A method for quickly generating AR teaching materials and related devices

Abstract

This application belongs to the field of augmented reality teaching technology, and discloses a method for quickly generating AR teaching materials and related devices. Prepare basic AR teaching materials and extended AR teaching materials in advance, and quantify their data volumes and learning gain scores. According to the natural language feedback of students, evaluate the students' mastery of knowledge points, and generate multiple teaching material generation schemes differently according to the mastery degree. Evaluate the performance of each teaching material generation scheme from two dimensions of bandwidth saving and learning gain improvement. Finally, select the teaching material generation scheme with the best performance, and generate and distribute AR teaching materials for each student accordingly; thus, it is possible to dynamically adjust teaching materials according to student feedback, optimize the utilization of bandwidth resources while ensuring personalized teaching, and achieve the generation and distribution of fast, efficient and high-quality AR teaching materials.

Description

Technical Field

[0001] The present application relates to the field of augmented reality teaching technology, and more specifically, to a method for quickly generating AR teaching materials and related equipment. Background Art

[0002] Augmented reality (AR) teaching technology is becoming a significant innovative force in education. In classrooms with large student populations, the use of AR glasses to assist instruction is seen as a key means of enhancing interactive and personalized learning. Advances in natural language processing (NLP) technology have made it possible to rapidly generate customized AR teaching materials. However, in classrooms with large student populations, the teaching environment is complex, and students' learning progress and comprehension abilities vary significantly. Teachers need to quickly generate and deliver differentiated AR teaching content based on real-time student feedback to meet the learning needs of individual students.

[0003] Existing AR teaching material generation and distribution technologies struggle to simultaneously achieve rapid content generation, personalized customization, and efficient distribution in large-scale teaching scenarios. Especially when content customization based on students' natural language feedback is required, achieving a balance between efficient content distribution and personalized teaching quality within the limited network bandwidth and computing power of augmented reality glasses remains a pressing technical challenge.

[0004] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the invention

[0005] The purpose of this application is to provide a method for quickly generating AR teaching materials and related equipment, which can dynamically generate AR teaching materials based on student feedback in large-scale teaching scenarios, taking into account the rapid generation, personalized customization and efficient distribution of teaching materials.

[0006] In a first aspect, the present application provides a method for rapidly generating AR teaching materials, which is used to dynamically generate AR teaching materials based on student feedback. The method comprises the following steps:

[0007] S1 retrieves the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database, and determines the amount of data and learning gain score of the basic AR teaching materials and the extended AR teaching materials;

[0008] S2. Receive the natural language feedback on the target knowledge points submitted by the student group through the augmented reality glasses, analyze the feedback content using natural language processing technology, estimate the mastery level of each student on the target knowledge points, and generate multiple teaching material generation plans based on the mastery level; the teaching material generation plan includes the composition method of the AR teaching material corresponding to each student, and the composition method is either only including the basic AR teaching material or including the basic AR teaching material and the extended AR teaching material;

[0009] S3. Calculate the bandwidth saving rate of each teaching material generation plan according to each teaching material generation plan, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material;

[0010] S4. Calculate the learning gain improvement rate of each teaching material generation plan according to each teaching material generation plan, the learning gain score of the basic AR teaching material, and the learning gain score of the extended AR teaching material;

[0011] S5. Calculate the comprehensive effectiveness score of each teaching material generation plan according to the bandwidth saving rate and the learning gain improvement rate;

[0012] S6. Generate the AR teaching materials for each student according to the teaching material generation plan with the highest comprehensive effectiveness score, and send them to the augmented reality glasses of each student correspondingly.

[0013] This method can dynamically generate AR teaching materials through student feedback, taking into account both bandwidth saving and learning gain. It can dynamically generate AR teaching materials according to student feedback in large-scale teaching scenarios, taking into account the rapid generation of teaching materials, personalized customization, and efficient distribution.

[0014] Preferably, step S1 includes:

[0015] S101. Retrieve the basic AR teaching material and the extended AR teaching material pre-entered by the teacher according to the target knowledge points from the teaching database;

[0016] S102. Read the storage information of the basic AR teaching material and the extended AR teaching material from the teaching database, and analyze the storage information to determine the file size of each teaching material as the data volume;

[0017] S103. Score the basic AR teaching material and the extended AR teaching material according to the preset learning gain scoring criteria, combined with the content depth of the teaching material to be scored, the average cognitive level of the target audience, and the data volume, to obtain the learning gain score.

[0018] Through the synergistic effect of the above steps, the effective determination of the data volume and learning gain score of the basic AR teaching materials and the extended AR teaching materials is realized, which guarantees the reliability and effectiveness of the entire AR teaching material rapid generation method.

[0019] Preferably, step S2 includes:

[0020] S201. Receive the voice feedback of the student group for the target knowledge point submitted through the augmented reality glasses, and use the voice activity detection algorithm to filter out the background noise in the voice feedback to obtain a pure voice signal;

[0021] S202. Perform speech recognition on the pure voice signal, convert the pure voice signal into text feedback, and use the sliding window technique to perform word segmentation on the text feedback to obtain multiple word fragments;

[0022] S203. For each student, according to the word fragments, count the occurrence frequency of the keywords associated with the target knowledge point in the text feedback, and combine the knowledge point mastery degree evaluation rules to calculate the mastery degree score of the student for the target knowledge point;

[0023] S204. Based on the mastery degree score, divide the students into two categories: high mastery degree and low mastery degree according to multiple different division criteria to obtain multiple division results;

[0024] S205. According to each division result, determine the composition method of the AR teaching materials corresponding to students with different mastery degrees to obtain the corresponding teaching material generation plan; the composition method of the AR teaching materials corresponding to students with a high mastery degree is to only include the basic AR teaching materials, and the composition method of the AR teaching materials corresponding to students with a low mastery degree is to include the basic AR teaching materials and the extended AR teaching materials.

[0025] Through the above steps, the rapid generation of personalized AR teaching materials according to students' feedback is realized, and a balance is achieved between the teaching content distribution efficiency and the personalized teaching quality.

[0026] Preferably, step S203 includes:

[0027] Analyze the semantic distance between each word fragment and the target knowledge point in the preset knowledge graph, and screen out the keywords with a semantic distance less than the preset threshold as the keywords associated with the target knowledge point;

[0028] For each student, count the occurrence frequency of the keywords associated with the target knowledge point in the text feedback, and perform weighted processing on the frequencies of different keywords according to the preset keyword weight table to obtain the weighted keyword frequency;

[0029] Calculate the mastery level score of the student for the target knowledge point according to the weighted keyword frequency and in combination with the evaluation rules for the mastery level of knowledge points; the evaluation rules for the mastery level of knowledge points include: calculating the mastery level score of the student according to the deviation between the weighted keyword frequency and the preset reference value, and the degree of deviation is positively correlated with the mastery level score.

[0030] Preferably, step S204 includes:

[0031] Extract the historical learning data of each student; the historical learning data includes the historical answering accuracy rate, learning duration, and knowledge point mastery preference;

[0032] According to the historical learning data, select a clustering algorithm that matches the characteristics of the student group; the clustering algorithms include the K-means clustering algorithm, hierarchical clustering algorithm, and density clustering algorithm;

[0033] Use the selected clustering algorithm to perform clustering analysis on the students according to the mastery level score and in combination with the preset clustering quantity range to obtain multiple clustering results; each clustering result represents a student grouping scheme, each grouping scheme contains multiple student subsets, and each student subset represents a group of students with similar mastery levels;

[0034] For each clustering result, calculate the average mastery level score of each student subset, compare the average mastery level score of each student subset with the preset mastery level score threshold. If the average mastery level score is higher than the mastery level score threshold, then determine that the corresponding student subset has a high mastery level, otherwise determine that the corresponding student subset has a low mastery level, thereby obtaining multiple division results.

[0035] Preferably, step S3 includes:

[0036] S301. Calculate the total teaching material data volume corresponding to each teaching material generation scheme, denoted as the first data volume, according to the number of students corresponding to two AR teaching material composition methods in each teaching material generation scheme, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material;

[0037] S302. Calculate the total teaching material data volume when the AR teaching materials of all students include both the basic AR teaching material and the extended AR teaching material, denoted as the second data volume;

[0038] S303. Calculate the bandwidth saving rate of each teaching material generation scheme according to the following formula: J = 1 - M1 / M2, where J is the bandwidth saving rate, M1 is the first data volume, and M2 is the second data volume.

