Teaching knowledge mining method, system and equipment based on VR intelligent education and medium

Abstract

The invention discloses a teaching knowledge mining method, system and device based on VR wisdom education and a medium, and relates to the technical field of knowledge mining, and the method comprises the steps: obtaining first behavior data of a learner, and constructing a VR model; according to the behavior data, generating a first-level learning path, and obtaining simulated learning effect data of each path; second behavior data are collected, and a second-level learning path is determined in combination with the simulation learning effect data; and acquiring the learned third behavior data and first health data, and comparing the learned third behavior data and first health data with the simulation effect data of the secondary learning path to form a feedback result. According to the teaching knowledge mining method based on VR wisdom education provided by the invention, the learning path is estimated and simulated, so that the unnecessary path exploration time is reduced, the optimal learning path is quickly determined, and the learner is ensured to achieve the best learning effect in the shortest time. The method has better effects in the aspects of learning content regulation and control, learning efficiency and individuation.

Description

Technical Field

[0001] The present invention relates to the field of knowledge mining technology, and specifically to a teaching knowledge mining method, system, device and medium based on VR smart education. Background Art

[0002] With the rapid development of information technology, online education and distance education have gradually become an important part of modern education. In particular, in recent years, the continuous advancement of technologies such as virtual reality (VR), augmented reality (AR), artificial intelligence (AI) and big data has brought new changes to the field of education. These emerging technologies provide more possibilities for teaching, break the limitations of traditional teaching methods, and make the learning process more interactive and immersive. However, despite the increasing application of these technologies in education, the current teaching platform still has some significant deficiencies in personalization and interactivity, which affects the improvement of learning effects.

[0003] Online education platforms (such as Coursera, edX, Udemy, etc.) enable learners around the world to access high-quality educational resources through the Internet. These platforms provide rich course content, including videos, texts, quizzes, etc., which help students learn independently. However, despite the rich content, this teaching method mainly based on videos and texts still lacks interactivity and is difficult to meet the needs of all learners.

[0004] Artificial intelligence technology is widely used in the field of education to achieve automated personalized teaching. Through machine learning algorithms, the system can analyze learners' behavioral data, infer their learning status, and recommend appropriate learning content for each learner. However, most existing AI education technologies are based on the analysis of static data, making it difficult to achieve real-time adjustment and multi-dimensional interaction.

[0005] With the continuous advancement of VR technology, its application in education has gradually increased. VR technology can provide learners with an immersive learning experience, and has been widely used in teaching in science, engineering, medicine and other fields. For example, VR can simulate dangerous chemical experiments, complex surgical operations and other scenes, helping students to practice safely in a virtual environment. However, existing VR teaching systems are often limited to the simulation of a single scene, lacking flexible knowledge point association and personalized learning path design.

[0006] Although these technologies have achieved certain results in education, the current teaching platforms still have some shortcomings in personalization, interactivity and intelligence. Most of the existing online education platforms are difficult to push personalized teaching content according to the actual situation of learners (such as learning ability, hobbies, health status, etc.). Many systems only make simple content recommendations based on learners' historical performance, without considering multi-dimensional data such as emotional state, physical health data, real-time feedback, etc., resulting in relatively single learning path design and difficulty in meeting learners' personalized needs. Traditional online learning mainly relies on videos and texts. This one-way teaching method lacks interactivity. Even in some VR teaching systems, although they can provide an immersive learning experience, most systems only support fixed 3D scene simulations and cannot interact deeply with learners. For example, learners cannot communicate with the system through voice, gestures, etc., nor can they customize the virtual scene according to their own learning needs. In addition, the feedback of existing systems in the teaching process is relatively single, and usually only learners' performance data can be obtained in the form of tests, but teaching strategies cannot be adjusted dynamically. Although the introduction of artificial intelligence technology has made personalized recommendations and automatic adjustment of learning paths possible, most systems are still based on offline data analysis and lack the ability to process real-time data. Learners' immediate emotional changes or health status fluctuations during the learning process are difficult to be quickly captured and responded to by the system, which causes the system to lag behind the actual needs of learners when providing personalized teaching, and cannot adjust the teaching content and difficulty in time according to the learners' emotional state or physical condition. The existing education system rarely takes into account the learners' physical and mental health. Although some systems can collect some physiological data of users (such as heart rate, number of steps, etc.), these data are usually used in the field of health management rather than education. The current teaching platform lacks in-depth mining and analysis of health data, and cannot dynamically adjust the learning content according to the learners' health status, ignoring the impact of health factors on learning efficiency during the learning process.

