Query Modification Using Non-Textual Context for Relevant Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search systems struggle to modify queries based on the context of non-textual resources displayed on user devices, leading to potential topic drift and irrelevant search results.
Innovation Solution
A system that modifies search queries based on active non-textual data, such as images or videos, by determining modification data, generating candidate queries, scoring them, and selecting the highest-scoring query to provide relevant search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If query modification based on non-textual resource context is implemented, then search result relevance is improved, but system complexity increases
Solution Approach 1:
The query processing system is divided into distinct modules: a non-textual resource context analyzer that extracts context from images/videos, a query modifier that generates candidate queries, and a scorer that ranks candidates. This segmentation allows each component to specialize in one task, improving overall relevance while managing complexity through modular design.
Solution Approach 2:
An intermediary query modification system is introduced between the user's original query and the search engine. This intermediary analyzes non-textual context, generates multiple candidate queries, scores them, and selects the best match, thereby improving result relevance without requiring the search engine itself to become more complex.
2Measurement precision
If multiple candidate queries are generated and scored, then query accuracy is improved, but processing time increases
Solution Approach 1:
Instead of generating and scoring all possible query variations, the system generates a limited set of candidate queries (e.g., 3-5 top candidates) based on the most relevant non-textual context features. This partial action approach achieves sufficient query accuracy without the exponential time cost of exhaustive enumeration.
Solution Approach 2:
The system performs preliminary filtering of non-textual context features before query generation, identifying only the most salient context elements that are likely to improve query accuracy. This preliminary action reduces the search space and accelerates the overall processing time while maintaining query precision.
3Adaptability or versatility
If query modification is always performed, then search completeness is improved, but user experience deteriorates due to unnecessary modifications
Solution Approach 1:
The system dynamically adjusts the query modification parameter based on the quality and relevance of detected non-textual context. When high-quality context is detected, modification is enabled to improve completeness; when context is absent or low-quality, modification is disabled to preserve user experience. This parameter change approach balances adaptability with ease of operation.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, modifying queries based on non-textual content. In one aspect, a method includes receiving, from a user device, a query including a plurality of terms; determining active non-textual data displayed in an application environment on the user device; determining, from the non-textual textual data, modification data for the query; generating a set of modified queries based on the query and the modification parameters; scoring the modified queries according to one or more scoring criteria; selecting one of the modified queries based on the scoring; and providing, to the user device, search results responsive to the selected modified query.