Online learning adjustment method and device based on large model, medium and equipment

By collecting and analyzing student learning behavior data, identifying learning styles and progress, and providing personalized teaching methods and content, the lack of personalization in the existing online learning system is solved, learning efficiency and motivation are improved, and the utilization of teaching resources is optimized. .

CN119089203APending Publication Date: 2024-12-06SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Patent Information

Application Number
CN202411195783.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing online learning system lacks personalization, cannot effectively meet the learning needs of different students, and fails to fully consider individual students' differences.

Method used

By collecting students' learning behavior data, extracting relevant characteristics of learning style and learning progress, using supervised learning classification models to identify learning styles, and providing personalized teaching methods and content based on learning styles and progress, and adjusting teaching content and adaptive learning algorithms. Path, providing personalized exercises and review materials, real-time feedback and learning incentive mechanisms.

Benefits of technology

It realizes a personalized learning experience, meets the learning needs of different students, improves learning efficiency and motivation, and optimizes the allocation and utilization of teaching resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089203A_ABST
    Figure CN119089203A_ABST
Patent Text Reader

Abstract

The invention provides an online learning adjustment method and device based on a large model, a medium and equipment. The method comprises the steps of collecting learning behavior data when a student performs a learning activity; extracting feature data related to a learning style from the learning behavior data; based on the feature data, adopting a supervised learning classification model to identify learning styles of the students; extracting index data influencing the learning progress from the learning behavior data; determining the learning progress of the student according to the index data; selecting a matched teaching method for the student according to the learning style; providing matched personalized learning content for the student according to the learning style and the learning progress; and according to the teaching method, providing the personalized learning content to a front-end user interface for display. According to the embodiment of the invention, learning requirements of different students can be met, and personalized learning experience is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of online learning systems, and in particular to an online learning adjustment method, device, medium and equipment based on a large model. Background Art

[0002] With the rapid development of information technology, online learning systems have become an important part of the education field. These systems provide rich learning resources and convenient learning methods, allowing learners to learn anytime and anywhere. However, most of the existing online learning systems adopt unified teaching content and schedule, lacking consideration for individual differences among students. Therefore, these online learning systems often fail to provide a truly personalized learning experience and are difficult to meet the learning needs of different students. Summary of the invention

[0003] In response to at least one of the above technical problems, an embodiment of the present invention provides an online learning adjustment method, device, medium, and equipment based on a large model.

[0004] According to the first aspect, the online learning adjustment method based on the large model provided by the embodiment of the present invention includes:

[0005] Collect learning behavior data when students are doing learning activities;

[0006] Extracting feature data related to learning style from the learning behavior data;

[0007] Based on the feature data, a supervised learning classification model is used to identify the learning style of the student;

[0008] Extracting indicator data that affects learning progress from the learning behavior data;

[0009] Determining the learning progress of the student according to the indicator data;

[0010] According to the learning style, a matching teaching method is selected for the student; according to the learning style and the learning progress, matching personalized learning content is provided for the student;

[0011] According to the teaching method, the personalized learning content is provided to the front-end user interface for display.

[0012] In one embodiment, the method further comprises:

[0013] When students are learning on the front-end interface, the student's answering behavior information is recorded, the student's answering accuracy is analyzed, and the difficulty of the questions is analyzed;

[0014] Record the student's learning activity information, count the student's learning time, and monitor the student's course completion;

[0015] Recording the students’ viewing behavior information of the teaching video, their participation in interactive exercises, and their learning paths;

[0016] Collect the students' speeches, interaction data and feedback in the discussion forum and provide course teaching suggestions;

[0017] Track the student's test scores and homework grades to analyze the student's learning outcomes; and analyze the student's performance behavior in specific learning abilities;

[0018] The various data recorded, analyzed or collected are integrated, and the integrated results are converted into a chart form through a visualization tool to be displayed on the front-end interface.

[0019] In one embodiment, the method further comprises at least one of the following:

[0020] Based on the learning behavior information and academic performance of multiple students, an unsupervised learning clustering algorithm is used to group the multiple students to obtain at least one group, and teaching resources matching the group are provided to each student;

[0021] Determine indicator data that affects learning progress; based on the indicator data, use a prediction model to predict the learning trend of the student, and when the predicted learning trend is a decline, provide the student with intervention measures to improve the learning trend;

[0022] Determine, based on the student's learning performance information, whether the student has encountered difficulties and / or bottlenecks in the learning process; if difficulties and / or bottlenecks occur, provide the student with personalized intervention measures;

[0023] Recommending a matching learning path for the student based on the student's learning style, learning progress, and learning performance information, and adjusting the learning path based on changes in the student's learning status;

[0024] The decision tree model is used to analyze the factors that affect students' learning outcomes, and the teaching resources and teaching strategies of students are optimized according to the results of factor analysis.

