Contextual Search Query Refinement via Document Content Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in formulating queries that accurately represent their informational needs, leading to high-quality search results, as existing search engines often return unrelated resources due to general or ambiguous query terms, making the search process time-consuming and frustrating.
Innovation Solution
A method that receives a query and adds supplemental terms based on the content of a displayed document, forming a formulated query to identify and rank search results, enhancing relevance by calculating similarity scores and re-ranking documents to provide contextually relevant results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users enter general or ambiguous query terms, then the search engine can quickly retrieve a large number of matching resources, but the search results become unrelated and low quality
Solution Approach 1:
The system performs preliminary action by automatically analyzing the displayed document and pre-computing supplemental terms before the user completes their query. This allows the search engine to have refined query formulations ready, eliminating the need for users to manually refine ambiguous queries while maintaining fast search speeds.
Solution Approach 2:
The system introduces an intermediary component that acts as a bridge between the user's simple query and the search engine. This intermediary automatically generates and injects supplemental terms derived from the displayed document context, effectively mediating between ambiguous user input and precise search requirements without requiring additional user effort.
2Measurement precision
If users manually refine their queries to improve search quality, then more relevant results are obtained, but the search process becomes time-consuming and frustrating
Solution Approach 1:
The system implements self-service by automatically performing the query refinement task that would otherwise require user effort. The system monitors the displayed document, extracts relevant supplemental terms, and autonomously formulates refined queries, allowing users to obtain high-quality results without manually investing time in query refinement.
Solution Approach 2:
The system uses feedback from the displayed document context to automatically adjust and refine the search query. By continuously monitoring the document being viewed and incorporating its content into query formulation, the system creates a feedback loop that automatically improves search relevance without requiring user intervention or additional time investment.
3Quantity of substance
If the search engine returns more comprehensive results, then the coverage of informational needs increases, but the quality and relevance of individual results decreases
Solution Approach 1:
The system applies local quality by enhancing specific aspects of the search process rather than uniformly treating all queries. It selectively incorporates supplemental terms from the displayed document into relevant queries, improving the quality of results for contextually appropriate searches while maintaining comprehensive coverage across different query types through its universal application mechanism.
Data Source
AI summary
Technology described herein enhances a user's search experience by providing refined search results that are relevant to a displayed document. Contextual search results are obtained which identify a list of documents responsive to a formulated query that is based on the user's search query, as well as one or more supplemental terms that are based on content in the displayed document during user entry of the search query. The contextual search results are then “refined” by re-ranking the documents in the list, based on the similarity between the user's original search query and terms in these documents. This re-ranking enables contextual search results to be provided that are also highly relevant to the user's informational need.