Personalized Education Experience AI Enables Student Card System

Abstract

The present invention relates to a personalized educational experience AI-enabled student card system, comprising an electronic student card, a remote server and a teacher client. The electronic student card comprises a display screen, a communication module, a memory and a processor. The display screen is used to display learning-related information, the memory stores student-related data, the processor retrieves data from the memory and generates personalized learning content using a pre-trained AI algorithm, and then displays it on the display screen. The communication module realizes two-way data communication between the electronic student card and the remote server and other student cards. Personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools. The remote server is used to store data of multiple students, train and update AI algorithm models, and send the latest version of the model to the electronic student card. The present invention aims to provide a comprehensive system for realizing personalized learning and interaction through AI technology to improve the quality and efficiency of education.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a personalized education experience AI-enabled student card system. Background Art

[0002] In the existing technology, the traditional education system usually relies on teachers and textbooks to provide learning content and evaluate students' learning progress. Although these methods are effective to a certain extent, they lack personalized teaching plans and cannot be adjusted according to the specific needs and learning speed of each student. With the development of technology, electronic learning devices and online education platforms have gradually been introduced, trying to improve the quality and efficiency of education through digital means.

[0003] However, there are multiple problems with existing e-learning devices and online education platforms. First, these systems usually provide standardized learning content, lack customized content for individual students, and cannot meet the unique needs of each student. Second, existing systems are deficient in real-time feedback and personalized assessment, making it difficult to adjust learning content in a timely manner to meet students' immediate needs. Finally, the interaction between teachers and students is limited, making it difficult for teachers to fully grasp students' learning situation and provide effective guidance.

[0004] Therefore, there is an urgent need to develop a new AI-enabled student card system with personalized educational experience. Summary of the invention

[0005] This application provides a personalized education experience AI-enabled student card system to improve the quality and efficiency of education.

[0006] This application provides a personalized education experience AI-enabled student card system, including:

[0007] An electronic student card comprises a display screen, a communication module, a memory and a processor; wherein the display screen is used to display learning-related information; the memory is used to store student-related data of the card-holding student; the processor communicates with the display screen and the memory, and is used to retrieve the student-related data from the memory; based on the retrieved student-related data, personalized learning content is generated using an AI algorithm model pre-trained and stored in the memory; the generated personalized learning content is displayed on the display screen; the communication module is used to perform two-way data communication with other electronic student cards on a remote server; wherein the personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools;

[0008] A remote server, communicating with the communication module, for centrally storing student-related data of multiple students; training and updating the AI ​​algorithm model, and sending the latest version of the AI ​​algorithm model to the memory of the electronic student card;

[0009] The teacher client communicates with the remote server to allow the teacher to monitor the student's progress, provide personalized feedback, adjust the student's personalized learning content and experience, and access the student's learning records and analysis reports.

[0010] Furthermore, the student-related data includes basic student information, extended student information, academic data, learning behavior data, psychometric data, interaction data and biometric data, wherein the basic student information includes the student's name, age, grade and gender, which is used to obtain a preliminary understanding of the student's background; the extended student information includes attendance records, health status, and participation in extracurricular activities, which is used to fully understand the student's overall situation; the academic data includes courses, grades, test scores, homework completion, and learning progress, which are used to evaluate students' academic performance and ability levels; the learning behavior data includes study time, study habits, preferred learning methods, participation, and interest in different topics, which are used to understand students' learning patterns and preferences; the psychometric data includes learning style, cognitive ability, personality traits, and motivation level, which are used to gain an in-depth understanding of students' personalities and learning needs; the interaction data includes interaction with learning content, answering questions, participating in discussions, and completing tests, which are used to evaluate students' understanding in real time and provide immediate feedback; the biometric data includes fingerprints, facial recognition, and voice recognition, which are used to verify students' identities and ensure data security.

[0011] Furthermore, the AI ​​algorithm model is implemented by a multi-layer recursive neural network, which includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, an attention mechanism layer, a dynamic personalized feedback layer and an output layer; wherein the input layer is used to preprocess the input student-related data to obtain a preprocessed feature vector, wherein the preprocessing includes normalization, encoding, filling missing values ​​and data formatting; the first hidden layer is implemented by a long short-term memory unit, which is used to process the preprocessed feature vector to obtain time series characteristics that reflect students' learning patterns and behaviors; the second hidden layer is implemented by a gated recurrent unit, which is used to process the time series characteristics output by the first hidden layer to obtain comprehensive feature data that reflect learning behaviors and psychological states; the third hidden layer is implemented by a bidirectional long The short-term memory unit is implemented to process the comprehensive feature data output by the second hidden layer to obtain bidirectional feature data reflecting the student interaction and academic characteristics; the attention mechanism layer adopts the attention mechanism to perform weighted processing on the bidirectional feature data provided by the third hidden layer to obtain weighted key feature data; the dynamic personalized feedback layer is implemented by a reinforcement learning algorithm to obtain optimized personalized learning content features based on the weighted key feature data provided by the attention mechanism layer and the instant feedback and behavior of the students during the learning process; the output layer is implemented by a fully connected layer to generate personalized learning content based on the optimized personalized learning content features provided by the dynamic personalized feedback layer, and the personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools.

[0012] Furthermore, the dynamic personalized feedback layer is implemented using a Q-learning algorithm, and the execution steps of the Q-learning algorithm include:

[0013] The weighted key feature data provided by the attention mechanism layer is used as the current state S t ;

[0014] According to the current state S t , select a set of potential personalized learning content features A through the ε-greedy strategy t ;

[0015] According to the correct answer rate C of the students t , Study time T t 、Interaction Frequency I t , according to the following formula 1, calculate the reward value R t :-

[0016]

[0017] Among them, a 1 、a 2 、a3 and α 4 is the weight coefficient; β 1 , β 2 To adjust the parameters;

[0018] According to the following formula 2, the new state S is obtained t+1 :

[0019] S t+1 =tanh(W s ·S t +W a ·A t +W c ·C t +W t ·T t +W i I t +b) (2)

[0020] Among them, W s , W a , W c , W t , W i is the weight matrix; b is the bias term; tanh is the activation function;

[0021] According to the following formula 3, according to the Q-learning algorithm, for the action value function Q(S t ,A t ) is updated to obtain the updated action value function Q′(S t ,A t ):

[0022]

[0023] Among them, α is the learning rate; γ is the discount factor; a′ is all possible actions for the next state;

[0024] Using the updated action value function Q′(S t ,A t )Generate optimized personalized learning content features.

[0025] Furthermore, the communication module includes a Wi-Fi, a Bluetooth module and a 4G / 5G module to achieve multiple connection modes.

[0026] Furthermore, the remote server includes a database for storing student-related data and AI algorithm models of multiple students.

[0027] Furthermore, the remote server has an automatic backup function to ensure the security and integrity of student data.

[0028] Furthermore, the teacher client includes a personalized dynamic monitoring interface for real-time display of students' learning status, emotion analysis and attention concentration. The personalized dynamic monitoring interface specifically includes:

[0029] Real-time emotion monitoring panel, which uses AI algorithms to analyze students' expressions and voices during the learning process, displays students' emotional states in real time, and sends reminders to teachers when students' emotions are abnormal;

[0030] Attention tracking charts, which generate dynamic charts of students’ attention based on their interactive behaviors and learning time, helping teachers identify moments when students’ attention is distracted during learning;

[0031] The learning status warning module is used to automatically generate warning notifications based on students' learning progress and performance, helping teachers to intervene and guide students in a timely manner.

