A generation method and system of interdisciplinary teaching based on virtual-real integration

Abstract

The present invention relates to the technical field of teaching scene generation, and discloses a generation method and system of interdisciplinary teaching based on virtual-real integration, the system comprising: an image acquisition module for acquiring and processing image information of interdisciplinary teaching courses, and an information acquisition module for extracting interdisciplinary teaching information in images. A personnel acquisition module performs evaluation based on the number of participating users and their learning concentration. A relationship map establishment module generates teaching scenes based on teaching information and subject information, determines the number of roles, and constructs a relationship map between roles and scenes, while determining the content of the roles' lines. A mapping module assigns a suitable role to each participant based on the user's learning concentration, ensures the match between the role and the user, and improves the teaching effect. The present invention uses an interdisciplinary teaching system that integrates virtual and real, accurately matches teaching content with user needs, realizes personalized role allocation and teaching scene construction, thereby improving learners' participation and concentration and optimizing teaching effects.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching scene generation, and in particular to a method and system for generating interdisciplinary teaching based on virtual-real integration. Background Art

[0002] In the current education field, the traditional teaching model is often limited to imparting knowledge of a single subject, which is difficult to meet the needs of cultivating students' interdisciplinary comprehensive abilities. With the development of information technology, the introduction of technologies such as virtual reality and augmented reality has provided new opportunities for educational innovation, especially in the field of interdisciplinary teaching. Through the integration of virtual and reality, a more vivid and interactive teaching method can be achieved.

[0003] However, existing virtual reality teaching systems often lack the precise matching of teaching content and user needs, resulting in poor personalization and flexibility of teaching results. Especially in the design process of interdisciplinary teaching, how to effectively integrate knowledge from multiple disciplines and generate appropriate teaching scenarios is a technical challenge. Most of the existing educational technology systems rely on traditional teaching methods, mainly through teacher-led explanations to complete knowledge transfer, and lack a systematic and multi-dimensional teaching scenario generation mechanism. In addition, although there are some teaching systems based on image processing and artificial intelligence technology, they often focus on the presentation of knowledge in a single discipline, do not fully consider the learners' participation and concentration, and cannot provide customized learning experiences according to the personalized needs of different learners.

[0004] Therefore, there is an urgent need to invent an interdisciplinary teaching technology to solve the problem of how to effectively integrate multidisciplinary knowledge, generate personalized teaching scenarios, and dynamically adjust teaching content according to learners' participation and concentration, so as to overcome the problems of existing virtual reality teaching systems in teaching content matching and user demand adaptation. Summary of the invention

[0005] In view of this, the present invention proposes a generation method and system for interdisciplinary teaching based on virtual-reality fusion, aiming to solve the problems of virtual reality teaching systems in current technology in terms of teaching content matching and user demand adaptation.

[0006] The present invention proposes a generation system of interdisciplinary teaching based on virtual-real integration, comprising:

[0007] An image acquisition module is configured to acquire image information of an interdisciplinary teaching course and perform image processing on the image information;

[0008] an information acquisition module, electrically connected to the image acquisition module, and configured to extract teaching information from the image information;

[0009] A personnel acquisition module is configured to acquire the number of users to be involved and the degree of concentration of the users to be involved in the course learning;

[0010] A relationship map establishment module is electrically connected to the personnel acquisition module and the information acquisition module respectively, and the relationship map establishment module is configured to acquire related subject information according to the teaching information, and generate a teaching scene according to the teaching information and a plurality of subject information; the relationship map establishment module is further configured to determine the number of roles in the teaching scene according to the number of personnel, and to construct a relationship map between the roles and the teaching scene; the relationship map establishment module is further configured to determine the lines of the roles according to the relationship map;

[0011] A mapping module is electrically connected to the relationship map establishing module, and is configured to determine the role played by each of the participating users according to the course learning concentration and perform mapping.

[0012] Furthermore, when the image acquisition module performs image processing on the image information, it includes:

[0013] The image acquisition module is further configured to perform denoising on the image information, and compare the contrast in the denoised image information with a preset contrast pre-configured by the image acquisition module, wherein:

[0014] If the contrast is lower than the preset contrast, the image acquisition module enhances the contrast of the image information after denoising;

[0015] If the contrast is higher than or equal to the preset contrast, the image acquisition module does not enhance the contrast of the image information after the denoising process, and performs grayscale processing on the image information after the denoising process.

[0016] Furthermore, when the information acquisition module is configured to extract the teaching information from the image information, it includes:

[0017] The information acquisition module is further configured to extract text content from the grayscale processed image information and generate a record document according to the text content;

[0018] The information acquisition module is further configured to acquire multiple teaching subjects of the teaching course, divide the course according to the learning content of the main subject and the related subjects, and establish noun features according to the noun concepts in each of the learning contents after the course division;

[0019] The information acquisition module is further configured to extract noun information from the record document, perform matching between the noun information and the noun features, and determine the teaching information in the image information according to the matching result.