[0039] Preferably, step S4 includes:

[0040] S401. Take the learning gain score of the basic AR teaching material as the first learning gain score, and take the weighted average of the learning gain score of the basic AR teaching material and the learning gain score of the extended AR teaching material as the second learning gain score;

[0041] S402. Calculate the total learning gain score of each teaching material generation plan, denoted as the first total learning gain score, according to the number of students corresponding to the two AR teaching material composition methods in each teaching material generation plan, the first learning gain score, and the second learning gain score;

[0042] S403. Calculate the total learning gain score when the AR teaching material composition methods corresponding to all students include both the basic AR teaching material and the extended AR teaching material according to the second learning gain score, denoted as the second total learning gain score;

[0043] S404. Calculate the learning gain improvement rate of each teaching material generation plan according to the following formula: R = (N1 - N2) / N2, where R is the learning gain improvement rate, N1 is the first total learning gain score, and N2 is the second total learning gain score.

[0044] Preferably, step S5 includes:

[0045] S501. Calculate the distribution of the bandwidth saving rate and the learning gain improvement rate in the historical teaching data respectively, and normalize the current bandwidth saving rate and the current learning gain improvement rate by using the standardization method;

[0046] S502. Obtain the bandwidth resource information of the AR teaching system to determine the bandwidth saving weight and the learning gain weight;

[0047] S503. Calculate the comprehensive effectiveness score of each teaching material generation plan by weighted summation according to the normalized bandwidth saving rate and learning gain improvement rate, and the determined bandwidth saving weight and learning gain weight.

[0048] In a second aspect, the present application provides an electronic device, including a processor and a memory, where the memory stores a computer program executable by the processor, and when the processor executes the computer program, it runs the steps in the AR teaching material rapid generation method described above.

[0049] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it runs the steps in the AR teaching material rapid generation method described above.

[0050] Beneficial effects: An AR teaching material rapid generation method and related devices provided by the present application can dynamically generate AR teaching materials based on student feedback, taking into account bandwidth savings and learning gain. It can dynamically generate AR teaching materials according to student feedback in large-scale teaching scenarios, taking into account rapid generation of teaching materials, personalized customization, and efficient distribution. Description of the Drawings

[0051] Figure 1 It is a flowchart of the AR teaching material rapid generation method provided by an embodiment of the present application.

[0052] Figure 2 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0053] Reference numeral description: 301, processor; 302, memory; 303, communication bus. Detailed Embodiments

[0054] Next, the technical solutions in the present application will be clearly and completely described in conjunction with the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the present application usually described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0055] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0056] Refer to Figure 1 , the present application proposes an AR teaching material rapid generation method for dynamically generating AR teaching materials according to student feedback. The method includes the following steps:

[0057] S1. Retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database, and determine the data volume and learning gain score of the basic AR teaching materials and the extended AR teaching materials;

[0058] S2. Receive the natural language feedback on the target knowledge points submitted by the student group through the augmented reality glasses, analyze the feedback content using natural language processing technology, estimate the mastery level of each student on the target knowledge points, and generate multiple teaching material generation plans based on the mastery level; the teaching material generation plan includes the composition method of the AR teaching material corresponding to each student, and the composition method is to include only the basic AR teaching material or to include both the basic AR teaching material and the extended AR teaching material;

[0059] S3. Calculate the bandwidth saving rate of each teaching material generation plan according to each teaching material generation plan, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material;

[0060] S4. Calculate the learning gain improvement rate of each teaching material generation plan according to each teaching material generation plan, the learning gain score of the basic AR teaching material, and the learning gain score of the extended AR teaching material;

[0061] S5. Calculate the comprehensive effectiveness score of each teaching material generation plan according to the bandwidth saving rate and the learning gain improvement rate;

[0062] S6. Generate the AR teaching materials for each student according to the teaching material generation plan with the highest comprehensive effectiveness score, and send them to the augmented reality glasses of each student correspondingly.

[0063] Among them, in step S1, the basic AR teaching materials and the extended AR teaching materials are pre-recorded to provide content reserves for the subsequent dynamic generation of teaching materials. Determine the data volume of the basic AR teaching materials and the extended AR teaching materials to provide data support for the subsequent calculation of the bandwidth saving rate. The determination of the learning gain score aims to quantify the teaching effect of the teaching materials and provide a basis for the subsequent calculation of the learning gain improvement rate and the comprehensive effectiveness score. Among them, the basic AR teaching materials can include at least one of the basic concepts, core principles, typical examples, etc. of the knowledge points, and the extended AR teaching materials can include at least one of the in-depth expansion, application cases, and frontier progress of the knowledge points.

[0064] Among them, in step S2, receive the natural language feedback submitted by the students through the augmented reality glasses, and analyze the students' feedback content using natural language processing technology. The purpose is to evaluate the mastery level of the students on the target knowledge points. Generate multiple teaching material generation plans based on the students' mastery level to provide a selection space for the subsequent screening and optimization of the plans. The teaching material generation plan is designed to include the composition method of the AR teaching material corresponding to each student, and the composition method is set to include only the basic AR teaching material or to include both the basic AR teaching material and the extended AR teaching material to achieve the differentiation and personalization of the teaching content.

[0065] Among them, in step S3, according to the generation schemes of each teaching material, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material, calculate the bandwidth saving rate of each teaching material generation scheme to evaluate the efficiency of different schemes in terms of bandwidth resource utilization.

[0066] Among them, in step S4, according to the generation schemes of each teaching material, the learning gain score of the basic AR teaching material, and the learning gain score of the extended AR teaching material, calculate the learning gain improvement rate of each teaching material generation scheme to evaluate the potential of different schemes in enhancing the teaching effect.

[0067] Among them, in step S5, according to the bandwidth saving rate and the learning gain improvement rate, calculate the comprehensive effectiveness score of each teaching material generation scheme, aiming to comprehensively consider the teaching efficiency and teaching quality and provide a comprehensive evaluation index for the final selection of the scheme.

[0068] Among them, in step S6, according to the teaching material generation scheme with the highest comprehensive effectiveness score, generate the AR teaching materials for each student and send them to the augmented reality glasses of each student correspondingly to achieve the final distribution and application of the teaching materials.

[0069] Specifically, this method aims to solve the problem that it is difficult to balance the efficiency of generating and distributing AR teaching materials and the quality of personalized teaching in large-scale teaching scenarios. First, prepare the basic AR teaching materials and extended AR teaching materials in advance, and quantify their data volumes and learning gain scores to provide a data basis for the subsequent steps. Subsequently, receive the natural language feedback of students through the augmented reality glasses, and use natural language processing technology to analyze the student feedback, evaluate the students' mastery of knowledge points, and generate multiple teaching material generation schemes differently according to the mastery level. The core of these schemes is to configure different combinations of teaching materials for students with different mastery levels, that is, students with a high mastery level only receive the basic AR teaching materials, and students with a low mastery level receive the basic AR teaching materials and the extended AR teaching materials. Then, evaluate the performance of each teaching material generation scheme from two dimensions: bandwidth saving and learning gain improvement. The calculation of the bandwidth saving rate quantifies the efficiency of each scheme in data transmission. The calculation of the learning gain improvement rate evaluates the potential of each scheme in enhancing the teaching effect. Comprehensively consider the bandwidth saving rate and the learning gain improvement rate, calculate the comprehensive effectiveness score of each scheme, so as to balance the teaching efficiency and teaching quality. Finally, select the teaching material generation scheme with the highest comprehensive effectiveness score, and generate and distribute AR teaching materials for each student accordingly. Through the above steps, this method can dynamically adjust the teaching materials according to the students' feedback, optimize the utilization of bandwidth resources while ensuring personalized teaching, and achieve the fast, efficient and high-quality generation and distribution of AR teaching materials.