[0032] Furthermore, the teacher client includes an intelligent feedback and interactive interface for instant communication and feedback between teachers and students. The intelligent feedback and interactive interface specifically includes:

[0033] Intelligent feedback module, which is used to automatically generate personalized feedback suggestions based on students' learning data and behavior analysis. Teachers can send these suggestions directly to students or edit them before sending them;

[0034] Real-time interactive tools, including instant messaging, video calling and collaborative whiteboards, allow teachers to interact with students in real time to answer questions, provide guidance and personalize instruction;

[0035] Feedback history records are used to save all teacher-student interactions and feedback records for teachers to review and evaluate students' progress at any time.

[0036] Furthermore, the teacher client includes a custom learning content generation and management interface, and the custom learning content generation and management interface specifically includes:

[0037] A custom content builder that allows teachers to create and edit learning content including text, images, videos, and interactive exercises through a drag-and-drop interface;

[0038] Personalized content recommendation engine, which is used to automatically recommend learning content suitable for students based on their learning data and interest preferences, which teachers can select and assign to students;

[0039] The content management panel provides search, classification and tagging functions to facilitate teachers to manage and retrieve customized learning content and track the use and effectiveness of content.

[0040] The beneficial effects of this application mainly include: (1) Through the AI ​​algorithm model in the electronic student card, the system can generate personalized learning content based on the individual data of students, including customized course plans, adaptive assessments, real-time feedback and collaborative learning tools. This personalized learning experience can meet the learning needs and learning speed of different students and improve learning effects. (2) The communication module of the electronic student card supports two-way data communication with the remote server and other electronic student cards to achieve real-time synchronization and update of data. The remote server can centrally store the students' learning data and continuously train and update the AI ​​algorithm model based on the latest data to ensure that the system always provides the highest quality personalized learning content. (3) The teacher client communicates with the remote server, and the teacher can monitor the students' learning progress, provide personalized feedback, adjust the learning content and experience, and access detailed learning records and analysis reports in real time through the client. This comprehensive monitoring and guidance function helps teachers manage and support students' learning process more effectively. (4) The AI ​​algorithm model can dynamically adjust the learning content according to the students' learning progress and performance, so that the learning plan and assessment can adapt to the students' current needs in real time, avoid the learning content being too difficult or too easy, and ensure that students can learn at an appropriate difficulty level. (5) Personalized learning content includes collaborative learning tools to promote interaction and collaborative learning among students, and enhance learning enthusiasm and teamwork ability. (6) By centrally storing and analyzing large amounts of student data on remote servers, the system can provide data support for educational decision-making, help schools and teachers optimize teaching strategies and resource allocation, and improve the quality of education. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a schematic diagram of a personalized education experience AI-enabled student card system provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0042] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0043] The first embodiment of the present application provides a personalized education experience AI-enabled student card system. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 The first embodiment of the present application provides a personalized education experience AI-enabled student card system for a detailed description.

[0044] The personalized education experience AI-enabled student card system includes an electronic student card 101, a remote server 102 and a teacher client 103.

[0045] The electronic student card 101 comprises a display screen, a communication module, a memory and a processor; wherein the display screen is used to display learning-related information; the memory is used to store student-related data of the card-holding student; the processor communicates with the display screen and the memory, and is used to retrieve the student-related data from the memory; based on the retrieved student-related data, personalized learning content is generated using an AI algorithm model pre-trained and stored in the memory; the generated personalized learning content is displayed on the display screen; the communication module is used to perform two-way data communication with other electronic student cards of a remote server; wherein the personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools.

[0046] The electronic student card 101 is one of the core components, which is designed to provide a personalized learning experience. The student card includes a display screen, a communication module, a memory and a processor, and each part works closely together to achieve intelligent and personalized learning functions.

[0047] The display is an important part of the electronic student card 101, which is used to display learning-related information. This information includes but is not limited to personalized learning content, real-time feedback, course plans, and collaborative learning tools. The display adopts a touch screen design, allowing students to interact with the displayed content through gestures such as clicking and sliding, thereby improving learning participation and interactivity. The high-resolution display ensures that the learning content is clearly visible, improving the visual effect and user experience.

[0048] The communication module is the key to achieve data transmission and remote interaction. The module supports multiple communication methods, including Wi-Fi and Bluetooth, to ensure that the electronic student card 101 can communicate with the remote server 102 and other electronic student cards in a two-way manner. The design of the communication module ensures the stability and security of data transmission, and protects the privacy and security of student data through encryption protocols. In addition, the communication module has an automatic reconnection function, which can automatically re-establish the connection when the network connection is interrupted to ensure that the learning process is not interrupted.

[0049] The memory is used to store relevant data of cardholders, including personal information, learning records, course progress, evaluation results, etc. The memory also stores pre-trained AI algorithm models, which are used to generate personalized learning content. To ensure the security and integrity of data, the memory uses efficient flash memory technology and is designed with a data backup and recovery mechanism to prevent data loss and damage.

[0050] The processor is the computing core of the electronic student card 101, responsible for executing the AI ​​algorithm model and generating personalized learning content. The processor retrieves student-related data from the memory and runs the pre-trained AI algorithm model based on this data. The processor adopts a multi-core design and has powerful computing power. It can quickly process large amounts of data, generate personalized learning content, and display it on the display. The processor communicates directly with the display and memory to ensure the efficiency and real-time performance of data processing and display.

[0051] The personalized learning content generated by the electronic student card 101 includes customized lesson plans, adaptive assessments, real-time feedback, and collaborative learning tools. Customized lesson plans are generated based on students' learning progress and interests, ensuring that each student can obtain learning content that suits them. The adaptive assessment function dynamically adjusts the assessment content and difficulty based on the student's learning performance, provides instant feedback, and helps students identify and improve their weaknesses in learning. Collaborative learning tools support interaction and collaboration between students, promoting team learning and knowledge sharing.

[0052] Through the communication module, the electronic student card 101 can perform two-way data communication with the remote server 102. The remote server 102 centrally stores the data of multiple students, is responsible for training and updating the AI ​​algorithm model, and sends the latest version of the model to the memory of the electronic student card. In this way, the electronic student card 101 always uses the latest AI algorithm model to ensure the quality and accuracy of personalized learning content.

[0053] In addition, the electronic student card 101 works in conjunction with the teacher client 103. The teacher client 103 allows teachers to monitor students' learning progress, provide personalized feedback, adjust learning content and experience, and access students' learning records and analysis reports. In this way, teachers can more effectively manage and support students' learning process.

[0054] In summary, the electronic student card 101 provides a personalized, dynamic and interactive learning experience through the close collaboration of display screen, communication module, memory and processor. Its design not only takes into account technical performance, but also focuses on user experience and data security, providing students and teachers with an efficient and intelligent educational tool.

[0055] Furthermore, the student-related data includes basic student information, extended student information, academic data, learning behavior data, psychometric data, interaction data and biometric data, wherein the basic student information includes the student's name, age, grade and gender, which is used to obtain a preliminary understanding of the student's background; the extended student information includes attendance records, health status, and participation in extracurricular activities, which is used to fully understand the student's overall situation; the academic data includes courses, grades, test scores, homework completion, and learning progress, which are used to evaluate students' academic performance and ability levels; the learning behavior data includes study time, study habits, preferred learning methods, participation, and interest in different topics, which are used to understand students' learning patterns and preferences; the psychometric data includes learning style, cognitive ability, personality traits, and motivation level, which are used to gain an in-depth understanding of students' personalities and learning needs; the interaction data includes interaction with learning content, answering questions, participating in discussions, and completing tests, which are used to evaluate students' understanding in real time and provide immediate feedback; the biometric data includes fingerprints, facial recognition, and voice recognition, which are used to verify students' identities and ensure data security.

[0056] In the personalized education experience AI-enabled student card system, student-related data covers multiple types of information to ensure a comprehensive understanding of students and personalized educational support. Student basic information is the most basic data, including the student's name, age, grade, and gender, which is used to initially understand the student's background and basic situation. With this basic information, the system can perform basic classification of students, such as grouping by grade, and take into account age and gender differences when generating personalized learning content.

