Query Refinement Module for Search Recall and Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional keyword search engines face challenges in retrieving relevant documents due to low recall and high irrelevance, as they struggle to recognize semantic meaning and vocabulary variations, requiring users to manually refine search queries, which is cumbersome and inefficient.
Innovation Solution
A search system with query refinement that uses a user interface to suggest alternative search terms and senses, allowing users to select relevant options, thereby enhancing the search query without the need for manual modification, and executes searches based on both original and alternative terms simultaneously.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If keyword search is used to retrieve documents, then search speed is fast, but recall is low and precision is poor
Solution Approach 1:
The system performs preliminary actions by automatically generating alternative search queries and refining the original query before final document retrieval. The query refinement module creates multiple variations of the search query in advance, expanding the search scope to improve recall while maintaining precision through structured refinement processes.
2Reliability
If manual query refinement is performed by users, then search precision can be improved, but user time and effort increase significantly
Solution Approach 1:
The system performs self-service by automatically generating and submitting alternative search queries without requiring user intervention. The query refinement module autonomously creates query variations, evaluates them, and submits the most promising ones to the search engine, freeing users from manual query refinement tasks while maintaining high search precision.
Solution Approach 2:
The query refinement module acts as an intermediary between the user's original query and the search engine. It automatically processes the query, generates alternatives, and selects the best refinement to submit, serving as a smart mediator that improves search precision without requiring direct user involvement in the refinement process.
3Reliability
If alternative search terms are generated and submitted, then recall is improved, but device complexity increases
Solution Approach 1:
The system applies segmentation by dividing the query refinement process into distinct modular components: the query refinement module that generates alternatives, the evaluation mechanism that assesses them, and the submission process that sends refined queries to the search engine. This modular architecture manages system complexity while enabling comprehensive alternative term generation and submission to improve recall.
Data Source
AI summary
A search system and method for searching for electronic documents, and providing a search result in response to a search query. In one embodiment, the search system includes a processor, a user interface module adapted to receive a search query from a user that includes a search query term, a search engine that electronically searches for electronic documents that satisfy the search query term, and a query processing module that identifies at least one alternative term for the search query term, and provides the alternative term to the user interface module for display to the user, and also provides the alternative term to the search engine to search for electronic documents that satisfy the alternative term.