[0020] Furthermore, when the personnel acquisition module is configured to acquire the number of users to be involved and the course learning concentration of the users to be involved, it includes:

[0021] The personnel acquisition module is configured to generate test questions according to the teaching information to test each of the users to be tested, and obtain the average test score of each of the users to be tested;

[0022] The personnel acquisition module is further configured to determine the course learning score of each of the to-be-participated users according to the relationship between the test score mean and the test score full score, and use the course learning score as the course learning basic concentration of each of the to-be-participated users;

[0023] The personnel acquisition module is further configured to determine an adjustment coefficient according to the score difference between the test score of the user to be involved and the test score mean, and determine the basic course learning concentration adjusted according to the adjustment coefficient as the course learning concentration of the user to be involved;

[0024] Wherein, the personnel acquisition module is pre-configured with a first preset score difference and a second preset score difference, and the first preset score difference is smaller than the second preset score difference;

[0025] When the score difference is less than the first preset score difference, the personnel acquisition module determines that the adjustment coefficient is L1;

[0026] When the score difference is greater than or equal to the first preset score difference, and the score difference is less than the second preset score difference, the personnel acquisition module determines that the adjustment coefficient is L2;

[0027] When the score difference is greater than or equal to the second preset score difference, the personnel acquisition module determines that the adjustment coefficient is L3;

[0028] Among them, L1<L2<L3<1.

[0029] Furthermore, the personnel acquisition module is further configured to determine the course learning score of each of the to-be-participated users according to the relationship between the test score mean and the test score full score, including:

[0030] The personnel acquisition module is further configured to acquire a test score difference between the test score mean and the full test score, and determine a course learning score for each of the to-be-participated users according to a relationship between the test score difference and a first preset test score difference and a second preset test score difference preconfigured by the personnel acquisition module;

[0031] When the test score difference is less than the first preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q1;

[0032] When the test score difference is greater than or equal to the first preset test score difference, and the test score difference is less than the second preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q2;

[0033] When the test score difference is greater than or equal to the second preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q3;

[0034] Wherein, the first preset test score difference is smaller than the second preset test score difference, and Q1<Q2<Q3.

[0035] Furthermore, when the relationship map establishment module is configured to obtain related subject information according to the teaching information and generate a teaching scenario according to the teaching information and the subject information, it includes:

[0036] The relationship map establishment module is further configured to perform word annotation processing on the teaching information, and extract the teaching content in the teaching information after the word annotation processing, wherein the word annotation processing includes: word segmentation processing, part-of-speech tagging processing and vocabulary standardization processing;

[0037] The relationship map establishment module is further configured to extract key concepts, terms and associated context information in the teaching content and specific entities and subject classifications in the teaching content based on natural language processing technology;

[0038] The relationship map establishment module is further configured to obtain the causal relationship, the contextual relationship or the category relationship between each of the key concepts based on the associated context information, and determine the role of each of the key concepts in the teaching content and the logical relationship between the key concepts in the teaching content;

[0039] The relationship graph establishment module is also configured to associate the key concepts, terms and specific entities with each subject, and construct a multidimensional knowledge graph across disciplines, obtain relevant subject information in the multidimensional knowledge graph based on the key concepts, and generate the teaching scenario based on the relevant subject information and key concepts.

[0040] Furthermore, the relationship map establishment module is further configured to determine the number of preset roles in the teaching scene according to the number of personnel, and to construct a relationship map between the role-playing roles and the teaching scene, including:

[0041] The relationship map establishment module is further configured to determine the number of roles to be played according to the relationship between the number of personnel and the number of preset roles in the teaching scene;

[0042] When the number of personnel is consistent with the preset number of roles, the relationship map establishment module determines that the number of roles played is the preset number of roles;

[0043] When the number of personnel is inconsistent with the preset number of roles, the relationship map establishment module determines the number of roles to be the number of personnel, wherein:

[0044] The relationship map establishment module is further configured to obtain the correlation between each of the playing roles and the teaching scene, and determine the adjustment coefficient according to the relationship between the number of preset roles and the number of personnel, and obtain the playing role to be played according to the correlation range adjusted by the adjustment coefficient;

[0045] The relationship map building module is also configured to construct the relationship map according to the correlation between the role-playing role and the teaching scene.

[0046] Furthermore, when the relationship map establishment module determines the adjustment coefficient according to the relationship between the number of preset roles and the number of personnel, it includes:

[0047] The relationship map establishment module is further configured to obtain a quantity difference between the preset number of roles and the number of personnel, and determine the adjustment coefficient according to a relationship between the quantity difference and a first preset quantity difference and a second preset quantity difference preconfigured by the relationship map establishment module;

[0048] When the quantity difference is less than the first preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W1;

[0049] When the quantity difference is greater than or equal to the first preset quantity difference, and the quantity difference is less than the second preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W2;

[0050] When the quantity difference is greater than or equal to the second preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W3;

[0051] Among them, zero is less than the first preset number difference is less than the second preset number difference, and W1<0<W2<W3.

[0052] Furthermore, when the mapping module is configured to determine the role played by each of the waiting participating users according to the course learning concentration, it includes:

[0053] The mapping module is further configured to sort the courses in reverse order according to their learning concentration;

[0054] The mapping module is further configured to determine the difficulty of the role-playing according to the lines of each role-playing character and the introduction of the role-playing character;

[0055] The mapping module is further configured to sort the roles in ascending order according to the difficulty of each role played, and determine the relationship between each course learning concentration and each role played according to the sorted numbers;

[0056] The mapping module is further configured to determine the role played by each of the participating users according to the relationship and perform mapping.