[0057] Student extended information provides more comprehensive background information, covering attendance records, health status, and participation in extracurricular activities. Attendance records help teachers and systems understand students' attendance rates and attendance patterns, which is crucial for assessing students' learning attitudes and engagement. Health status data includes students' physical health information, such as past medical history and current health problems, which requires special consideration when arranging learning tasks and activities to ensure students' physical and mental health. Participation in extracurricular activities reflects students' interests and strengths outside of school, helping the system to comprehensively consider students' all-round development when formulating learning plans.

[0058] Academic data is the core data for evaluating students' academic performance and ability level, including courses, grades, test scores, homework completion and learning progress. These data record students' learning in various subjects in detail. By analyzing these data, the system can find students' strong subjects and weak links, so as to provide them with targeted learning content and assessment plans. Grades and test scores provide quantitative academic performance indicators, while homework completion and learning progress reflect students' learning habits and self-management abilities.

[0059] Learning behavior data further reveals students’ learning patterns and preferences. This data includes study time, study habits, preferred learning methods, engagement, and interest in different topics. By analyzing study time, we can understand students’ time management ability and learning rhythm. Study habits and preferences reflect students’ personalized choices in learning, such as whether they prefer to learn through videos or text. Engagement is an important indicator of student motivation, while interest in different topics helps the system recommend learning content suitable for students and stimulate their learning motivation.

[0060] Psychometric data provides deep insights into students’ personalities and learning needs. This data includes learning styles, cognitive abilities, personality traits, and motivation levels. Learning styles describe students’ preferences in the learning process, such as visual, auditory, or kinesthetic. Cognitive ability measures include information about students’ memory, comprehension, and thinking abilities. Personality traits involve students’ personalities, such as introversion or extroversion, and motivation levels reflect students’ motivation and self-drive. This data is important for developing personalized learning plans and motivating students.

[0061] Interaction data records the interaction between students and learning content, including answering questions, participating in discussions, and completing tests. This data evaluates students' understanding of learning content in real time and provides immediate feedback to help students correct mistakes and consolidate knowledge points in a timely manner. By analyzing these interaction data, the system can dynamically adjust the difficulty and progress of learning content to improve the effectiveness of learning.

[0062] Biometric data, including fingerprints, facial recognition, and voice recognition, are used to verify students’ identities and ensure data security. These data are collected and processed through advanced biometric technology to ensure the uniqueness of student identities and the security of data access. Biometric technology not only improves the security of the system, but also simplifies the student login and verification process, improving the user experience.

[0063] In summary, the personalized education experience AI-enabled student card system provides a comprehensive and personalized education support system through detailed and comprehensive student-related data. The refined collection and analysis of various types of data ensures that the system can deeply understand the personalized needs of each student, thereby providing the most suitable learning content and support, greatly improving the education effect and students' learning experience.

[0064] Furthermore, the communication module includes a Wi-Fi, a Bluetooth module and a 4G / 5G module to achieve multiple connection modes.

[0065] In the personalized education experience AI-enabled student card system, the design of the communication module is particularly important. The communication module includes Wi-Fi, Bluetooth module and 4G / 5G module to achieve multiple connection methods and ensure that the student card can smoothly transmit and communicate data in various environments.

[0066] First of all, the Wi-Fi module is an important part of the communication module. It allows the student card to connect to the wireless LAN of the school, home or other places for high-speed data transmission. The Wi-Fi module supports common Wi-Fi protocols such as 802.11a / b / g / n / ac, ensuring compatibility and connection stability. Through the Wi-Fi connection, the student card can access online learning resources, synchronize learning progress, download updates and communicate with teachers in real time. The design of the Wi-Fi module also takes into account power consumption optimization, ensuring that the energy consumption of the device is not significantly increased while providing high-speed connection.

[0067] The Bluetooth module provides short-range wireless communication, suitable for fast, low-power connections with other devices. Through Bluetooth, the student card can be connected to peripherals such as headphones and keyboards to enhance the learning experience. In addition, the Bluetooth module also supports direct communication with other student cards, enabling close-range collaborative learning and data sharing. The Bluetooth module is compatible with Bluetooth 4.0 and above, and supports BLE (Bluetooth Low Energy) mode, further reducing energy consumption and extending device battery life.

[0068] The 4G / 5G module provides wide area network connectivity, allowing the student card to remain connected in areas without Wi-Fi coverage. The 4G / 5G module supports high-speed mobile network connections, ensuring that students can continue to learn and access online resources outdoors, on public transportation, and other scenarios. The 4G / 5G module is designed to comply with LTE and NR standards, supports multi-band and multi-mode operations, and ensures compatibility and connection quality in various network environments. Through the 4G / 5G network, the student card can make video calls, live online courses, and interact in real time, further enhancing the flexibility and continuity of learning.

[0069] The multiple connection modes of the communication module not only improve the flexibility of the student card, but also ensure the stability and reliability of data transmission. No matter where the students are, they can access learning resources, communicate with teachers and classmates, and synchronize their learning progress through appropriate connection methods. This diverse connection mode design enables the student card to adapt to various usage scenarios, thereby providing a continuous and seamless learning experience.

[0070] To ensure efficient operation of the communication module, an intelligent connection management system is also integrated into the device. This system can automatically switch to the optimal connection mode according to the current network environment and signal strength. For example, when the Wi-Fi signal is weak, the system will automatically switch to the 4G / 5G network, and vice versa. Bluetooth connection is enabled when short-range communication with peripherals or other student cards is required. This intelligent management mechanism not only improves the stability and reliability of the connection, but also optimizes the power consumption of the device, ensuring seamless switching between different connection methods.

[0071] In summary, the communication module integrates Wi-Fi, Bluetooth and 4G / 5G modules to achieve multiple connection methods, providing efficient and reliable communication capabilities for student cards. This design ensures that students can study and communicate smoothly in various environments, greatly improving the practicality and user experience of the personalized education experience AI-enabled student card system.

[0072] The remote server 102 communicates with the communication module and is used to centrally store student-related data of multiple students; train and update the AI ​​algorithm model, and send the latest version of the AI ​​algorithm model to the memory of the electronic student card.

[0073] The remote server 102 plays a key role in the personalized education experience AI-enabled student card system. It is responsible for centrally storing the data of multiple students, training and updating the AI ​​algorithm model, and sending the latest version of the AI ​​algorithm model to the memory of the electronic student card. First of all, the remote server 102 has a strong storage capacity and can safely store a large amount of students' personal data, including basic information, learning progress, evaluation results, and interaction records. These data are uploaded from the electronic student card 101 through the communication module and stored in the server's database. The remote server 102 is equipped with a high-performance processor and sufficient storage space to ensure the efficiency and reliability of data processing and storage. The server is also designed with an automatic backup and data recovery mechanism to prevent data loss and damage and ensure the security and integrity of the data.

[0074] Another core function of the remote server 102 is to train and update the AI ​​algorithm model. The server continuously optimizes and improves the AI ​​algorithm model by collecting and analyzing a large amount of student learning data. These models include but are not limited to natural language processing, adaptive learning, and sentiment analysis, and are designed to generate personalized learning content based on students' individual needs and learning behaviors. Training AI models requires powerful computing power, and the server is equipped with high-performance computing units such as GPUs or TPUs to accelerate the model training process. At the same time, the server adopts a distributed computing architecture that can process large amounts of data and model training tasks in parallel to improve efficiency and accuracy.

[0075] After the model training is completed, the remote server 102 will send the latest version of the AI ​​algorithm model to the memory of the electronic student card. The server ensures the security and integrity of the model transmission through a secure communication protocol. After the electronic student card 101 receives the updated model, it can immediately apply the new algorithm to generate personalized learning content, thereby improving the learning effect and experience. The remote server 102 also communicates with the teacher client 103, allowing teachers to monitor students' learning progress in real time, provide personalized feedback, adjust learning content and experience, and access students' learning records and analysis reports. Teachers can see detailed student data analysis through the client, including learning trends, knowledge mastery, and emotional changes, etc., which are processed and provided by the remote server 102. In this way, teachers can manage and support students' learning process more effectively.

