Visual Query Search System Parallel Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies are limited in their ability to process visual queries, as they require users to input text-based terms and cannot effectively handle image-based inquiries, such as identifying individuals or objects in images, without manual input or specific queries.
Innovation Solution
A computer-implemented method that processes visual queries by sending them to multiple parallel search systems for simultaneous processing, generating interactive results documents with user-selectable links, and providing search results related to the visual query, including bounding boxes or labels for identified entities, which can include text-based queries for further information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple parallel search systems are used to process visual queries simultaneously, then search coverage and result accuracy are improved, but system complexity increases
Solution Approach 1:
The patent divides the visual query processing into multiple specialized search systems, each handling different types of visual content (e.g., image recognition, text extraction, object detection). Each search system processes specific aspects of the visual query independently, then results are aggregated to provide comprehensive answers.
Solution Approach 2:
The patent creates a universal visual query processing framework that can handle multiple types of search tasks through a single integrated system. The system accepts various visual inputs (images, videos, screenshots) and routes them to appropriate search processes, making the system adaptable to different query types without requiring separate specialized systems.
2Ease of operation
If visual queries are processed without requiring manual text input, then ease of operation is improved, but the ability to retrieve specific information may be reduced
Solution Approach 1:
The patent enables the system to automatically extract meaningful query terms from visual content without user intervention. The system performs self-service by conducting optical character recognition, identifying key objects, and generating search terms autonomously based on the visual input, eliminating the need for manual text entry while maintaining search effectiveness.
Solution Approach 2:
The patent incorporates feedback mechanisms where the system analyzes user interactions with visual search results and refines its automatic query generation. By observing which extracted terms lead to successful searches and which don't, the system learns to improve its automatic term extraction and visual content analysis, progressively reducing information loss.
Data Source
AI summary
A visual query such as a photograph, screen shot, scanned image, or video frame is submitted to a visual query search system from a client system. The search system processes the visual query by sending it to a plurality of parallel search systems, each implementing a distinct visual query search process. A plurality of results is received from the parallel search systems. Utilizing the search results, an interactive results document is created and sent to the client system. The interactive results document has at least one visual identifier for a sub-portion of the visual query with a selectable link to at least one search result for that sub-portion. The visual identifier may be a bounding box around the respective sub-portion, or a semi-transparent label over the respective sub-portion. Optionally, the bounding box or label is color coded by type of result.