Dynamic Personalized Knowledge Graph Generation via Prompt Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing personalized knowledge graphs are static and fail to dynamically adjust to the changing learning needs and interests of students, limiting their effectiveness in providing personalized education.
Innovation Solution
A method for dynamically generating a personalized knowledge graph based on prompt learning, which involves constructing a prompt word library with difficulty and learning target prompt words, evaluating student learning ability, and using a knowledge point linking method to generate a dynamic knowledge graph.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a traditional static personalized knowledge graph is constructed based on student learning behavior and feedback, then personalized learning paths can be provided, but the learning paths cannot be dynamically adjusted to meet changing student needs
Solution Approach 1:
The patent applies the dynamics principle by transforming the static knowledge graph into a dynamic structure that can be continuously updated and reconfigured. The system generates learning paths based on real-time student performance data, allowing the knowledge graph to adapt and evolve as student needs change, thereby achieving dynamic adjustability without requiring complete system redesign
Solution Approach 2:
The patent utilizes parameter changes by adjusting key parameters such as learning difficulty level, knowledge point selection, and learning path routing based on student performance metrics. The system dynamically modifies these parameters to optimize learning paths while maintaining manageable system complexity through automated parameter adjustment mechanisms
2Reliability
If the knowledge graph is highly personalized to meet individual student needs, then learning effectiveness is improved, but the system complexity and computational requirements increase
Solution Approach 1:
The patent applies segmentation by dividing the knowledge graph into modular knowledge points and skill categories that can be independently evaluated and combined. This allows the system to generate personalized learning paths by selectively combining predefined modules rather than constructing entirely new paths, reducing system complexity while maintaining high personalization accuracy
Solution Approach 2:
The patent utilizes feedback mechanisms where student performance data continuously informs the knowledge graph generation process. The system incorporates feedback loops that adjust learning path recommendations based on real-time student responses, thereby improving personalization accuracy through data-driven iteration while managing complexity through automated feedback processing
3Ease of operation
If learning paths are made flexible and adjustable to student preferences, then student autonomy is enhanced, but the difficulty of managing and monitoring learning progress increases
Solution Approach 1:
The patent applies self-service by enabling students to independently select learning paths and knowledge points based on their interests and goals. The system provides students with autonomy to navigate the knowledge graph and make learning decisions without requiring extensive teacher intervention, thereby enhancing student autonomy while managing monitoring complexity through automated progress tracking
Data Source
AI summary
Provided is a method of dynamically generating a personalized knowledge graph based on prompt learning. The method includes the following steps: classifying a textbook difficulty to obtain textbook difficulty prompt words; extracting a learning target to obtain learning target prompt words; evaluating the learning ability of students to obtain a level of the learning ability of students; and generating a dynamic personalized knowledge graph according to prompt words selected by students, evaluation results of the learning ability and a set prompt mapping rule. The method evaluates the learning ability, and selects a course learning difficulty and a course learning target as required. The above steps are combined with subjectivity and passivity to integrally and dynamically generate personalized courses. Each class can make a selection, so as to meet ever-changing learning needs of the student.