[0076] In addition, the design of the remote server 102 fully considers the scalability and maintainability of the system. The server software and hardware structure adopts a modular design to facilitate subsequent upgrades and maintenance. System administrators can add storage space or computing units as needed to ensure that the server always meets the needs of system operation. The remote server 102 also supports regular updates and maintenance to ensure the stability and security of the system. The server's operating system and application software are regularly updated, and patches and security policies are applied in a timely manner to prevent potential security threats and vulnerabilities.

[0077] In summary, the remote server 102 plays a vital role in the personalized educational experience AI-enabled student card system of the present invention. It not only stores and processes a large amount of student data, but is also responsible for training and updating the AI ​​algorithm model, and provides personalized learning content and comprehensive learning support through communication with the electronic student card 101 and the teacher client 103. Through efficient storage and computing power, secure and reliable data transmission mechanism, and strong scalability and maintainability, the remote server 102 provides a solid guarantee for the overall function and performance of the system.

[0078] Furthermore, the remote server has an automatic backup function to ensure the security and integrity of student data.

[0079] In the personalized education experience AI-enabled student card system according to claim 1, the design of the remote server takes into account the importance of data security and integrity, especially its automatic backup function. This function ensures that student data can be safely stored and restored in a timely manner under various circumstances, thereby preventing data loss and maintaining data integrity.

[0080] The automatic backup function includes scheduled backup and real-time backup. Scheduled backup means that the remote server will automatically back up student data to a secure storage medium or remote backup server within a preset time interval. This time interval can be set according to the needs of the system and the importance of the data, such as every day, every hour, or every minute. Through scheduled backup, even if the system fails, it can be restored to the most recent backup state, thereby minimizing data loss.

[0081] Real-time backup is to back up data immediately when it changes, ensuring that each data update can be saved to the backup medium in real time. This method can provide higher security and data integrity, especially in high-frequency data modification scenarios, such as real-time learning records, test score updates, etc. Real-time backup captures data changes and quickly synchronizes them to the backup system to ensure the immediacy and accuracy of data.

[0082] In order to realize the automatic backup function, the remote server is equipped with special backup software and hardware facilities. The backup software is responsible for monitoring data changes, executing backup tasks and managing backup files. It can intelligently identify the data blocks that need to be backed up, avoid repeated backup of unchanged data, and thus improve backup efficiency. The backup hardware facilities include high-performance storage devices and backup servers. These devices have large capacity, high-speed storage and fast read and write capabilities, which can meet the needs of large-scale data backup.

[0083] During the data backup process, the server adopts multi-level security measures to ensure the security of the backup data. All backup data is encrypted during transmission and storage to prevent unauthorized access and data leakage. The backup system also implements strict access control, and only authorized personnel and applications can access and manage backup data. In addition, the backup log recording function can record each backup operation in detail, including backup time, data volume, and operator information, for easy auditing and troubleshooting.

[0084] In terms of data recovery, the automatic backup function of the remote server also plays an important role. When the system fails or the data is damaged, the administrator can easily select the backup version to be restored through the backup management interface and restore the data to the original location. The data recovery process is fast and efficient, and the normal operation of the system can be restored in the shortest time, ensuring that students' learning activities are not affected.

[0085] In addition, to further improve the reliability of the backup system, the remote server also adopts a multi-copy backup strategy. That is, each time the data is backed up, multiple copies are generated and stored in different physical locations. This method can prevent the risk of data loss caused by a single point of failure. For example, one copy of the backup data can be stored on the local server and another copy in the remote data center. With multi-copy storage, even if a storage device fails, the data can still be restored from other copies.

[0086] In general, the automatic backup function of the remote server ensures the security and integrity of student data by combining scheduled backup and real-time backup. Its efficient backup software and hardware facilities, multi-level security measures, detailed log records and multi-copy backup strategies constitute a comprehensive and reliable data protection system. This design not only ensures the security and recoverability of data, but also ensures the continuity and stability of the system.

[0087] Furthermore, the remote server includes a database for storing student-related data and AI algorithm models of multiple students.

[0088] In the personalized education experience AI-enabled student card system, the remote server plays a vital role, especially the database part it includes. This database is specifically used to store student-related data and AI algorithm models of multiple students, thereby supporting various functions of the system.

[0089] First, the database stores student-related data, which covers basic information, academic data, learning behavior data, psychometric data, interaction data, and biometric data. Basic information includes the student's name, age, grade, and gender, which is used to identify the student and gain a preliminary understanding of the student's background. Academic data covers courses, grades, test scores, homework completion, and learning progress, which are used to evaluate students' academic performance and ability levels. Learning behavior data records students' study time, study habits, preferred learning methods, participation, and interest in different topics, helping the system understand students' learning patterns and preferences. Psychometric data includes learning style, cognitive ability, personality traits, and motivation level, which are used to gain a deep understanding of students' personalities and learning needs. Interaction data records students' interactions with learning content, such as answering questions, participating in discussions, and completing quizzes, which are used to assess students' understanding in real time and provide immediate feedback. Biometric data includes fingerprints, facial recognition, and voice recognition, which are used to verify students' identities and ensure data security.

[0090] Secondly, the database also stores AI algorithm models. Each model is trained based on the individual needs and learning behaviors of students. These AI algorithm models are pre-trained and continuously updated to generate personalized learning content. Through the remote server, the latest version of the AI ​​algorithm model is regularly sent to the memory of the electronic student card to ensure that the student card uses the most advanced and appropriate model. These models not only include natural language processing, adaptive learning, and sentiment analysis, but also contain optimization algorithms for students' real-time feedback and behavior to ensure that students get the best personalized learning experience.

[0091] The database of the remote server uses an efficient storage and retrieval mechanism to ensure fast access and processing of data. Data is stored in a relational database or a non-relational database, and the most appropriate storage method is selected according to the type of data and access requirements. Relational databases are suitable for storing structured data, such as students' basic information and academic data, while non-relational databases are suitable for storing more complex and dynamic data, such as learning behavior data and interaction data. Through these mechanisms, the database can efficiently manage a large amount of student data and support complex query and analysis operations.

[0092] To ensure data security and privacy, the database implements multi-level security measures, including data encryption, access control, and logging. Data is encrypted during storage and transmission to prevent unauthorized access and data leakage. Access control mechanisms ensure that only authorized users and system components can access and operate data in the database. The logging function records all data access and modification operations in detail to facilitate security audits and problem tracking.

[0093] The database is also designed with scalability and high availability in mind. Through a distributed database architecture, the database can scale horizontally to handle growing data volumes and access requirements. High availability design ensures that the database can still provide uninterrupted services in the event of hardware failures or network outages. Through master-slave replication, data backup, and failover mechanisms, the database system has strong fault tolerance and recovery capabilities.

[0094] In summary, the database of the remote server plays a core role in the personalized education experience AI-enabled student card system. It not only stores and manages a large amount of student data and AI algorithm models, but also ensures that the system can provide efficient, reliable and secure services through efficient storage and retrieval mechanisms, strict security measures, strong scalability and high availability design.

