Teaching management method and management system based on VR

Abstract

The invention relates to the field of teaching, and discloses a VR-based teaching management method and management system, and the method comprises the steps that a VR interaction module receives interaction information, obtains student learning behavior data according to student personal information in the interaction information, and obtains student learning preference information according to the student learning behavior data; the cloud teaching server generates a student learning container, matches student category portraits according to student personal information and sends the student category portraits to the student learning container, the cloud teaching server determines a teaching mode according to student learning preference information, and the teaching recommendation generation module generates teaching recommendation information according to teaching recommendation sequence information and corresponding teaching resource weight information. And a recommendation scheme is generated and sent to the VR interaction module, and the VR interaction module carries out display page division according to the recommendation scheme and carries out teaching recommendation display. According to the invention, teaching modes and teaching contents can be dynamically adjusted according to individual differences and learning preferences of students, customized teaching recommendation is provided, and personalized teaching is realized.

Description

Technical Field

[0001] The present invention relates to the field of teaching, and in particular to a teaching management method and management system based on VR. Background Art

[0002] With the rapid development of information technology, the field of education has also ushered in unprecedented changes. The traditional teaching model is often teacher-centered, and students passively accept knowledge, lacking sufficient interactivity and personalization. The emergence of virtual reality (VR) technology has brought new possibilities to the field of education. VR technology can create an immersive learning environment, making students feel as if they are in a real scene, thereby enhancing the fun and participation of learning.

[0003] However, most current VR teaching applications remain at the level of simple scene simulation and interactive experience, lacking sufficient consideration of individual differences among students. Different students differ in learning ability, interest preferences, learning styles, etc., and uniform teaching content and methods are difficult to meet the needs of all students. Therefore, how to combine VR technology to achieve personalized recommendations for teaching content has become an urgent problem to be solved in the current field of educational technology.

[0004] In the existing technology, although there are some teaching recommendation systems based on data analysis, these systems often focus on recommending traditional online courses or electronic textbooks, and fail to fully utilize the advantages of VR technology. At the same time, these systems do not dig deep enough into students' personal information and learning behavior data during the recommendation process, resulting in limited accuracy and effectiveness of the recommendation results. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a teaching management method based on VR, comprising the following steps: Step 1: The VR interaction module receives the interaction information, obtains the student learning behavior data according to the student personal information in the interaction information, and obtains the student learning preference information according to the student learning behavior data; Step 2: The cloud-based teaching server generates a student learning container, matches the student category profile based on the student's personal information, and sends it to the student learning container. The cloud-based teaching server determines the teaching mode based on the student's learning preference information. If it is a single-subject teaching mode, it proceeds to step 3; if it is a multi-subject teaching mode, it proceeds to step 4. Step 3: Send the student's learning preference information to the student learning container. The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the student category portrait and the subject in the preference information to generate a teaching recommendation plan, and sends it to the VR interaction module to enter step 6; Step 4: The cloud-based teaching server generates teaching containers corresponding to the subject information according to the multiple subject information in the student learning preference information, and connects the teaching containers corresponding to the subject information to the student learning container. The student learning container obtains the teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, generates a subject teaching recommendation plan, and generates teaching recommendation sequence information according to the browsing learning data of each corresponding subject information, and sends it to the teaching recommendation generation module, and then proceeds to step 5; Step 5: The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information, and sends it to the VR interaction module to enter step 6; Step 6: The VR interaction module divides the display pages according to the recommended solutions and displays the teaching recommendations.

[0006] Furthermore, the obtaining of student learning behavior data and obtaining student learning preference information according to the student learning behavior data includes: The student learning behavior data includes learning history records, and the student's learning preference information is obtained based on the learning history records. The learning preferences include single subjects and multiple subjects. If the learning history records are single subjects, the learning preference is single subject; if the learning history records are multiple subjects, the learning preference is multiple subjects.

[0007] Furthermore, the cloud-based teaching server generates a student learning container, matches the student category portrait according to the student personal information and sends it to the student learning container, including: The student personal information includes data obtained by matching characteristic data according to the set student category portrait, including grade, age, gender and student course browsing data.

[0008] Furthermore, the cloud-based teaching server determines the teaching mode according to the student's learning preference information, including: If the student's learning preference information is a single subject, then the single subject teaching mode is adopted; if the student's learning preference information is multiple subjects, then the multiple subject teaching mode is adopted.