[0025] In one embodiment, the method may further include at least one of the following:

[0026] Analyze the student's test scores and learning behavior data to obtain the student's mastery level, dynamically adjust the course content according to the mastery level, and provide the student with personalized exercises and review materials;

[0027] Recommending corresponding courses to the student based on the student's learning history and interests;

[0028] Adjust the teaching difficulty according to the students' answering performance; and use an adaptive learning algorithm to adjust the presentation order and depth of teaching content according to the students' learning pace;

[0029] Provide a user control panel to enable students to adjust their learning plans and speed according to their own learning goals and schedules; provide a learning incentive mechanism to stimulate the learning motivation of the students.

[0030] In one embodiment, the method further comprises at least one of the following:

[0031] After students complete a test or homework, provide performance feedback, which includes the correct answer and solution ideas; display the student's learning progress and goal achievement in the form of charts and progress bars; provide personalized learning suggestions and improvement strategies for the student based on the student's test scores and learning behavior data;

[0032] Providing feedback forms to enable the students to make suggestions on the course content, teaching methods and learning experience; establishing discussion areas and forums to enable the students to communicate and discuss;

[0033] Collect student feedback and suggestions centrally and identify themes in said feedback and suggestions so that the teacher can respond to said themes;

[0034] Improve students' feedback participation by rewarding points; regularly display feedback cases with suggestions;

[0035] Propose a mechanism for teachers to evaluate students' learning and a mechanism for students to evaluate each other.

[0036] In one embodiment, the method further comprises:

[0037] Based on the suggestions and feedback from students and teachers, the teaching content is regularly updated and new teaching methods are explored.

[0038] In one embodiment, the method further comprises at least one of the following:

[0039] Provide barrier-free learning mode, provide screen reader compatibility for the visually impaired, and provide subtitles and sign language learning methods for the hearing impaired;

[0040] A note-taking tool is provided so that students can use the note-taking tool to mark during learning activities.

[0041] According to the second aspect, the online learning adjustment device based on the large model provided by the embodiment of the present invention includes:

[0042] The data collection module is used to collect learning behavior data when students are carrying out learning activities;

[0043] A feature extraction module, used to extract feature data related to learning style from the learning behavior data;

[0044] A model identification module, used to identify the learning style of the student using a supervised learning classification model based on the feature data;

[0045] An indicator extraction module, used to extract indicator data affecting learning progress from the learning behavior data;

[0046] A progress determination module, used to determine the learning progress of the student according to the indicator data;

[0047] A content determination module, configured to select a matching teaching method for the student according to the learning style; and to provide the student with matching personalized learning content according to the learning style and the learning progress;

[0048] The content display module is used to provide the personalized learning content to the front-end user interface for display according to the teaching method.

[0049] According to a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method provided in the first aspect.

[0050] According to a fourth aspect, an embodiment of the present invention provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method provided in the first aspect is implemented.

[0051] The online learning adjustment method, device, medium, and equipment based on a large model provided in the embodiment of the present invention collect learning behavior data when students are performing learning activities, extract feature data related to learning style from the learning behavior data, and thus use a supervised learning classification model to identify the learning style of the student. Then, the indicator data affecting the learning progress is extracted from the learning behavior data, and the learning progress of the student is determined based on the indicator data. Thus, a matching teaching method can be selected for the student according to the learning style, and matching personalized learning content can be provided for the student according to the learning style and the learning progress. It can be seen that the embodiment of the present invention takes into account the individual differences of students and provides students with suitable teaching methods and personalized learning content, and the personalized learning content is in line with the learning style and learning progress. It can be seen that compared with the unified teaching content and progress schedule in the prior art, the embodiment of the present invention can meet the learning needs of different students and realize a personalized learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flowchart of an online learning adjustment method based on a large model in one embodiment of the present invention;

[0053] Figure 2 A schematic diagram of various contents involved in generating a personalized learning plan in one embodiment of the present invention;

[0054] Figure 3 A schematic diagram of a system architecture involved in an embodiment of the present invention;

[0055] Figure 4 It is a structural block diagram of an online learning adjustment device based on a large model in one embodiment of the present invention. DETAILED DESCRIPTION

[0056] In a first aspect, an embodiment of the present invention provides an online learning adjustment method based on a large model, the method comprising the following steps S110 to S170:

[0057] S110. Collect learning behavior data when students are doing learning activities;

[0058] Among them, learning behavior data, for example, students' operations on the online learning system, test scores, feedback suggestions and interaction information, etc.

[0059] S120, extracting characteristic data related to learning style from the learning behavior data;

[0060] Among them, characteristic data related to learning style include video viewing preferences, note-taking habits, and participation in interactive exercises.

[0061] S130, based on the feature data, using a supervised learning classification model to identify the learning style of the student;

[0062] In other words, by inputting the feature data related to learning style into the supervised learning classification model, the student's learning style can be obtained.

[0063] Among them, supervised learning classification models, such as support vector machines.

[0064] Among them, learning style refers to the way students have or prefer when learning. In other words, it is the personal way students show when studying and solving their learning tasks.

[0065] S140, extracting indicator data affecting learning progress from the learning behavior data;

[0066] Among them, indicator data that affect learning progress include homework submission rate, test scores, learning activity and other indicator data.

[0067] S150, determining the learning progress of the student according to the indicator data;

[0068] It can be seen that after determining the indicator data that affect students' learning progress, the students' learning progress can be determined based on these indicators.

