A management method and system for a smart teaching platform combined with virtual reality

Abstract

The present invention relates to the field of educational management technology, and in particular to a method and system for managing a smart teaching platform in conjunction with virtual reality. A method for managing a smart teaching platform in conjunction with virtual reality, comprising the following steps: S1: obtaining employee learning-related data, and determining a first objective evaluation score and a second objective evaluation score to be calculated based on the employee's learning-related data; S2: obtaining the employee's first objective evaluation score using a dual-engine subjective question intelligent review model based on the employee's learning-related data; S3: obtaining the employee's second objective evaluation score using a two-dimensional integral quantification formula based on the employee's learning-related data. The present invention analyzes the employee's open-book and closed-book scores and adopts a role quantity adjustment formula to achieve real-time adjustment of the number and proportion of guiding and collaborative virtual roles in a virtual reality teaching environment.

Description

Technical Field

[0001] The present invention relates to the field of education management technology, and in particular to a management method and system for a smart teaching platform combined with virtual reality. Background Art

[0002] With the deepening of smart power plant construction, training platforms centered on quantitative management have become an important tool for corporate talent development. Existing smart training platforms have reduced training costs and improved management efficiency through online learning, exams, and a quantitative scoring system. However, existing solutions still have the following limitations: Most existing teaching platforms rely on a single evaluation metric, and their evaluation results often fail to fully reflect the learner's comprehensive abilities and learning status. Although the introduction of virtual reality technology has provided smart teaching platforms with new interactive methods and immersive experiences, making teaching scenarios more diverse, virtual reality teaching platforms currently lack effective management mechanisms for teaching evaluation and environmental control. They are unable to dynamically optimize teaching content and interaction methods based on learners' performance in the virtual environment, and it is difficult to adjust configurations in a timely manner to meet different learning needs.

[0003] Therefore, there is an urgent need to develop a smart teaching platform management method that can comprehensively collect and analyze employees' multi-dimensional learning data and combine virtual reality technology to achieve adaptive learning environment regulation, so as to break through the limitations of the existing evaluation mechanism and improve teaching effectiveness and management efficiency. Summary of the Invention

[0004] In order to overcome the shortcoming that it is difficult to adjust the configuration of virtual teaching characters in time to meet different learning needs, the present invention provides a management method and system for a smart teaching platform combined with virtual reality.

[0005] The technical implementation scheme of the present invention is: a management method of a smart teaching platform combined with virtual reality, comprising the following steps:

[0006] S1: Acquire learning-related data of an employee, and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee;

[0007] S2: Obtaining a first objective evaluation score for the employee using the dual-engine subjective question intelligent review model based on the employee's learning-related data;

[0008] S3: Obtaining a second objective evaluation score for the employee using a two-dimensional integral quantification formula based on the employee's learning-related data;

[0009] S4: Obtaining an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and managing the employee and the teaching platform according to the objective evaluation score;

[0010] S5: Adjust employees’ auxiliary learning based on their open-book learning points and closed-book learning points.

[0011] Preferably, the obtaining of the employee's learning-related data and determining the first objective evaluation score and the second objective evaluation score to be calculated based on the employee's learning-related data include: obtaining the employee's learning-related data, the employee's learning-related data including the employee's answer data, the employee's effective learning time, the employee's answer quality, the employee's learning status and the employee's learning environment, and using a dual-engine subjective question intelligent review model and a two-dimensional integral quantification formula based on the employee's learning-related data to obtain the first objective evaluation score and the second objective evaluation score of the teaching.

[0012] Preferably, the dual-engine subjective question intelligent review model is used according to the employee's learning-related data to obtain the employee's first objective evaluation score, including: using an intelligent word segmentation model and a fuzzy matching algorithm to construct a dual-engine subjective question intelligent review model, and inputting the employee's answer data into the dual-engine subjective question intelligent review model to obtain the first objective evaluation score, using a Transformer model for training to obtain an intelligent word segmentation model, and the intelligent word segmentation model is used to perform semantic analysis and keyword extraction on the employee's answer data to obtain word segmentation results; the fuzzy matching algorithm is based on a predefined rule library and a dynamic threshold adjustment mechanism, and is used to perform multi-dimensional matching on the word segmentation results, calculate the matching degree between the employee's answer data and the standard answer data, and obtain the first objective evaluation score of teaching.