[0009] Furthermore, the student learning container obtains teaching resource data of the corresponding subject in the teaching database according to the subject in the student category portrait and preference information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject is obtained in the teaching database, as well as the learning difficulty preference contained in the student category portrait, to obtain the teaching resource recommendation information.

[0010] Furthermore, the student learning container obtains teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject and the learning difficulty preference contained in the student category portrait are obtained in the teaching database to obtain the subject teaching recommendation information. According to the number of views of the corresponding teaching resources in the student learning data, the teaching resource weight is obtained.

[0011] Furthermore, the generation of teaching recommendation sequence information based on the browsing learning data of each corresponding subject information includes: According to the subject browsing volume in the browsing learning data of the corresponding subject information, the teaching recommendation information of each subject is sorted to obtain the teaching recommendation sequence information.

[0012] Furthermore, the teaching recommendation generation module generates a recommendation scheme according to the teaching recommendation sequence information and the corresponding teaching resource weight information, including: According to the number of views of the teaching resources corresponding to the teaching resource recommendation information and the corresponding teaching resource weight information, the proportion of recommended pages of the corresponding subject web pages is obtained. All the subject teaching recommendation information and the proportion of recommended pages of the corresponding web pages constitute a recommendation plan.

[0013] Furthermore, the VR interaction module divides the display page according to the recommendation scheme, and recommends the display information for teaching recommendation display, including: The VR interactive module divides the recommended web pages according to the proportion of recommended pages of each corresponding subject web page in the recommendation plan, and displays the corresponding subject teaching recommendation information on the divided corresponding recommended web pages.

[0014] A VR-based teaching management system, which applies the VR-based teaching management method, includes a cloud-based teaching server, a student learning behavior data acquisition device, a data storage module, a student category portrait construction module, a teaching recommendation generation module, a VR interaction module, a data processing module, and a communication module.

[0015] The student learning behavior data acquisition device, data storage module, student category portrait construction module, teaching recommendation generation module, VR interaction module, and communication module are respectively connected to the data processing module; the cloud-based teaching server is communicatively connected to the communication module.

[0016] The student learning behavior data collection device is used to collect student learning behavior data, including student course browsing records, learning progress records, and operation interaction records; The data storage module is used to store student learning behavior data and teaching-related data in each teaching cycle; The student category portrait construction module generates a student category portrait based on the student’s personal information; The cloud teaching server includes a teaching mode generation module, a teaching database and a teaching classification module; The teaching mode generation module is used to determine the teaching mode according to the student category portrait; The teaching database is used to store teaching-related information, including teaching resource library, teaching strategies, and recommendation rules; The VR interaction module is used to perform teaching recommendation display and student learning interaction according to the recommendation plan.

[0017] The beneficial effects of the present invention are: by collecting and analyzing students' learning behavior data, generating student portraits, and dynamically adjusting teaching modes and teaching contents according to students' individual differences and learning preferences, providing customized teaching recommendations, and realizing personalized teaching.

[0018] Combined with VR technology, accurate and effective teaching recommendation plans are generated based on multiple factors such as students' learning preferences, learning styles, and the popularity of teaching resources, thereby improving teaching efficiency and students' learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the VR-based teaching management method; Figure 2 Schematic diagram of the principle of VR-based teaching management system. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0021] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0022] like Figure 1 As shown in the figure, the VR-based teaching management method includes the following steps: Step 1: The VR interaction module receives the interaction information, obtains the student learning behavior data according to the student personal information in the interaction information, and obtains the student learning preference information according to the student learning behavior data; Step 2: The cloud-based teaching server generates a student learning container, matches the student category profile based on the student's personal information, and sends it to the student learning container. The cloud-based teaching server determines the teaching mode based on the student's learning preference information. If it is a single-subject teaching mode, it proceeds to step 3; if it is a multi-subject teaching mode, it proceeds to step 4. Step 3: Send the student's learning preference information to the student learning container. The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the student category portrait and the subject in the preference information to generate a teaching recommendation plan, and sends it to the VR interaction module to enter step 6; Step 4: The cloud-based teaching server generates teaching containers corresponding to the subject information according to the multiple subject information in the student learning preference information, and connects the teaching containers corresponding to the subject information to the student learning container. The student learning container obtains the teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, generates a subject teaching recommendation plan, and generates teaching recommendation sequence information according to the browsing learning data of each corresponding subject information, and sends it to the teaching recommendation generation module, and then proceeds to step 5; Step 5: The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information, and sends it to the VR interaction module to enter step 6; Step 6: The VR interaction module divides the display pages according to the recommended solutions and displays the teaching recommendations.