[0069] S160, selecting a matching teaching method for the student according to the learning style; providing matching personalized learning content for the student according to the learning style and the learning progress;

[0070] Among them, teaching methods, for example, visual aids, auditory instruction, or hands-on practice.

[0071] Among them, personalized learning content, videos, articles, charts, etc., are provided to suit different learning styles.

[0072] It can be seen that matching teaching methods are selected for students based on their learning styles, and personalized learning content that suits their learning progress and learning style is provided to students based on their learning styles and learning progress.

[0073] S170. According to the teaching method, the personalized learning content is provided to a front-end user interface for display.

[0074] That is, personalized learning content that conforms to the teaching method is provided to the front-end user interface so that students can get personalized learning content. At the same time, the student's learning progress can be monitored to ensure that the student is progressing according to the learning plan and provide additional support when necessary.

[0075] In actual scenarios, relevant data of students can be collected and then displayed on the front end so that students can understand their own learning situation. To this end, in one embodiment, the embodiment of the present invention can also include the following steps S210 to S260:

[0076] S210, when the student is learning on the front-end interface, record the student's answering behavior information, analyze the student's answering accuracy, and analyze the difficulty of the questions;

[0077] For example, the student's answering behavior information such as answering time, number of attempts, and modification records are recorded. Based on an automatic scoring system, the accuracy of the answer is instantly evaluated, so as to analyze the difficulty of the question for the student based on the student's answer accuracy. The answering behavior information, answering accuracy, question difficulty, etc. can be displayed on the front-end interface later.

[0078] S220, recording the student's learning activity information, counting the student's learning time, and monitoring the student's course completion;

[0079] Specifically, the learning management system can be used to record students' login activities, course access, learning progress and other learning activity information, count students' online learning time, monitor students' course completion, and thus learn students' learning efficiency and course progress. If the learning efficiency is relatively low or the course progress is relatively backward, the student can be identified as a student who needs additional help, and the teacher can be reminded to provide additional help. It can be seen that information such as learning activity information, learning time, course completion, and whether additional help is needed can be displayed on the front-end interface.

[0080] S230, recording the student's viewing behavior information of the teaching video, interactive exercise participation and learning path;

[0081] Specifically, record students' behavior when watching teaching videos, such as viewing speed, pause and replay times, to understand learning difficulties. Monitor students' participation in interactive exercises, including number of attempts, accuracy and completion time. Track students' learning paths on the system and analyze learning behavior patterns and preferences.

[0082] S240, collecting the student's speech, interaction data and feedback course teaching suggestions in the discussion area;

[0083] Specifically, we collect students' speech and interaction data in the discussion area, and then evaluate their participation and community contribution. We encourage students to provide feedback on courses and teaching methods, and collect suggestions to improve teaching content. It can be seen that students' speech, interaction data, and feedback course teaching suggestions can be displayed on the front-end interface.

[0084] S250, tracking the test scores and homework scores of the students to analyze the learning outcomes of the students; and analyzing the performance of the students in specific learning abilities;

[0085] Specifically, track students' test scores and assignment grades, analyze learning outcomes and progress trends, and assess students' performance on key competencies, such as critical thinking, problem solving, and application of knowledge.

[0086] S260, integrating various recorded, analyzed or collected data, and converting the integration results into a chart form through a visualization tool to display them on the front-end interface.

[0087] Specifically, various data that are recorded, analyzed, and collected are integrated, and data visualization tools are used to present the integrated data in the form of charts and graphs for easy understanding and analysis.

[0088] In practical scenarios, the present invention involves various algorithms, and different algorithms are used to implement different functions. In one embodiment, the method provided by the embodiment of the present invention may also include at least one of the following:

[0089] (1) based on the learning behavior information and academic performance of multiple students, using an unsupervised learning clustering algorithm to group the multiple students to obtain at least one group, and providing each student with teaching resources that match the group;

[0090] It can be seen that the unsupervised learning clustering algorithm K-means uses students' learning behavior, grades and other characteristics to determine the similarities between students, conduct effective grouping, and then provide students with matching teaching resources based on grouping. The grouping strategy can also be regularly evaluated and optimized to ensure that teaching resources match the needs of the student group.

[0091] (2) determining indicator data that affects learning progress; based on the indicator data, using a prediction model to predict the student's learning trend, and when the predicted learning trend is a downward trend, providing the student with intervention measures to improve the learning trend;

[0092] Specifically, determine the key indicators that affect learning progress, such as homework submission rate, test scores, and learning activity. Use time series analysis, regression analysis, or deep learning technology to build a prediction model. Input the indicator data into the prediction model to obtain the student's learning trend. If the learning trend is declining, intervention measures to improve the learning trend can be provided to the student.

[0093] (3) determining, based on the student's learning performance information, whether the student has encountered difficulties and / or bottlenecks in the learning process; if difficulties and / or bottlenecks have occurred, providing the student with personalized intervention measures;

[0094] Specifically, by analyzing students' performance on specific courses or topics, possible learning difficulties are identified. Algorithms are developed to identify bottlenecks in students' learning process, such as barriers to conceptual understanding or insufficient skill mastery. If students encounter difficulties and / or bottlenecks, personalized intervention measures are provided to the students, such as additional practice, tutoring, or learning resources. Personalized tutoring services can also be provided to students who need additional help, such as one-on-one online tutoring or targeted study groups.

