Attribute Extraction System for E-commerce Search Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
E-commerce search engines struggle to accurately identify product and service attributes from search queries due to linguistic variations, leading to incongruities between search queries and search results, and providers may miss relevant labels, resulting in suboptimal search experiences.
Innovation Solution
A system and method for extracting attributes from text passages using an N-Gram Extractor, Attribute Selector Interface, and Dictionary Builder to build a dictionary of service/product attribute pairs, enabling the identification and interpretation of product and service attributes, and improving search query interpretation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If general search engines use multiple labels for web pages, then search coverage is improved, but search precision deteriorates due to linguistic variations and incongruities between search queries and results
Solution Approach 1:
The patent introduces an intermediary system consisting of an attribute extractor, attribute selector interface, and dictionary builder that mediates between search queries and web page content. This intermediary layer processes and standardizes attributes, acting as a bridge that reconciles linguistic variations while maintaining search precision and coverage simultaneously
2Ease of operation
If e-commerce providers tag web pages with multiple relevant labels, then accessibility to consumers is improved, but the complexity of managing and interpreting these labels increases
Solution Approach 1:
The system enables self-service by automatically extracting attributes from web page content and building dictionaries without requiring manual intervention. The attribute extractor and dictionary builder work autonomously to manage labels, reducing the complexity of label management while maintaining high accessibility for consumers
3Quantity of substance
If search engines attempt to handle all variations of product and service terms, then search completeness is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-processing web page content to extract and standardize attributes before search operations. The dictionary builder creates predefined attribute dictionaries in advance, allowing the search system to quickly match queries against standardized attributes rather than processing all variations in real-time, thus maintaining completeness while reducing processing time
Data Source
AI summary
A system for extracting attributes can analyze text from data sources, extract n-grams from the text as candidate attribute and service/product pairs, prompt a human operator to rate the suitability of the candidate attribute and service/product pairs, and, based on the ratings, add the candidate attribute and service/product pairs to an attribute dictionary. In embodiments, an attribute extraction system includes an n-gram extractor, an attribute selector interface, and a dictionary builder. Data sources may include product titles, category descriptions, product descriptions, and like data from one or more product databases. In embodiments, the attribute dictionary is analyzed to determine canonical names for products or services and name variants for the products or services.