[0070] In some specific embodiments, in step S1, the teacher pre-enters basic AR teaching materials and extended AR teaching materials for the target knowledge points. For example, for the knowledge point of "Newton's First Law", the basic AR teaching materials can be a 3D model animation containing basic concepts and simple examples, and the extended AR teaching materials can be an interactive simulation experiment containing more in-depth principle analysis and complex application scenarios. In step S2, the student submits feedback on "Newton's First Law" in the form of voice through the augmented reality glasses, such as "don't quite understand what inertia is" or "feel basically mastered". Natural language processing technology analyzes these feedbacks to evaluate the student's mastery of "Newton's First Law". The mastery evaluation can adopt a method combining keyword matching and semantic analysis. For example, the appearance of negative keywords such as "don't understand" and "haven't mastered", as well as the deviation in the understanding of core concepts such as "inertia", will be recognized by the system as a low mastery level. On the contrary, if the student's feedback contains positive keywords such as "understood" and "mastered", and can correctly apply relevant concepts, it will be evaluated as a high mastery level. Based on the mastery evaluation results, the system generates multiple teaching material generation plans. For example, Plan 1: Students with a high mastery level only receive basic AR teaching materials, and students with a low mastery level receive basic AR teaching materials and extended AR teaching materials; Plan 2: Students with a slightly low mastery level only receive basic AR teaching materials, and students with a severely low mastery level receive basic AR teaching materials and extended AR teaching materials. In step S3, assume that the data volume of the basic AR teaching materials is 10MB, and the data volume of the extended AR teaching materials is 20MB. For Plan 1, if 30 out of 100 students have a low mastery level, the total data volume of the teaching materials is (70 * 10MB) + (30 * (10MB + 20MB)) = 1600MB. If all students receive basic AR teaching materials and extended AR teaching materials, the total data volume of the teaching materials is 100 * (10MB + 20MB) = 3000MB. The bandwidth saving rate is 1 - (1600MB / 3000MB) = 46.7%. In step S4, assume that the learning gain score of the basic AR teaching materials is 0.7, and the learning gain score of the extended AR teaching materials is 0.9. For Plan 1, the total learning gain score is (70 * 0.7) + (30 * 0.9) = 76. If all students receive basic AR teaching materials and extended AR teaching materials, the total learning gain score is 100 * 0.9 = 90. The learning gain improvement rate is (76 - 90) / 90 = -15.6%. Here, it is a negative improvement rate, and in practical applications, it needs to be adjusted according to the specific scoring model and parameters, with the goal of improving the learning gain. In step S5, assume that the bandwidth saving weight is 0.6 and the learning gain weight is 0.4. The comprehensive effectiveness score of Plan 1 is (0.6 * the normalized bandwidth saving rate) + (0.4 * the normalized learning gain improvement rate).By comparing the comprehensive effectiveness scores of different solutions, the solution with the highest score is selected as the final teaching material generation solution. In step S6, according to the selected solution, the system automatically generates and sends teaching content containing only basic AR teaching materials to students with a high level of mastery, and sends teaching content containing basic AR teaching materials and extended AR teaching materials to students with a low level of mastery, and distributes the teaching materials to the students' augmented reality glasses through the network, realizing the rapid generation and efficient distribution of personalized teaching content. Through the above embodiments, the application of the AR teaching material rapid generation method in actual teaching scenarios is demonstrated, and its effectiveness in solving the balance problem between teaching efficiency and personalized teaching quality is verified.

[0071] In some embodiments, step S1 includes:

[0072] S101. Retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database;

[0073] S102. Read the storage information of the basic AR teaching materials and extended AR teaching materials from the teaching database, and analyze the storage information to determine the file size of each teaching material as the data volume;

[0074] S103. According to the preset learning gain scoring criteria, combine the content depth of the teaching materials to be scored, the average cognitive level of the target audience, and the data volume, and score the basic AR teaching materials and extended AR teaching materials to obtain the learning gain score.

[0075] Among them, in step S101, the teaching database is configured to store pre-entered teaching materials. The teacher prepares basic AR teaching materials and extended AR teaching materials in advance according to the teaching target knowledge points, and enters these materials into the teaching database. The entry process may include links such as file upload, data annotation, and information registration to ensure that each teaching material is associated with a specific target knowledge point and can be retrieved and called by the system.

[0076] Among them, in step S102, the storage information analysis process is specifically that the system reads the metadata of the teaching materials from the teaching database. The metadata includes information such as the file storage path, file type, and file size. The system analyzes the file size information and directly uses the file size value as the data volume of the teaching material. The file size is measured in bytes, KB, MB, etc.

[0077] Among them, in step S103, the preset learning gain scoring criterion is a rule for quantifying the effectiveness of teaching materials. The criterion can include multiple dimensions such as content depth, average cognitive level of the target audience, data volume, etc. For different content types (such as videos, 3D models, texts), the learning gain scoring criterion can be different. The content depth can be preset by the teacher or evaluated by the system through content analysis algorithms. The average cognitive level of the target audience can be estimated based on students' historical learning data or test results. The data volume is the file size determined in step S102. The scoring process can adopt methods such as weighted average, expert scoring, model prediction, etc., and the final learning gain score is obtained by integrating information from various dimensions.

[0078] Specifically, through the above method, the determination methods of the data volume and learning gain score of the basic AR teaching materials and extended AR teaching materials are clarified. Step S101 ensures the controllable source and pre-preparation of the teaching materials, providing a data basis for the subsequent steps; step S102 provides a direct and easy-to-implement method for determining the data volume, obtaining the file size by parsing the file storage information, thereby quantifying the data resource occupancy of the teaching materials; step S103 constructs a comprehensive learning gain scoring mechanism, evaluating the learning effect of the teaching materials from multiple perspectives such as content quality, teaching object, and resource consumption. This multi-dimensional evaluation method makes the learning gain score more objective and reasonable, providing an important basis for optimizing the subsequent teaching material generation plan. Through the coordinated action of steps S101, S102, and S103, the effective determination of the data volume and learning gain score of the basic AR teaching materials and extended AR teaching materials is achieved, ensuring the reliability and effectiveness of the entire AR teaching material rapid generation method.

[0079] In some specific implementation manners, the teaching database is constructed using a relational database or a NoSQL database, which is used to store teaching materials and related metadata. The teacher uploads AR teaching materials through the teaching content management platform, and the platform automatically extracts and stores information such as the file name, file type, file size, and storage path of the teaching materials as storage information. In the formulation of the learning gain scoring criterion, for video teaching materials, indicators such as content depth levels (such as: shallow, medium, deep), average cognitive level levels of the target audience (such as: primary, intermediate, advanced), and data volume ranges (such as: <10MB, 10 - 50MB, >50MB) can be set, and corresponding scoring values are set for each indicator level. The learning gain score of the video teaching materials is obtained by looking up the table or weighted calculation. For example, for a video teaching material with a content depth of medium, an average cognitive level of the target audience of intermediate, and a data volume of 30MB, its learning gain score can be calculated as 75 points.

[0080] In some preferred implementation manners, step S103 includes:

[0081] Identify the content type of the teaching materials to be scored; the content types include videos, 3D models, and texts;

[0082] Call the corresponding learning gain scoring model according to the content type; among them, the learning gain scoring model for video teaching materials takes the weighted average of video duration, information density, and interactivity indicators, as well as content depth, average cognitive level of the target audience, and data volume as inputs, and the output is the video learning gain scoring sub-item; the learning gain scoring model for 3D model teaching materials takes the weighted average of calculated model complexity, interaction method, and visualization effect indicators, as well as content depth, average cognitive level of the target audience, and data volume as inputs, and the output is the 3D model learning gain scoring sub-item; the learning gain scoring model for text teaching materials takes the weighted average of text length, information organizational structure, and illustration richness indicators, as well as content depth, average cognitive level of the target audience, and data volume as inputs, and the output is the text learning gain scoring sub-item;

[0083] Adjust the weights of each indicator in the called learning gain scoring model according to the average cognitive level of the target audience;

[0084] Use the learning gain scoring model with adjusted weights to calculate the learning gain scoring sub-items of various contents in the teaching materials to be scored, and comprehensively calculate the learning gain score of the teaching materials to be scored based on these learning gain scoring sub-items.

[0085] Among them, identifying the content type of the teaching materials to be scored means determining which one of videos, 3D models, or texts the teaching materials belong to. Specifically, content type identification can be achieved through file extension analysis, content format recognition, or user manual marking. For example, for the uploaded teaching materials file, the system can first check the file extension. For example, files with extensions such as ".mp4" and ".avi" are identified as video types, files with extensions such as ".obj" and ".stl" are identified as 3D model types, and files with extensions such as ".txt" and ".pdf" are identified as text types. Further, content format recognition technology can be combined, such as by analyzing specific bytes or metadata in the file header, to more accurately determine the file type. As a supplement, users are allowed to manually specify the content type when uploading teaching materials to handle errors or special cases that may occur in automatic recognition.

[0086] Among them, calling the corresponding learning gain scoring model according to the content type means that the system maintains a learning gain scoring model library, which stores learning gain scoring models for different content types. After identifying the content type of the teaching material to be scored, the system will automatically select a model that matches the content type from the model library. For example, if the teaching material to be scored is identified as a video type, the system calls the learning gain scoring model for video teaching materials. The model library can be constructed and managed in the form of a database or configuration file to facilitate the addition, update and maintenance of the model. Among them, each learning gain scoring model can be a calculation formula model or a deep learning model based on expert experience training.

[0087] The learning gain scoring model for video-based instructional materials takes as input a weighted average of video length, information density, and interactivity, as well as content depth, the target audience's average cognitive level, and data volume. It outputs a video learning gain score component. This model is specifically designed to assess the learning gain of video-based instructional materials. The model's input parameters include characteristic video metrics (video length, information density, and interactivity) as well as common evaluation metrics for instructional materials (content depth, target audience's average cognitive level, and data volume). Video length can be directly extracted from video file metadata. Information density can be measured by analyzing the video's subtitles or audio using natural language processing techniques to calculate the amount of information contained per unit of video time. Interactivity can be assessed by counting the number and type of interactive elements in the video, such as questions, comments, and chapter quizzes. The model then takes a weighted average of these input parameters to produce the video learning gain score component. The weights can be pre-set based on practical teaching data or expert experience and can be adjusted later.

