Facet Group Ranking for Product Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online retailers face challenges in providing relevant search results due to the large number of products available, leading to many irrelevant matches in free-form text searches.
Innovation Solution
Implementing a system that uses facet groups and probability calculations to rank search results, where facet groups are attributes of products and their probabilities are determined by user behavior, to enhance search relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If free-form text searches are used to search through a large product database, then the quantity of search results increases, but the relevance of search results deteriorates
Solution Approach 1:
The patent segments the large product database into facet groups (categories, brands, prices, etc.) and organizes products hierarchically. Instead of returning all matching products in a flat list, the system divides results into structured facets that guide users through progressively refined categories, improving relevance while maintaining comprehensive coverage of the product database.
Solution Approach 2:
The patent introduces facet groups as intermediary structures between the user query and the final product results. These facets act as mediators that filter and organize the large set of matching products through multiple levels of categorization, enabling users to navigate from broad categories to specific products while maintaining relevance at each filtering stage.
2Measurement precision
If facet groups are used to organize search results, then the relevance of search results improves, but the device complexity increases
Solution Approach 1:
The patent creates a universal facet group structure that serves multiple functions: organizing products by category, filtering by attributes, ranking results, and providing navigation. This multi-functional facet system handles diverse product types and search scenarios through a single unified framework, improving relevance without proportionally increasing complexity.
Solution Approach 2:
The patent dynamically adjusts facet group parameters (such as which facets are displayed, their hierarchy, and weighting) based on the specific search query and user behavior. This parameter adjustment allows the system to adapt to different search contexts and user preferences, maintaining high relevance while optimizing the complexity level for each specific search scenario.
Data Source
AI summary
Systems and methods are disclosed herein for providing search results, particularly product records from a product database. Products records have facet groups associated therewith and facet groups have probabilities associated therewith indicating the usefulness of the facet group as a way of organizing or filtering search results. For a query, relevant product records are identified. For facet groups present among the relevant product records entropy values are calculated based on a distribution of values for the attribute defining the facet group. The entropy value increases as the distribution of values becomes more uniform. The facet group probability and entropy value are combined to assign a score to the facet groups. The facet groups are ranked and selected according to the score and search results are presented with indicators of the facet groups to enable a user to manage the search results.