[0007] Most existing education platforms organize content by course or subject, and lack the ability to associate knowledge across disciplines. Learners may need to combine knowledge from multiple disciplines to solve complex problems during the learning process, but existing systems have difficulty automatically establishing these interdisciplinary associations. Knowledge graphs are used in some platforms, but they are usually static and lack the ability to dynamically update and adaptively adjust. Summary of the invention

[0008] In view of the above-mentioned problems, the present invention is proposed.

[0009] Therefore, the technical problems solved by the present invention are: the existing VR online education platform has insufficient personalization, low interactivity, insufficient data utilization, and how to effectively integrate real-time health data and emotional feedback to improve teaching quality.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions: A teaching knowledge mining method based on VR smart education, comprising obtaining the first behavior data of the learner and constructing a VR model. According to the behavior data, a first-level learning path is generated, and the simulated learning effect data of each path is obtained. The second behavior data is collected, and the second-level learning path is determined in combination with the simulated learning effect data. The third behavior data and the first health data after learning are obtained, and compared with the simulated effect data of the second-level learning path to form a feedback result.

[0011] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: the acquisition of the learner's first behavior data includes collecting the learner's behavior data in a virtual learning environment through a VR device.

[0012] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: generating a first-level learning path based on the behavior data includes using the behavior data to generate multiple first-level learning paths with different content structures and presentation orders, and each learning path is simulated according to the learner's personal situation.

[0013] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: the acquisition of simulated learning effect data of each path includes predicting the learning effect of each path based on historical data and related features.

[0014] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: the collecting of the second behavior data includes collecting the learner's current behavior data as the second behavior data, and the collected data type is the same as the first behavior data.

[0015] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: the determination of the secondary learning path includes comparing the learner's current behavior data and the simulation effect data of each path, determining the learning path with the best expected effect as the secondary learning path, and adapting to the learner's personalized needs and real-time status.

[0016] As a preferred solution of the teaching knowledge mining method based on VR smart education described in the present invention, wherein: the third behavior data and the first health data after learning are obtained, and compared with the simulated effect data of the secondary learning path to form a feedback result, including evaluating the effectiveness of the learning process by comparing the new behavior data collected in the actual learning process with the simulated learning effect data of the optimal path, integrating the differences in knowledge mastery, learning efficiency and physiological load into a comprehensive deviation score through a weighted scoring method, and performing feedback adjustment of knowledge mining based on the comprehensive score. When the comprehensive deviation score is ≥0.7, and the difference scores of at least two dimensions exceed the preset threshold values, it is identified that the learner cannot adapt to the current learning intensity and knowledge mining intensity, and the system immediately adjusts the learning path to enhance the learner's adaptability by reducing the difficulty of the content and increasing the rest time.

[0017] When 0.4≤comprehensive deviation score<0.7 is identified and the physiological load difference does not exceed the preset self-threshold, and only one of the knowledge mastery difference and learning efficiency difference exceeds the preset self-threshold, the learning effect is optimized by providing additional interesting auxiliary materials to guide learning interest.

[0018] When the comprehensive deviation score is <0.4, it means that the learning process is close to the expected effect and the existing learning path is maintained.

[0019] Another purpose of the present invention is to provide a teaching knowledge mining system based on VR smart education, which can comprehensively collect various behavioral data of learners, accurately understand the initial learning status of learners, and build a VR model that adapts to their personalized needs based on the data analysis results, providing accurate basic information for the generation of subsequent learning paths. This solves the problem that the current VR online education platform is not personalized enough.

[0020] As a preferred solution of the teaching knowledge mining system based on VR smart education described in the present invention, it includes: a data acquisition module, a learning effect evaluation module, and a path evaluation module. The data acquisition module is used to obtain the learner's first behavior data, second behavior data, third behavior data and first health data. The learning effect evaluation module is used to evaluate the learning effect of the learning path in combination with the expected indicators. The path evaluation module is used to compare with the simulation effect data of the secondary learning path to form a feedback result.

[0021] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a teaching knowledge mining method based on VR smart education.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a teaching knowledge mining method based on VR smart education.