[0013] Preferably, obtaining the second objective evaluation score of the employee using a two-dimensional integral quantification formula based on the employee's learning-related data includes: inputting the employee's answer data into the two-dimensional integral quantification formula to obtain the second objective evaluation score, wherein the two-dimensional integral quantification formula is:

[0014] ;

[0015] Where, is the second objective assessment score; For the times open-book learning points; For the The weight coefficient of the open-book learning integral; For the Closed-book learning points; For the The weight coefficient of the closed-book learning integral;

[0016] The integral formula for open-book learning is:

[0017] ;

[0018] Where, For the times open-book learning points; Effective learning time for employees; is the effective learning time weight coefficient; Score employees' learning status; rate the learning environment for employees;

[0019] The closed-book learning integral formula is:

[0020] ;

[0021] Where, For the Closed-book learning points; The quality of employees' answers; is the answer quality weight coefficient; Score employees' learning status; Rate the learning environment for employees.

[0022] Preferably, the Scoring the employee's learning status includes: using a learning status scoring formula to obtain the employee's learning status score; and using a learning environment scoring formula to obtain the employee's learning environment score, wherein the learning status scoring formula is:

[0023] ;

[0024] Where, Score employees' learning status; The number of effective interactions for answering real questions; The number of valid interactions for answering questions in VR; The total learning time in the actual test-taking process; The total learning time during the virtual reality question-answering process; The weight coefficient of the effective number of interactions for answering real questions; The weight of the number of page switching times in the real-world and virtual-reality question-answering processes; The number of page switches during the actual answering process; The number of page switches during the virtual reality question-answering process; The preset standard page switching times.

[0025] Preferably, the Rate the learning environment for employees, including:

[0026] The learning environment scoring formula is:

[0027] ;

[0028] Where, rate the learning environment for employees; The actual activity space for employees to answer questions in virtual reality; A standard preset space for employees to answer questions in virtual reality; The similarity between the employees’ virtual reality learning environment and their real learning environment; Tuning parameters for weights.

[0029] Preferably, the adjustment of employee assisted learning based on the employee's open-book learning points and the employee's closed-book learning points includes: dividing the virtual roles of virtual reality into guiding roles and collaborative roles, the guiding role is a teaching role that dynamically adjusts the explanation rhythm according to the employee; the collaborative role is a student role that simulates the behavior of real students, participates in group discussions or asks questions, and the ratio of guiding roles and collaborative roles in virtual reality is adjusted according to the employee's open-book learning points and the employee's closed-book learning points, and the total number of roles in the employee's virtual reality learning environment is adjusted using a role number adjustment formula.

[0030] Preferably, the total number of roles in the employee's virtual reality learning environment is adjusted using a role number adjustment formula, including: the total number of roles includes the number of virtual roles and the number of real roles, wherein the role number adjustment formula is:

[0031] ;

[0032] Where, is the total number of roles; is the minimum integral adjustment value; is the maximum integral adjustment value; for The critical value of The average of the employee's historical open-book learning scores; The average of the employee's historical closed-book learning scores; is the adjustment parameter; To round up.

[0033] Preferably, the adjusting the proportion of guiding roles and collaborative roles in virtual reality according to the employee's open-book learning points and the employee's closed-book learning points includes: when the employee's open-book learning points are greater than the employee's closed-book learning points, increasing the proportion of collaborative roles; when the employee's open-book learning points are less than or equal to the employee's closed-book learning points, increasing the proportion of guiding roles.

[0034] Preferably, a smart teaching platform management system combined with virtual reality also includes:

[0035] a data acquisition module, configured to acquire learning-related data of an employee and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee;

[0036] A first score acquisition module is configured to obtain a first objective evaluation score of the employee using a dual-engine subjective question intelligent review model based on the employee's learning-related data;

[0037] A second score acquisition module is used to obtain a second objective evaluation score of the employee using a two-dimensional integral quantification formula based on the employee's learning-related data;

[0038] a score acquisition management module, configured to obtain an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and to manage employees and the teaching platform according to the objective evaluation score;

[0039] The auxiliary learning adjustment module is used to adjust employees' auxiliary learning based on their open-book learning points and closed-book learning points.

[0040] The present invention has the following advantages:

[0041] 1. This invention comprehensively collects and quantifies multiple indicators of employees' answer data, learning time, answer quality, interactive behavior, learning status, and virtual learning environment during the learning process. It constructs a two-dimensional scoring system that covers both open-book and closed-book exams, achieving a comprehensive and objective evaluation of employees' learning situation. This evaluation method breaks through the traditional single evaluation model and makes the evaluation results more credible and referenceable.

