Query Refinement via N-Gram Concept Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current internet search engines fail to effectively provide relevant query refinements that cater to users' interests, often resulting in unsatisfactory search results due to broad queries or incorrect terminology, leading to increased user interaction and reduced precision in search outcomes.
Innovation Solution
The method involves dividing search queries into n-grams, determining shared concepts, and generating candidate refinement queries based on context, frequency, and correlation analysis, which are then scored and filtered to provide relevant alternatives that are textually distinct yet related to the original query.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search engines provide query refinements based on broad queries, then the search scope is expanded, but the precision of search results deteriorates
Solution Approach 1:
The system segments the query refinement generation process into multiple independent components: n-gram extraction, concept determination, candidate refinement generation, category determination, and scoring. Each component handles a specific aspect of the refinement process, allowing the system to expand search scope through diverse refinement sources while maintaining precision through targeted scoring and selection based on shared concepts and categories.
2Productivity
If search engines provide more query refinements, then user interaction is reduced, but the complexity of the refinement system increases
Solution Approach 1:
The system performs preliminary actions by pre-determining categories for both the original query and candidate refinements before scoring. It also pre-identifies shared n-grams and concepts. This preliminary categorization and analysis enables the system to efficiently score and rank multiple refinement candidates without requiring complex real-time processing, thus reducing user interaction steps while managing system complexity through structured preprocessing.
3Reliability
If query refinements are generated based on contextual analysis, then the relevance of refinements is improved, but the computational requirements increase
Solution Approach 1:
The system extracts only the essential contextual elements needed for refinement generation: specific n-grams from the query, shared concepts between query and refinements, and category labels. By extracting and focusing on these key contextual features rather than analyzing entire query structures, the system improves refinement relevance through meaningful contextual analysis while reducing computational energy requirements through selective feature extraction.
Data Source
AI summary
Methods, systems, and apparatus, including computer program products, for generating query refinements. In one implementation, a method includes dividing a search query into one or more n-grams; determining that each of the one or more n-grams represents a same concept, and in response to the determination: selecting one or more candidate refinement queries; determining one or more categories for the search query; determining one or more categories for each of the candidate refinement queries; determining a respective first score for each of the candidate refinement queries; and identifying as query refinements for the search query one or more of the candidate refinement queries based on the first scores.