Visual Query Keyword Selection for Context-Aware Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often struggle to effectively search for entities they do not recognize or remember, such as characters or locations, as traditional character-based searches may return out-of-context results.
Innovation Solution
A system and method that combines character-based and non-character-based inputs, such as images or colors, to identify relevant keywords and generate a modified search query, allowing users to select and rank keywords for accurate search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a traditional character-based search is performed, then the search process is simple and fast, but the search results may be out of context or not reflect user intent
Solution Approach 1:
The patent introduces an image analysis module as an intermediary between the user's image input and the search query generation. This module automatically identifies objects, scenes, or elements in the uploaded image and converts them into searchable keywords, bridging the gap between visual input and text-based search without requiring complex manual intervention from the user
Solution Approach 2:
The system performs preliminary actions by automatically generating multiple candidate search queries from the uploaded image before the user submits the search. The image analysis module pre-processes the image, extracts relevant features, and formulates several possible search queries that the user can then select from, rather than requiring the user to manually construct the search query
2Measurement precision
If multiple keywords are generated and presented for user selection, then search accuracy is improved, but the time and effort required for search increases
Solution Approach 1:
The system generates a limited number of carefully selected candidate keywords (e.g., top 3-5 most relevant keywords) rather than presenting all possible keywords. This partial action approach provides enough options for the user to find the correct search term without overwhelming them with excessive choices, thus maintaining search accuracy while minimizing the time required for keyword selection
3Productivity
If the system automatically selects keywords without user input, then the search process is faster, but the search results may not match user intent
Solution Approach 1:
The system implements feedback by presenting the automatically generated candidate keywords to the user for review and selection. The user can provide feedback by selecting the keyword that best matches their intent or by rejecting and requesting alternative keywords. This feedback loop ensures that the final search query accurately reflects user intent while maintaining efficient automated processing
Data Source
AI summary
A method and system are provided for searching a search query having a non-character-based input. The method comprises receiving the search query comprising a first part and a second part. The first part comprises a non-character-based input. The method further comprises identifying a first plurality of keywords associated with the non-character-based input and receiving a selection of at least one of the first plurality of keywords. The method further comprises generating a modified search query comprising the at least one selected keyword and the second part. The method further comprises retrieving search results based on the modified search query and generating for presentation the search results.