[0057] Compared with the prior art, the beneficial effect of the present invention is that the personalized generation of interdisciplinary teaching scenes is realized through the virtual-real fusion technology, thereby greatly improving the flexibility and interactivity of teaching. The traditional teaching mode is usually led by teachers, and the fixed course content and learning methods make it difficult to flexibly adjust the teaching process and meet the personalized learning needs of different students. However, the present application can capture and process the teaching content in real time through the image acquisition module and the information acquisition module, and convert it into structured teaching information, which provides technical support for the precise matching of teaching content. Combined with the interdisciplinary knowledge fusion, it can automatically generate teaching scenes associated with the subject, providing students with a rich learning experience. In addition, the relationship map establishment module can automatically construct the subject information map associated with the course content according to the teaching information and subject knowledge, ensuring that the interdisciplinary knowledge points can be organically combined to form a multi-dimensional and three-dimensional teaching scene. This interdisciplinary scene generation method can break through the limitations of traditional teaching, prompt students to understand the inherent connection between different subjects in interaction, and stimulate students' comprehensive thinking ability. In the cross-integration of subject knowledge, students can deeply understand the application scenarios of knowledge points through practice and experience, and improve their interdisciplinary comprehensive literacy. In terms of role allocation, the mapping module dynamically adjusts the roles played by learners according to their concentration and participation, and sets corresponding lines according to different roles. This mechanism can better stimulate students' interest in learning and sense of participation by accurately matching learners' concentration and needs. Different learners play different roles in the same teaching scenario, which can stimulate students to think and learn actively through the interactive way of role-playing, thereby improving students' learning motivation and effectiveness. Especially in interdisciplinary teaching, students can not only deepen their understanding of subject content through the interaction of multiple roles, but also cultivate teamwork and the ability to solve complex problems.

[0058] On the other hand, the present application also provides a generation method of interdisciplinary teaching based on virtual-real integration, including:

[0059] Acquire image information of the teaching course, and perform image processing on the image information;

[0060] Extracting teaching information from the image information, acquiring related subject information according to the teaching information, and generating a teaching scene according to the teaching information and subject information;

[0061] Obtaining the number of users to be involved and the degree of concentration of the users to be involved in the course learning, determining the number of roles to be played in the teaching scene according to the number of users, and constructing a relationship map between the roles to be played and the teaching scene;

[0062] Determine the lines of the role-playing character according to the relationship map;

[0063] The role played by each of the participating users is determined according to the course learning concentration, and mapping is performed.

[0064] It can be understood that the generation method and system of interdisciplinary teaching based on virtual-real integration in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be described in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0066] Figure 1 A functional block diagram of a generation system of interdisciplinary teaching based on virtual-real integration provided by an embodiment of the present invention;

[0067] Figure 2 A flowchart of a method for generating interdisciplinary teaching based on virtual-reality fusion provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0069] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a generation system for interdisciplinary teaching based on virtual-real fusion, including: an image acquisition module, an information acquisition module, a personnel acquisition module, a relationship map establishment module and a mapping module.

[0070] Specifically, the image acquisition module is configured to acquire image information of the teaching course and perform image processing on the image information. The information acquisition module is electrically connected to the image acquisition module, and the information acquisition module is configured to extract teaching information from the image information. The personnel acquisition module is configured to acquire the number of users to be involved and the course learning concentration of the users to be involved. The relationship map establishment module is electrically connected to the personnel acquisition module and the information acquisition module respectively, and the relationship map establishment module is configured to acquire related subject information according to the teaching information, and generate a teaching scene according to the teaching information and the subject information. The relationship map establishment module is also configured to determine the number of roles played in the teaching scene according to the number of personnel, and to construct a relationship map between the roles played and the teaching scene. The relationship map establishment module is also configured to determine the lines of the roles played according to the relationship map. The mapping module is electrically connected to the relationship map establishment module, and the mapping module is configured to determine the roles played by each user to be involved according to the course learning concentration, and to perform mapping.

[0071] It can be seen that the teaching images are acquired through the image acquisition module, and the teaching information is extracted from them in combination with the information acquisition module, and then the teaching information is associated with the relevant subject knowledge through the relationship map establishment module to construct a multi-dimensional teaching scene. At the same time, the mapping module intelligently assigns roles and generates corresponding lines according to the number of participating users and their learning concentration, to ensure that each learner participates in the teaching link that suits them according to their personal needs, thereby enhancing the interactivity and personalization of the learning experience.

[0072] It can be understood that the image acquisition module captures and processes the image information of the teaching course to extract the key teaching elements in the image. The information acquisition module is linked with the image acquisition module to further deconstruct the image information, automatically identify and extract the teaching information, including the teaching elements in the text and image. In this way, valuable teaching content can be extracted from the rich visual information, laying the foundation for the subsequent generation of teaching scenes. This module provides highly flexible and automated content acquisition capabilities through image processing and information extraction technology, so that it can dynamically adapt to different teaching contents. Next, after receiving the teaching information and subject data, the relationship map establishment module automatically associates the relevant subject knowledge and generates a comprehensive teaching scene based on these data. By deeply mining the relationship between subjects, the relationship map establishment module can organically integrate the knowledge points of each subject and dynamically adjust the teaching content according to the needs of the scene and the user's participation. The construction of this knowledge map makes the teaching process no longer limited to a single subject, but can integrate knowledge from different fields across disciplines and realize the cross-integration of knowledge. This process not only optimizes the presentation of teaching content, but also enables interdisciplinary knowledge to be better understood and applied in actual teaching. In addition, the personnel acquisition module further optimizes the design of teaching scenarios and role allocation by analyzing the number of users participating and their learning concentration. By dynamically monitoring the learner participation, the number of roles and the way of role allocation can be automatically adjusted to better adapt to the learning progress and needs of different students. The relationship map establishment module generates matching teaching roles according to the learner participation and designs the role's lines. The content of the role's lines not only helps students understand the teaching content, but also enhances the learning experience through interaction, allowing students to better absorb knowledge in contextualized teaching scenarios. Finally, the mapping module intelligently allocates roles according to the course learning concentration, and assigns each learner the role that best suits their current learning status. This mechanism can not only enhance the interactivity of learning, but also improve the learner's sense of participation and immersion, and avoid students from having too much passive acceptance in the learning process. Through this dynamic adjustment method, the mapping module can achieve accurate adaptation of learners and effectively improve the effect of interdisciplinary teaching.