[0023] The obtaining of student learning behavior data and obtaining student learning preference information according to the student learning behavior data includes: The student learning behavior data includes learning history records, and the student's learning preference information is obtained based on the learning history records. The learning preferences include single subjects and multiple subjects. If the learning history records are single subjects, the learning preference is single subject; if the learning history records are multiple subjects, the learning preference is multiple subjects.

[0024] The cloud-based teaching server generates a student learning container, matches the student category portrait according to the student personal information and sends it to the student learning container, including: The student personal information includes data obtained by matching characteristic data according to the set student category portrait, including grade, age, gender and student course browsing data.

[0025] The cloud-based teaching server determines the teaching mode according to the student's learning preference information, including: If the student's learning preference information is a single subject, then the single subject teaching mode is adopted; if the student's learning preference information is multiple subjects, then the multiple subject teaching mode is adopted.

[0026] The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the subject in the student category portrait and preference information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject is obtained in the teaching database, as well as the learning difficulty preference contained in the student category portrait, to obtain the teaching resource recommendation information.

[0027] The student learning container obtains teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject and the learning difficulty preference contained in the student category portrait are obtained in the teaching database to obtain the subject teaching recommendation information. According to the number of views of the corresponding teaching resources in the student learning data, the teaching resource weight is obtained.

[0028] The generation of teaching recommendation sequence information based on the browsing learning data of each corresponding subject information includes: According to the subject browsing volume in the browsing learning data of the corresponding subject information, the teaching recommendation information of each subject is sorted to obtain the teaching recommendation sequence information.

[0029] The teaching recommendation generation module generates a recommendation scheme according to the teaching recommendation sequence information and the corresponding teaching resource weight information, including: According to the number of views of the teaching resources corresponding to the teaching resource recommendation information and the corresponding teaching resource weight information, the proportion of recommended pages of the corresponding subject web pages is obtained. All the subject teaching recommendation information and the proportion of recommended pages of the corresponding web pages constitute a recommendation plan.

[0030] The VR interaction module divides the display page according to the recommendation scheme, and recommends display information for teaching recommendation display, including: The VR interactive module divides the recommended web pages according to the proportion of recommended pages of each corresponding subject web page in the recommendation plan, and displays the corresponding subject teaching recommendation information on the divided corresponding recommended web pages.

[0031] like Figure 2 As shown, the VR-based teaching management system applies the VR-based teaching management method, including a cloud-based teaching server, a student learning behavior data acquisition device, a data storage module, a student category portrait construction module, a teaching recommendation generation module, a VR interaction module, a data processing module and a communication module.

[0032] The student learning behavior data acquisition device, data storage module, student category portrait construction module, teaching recommendation generation module, VR interaction module, and communication module are respectively connected to the data processing module; the cloud-based teaching server is communicatively connected to the communication module.

[0033] The student learning behavior data collection device is used to collect student learning behavior data, including student course browsing records, learning progress records, and operation interaction records; The data storage module is used to store student learning behavior data and teaching-related data in each teaching cycle; the student category portrait construction module generates student category portraits based on student personal information; the cloud-based teaching server includes a teaching mode generation module, a teaching database and a teaching classification module; the teaching mode generation module is used to determine the teaching mode based on the student category portrait; the teaching database is used to store teaching-related information, including a teaching resource library, teaching strategies, and recommendation rules; the VR interaction module is used to perform teaching recommendation displays and student learning interactions based on the recommended plan.

[0034] Specifically, a VR-based teaching management method is characterized by comprising the following steps: Step 1: The VR interaction module receives the interaction information, obtains the student learning behavior data based on the student personal information in the interaction information, and obtains the student learning preference information based on the student learning behavior data.