[0023] Beneficial effects of the present invention: The teaching knowledge mining method based on VR smart education provided by the present invention reduces unnecessary path exploration time by estimating and simulating the learning path, quickly determines the optimal learning path, and ensures that learners achieve the best learning effect in the shortest time. Dynamic adjustment of the learning path ensures the continuity and adaptability of the personalized learning experience, so that learners can always obtain the most appropriate learning content and rhythm arrangement throughout the learning process. The present invention achieves better results in learning content regulation, learning efficiency and personalization. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 An overall flow chart of a teaching knowledge mining method based on VR smart education provided in the first embodiment of the present invention.

[0026] Figure 2 A module diagram of a teaching knowledge mining system based on VR smart education provided by a third embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0028] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a teaching knowledge mining method based on VR smart education, including: S1: Obtain learners’ first behavior data and build a VR model.

[0029] Furthermore, obtaining the first behavior data of the learner includes collecting the behavior data of the learner in the virtual learning environment through VR equipment. The behavior data of the learner is obtained through VR equipment. These devices include but are not limited to head-mounted displays (HMDs), handheld controllers, body tracking devices, etc. Through these devices, various behavior data of the learner in the virtual learning environment can be comprehensively collected. The specific collection methods include: Position and movement tracking: Using head-mounted displays and body tracking sensors, the system can record the learner's spatial position, movement path, and head and body orientation. Based on this data, the learner's attention to each element in the virtual environment and their movement habits can be analyzed.

[0030] Eye tracking, through the eye tracking technology integrated in VR devices, can accurately capture the learner's eye direction and gaze point. Eye data is used to analyze the learner's attention distribution, thereby judging their interest in and depth of understanding of specific knowledge points.

[0031] Gesture and operation analysis: Using handheld controllers or hand tracking technology, the system can record learners’ gestures and interactions with virtual objects, such as grabbing, pointing, and operating virtual devices. These data help evaluate learners’ operation skills and practical application capabilities.

[0032] Physiological response monitoring collects learners’ heart rate, eye movement speed, etc. This information is used to analyze learners’ emotional state and stress level.

[0033] Speech and communication analysis: If the VR environment supports voice interaction, voice data can be collected to analyze the learner’s inquiry content, tone, speaking speed, etc., in order to assess their language expression ability and level of comprehension.

[0034] It should be noted that building VR models is the focus of VR smart education. The construction of the model usually adopts NLP-based teaching content analysis and 3D model generation.

[0035] Natural language processing (NLP) technology is used to perform text analysis on teaching materials, extract keywords and core concepts, and build a hierarchical 3D model through the knowledge graph framework.

[0036] The TF-IDF algorithm is used to calculate the importance score of each word, and a preset threshold is set, and words above this threshold are used as keyword candidates.

[0037] Similar keywords are grouped into topics through clustering algorithms to form different knowledge nodes. For example, the content related to "force" and "motion" in a physics course can be divided into a subset.

[0038] Knowledge node association: Use knowledge graph technology to add relevant attributes and associations such as formulas and historical background to each node to form the initial hierarchical structure of the 3D model.

[0039] The stratification mainly includes three levels, namely the basic knowledge level, the intermediate knowledge level and the advanced application level. The three levels respectively assist learners in understanding, expanding and applying the mined knowledge.

[0040] The basic knowledge level is suitable for learners who are just beginning to learn new knowledge. The content is mainly about concept introduction and simple demonstration. The 3D model structure is relatively simple and demonstrates the core concepts. Taking learning physics as an example, when learning mechanics, a simple 3D animation showing the force on an object is used to emphasize the definition and basic properties of force.

[0041] For the knowledge points of the basic layer, the 3D model complexity of each node is measured by the number of faces and polygons, and the upper limit is set to 500 faces to ensure rendering efficiency.

[0042] When the system detects that the learner's mastery of basic knowledge points in a single exercise has reached more than 80% accuracy, it automatically unlocks the intermediate level content and provides more detailed interpretations such as formula derivations and more complex 3D demonstrations such as the interaction of forces between multiple objects.

[0043] The polygon count of the intermediate layer 3D model can be increased to 1000-2000 to show more details such as force direction and exploded illustration.

[0044] The advanced application layer is suitable for in-depth research or interdisciplinary applications. The 3D model will show complex systems, such as multi-degree-of-freedom vibration systems in physics, or associate cell metabolism processes with chemical reactions in biology. According to the learner's learning trajectory, the system monitors their learning time, exploration path coverage greater than 70%, and test question accuracy above 90%. When the above conditions are met, the system automatically unlocks the advanced level of 3D models and supports custom modification parameters, such as increasing friction or changing system boundary conditions.

