Search Engine Query Refinement Intent Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current internet search engines face challenges in accurately determining user intent, particularly with ambiguous queries, as they rely on traditional ranking techniques that do not effectively account for user-specific interactions and query refinements over time.
Innovation Solution
The system processes query information by identifying refining query terms, associating intents with sessions based on their frequency of use across multiple sessions, and modifying document scores based on user interaction data to improve search result relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional ranking techniques are used, then the search engine can process queries efficiently, but the accuracy of determining user intent deteriorates
Solution Approach 1:
The system pre-processes query sequences to identify refining query terms and associates them with user intents before actual search execution. By analyzing patterns of query refinements across multiple sessions in advance, the system builds a knowledge base of user intent signals that can be quickly applied during live searches, thus maintaining efficiency while improving accuracy
Solution Approach 2:
The system transitions from analyzing single isolated queries to analyzing sequences of queries across multiple sessions. By adding the temporal and contextual dimension of query sequences, the system can infer user intent more accurately without significantly increasing processing complexity, as the additional information comes from leveraging existing search session data
2Reliability
If query refinements and user interactions are analyzed in detail, then search result relevance improves, but system complexity increases
Solution Approach 1:
The system extracts specific refining query terms from sequences of user queries and isolates them as distinct intent signals. By taking out only the relevant refinement terms rather than analyzing entire query sequences, the system reduces computational complexity while maintaining the ability to accurately determine user intent and improve search result relevance
Solution Approach 2:
The system changes the parameter being measured from individual query characteristics to the frequency and pattern of refining query term usage across multiple sessions. This parameter transformation allows the system to leverage statistical patterns in user behavior to improve relevance without requiring complex real-time analysis of each query interaction
Data Source
AI summary
Methods, systems and program products for identifying user intent from query patterns including, in one implementation, a method including identifying a current query including a query term, and obtaining search results responsive to the current query. Each search result identifying a document associated with a score indicating relevance. The method includes associating an intent with the session based on submission of a query containing a refining term, where each refining term was previously submitted with different unique queries. The method includes identifying prior sessions, where each prior session includes a query that matches the current query, and each prior session includes a query that contains the refining term. The method includes identifying a document selected more frequently in the prior sessions than by a general population and modifying the scores of the document in the search results. The method also includes ranking the search results based on the scores.