[0035] In this step, the VR interaction module serves as a user interface and is responsible for receiving students' interactive operations, such as clicking, browsing, and selecting. At the same time, the student's personal information (such as student ID, login account, etc.) is linked to the student's learning behavior data, which includes but is not limited to student course browsing records, learning progress records, operation interaction records, etc. By analyzing these data, students' learning preference information can be obtained, such as preference for single-subject or multi-subject learning, preference for a certain type of teaching resources, etc.

[0036] In step 2, the cloud-based teaching server generates a student learning container, matches the student category portrait based on the student's personal information, and sends it to the student learning container. The cloud-based teaching server determines the teaching mode based on the student's learning preference information. If it is a single-subject teaching mode, it proceeds to step 3; if it is a multi-subject teaching mode, it proceeds to step 4.

[0037] The student learning container is a virtual learning environment that stores and manages students' personal information, learning preferences, learning progress and other data. The cloud teaching server matches the student's personal information to the corresponding student category profile, such as grade, age, gender and student course browsing data, and sends this information to the student learning container. Then, based on the student's learning preference information, it determines whether to adopt a single subject teaching mode or a multi-subject teaching mode.

[0038] Step three, sending the student's learning preference information to the student learning container. The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the student category portrait and the subject in the preference information to generate a teaching recommendation plan, and sends it to the VR interaction module to enter step six.

[0039] In the single-subject teaching mode, the student learning container searches and obtains the corresponding teaching resource data in the teaching database according to the subject in the student category portrait and preference information. This data may include video tutorials, virtual experiments, interactive questions and answers, etc. Then, a teaching recommendation plan is generated based on this data and sent to the VR interactive module for display.

[0040] In step 4, the cloud-based teaching server generates teaching containers corresponding to the subject information based on the multiple subject information in the student learning preference information, and connects the teaching containers corresponding to the subject information to the student learning container. The student learning container obtains the teaching resource data corresponding to the subject information in the teaching database based on the student category portrait and subject information, generates a subject teaching recommendation plan, and generates teaching recommendation sequence information based on the browsing learning data of each corresponding subject information, and sends it to the teaching recommendation generation module to enter step 5.

[0041] In the multi-disciplinary teaching mode, the cloud teaching server generates multiple teaching containers corresponding to different subjects for each student, and connects these teaching containers to the student learning container. The student learning container obtains the corresponding teaching resource data in the teaching database based on the student category portrait and subject information, and generates the subject teaching recommendation plan for each subject. At the same time, based on the browsing learning data of each subject, the teaching recommendation sequence information is generated, that is, the teaching recommendation plans for each subject are sorted according to the student's preferences and learning progress.

[0042] Step 5: The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information, and sends it to the VR interaction module to enter step 6.

[0043] The teaching recommendation generation module generates the final recommendation plan based on the teaching recommendation sequence information and teaching resource weight information (such as page views, likes, comments, etc.), taking into account students' preferences, learning progress, and the popularity of teaching resources. Then, this recommendation plan is sent to the VR interaction module for display.

[0044] Step 6: The VR interaction module divides the display pages according to the recommended solutions and displays the teaching recommendations.

[0045] The VR interactive module divides the display pages according to the recommended teaching information of each subject in the recommendation plan and the corresponding page ratio. Then, the corresponding teaching recommendation information, such as video tutorials, virtual experiments, interactive questions and answers, etc., are displayed on the divided pages. In this way, students can choose the corresponding teaching content to study according to their interests and needs.

[0046] The obtaining of student learning behavior data and obtaining student learning preference information based on the student learning behavior data include: the student learning behavior data includes learning history records, and obtaining student learning preference information based on the learning history records, wherein the learning preferences include single subjects and multiple subjects; if the learning history record is a single subject, then the learning preference is a single subject; if the learning history record is multiple subjects, then the learning preference is multiple subjects.

[0047] Through the learning history records, we can intuitively understand the student's learning preferences. If the student's learning history records are mainly concentrated in a certain subject, then it can be judged that the student's learning preference is a single subject; if the student's learning history records involve multiple subjects, then it can be judged that the student's learning preference is multi-disciplinary.

[0048] The cloud-based teaching server generates a student learning container, matches a student category portrait based on the student personal information and sends it to the student learning container, including: the student personal information includes data obtained by matching feature data based on the set student category portrait, including grade, age, gender and student course browsing data.

