Knowledge Point Implicit Relationship Extraction via Path Normalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for acquiring implicit relationships between knowledge points are insufficiently accurate due to reliance on relationship strength ratios without normalization, making it difficult to obtain representative implicit relationships.
Innovation Solution
A method and system that establish a graph of explicit relationships between knowledge points, calculate simple paths, and determine significant implicit relationship strengths by normalizing forward and backward explicit relationship strengths, setting thresholds for meaningful implicit relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If implicit relationship strength is calculated based on relationship strength ratio without normalization, then the calculation process is simple, but the measurement precision is insufficient and lacks absolute measurable values
Solution Approach 1:
The patent transforms the relationship strength calculation from a relative ratio-based parameter to an absolute normalized parameter. By introducing normalization of explicit relationship strengths and calculating implicit relationship strength as the product of edge weights along paths, the system changes the parameter scale from relative (0-1 ratio) to absolute (multiplied weights with threshold filtering), thereby improving measurement precision while maintaining computational feasibility through systematic parameter transformation.
2Ease of operation
If only explicit relationship strength is used to determine implicit relationships, then the acquisition process is straightforward, but the reliability of implicit relationship acquisition is insufficient
Solution Approach 1:
The patent segments the implicit relationship acquisition process into multiple independent calculation components: (1) calculating explicit relationship strengths between direct knowledge points, (2) identifying all simple paths between knowledge point pairs, (3) calculating implicit relationship strength as the product of edge weights along each path, and (4) filtering paths by threshold. This segmentation allows each component to be processed independently and systematically, improving reliability through comprehensive path-based analysis while keeping the overall process structured and manageable.
Solution Approach 2:
The patent implements a feedback mechanism where implicit relationship strengths are calculated based on explicit relationship strengths, and then these implicit relationships are used to enhance the overall knowledge graph. The system continuously refines relationship strengths by considering multiple paths and their cumulative weights, creating a feedback loop that improves the reliability of implicit relationship acquisition through iterative calculation and threshold-based validation.
Data Source
AI summary
A method and system for obtaining a knowledge point implicit relationship are provided; first, establishing a knowledge point explicit relationship map according to knowledge point explicit relationship strengths; second, computing according to said knowledge point explicit relationship map a simple path set of two knowledge points; then, computing the implicit relationship strength values corresponding to each simple path in said simple path set; further, comparing the relationship strength values of the simple paths and setting as the significant implicit relationship strength value the simple path relationship strength having the largest value also greater than a preset threshold value. The described solution effectively avoids the problems of only using the relationship strengths between knowledge points and the ratio of relationship strengths to obtain the implicit relationship of knowledge points, the manner of searching for an implicit relationship being insufficiently accurate, and not performing normalization processing on the relationship strengths.