[0088] The learning gain scoring model for 3D model-based teaching materials uses as input a weighted average of model complexity, interaction methods, and visualization effects, as well as content depth, target audience average cognitive level, and data volume. The output is a 3D model learning gain score. This model is used to evaluate the learning gain of 3D model-based teaching materials. The model's input parameters include characteristic metrics of the 3D model itself (model complexity, interaction methods, and visualization effects) as well as general evaluation metrics for teaching materials (content depth, target audience average cognitive level, and data volume). Model complexity can be calculated from parameters such as the model's file size, number of polygons, or number of vertices. Interaction methods can be evaluated based on the type and richness of interactive operations supported by the model, such as rotation, scaling, translation, slicing, and animation. Visualization effects can be analyzed using image processing techniques to analyze the model's rendering quality, texture detail, and lighting effects. The model then takes a weighted average of these input parameters to produce a 3D model learning gain score. The weights can also be set and adjusted based on practical teaching data or expert experience.

[0089] Among them, the learning gain scoring model for text-based teaching materials takes the weighted average of the indicators of text length, information organization structure, and degree of illustration with text and pictures, as well as content depth, average cognitive level of the target audience, and data volume as input, and the output is the sub-items of text learning gain scoring, which means that this model is used to evaluate the learning gain of text-based teaching materials. The input parameters of the model include the characteristic indicators of the text itself (text length, information organization structure, degree of illustration with text and pictures) and the general evaluation indicators of teaching materials (content depth, average cognitive level of the target audience, data volume). The text length can be directly obtained by counting the number of words or paragraphs in the text. The information organization structure can be analyzed by using natural language processing technology to analyze the chapter structure, paragraph logic, keyword distribution, etc. of the text. The degree of illustration with text and pictures can be evaluated by detecting the quantity and proportion of non-text elements such as pictures, charts, formulas, etc. in the text. The model performs a weighted average of these input parameters to obtain the sub-items of text learning gain scoring. The weight values can be set and adjusted according to teaching practice data or expert experience.

[0090] Among them, adjusting the weights of each indicator in the learning gain scoring model called according to the average cognitive level of the target audience means that considering the differences in the concerns of students with different cognitive levels about different types of teaching materials, the system will dynamically adjust the weights of each indicator in the scoring model according to the average cognitive level of the target audience. The average cognitive level of the target audience can be obtained through methods such as students' historical learning data, test scores, or teacher evaluations. For example, for students with a relatively high average cognitive level, the weights of indicators such as information density and model complexity can be appropriately increased, and the weights of indicators such as video duration and text length can be decreased; for students with a relatively low average cognitive level, the opposite weight adjustment can be made. The adjustment of weights can adopt a preset weight adjustment strategy or an adaptive adjustment algorithm based on machine learning.

[0091] Among them, using the learning gain scoring model with adjusted weights to calculate the sub-items of learning gain scoring for various types of content in the teaching material to be scored and comprehensively calculating the learning gain scoring of the teaching material to be scored based on these sub-items of learning gain scoring means that if a teaching material contains multiple content types, such as both video and text, the system will first calculate the sub-items of learning gain scoring for each content type using the corresponding learning gain scoring model with adjusted weights. Then, the system will comprehensively combine these sub-items to obtain the overall learning gain scoring of the teaching material. The comprehensive method can adopt weighted average, summation, or other appropriate mathematical models. The weights can be determined according to the proportion or importance of different content types in the teaching material. The finally obtained learning gain scoring will be used as an important basis for evaluating the quality of teaching materials and selecting teaching materials.

[0092] Specifically, when the present application scheme scores the learning gain of teaching materials, it first identifies the content type of the teaching materials, such as video, three-dimensional model or text. After identifying the content type, the system will call the learning gain scoring model corresponding to the content type. For video teaching materials, the scoring model will consider video-specific indicators such as video length, information density and interactivity, as well as general indicators such as content depth, average cognitive level of the target audience and data volume, and calculate the weighted average as the video learning gain scoring item. For three-dimensional model teaching materials, the scoring model focuses on three-dimensional model-specific indicators such as calculation model complexity, interaction method and visualization effect, and also combines general indicators for weighted average calculation to obtain the three-dimensional model learning gain scoring item. For text teaching materials, the scoring model will focus on text-specific indicators such as text length, information organization structure and degree of text and pictures, and combine general indicators for weighted average calculation to obtain the text learning gain scoring item. During the scoring process, the system will also dynamically adjust the weight of each indicator according to the average cognitive level of the target audience to make the scoring model more in line with actual teaching needs. If the teaching materials contain multiple content types, the learning gain score sub-items of each content type will be combined to obtain the overall learning gain score of the teaching materials. As a result, this application solution can use different scoring models and indicator weights for teaching materials of different content types, thereby achieving a more refined and accurate learning gain assessment, overcoming the limitations of the unified scoring method in the existing technology, and providing more effective support for the optimization and personalized promotion of teaching materials.

[0093] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0094] For an AR instructional material containing both video and text content, the system first identifies the video and text content by analyzing the file extension and content format. The system then uses the video learning gain scoring model and the text learning gain scoring model, respectively. In the video learning gain scoring model, the weight of video length is set to 0.3, the weight of information density is set to 0.4, the weight of interactivity is set to 0.3, and the weights of content depth, average target audience knowledge level, and data volume are each set to 0.1. In the text learning gain scoring model, the weight of text length is set to 0.2, the weight of information organization structure is set to 0.4, the weight of text and illustration combination is set to 0.4, and the weights of content depth, average target audience knowledge level, and data volume are each set to 0.1. Assuming the target audience has a higher average knowledge level, the weights are further adjusted. For example, in the video model, the weight of information density is increased to 0.5 and the weight of video length is decreased to 0.2; in the text model, the weight of information organization structure is increased to 0.5 and the weight of text length is decreased to 0.1. The adjusted weights are used to calculate the learning gain scores for both video and text. Assuming that the video learning gain score is 85 points, the text learning gain score is 90 points, the video content accounts for 60% of the teaching materials, and the text content accounts for 40%, the final teaching material learning gain score is 85*0.6+90*0.4=87 points.

[0095] Through the above technical solution, this application can use a customized learning gain scoring model to evaluate teaching materials of different content types, and can dynamically adjust the model parameters according to the average cognitive level of the target audience, thereby achieving a more accurate assessment of the learning gain of teaching materials and providing more effective technical means for quality control and personalized recommendation of teaching materials.

[0096] In some embodiments, step S2 includes:

[0097] S201. Receive voice feedback on target knowledge points submitted by students through augmented reality glasses, and use a voice activity detection algorithm to filter out background noise in the voice feedback to obtain a pure voice signal;

[0098] S202. Perform speech recognition on the clean speech signal, convert the clean speech signal into text feedback, and perform word segmentation on the text feedback using sliding window technology to obtain multiple word fragments;

[0099] S203. For each student, based on the word fragments, the frequency of occurrence of keywords associated with the target knowledge point in the text feedback is counted, and combined with the knowledge point mastery evaluation rules, the student's mastery score of the target knowledge point is calculated;

[0100] S204. Based on the mastery level scores, divide the students into two categories of high and low mastery levels according to multiple different classification criteria, obtaining multiple classification results;

[0101] S205. According to each classification result, determine the composition methods of AR teaching materials corresponding to students with different mastery levels, obtaining corresponding teaching material generation plans; the composition method of AR teaching materials corresponding to students with high mastery levels is to only include basic AR teaching materials, and the composition method of AR teaching materials corresponding to students with low mastery levels is to include basic AR teaching materials and extended AR teaching materials.

[0102] Among them, step S2 refers to using natural language processing technology to analyze students' natural language feedback to evaluate the mastery level. Specifically, deep learning models such as recurrent neural networks and Transformer models can be used to implement natural language processing analysis, and traditional methods such as bag-of-words models and TF-IDF can be used to implement natural language processing analysis.

[0103] Among them, step S201 refers to receiving the voice feedback of the student group on the target knowledge point submitted through the augmented reality glasses, using a voice activity detection algorithm to filter out the background noise in the voice feedback, and obtaining a pure voice signal. Specifically, voice activity detection algorithms such as WebRTC VAD and Speex VAD can be used to filter out the background noise in the voice feedback, hardware devices such as directional microphones and bone conduction microphones can be used to reduce the interference of background noise, and wireless communication technologies such as Wi-Fi and Bluetooth can be used to implement the voice data transmission between the augmented reality glasses and the data processing center.