[0045] It should also be noted that the first behavioral data includes learning time, interaction frequency, exploration path (i.e., the order in which knowledge points are visited during the learning process), accuracy of answering questions, learning speed, and attention data (through eye tracking and facial expression analysis).

[0046] S2: Generate a first-level learning path based on the behavioral data, and obtain the simulated learning effect data of each path.

[0047] Furthermore, based on the behavior data, generating the first-level learning path includes using the behavior data to generate multiple first-level learning paths with different content structures and presentation orders, each of which is simulated according to the individual situation of the learner. The first-level learning path system generates multiple learning paths based on different behavior data characteristics, and these paths are different in content structure and presentation order. There are four learning paths, namely: Fast progressive path: suitable for learners who master knowledge quickly and whose behavior data shows that they have strong autonomous learning ability. The design of the path includes reducing the dwell time on basic content, entering complex knowledge points more quickly, and encouraging interdisciplinary applications. This route mainly reduces repetitive learning and enhances the extended application of knowledge by combining it with the advanced application layer.

[0048] In-depth reinforcement path: suitable for learners who learn slowly and have difficulty understanding some knowledge points. The system will extend the explanation time of key knowledge points, increase practice sessions, and provide more related explanations between knowledge points. This route is mainly used in combination with the intermediate knowledge layer to achieve in-depth learning of knowledge.

[0049] Exploratory Path: For learners who prefer free exploration and jumping between knowledge points. The system will provide more open options, guide learners to choose the learning order independently, and push relevant supplementary materials.

[0050] Progressive path: for learners who have no basic knowledge or are new to the subject. The path starts with basic knowledge and gradually progresses to more complex content. The content is explained step by step to ensure that learners can fully master the basic content before going to a deeper level of learning. This route mainly achieves the learning of basic knowledge by combining it with the basic knowledge layer.

[0051] It should be noted that the system simulates each generated first-level learning path based on behavioral data. For example, the learner's historical learning records are used to simulate the learning effects under different paths and predict the learning progress and knowledge mastery of each path. Reinforcement learning algorithms (such as Q-learning) are used to optimize the order and content density of each knowledge point in each path to improve learning efficiency and comprehensive knowledge mastery.

[0052] During the simulation, the system uses evaluation indicators including completion time, degree of improvement in mastery, and cognitive load (by measuring changes in brain wave and eye movement data during the learning process). Based on these evaluation indicators, the system will select the most appropriate first-level learning path for the learner and dynamically adjust the path during the learning process.

[0053] It should also be noted that obtaining the simulated learning effect data of each path includes predicting the learning effect of each path based on historical data and related features. The causal inference method is used to clarify the causal relationship between different features. For example, the learner's emotional state and learning time may directly affect the learning effect, and the structure and presentation order of the learning path will indirectly affect the learning effect by affecting the learner's mastery of knowledge points.

[0054] Based on these causal relationships, a structural equation model (SEM) was constructed to analyze the direct and indirect effects between various characteristics through hypothesized paths.

[0055] Random forest regression is selected to predict the learning effect of each path. The target variables predicted for each path can include the learner's knowledge mastery, completion time, average score improvement rate, etc.

[0056] The ensemble learning method is used to perform weighted averaging of the prediction results of multiple models to improve the prediction accuracy.

[0057] The learning effect prediction is mainly based on the following indicators, and the system scores each path: Knowledge point mastery (K): predicts the learner's mastery of each knowledge point after completing learning under a certain path. It can be quantified as the correct answer rate or the test score of the knowledge point.

[0058] Learning time (T): predicts the total time required for learners to complete all tasks in the path.

[0059] Cognitive load (C): Quantifies the cognitive burden during the learning process based on physiological data (such as brain waves, eye movement changes, etc.), and is divided into three levels: low, medium, and high.

[0060] Knowledge point conversion rate (R): refers to the degree to which learners absorb and apply new knowledge points, using the influence on subsequent knowledge point tests as the evaluation criterion.

[0061] In order to select the optimal learning path, the system adopts a multi-objective optimization algorithm to comprehensively optimize the above four quantitative indicators (K, T, C, R), sets the objective function based on the four indicators, and determines the most suitable secondary learning path.

[0062] S3: Collect the second behavior data, combine it with the simulated learning effect data, and determine the secondary learning path.