[0049] Student personal information is the basis for generating student category portraits. A relatively accurate student category portrait can be constructed through basic information such as grade, age, gender, and feature data such as student course browsing data. This portrait is then sent to the student learning container for subsequent teaching recommendations and personalized learning.

[0050] The cloud-based teaching server determines the teaching mode according to the student's learning preference information, including: if the student's learning preference information is a single subject, then a single subject teaching mode is used; if the student's learning preference information is multiple subjects, then a multiple subject teaching mode is used.

[0051] According to the students' learning preference information, we can determine which teaching mode to use. If the students' learning preference is a single subject, then the single subject teaching mode is used; if the students' learning preference is multiple subjects, then the multi-subject teaching mode is used. In this way, the students' personalized learning needs can be better met.

[0052] The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the student category portrait and the subject in the preference information, and generates subject teaching recommendation information, including: obtaining the teaching resource data of the corresponding subject in the teaching database according to the subject information in the preference information, and the learning difficulty preference contained in the student category portrait, to obtain teaching resource recommendation information.

[0053] In the process of teaching recommendation, in addition to considering students’ subject preferences, students’ learning difficulty preferences also need to be considered. Through learning difficulty preferences, we can recommend teaching resources suitable for students’ level to avoid students losing interest in learning due to content that is too difficult or too easy.

[0054] The student learning container obtains the teaching resource data of the corresponding subject information in the teaching database according to the student category portrait and subject information, and generates subject teaching recommendation information, including: obtaining the teaching resource data of the corresponding subject in the teaching database according to the subject information in the preference information, and the learning difficulty preference contained in the student category portrait, obtaining the subject teaching recommendation information, and obtaining the teaching resource weight according to the number of views of the corresponding teaching resources in the student learning data.

[0055] The weight of a teaching resource is an indicator of its popularity and importance. The weight information of a teaching resource can be obtained by the number of views of the corresponding teaching resource in the learning data of students. Then, in the teaching recommendation process, the weight of the teaching resource and the student's preference are comprehensively considered to generate a more accurate and effective recommendation plan.

[0056] The generating of teaching recommendation sequence information according to the browsing learning data of each corresponding subject information includes: sorting the teaching recommendation information of each subject according to the subject browsing volume in the browsing learning data of the corresponding subject information to obtain the teaching recommendation sequence information.

[0057] By collecting statistics and analyzing the browsing and learning data of each subject, we can get the students' preference for different subjects. Then, we sort the teaching recommendation information of each subject according to this preference and generate teaching recommendation sequence information. In this way, we can ensure that students see the teaching content that they are most interested in first.

[0058] The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information, including: obtaining the proportion of recommended pages on the corresponding subject web pages based on the number of views of the teaching resources corresponding to the teaching resource recommendation information and the corresponding teaching resource weight information, all the subject teaching recommendation information and the corresponding proportion of recommended pages on the web pages, forming a recommendation plan.

[0059] In the process of generating teaching recommendations, it is necessary to comprehensively consider the teaching recommendation sequence information and teaching resource weight information. Through these two factors, the recommended page ratio of the corresponding subject web page can be obtained. Then, all the subject teaching recommendation information and the corresponding web page recommended page ratio are combined to form the final recommendation plan.

[0060] The VR interaction module divides the display pages according to the recommendation scheme, and recommends the display information for teaching recommendation display, including: the VR interaction module divides the recommended web pages according to the recommended page ratio of each corresponding subject web page in the recommendation scheme, and displays the corresponding subject teaching recommendation information on the divided corresponding recommended web pages.

[0061] As a user interface, the VR interactive module is responsible for displaying the teaching recommendation information in the recommendation plan to students. The recommended web pages are divided according to the recommended page ratio of each corresponding subject web page in the recommendation plan. Then, the corresponding teaching recommendation information, such as video tutorials, virtual experiments, interactive questions and answers, etc., are displayed on the divided pages. In this way, students can choose the corresponding teaching content to learn according to their interests and needs.

[0062] Example 1: VR teaching management for students with a single subject preference Xiao Ming, a sophomore in high school, shows a strong interest in physics. He often browses and learns physics-related content through the VR teaching platform. His learning history is mainly concentrated in physics.

[0063] The VR interaction module receives Xiao Ming's interactive information, such as clicking on physics courses, browsing physics experiment videos, etc.