[0095] (4) recommending a matching learning path for the student based on the student's learning style, learning progress, and learning performance information, and adjusting the learning path based on changes in the student's learning status;

[0096] Specifically, we develop adaptive algorithms to recommend the most appropriate learning path based on students’ learning style, progress, and performance. As students’ learning status changes, we update the recommended path in a timely manner to ensure that each student can get a learning experience that meets their individual needs and abilities.

[0097] (5) Use the decision tree model to analyze the factors that affect students’ learning outcomes, and optimize students’ teaching resources and teaching strategies based on the results of the factor analysis.

[0098] Specifically, a decision tree model is constructed and used to analyze various factors that affect students’ learning outcomes, such as learning motivation, external environment, and psychological state. Based on the data analysis results, the teaching strategy and allocation of teaching resources are optimized to improve the teaching effect, thereby providing data-based teaching decision support for teachers and educators.

[0099] The algorithms mentioned above need to be regularly evaluated and optimized. Specifically, define and track key performance indicators of the algorithm, such as precision, recall, and F1 score. Use methods such as cross-validation to evaluate the accuracy and generalization ability of the algorithm.

[0100] In actual scenarios, the generation of intelligent learning adjustment plans can be achieved. To this end, in one embodiment, see Figure 2 , the embodiment of the present invention may further include at least one of the following:

[0101] (1) analyzing the student's test scores and learning behavior data to obtain the student's mastery level, dynamically adjusting the course content according to the mastery level, and providing the student with personalized exercises and review materials;

[0102] Specifically, we analyze students’ test scores and learning behavior data in real time to identify their mastery level. Based on their mastery level, we dynamically adjust the difficulty of the course content to ensure that students feel neither too easy nor too difficult, and provide them with exercises and review materials of moderate difficulty.

[0103] (2) recommending appropriate courses to the student based on the student’s learning history and interests;

[0104] Specifically, an intelligent recommendation system is developed to recommend relevant courses and topics based on students' learning history and interests.

[0105] (3) adjusting the teaching difficulty according to the students’ answering performance; and adjusting the presentation order and depth of the teaching content using an adaptive learning algorithm according to the students’ learning pace;

[0106] Specifically, a real-time feedback loop is established to adjust the teaching difficulty in real time according to the students’ answering performance. Adaptive learning algorithms are used to automatically adjust the presentation order and depth of learning content to match the students’ learning pace.

[0107] (4) Providing a user control panel to enable students to adjust their learning plans and speed according to their own learning goals and schedules; providing a learning incentive mechanism to stimulate the learning motivation of the students.

[0108] Specifically, provide a user control panel that allows students to adjust their learning plans and speed according to their learning goals and schedules. Design a learning achievement system to motivate students through badges, certificates, and rewards to increase learning motivation and participation.

[0109] In actual scenarios, a feedback mechanism may also be implemented. To this end, in one embodiment, the method provided by the embodiment of the present invention may also include at least one of the following:

[0110] (1) Providing performance feedback after students complete a test or homework, the performance feedback including the correct answer and solution ideas; displaying the student's learning progress and goal achievement in the form of charts and progress bars; providing the student with personalized learning suggestions and improvement strategies based on the student's test scores and learning behavior data;

[0111] Specifically, after students complete a test or homework, they will receive immediate feedback on their performance, including the correct answer and solution. Through charts and progress bars, students' learning progress and goal achievement can be intuitively displayed. Based on students' test scores and learning behaviors, personalized learning suggestions and improvement strategies can be provided.

[0112] (2) Providing feedback forms to enable the students to make suggestions on the course content, teaching methods and learning experience; establishing discussion areas and forums to enable the students to communicate and discuss;

[0113] Specifically, design simple and easy-to-use feedback forms to encourage students to make suggestions on course content, teaching methods and learning experience. Establish discussion areas and forums to promote communication and discussion among students and collect collective feedback from students. Use online chats and question-and-answer sessions to achieve real-time interaction and feedback exchanges between teachers and students.

[0114] (3) Collect students' feedback and suggestions and identify themes in the feedback and suggestions so that teachers can respond to the themes;

[0115] Specifically, provide a system that allows teachers to easily collect, view and manage student feedback. Use data analysis tools to help teachers identify common themes and trends in feedback. Establish a systematic feedback response mechanism to ensure that teachers can respond to student feedback in a timely manner.

[0116] (4) Improving the feedback participation of the students by means of point rewards; regularly displaying feedback cases that provide suggestions;

[0117] Specifically, students who actively participate in feedback are rewarded with points to increase their participation and enthusiasm. Excellent feedback cases are regularly displayed to encourage students to put forward constructive opinions and suggestions. The results of feedback and improvement measures are shared with students to make them feel that their voices are valued.

[0118] (5) Propose a mechanism for teachers to evaluate students’ learning and a mechanism for students to evaluate each other.