[0095] Furthermore, the AI ​​algorithm model is implemented by a multi-layer recursive neural network, which includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, an attention mechanism layer, a dynamic personalized feedback layer and an output layer; wherein the input layer is used to preprocess the input student-related data to obtain a preprocessed feature vector, wherein the preprocessing includes normalization, encoding, filling missing values ​​and data formatting; the first hidden layer is implemented by a long short-term memory unit, which is used to process the preprocessed feature vector to obtain time series characteristics that reflect students' learning patterns and behaviors; the second hidden layer is implemented by a gated recurrent unit, which is used to process the time series characteristics output by the first hidden layer to obtain comprehensive feature data that reflect learning behaviors and psychological states; the third hidden layer is implemented by a bidirectional long The short-term memory unit is implemented to process the comprehensive feature data output by the second hidden layer to obtain bidirectional feature data reflecting the student interaction and academic characteristics; the attention mechanism layer adopts the attention mechanism to perform weighted processing on the bidirectional feature data provided by the third hidden layer to obtain weighted key feature data; the dynamic personalized feedback layer is implemented by a reinforcement learning algorithm to obtain optimized personalized learning content features based on the weighted key feature data provided by the attention mechanism layer and the instant feedback and behavior of the students during the learning process; the output layer is implemented by a fully connected layer to generate personalized learning content based on the optimized personalized learning content features provided by the dynamic personalized feedback layer, and the personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools.

[0096] In the personalized education experience AI-enabled student card system, the AI ​​algorithm model is implemented using a multi-layer recursive neural network (RNN). This multi-layer recursive neural network includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, an attention mechanism layer, a dynamic personalized feedback layer, and an output layer. Each layer works together to process and analyze relevant data of students and generate personalized learning content.

[0097] The input layer is responsible for receiving and preprocessing student-related data, including basic information, learning behavior data, academic data, etc. The preprocessing steps include data normalization, encoding, filling missing values, and data formatting to ensure that all input data has a unified format and range. Through preprocessing, the input layer generates a normalized feature vector, which provides a basis for subsequent neural network processing.

[0098] The first hidden layer is implemented using long short-term memory (LSTM) units. LSTM units are able to process time series data and effectively capture and memorize the long-term dependencies of students’ learning patterns and behaviors through their unique gating mechanism. Specifically, the first hidden layer receives the preprocessed feature vectors and processes these features using LSTM units to generate time series features that reflect students’ learning behaviors and patterns. The input gate, forget gate, and output gate of the LSTM unit work together to selectively retain or forget specific information, thereby maintaining the long-term dependencies and sequence relationships of the data.

[0099] The second hidden layer uses a gated recurrent unit (GRU) to process the time series features of the first hidden layer output. GRU units are simpler than LSTM units, but are equally efficient in processing time series data. The second hidden layer further processes the input features through GRU units to generate feature data that comprehensively reflects learning behavior and psychological state. The reset gate and update gate of GRU selectively update or reset the unit state at each time step, ensuring that the model can flexibly capture students' learning behavior patterns and psychological changes.

[0100] The third hidden layer is implemented with a bidirectional long short-term memory unit (BiLSTM) to process the comprehensive feature data output by the second hidden layer. Bidirectional LSTM processes the input sequence in both the forward and backward directions to generate bidirectional feature data. This bidirectional processing method allows the model to consider the relationship between the sequence and the past and present at the same time, thereby more comprehensively understanding the students' interactive behavior and academic characteristics. By combining the forward and backward outputs, the third hidden layer is able to generate feature representations that contain richer information.

[0101] The attention mechanism layer performs weighted processing on the bidirectional feature data provided by the third hidden layer. The attention mechanism generates weighted key feature data by calculating the attention weights for each time step, highlighting important features and ignoring unimportant information. The weighted processing of the attention mechanism layer can improve the performance of the model, making it pay more attention to features that are critical to the generation of personalized learning content.

[0102] The dynamic personalized feedback layer uses a reinforcement learning algorithm to generate optimized personalized learning content features based on the weighted key feature data provided by the attention mechanism layer and the students' immediate feedback and behavior during the learning process. The reinforcement learning algorithm optimizes the learning strategy through continuous experimentation and adjustment to maximize long-term rewards. The design of this layer enables the system to dynamically adjust the learning content based on the students' real-time feedback to improve the learning effect.

[0103] The output layer uses a fully connected layer to achieve the final generation of personalized learning content. The fully connected layer receives the optimized features provided by the dynamic personalized feedback layer to generate specific personalized learning content. These contents include customized course plans, adaptive assessments, real-time feedback, and collaborative learning tools. The fully connected layer adjusts weights and biases, integrates the feature data of the previous layers, and generates learning content suitable for each student to ensure personalization and adaptability.

[0104] In summary, the present invention effectively processes and analyzes student-related data through the collaborative work of multiple layers of recursive neural networks to generate highly personalized learning content. The design and function of each layer are clear, ensuring that the system can provide efficient and intelligent educational support.

[0105] Furthermore, the dynamic personalized feedback layer is implemented using a Q-learning algorithm, and the execution steps of the Q-learning algorithm include:

[0106] The weighted key feature data provided by the attention mechanism layer is used as the current state S t ;

[0107] According to the current state S t , select a set of potential personalized learning content features A through the ε-greedy strategy t ;

[0108] According to the correct answer rate C of the students t , Study time T t 、Interaction Frequency I t , according to the following formula 1, calculate the reward value R t :

[0109]

[0110] Among them, α 1 , α 2 , α 3 and α 4 is the weight coefficient; β 1 , β 2 To adjust the parameters;

[0111] According to the following formula 2, the new state S is obtained t+1 :

[0112] S t+1 =tanh(W s ·S t +W a ·A t +W c ·C t +W t ·T t +W i It +b) (2)

[0113] Among them, W s , W a , W c , W t , W i is the weight matrix; b is the bias term; tanh is the activation function;

[0114] According to the following formula 3, according to the Q-learning algorithm, for the action value function Q(S t ,A t ) is updated to obtain the updated action value function Q′(S t ,A t ):

[0115]

[0116] Where a is the learning rate; γ is the discount factor; a′ is all possible actions for the next state;

[0117] Using the updated action value function Q′(S t ,A t )Generate optimized personalized learning content features.

[0118] According to the personalized education experience AI-enabled student card system, its dynamic personalized feedback layer is implemented through the Q-learning algorithm to provide real-time optimization and personalized learning content. The execution steps of the Q-learning algorithm first involve taking the weighted key feature data provided by the attention mechanism layer as the current state S t These feature data are processed by a multi-layer recursive neural network to extract the features most relevant to students' learning situation.

[0119] In determining the current state S t After that, the system adopts the ε-greedy strategy to select a set of potential personalized learning content features A t The strategy strikes a balance between exploration and exploitation by randomly selecting actions with a certain probability ε to ensure that new possibilities are explored, while selecting the current optimal action with a probability of 1-ε. This approach allows the system to continuously optimize its strategy while providing personalized learning content.

[0120] Next, according to the correct answer rate C t , Study time T t and interaction frequency I t , calculate the reward value R t The reward value is calculated as follows:

[0121]

[0122] Among them, α 1 、a 2 、a 3 and a 4 is the weight coefficient, which adjusts the importance of each indicator in the reward value, and β 1 , β 2 is the adjustment parameter that controls the nonlinear impact of each indicator. This formula takes into account the student’s academic performance, learning time, and interaction frequency, so that the reward value can reflect the student’s multi-faceted performance.

[0123] According to the reward value R t , the system updates the state S through the following formula t+1 :

[0124] S t+1 =tanh(W s ·S t +W a ·A t +W c ·C t +W t ·T t +W i I t +b) (2)

[0125] In this formula, W s , W a , W c , W t , W i is the weight matrix, which adjusts the influence of the current state, action, answer accuracy, learning time and interaction frequency on the new state. The bias term b and activation function tanh are used to ensure the nonlinear characteristics and stability of state updates. The weight matrix and bias term are continuously adjusted through the training process to adapt to the learning mode and characteristics of students.

