Knowledge Graph Entity Alignment via Multi-Dimensional Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current knowledge graph construction methods face challenges in ensuring data accuracy, leading to erroneous or redundant data being imported, which affects the precision of search results.
Innovation Solution
A method and device for knowledge graph construction that perform entity alignment processing based on similarity measurements, including character, structure, and attribute similarities, to accurately align and import structured data, preventing incorrect data from being added and enhancing data accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If entity alignment processing is performed without comprehensive similarity measurements, then the construction process is simple and fast, but data accuracy deteriorates leading to erroneous or redundant data being imported
Solution Approach 1:
The entity alignment process is segmented into three independent similarity measurement dimensions: character similarity (comparing entity names), structure similarity (comparing classification tree positions), and attribute similarity (comparing entity attributes). Each dimension is measured separately and their results are combined, allowing comprehensive accuracy improvement while maintaining modular processing that limits overall complexity growth.
2Manufacturing precision
If multiple similarity measurement types are used for entity alignment, then data accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system measures all three similarity dimensions (character, structure, attribute) for every entity alignment case, which appears excessive. However, this comprehensive approach ensures high accuracy by capturing multiple aspects of entity similarity simultaneously, with the benefit that the measurements are computationally efficient and can be performed in parallel.
3Manufacturing precision
If strict entity alignment criteria are applied, then data quality is improved, but the quantity of importable data decreases due to more entities being identified as duplicates
Solution Approach 1:
The system uses three different similarity measurement parameters (character similarity, structure similarity, attribute similarity) to evaluate entity pairs. By changing the measurement parameters rather than using a single criterion, the system can accurately distinguish between true duplicates and distinct entities, maintaining high data quality while preserving legitimate data quantity through multi-dimensional verification.
Data Source
AI summary
The present invention provides a knowledge graph construction method and device. The method includes: obtaining structured data, where the structured data includes a first entity name of a first entity and attribute information corresponding to the first entity name, and the attribute information includes a first attribute and a first attribute value; performing, based on measurement of a similarity between the first entity and a second entity in a knowledge graph, entity alignment processing on the first entity, where the measurement of the similarity includes at least one of the following types: measurement of a character similarity, measurement of a structure similarity of a classification tree on which an entity is located, and measurement of an attribute similarity; and importing the structured data into the knowledge graph according to an entity alignment processing result. Embodiments may ensure correctness of data in the knowledge graph.