[0063] Furthermore, feature extraction is performed after collecting the second behavior data, and the learning behavior data is segmented using sliding window technology to extract time series features, such as the trend of learning time in the last 10 minutes and the change in the correct answer rate. The physiological and emotional data are analyzed in the time domain and frequency domain to extract key indicators such as the mean and standard deviation of the heart rate and the spectral density of the eye movement frequency.

[0064] Perform statistical analysis on the interaction data to calculate the total number, frequency, and distribution of gesture and voice interactions.

[0065] The features of multi-source data such as learning behavior, emotions and physiological signals are fused into high-dimensional feature vectors, and the main feature dimensions are extracted through dimensionality reduction techniques such as principal component analysis (PCA) or linear discriminant analysis (LDA).

[0066] Learners' physiological and emotional data, such as fatigue status, may directly affect learning behavior data, such as learning time and answer accuracy, and thus indirectly affect learning outcomes. This causal relationship is quantified through Bayesian networks.

[0067] The relationship between interaction data and learning behavior can reflect the learner's learning strategy. For example, frequent gesture interactions and high-frequency knowledge point jumps may indicate that the learner tends to be "exploratory" learning, while fewer interactions and longer stays on a single knowledge point may indicate that the learner is a "deep learning type."

[0068] Based on the learning behavior and physiological data of the first 10 minutes, predict the learning effect of the next 10 minutes, such as the accuracy of answering questions and the mastery of knowledge points. Use long short-term memory networks to predict time series data.

[0069] It should be noted that determining the secondary learning path includes comparing the learner's current behavior data with the simulation effect data of each path, determining the learning path with the best expected effect as the secondary learning path, and adapting to the learner's personalized needs and real-time status. When the difference between the learner's current behavior data and the simulation effect data of each path is small or the best expected effect is not set, in order to select the optimal learning path, the system adopts a multi-objective optimization algorithm to comprehensively optimize the above four quantitative indicators (K, T, C, R), set the objective function based on the four indicators, and determine the most suitable secondary learning path.

[0070] S4: Obtain the third behavior data and the first health data after learning, and compare them with the simulation effect data of the secondary learning path to form feedback results.

[0071] Furthermore, the third behavior data and the first health data after learning are obtained and compared with the simulated effect data of the secondary learning path to form feedback results, including evaluating the effectiveness of the learning process by comparing the new behavior data collected in the actual learning process with the simulated learning effect data of the optimal path, integrating the differences in knowledge mastery, learning efficiency and physiological load into a comprehensive deviation score through a weighted scoring method, and performing feedback adjustment of knowledge mining based on the comprehensive score. When the comprehensive deviation score is ≥0.7 and the difference scores of at least two dimensions exceed the preset self-thresholds, it is identified that the learner cannot adapt to the current learning intensity and knowledge mining intensity, and the system immediately adjusts the learning path to enhance the learner's adaptability by reducing the difficulty of the content and increasing the rest time.

[0072] The first health data may be heart rate, blinking frequency, gaze time, etc.

[0073] When 0.4≤comprehensive deviation score<0.7 is identified and the physiological load difference does not exceed the preset self-threshold, and only one of the knowledge mastery difference and learning efficiency difference exceeds the preset self-threshold, the learning effect is optimized by providing additional interesting auxiliary materials to guide learning interest.

[0074] When the comprehensive deviation score is <0.4, it means that the learning process is close to the expected effect and the existing learning path is maintained.

[0075] It should be noted that three behavioral data collections were conducted. The first behavioral data collection was conducted at the beginning of the learner's entry into the virtual learning environment, with the purpose of providing basic information for the learner's personalized learning path and VR model construction. The second behavioral data collection was conducted after the learner started the first-level learning path, and was used to monitor the learner's learning process and status in real time. The data type was the same as the first behavioral data type, and was collected every 10 minutes after the learner started learning. The purpose was to dynamically adjust the learning path based on these data, generate a second-level learning path, and make the learning experience more in line with the learner's real-time needs. The third behavioral data was used to evaluate the learning effect and feedback adjustment to ensure that the goal of the second-level learning path was achieved. The data type of the third behavioral data was different from the first and second behavioral data, including but not limited to the accuracy of answering questions, the dwell time of a single test question, the number of touches, the number of answer changes, etc. By comparing the third behavioral data with the simulated learning effect data, the system can judge the applicability of the learning path and make further optimizations.

