Automated Item Attribute Generation for E-Commerce Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
E-commerce companies face challenges in helping customers find items online due to inefficient item search mechanisms, where customers must manually sift through numerous results, and the process of obtaining item attributes and values is manual and labor-intensive.
Innovation Solution
Automated generation of item attributes and values based on descriptive item titles, using two processes: one considering general context from item titles and another incorporating customer search queries, to enhance item search mechanisms and reduce manual effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated generation of item attributes and values is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The system automatically generates item attributes and values by processing item titles through contextual analysis and customer query matching, eliminating the need for manual attribute entry by merchants. The system serves itself by using its own stored data (customer queries and item attributes) to generate new attributes without external human intervention.
Solution Approach 2:
The patent introduces an automated processing system that acts as an intermediary between item titles and the item attribute index. This intermediary system analyzes item titles, matches them with customer queries, and generates attributes automatically, reducing the complexity burden on merchants while improving productivity.
2Loss of time
If manual item description process is used, then device complexity is reduced, but loss of time increases
Solution Approach 1:
The system performs preliminary actions by storing customer queries and item attributes in advance in an item attribute index. When a new item needs attributes, the system quickly retrieves and processes relevant pre-stored information, significantly reducing the time required compared to manual description while the automation complexity is managed through systematic organization.
3Quantity of substance
If item search mechanisms provide hundreds of item hits, then completeness is improved, but ease of operation deteriorates
Solution Approach 1:
The patent applies local quality by generating specific, context-relevant attributes for each item based on its title and matching customer queries. Instead of providing generic attributes to all items, the system tailors attributes locally to each item's specific context, making search results more discriminating and easier for customers to navigate while maintaining completeness.
Solution Approach 2:
The system changes parameters by dynamically generating item attributes based on contextual analysis of item titles and customer query patterns. This parameter change approach transforms static, manual attribute entry into dynamic, context-aware attribute generation, improving both the quantity and quality of search results while enhancing customer ability to find relevant items.
Data Source
AI summary
Arrangements and methods provide item data information to one or more merchants. A Web server includes various modules that interact with customer item search queries and item data to create a set of attributes that is sent to a merchant as part of an item data form. The set of attributes included on the form is designed to aid in describing and identifying various items that a merchant may offer or currently offer for purchase on an e-commerce service provider. The set of attributes may also be used to augment or generate an item attribute index usable in conjunction with a service provider searching mechanism related to items offered for sale.