[0042] 2. A dual-engine intelligent review model for subjective questions, built using an intelligent word segmentation system trained on a Transformer model and a fuzzy matching algorithm, can automatically perform semantic analysis and keyword extraction on open-ended questions answered by employees, accurately calculating the matching degree of answers. This improves the automation and accuracy of subjective question scoring, thereby reducing the workload of manual review and improving overall review efficiency.

[0043] 3. This method analyzes employees' open-book and closed-book scores and adopts a role quantity adjustment formula to achieve real-time adjustment of the number and proportion of guiding and collaborative virtual roles in the virtual reality teaching environment. This dynamic control mechanism can provide personalized teaching guidance and interactive atmosphere based on learning data feedback in different teaching scenarios, which not only optimizes learners' immersive experience but also improves the overall teaching effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the management method of the intelligent teaching platform combined with virtual reality of the present invention;

[0045] Figure 2 This is a structural diagram of the management system of the intelligent teaching platform combined with virtual reality in the present invention. DETAILED DESCRIPTION

[0046] Reference herein to an embodiment means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of such a phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0047] Example 1: A method for managing a smart teaching platform in conjunction with virtual reality, such as Figure 1 As shown, the following steps are included:

[0048] S1: Acquire learning-related data of an employee, and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee;

[0049] Obtain employee learning-related data, which includes employee answer data, employee effective learning time, employee answer quality, employee learning status and employee learning environment. Based on the employee learning-related data, use a dual-engine subjective question intelligent review model and a two-dimensional integral quantification formula to obtain a first objective evaluation score and a second objective evaluation score of the teaching.

[0050] It should be noted that, through the preset data collection module, information on employees is collected from multiple angles, and the employee learning-related data includes but is not limited to the following: employee answer data: including answers to various questions completed by employees on the teaching platform, including multiple-choice questions, true-or-false questions and objective questions, as well as answers to subjective questions that require manual or intelligent scoring; employee effective learning time: refers to the cumulative time that employees are in an effective learning state on the teaching platform. The teaching platform will eliminate abnormal interruptions or invalid time; employee answer quality: quantitative scoring is based on the accuracy of employees' answers, completeness of answers and standardization; employee learning status: assessed by examining the frequency of effective interactions of employees in the answering process, the total learning time in the real answering process and the total learning time in the virtual reality answering process; employee learning environment: assessed by the similarity between the virtual reality and the real environment and the interactive space in which the employees are located. Comprehensive scoring is performed. After data collection is completed, the learning-related data of the employees obtained are preprocessed and normalized to ensure that the data of each dimension meets the requirements of subsequent calculations. According to the pre-set calculation mode, the preset dual-engine subjective question intelligent review model and the two-dimensional integral quantification formula are used to process the data. The pre-processed employee answer data and other learning-related data are input one by one according to the project. For the first objective evaluation score, the embedded dual-engine subjective question intelligent review model is called to complete the scoring; for the second objective evaluation score, the open-book and closed-book scores of the employees are calculated according to the two-dimensional integral quantification formula. The various weight coefficients and scoring parameters involved in the formula are read from the pre-designed parameter library and matched with the actual collected data for calculation; finally, the system integrates the two scores to obtain an objective evaluation result reflecting the overall teaching effect, and uses this result as the basis for subsequent teaching platform management.

[0051] S2: Obtaining a first objective evaluation score for the employee using the dual-engine subjective question intelligent review model based on the employee's learning-related data;

[0052] A dual-engine subjective question intelligent review model is constructed using an intelligent word segmentation model and a fuzzy matching algorithm, and the employee's answer data is input into the dual-engine subjective question intelligent review model to obtain a first objective evaluation score. The Transformer model is used for training to obtain an intelligent word segmentation model. The intelligent word segmentation model is used to perform semantic analysis and keyword extraction on the employee's answer data to obtain word segmentation results; the fuzzy matching algorithm is based on a predefined rule library and a dynamic threshold adjustment mechanism to perform multi-dimensional matching on the word segmentation results, calculate the matching degree between the employee's answer data and the standard answer data, and obtain the first objective evaluation score of teaching.