[0076] Example 2, an embodiment of the present invention, provides a teaching knowledge mining method based on VR smart education. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0077] First of all, the purpose of this experiment is to verify the effect of collecting learners' behavioral data through the VR smart education system to generate and optimize personalized learning paths. The experimental subjects are 10 students from a high school (5 of whom are science students and 5 are liberal arts students), who participated in a learning experiment on the "mechanics" knowledge of the high school physics course. During the experiment, high-end VR equipment, including head-mounted displays (HMDs), handheld controllers, and body tracking devices, were used to collect learners' first behavioral data in the virtual learning environment. The data types include position and movement tracking, eye tracking, gesture and operation analysis, physiological response monitoring, and voice interaction analysis. The experiment lasted for 5 days, with 2 hours of learning per day.

[0078] Before the experiment began, a VR teaching model based on natural language processing (NLP) technology was built for learners. The specific process is as follows: We conduct text analysis on mechanics textbooks and extract core concepts such as "force", "motion", and "energy". We use the TF-IDF algorithm to filter out words with high importance, and use the clustering algorithm to group similar keywords to form multiple knowledge nodes.

[0079] Construct a hierarchical 3D model, including the basic knowledge layer, intermediate knowledge layer and advanced application layer. The basic knowledge layer uses simplified animation to show the basic definition of force and the 3D effect of the force on the object. The intermediate layer adds a detailed interpretation of the force direction. The advanced application layer introduces the demonstration of a multi-degree-of-freedom vibration system.

[0080] The system records learners’ behavior data in real time. The first behavior data includes learning time, exploration path, correct answer rate, attention data (time of gaze retention and change of gaze point), gesture operation frequency, physiological response (heart rate, eye movement speed), etc. These data are used to preliminarily generate personalized first-level learning paths.

[0081] In the second phase of the experiment, four primary learning paths were generated based on the first behavior data: fast progressive path, deep reinforcement path, exploratory path, and progressive path. By simulating learning effect data, the system selects the most suitable path for each learner and monitors the learner's second behavior data in real time during the learning process to dynamically adjust the learning path. The collected second behavior data is feature extracted through sliding window technology to obtain real-time learning time trends, changes in answer accuracy, and changes in physiological load.

[0082] Finally, feedback adjustment is performed by comparing the third behavior data after learning with the simulation effect data. The system adjusts the learning path according to the comprehensive deviation score and adopts different adjustment strategies according to different score results.

[0083] Table 1 Experimental data comparison table , Through the analysis of the table data, it can be seen that the use of the present invention to generate and optimize personalized learning paths has significant advantages. The data show that different path types have different effects on learners' learning effects and cognitive load. For example, students who adopted the fast progressive path (students A, E, I) performed well in terms of correct answer rate (85%, 88%, 86%) and exploration path coverage (80%, 85%, 83%), and the average heart rate was relatively low (70-75 times / minute), which shows that the fast progressive path can effectively improve learning efficiency and reduce cognitive load. This path is suitable for learners who master knowledge quickly and have strong autonomous learning ability.

[0084] On the other hand, the students who chose the deep reinforcement path (students B, F, and J) had a lower accuracy rate (62%-65%) and a higher cognitive load (heart rate averaged 82-85 beats / minute), indicating that this path is more challenging for learners with weaker knowledge understanding. However, this path provides more detailed interpretation and repeated practice opportunities, which helps to improve the knowledge mastery level of learners with weak foundations. The use of the deep reinforcement path can ensure in-depth knowledge mastery by extending the learning time (90-100 minutes) for students with slower learning speed.

[0085] Students who took the exploratory path (students C and G) performed well in terms of exploration path coverage (90%, 88%) and correct answer rate (78%, 79%), with a moderate cognitive load. This shows that the free exploration learning method helps to stimulate learners' interest and promote active learning. However, for students who learn relatively slowly or have a weaker knowledge base, appropriate guidance may be needed to improve learning efficiency.

[0086] Although the students in the progressive path (students D and H) took longer to study (110-120 minutes), their accuracy rate remained high (77%-80%) and their cognitive load was low (heart rate 70-72 beats / minute). This path is suitable for learners with no basic knowledge, and ensures the gradual mastery of knowledge by gradually deepening from basic knowledge to complex content.