[0126] Then, the system updates the action value function Q(S) according to the Q-learning algorithm by the following formula t ,A t ):

[0127]

[0128] Among them, the learning rate a controls the update step, the discount factor γ adjusts the impact of future rewards on the current decision, and a′ is all possible actions for the next state. This update process enables the system to gradually improve the accuracy of selecting the optimal learning content.

[0129] Finally, using the updated action value function Q′(S t ,A t), the system generates optimized personalized learning content features. These features include customized lesson plans, adaptive assessments, real-time feedback, and collaborative learning tools. Through this systematic feedback and optimization process, students can obtain highly personalized and dynamically adjusted learning content, thereby improving learning outcomes and engagement.

[0130] The following is a reference implementation code of a multi-layer recurrent neural network. This code shows how to build a model including an input layer, an LSTM layer, a GRU layer, a bidirectional LSTM layer, an attention mechanism layer, a dynamic personalized feedback layer, and an output layer, and optimize it using the Q-learning algorithm.

[0131]

[0132]

[0133]

[0134]

[0135]

[0136] Training a multi-layer recursive neural network model to implement a personalized education experience AI-enabled student card system requires a series of detailed steps. These steps include data preprocessing, model building, model training, and applying Q-learning algorithm for optimization.

[0137] First of all, data preprocessing is a key step. Student-related data includes students' basic information, learning behavior data, academic data, etc. These data need to be normalized, encoded, missing values ​​filled, and data formatted to ensure that all input data have a unified format and range. Normalization can scale the data to a standard range, encoding can convert categorical data into numerical form, filling missing values ​​can handle gaps in the data, and data formatting ensures that all data meets the model requirements. After preprocessing, a normalized feature vector is generated to provide a basis for subsequent neural network processing.

[0138] Next, a multi-layer recursive neural network model is constructed. The model consists of multiple layers, including the input layer, the first hidden layer, the second hidden layer, the third hidden layer, the attention mechanism layer, the dynamic personalized feedback layer, and the output layer. The input layer receives the preprocessed feature vector. The first hidden layer uses long short-term memory units (LSTM), which can process time series data and effectively capture and remember the long-term dependencies of students' learning patterns and behaviors. The second hidden layer uses gated recurrent units (GRU), which are concise and efficient and can further process time series features to generate comprehensive feature data reflecting learning behaviors and psychological states. The third hidden layer uses bidirectional long short-term memory units (BiLSTM), which process input sequences in both forward and backward directions to generate bidirectional feature data and fully understand students' interactive behaviors and academic characteristics.

[0139] After these recursive layers, an attention mechanism layer is added. The attention mechanism layer performs weighted processing on the bidirectional feature data provided by the third hidden layer, and generates weighted key feature data by calculating the attention weights for each time step, highlighting important features and ignoring unimportant information. This layer can significantly improve the performance of the model, making it more focused on features that are critical to generating personalized learning content.

[0140] The dynamic personalized feedback layer uses reinforcement learning algorithms, especially Q-learning algorithms, to optimize personalized learning content. First, the weighted key feature data provided by the attention mechanism layer is used as the current state S t According to the current state S t , the system selects a set of potential personalized learning content features A through the ε-greedy strategy t This strategy randomly selects actions with a certain probability ε to ensure that new possibilities are explored, while selecting the current best action with a probability of 1-ε, thus achieving a balance between exploration and exploitation.

[0141] Next, according to the students' correct answer rate C t , Study time T t 、Interaction Frequency I t , calculate the reward value R t The calculation of the reward value takes into account the student's academic performance, learning time and interaction frequency, so that the reward value can comprehensively reflect the student's multi-faceted performance. Then, the system updates the state S t+1 , combined with the current state, action, answer accuracy, learning time and interaction frequency, the stability of state update is ensured through nonlinear activation functions (such as tanh).

[0142] According to the Q-learning algorithm, by updating the action value function Q(S t ,A t ) to obtain the updated action value function Q′(St ,A t ). This process uses the learning rate to control the update step, and the discount factor to adjust the impact of future rewards on current decisions, ensuring that the model gradually improves the accuracy of selecting the optimal learning content.

[0143] Finally, using the updated action value function Q′(S t ,A t ), the system generates optimized personalized learning content features. These features include customized lesson plans, adaptive assessments, real-time feedback, and collaborative learning tools. Through this systematic feedback and optimization process, students can obtain highly personalized and dynamically adjusted learning content, thereby improving learning outcomes and engagement.

[0144] The training process requires repeated iterations and multiple training cycles (epochs) until the model converges or reaches the expected performance. During training, the model performance can be verified regularly and hyperparameters such as learning rate and batch size can be adjusted as needed. The entire training process involves the coordination and repeated optimization of multiple steps to ensure that the final model can effectively provide personalized education support, improve teaching quality and student learning outcomes.

[0145] The teacher client 103 communicates with the remote server to allow the teacher to monitor the student's progress, provide personalized feedback, adjust the student's personalized learning content and experience, and access the student's learning records and analysis reports.

[0146] The teacher client 103 plays a key role in the personalized education experience AI-enabled student card system, which aims to provide an intuitive and powerful platform for teachers to monitor students' learning progress, provide personalized feedback, adjust learning content and experience, and access detailed learning records and analysis reports. First of all, the teacher client 103 is equipped with a user-friendly graphical user interface (GUI), which enables teachers to easily access and manage various functions through a clear layout and intuitive operation. The interface displays key indicators such as students' learning progress, grades, and participation, helping teachers to grasp the learning status of each student in real time.

[0147] In terms of monitoring student progress, the teacher client 103 allows teachers to view students' real-time learning data, which is transmitted through the communication module of the electronic student card 101 and stored in the remote server 102. Teachers can see detailed information such as each student's course completion, test scores, interaction frequency, etc. These data are not only updated in real time, but can also be displayed in chronological order to help teachers understand students' learning progress and trends. The system also provides data visualization tools to present data in charts and graphs, allowing teachers to analyze students' performance more intuitively.

[0148] Providing personalized feedback is an important function of the teacher client 103. Based on the real-time learning data and behavior analysis of students, the system can automatically generate personalized feedback suggestions, which teachers can directly view and edit before sending to students. In addition, teachers can also manually enter feedback to provide detailed guidance and suggestions for students' specific problems. This process not only improves the pertinence and timeliness of feedback, but also helps students identify and improve their learning problems more quickly.

[0149] The teacher client 103 also allows teachers to adjust students' personalized learning content and experience. Through the client, teachers can customize course plans and learning tasks according to students' learning progress and needs. The system provides a rich resource library, and teachers can select suitable teaching materials, exercises and assessment content and assign them to different students. Teachers can also set learning goals and milestones, monitor students' achievement, and adjust learning plans as needed. In addition, the teacher client 103 supports teachers to upload customized learning content, including text, pictures, videos and interactive exercises, etc., to further personalize students' learning experience.

[0150] Accessing students' learning records and analysis reports is another key function of the teacher client 103. The learning reports generated by the system include detailed analysis of students' overall performance, knowledge mastery, and emotional changes. These reports are based on data processed by the remote server 102, and teachers can view and download them at any time through the client. The reports not only help teachers evaluate students' learning effects, but also provide a basis for improving teaching strategies. Teachers can adjust teaching methods and content based on the data analysis in the reports to more effectively support students' learning.

[0151] The teacher client 103 also has real-time interactive functions, supporting tools such as instant messaging, video calls, and collaborative whiteboards. Teachers can use these tools to communicate with students in real time, answer questions, provide guidance, and conduct personalized teaching. The interaction history will be saved for teachers to review and evaluate students' progress at any time. In this way, teachers can achieve an efficient face-to-face teaching experience in a virtual environment.

[0152] In summary, Teacher Client 103 provides teachers with a comprehensive and efficient tool through its intuitive user interface, powerful data analysis and management functions, flexible content adjustment and real-time interactive capabilities to help them better manage and support students' learning process. Through Teacher Client 103, teachers can monitor students' learning progress in real time, provide personalized feedback, adjust learning content and experience, and access detailed learning records and analysis reports, which greatly improves teaching quality and efficiency.