[0073] Specifically, when the image acquisition module performs image processing on the image information, it includes: the image acquisition module is also configured to perform denoising processing on the image information, and compare the contrast in the image information after denoising processing with the preset contrast pre-configured by the image acquisition module, wherein: if the contrast is lower than the preset contrast, the image acquisition module enhances the contrast of the image information after denoising processing. If the contrast is higher than or equal to the preset contrast, the image acquisition module does not enhance the contrast of the image information after denoising processing, and performs grayscale processing on the image information after denoising processing.

[0074] It is understandable that the image acquisition module first performs denoising on the collected image information to eliminate interference noise in the image and improve the clarity of the image. Then, the image quality is judged by comparing the contrast of the image with the preset standard contrast. If the contrast of the image is lower than the preset value, the system will automatically enhance the contrast of the image to improve the visual clarity of the image; if the contrast is high enough, the contrast is not enhanced, but grayscale processing is performed to further simplify the image content and highlight key information.

[0075] Specifically, when the information acquisition module is configured to extract teaching information from the image information, it includes: the information acquisition module is also configured to extract text content from the grayscale processed image information, and generate a record document based on the text content. The information acquisition module is also configured to obtain the teaching subjects of the teaching course, divide the courses according to the learning content of the teaching subjects, and establish noun features according to the nouns in each learning content after the course division. The information acquisition module is also configured to extract noun information from the record document, match the noun information with the noun feature, and determine the teaching information in the image information based on the matching result.

[0076] It can be understood that the information acquisition module converts the image into operable text data by extracting the text content in the grayscale processed image, and generates a record document to ensure the preservation and subsequent processing of the text information. Then, by obtaining the teaching subjects of the course and dividing the course based on the subject content, a basis is provided for the subsequent establishment of noun features. The establishment of noun features is to classify and annotate the professional nouns in the course content in order to conduct an in-depth analysis of the teaching information. The information acquisition module then extracts the noun information in the record document and matches it with the established noun features to accurately determine the teaching information contained in the image. This technical principle uses multi-level and multi-step information extraction and matching to enable the teaching content in the image to be consistent with the course objectives and knowledge points, ensuring that the extracted information is highly relevant and practical for teaching.

[0077] Specifically, the image is grayed out by the image acquisition module, thereby converting the detailed information in the image into text data that is easy to parse. This step not only eliminates the excess noise in the image, but also standardizes the expression of the image content into text form, ensuring that the system can efficiently extract the key information. The information acquisition module then extracts the text content from the grayed image and generates a record document for subsequent operations and data storage. Once the record document is generated, the course content is further divided according to the learning objectives and syllabus of the course by analyzing the teaching subjects of the course. Each part of the learning content has corresponding professional terms and nouns, which have specific meanings in different disciplines and fields. The information acquisition module annotates and classifies the nouns in each learning content by establishing a noun feature database. This process ensures that the system can identify key terms in specific disciplines and can use these features for accurate matching in subsequent teaching information extraction. For example, in the subject of language, terms such as "explanatory method", "system concept", "language symbol", etc. will be classified into specific noun feature categories. Finally, the noun information in the record document is extracted and matched with the pre-built noun feature library. This matching process uses advanced algorithms to analyze the context of each noun to ensure its relevance to the corresponding course content. In this way, the teaching information contained in the image can be accurately identified and effectively connected with the course syllabus and learning content. If the matching results show that a noun has specific educational value in the course content, the system can automatically generate a suitable teaching scene based on the matching teaching information.

[0078] Specifically, when the personnel acquisition module is configured to obtain the number of users to be involved and the course learning concentration of the users to be involved, it includes: the personnel acquisition module is configured to generate test questions according to the teaching information to test each user to be involved, and obtain the average test score between each user to be involved. The personnel acquisition module is also configured to determine the course learning score of each user to be involved according to the relationship between the average test score and the full test score, and use the course learning score as the basic course learning concentration of each user to be involved. The personnel acquisition module is also configured to determine the adjustment coefficient according to the score difference between the test score of the user to be involved and the test score mean, and determine the basic course learning concentration adjusted according to the adjustment coefficient as the course learning concentration of the user to be involved: wherein the personnel acquisition module is pre-configured with a first preset score difference and a second preset score difference, and the first preset score difference is less than the second preset score difference. When the score difference is less than the first preset score difference, the personnel acquisition module determines the adjustment coefficient to be L1. When the score difference is greater than or equal to the first preset score difference, and the score difference is less than the second preset score difference, the personnel acquisition module determines the adjustment coefficient to be L2. When the score difference is greater than or equal to the second preset score difference, the personnel acquisition module determines the adjustment coefficient to be L3, wherein L1<L2<L3<1.

[0079] Specifically, when the personnel acquisition module is further configured to determine the course learning score of each user to be involved according to the relationship between the test score mean and the test score full score, it includes: the personnel acquisition module is also configured to obtain the test score difference between the test score mean and the test score full score, and determine the course learning score of each user to be involved according to the relationship between the test score difference and the first preset test score difference and the second preset test score difference pre-configured by the personnel acquisition module. When the test score difference is less than the first preset test score difference, the personnel acquisition module determines that the course learning score of each user to be involved is Q1. When the test score difference is greater than or equal to the first preset test score difference, and the test score difference is less than the second preset test score difference, the personnel acquisition module determines that the course learning score of each user to be involved is Q2. When the test score difference is greater than or equal to the second preset test score difference, the personnel acquisition module determines that the course learning score of each user to be involved is Q3. Among them, the first preset test score difference is less than the second preset test score difference, and Q1<Q2<Q3.