[0053] It should be noted that the teaching platform uses an intelligent word segmentation model and a fuzzy matching algorithm to construct a dual-engine subjective question intelligent review model. During the construction process, a high-precision intelligent word segmentation model is obtained by training with a Transformer model. The intelligent word segmentation model is mainly used to perform semantic analysis and keyword extraction on the input employee answer data. The extracted word segmentation results can accurately reflect the key technical terms, concepts and logical associations in the employee's answer. The employee's answer data is used as input data and input into the constructed dual-engine subjective question intelligent review model to ensure that the data can be accessed and called between the engines of the model. In the fuzzy matching part, based on the predefined rule library and the dynamic threshold adjustment mechanism, the obtained word segmentation results are matched in multiple dimensions. The core of the fuzzy matching algorithm is to automatically calculate a quantitative matching score by comparing the matching degree between the employee's answer data and the standard answer data, and reflect the accuracy and completeness of the employee's subjective question answer based on this. The first objective evaluation score of the employee is obtained and output by combining the results of the above two engines.

[0054] S3: Obtaining a second objective evaluation score for the employee using a two-dimensional integral quantification formula based on the employee's learning-related data;

[0055] The employee's answer data is input into a two-dimensional integral quantification formula to obtain a second objective evaluation score, wherein the two-dimensional integral quantification formula is:

[0056] ;

[0057] Where, is the second objective assessment score; For the times open-book learning points; For the The weight coefficient of the open-book learning integral; For the Closed-book learning points; For the The weight coefficient of the closed-book learning integral;

[0058] The integral formula for open-book learning is:

[0059] ;

[0060] Where, For the times open-book learning points; Effective learning time for employees; is the effective learning time weight coefficient; Score employees' learning status; rate the learning environment for employees;

[0061] The closed-book learning integral formula is:

[0062] ;

[0063] Where, For the Closed-book learning points; The quality of employees' answers; is the answer quality weight coefficient; Score employees' learning status; Rate the learning environment for employees.

[0064] It should be noted that first, all relevant records are extracted from the pre-collected employee answer data. The answer data includes all information generated by employees during open-book learning and closed-book examinations. After pre-processing, the collected data will be input into the two-dimensional integral quantification formula in sequence.

[0065] in The effective learning time of employees is recorded, which records the total time that employees are in an effective learning state on the teaching platform. 1. Original time collection: Through the client or server log, record the total time from the employee entering the learning page (or starting the VR scene) to leaving the page (or exiting VR), which is recorded as ; 2. Invalid duration elimination: Away detection: When a user does not have any interaction (mouse movement, keystrokes, head tracking and voice detection) for a certain period of time (such as 30 consecutive seconds), it is considered to be in the "away" state, and the accumulated time is ; Hang up detection: If the VR device or client is detected to be in the background for a long time (such as minimized or lost focus), the corresponding time will also be counted ; Abnormal interruption elimination: In case of network interruption or system crash, the corresponding period will be eliminated through log mark; 3. Effective duration calculation: ; Among them, it should be ensured , and cut off the negative or too small values (such as less than 5 seconds) to avoid abnormal data interference;

[0066] To determine the effective learning time weight coefficient, we collected a large amount of employee learning data and final assessment scores or performance improvement indicators. Using effective learning time, status, environment, and answer quality as features and performance as labels, we trained a linear regression or tree model. The linear coefficient or feature importance index obtained from the model fitting was used as the effective learning time weight coefficient.

[0067] To assess the quality of employee answers, we comprehensively consider accuracy, completeness, and standardization, performing a weighted summation to obtain a normalized answer quality. We automatically compare employee answers with standard answers (for multiple-choice, true / false, and fill-in-the-blank questions) and calculate the ratio of correct answers to the total number of questions to obtain accuracy. We use a dual-engine intelligent review model for subjective questions (word segmentation + fuzzy matching) or a semantic similarity model (such as BERT / SBERT similarity) to extract a list of key points from the standard answers and check the proportion of key points hit in employee answers to obtain completeness. We also compare employee answers with template formats (paragraph structure and term list) to calculate the completeness of format symbols, or use regular rules and keyword lists to supply a rule library to check for non-standard wording and typos to obtain standardization.