[0119] Specifically, in addition to student feedback, teachers’ evaluation and suggestions on students’ learning are also collected. A peer evaluation mechanism is implemented to allow students to evaluate and provide feedback to each other, promoting learning exchanges.

[0120] In one embodiment, the method provided by the embodiment of the present invention may further include:

[0121] Based on the suggestions and feedback from students and teachers, the teaching content is regularly updated and new teaching methods are explored.

[0122] Specifically, we regularly update and optimize teaching content based on feedback from students and teachers, and explore and implement new teaching methods to improve teaching effectiveness and student satisfaction.

[0123] Of course, you can also provide anonymous feedback options to allow students to provide authentic feedback without having to worry about privacy issues. To ensure the security of all feedback data, measures such as encrypted storage and access control can be taken. Develop a feedback ethics code to ensure respect and fairness in the feedback process.

[0124] In practical applications, SSL / TLS protocols can be used to encrypt all data in transit to ensure the security of data during transmission. Encrypt sensitive data stored in the database so that even if the data is illegally accessed, it cannot be easily interpreted. Implement end-to-end encryption for particularly sensitive information, such as user communication content, so that only the sender and receiver can decrypt it. Implement multi-factor authentication, combining passwords and mobile phone verification codes to enhance account security. Set different access rights based on user roles and responsibilities to ensure that users can only access corresponding data and resources. Strictly manage user sessions, including session timeouts, automatic logouts, and session restarts to prevent unauthorized access. Conduct regular compliance reviews to ensure that the system's operations and data processing processes comply with data protection regulations such as GDPR and CCPA. Develop a clear privacy policy to clearly inform users how their data is collected, used, shared, and protected. Protect users' data subject rights, such as the right to access, the right to correct, the right to delete, and the right to carry data. Provide users with security education, including how to set strong passwords, identify phishing attacks, and protect personal information. Raise users' privacy awareness and let them understand the value of their data and how to protect their privacy. Establish security and privacy-related user feedback channels to encourage users to report suspicious activities or security issues.

[0125] It can be seen that security and privacy protection can be achieved through data encryption and access control, while also complying with data protection regulations and improving user security education and awareness.

[0126] In order to realize the above functions, the system architecture of the embodiment of the present invention involves a front-end interface, a back-end server, a database, a data analysis engine, etc. Figure 3 .

[0127] The front-end interface uses JavaScript framework as the front-end technology stack to achieve adaptive layout to adapt to different screen sizes and resolutions. The interface design focuses on interactivity, providing drag-and-drop, click feedback and animation effects to enhance user participation and learning motivation.

[0128] The backend server uses a powerful server-side language to handle complex business logic, such as user authentication, course logic, and personalized recommendation algorithms. Build a RESTful API to support efficient data exchange between the frontend and backend. Design a microservice architecture to modularize different business functions for easy future expansion and maintenance.

[0129] Among them, we design optimized databases to support fast query and transaction processing, and ensure data consistency and integrity. We implement regular data backup strategies and disaster recovery plans to prevent data loss and system failures, and ensure data backup and recovery. We use encrypted storage and access control to protect sensitive data from unauthorized access.

[0130] For the data analysis engine, data mining techniques such as clustering, association rules, and anomaly detection can be used to discover valuable patterns and associations from a large amount of learning data. Integrate a variety of machine learning models, such as decision trees, random forests, neural networks, etc., to meet the needs of different types of learning data analysis. Realize real-time data analysis capabilities, quickly respond to changes in students' learning behaviors, and adjust teaching strategies in real time. Develop prediction models to predict students' future performance based on historical data, and provide students with early warnings and personalized guidance.

[0131] In order to ensure user-friendliness, the front-end interface is designed with an intuitive navigation bar so that users can easily find the courses and resources they need. The navigation bar includes course classification, learning path, personal center and help support. Simplify the user operation process and reduce the learning curve. Guided tutorials and prompts are used to help new users quickly familiarize themselves with the system and ensure intuitive operation. Ensure that the buttons, icons and font styles of the entire system are consistent to enhance user cognition and memory and ensure visual consistency.

[0132] The front-end interface supports multiple languages. A language selection function is provided when users register or log in, allowing users to set the interface language according to their native language or preference. In addition to the interface language, localized learning content is also provided, including translated course materials and case studies related to local culture. The interface design takes into account the character length and reading habits of different languages ​​to ensure the display effect in different language environments.

[0133] Among them, the front-end interface can be personalized. Allow users to adjust the interface layout according to personal preferences, such as adjusting the width of the sidebar, changing the layout of the content area, etc. Provide function customization options, users can choose to display or hide certain components, such as the note area, discussion board or progress bar. Users can choose different themes and styles, such as dark mode, light mode or custom color schemes to adapt to different visual preferences and ambient light conditions.

[0134] Among them, the front-end interface has accessibility features. Ensure that the system meets barrier-free design standards, provide screen reader compatibility for the visually impaired, and provide subtitles and sign language videos for the hearing impaired. Provide options to adjust font size and contrast to help users with reading difficulties read text more comfortably. Design interactive prompts and help systems for users who need additional help, such as online customer service, FAQs, and system operation learning guides.