[0080] It can be seen that by generating test questions and testing users, the test scores of each user and the difference between them and the average score are extracted, so as to evaluate the course learning score of each user. Based on this score, the user's learning concentration can be reflected, and the learning concentration can be adjusted according to the difference between the test score and the mean. Users with smaller differences (whose performance is closer to the average level) will maintain a higher concentration, while users with larger differences will dynamically adjust their concentration according to the preset adjustment coefficient, thereby achieving a more personalized learning path and feedback. In addition, by setting different test score difference thresholds, the user's learning score is further subdivided to quantify the user's concentration level according to their learning performance. Smaller differences correspond to higher scores and concentration, while larger differences may lead to lower scores and concentration. Through this hierarchical scoring mechanism based on score differences, the learning status of each user in the course can be accurately identified, and the learning concentration can be flexibly adjusted accordingly to ensure the personalization and refinement of the learning experience, thereby maximizing the learning effect.

[0081] It is understandable that the learners' mastery is measured by generating test questions and calculating the difference between each learner's test score and the average score. This difference reflects the learning differences of students. Students with small differences indicate that their learning status is consistent with the class as a whole, while students with large differences may need more personalized attention. Based on these differences, the learners' concentration is dynamically adjusted by using preset adjustment coefficients. For example, students with large and negative differences adjust their concentration according to the degree of deviation of their grades to ensure that they can continue to learn at a suitable pace and avoid excessive confusion or frustration. This dynamic adjustment mechanism effectively avoids the learning bottleneck caused by too fast or too slow pace in the same learning environment. On this basis, the design of the personnel acquisition module makes the adjustment of concentration more refined and accurate. Through multiple preset score differences and course learning scores corresponding to these differences, the system can accurately compare students' performance with expected goals based on test results and adjust students' learning pace in real time. A lower difference means that learners maintain a high level of participation in the learning process, and they will be given more positive feedback; a larger difference indicates that learners have difficulty in mastering knowledge, and they will be helped to gradually keep up with the learning progress by adjusting learning tasks and concentration. In this way, not only the personalization of the learning process is improved, but also the efficiency and flexibility of interdisciplinary teaching are ensured. Compared with the traditional teaching model, this dynamic adjustment mechanism based on learning performance can better adapt to the learning needs of each student, especially when it involves the intersection of multiple disciplines. Students' knowledge background, concentration and learning strategies will be different, and targeted adjustments can be made according to their different learning states. In addition, this method can also improve the interactivity and immersion of the teaching scene. Learners can not only obtain different learning paths according to their concentration, but also improve their participation in learning during the interaction process, promote the internalization and application of knowledge, and ultimately achieve the integration and in-depth understanding of interdisciplinary knowledge.

[0082] Specifically, when the relationship map establishment module is configured to obtain related subject information according to the teaching information, and generate teaching scenarios according to the teaching information and subject information, it includes: the relationship map establishment module is also configured to perform word annotation processing on the teaching information, and extract the teaching content in the teaching information after the word annotation processing, wherein the word annotation processing includes: word segmentation processing, part-of-speech tagging processing and vocabulary standardization processing. The relationship map establishment module is also configured to extract key concepts, terms and related context information in the teaching content, as well as specific entities and their subject classifications in the teaching content based on natural language processing technology. The relationship map establishment module is also configured to obtain the causal relationship, before-and-after association or category association between each key concept based on the associated context information, and determine the role of each key concept in the teaching content and the logical relationship between the key concept in the teaching content. The relationship map establishment module is also configured to associate each subject according to the key concepts, terms and specific entities, and construct a multidimensional knowledge map of interdisciplinary fields, obtain relevant subject information in the multidimensional knowledge map according to the key concepts, and generate teaching scenarios according to the relevant subject information and key concepts.

[0083] It can be understood that the relationship map establishment module uses natural language processing technology to perform word annotation processing on the teaching information, and the word annotation processing includes word segmentation, part-of-speech tagging and vocabulary standardization. The goal of this process is to convert the teaching information into structured data that the system can understand and analyze. Word segmentation divides the teaching information into word units, part-of-speech tagging further indicates the grammatical role of each word, and vocabulary standardization normalizes synonyms and different forms of words to facilitate accuracy and consistency in subsequent analysis. Through these preprocessing steps, the relationship map establishment module can obtain the semantics of each word in the teaching content and their mutual relationships. Next, based on the extracted teaching content, the relationship map establishment module uses natural language processing technology to perform in-depth semantic analysis to extract key concepts, terms and related context information in the teaching content. Through the understanding of the context, the relationship map establishment module can identify the causal relationship, time sequence relationship or category affiliation relationship between concepts. For example, some concepts may play a guiding role in a certain teaching module, or there may be causal logical relationships that need to be presented in the teaching scene. This analysis enables the system to more accurately capture the core information in the teaching content and lay the foundation for generating teaching scenes that meet actual needs. In addition, the relationship map establishment module can also analyze based on specific entities in the teaching content. These entities are usually subject terms, knowledge points, theorems, formulas, etc. involved in the course. Through entity recognition technology, the relationship map establishment module can identify these important subject entities and classify them by subject. This step enables the relationship map establishment module to not only extract individual teaching content, but also clearly identify the intersections and intersections between disciplines. Especially in interdisciplinary scenarios, how to effectively combine the knowledge points of Chinese and history subjects into a unified teaching module has become the key to technical implementation. Through the combination of the above-mentioned natural language processing and knowledge map technology, the relationship map establishment module can construct an interdisciplinary multidimensional knowledge map based on the extracted key concepts, terms and related entities. This map not only represents the knowledge structure within the discipline, but also represents the correlation between different disciplines, such as the intersection between Chinese and history. Using this knowledge map, the relationship map establishment module can intelligently generate teaching scenarios that meet the teaching objectives according to the needs and associations of different disciplines, and provide diversified and personalized interdisciplinary teaching designs. Finally, based on the association between multidimensional knowledge graphs and teaching information, the system can flexibly generate corresponding teaching scenarios according to the characteristics of the subject and teaching objectives.

