Virtual Shelves for Search Query Reformulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in browsing and finding specific products when entering broad search queries in online marketplaces, as existing systems overwhelm them with numerous results and lack effective filtering options, leading to frustration and potential navigation away from the site.
Innovation Solution
The implementation of virtual shelves that logically group products based on features such as brand, style, and material, using machine learning to cluster items and rank them according to user intent, allowing for intuitive browsing and selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional filtering options are provided for broad search queries, then users can narrow down results, but users become overwhelmed by the number of choices and may navigate away from the site
Solution Approach 1:
The patent segments the overwhelming search results into organized virtual shelves grouped by common user intents (e.g., 'Best Sellers,' 'New Arrivals,' 'Budget Options'). This segmentation divides the complex result set into manageable, intuitive categories that reduce cognitive load while maintaining comprehensive coverage of available products.
Solution Approach 2:
The patent introduces virtual shelves as an intermediary layer between the broad search query and individual product listings. These shelves act as mediators that pre-organize results based on inferred user intent, eliminating the need for users to directly interact with complex filtering options while still providing structured navigation paths.
2Adaptability or versatility
If users enter broad search terms to discover items, then they can explore various products, but the results are difficult to browse and may not lead to finding the preferred product
Solution Approach 1:
The patent dynamically generates virtual shelves based on the specific broad search query entered by the user. The system adapts the organization and content of shelves in real-time according to the query context, maintaining versatility in handling different broad search terms while providing consistent ease of browsing through the uniform virtual shelf interface.
Solution Approach 2:
The patent changes the organizational parameters of search results by transitioning from traditional flat listing to hierarchical virtual shelf structures. This parameter change allows the system to maintain adaptability across different search queries while improving browsability through consistent structural organization based on user intent categories.
3Reliability
If users navigate away from the site in search of alternatives, then they may find other options, but their preferred product may be available through the marketplace
Solution Approach 1:
The patent performs preliminary organization of search results into virtual shelves before the user needs to browse them. By pre-grouping products according to common user intents and preferences, the system ensures that the preferred product is already positioned in an accessible location within the virtual shelf structure, eliminating the need for users to navigate away and spend additional time searching.
Data Source
AI summary
Search results are filtered using one or more rankers that evaluate a searcher intention to select items from a subset of search results. A subset of items may be provided that are responsive to a user search query. This subset of items may have one or more related properties and may be logically grouped together. A database of rankers may be evaluated and applied to the subset of items to determine items that are both relevant to the user search query and also correspond to a user intention for the search. As a result, the ranker may select and filter out certain items having one or more features that do not correspond to the user intention.