[0135] The front-end interface integrates learning tools. The integrated note-taking tool allows users to take notes and mark during the learning process, which is convenient for review and memory. Interactive quizzes and gamification elements are designed to increase the fun and participation of learning. Forums and discussion boards are provided to encourage communication and cooperation among students and enhance the sense of community.

[0136] It can be seen that, in one embodiment, the method provided by the embodiment of the present invention further includes at least one of the following:

[0137] 1. Provide barrier-free learning mode, provide screen reader compatibility for the visually impaired, and provide subtitles and sign language learning methods for the hearing impaired;

[0138] 2. Provide note-taking tools so that students can use them to mark during learning activities.

[0139] Based on the above content, the following summary is made:

[0140] The system architecture involved in the embodiment of the present invention includes:

[0141] (1) Front-end interface: Built with JavaScript framework, it has responsive design, can adapt to different screen sizes and resolutions, and provides interactive design such as drag-and-drop, click feedback, and animation effects;

[0142] (2) Backend server: Use server-side languages ​​to process business logic, build RESTful APIs, and adopt microservice architecture design;

[0143] (3) Database: Have an optimized data model, implement data backup and recovery strategies, as well as data encryption and access control;

[0144] (4) Data analysis engine: Uses data mining technology and integrates multiple machine learning models to achieve real-time data analysis and develop predictive models.

[0145] Among them, the front-end user interface can achieve clear navigation, including course classification, learning path, personal center and help support; it can also achieve intuitive operation process, specifically through guided tutorials and prompts to help new users quickly familiarize themselves with the system; it can also achieve visual consistency, specifically by ensuring that the buttons, icons and font styles are consistent.

[0146] The backend server has a multi-factor authentication mechanism and session management capabilities, including session timeout, automatic logout, and session restart.

[0147] Among them, the database complies with the compliance of data protection regulations such as GDPR and CCPA, and protects the rights of user data subjects, such as the right to access, the right to correct, the right to delete, and the right to data portability.

[0148] Among them, the data analysis engine includes: the application of classification algorithms for learning style identification; clustering algorithms for student grouping; and the construction of predictive models for learning progress prediction.

[0149] Based on the above system architecture, the embodiment of the present invention can realize intelligent learning adjustment, specifically including: dynamic course adjustment function, specifically real-time adjustment according to students' test scores and learning behavior data; intelligent learning adjustment path planning capability, including course recommendation system and learning material customization; real-time feedback loop and learning progress monitoring capability. The embodiment of the present invention can realize feedback mechanism, mainly including: instant feedback system, providing score analysis and learning progress visualization; interactive feedback tools, including feedback forms, discussion areas and forums; teacher feedback management system, integrated with data analysis tools and feedback response mechanism. The embodiment of the present invention can also realize security and privacy protection functions, specifically including: transmission encryption, storage encryption and end-to-end encryption; multi-factor authentication, permission management and session management; user education and awareness enhancement, including security education, privacy awareness and feedback channels.

[0150] It can be seen that the embodiments of the present invention use advanced front-end technology, powerful back-end services, a secure database system, and an intelligent data analysis engine to create a responsive, user-friendly, and highly interactive learning environment. Through real-time data collection and analysis, the system is able to identify students' learning styles, learning progress, bottlenecks, etc., and dynamically adjust the course difficulty and teaching methods accordingly. In addition, multi-language support, personalized setting options, and integrated learning tools are provided to enhance the learning experience. The feedback mechanism allows students and teachers to communicate effectively and promotes continuous improvement of teaching content and methods. Security and privacy protection measures ensure the security of user data and the protection of user privacy.

[0151] The embodiments of the present invention create a flexible and adaptive learning environment, in which teaching content, learning paths and evaluation criteria are dynamically generated based on students' real-time performance and learning data. In this way, the system can provide each student with a tailored learning plan to help them learn in the way that best suits them. Moreover, advanced data analysis techniques such as machine learning and data mining are used to deeply understand students' learning behaviors and needs. This will enable the system to predict the difficulties that students may encounter and provide corresponding support and resources in advance. Moreover, by providing a highly personalized learning system, it can not only improve students' learning efficiency and results, but also stimulate their interest in learning, cultivate the habit of lifelong learning, and contribute to the modernization and innovation of education.

[0152] The embodiments of the present invention have the following beneficial effects:

[0153] (1) Intelligent learning adjustment experience: Dynamically adjust teaching content and methods to meet the learning needs and preferences of different students.

[0154] (2) Improve learning efficiency: Real-time analysis and prediction models help students overcome learning bottlenecks and speed up their learning progress.

[0155] (3) Enhance learning motivation: Stimulate students’ interest and motivation through interactive feedback tools and learning achievement systems.

[0156] (4) Optimizing teaching resources: Data-driven decision support helps teachers and educators allocate and utilize teaching resources more effectively.

