Shape-Based Search Service Glyph Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In online merchandising environments, users face difficulties in finding similar items due to large search result sets, requiring labor-intensive and error-prone additional keyword descriptions to refine searches based on item characteristics like shape and style.
Innovation Solution
The Shape-Based Search Service allows users to search for items by capturing an image and drawing a glyph approximating the item's shape, which is matched to predefined glyphs or analyzed to infer a shape category, enabling a refined search within that category based on extracted features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users provide additional keyword descriptions to refine search results, then search accuracy improves, but user effort and time increase
Solution Approach 1:
The patent replaces the mechanical system of manual keyword input with an image-based input system. Users capture photos of items and draw glyphs on the images instead of typing detailed keyword descriptions. The system automatically extracts features from the image and glyph to generate search queries, substituting manual text entry with automated image analysis.
Solution Approach 2:
The patent uses visual copying where users draw a glyph that copies or approximates the shape of the item in the captured image. This glyph serves as a visual representation that the system can process to understand item characteristics without requiring users to describe them in text, thereby reducing effort while maintaining search accuracy.
2Adaptability or versatility
If search results include a large number of items, then search coverage improves, but result usability deteriorates
Solution Approach 1:
The patent applies segmentation by dividing the search process into distinct phases: initial broad search for coverage, then refinement based on glyph analysis. The system segments the large result set by analyzing the drawn glyph's characteristics and re-ranking results based on shape similarity, making it easier for users to find relevant items without manually filtering through hundreds of results.
Solution Approach 2:
The system performs preliminary analysis of the user's drawn glyph against the search results before presenting the final refined list. This preliminary action of comparing glyph characteristics with item features allows the system to pre-filter and re-order results, improving usability before the user even sees the final search results.
3Measurement precision
If users manually describe item characteristics, then search refinement improves, but error rate increases
Solution Approach 1:
The patent replaces the error-prone manual text description process with an image-based system where users draw glyphs on captured item photos. The system automatically extracts features from both the image and glyph, eliminating typos, syntax errors, and vocabulary limitations that plague manual keyword input, thereby improving reliability while maintaining search refinement capability.
Data Source
AI summary
Techniques for facilitating a shape-based search of content items are disclosed. In some situations, the techniques include receiving a request for search of content that includes an image of an item and a glyph input by the user on the image that indicates a shape of the first item, extracting features associated with the item from an area of the image on which the glyph is input; identifying a shape category of the first item based at least in part on the indicated shape of the glyph; and conducting a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category. The retrieved search results may be returned to a user.