Semantic Query Suggestion via Entity Store Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often fail to accurately reflect users' intentions due to reliance on past search queries, leading to unsatisfactory results as they do not account for unseen or seldom-entered queries that may better represent the user's intent.
Innovation Solution
A system that semantically analyzes search queries to provide query formulation suggestions based on identified entities, including categories, attributes, and attribute values, stored in an entity store, to assist users in clarifying their intent and offer better search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If query completion suggestions are generated based solely on past search queries, then the system can provide suggestions quickly using existing data, but the suggestions may not reflect the user's actual intent for unseen or seldom-entered queries
Solution Approach 1:
The system performs preliminary semantic analysis on the user's current query input to identify entities and their attributes before generating suggestions. This allows the system to proactively understand user intent rather than relying solely on historical patterns, resolving the contradiction by preparing intent understanding in advance while maintaining fast suggestion delivery
Solution Approach 2:
The patent introduces an entity store as an intermediary between the query input and suggestion generation. The entity store contains structured knowledge about entities, categories, and attributes that mediates the suggestion process, enabling the system to bridge historical data with current user intent for more accurate suggestions
2Device complexity
If the system relies on collective user search queries, then it can maintain a simple suggestion mechanism, but it fails to understand or disambiguate individual user intent
Solution Approach 1:
The system segments the suggestion generation process into distinct components: entity identification from the query, attribute extraction from identified entities, and suggestion generation based on the structured entity-attribute data. This segmentation allows the system to maintain manageable complexity while significantly improving user intent understanding through structured analysis
Solution Approach 2:
The patent changes the parameters of suggestion generation from relying solely on query string patterns to using semantic parameters extracted from identified entities (such as entity types, categories, and attributes). This parameter transformation enables the system to disambiguate user intent while maintaining system complexity through structured data organization
Data Source
AI summary
Systems, methods and computer-storage media are provided for identifying query formulation suggestions in response to receiving a search query. A portion of a search query is received. Query formulation suggestions are identified by semantically analyzing the search query. The query formulation suggestions are used to further formulate the received search query. The query formulation suggestions include semantic-pattern-based query suggestions that are derived from semantic query patterns, one or more entities, and information associated with these entities. The query formulation suggestions are transmitted for presentation.