[0157] In a second aspect, an embodiment of the present invention provides an online learning adjustment device based on a large model, see Figure 4 , the device 100 comprises:

[0158] The data collection module 110 is used to collect learning behavior data when students are performing learning activities;

[0159] A feature extraction module 120, used to extract feature data related to learning style from the learning behavior data;

[0160] A model identification module 130, for identifying the learning style of the student using a supervised learning classification model based on the feature data;

[0161] An indicator extraction module 140, used to extract indicator data affecting learning progress from the learning behavior data;

[0162] A progress determination module 150, for determining the learning progress of the student according to the indicator data;

[0163] The content determination module 160 is used to select a matching teaching method for the student according to the learning style; and provide the student with matching personalized learning content according to the learning style and the learning progress;

[0164] The content display module 170 is used to provide the personalized learning content to the front-end user interface for display according to the teaching method.

[0165] In one embodiment, the apparatus further comprises:

[0166] The data collection module is used to record the students' answering behavior information, analyze the students' answering accuracy, and analyze the difficulty of questions when the students are learning on the front-end interface; record the students' learning activity information, count the students' learning time, and monitor the students' course completion; record the students' viewing behavior information of teaching videos, interactive exercise participation and learning paths; collect the students' speeches, interactive data and feedback on course teaching suggestions in the discussion area; track the students' test scores and homework scores to analyze the students' learning outcomes; and analyze the students' performance behaviors in specific learning abilities; integrate the various recorded, analyzed or collected data, and convert the integrated results into charts through visualization tools to display on the front-end interface.

[0167] In one embodiment, the device may further include at least one of the following:

[0168] A student grouping module is used to group the multiple students based on their learning behavior information and academic performance, using an unsupervised learning clustering algorithm to obtain at least one group, and provide each student with teaching resources that match the group to which they belong;

[0169] A trend prediction module is used to determine indicator data that affects learning progress; based on the indicator data, a prediction model is used to predict the learning trend of students, and when the predicted learning trend is a downward trend, intervention measures are provided to the students to improve the learning trend;

[0170] A bottleneck prediction module is used to determine whether the student encounters difficulties and / or bottlenecks in the learning process according to the student's learning performance information; if difficulties and / or bottlenecks occur, provide personalized intervention measures for the student;

[0171] A path recommendation module, used to recommend a matching learning path for the student according to the student's learning style, learning progress and learning performance information, and to adjust the learning path according to changes in the student's learning status;

[0172] The factor analysis module is used to analyze the factors that affect students' learning outcomes using a decision tree model, and optimize students' teaching resources and teaching strategies based on the results of the factor analysis.

[0173] In one embodiment, the device may further include at least one of the following:

[0174] A dynamic adjustment module is used to analyze the test scores and learning behavior data of the students to obtain the mastery level of the students, dynamically adjust the course content according to the mastery level, and provide personalized exercises and review materials for the students;

[0175] A course recommendation module, used to recommend corresponding courses to the student based on the student's learning history and interests;

[0176] A difficulty adjustment module is used to adjust the teaching difficulty according to the student's answering performance; according to the student's learning rhythm, an adaptive learning algorithm is used to adjust the presentation order and depth of the teaching content;

[0177] The panel provides a module for providing a user control panel so that students can adjust their learning plans and speeds according to their own learning goals and schedules; and provides a learning incentive mechanism to stimulate the learning motivation of the students.

[0178] In one embodiment, the device may further include at least one of the following:

[0179] The performance feedback module is used to provide performance feedback after students complete a test or homework, including the correct answer and solution ideas; display the student's learning progress and goal achievement in the form of charts and progress bars; and provide personalized learning suggestions and improvement strategies for the student based on the student's test scores and learning behavior data;

[0180] A form providing module is used to provide feedback forms so that the students can make suggestions on the course content, teaching methods and learning experience; establish discussion areas and forums so that the students can communicate and discuss;

[0181] A topic identification module is used to centrally collect students' feedback and suggestions and identify topics in the feedback and suggestions so that the teacher can respond to the topics;

[0182] Points reward module, used to improve the feedback participation of students by means of points rewards; regularly display feedback cases with suggestions;

[0183] The evaluation module is used to propose a mechanism for teachers to evaluate students' learning and a mechanism for students to evaluate each other.

[0184] In one embodiment, the apparatus further comprises:

[0185] The regular update module is used to regularly update the teaching content and explore new teaching methods based on the suggestions and feedback from the students and teachers.

[0186] In one embodiment, the device further comprises at least one of the following:

[0187] Mode provision module, which is used to provide barrier-free learning mode, providing screen reader compatibility for the visually impaired, and providing subtitles and sign language learning methods for the hearing impaired;

[0188] The tool providing module is used to provide a note-taking tool so that students can use the note-taking tool to mark during learning activities.

[0189] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0190] In a third aspect, an embodiment of the present invention provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0191] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can read and execute the program code stored in the storage medium.

[0192] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0193] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0194] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0195] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0196] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0197] In a fourth aspect, an embodiment of the present specification provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method in any embodiment of the specification.