[0084] Specifically, the relationship map establishment module is also configured to determine the number of preset roles in the teaching scene according to the number of personnel, and to construct a relationship map between the role played and the teaching scene, including: the relationship map establishment module is also configured to determine the number of roles played according to the relationship between the number of personnel and the number of preset roles in the teaching scene. When the number of personnel is consistent with the number of preset roles, the relationship map establishment module determines the number of roles played as the number of preset roles. When the number of personnel is inconsistent with the number of preset roles, the relationship map establishment module determines the number of roles played as the number of personnel, wherein: the relationship map establishment module is also configured to obtain the correlation between each role played and the teaching scene, and determine the adjustment coefficient according to the relationship between the number of preset roles and the number of personnel, and obtain the role to be played according to the correlation range adjusted by the adjustment coefficient. The relationship map establishment module is also configured to construct a relationship map according to the correlation between the role played and the teaching scene.

[0085] Specifically, when the relationship map establishment module determines the adjustment coefficient based on the relationship between the preset number of roles and the number of personnel, it includes: the relationship map establishment module is also configured to obtain the quantity difference between the preset number of roles and the number of personnel, and determine the adjustment coefficient based on the relationship between the quantity difference and the first preset quantity difference and the second preset quantity difference pre-configured by the relationship map establishment module. When the quantity difference is less than the first preset quantity difference, the relationship map establishment module determines the adjustment coefficient to be W1. When the quantity difference is greater than or equal to the first preset quantity difference, and the quantity difference is less than the second preset quantity difference, the relationship map establishment module determines the adjustment coefficient to be W2. When the quantity difference is greater than or equal to the second preset quantity difference, the relationship map establishment module determines the adjustment coefficient to be W3. Among them, zero is less than the first preset quantity difference and less than the second preset quantity difference, and W1<0<W2<W3.

[0086] It can be seen that the relationship map establishment module intelligently determines the number of roles in the teaching scene according to the difference between the number of personnel and the preset number of roles. When the number of personnel is consistent with the preset number of roles, the number of roles remains unchanged; if not, the system will automatically adjust the number of roles according to the number of personnel, so as to ensure that each participant has a corresponding role assignment. In this way, the relationship map establishment module can optimize the role design according to the actual number of participants, avoid the situation of too many or too few roles, and ensure the fluency and rationality of the teaching scene. Next, the relationship map establishment module calculates the adjustment coefficient by analyzing the difference in the number of people, which is used to adjust the range of correlation between the role and the teaching scene. The adjustment coefficient changes dynamically according to the difference between the number of personnel and the preset number of roles. The system sets three preset values ​​(W1, W2, W3) for different differences for flexible adjustment of the correlation. When the difference is small, the correlation is low; when the difference is large, the correlation increases, thereby adjusting the fit between the role and the scene. Through this adjustment of the correlation, the relationship map establishment module can optimize the matching of teaching content and roles according to the changes in the actual number of people, making the teaching activities more personalized and adapted to the needs of the participants. Through this technical principle, the relationship map establishment module can not only realize flexible role allocation in interdisciplinary teaching scenarios, but also improve teaching effectiveness and learners' sense of participation by adjusting the matching degree between roles and scenarios.

[0087] Specifically, when the mapping module is configured to determine the role of each user to be involved according to the course learning concentration, it includes: the mapping module is also configured to sort in reverse order according to the course learning concentration. The mapping module is also configured to determine the difficulty of playing the role according to the lines of each role and the introduction of the role. The mapping module is also configured to sort in ascending order according to the difficulty of each role, and determine the relationship between the course learning concentration and each role according to the sorted number. The mapping module is also configured to determine the role of each user to be involved according to the relationship and perform mapping.

[0088] It can be seen that by first sorting the course learning concentration of each participating user in reverse order, users with higher learning concentration are preferentially assigned to more challenging or complex roles. Subsequently, the mapping module evaluates the "difficulty" of each role based on the lines and role introduction content of each role, that is, the participation, depth of understanding, and task complexity required by the role. By sorting the difficulty of the role in ascending order, the mapping module can reasonably match the role with the user's concentration level, ensuring that users with high concentration play more complex roles, while users with lower concentration play simpler roles.

[0089] It is understandable that the mapping module first sorts the learning concentration of each participating user in reverse order to ensure that users with higher learning concentration can participate in more complex and challenging roles, while users with lower concentration are assigned to simple roles suitable for their cognitive load and participation level. This process helps prevent users from feeling bored or uncomfortable because the role is too simple or too complex, thereby affecting the learning effect. Next, the mapping module evaluates the "difficulty" of the role based on the lines and role introduction of each role. The difficulty evaluation takes into account the depth of knowledge, complexity of thinking, and the interaction and thinking ability that the user needs to show when playing the role. By sorting the difficulty of the role, the mapping module can assign the user a role suitable for his learning ability and concentration, avoiding negative emotions when the user challenges tasks that are too simple or too difficult, thereby improving his sense of participation and learning effect. After the role difficulty is sorted, the mapping module ensures that the role allocation is more accurate by establishing a relationship. The establishment of the relationship is based on the matching relationship between the difficulty sorting of the role and the user's learning concentration, ensuring that each user's role is both in line with his concentration level and has a certain degree of challenge. This matching mechanism achieves personalized allocation through intelligent algorithms, which not only enhances learners’ interest and engagement, but also enables each user to fully realize their potential in the teaching scenario through continuous adjustment and optimization.