[0104] Among them, step S202 refers to performing speech recognition on the pure voice signal, converting the pure voice signal into text feedback, and using the sliding window technique to perform word segmentation on the text feedback to obtain multiple word segments. Specifically, speech recognition engines such as Kaldi and Whisper can be used to implement the conversion from voice to text, and word segmentation tools such as jieba and spaCy can be used to perform word segmentation. The size of the sliding window can be set to 3 - 5 words, and the sliding step can be set to 1 word.

[0105] Among them, step S203 refers to, for each student, according to the word segments, counting the occurrence frequency of keywords associated with the target knowledge point in the text feedback, and combining the knowledge point mastery level evaluation rules to calculate the mastery level score of the student for the target knowledge point. Specifically, a knowledge graph can be pre-constructed. The knowledge graph includes the target knowledge point and keywords related to the target knowledge point. The keywords can include concept words, attribute words, instance words, etc. The mastery level evaluation rules can be linear models, non-linear models, rule bases, etc. The mastery level score can be a percentage score, a grade score, etc.

[0106] Among them, step S204 refers to dividing students into two categories of high mastery level and low mastery level based on the mastery level score with multiple different classification criteria, obtaining multiple classification results. Specifically, methods such as threshold classification and clustering classification can be used. The classification criteria can include the absolute value of the mastery level score, the relative ranking of the mastery level score, the distribution of the mastery level score, etc. The clustering algorithm can adopt K-means clustering, hierarchical clustering, DBSCAN clustering, etc. The range of the number of clusters can be set to 2-5.

[0107] Among them, step S205 refers to determining the composition method of the AR teaching materials corresponding to students with different mastery levels according to each classification result, obtaining the corresponding teaching material generation plan; the composition method of the AR teaching materials corresponding to students with a high mastery level is to only include basic AR teaching materials, and the composition method of the AR teaching materials corresponding to students with a low mastery level is to include basic AR teaching materials and extended AR teaching materials.

[0108] Specifically, aiming at the goal of evaluating students' mastery of knowledge points by analyzing their natural language feedback and generating personalized teaching material generation plans based on this, this application aims to achieve this goal more precisely and effectively through a series of detailed steps. First, the feedback form is limited to voice feedback, and a voice activity detection algorithm is added to filter out noise. This is considering that in the AR teaching scenario, voice interaction is more natural and convenient, but environmental noise may affect the accuracy of voice recognition. By filtering out noise in advance, the accuracy of subsequent voice recognition can be improved, laying a foundation for subsequent text analysis. Then, the pure voice signal is converted into text feedback, and word segmentation is performed using the sliding window technique. Voice recognition is a basic step in natural language processing, and word segmentation decomposes the continuous text stream into discrete word segments, facilitating subsequent keyword extraction and semantic analysis. For each student, the keyword frequency is counted and the mastery degree score is calculated in combination with the mastery degree evaluation rule. The keyword frequency reflects the degree of association between the student's feedback content and the target knowledge point, and the mastery degree evaluation rule quantifies this degree of association into a comparable score, providing a basis for subsequent student grouping and selection of teaching material generation plans. Based on the mastery degree score, students are grouped according to multiple different classification criteria. Different classification criteria can generate different student group division plans, providing more choices for subsequent selection of the optimal teaching material generation plan. Finally, according to the grouping results, the composition method of teaching materials is determined. Students with a high degree of mastery only include basic materials, while students with a low degree of mastery include basic and extended materials. This differential configuration aims to ensure the teaching effect while saving bandwidth resources as much as possible and meeting the different learning needs of students with different mastery degrees. Thus, a more precise evaluation of students' mastery degree and a more effective generation of teaching materials are achieved, providing strong support for the realization of fast, personalized, and efficient AR teaching material generation. And it makes the natural language processing process more controllable and the evaluation results more reliable, laying a foundation for the subsequent personalized generation of teaching materials.

[0109] Through the above technical solutions, this application can more precisely evaluate students' mastery of target knowledge points and, based on this, quickly generate differentiated AR teaching materials for students with different mastery degrees. This enables the AR teaching system to dynamically adjust teaching content according to students' real-time feedback, taking into account both teaching efficiency and personalization. In teaching scenarios with a large number of students, it ensures the rapid generation, personalized customization, and efficient distribution of teaching content, achieving a balance between the efficiency of teaching content distribution and the quality of personalized teaching under limited network bandwidth and the computing power of augmented reality glasses.

[0110] In some preferred embodiments, step S203 includes:

[0111] Analyze the semantic distance between each word segment and the target knowledge point in the preset knowledge graph, and filter out the keywords with a semantic distance less than the preset threshold as the keywords associated with the target knowledge point;

[0112] For each student, count the frequency of the keywords associated with the target knowledge point in the text feedback, and according to the preset keyword weight table, perform weighted processing on the frequencies of different keywords to obtain the weighted keyword frequency;

[0113] According to the weighted keyword frequency, combined with the knowledge point mastery degree evaluation rule, calculate the mastery degree score of the student for the target knowledge point; the knowledge point mastery degree evaluation rule includes: calculating the mastery degree score of the student according to the deviation between the weighted keyword frequency and the preset reference value, and the degree of deviation is positively correlated with the mastery degree score.

[0114] Among them, analyzing the semantic distance between each word segment and the target knowledge point in the preset knowledge graph, and filtering out the keywords with a semantic distance less than the preset threshold as the keywords associated with the target knowledge point means that instead of directly counting the frequencies of all keywords, first analyze the semantic distance between each word segment and the target knowledge point in the preset knowledge graph. The following methods can be specifically used to achieve this: First, construct a preset knowledge graph, which includes the target knowledge point and the word segments related to the target knowledge point; then, use word vector technology, such as Word2Vec or GloVe, to map each word segment and the target knowledge point into the vector space; next, calculate the semantic distance between the vector of each word segment and the vector of the target knowledge point, and the semantic distance can be calculated using measurement methods such as cosine similarity or Euclidean distance; finally, set a preset threshold, and filter out the word segments with a semantic distance less than the preset threshold as the keywords associated with the target knowledge point. Through the analysis of the semantic distance, keywords with stronger relevance to the target knowledge point can be effectively filtered out, excluding those words that although appear in the text but have weak relevance to the current knowledge point, ensuring that the keywords used for subsequent mastery degree evaluation are truly centered around the target knowledge point.

[0115] Among them, for each student, the frequency of keywords associated with the target knowledge point appearing in the text feedback is counted. According to the preset keyword weight table, the frequencies of different keywords are weighted to obtain the weighted keyword frequency. That is, after determining the associated keywords, it is not simply counting the number of times the keywords appear, but introducing the concept of the keyword weight table to weight the frequencies of different keywords. Specifically, the following method can be used to achieve it: First, establish a keyword weight table, which records each keyword and its corresponding weight value. The weight value can be set according to the importance of the keyword or its degree of association with the target knowledge point; then, for each student, count the frequency of each associated keyword appearing in their text feedback; next, according to the keyword weight table, find the weight value corresponding to each associated keyword; finally, multiply the frequency of each associated keyword by its corresponding weight value to obtain the weighted keyword frequency. This means that different keywords have different importance in reflecting the student's mastery level. By presetting the weight table, the keywords that can better represent the student's understanding level can be highlighted, further optimizing the calculation of the mastery level score and making the score result more accurately reflect the student's knowledge mastery level.

[0116] Among them, according to the weighted keyword frequency, combined with the evaluation rules for the knowledge point mastery level, calculate the mastery level score of the student for the target knowledge point; the evaluation rules for the knowledge point mastery level include: calculating the mastery level score of the student according to the deviation between the weighted keyword frequency and the preset reference value, and the degree of deviation is positively correlated with the mastery level score. That is, the evaluation rules for the mastery level are based on the deviation between the weighted keyword frequency and the preset reference value to calculate the mastery level score, and the degree of deviation is positively correlated with the mastery level score. Specifically, the following method can be used to achieve it: First, determine the preset reference value. The preset reference value can be a fixed value set according to historical data or expert experience, or a value dynamically adjusted according to the average level of the student group; then, calculate the deviation between the weighted keyword frequency of each student and the preset reference value. The deviation can be an absolute deviation or a relative deviation; next, according to the preset mastery level scoring function, map the deviation value to the mastery level score. The mastery level scoring function needs to ensure that the degree of deviation is positively correlated with the mastery level score. For example, a linear function or a non-linear function can be used to achieve it. This evaluation rule compares the student's feedback situation with a preset standard, and quantifies the student's mastery level through the size of the deviation, making the evaluation result more objective and quantifiable, and facilitating the system to make subsequent decisions on teaching material generation and push.

[0117] The above steps ensure a more accurate and effective evaluation of the student's mastery level on the basis of ensuring the relevance between the keywords and the target knowledge point, providing a more reliable basis for the generation of subsequent teaching materials.

