability quantitative index of the teacher is obtained, comprising: according to the node attribute of the teaching behavior characteristic map, the feature dimension mapping of the teaching behavior characteristic map is carried out, and the teaching ability quantitative index of the teacher is obtained, comprising: collecting node attribute parameters of the teaching behavior characteristic map; according to the semantic correlation of the node attribute parameters, the node attribute parameters are classified by semantic correlation to obtain dimension grouping data of the node attribute parameters; the dimension grouping data is mapped to a vector space to obtain a dimension feature vector of the dimension grouping data; according to the preset feature weight configuration, the quantitative score of the dimension feature vector is calculated; the quantitative score is mapped to a preset teaching ability evaluation standard to obtain the teaching ability quantitative index of the teacher; S4, analyze the dynamic evolution law of the teaching ability quantitative index to obtain the change trend of the teaching ability quantitative index; S5, according to the key features of the change trend, the stage trajectory fitting of the teaching ability quantitative index is carried out to obtain the teaching ability development trajectory of the teacher, comprising: extracting the key features of the change trend; according to the time distribution and feature intensity of the key features, the state sequence of the teaching ability quantitative index is sequenced to obtain the evolution state sequence of the teaching ability quantitative index; according to the logical association between states in the evolution state sequence, the connection relationship between the states is established; the states in the evolution state sequence are taken as trajectory nodes, and the connection relationship is taken as a connection edge to construct a basic trajectory framework of the teaching ability quantitative index; the basic trajectory framework is segmented and interpolated to obtain a segmented trajectory segment of the basic trajectory framework; the segmented trajectory segment is smoothed by a transition zone to obtain the teaching ability development trajectory of the teacher; S6, integrate the teaching ability quantitative index and the teaching ability development trajectory to generate a comprehensive quantitative evaluation index of the teacher.

2. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, the teaching behavior data of the teacher is fused with multi-modal characteristics, and the teaching behavior characteristics of the teaching behavior data are obtained, comprising: Acquiring teaching behavior data of a teacher; Extracting speech features of original speech waveforms in the teaching behavior data; Tracking skeleton key point data of the teaching behavior data to obtain posture features of the teacher; Extracting features of interaction frequency, response time and interaction depth of the teaching behavior data to obtain interaction features of the teacher; Performing semantic alignment on the speech features, the posture features and the interaction features to obtain preliminary teaching behavior features of the teacher; Removing redundant features of the preliminary teaching behavior features to obtain teaching behavior features of the teaching behavior data.

3. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, The semantic correlation analysis on the teaching behavior features generates a feature similarity matrix of the teaching behavior features, including: Numerical processing is performed on the teaching behavior features while the semantic information of the teaching behavior features is preserved to obtain a feature vector of the teaching behavior features; According to the distribution characteristics of the feature vector, a semantic space framework of the feature vector is constructed; In the semantic space framework, the relative position and distribution mode of the feature vector are analyzed to obtain similarity relationship data of the feature vector; The similarity relationship data is organized in a matrix structure to obtain a feature similarity matrix of the teaching behavior features.

4. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, The calculation formula of the quantitative score is as follows: ； In the formula, denotes a quantization score of the dimension feature vector, denotes a weight coefficient of the dimension feature vector, denotes a component value of the dimension feature vector, denotes a Sigmoid activation function, denotes a historical mean value of the component in the dimension feature vector, denotes a preset information entropy adjustment coefficient, denotes an information entropy of the dimension feature vector, denotes a dimension number of the dimension feature vector, denotes a summation operation, denotes a square root operation.

5. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, The analysis of the dynamic evolution rule of the teaching ability quantitative index obtains the change trend of the teaching ability quantitative index, including: The teaching ability quantitative index is sequentially organized to obtain a time sequence of the teaching ability quantitative index; The dynamic mode of the time sequence of the teaching ability quantitative index is analyzed to obtain a trend mode of the time sequence of the teaching ability quantitative index; According to the trend mode, the trend of the teaching ability quantitative index is synthesized to obtain the change trend of the teaching ability quantitative index.

6. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, The transition zone smoothing of the segmented trajectory segment obtains the teaching ability development trajectory of the teacher, including: According to the connection point features of the segmented trajectory segment, the transition zone region of the segmented trajectory segment is identified; The curvature continuity of the trajectory points in the transition zone region is optimized to obtain a smoothed trajectory of the segmented trajectory segment; The smoothness of the smoothed trajectory is verified to confirm the teaching ability development trajectory of the teacher.

7. The high school VR instructor training simulation teaching data quantitative evaluation method of claim 1, wherein, The integration of the teaching ability quantitative index and the teaching ability development trajectory generates a comprehensive quantitative evaluation index of the teacher, including: According to the target requirements of the teaching ability evaluation standard, the weight coefficients of the teaching ability quantitative index and the teaching ability development trajectory are configured; Based on the weight coefficients, the teaching ability quantitative index and the teaching ability development trajectory are fused to obtain a preliminary comprehensive index of the teacher; The dimensional influence of the preliminary comprehensive index is eliminated to obtain the comprehensive quantitative evaluation index of the teacher.

8. A high school VR teacher training simulation teaching data quantitative evaluation system, characterized in that, A high school VR teacher training simulation teaching data quantitative evaluation method according to claim 1, the system comprises: A multi-modal feature fusion module is configured to fuse multi-modal features of the teaching behavior data of a teacher to obtain teaching behavior features of the teaching behavior data. The semantic network reconstruction module is configured to perform semantic network reconstruction on the teaching behavior characteristics to obtain a teaching behavior characteristic map of the teaching behavior characteristics, including: performing semantic correlation analysis on the teaching behavior characteristics to generate a characteristic similarity matrix of the teaching behavior characteristics; establishing a connection relationship between relevant characteristics of the teaching behavior characteristics when an association strength in the characteristic similarity matrix reaches a preset threshold value according to the association strength; constructing an initial characteristic map of the teaching behavior characteristics by taking the relevant characteristics as nodes and the connection relationship as connection edges; performing semantic relationship enhancement on the initial characteristic map to obtain an optimized characteristic map of the initial characteristic map; verifying connectivity of the optimized characteristic map to confirm a teaching behavior characteristic map of the teaching behavior characteristics; The feature dimension mapping module is configured to perform feature dimension mapping on the teaching behavior characteristic map according to node attributes of the teaching behavior characteristic map to obtain a teaching ability quantitative index of the teacher, including: performing feature dimension mapping on the teaching behavior characteristic map according to node attributes of the teaching behavior characteristic map to obtain a teaching ability quantitative index of the teacher, including: collecting node attribute parameters of the teaching behavior characteristic map; performing semantic correlation classification on the node attribute parameters according to semantic correlation of the node attribute parameters to obtain dimension grouping data of the node attribute parameters; performing vector space mapping on the dimension grouping data to obtain a dimension feature vector of the dimension grouping data; calculating a quantitative score of the dimension feature vector according to a preset feature weight configuration; mapping the quantitative score to a preset teaching ability evaluation standard to obtain the teaching ability quantitative index of the teacher; The dynamic evolution analysis module is configured to analyze a dynamic evolution law of the teaching ability quantitative index to obtain a change trend of the teaching ability quantitative index. The stage trajectory fitting module is configured to perform stage trajectory fitting on the teaching ability quantitative index according to key features of the change trend to obtain a teaching ability development trajectory of the teacher, including: extracting key features of the change trend; performing state serialization on the teaching ability quantitative index according to time distribution and feature intensity of the key features to obtain an evolution state sequence of the teaching ability quantitative index; establishing a connection relationship between states according to a logical association between the states in the evolution state sequence; constructing a basic trajectory framework of the teaching ability quantitative index by taking the states in the evolution state sequence as trajectory nodes and the connection relationship as connection edges; performing segmented trajectory interpolation on the basic trajectory framework to obtain segmented trajectory segments of the basic trajectory framework; performing transition zone smoothing on the segmented trajectory segments to obtain the teaching ability development trajectory of the teacher; The comprehensive evaluation index generation module is configured to integrate the teaching ability quantitative index and the teaching ability development trajectory to generate a comprehensive quantitative evaluation index of the teacher.

Images