[0087] In summary, the experiments show that the present invention can not only accurately construct a personalized learning model through the collection of first-behavior data, but also dynamically adjust the learning path during the learning process to meet the actual needs of the learners. Compared with the traditional fixed teaching model, the present invention significantly improves learning efficiency and knowledge mastery, while reducing the cognitive load of learners, especially in dealing with the personalized needs of different learners. By integrating multiple data collection and analysis methods, the present invention effectively solves the problem of difficulty in optimizing dynamic learning paths for individuals in the prior art, and has high innovation and practicality.

[0088] Example 3, reference Figure 2 , is an embodiment of the present invention, which provides a teaching knowledge mining system based on VR smart education, including a data acquisition module, a learning effect evaluation module, and a path evaluation module.

[0089] The data collection module is used to obtain the learner's first behavior data, second behavior data, third behavior data and first health data. The learning effect evaluation module is used to evaluate the learning effect of the learning path in combination with the expected indicators. The path evaluation module is used to compare with the simulation effect data of the secondary learning path to form a feedback result.

[0090] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0091] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0092] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0093] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logical function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A teaching knowledge mining method based on VR smart education, characterized in that: include: Obtain learners’ first behavior data and build a VR model; Generate a first-level learning path based on the behavior data, and obtain simulated learning effect data of each path; Collect the second behavior data and combine it with the simulated learning effect data to determine the secondary learning path; The third behavior data and the first health data after learning are obtained, and compared with the simulation effect data of the secondary learning path to form a feedback result.

2. The teaching knowledge mining method based on VR smart education as claimed in claim 1, characterized in that: The obtaining of the first behavior data of the learner includes collecting the behavior data of the learner in the virtual learning environment through a VR device.

3. The teaching knowledge mining method based on VR smart education as claimed in claim 2, characterized in that: Generating a primary learning path according to the behavior data includes utilizing the behavior data to generate a plurality of primary learning paths having different content structures and presentation orders, each learning path being simulated according to the individual circumstances of the learner.

4. The teaching knowledge mining method based on VR smart education as claimed in claim 3 is characterized by: The obtaining of the simulated learning effect data of each path includes predicting the learning effect of each path based on historical data and related features.

5. The teaching knowledge mining method based on VR smart education as claimed in claim 4, characterized in that: The collecting of the second behavior data includes collecting the learner's current behavior data as the second behavior data, and the collected data type is the same as the first behavior data.

6. The teaching knowledge mining method based on VR smart education as claimed in claim 5, characterized in that: Determining the secondary learning path includes comparing the learner's current behavior data and the simulation effect data of each path, determining the learning path with the best expected effect as the secondary learning path, and adapting to the learner's personalized needs and real-time status.

7. The teaching knowledge mining method based on VR smart education as claimed in claim 6, characterized in that: The obtaining of the third behavior data and the first health data after learning and comparing them with the simulated effect data of the secondary learning path to form a feedback result includes evaluating the effectiveness of the learning process by comparing the new behavior data collected in the actual learning process with the simulated learning effect data of the optimal path, integrating the differences in knowledge mastery, learning efficiency and physiological load into a comprehensive deviation score through a weighted scoring method, and performing feedback adjustment of knowledge mining based on the comprehensive score. When the comprehensive deviation score is ≥0.7, and the difference scores of at least two dimensions exceed the preset self-threshold value, it is identified that the learner cannot adapt to the current learning intensity and knowledge mining intensity, and the system immediately adjusts the learning path to enhance the learner's adaptability by reducing the difficulty of the content and increasing the rest time; When 0.4≤comprehensive deviation score<0.7 is identified and the physiological load difference does not exceed the preset self-threshold, and only one of the knowledge mastery difference and learning efficiency difference exceeds the preset self-threshold, the learning effect is optimized by providing additional interesting auxiliary materials to guide learning interest; When the comprehensive deviation score is <0.4, it means that the learning process is close to the expected effect and the existing learning path is maintained.

8. A system using the teaching knowledge mining method based on VR smart education as described in any one of claims 1 to 7, characterized in that: Including data collection module, learning effect evaluation module, and path evaluation module; The data collection module is used to obtain the learner's first behavior data, second behavior data, third behavior data and first health data; The learning effect evaluation module is used to evaluate the learning effect of the learning path in combination with the expected indicators; The path evaluation module is used to compare with the simulation effect data of the secondary learning path to form a feedback result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the teaching knowledge mining method based on VR smart education described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the teaching knowledge mining method based on VR smart education described in any one of claims 1 to 7 are implemented.

Images