Knowledge Graph Query Correction for Entity Confusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies fail to accurately correct queries with errors, leading to unhelpful search results due to user confusion between entities, which traditional spelling and grammar correction tools cannot address effectively.
Innovation Solution
A computer system uses a knowledge graph to identify error candidates in queries by determining relationships between entities and proposes or automatically replaces the error with a more relevant entity, improving the query's coherence and generating more accurate search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional spelling and grammar correction tools are used, then query processing is simple, but query accuracy is insufficient when users confuse entities
Solution Approach 1:
A knowledge graph is introduced as an intermediary component between the query and search results. The knowledge graph stores semantic relationships between entities and uses these relationships to determine whether entities in a query are confused, enabling accurate query correction without complex traditional methods
Solution Approach 2:
Traditional mechanical spelling and grammar correction mechanisms are replaced with a semantic-based correction system using knowledge graphs. This substitution allows the system to understand entity relationships and correct queries based on semantic meaning rather than just surface-level text processing
2Reliability
If search results are generated without query correction, then processing is fast, but search results are unhelpful when queries contain entity confusion
Solution Approach 1:
The system performs preliminary query correction using the knowledge graph before generating search results. By identifying and correcting entity confusion in advance, the system ensures high-quality search results are obtained from corrected queries rather than processing time-consuming incorrect queries
Solution Approach 2:
The knowledge graph provides feedback about entity relationships to the query processing system. When entities in a query are found to be confused based on knowledge graph relationships, the system uses this feedback to automatically correct the query before search result generation
3Productivity
If queries with entity confusion are processed as-is, then resource usage is low, but unneeded search results are generated
Solution Approach 1:
The system extracts and removes confused entities from the query using knowledge graph analysis. By identifying which entities are likely confused and removing or correcting them, the system prevents unnecessary search result generation and reduces resource consumption on irrelevant queries
Data Source
AI summary
A method includes receiving, by a computer system configured to generate search result, a query, identifying a plurality of entities in the query, determining, using a knowledge graph, a measure of a relationship between the entities in the query, identifying a replacement entity for a first entity of the entities in the query, wherein the replacement entity is determined to improve the measure of the relationship between the entities when the first entity is replaced by the replacement entity, and generating a search result using the query modified by the replacement entity, which replaces the first entity in the query.