[0068] The weight coefficient for answer quality is calculated based on the factory's internal teaching experts, course designers, HR, and data analysts. The relative importance of answer quality and other indicators (such as time, environment, and status) is compared pairwise or scored anonymously on a scale of 1-10. After the feedback is summarized, the anonymous statistical results can be seen in the second round and the scores can be revised. The final score average or weighted average is taken and normalized to obtain ;

[0069] Scoring employees' learning status reflects the number of effective interactions during the actual question-answering process; The employee's learning environment is scored. This score reflects the comparison between the employee's actual activity space and the preset standard space during the virtual reality question-answering process, as well as the similarity of the environment. All processed open-book learning points and closed-book learning points are multiplied by the corresponding weight coefficients and then accumulated to obtain the final second objective evaluation score.

[0070] Use the learning status scoring formula to obtain the employee's learning status score; and use the learning environment scoring formula to obtain the employee's learning environment score. The learning status scoring formula is:

[0071] ;

[0072] Where, Score employees' learning status; The number of effective interactions for answering real questions; The number of valid interactions for answering questions in VR; The total learning time in the actual test-taking process; The total learning time during the virtual reality question-answering process; The weight coefficient of the effective number of interactions for answering real questions; The weight of the number of page switching times in the real-world and virtual-reality question-answering processes; The number of page switches during the actual answering process; The number of page switches during the virtual reality question-answering process; The preset standard page switching times.

[0073] It should be noted that The number of effective interactions for real-world answering reflects the frequency of interaction between employees and the platform or teachers during the traditional answering process; The number of effective interactions in virtual reality quiz, reflecting the number of effective interactions of employees in the virtual quiz environment; The total learning time in the actual test-taking process; The total learning time during the VR question-answering process is used to normalize the number of interactions to ensure comparability of scores. The number of page switches during the actual answering process; is the number of page switching during the virtual reality question-answering process. The sum of the two is used to quantify the interference factors in the learning process; is the preset standard page switching number, which is used as a reference value under normal learning state; The weight coefficient of the number of effective interactions in real-world answering is usually more difficult to simulate. It can better reflect employees' real-time understanding and feedback of the content. The quality of the existing VR environment interaction should be improved due to technical controllability, immersion error and hardware differences. ;in exist In the early stages, the weights of reality and virtual interaction are close, and the balance between the two can be flexibly tested; in the In the long run, the weight of real-world interactions continues to increase, but the weight of virtual interactions tends to be saturated, to avoid the virtual interactions accounting for too much and distorting the evaluation results.

[0074] The learning environment scoring formula is:

[0075] ;

[0076] Where, rate the learning environment for employees; The actual activity space for employees to answer questions in virtual reality; A standard preset space for employees to answer questions in virtual reality; The similarity between the employees’ virtual reality learning environment and their real learning environment; Tuning parameters for weights.

[0077] It should be noted that the data on employees’ actual activity space when answering questions is collected to reflect the actual spatial range in which employees can move freely in the real environment when answering questions in virtual reality; The standard preset space for employees to answer questions in VR represents the spatial standards required in the real environment for normal VR answering. 1. Scenario Requirements Analysis: During the scenario deployment phase, the system administrator or training designer will conduct site measurements and experimental verification to set the required space. The specific process is to define the minimum range of activity based on the course type (such as mechanical principle demonstrations, assembly simulations, and fire evacuation drills); and to provide a lower limit for the space by referring to industry standards or safety regulations. 2. On-site measurement and verification: Measurements and field research are conducted at the training venue or the VR area in the employee's home to ensure that the venue at least meets the preset space requirements. Several test users will demonstrate the key points of the course actions to check whether there are no collisions or lags in the standard preset space. 3. Parameter entry: Enter the parameters.

[0078] The similarity between the employee's virtual reality learning environment and the employee's real learning environment is calculated by comparing environmental features (such as light, sound and layout). First, data collection is performed: 1. Visual features, real environment: multiple panoramic images are collected through the environment camera or the user's mobile phone; virtual environment: renderings of the corresponding scene are captured in VR (panoramic or multi-perspective); 2. Sound features, real environment: background sound is recorded using a microphone (volume, reverberation duration and spectrum distribution); virtual environment: ambient sound track output by the system (spectrum and reverberation index are also collected); 3. Spatial features, real environment: spatial geometry (wall distance, door and window position and furniture layout) is obtained through indoor mapping instrument or depth camera; virtual environment: scene geometry data provided by the engine The method uses pre-trained deep networks (such as ResNet and Vision-Transformer) to extract image feature vectors; calculates the Mel-spectrogram after extracting the short-time Fourier transform (STFT), and then obtains sound features through convolutional networks or PCA dimensionality reduction; voxelizes the three-dimensional geometry to a uniform resolution grid, and performs two-dimensional or three-dimensional convolution encoding on the occupied voxels to obtain spatial features; concatenates or weightedly fuses the visual, acoustic, and layout features, and finally uses cosine similarity to calculate the visual, acoustic, and layout similarities respectively, and then takes a weighted average to obtain the similarity between the employee's virtual reality learning environment and the employee's real learning environment;

[0079] Finally, the output results are normalized to ensure that the learning environment score matches the other scoring items, so that it occupies a reasonable weight in the overall multi-dimensional scoring system.