[0153] Furthermore, the teacher client includes a personalized dynamic monitoring interface for real-time display of students' learning status, emotion analysis and attention concentration. The personalized dynamic monitoring interface specifically includes:

[0154] Real-time emotion monitoring panel, which uses AI algorithms to analyze students' expressions and voices during the learning process, displays students' emotional states in real time, and sends reminders to teachers when students' emotions are abnormal;

[0155] Attention tracking charts, which generate dynamic charts of students’ attention based on their interactive behaviors and learning time, helping teachers identify moments when students’ attention is distracted during learning;

[0156] The learning status warning module is used to automatically generate warning notifications based on students' learning progress and performance, helping teachers to intervene and guide students in a timely manner.

[0157] In the personalized education experience AI-enabled student card system, one of the important functions of the teacher client is the personalized dynamic monitoring interface. This interface is designed for teachers to monitor students' learning status, emotion analysis, and attention concentration in real time, so as to provide timely and effective guidance and intervention. The personalized dynamic monitoring interface specifically includes three main modules: real-time emotion monitoring panel, attention tracking chart, and learning status warning module.

[0158] First of all, the real-time emotion monitoring panel is one of the core parts of the personalized dynamic monitoring interface. Through the built-in AI algorithm, the panel can analyze students' expressions and voices during the learning process and display students' emotional state in real time. The AI ​​algorithm captures students' facial expressions and voice intonations through the camera to identify emotional changes, such as happiness, anger, anxiety, etc. These emotional data will be presented instantly on the monitoring interface to help teachers understand students' emotional dynamics. If the system detects abnormal student emotions, such as persistent anxiety or depression, the system will automatically send a reminder to the teacher. This real-time emotion monitoring and reminder function enables teachers to respond quickly when students encounter emotional problems and provide necessary support and comfort.

[0159] Secondly, the attention tracking chart is another important component of the personalized dynamic monitoring interface. The chart generates a dynamic chart of students' concentration based on their interactive behaviors and learning time. By analyzing students' mouse clicks, keyboard input, eye tracking and other behaviors during the learning process, the system is able to determine the students' concentration level. For example, frequent mouse clicks and keyboard inputs may indicate active student participation, while long periods of inactivity may indicate distraction. The chart shows the changes in students' attention in a dynamic way, helping teachers identify moments when students are distracted during the learning process. This feature enables teachers to intervene at the appropriate time to redirect students' attention and ensure learning effectiveness.

[0160] Finally, the learning status warning module is an integral part of the personalized dynamic monitoring interface. This module automatically generates warning notifications based on students’ learning progress and performance. For example, if a student’s progress in a course falls behind expectations, or if they perform poorly in several consecutive quizzes, the system will issue a warning notification to remind teachers to pay attention and intervene. The warning notification includes detailed student performance data and recommended intervention measures, helping teachers to quickly understand the situation and take action. With these warnings, teachers can adjust their teaching strategies in a timely manner, provide personalized help, and prevent students from falling behind.

[0161] The personalized dynamic monitoring interface provides comprehensive student monitoring and management tools by integrating three modules: real-time emotion monitoring, attention tracking, and learning status warning. Through this interface, teachers can grasp the learning dynamics and emotional state of each student in real time, identify and solve problems in a timely manner, and improve teaching efficiency and student learning effects. This design not only improves teachers' ability to control students' learning situation, but also provides strong technical support for personalized teaching.

[0162] Furthermore, the teacher client includes an intelligent feedback and interactive interface for instant communication and feedback between teachers and students. The intelligent feedback and interactive interface specifically includes:

[0163] Intelligent feedback module, which is used to automatically generate personalized feedback suggestions based on students' learning data and behavior analysis. Teachers can send these suggestions directly to students or edit them before sending them;

[0164] Real-time interactive tools, including instant messaging, video calling and collaborative whiteboards, allow teachers to interact with students in real time to answer questions, provide guidance and personalize instruction;

[0165] Feedback history records are used to save all teacher-student interactions and feedback records for teachers to review and evaluate students' progress at any time.

[0166] In the personalized education experience AI-enabled student card system, the teacher client has designed a set of intelligent feedback and interactive interfaces to enhance instant communication and feedback between teachers and students. This intelligent feedback and interactive interface includes multiple functional modules to ensure that teachers can effectively manage students' learning process and provide personalized guidance and support.

[0167] First of all, the intelligent feedback module is the core part of this interface. This module automatically generates personalized feedback suggestions based on students' learning data and behavior analysis. The system generates detailed feedback reports by analyzing students' test scores, homework completion, class participation, and other learning behaviors. These reports not only point out students' strengths and weaknesses, but also provide specific suggestions for improvement. Teachers can send these automatically generated feedback directly to students, or edit them when necessary to better suit the actual teaching situation. This automated and personalized feedback mechanism ensures that every student can receive timely and accurate guidance to promote their learning progress.

[0168] Secondly, real-time interactive tools are another key component of intelligent feedback and interactive interfaces. This tool integrates functions such as instant messaging, video calls, and collaborative whiteboards, allowing teachers to interact with students in real time in various forms. Through instant messaging, teachers can quickly answer students' questions and provide instant learning guidance. The video call function enables teachers to conduct face-to-face virtual teaching and tutoring to enhance the effectiveness of communication. The collaborative whiteboard allows teachers and students to write, draw, and annotate on the virtual whiteboard together, which is suitable for explaining complex concepts and conducting interactive teaching. These real-time interactive tools enable teachers to communicate and teach with students flexibly, improving learning outcomes and participation.

[0169] In addition, the feedback history feature provides teachers with a convenient tool to save all teacher-student interactions and feedback records. Each interaction and feedback will be recorded in detail, including time, content, and participants. These records can be accessed at any time to help teachers track students' learning progress and historical performance. By analyzing these historical records, teachers can better understand students' learning trajectories, evaluate teaching effectiveness, and adjust teaching strategies as needed. Feedback history also provides teachers with a comprehensive reference to ensure that each student's personalized learning needs are continuously paid attention to and met.

[0170] In general, the intelligent feedback and interactive interface provides teachers with a powerful and flexible teaching management platform through three main functional modules: intelligent feedback module, real-time interactive tool and feedback history. Teachers can use this interface to understand students' learning situation in real time, provide personalized guidance and support, and enhance teaching effectiveness through a variety of interactive methods. This design ensures efficient communication and interaction between teachers and students and promotes the implementation of personalized teaching.

[0171] Furthermore, the teacher client includes a custom learning content generation and management interface, and the custom learning content generation and management interface specifically includes:

[0172] A custom content builder that allows teachers to create and edit learning content including text, images, videos, and interactive exercises through a drag-and-drop interface;

[0173] Personalized content recommendation engine, which is used to automatically recommend learning content suitable for students based on their learning data and interest preferences, which teachers can select and assign to students;

[0174] The content management panel provides search, classification and tagging functions to facilitate teachers to manage and retrieve customized learning content and track the use and effectiveness of content.

[0175] In the personalized educational experience AI-enabled student card system, the teacher client includes a custom learning content generation and management interface that is designed to provide teachers with powerful tools to create, recommend, and manage personalized learning content.

[0176] First of all, the custom content builder is one of the core features of this interface. Through an intuitive drag-and-drop interface, teachers can easily create and edit a variety of learning content, including text, pictures, videos, and interactive exercises. This interface design allows teachers to integrate different types of media and exercises into a learning unit through simple drag and drop operations. The text editor supports rich formatting, allowing teachers to insert pictures, links, and other multimedia elements. The video editing tool enables teachers to upload, clip, and annotate teaching videos. The interactive exercise builder allows teachers to create multiple types of quiz questions, including multiple-choice questions, fill-in-the-blank questions, and drag-and-drop questions, thereby enriching students' learning experience.