[0064] Based on Xiao Ming’s personal information (student number, login account), the VR interaction module obtains Xiao Ming’s learning behavior data, including browsing history, learning progress and interactive question and answer records of physics courses.

[0065] By analyzing these data, we can conclude that Xiao Ming's learning preference is a single subject (physics).

[0066] The cloud teaching server generates a student learning container for Xiao Ming. According to Xiao Ming's personal information (grade, age, gender, and course browsing data), it matches the corresponding student category portrait and sends it to the student learning container.

[0067] The cloud-based teaching server determines to adopt a single-subject teaching mode based on Xiao Ming's learning preference information (single subject). The student learning container obtains the teaching resource data of the physics subject from the teaching database based on Xiao Ming's student category portrait and the subject (physics) in the preference information. Generate a physics teaching recommendation plan, including physics video tutorials, virtual physics experiments, and interactive questions and answers. Send the teaching recommendation plan to the VR interaction module. The VR interaction module divides the display pages according to the teaching recommendation plan and allocates the main page ratio for the physics teaching content. The physics teaching recommendation information is displayed on the divided pages, and Xiao Ming can immerse himself in learning physics content through VR equipment.

[0068] Example 2: VR teaching management for students with multiple subject preferences Xiaohong, a freshman at a certain university, shows interest in multiple subjects. She often browses and studies mathematics, biology, and chemistry-related content through the VR teaching platform. Her learning history covers multiple subjects.

[0069] The VR interaction module receives Xiaohong's interactive information, such as clicking on math courses, browsing biology experiment videos, participating in chemistry interactive questions and answers, etc. Based on Xiaohong's personal information, the VR interaction module obtains Xiaohong's learning behavior data, including browsing records, learning progress, and interactive data of multiple subjects. By analyzing these data, it is concluded that Xiaohong's learning preference information is multi-disciplinary (mathematics, biology, chemistry). The cloud teaching server generates a student learning container for Xiaohong. Based on Xiaohong's personal information, the corresponding student category portrait is matched and sent to the student learning container.

[0070] The cloud-based teaching server determines to adopt a multi-disciplinary teaching mode based on Xiaohong's learning preference information (multi-disciplinary) and proceeds to step 4. The cloud-based teaching server generates teaching containers for Xiaohong in three subjects: mathematics, biology, and chemistry, and connects these teaching containers to the student learning container. The student learning container obtains the teaching resource data of the corresponding subject in the teaching database based on Xiaohong's student category portrait and subject information. Generate subject teaching recommendation plans for each subject, and generate teaching recommendation sequence information (such as in the order of mathematics, biology, and chemistry) based on the browsing learning data. Send the teaching recommendation sequence information to the teaching recommendation generation module.

[0071] The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information (such as page views and likes). The recommendation plan is sent to the VR interaction module. The VR interaction module divides the display pages according to the recommendation plan and allocates corresponding page proportions for mathematics, biology and chemistry teaching content.

[0072] The recommended teaching information for each subject is displayed on the divided pages, and Xiaohong can choose the content of her interest to study through the VR device.

Claims

1. VR-based teaching management method, characterized by: The steps include: Step 1: The VR interaction module receives the interaction information, obtains the student learning behavior data according to the student personal information in the interaction information, and obtains the student learning preference information according to the student learning behavior data; Step 2: The cloud-based teaching server generates a student learning container, matches the student category profile based on the student's personal information, and sends it to the student learning container. The cloud-based teaching server determines the teaching mode based on the student's learning preference information. If it is a single-subject teaching mode, it proceeds to step 3; if it is a multi-subject teaching mode, it proceeds to step 4. Step 3: Send the student's learning preference information to the student learning container. The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the student category portrait and the subject in the preference information to generate a teaching recommendation plan, and sends it to the VR interaction module to enter step 6; Step 4: The cloud-based teaching server generates teaching containers corresponding to the subject information according to the multiple subject information in the student learning preference information, and connects the teaching containers corresponding to the subject information to the student learning container. The student learning container obtains the teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, generates a subject teaching recommendation plan, and generates teaching recommendation sequence information according to the browsing learning data of each corresponding subject information, and sends it to the teaching recommendation generation module, and then proceeds to step 5; Step 5: The teaching recommendation generation module generates a recommendation plan based on the teaching recommendation sequence information and the corresponding teaching resource weight information, and sends it to the VR interaction module to enter step 6; Step 6: The VR interaction module divides the display pages according to the recommended solutions and displays the teaching recommendations.

