Intent Sensitive Search Results via Trigger Map Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often receive search results that do not meet their informational needs due to poorly expressed queries, leading to frequent query refinements, which can be time-consuming and inefficient.
Innovation Solution
A search system that analyzes user search history to determine potential user intents and generates secondary queries using a trigger map of query-refinement pairs, providing intent-sensitive search results that include both primary and secondary queries, thereby improving the relevance of search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If search engines provide results based on query terms and frequency, then search results can be generated automatically, but the results often do not meet user informational needs
Solution Approach 1:
The system performs preliminary analysis of search history and query patterns to predict intended refinements before the user actually refines their query. By pre-identifying potential refinements based on historical data, the system proactively adjusts search results to match user intent, eliminating the need for users to manually refine queries while improving result relevance.
Solution Approach 2:
The system continuously monitors and analyzes user search history to learn from actual query refinements. This feedback loop allows the system to update its understanding of user intent and improve future search result generation, creating a progressively more accurate model of user needs that reduces the need for manual query refinement.
2Reliability
If users refine queries multiple times during search sessions, then search results can be improved, but the search process becomes time-consuming
Solution Approach 1:
The system performs preliminary identification of potential query refinements by analyzing search history patterns. Instead of waiting for users to manually refine their queries, the system pre-determines likely refinement directions based on historical data and presents results that already account for these predicted refinements, significantly reducing the time users would otherwise spend on iterative query adjustments.
3Productivity
If search engines use scoring functions based on query term frequency, then search results can be generated efficiently, but results do not fully satisfy user information needs
Solution Approach 1:
The system performs preliminary analysis of search history and query patterns to predict user intent before generating final search results. By pre-identifying potential refinements based on historical data, the system enriches the traditional scoring function with intent-based weighting, maintaining efficient automated generation while significantly improving the match between results and user informational needs.
Solution Approach 2:
The system modifies the scoring function parameters by incorporating intent signals derived from search history analysis. Instead of relying solely on query term frequency, the scoring function now weights results based on predicted user intent and historical refinement patterns, changing the evaluation parameters to better align with user informational needs while maintaining automated generation efficiency.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing intent sensitive search results. In one aspect, a method includes receiving a current query for a current search session that is associated with a user identifier. One or more potential refinements for the current query are identified, each potential refinement being one or more terms and based on previous queries associated with the user identifier and previous queries associated with other user identifiers. One or more secondary queries are generated, each secondary query including the current query and one of the potential refinements, each secondary query matching a query-refinement pair in a trigger map that includes a plurality of query-refinement pairs. Secondary search results are identified for the secondary queries. Search results are provided including at least one of the secondary search results.