[0198] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the computing device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0199] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0200] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, widgets, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0201] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. An online learning adjustment method based on a large model, characterized in that: include: Collect learning behavior data when students are doing learning activities; Extracting feature data related to learning style from the learning behavior data; Based on the feature data, a supervised learning classification model is used to identify the learning style of the student; Extracting indicator data that affects learning progress from the learning behavior data; Determining the learning progress of the student according to the indicator data; According to the learning style, a matching teaching method is selected for the student; according to the learning style and the learning progress, matching personalized learning content is provided for the student; According to the teaching method, the personalized learning content is provided to the front-end user interface for display.

2. The method according to claim 1, characterized in that Also includes: When students are learning on the front-end interface, the student's answering behavior information is recorded, the student's answering accuracy is analyzed, and the difficulty of the questions is analyzed; Record the student's learning activity information, count the student's learning time, and monitor the student's course completion; Recording the students’ viewing behavior information of the teaching video, their participation in interactive exercises, and their learning paths; Collect the students' speeches, interaction data and feedback in the discussion forum and provide course teaching suggestions; Tracking the test scores and homework grades of the students to analyze the learning outcomes of the students; and analyzing said students' performance behaviors in specific learning abilities; The various data recorded, analyzed or collected are integrated, and the integrated results are converted into a chart form through a visualization tool to be displayed on the front-end interface.

3. The method according to claim 1, characterized in that: Also includes at least one of the following: Based on the learning behavior information and academic performance of multiple students, an unsupervised learning clustering algorithm is used to group the multiple students to obtain at least one group, and teaching resources matching the group are provided to each student; Determine indicator data that affects learning progress; based on the indicator data, use a prediction model to predict the learning trend of the student, and when the predicted learning trend is a decline, provide the student with intervention measures to improve the learning trend; Determine, based on the student's learning performance information, whether the student has encountered difficulties and / or bottlenecks in the learning process; if difficulties and / or bottlenecks occur, provide the student with personalized intervention measures; Recommending a matching learning path for the student based on the student's learning style, learning progress, and learning performance information, and adjusting the learning path based on changes in the student's learning status; The decision tree model is used to analyze the factors that affect students' learning outcomes, and the teaching resources and teaching strategies of students are optimized according to the results of factor analysis.

4. The method according to claim 1, characterized in that: Also includes at least one of the following: Analyze the student's test scores and learning behavior data to obtain the student's mastery level, dynamically adjust the course content according to the mastery level, and provide the student with personalized exercises and review materials; Recommending corresponding courses to the student based on the student's learning history and interests; Adjust the teaching difficulty according to the students' answering performance; and use an adaptive learning algorithm to adjust the presentation order and depth of teaching content according to the students' learning pace; Provide a user control panel to enable students to adjust their learning plans and speed according to their own learning goals and schedules; provide a learning incentive mechanism to stimulate the learning motivation of the students.

5. The method according to claim 1, characterized in that Also includes at least one of the following: After students complete a test or homework, provide performance feedback, which includes the correct answer and solution ideas; display the student's learning progress and goal achievement in the form of charts and progress bars; provide personalized learning suggestions and improvement strategies for the student based on the student's test scores and learning behavior data; Providing feedback forms to enable the students to make suggestions on the course content, teaching methods and learning experience; establishing discussion areas and forums to enable the students to communicate and discuss; Collect student feedback and suggestions centrally and identify themes in said feedback and suggestions so that the teacher can respond to said themes; Improve students' feedback participation by rewarding points; regularly display feedback cases with suggestions; Propose a mechanism for teachers to evaluate students' learning and a mechanism for students to evaluate each other.

6. The method according to claim 1, characterized in that Also includes: Based on the suggestions and feedback from students and teachers, the teaching content is regularly updated and new teaching methods are explored.

7. The method according to claim 1, characterized in that Also includes at least one of the following: Provide barrier-free learning mode, provide screen reader compatibility for the visually impaired, and provide subtitles and sign language learning methods for the hearing impaired; A note-taking tool is provided so that students can use the note-taking tool to mark during learning activities.

8. An online learning adjustment device based on a large model, characterized in that: include: The data collection module is used to collect learning behavior data when students are carrying out learning activities; A feature extraction module, used to extract feature data related to learning style from the learning behavior data; A model identification module, used to identify the learning style of the student based on the feature data using a supervised learning classification model; An indicator extraction module, used to extract indicator data affecting learning progress from the learning behavior data; A progress determination module, used to determine the learning progress of the student according to the indicator data; A content determination module, configured to select a matching teaching method for the student according to the learning style; and to provide the student with matching personalized learning content according to the learning style and the learning progress; The content display module is used to provide the personalized learning content to the front-end user interface for display according to the teaching method.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

10. A computing device, characterized in that The method comprises a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Smart education system based on SPOC

    CN118014796A

  • Intelligent language education system and method

    CN118135851A

  • Multimedia information visualization system

    CN118333805A

  • Intelligent classroom management method and system based on artificial intelligence

    CN118469777A

  • Server and method for providing AI chatbot tutor for complete learning-based personalized learning support

    KR102648139B1

Cited By

  • Multimedia education course resource playing method and device

    CN119402686A

  • A multimedia education course resource playing method and device

    CN119402686B

  • Large model-based intelligent children interaction cloud system and control method therefor

    WO2026129465A1