[0090] In the above embodiments, the personalized generation of interdisciplinary teaching scenes is realized through the virtual-real fusion technology, thereby greatly improving the flexibility and interactivity of teaching. The traditional teaching mode is usually led by teachers, and the fixed course content and learning methods make it difficult to flexibly adjust the teaching process and meet the personalized learning needs of different students. However, this application can capture and process teaching content in real time through the image acquisition module and the information acquisition module, and convert it into structured teaching information, which provides technical support for the precise matching of teaching content. Combined with interdisciplinary knowledge fusion, it can automatically generate teaching scenes associated with the subject, providing students with a rich learning experience. In addition, the relationship map establishment module can automatically construct a subject information map associated with the course content based on teaching information and subject knowledge, ensuring that interdisciplinary knowledge points can be organically combined to form a multi-dimensional and three-dimensional teaching scene. This interdisciplinary scene generation method can break through the limitations of traditional teaching, prompt students to understand the inherent connection between different subjects in interaction, and stimulate students' comprehensive thinking ability. In the cross-integration of subject knowledge, students can deeply understand the application scenarios of knowledge points through practice and experience, and improve their interdisciplinary comprehensive literacy. In terms of role allocation, the mapping module dynamically adjusts the roles played by learners according to their concentration and participation, and sets corresponding lines according to different roles. This mechanism can better stimulate students' interest in learning and sense of participation by accurately matching learners' concentration and needs. Different learners play different roles in the same teaching scenario, which can stimulate students to think and learn actively through the interactive way of role-playing, thereby improving students' learning motivation and effectiveness. Especially in interdisciplinary teaching, students can not only deepen their understanding of subject content through the interaction of multiple roles, but also cultivate teamwork and the ability to solve complex problems.

[0091] In another preferred embodiment based on the above embodiment, Figure 2 As shown, this embodiment provides a generation method of interdisciplinary teaching based on virtual-real integration, including:

[0092] Step S100: Acquire image information of the teaching course and perform image processing on the image information.

[0093] Step S200: extract teaching information from the image information, obtain related subject information based on the teaching information, and generate a teaching scene based on the teaching information and the subject information.

[0094] Step S300: Obtain the number of users to be involved and their concentration in course learning, determine the number of roles to be played in the teaching scene according to the number of users, and construct a relationship map between the roles to be played and the teaching scene.

[0095] Step S400: Determine the lines of the role played according to the relationship graph.

[0096] Step S500: Determine the role of each participating user according to the course learning concentration, and perform mapping.

[0097] It can be understood that the generation method and system of interdisciplinary teaching based on virtual-real integration in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be described in detail.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0102] Finally, 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A generation system for interdisciplinary teaching based on virtual-real integration, characterized in that: include: An image acquisition module is configured to acquire image information of the course to be taught and perform image processing on the image information; an information acquisition module, electrically connected to the image acquisition module, and configured to extract teaching information from the image information; A personnel acquisition module is configured to acquire the number of users to be involved and the degree of concentration of the users to be involved in the course learning; a relationship map establishment module, electrically connected to the personnel acquisition module and the information acquisition module respectively, the relationship map establishment module being configured to acquire associated subject information according to the teaching information, and to generate a teaching scenario according to the teaching information and the subject information; The relationship map establishment module is further configured to determine the number of roles in the teaching scene according to the number of personnel, and to construct a relationship map according to the correlation between the roles and the teaching scene; the relationship map establishment module is further configured to determine the lines of the roles according to the relationship map; A mapping module, electrically connected to the relationship map establishment module, the mapping module is configured to determine the role played by each of the to-be-participated users according to the course learning concentration, and perform mapping; When the image acquisition module performs image processing on the image information, it includes: The image acquisition module is further configured to perform denoising on the image information, and compare the contrast in the denoised image information with a preset contrast pre-configured by the image acquisition module, wherein: If the contrast is lower than the preset contrast, the image acquisition module enhances the contrast of the image information after denoising; If the contrast is higher than or equal to the preset contrast, the image acquisition module does not enhance the contrast of the image information after the denoising process, and performs grayscale processing on the image information after the denoising process; The relationship map establishment module is further configured to determine the number of preset roles in the teaching scene according to the number of personnel, and to construct a relationship map according to the correlation between the role played and the teaching scene, including: The relationship map establishment module is further configured to determine the number of roles to be played according to the relationship between the number of personnel and the number of preset roles in the teaching scene; When the number of personnel is consistent with the preset number of roles, the relationship map establishment module determines that the number of roles played is the preset number of roles; When the number of personnel is inconsistent with the preset number of roles, the relationship map establishment module determines the number of roles to be the number of personnel, wherein: The relationship map establishment module is further configured to obtain the correlation between each of the playing roles and the teaching scene, and determine the adjustment coefficient according to the relationship between the number of preset roles and the number of personnel, and obtain the playing role to be played according to the correlation range adjusted by the adjustment coefficient; The relationship map building module is also configured to construct the relationship map according to the correlation between the role-playing role and the teaching scene.

2. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 1 is characterized in that: When the information acquisition module is configured to extract the teaching information from the image information, it includes: The information acquisition module is further configured to extract text content from the grayscale processed image information and generate a record document according to the text content; The information acquisition module is further configured to acquire the teaching subject of the course to be taught, divide the course according to the learning content of the teaching subject, and establish noun features according to the nouns in each learning content after the course division; The information acquisition module is further configured to extract noun information from the record document, perform matching between the noun information and the noun features, and determine the teaching information in the image information according to the matching result.

3. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 1 is characterized in that: When the personnel acquisition module is configured to acquire the number of users to be involved and the course learning concentration of the users to be involved, it includes: The personnel acquisition module is configured to generate test questions according to the teaching information to test each of the users to be tested, and obtain the average test score of each of the users to be tested; The personnel acquisition module is further configured to determine the course learning score of each of the to-be-participated users according to the relationship between the test score mean and the test score full score, and use the course learning score as the basic concentration of the course learning of each of the to-be-participated users; The personnel acquisition module is further configured to determine an adjustment coefficient according to the score difference between the test score of the user to be involved and the test score mean, and determine the basic course learning concentration adjusted according to the adjustment coefficient as the course learning concentration of the user to be involved; Wherein, the personnel acquisition module is pre-configured with a first preset score difference and a second preset score difference, and the first preset score difference is smaller than the second preset score difference; When the score difference is less than the first preset score difference, the personnel acquisition module determines that the adjustment coefficient is L1; When the score difference is greater than or equal to the first preset score difference, and the score difference is less than the second preset score difference, the personnel acquisition module determines that the adjustment coefficient is L2; When the score difference is greater than or equal to the second preset score difference, the personnel acquisition module determines that the adjustment coefficient is L3; Among them, L1<L2<L3<1.

4. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 3 is characterized in that: The personnel acquisition module is further configured to determine the course learning score of each of the to-be-participated users according to the relationship between the test score mean and the test score full score, including: The personnel acquisition module is further configured to acquire a test score difference between the test score mean and the full test score, and determine a course learning score for each of the to-be-participated users according to a relationship between the test score difference and a first preset test score difference and a second preset test score difference preconfigured by the personnel acquisition module; When the test score difference is less than the first preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q1; When the test score difference is greater than or equal to the first preset test score difference, and the test score difference is less than the second preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q2; When the test score difference is greater than or equal to the second preset test score difference, the personnel acquisition module determines that the course learning score of each of the to-be-participated users is Q3; Wherein, the first preset test score difference is smaller than the second preset test score difference, and Q1<Q2<Q3.

5. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 4 is characterized in that: When the relationship map establishment module is configured to obtain related subject information according to the teaching information and generate a teaching scenario according to the teaching information and the subject information, it includes: The relationship map establishment module is further configured to perform word annotation processing on the teaching information, and extract the teaching content in the teaching information after the word annotation processing, wherein the word annotation processing includes: word segmentation processing, part-of-speech tagging processing and vocabulary standardization processing; The relationship map establishment module is further configured to extract key concepts, terms and associated context information in the teaching content and specific entities and subject classifications in the teaching content based on natural language processing technology; The relationship map establishment module is further configured to obtain the causal relationship, the contextual relationship or the category relationship between each of the key concepts based on the associated context information, and determine the role of each of the key concepts in the teaching content and the logical relationship between the key concepts in the teaching content; The relationship graph establishment module is also configured to associate the key concepts, terms and specific entities with each subject, and construct a multidimensional knowledge graph across disciplines, obtain relevant subject information in the multidimensional knowledge graph based on the key concepts, and generate the teaching scenario based on the relevant subject information and key concepts.

6. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 1, characterized in that: The relationship map establishment module determines the adjustment coefficient according to the relationship between the number of preset roles and the number of personnel, including: The relationship map establishment module is further configured to obtain a quantity difference between the preset number of roles and the number of personnel, and determine the adjustment coefficient according to a relationship between the quantity difference and a first preset quantity difference and a second preset quantity difference preconfigured by the relationship map establishment module; When the quantity difference is less than the first preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W1; When the quantity difference is greater than or equal to the first preset quantity difference, and the quantity difference is less than the second preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W2; When the quantity difference is greater than or equal to the second preset quantity difference, the relationship map establishment module determines that the adjustment coefficient is W3; Among them, zero is less than the first preset number difference is less than the second preset number difference, and W1<0<W2<W3.

7. The generation system of interdisciplinary teaching based on virtual-real integration as claimed in claim 6 is characterized in that: When the mapping module is configured to determine the role played by each of the to-be-participated users according to the course learning concentration, it includes: The mapping module is further configured to sort the courses in reverse order according to their learning concentration; The mapping module is further configured to determine the difficulty of the role-playing according to the lines of each role-playing character and the introduction of the role-playing character; The mapping module is further configured to sort the roles in ascending order according to the difficulty of each role played, and determine the relationship between each course learning concentration and each role played according to the sorted numbers; The mapping module is further configured to determine the role played by each of the participating users according to the relationship and perform mapping.

8. A method for generating interdisciplinary teaching based on virtual-real integration, applicable to a system for generating interdisciplinary teaching based on virtual-real integration as claimed in any one of claims 1 to 7, characterized in that: include: Acquire image information of the course to be taught, and perform image processing on the image information; Extracting teaching information from the image information, acquiring related subject information according to the teaching information, and generating a teaching scene according to the teaching information and subject information; Obtaining the number of users to be involved and the degree of concentration of the users to be involved in the course learning, determining the number of roles to be played in the teaching scene according to the number of users, and constructing a relationship map between the roles to be played and the teaching scene; Determine the lines of the role-playing character according to the relationship map; The role played by each of the participating users is determined according to the course learning concentration, and mapping is performed.

Images