[0177] Next, the personalized content recommendation engine automatically recommends learning content suitable for each student based on the student's learning data and interest preferences. The system generates a personalized content recommendation list by analyzing the student's historical learning records, current learning progress and personal interests. Teachers can view these recommended contents and select and assign them as needed. The recommendation engine not only improves the relevance and applicability of learning content, but also helps teachers save a lot of time, allowing them to focus more on teaching and student tutoring.

[0178] The content management panel is another important part of the custom learning content generation and management interface. It provides powerful search, classification and labeling functions to facilitate teachers to manage and retrieve custom learning content. Teachers can quickly find the required content through keyword search. The classification function allows teachers to organize content by topic, course or difficulty level. The label function provides a more detailed content tagging and management method. In addition, the content management panel also provides content usage and effect tracking functions. Teachers can view the frequency of use of each learning content, student feedback and learning effect, so as to continuously optimize and adjust the teaching content.

[0179] In general, the custom learning content generation and management interface provides teachers with a comprehensive and flexible toolbox by integrating a custom content generator, a personalized content recommendation engine, and a content management panel. Teachers can easily create and edit high-quality learning content, automatically recommend the most suitable learning materials for students, and efficiently manage and track the use and effectiveness of content. The design of this interface not only improves the personalization and pertinence of teaching content, but also greatly improves the work efficiency of teachers.

[0180] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A personalized education experience AI-enabled student card system, characterized in that: include: An electronic student card comprises a display screen, a communication module, a memory and a processor; wherein the display screen is used to display learning-related information; the memory is used to store student-related data of the card-holding student; the processor communicates with the display screen and the memory, and is used to retrieve the student-related data from the memory; based on the retrieved student-related data, personalized learning content is generated using an AI algorithm model pre-trained and stored in the memory; the generated personalized learning content is displayed on the display screen; the communication module is used to perform two-way data communication with other electronic student cards on a remote server; wherein the personalized learning content includes customized course plans, adaptive assessments, real-time feedback and collaborative learning tools; A remote server, communicating with the communication module, is used to centrally store student-related data of multiple students; train and update the AI ​​algorithm model, and send the latest version of the AI ​​algorithm model to the memory of the electronic student card; A teacher client, communicating with the remote server, for allowing the teacher to monitor the student's progress, provide personalized feedback, adjust the student's personalized learning content and experience, and access the student's learning records and analysis reports; Among them, the AI ​​algorithm model is implemented by a multi-layer recursive neural network, and the multi-layer recursive neural network includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, an attention mechanism layer, a dynamic personalized feedback layer and an output layer; wherein the input layer is used to preprocess the input student-related data to obtain the preprocessed feature vector, wherein the preprocessing includes normalization, encoding, filling missing values ​​and data formatting; the first hidden layer is implemented by a long short-term memory unit, which is used to process the preprocessed feature vector to obtain the time series characteristics that reflect the students' learning patterns and behaviors; the second hidden layer is implemented by a gated recurrent unit, which is used to process the time series characteristics output by the first hidden layer to obtain comprehensive feature data that reflect learning behaviors and psychological states; the third hidden layer adopts a bidirectional long short-term memory unit. The memory unit is implemented to process the comprehensive feature data output by the second hidden layer to obtain bidirectional feature data reflecting the student interaction and academic characteristics; the attention mechanism layer adopts the attention mechanism to perform weighted processing on the bidirectional feature data provided by the third hidden layer to obtain weighted key feature data; the dynamic personalized feedback layer is implemented by a reinforcement learning algorithm to obtain optimized personalized learning content features based on the weighted key feature data provided by the attention mechanism layer and the instant feedback and behavior of the students during the learning process; the output layer is implemented by a fully connected layer to generate personalized learning content based on the optimized personalized learning content features provided by the dynamic personalized feedback layer, and the personalized learning content includes customized course plans, adaptive assessments, real-time feedback, and collaborative learning tools; The dynamic personalized feedback layer is implemented by using a Q-learning algorithm, and the execution steps of the Q-learning algorithm include: The weighted key feature data provided by the attention mechanism layer is used as the current state ; According to the current status ,pass - Greedy strategy selects a set of potential personalized learning content features ; According to the correct answer rate of students , Study time , interaction frequency , according to the following formula 1, calculate the reward value : ； in, , is the weight coefficient; , To adjust the parameters; According to the following formula 2, the new state is obtained : ； in, is the weight matrix; is the bias term; is the activation function; According to the following formula 3, according to the Q-learning algorithm, for the action value function Update and obtain the updated action value function : ； in, is the learning rate; is the discount factor; All possible actions for the next state; Using the updated action-value function Generate optimized personalized learning content features.

2. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The student-related data includes basic student information, extended student information, academic data, learning behavior data, psychometric data, interaction data and biometric data, wherein the basic student information includes the student's name, age, grade and gender, which is used to obtain a preliminary understanding of the student's background; the extended student information includes attendance records, health status, and participation in extracurricular activities, which is used to fully understand the student's overall situation; the academic data includes courses, grades, test scores, homework completion status, and learning progress, which are used to evaluate students' academic performance and ability levels; the learning behavior data includes study time, study habits, preferred learning methods, participation, and interest in different topics, which are used to understand students' learning patterns and preferences; the psychometric data includes learning style, cognitive ability, personality traits, and motivation level, which are used to gain an in-depth understanding of students' personalities and learning needs; the interaction data includes interaction with learning content, answering questions, participating in discussions, and completing tests, which are used to evaluate students' understanding in real time and provide immediate feedback; the biometric data includes fingerprints, facial recognition, and voice recognition, which are used to verify students' identities and ensure data security.

3. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The communication module includes Wi-Fi, Bluetooth module and 4G / 5G module to achieve multiple connection modes.

4. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The remote server includes a database for storing student-related data and AI algorithm models of multiple students.

5. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The remote server has an automatic backup function to ensure the security and integrity of student data.

6. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The teacher client includes a personalized dynamic monitoring interface for real-time display of students' learning status, emotional analysis and attention concentration. The personalized dynamic monitoring interface specifically includes: Real-time emotion monitoring panel, which uses AI algorithms to analyze students' expressions and voices during the learning process, displays students' emotional states in real time, and sends reminders to teachers when students' emotions are abnormal; Attention tracking charts, which generate dynamic charts of students’ attention based on their interactive behaviors and learning time, helping teachers identify moments when students’ attention is distracted during learning; The learning status warning module is used to automatically generate warning notifications based on students' learning progress and performance, helping teachers to intervene and guide students in a timely manner.

7. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The teacher client includes an intelligent feedback and interactive interface for instant communication and feedback between teachers and students. The intelligent feedback and interactive interface specifically includes: Intelligent feedback module, which is used to automatically generate personalized feedback suggestions based on students' learning data and behavior analysis. Teachers can send feedback suggestions directly to students or edit them before sending them; Real-time interactive tools, including instant messaging, video calling and collaborative whiteboards, allow teachers to interact with students in real time to answer questions, provide guidance and personalize instruction; Feedback history records are used to save all teacher-student interactions and feedback records for teachers to review and evaluate students' progress.

8. The personalized education experience AI-enabled student card system according to claim 1, characterized in that: The teacher client includes a custom learning content generation and management interface, and the custom learning content generation and management interface specifically includes: A custom content builder that allows teachers to create and edit learning content including text, images, videos, and interactive exercises through a drag-and-drop interface; Personalized content recommendation engine, which is used to automatically recommend learning content suitable for students based on their learning data and interest preferences, which teachers can select and assign to students; The content management panel provides search, classification and tagging functions to facilitate teachers to manage and retrieve customized learning content and track the use and effectiveness of content.

Images