[0118] Through the above technical solution, the present application can more accurately and effectively evaluate the students' mastery of target knowledge points, solve the problem in the prior art of only statistically analyzing the keyword frequency while ignoring the relevance between keywords and target knowledge points, improve the accuracy and pertinence of evaluation, provide more reliable data support for the subsequent differential generation of AR teaching materials according to the students' mastery level, and thus contribute to enhancing the personalization and effectiveness of AR teaching.

[0119] In some preferred embodiments, step S204 includes:

[0120] Extract the historical learning data of each student; the historical learning data includes historical answering accuracy rate, learning duration, and knowledge point mastery preference;

[0121] According to the historical learning data, select a clustering algorithm that matches the characteristics of the student group; the clustering algorithms include K-means clustering algorithm, hierarchical clustering algorithm, and density clustering algorithm;

[0122] Using the selected clustering algorithm, based on the mastery level score, combined with the preset clustering quantity range, perform clustering analysis on the students to obtain multiple clustering results; each clustering result represents a student grouping scheme, each grouping scheme contains multiple student subsets, and each student subset represents a group of students with similar mastery levels;

[0123] For each clustering result, calculate the average mastery level score of each student subset, compare the average mastery level score of each student subset with the preset mastery level score threshold. If the average mastery level score is higher than the mastery level score threshold, it is determined that the corresponding student subset has a high mastery level; otherwise, it is determined that the corresponding student subset has a low mastery level, thereby obtaining multiple division results.

[0124] Among them, the historical learning data refers to a data set that can reflect the students' past learning situations, and can be specifically implemented by using the students' historical answering records, learning duration statistics, and knowledge point mastery preference records on the learning platform. By collecting and organizing these data, the learning characteristics and habits of students can be more comprehensively understood.

[0125] Among them, the historical answering accuracy rate refers to the proportion of the number of questions answered correctly by students during the historical answering process to the total number of questions. Specifically, it can be obtained by counting the answering records of students in previous exercises and tests. The higher the answering accuracy rate, the higher the degree of students' mastery of knowledge points. Among them, the learning duration refers to the length of time invested by students during the historical learning process. Specifically, it can be obtained by recording the duration of students' learning activities on the learning platform. The longer the learning duration, usually the more energy students invest in learning. Among them, the preference for knowledge point mastery refers to the degree of preference of students for different knowledge points during the historical learning process. Specifically, it can be analyzed using data such as the learning duration and answering accuracy rate of students on different knowledge points. For example, if a student spends a longer learning time on a certain knowledge point and has a higher answering accuracy rate, it indicates that the student may have a preference for mastering this knowledge point.

[0126] Among them, the clustering algorithm refers to an algorithm used to divide a data set into several non-overlapping subsets, such that the data within the subsets has a high similarity, while the data between the subsets has a low similarity. Specifically, it can be implemented using algorithms such as the K-means clustering algorithm, hierarchical clustering algorithm, or density clustering algorithm. These algorithms are all mature and commonly used clustering methods, which can effectively divide the student group.

[0127] Among them, the clustering quantity range refers to the pre-set value range of the number of clustering results. For example, the clustering quantity range can be set to 2 - 5, which means that the clustering analysis will try to generate 2, 3, 4, or 5 clustering results to select the optimal grouping scheme. The setting of the clustering quantity range can be adjusted according to the actual teaching scenario and requirements. Different clustering results can partially or fully correspond to different numbers of clustering centers.

[0128] Among them, clustering analysis refers to the process of using a clustering algorithm to analyze data to discover the clustering structure contained in the data set. In this solution, clustering analysis refers to using the selected clustering algorithm to cluster students based on the mastery degree score and historical learning data, obtaining multiple clustering results, and each clustering result represents a student grouping scheme.

[0129] Among them, the mastery degree score threshold refers to the pre-set critical value used to divide the high and low levels of students' mastery degree, which can be adjusted according to specific scoring criteria and teaching requirements.

[0130] Among them, the division result refers to the final student grouping result obtained through clustering analysis and threshold comparison. The division result contains multiple student subsets, each student subset represents a group of students with similar mastery degrees, and each student subset is judged to have a high or low mastery degree.

[0131] Specifically, in order to group students more precisely, in step S204, first, the system extracts the historical learning data of each student, including the historical answering accuracy rate, learning duration, and knowledge point mastery preferences, to comprehensively evaluate the learning situation of students. Then, based on this historical learning data, the system selects a clustering algorithm that matches the characteristics of the student group. For example, if the number of students in the group is large and the feature distribution is relatively uniform, the K-means clustering algorithm can be selected; if the characteristics of the student group show an obvious hierarchical structure, the hierarchical clustering algorithm can be selected; if there is uneven density in the student group, the density clustering algorithm can be selected. Next, the system uses the selected clustering algorithm, combines the previously obtained mastery level scores and the preset clustering quantity range, and performs clustering analysis on the students to obtain multiple clustering results, each of which represents a possible student grouping scheme. Finally, for each clustering result, the system calculates the average mastery level score of each student subset and compares the average mastery level scores of each student subset with the preset mastery level score threshold, thereby determining whether the corresponding student subset belongs to a high or low mastery level, and obtaining the final classification result. Through the above steps, students can be more scientifically and reasonably divided into groups with different mastery levels, overcoming the one-sidedness of grouping only relying on the current mastery level scores, and improving the accuracy and reliability of student grouping.

[0132] Through the above technical solution, this application can more accurately and comprehensively evaluate the mastery level of students, overcome the limitations of grouping students only relying on the current mastery level scores, improve the accuracy and scientific nature of student grouping, lay a foundation for the personalized generation and distribution of subsequent AR teaching materials, and thus improve the personalization and effectiveness of AR teaching.

[0133] In some preferred embodiments, after step S203 and before step S204, the following step is further included:

[0134] S206. Calculate the average student feedback delay time based on the feedback time of the natural language feedback of each student, and correct the mastery level score according to the average student feedback delay time; the longer the average student feedback delay time, the lower the mastery level score.

[0135] Among them, step S206 first completes the calculation of the average student feedback delay time, which reflects the overall feedback speed of the student group. Then, this average delay time is used to correct the mastery level score of each student. The correction method is that the longer the average feedback delay time of the student, the lower the mastery level score of the student is adjusted.

[0136] Specifically, in the teaching system, when students submit natural language feedback through augmented reality glasses, the system records the feedback submission timestamps of each student. Step S206 is first used to calculate the average feedback delay time of the student group. The calculation method can be to set a reference time point (for example, the time point when the teacher asks a question), and then calculate the time difference between the time point when each student submits feedback and the reference time point to obtain the feedback delay time of each student. After that, calculate the average value of the feedback delay times of all students to obtain the average feedback delay time of the students. After obtaining the average feedback delay time of the students, step S206 is used to correct the preliminary mastery level score calculated in step S203 according to this average delay time. The correction process can adopt various methods. As an example, a delay time threshold and a mastery level score adjustment coefficient can be preset. If the average feedback delay time of a student exceeds the delay time threshold, the mastery level score of this student is reduced according to the adjustment coefficient. The size of the adjustment coefficient can be adjusted according to the actual teaching effect to ensure the accuracy of the mastery level score. The specific values of the delay time threshold and the adjustment coefficient can be optimized according to teaching practice and data analysis.

[0137] By correcting the mastery level score through the feedback delay time, the evaluation of the students' mastery level can be made more refined, providing a more reliable basis for the personalized generation of subsequent teaching materials, and thus improving the teaching effect.

[0138] Specifically, step S3 includes:

[0139] S301. Calculate the total teaching material data volume corresponding to each teaching material generation plan, denoted as the first data volume, according to the number of students corresponding to the two AR teaching material composition methods in each teaching material generation plan, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material.

[0140] S302. Calculate the total teaching material data volume when the AR teaching materials of all students include both the basic AR teaching material and the extended AR teaching material, denoted as the second data volume.

[0141] S303. Calculate the bandwidth saving rate of each teaching material generation plan according to the following formula: J = 1 - M1 / M2, where J is the bandwidth saving rate, M1 is the first data volume, and M2 is the second data volume.

[0142] Among them, in step S301, for each teaching material generation plan, count the number of students assigned only basic AR teaching materials and the number of students assigned both basic AR teaching materials and extended AR teaching materials. Then, multiply the number of students assigned only basic AR teaching materials by the data volume of the basic AR teaching materials to obtain the first part of the data volume; multiply the number of students assigned both basic AR teaching materials and extended AR teaching materials by the sum of the data volumes of the basic AR teaching materials and the extended AR teaching materials to obtain the second part of the data volume; add the first part of the data volume and the second part of the data volume to calculate the total data volume of the teaching materials corresponding to each teaching material generation plan, that is, the first data volume.