[0080] The actual activity space for employees when answering questions in virtual reality refers to the volume or area of physical space that employees actually occupy and move freely in virtual reality (VR) answering questions or interactive scenes. It reflects the degree to which employees need to complete VR learning in a real environment, including the behavioral scope of walking, interacting around poles, and waving arms. It is obtained through the following steps: 1. Trajectory data collection: Sample the 3D coordinates of the headset and handle at the beginning of learning, with a sampling frequency of usually 30-90Hz; record all position points during the entire effective interaction; 2. Spatial boundary reconstruction: Convex hull algorithm: Calculate the three-dimensional convex hull of the trajectory point set to obtain the minimum convex polyhedron; Bounding box: Or directly use the axis-aligned or direction-aligned minimum bounding box as the approximate boundary; 3. Volume calculation: Calculate the volume of the convex hull or OBB; or measure the actual size of the reserved space as the actual activity space for employees when answering questions in virtual reality;

[0081] To adjust the weight parameters, we invite several experimental users to learn in a variety of real environments and VR scenes. The expert team will score the comfort or satisfaction. The learning environment scoring formula is regarded as the model prediction value, which is aligned with the comfort score marked by the experts. The loss function is defined and the optimal solution is iterated on the offline samples using gradient descent. .

[0082] S4: Obtaining an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and managing the employee and the teaching platform according to the objective evaluation score;

[0083] S5: Adjust employees’ auxiliary learning based on their open-book learning points and closed-book learning points.

[0084] The virtual roles in virtual reality are divided into guiding roles and collaborative roles. The guiding role is a teaching role that dynamically adjusts the explanation rhythm according to the employees; the collaborative role is a student role that simulates the behavior of real students and participates in group discussions or asks questions. The ratio of guiding roles and collaborative roles in virtual reality is adjusted according to the employees' open-book learning points and closed-book learning points, and the total number of roles in the employees' virtual reality learning environment is adjusted using the role quantity adjustment formula.

[0085] It should be noted that in the intelligent teaching platform of joint virtual reality, in order to simulate the interaction and guidance effects in real teaching, virtual characters are divided into two categories: Guidance roles: This type of role mainly undertakes teaching responsibilities and can dynamically adjust the explanation rhythm according to the fluctuation of employees' points in the learning process. Guidance roles provide employees with real-time explanations and prompts through voice and animation display, making the teaching process smoother and more personalized; Collaboration roles: This type of role simulates the behavior of real students, participates in group discussions, asks questions or interacts, helps employees gain richer interactive experience in the virtual reality environment, and improves teamwork ability and comprehensive quality; when making auxiliary learning adjustments, the open-book learning points and closed-book learning points of employees are counted and compared When an employee's open-book learning score is significantly higher than his closed-book learning score, it is believed that the employee performs well in independent thinking and real-time interaction. At this time, the proportion of collaborative roles is increased to stimulate the employee's enthusiasm for participating in discussions and solving problems together. When an employee's open-book learning score is lower than or equal to his closed-book learning score, it is believed that the employee needs more guidance and explanation. At this time, the proportion of guiding roles is increased to provide employees with more targeted teaching explanations and operation prompts. The average of the open-book and closed-book scores is calculated based on the employee's historical score data, and the preset critical value and adjustment parameters are used to determine the total number of roles, so that the number of virtual roles (including guiding and collaborative types) can meet the needs of teaching interaction without causing information overload or interference.

[0086] The total number of roles includes the number of virtual roles and the number of real roles, wherein the role number adjustment formula is:

[0087] ;

[0088] Where, is the total number of roles; is the minimum integral adjustment value; is the maximum integral adjustment value; for The critical value of The average of the employee's historical open-book learning scores; The average of the employee's historical closed-book learning scores; is the adjustment parameter; To round up.