2. The VR-based teaching management method according to claim 1, characterized in that: The obtaining of student learning behavior data and obtaining student learning preference information according to the student learning behavior data includes: The student learning behavior data includes learning history records, and the student's learning preference information is obtained based on the learning history records. The learning preferences include single subjects and multiple subjects. If the learning history records are single subjects, the learning preference is single subject; if the learning history records are multiple subjects, the learning preference is multiple subjects.

3. The VR-based teaching management method according to claim 2, characterized in that: The cloud-based teaching server generates a student learning container, matches the student category portrait according to the student personal information and sends it to the student learning container, including: The student personal information includes data obtained by matching characteristic data according to the set student category portrait, including grade, age, gender and student course browsing data.

4. The VR-based teaching management method according to claim 3 is characterized in that: The cloud-based teaching server determines the teaching mode according to the student's learning preference information, including: If the student's learning preference information is a single subject, then the single subject teaching mode is adopted; if the student's learning preference information is multiple subjects, then the multiple subject teaching mode is adopted.

5. The VR-based teaching management method according to claim 4 is characterized in that: The student learning container obtains the teaching resource data of the corresponding subject in the teaching database according to the subject in the student category portrait and preference information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject is obtained in the teaching database, as well as the learning difficulty preference contained in the student category portrait, to obtain the teaching resource recommendation information.

6. The VR-based teaching management method according to claim 4, characterized in that: The student learning container obtains teaching resource data corresponding to the subject information in the teaching database according to the student category portrait and subject information, and generates subject teaching recommendation information, including: According to the subject information in the preference information, the teaching resource data of the corresponding subject and the learning difficulty preference contained in the student category portrait are obtained in the teaching database to obtain the subject teaching recommendation information. According to the number of views of the corresponding teaching resources in the student learning data, the teaching resource weight is obtained.

7. The VR-based teaching management method according to claim 6, characterized in that: The generation of teaching recommendation sequence information based on the browsing learning data of each corresponding subject information includes: According to the subject browsing volume in the browsing learning data of the corresponding subject information, the teaching recommendation information of each subject is sorted to obtain the teaching recommendation sequence information.

8. The VR-based teaching management method according to claim 7, characterized in that: The teaching recommendation generation module generates a recommendation scheme according to the teaching recommendation sequence information and the corresponding teaching resource weight information, including: According to the number of views of the teaching resources corresponding to the teaching resource recommendation information and the corresponding teaching resource weight information, the proportion of recommended pages of the corresponding subject web pages is obtained. All the subject teaching recommendation information and the proportion of recommended pages of the corresponding web pages constitute a recommendation plan.

9. The VR-based teaching management method according to claim 8, characterized in that: The VR interaction module divides the display page according to the recommendation scheme, and recommends display information for teaching recommendation display, including: The VR interactive module divides the recommended web pages according to the proportion of recommended pages of each corresponding subject web page in the recommendation plan, and displays the corresponding subject teaching recommendation information on the divided corresponding recommended web pages.

10. VR-based teaching management system, characterized by: The teaching management method based on VR described in any one of claims 1 to 9 is applied, comprising a cloud teaching server, a student learning behavior data acquisition device, a data storage module, a student category portrait construction module, a teaching recommendation generation module, a VR interaction module, a data processing module and a communication module; The student learning behavior data acquisition device, data storage module, student category portrait construction module, teaching recommendation generation module, VR interaction module, and communication module are respectively connected to the data processing module; the cloud teaching server is connected to the communication module for communication; The student learning behavior data collection device is used to collect student learning behavior data, including student course browsing records, learning progress records, and operation interaction records; The data storage module is used to store student learning behavior data and teaching-related data in each teaching cycle; The student category portrait construction module generates a student category portrait based on the student’s personal information; The cloud teaching server includes a teaching mode generation module, a teaching database and a teaching classification module; The teaching mode generation module is used to determine the teaching mode according to the student category portrait; The teaching database is used to store teaching related information, including teaching resource library and teaching strategies; The VR interaction module is used to perform teaching recommendation display and student learning interaction according to the recommendation plan.

Images