[0143] Among them, in step S302, assume that all students are assigned the composition method including both basic AR teaching materials and extended AR teaching materials, multiply the total number of students by the sum of the data volumes of the basic AR teaching materials and the extended AR teaching materials, and calculate to obtain the second data volume, which represents the total data volume in the case of the maximum bandwidth consumption.

[0144] Among them, in step S303, use the formula J = 1 - M1 / M2 to calculate the bandwidth saving rate. Where M1 represents the first data volume of the current teaching material generation plan, and M2 represents the second data volume in the case of the maximum bandwidth consumption. Through this formula, the bandwidth saving degree of each teaching material generation plan relative to the maximum bandwidth consumption can be quantitatively evaluated.

[0145] Thus, through the above bandwidth saving rate calculation method, the bandwidth efficiency of different teaching material generation plans can be effectively and quantitatively compared.

[0146] Furthermore, step S4 includes:

[0147] S401. Take the learning gain score of the basic AR teaching materials as the first learning gain score, and take the weighted average of the learning gain score of the basic AR teaching materials and the learning gain score of the extended AR teaching materials as the second learning gain score;

[0148] S402. According to the number of students corresponding to the two AR teaching material composition methods in each teaching material generation plan, the first learning gain score and the second learning gain score, calculate the total learning gain score of each teaching material generation plan, denoted as the first total learning gain score;

[0149] S403. According to the second learning gain score, calculate the total learning gain score when the AR teaching material composition method corresponding to all students includes both basic AR teaching materials and extended AR teaching materials, denoted as the second total learning gain score;

[0150] S404. Calculate the learning gain improvement rate for each teaching material generation plan according to the following formula: R = (N1 - N2) / N2, where R is the learning gain improvement rate, N1 is the first total learning gain score, and N2 is the second total learning gain score

[0151] Among them, in step S401, the first learning gain score is set as the learning gain score of the basic AR teaching material, which represents the learning gain level when only the basic teaching material is used. The second learning gain score is set as the weighted average of the learning gain scores of the basic AR teaching material and the extended AR teaching material, reflecting the comprehensive learning gain effect when both teaching materials are used simultaneously. The weight allocation can be adjusted according to the actual teaching scenario and the characteristics of the teaching materials. For example, if the extended AR teaching material plays a greater role in enhancing students' understanding depth, a higher weight can be assigned to the extended AR teaching material.

[0152] Among them, in step S402, multiply the number of students whose AR teaching material composition only includes the basic AR teaching material by the first learning gain score to obtain the first part of the total learning gain score. Multiply the number of students whose AR teaching material composition includes the basic AR teaching material and the extended AR teaching material by the second learning gain score to obtain the second part of the total learning gain score. Then calculate the sum of the first part of the total learning gain score and the second part of the total learning gain score to obtain the first total learning gain score.

[0153] Among them, in step S403, the second total learning gain score is calculated as a benchmark value, which represents the total learning gain score when all students receive a combination including the basic AR teaching material and the extended AR teaching material. The establishment of this benchmark value provides a comparison basis for the subsequent calculation of the learning gain improvement rate.

[0154] Among them, in step S404, the learning gain improvement rate is calculated through the formula R = (N1 - N2) / N2. In the formula, N1 represents the first total learning gain score, and N2 represents the second total learning gain score. Thus, the learning gain improvement rate is quantified as the learning gain improvement ratio of different teaching material generation plans relative to the benchmark plan, realizing the quantifiable evaluation and comparison of the learning gain effect.

[0155] Specifically, in the process of calculating the learning gain improvement rate, first determine the learning gain scores of the basic AR teaching materials and the extended AR teaching materials respectively. Then, for each teaching material generation plan, according to the distribution of different types of teaching materials received by students in the plan, calculate the total learning gain score of the plan as the first total learning gain score. At the same time, calculate the total learning gain score when all students receive a combination of the basic AR teaching materials and the extended AR teaching materials as the second total learning gain score. Thus, by comparing the first total learning gain score and the second total learning gain score and using a formula to calculate the learning gain improvement rate, the performance of each teaching material generation plan in terms of learning gain can be quantitatively evaluated. The higher the learning gain improvement rate, the greater the potential of the plan in enhancing the overall learning effect. By calculating the learning gain improvement rate, it can provide an important reference for the learning gain dimension for selecting the teaching material generation plan with the highest comprehensive effectiveness score, and further optimize the generation and distribution strategies of teaching materials.

[0156] Specifically, step S5 includes:

[0157] S501. Calculate the distribution of the bandwidth saving rate and the learning gain improvement rate in the historical teaching data respectively, and normalize the current bandwidth saving rate and the current learning gain improvement rate using a standardization method;

[0158] S502. Obtain the bandwidth resource information of the AR teaching system to determine the bandwidth saving weight and the learning gain weight;

[0159] S503. According to the normalized bandwidth saving rate and learning gain improvement rate, as well as the determined bandwidth saving weight and learning gain weight, calculate the comprehensive effectiveness score of each teaching material generation plan through weighted summation.

[0160] Among them, the purpose of performing the normalization process in step S501 is to eliminate the ineffectiveness caused by different dimensions or numerical ranges between the bandwidth saving rate and the learning gain improvement rate. The standardization method can adopt min-max standardization or Z-score standardization. For example, when adopting min-max standardization, the normalization formula can be expressed as: Normalized value = (Original value - Minimum value) / (Maximum value - Minimum value). Among them, the minimum value and the maximum value are obtained by analyzing the distribution of the bandwidth saving rate and the learning gain improvement rate in the historical teaching data.

[0161] Among them, in step S502, the bandwidth resource information can be obtained from the network monitoring module of the AR teaching system, such as the current bandwidth utilization rate. The bandwidth saving weight and the learning gain weight can be dynamically determined according to the bandwidth resource information. Specifically, when the system bandwidth resources are tight, the bandwidth saving weight is increased and the learning gain weight is decreased; when the system bandwidth resources are sufficient, the learning gain weight is increased and the bandwidth saving weight is decreased. The weight determination method can be linear mapping or non-linear function mapping.

[0162] Among them, in step S503, through weighted summation, the normalized bandwidth saving rate and the learning gain improvement rate are comprehensively considered. The comprehensive effectiveness score calculation formula can be expressed as: Comprehensive effectiveness score = (Normalized bandwidth saving rate × Bandwidth saving weight) + (Normalized learning gain improvement rate × Learning gain weight).

[0163] Specifically, for the problem of improving the accuracy of the comprehensive effectiveness score calculation result, first, in step S501, by normalizing the bandwidth saving rate and the learning gain improvement rate, the influence caused by the dimension and numerical range differences is eliminated, so that the two can be compared and integrated on the same scale. Then, in step S502, the bandwidth resource information of the AR teaching system is introduced as the basis for determining the bandwidth saving weight and the learning gain weight, realizing the dynamic adjustment of the weight parameters, so that the calculation of the comprehensive effectiveness score can adapt to the actual operation state of the teaching system. Finally, in step S503, through weighted summation, the normalized bandwidth saving rate and the learning gain improvement rate are effectively fused, and according to the dynamically adjusted weight parameters, the comprehensive effectiveness score is obtained. Thus, a score result that can more accurately and comprehensively reflect the comprehensive effectiveness of the teaching material generation scheme can be obtained, providing a basis for selecting the optimal scheme in the follow-up.

[0164] Please refer to Figure 2 , Figure 2A structural schematic diagram of an electronic device provided by an embodiment of the present application. The present application provides an electronic device, including: a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other through a communication bus 303 and / or other forms of connection mechanisms (not marked). The memory 302 stores a computer program executable by the processor 301. When the electronic device runs, the processor 301 executes the computer program to execute the AR teaching material rapid generation method in any optional implementation manner of the above embodiment to achieve the following functions: retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database, and determine the data volume and learning gain scores of the basic AR teaching materials and the extended AR teaching materials; receive the natural language feedback submitted by the student group for the target knowledge points through the augmented reality glasses, analyze the feedback content using natural language processing technology, estimate the mastery degree of each student for the target knowledge points, and generate multiple teaching material generation schemes based on the mastery degree; the teaching material generation scheme includes the composition method of the AR teaching materials corresponding to each student, and the composition method is to include only the basic AR teaching materials or to include the basic AR teaching materials and the extended AR teaching materials; calculate the bandwidth saving rate of each teaching material generation scheme according to each teaching material generation scheme, the data volume of the basic AR teaching materials, and the data volume of the extended AR teaching materials; calculate the learning gain improvement rate of each teaching material generation scheme according to each teaching material generation scheme, the learning gain score of the basic AR teaching materials, and the learning gain score of the extended AR teaching materials; calculate the comprehensive effectiveness score of each teaching material generation scheme according to the bandwidth saving rate and the learning gain improvement rate; generate the AR teaching materials for each student according to the teaching material generation scheme with the highest comprehensive effectiveness score, and correspondingly send them to the augmented reality glasses of each student.

