Dynamic Search Control for Object-Level Visual Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing search techniques struggle with inefficiencies in discovering relevant content due to the vast amount of digital information, requiring users to search entire images or provide static search inputs, which may not yield results of interest.

Innovation Solution

A dynamically positionable search control that overlays a portion of displayed information, allowing users to select and adjust its position and size, generating and updating additional images that are visually similar to the selected portion, accompanied by relevant keywords.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If users search entire images or provide static search inputs, then comprehensive search coverage is achieved, but search efficiency and relevance deteriorate due to vast digital information

Engineering Contradiction:
Improvesearch efficiencyVSAvoidrelevance of search results
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent segments the search process by allowing users to focus on specific portions of displayed information using a dynamically positionable search control. Instead of searching entire images or static inputs, the search control enables localized search on selected regions, improving efficiency while maintaining relevance through targeted object-by-object analysis.

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If static search inputs are used, then simple search operation is maintained, but adaptability to different content regions deteriorates

Engineering Contradiction:
Improvesearch operation simplicityVSAvoidadaptability to different content regions
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamically positionable search control that can be moved to different locations on displayed information. This dynamic positioning maintains operational simplicity while significantly improving adaptability to different content regions, allowing users to search specific areas of interest without complex procedures.

Inventive Principle:
Principle #15Dynamics

3Reliability

If comprehensive search of all digital content is performed, then complete information coverage is achieved, but time consumption and resource usage increase

Engineering Contradiction:
Improvecompleteness of information coverageVSAvoidsearch time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies local quality by enabling searches on specific portions of displayed information rather than performing comprehensive searches on all content. The dynamically positionable search control allows users to concentrate search resources on relevant regions, reducing time consumption while maintaining reliability for the specific objects of interest through targeted object-by-object search.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS12461962B2Dynamic search control invocation and visual search
Publication Date: 2025.11.04 PINTEREST INC
  • US12461962B2 patent drawing
  • US12461962B2 patent drawing
  • US12461962B2 patent drawing

AI summary

Described is a system and method for enabling dynamic selection of a search input. For example, rather than having a static search input box, the search input may be dynamically positioned such that it encompasses a portion of displayed information. For example, a user may touch a touch-based display using two fingers to invoke the dynamic search input and then determine a size and a position of the dynamic search input by moving their fingers on the display. An image segment that includes a representation of the encompassed portion of the displayed information is generated and processed to determine an object represented in the portion of the displayed information. Additional images with visually similar representations of objects are then determined and presented to the user.