[0089] It should be noted that when Less than or equal to When Greater than or equal to , the function takes a linear value; when Greater than When the linear term is less than , the function remains ; Ensure that the total number of roles is within the preset range. In this embodiment It is the minimum score adjustment value and also the minimum total number of characters; It is the maximum score adjustment value and also the maximum total number of characters; for The critical value of The critical integral value is used to adjust the total number of characters.

[0090] When an employee's open-book learning points are greater than his / her closed-book learning points, the proportion of collaborative roles will be increased; when an employee's open-book learning points are less than or equal to his / her closed-book learning points, the proportion of guiding roles will be increased.

[0091] Example 2: Based on Example 1, a smart teaching platform management system combined with virtual reality, such as Figure 2 As shown, it also includes:

[0092] a data acquisition module, configured to acquire learning-related data of an employee and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee;

[0093] A first score acquisition module is configured to obtain a first objective evaluation score of the employee using a dual-engine subjective question intelligent review model based on the employee's learning-related data;

[0094] A second score acquisition module is used to obtain a second objective evaluation score of the employee using a two-dimensional integral quantification formula based on the employee's learning-related data;

[0095] a score acquisition management module, configured to obtain an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and to manage employees and the teaching platform according to the objective evaluation score;

[0096] The auxiliary learning adjustment module is used to adjust employees' auxiliary learning based on their open-book learning points and closed-book learning points.

[0097] The technical principles of the embodiments of the present invention have been described above in conjunction with specific embodiments. These descriptions are intended solely to explain the principles of the embodiments of the present invention and should not be construed in any way as limiting the scope of protection of the embodiments of the present invention. Based on the explanations herein, those skilled in the art will be able to conceive of other specific implementations of the embodiments of the present invention without inventive effort, and such implementations will fall within the scope of protection of the embodiments of the present invention.

Claims

1. A management method for a smart teaching platform combined with virtual reality, characterized by: The following steps are involved: S1: Acquire learning-related data of an employee, and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee; S2: Obtaining a first objective evaluation score for the employee using the dual-engine subjective question intelligent review model based on the employee's learning-related data; S3: Obtaining a second objective evaluation score for the employee using a two-dimensional integral quantification formula based on the employee's learning-related data; S4: Obtaining an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and managing the employee and the teaching platform according to the objective evaluation score; S5: Adjust employees’ auxiliary learning according to their open-book learning points and closed-book learning points; The method of using a dual-engine subjective question intelligent review model based on the employee's learning-related data to obtain the employee's first objective evaluation score includes: using an intelligent word segmentation model and a fuzzy matching algorithm to construct a dual-engine subjective question intelligent review model, inputting the employee's answer data into the dual-engine subjective question intelligent review model to obtain the first objective evaluation score, and using a Transformer model for training to obtain an intelligent word segmentation model, wherein the intelligent word segmentation model is used to perform semantic analysis and keyword extraction on the employee's answer data to obtain a word segmentation result; the fuzzy matching algorithm is based on a predefined rule library and a dynamic threshold adjustment mechanism to perform multi-dimensional matching on the word segmentation results, calculate the matching degree between the employee's answer data and the standard answer data, and obtain the first objective evaluation score of teaching; the method of using a two-dimensional integral quantization formula based on the employee's learning-related data to obtain the employee's second objective evaluation score includes: inputting the employee's answer data into the two-dimensional integral quantization formula to obtain the second objective evaluation score, wherein the two-dimensional integral quantization formula is: S=∑ i αi*x i +∑ j β j *y j ; Where S is the second objective evaluation score; x i is the integral of the i-th open-book study; α i is the weight coefficient of the i-th open-book learning integral; y j is the jth closed-book learning integral; β j is the weight coefficient of the j-th closed-book learning integral; The integral formula for open-book learning is: x i =T*W t *F s *F e ; Where x i is the score of the i-th open-book learning; T is the effective learning time of the employee; W t is the effective learning time weight coefficient; F s Score the employee's learning status; F e rate the learning environment for employees; The closed-book learning integral formula is: y j =Q*W q *F s *F e ; Where y j is the score of the jth closed-book study; Q is the quality of the employee's answer; W q is the answer quality weight coefficient; F s Score the employee's learning status; F e Rate the learning environment for employees.