[0165] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it executes the AR teaching material rapid generation method in any optional implementation manner of the above embodiment to achieve the following functions: retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by a teacher according to target knowledge points from a teaching database, and determine the data volume and learning gain scores of the basic AR teaching materials and the extended AR teaching materials; receive the natural language feedback submitted by a student group for the target knowledge points through augmented reality glasses, analyze the feedback content using natural language processing technology, estimate the mastery level of each student for the target knowledge points, and generate multiple teaching material generation schemes based on the mastery level; the teaching material generation scheme includes the composition method of the AR teaching material corresponding to each student, and the composition method is either only including the basic AR teaching material or including the basic AR teaching material and the extended AR teaching material; calculate the bandwidth saving rate of each teaching material generation scheme according to each teaching material generation scheme, the data volume of the basic AR teaching materials, and the data volume of the extended AR teaching materials; calculate the learning gain improvement rate of each teaching material generation scheme according to each teaching material generation scheme, the learning gain score of the basic AR teaching materials, and the learning gain score of the extended AR teaching materials; calculate the comprehensive effectiveness score of each teaching material generation scheme according to the bandwidth saving rate and the learning gain improvement rate; generate the AR teaching materials for each student according to the teaching material generation scheme with the highest comprehensive effectiveness score, and correspondingly send them to the augmented reality glasses of each student.

[0166] Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0167] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0168] In addition, the units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] Furthermore, in each embodiment of this application, the various functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0170] In this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0171] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A method for quickly generating AR teaching materials, which is used to dynamically generate AR teaching materials according to students' feedback, characterized in that, The method includes the following steps: S1. Retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database, and determine the data volume and learning gain score of the basic AR teaching materials and the extended AR teaching materials; S2. Receive the natural language feedback on the target knowledge points submitted by the student group through the augmented reality glasses, analyze the feedback content using natural language processing technology, estimate the mastery level of each student on the target knowledge points, and generate multiple teaching material generation plans based on the mastery level; The teaching material generation plan includes the composition method of the AR teaching materials corresponding to each student, and the composition method is either only including the basic AR teaching materials or including the basic AR teaching materials and the extended AR teaching materials; S3. Calculate the bandwidth saving rate of each teaching material generation plan according to each teaching material generation plan, the data volume of the basic AR teaching materials, and the data volume of the extended AR teaching materials; S4. Calculate the learning gain improvement rate of each teaching material generation plan according to each teaching material generation plan, the learning gain score of the basic AR teaching materials, and the learning gain score of the extended AR teaching materials; S5. Calculate the comprehensive effectiveness score of each teaching material generation plan according to the bandwidth saving rate and the learning gain improvement rate; S6. Generate the AR teaching materials for each student according to the teaching material generation plan with the highest comprehensive effectiveness score, and send them to the augmented reality glasses of each student correspondingly; Step S2 includes: S201. Receive the voice feedback on the target knowledge points submitted by the student group through the augmented reality glasses, and use the voice activity detection algorithm to filter out the background noise in the voice feedback to obtain a pure voice signal; S202. Perform speech recognition on the pure voice signal, convert the pure voice signal into text feedback, and use the sliding window technology to perform word segmentation on the text feedback to obtain multiple word segments; S203. For each student, according to the word segments, count the occurrence frequency of the keywords associated with the target knowledge points in the text feedback, and combine the knowledge point mastery level evaluation rules to calculate the mastery level score of the student on the target knowledge points; S204. Based on the mastery level score, divide the students into two categories: high mastery level and low mastery level according to multiple different division criteria to obtain multiple division results; S205. According to each division result, determine the composition method of the AR teaching materials corresponding to students with different mastery levels to obtain the corresponding teaching material generation plan; The composition method of the AR teaching materials corresponding to students with a high mastery level is only including the basic AR teaching materials, and the composition method of the AR teaching materials corresponding to students with a low mastery level is including the basic AR teaching materials and the extended AR teaching materials.

2. The rapid generation method of an AR teaching material according to claim 1, wherein, Step S1 includes: S101. Retrieve the basic AR teaching materials and extended AR teaching materials pre-entered by the teacher according to the target knowledge points from the teaching database; S102. Read the storage information of the basic AR teaching materials and the extended AR teaching materials from the teaching database, and parse the storage information to determine the file size of each teaching material as the data volume. S103. According to the preset learning gain scoring criteria, combine the content depth, the average cognitive level of the target audience, and the data volume of the teaching materials to be scored, and score the basic AR teaching materials and the extended AR teaching materials to obtain the learning gain score.

3. A method for quickly generating AR teaching materials according to claim 1, characterized in that, Step S203 includes: Analyze the semantic distance between each word segment and the target knowledge point in the preset knowledge graph, and screen out the keywords with a semantic distance less than the preset threshold as the keywords associated with the target knowledge point. For each student, count the frequency of the keywords associated with the target knowledge point that appear in the text feedback, and perform weighted processing on the frequencies of different keywords according to the preset keyword weight table to obtain the weighted keyword frequency. According to the weighted keyword frequency, combine the knowledge point mastery degree evaluation rules to calculate the mastery degree score of the student for the target knowledge point; the knowledge point mastery degree evaluation rules include: calculate the mastery degree score of the student according to the deviation between the weighted keyword frequency and the preset reference value, and the degree of deviation is positively correlated with the mastery degree score.

4. The rapid generation method of an AR teaching material according to claim 1, characterized in that Step S204 includes: Extract the historical learning data of each student; the historical learning data includes the historical answering correct rate, learning duration, and knowledge point mastery preference. According to the historical learning data, select a clustering algorithm that matches the characteristics of the student group; the clustering algorithms include the K-means clustering algorithm, hierarchical clustering algorithm, and density clustering algorithm. Use the selected clustering algorithm to perform clustering analysis on the students according to the mastery degree score, combined with the preset clustering quantity range, to obtain multiple clustering results; each clustering result represents a student grouping scheme, each grouping scheme contains multiple student subsets, and each student subset represents a group of students with similar mastery degrees. For each clustering result, calculate the average mastery degree score of each student subset, and compare the average mastery degree score of each student subset with the preset mastery degree score threshold. If the average mastery degree score is higher than the mastery degree score threshold, it is determined that the corresponding student subset has a high mastery degree, otherwise it is determined that the corresponding student subset has a low mastery degree, and thus multiple division results are obtained.

5. The method for rapidly generating AR teaching materials according to claim 1, characterized in that: Step S3 includes: S301. According to the number of students corresponding to the two AR teaching material composition methods in each teaching material generation scheme, the data volume of the basic AR teaching material, and the data volume of the extended AR teaching material, calculate the total teaching material data volume corresponding to each teaching material generation scheme, denoted as the first data volume. S302. Calculate the total teaching material data volume when the AR teaching materials of all students include both the basic AR teaching material and the extended AR teaching material, denoted as the second data volume. S303. Calculate the bandwidth saving rate of each teaching material generation scheme according to the following formula: J = 1 - M1 / M2, where J is the bandwidth saving rate, M1 is the first data volume, and M2 is the second data volume.

6. The method for rapidly generating AR teaching materials according to claim 1, characterized in that: Step S4 includes: S401. The learning gain score of the basic AR teaching materials is used as the first learning gain score, and the weighted average of the learning gain score of the basic AR teaching materials and the learning gain score of the extended AR teaching materials is used as the second learning gain score; S402. Calculate the total learning gain score of each teaching material generation scheme based on the number of students corresponding to the two AR teaching material composition methods in each teaching material generation scheme, the first learning gain score, and the second learning gain score, recorded as the first total learning gain score; S403. According to the second learning gain score, calculate the total learning gain score for all students when the AR teaching material composition includes basic AR teaching materials and extended AR teaching materials, recorded as the second total learning gain score; S404. Calculate the learning gain improvement rate of each teaching material generation plan according to the following formula: R=(N1-N2) / N2, where R is the learning gain improvement rate, N1 is the first total learning gain score, and N2 is the second total learning gain score.

7. The method for rapidly generating AR teaching materials according to claim 1, characterized in that: Step S5 includes: S501. Calculate the distribution of bandwidth saving rate and learning gain improvement rate in historical teaching data, and normalize the current bandwidth saving rate and the current learning gain improvement rate using a standardization method; S502. Obtaining bandwidth resource information of the AR teaching system to determine the bandwidth saving weight and learning gain weight; S503. Calculate the comprehensive effectiveness score of each teaching material generation scheme by weighted summation based on the normalized bandwidth saving rate and learning gain improvement rate, as well as the determined bandwidth saving weight and learning gain weight.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, the method runs the steps of the method for quickly generating AR teaching materials according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method for quickly generating AR teaching materials according to any one of claims 1 to 7 are executed.

Images