Search Result Re-ranking via Concept Graph Ontology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often fail to accurately rank search results based on their relevance to the user's context, leading to lessened importance of key result items that are relevant to the user's dominant topical context.
Innovation Solution
Analyzing the query context to identify dominant concepts, expanding them using a concept graph from a metabase, and re-ranking search results based on the strength of relationship to these expanded concepts and the dominant concepts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results are ranked using traditional search algorithms, then search results are returned in a general order, but the relevance to user context is reduced
Solution Approach 1:
A concept graph is introduced as an intermediary structure between search queries and search results. The concept graph maps dominant concepts from queries to expanded concepts, which then serve as mediators for re-ranking search results based on their lexical and ontological relationships to these concepts, thereby improving relevance without directly complexifying the core ranking algorithm
Solution Approach 2:
The system performs preliminary analysis of search queries to identify dominant concepts and expands these concepts using the concept graph before re-ranking search results. This preliminary concept expansion prepares relevant concept associations in advance, enabling more accurate relevance ranking without adding complexity to the main search processing flow
2Measurement precision
If search results are ranked without considering topical context, then the ranking process is simple, but key result items relevant to user context lose importance
Solution Approach 1:
The system extracts dominant concepts from search queries by analyzing query context, then separates the ranking process into two independent stages: initial ranking based on query terms and re-ranking based on extracted dominant concepts and their expanded concept relationships. This extraction approach maintains simplicity while improving the importance of context-relevant results
Solution Approach 2:
The concept graph provides localized concept relationships specific to each query's dominant concepts, allowing the system to apply context-aware re-ranking only where needed. Each search result is evaluated locally against the expanded concepts derived from its query context, enabling precise importance assignment without global complexity
Data Source
AI summary
Search result re-ranking is provided by employing a concept graph from a metabase. When a search query is received, a query context of the search query is analyzed to identify dominant concepts for the search query. The dominant concepts are expanded by identifying the dominant concepts within a concept graph and identifying additional concepts having a strong relationship with the dominant concepts within the concept graph. A set of search results for the search query is analyzed to determine strength of relationship of each search result to the expanded concepts. The search results are re-ranked based on the strength of relationship of each search result to the expanded concepts and the strength of relationship of each expanded concept to the dominant concepts.