2. A management method for a combined virtual reality intelligent teaching platform according to claim 1, characterized in that: The obtaining of the employee's learning-related data and determining the first objective evaluation score and the second objective evaluation score to be calculated based on the employee's learning-related data include: obtaining the employee's learning-related data, the employee's learning-related data including the employee's answer data, the employee's effective learning time, the employee's answer quality, the employee's learning status and the employee's learning environment; and obtaining the first objective evaluation score and the second objective evaluation score of the teaching based on the employee's learning-related data using a dual-engine subjective question intelligent review model and a dual-dimensional integral quantification formula.

3. The method for managing a combined virtual reality intelligent teaching platform according to claim 1, wherein: The F s Scoring the employee's learning status includes: using a learning status scoring formula to obtain the employee's learning status score; and using a learning environment scoring formula to obtain the employee's learning environment score, wherein the learning status scoring formula is: Where, F s Score the employee's learning status; n1 is the number of effective interactions in real-life answering; n2 is the number of effective interactions in virtual-reality answering; T1 is the total learning time in the real-life answering process; T2 is the total learning time in the virtual-reality answering process; γ1 is the weight coefficient of the number of effective interactions in real-life answering; γ2 is the weight of the number of page switches in the real-life answering process and the virtual-reality answering process; Y1 is the number of page switches in the real-life answering process; Y2 is the number of page switches in the virtual-reality answering process; Y0 is the preset standard number of page switches.

4. The method for managing a combined virtual reality intelligent teaching platform according to claim 1, wherein: The F e Rate the learning environment for employees, including: The learning environment scoring formula is: Where, F e Score the employee's learning environment; k is the employee's actual activity space when answering questions in virtual reality; k0 is the standard preset space when answering questions in virtual reality; k1 is the similarity between the employee's virtual reality learning environment and the employee's real learning environment; θ1 and θ2 are weight adjustment parameters.

5. The method for managing a combined virtual reality intelligent teaching platform according to claim 1 is characterized in that: The adjustment of employee assisted learning based on the employee's open-book learning points and the employee's closed-book learning points includes: dividing the virtual roles of virtual reality into guiding roles and collaborative roles, the guiding role is a teaching role that dynamically adjusts the explanation rhythm according to the employee; the collaborative role is a student role that simulates the behavior of real students and participates in group discussions or asks questions, adjusting the ratio of the guiding role and the collaborative role in virtual reality based on the employee's open-book learning points and the employee's closed-book learning points, and using the role quantity adjustment formula to adjust the total number of roles in the employee's virtual reality learning environment.

6. A management method for a combined virtual reality intelligent teaching platform according to claim 5, characterized in that: The total number of roles in the employee's virtual reality learning environment is adjusted using a role number adjustment formula, including: the total number of roles includes the number of virtual roles and the number of real roles, wherein the role number adjustment formula is: Where N 总 is the total number of roles; b is the minimum score adjustment value; c is the maximum score adjustment value; a is The critical value of The average of the employee's historical open-book learning scores; is the average of employees’ historical closed-book learning scores; ρ1 is the adjustment parameter.

7. The method for managing a combined virtual reality intelligent teaching platform according to claim 5, characterized in that: The adjustment of the ratio of guiding roles and collaborative roles in virtual reality based on the employee's open-book learning points and the employee's closed-book learning points includes: When an employee's open-book learning points are greater than his / her closed-book learning points, the proportion of collaborative roles will be increased; when an employee's open-book learning points are less than or equal to his / her closed-book learning points, the proportion of guiding roles will be increased.

8. A management system for a smart teaching platform in conjunction with virtual reality, according to a management method for a smart teaching platform in conjunction with virtual reality according to any one of claims 1 to 7, characterized in that: include: a data acquisition module, configured to acquire learning-related data of an employee and determine a first objective evaluation score and a second objective evaluation score to be calculated based on the learning-related data of the employee; A first score acquisition module is configured to obtain a first objective evaluation score of the employee using a dual-engine subjective question intelligent review model based on the employee's learning-related data; A second score acquisition module is used to obtain a second objective evaluation score of the employee using a two-dimensional integral quantification formula based on the employee's learning-related data; a score acquisition management module, configured to obtain an objective evaluation score by weighted summing the first objective evaluation score and the second objective evaluation score, and to manage employees and the teaching platform according to the objective evaluation score; The auxiliary learning adjustment module is used to adjust employees' auxiliary learning based on their open-book learning points and closed-book learning points.

Images