Query Handling System for E-Commerce Search Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search queries in e-commerce settings often return no results due to unintuitive product identifiers and variations in product specifications across different sites, leading to frustration and inefficiency for users.
Innovation Solution
A method that extracts keywords from information sources, classifies them according to a query schema, combines them into a new query, and executes it to generate results, using a redirect database and external sources to find corresponding successful queries, and calculates probabilities to select the most likely candidate query.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users search for specific product identifiers, then search precision is improved, but search reliability deteriorates due to no results from specification variations
Solution Approach 1:
The patent introduces an intermediary query rewriting mechanism that acts as a mediator between the user's original query and the search system. When a query returns no results, the system automatically rewrites the query by extracting keywords, classifying them according to schema, and generating alternative queries that are more likely to match products across different sites with varying specifications.
Solution Approach 2:
The system changes the parameters of the search query dynamically. It extracts keywords from the original query, classifies them into categories (brand, model, attributes), and generates new queries with modified parameters that broaden the search scope to accommodate specification variations while maintaining relevance.
2Reliability
If manually rewriting queries is done to handle no results, then search reliability is improved, but loss of time increases
Solution Approach 1:
The system performs self-service by automatically detecting when a query returns no results and autonomously rewriting the query without requiring user intervention. The automated query rewriting process extracts keywords, classifies them, generates alternative queries, and executes them to find relevant products, eliminating the need for users to manually rewrite queries.
Solution Approach 2:
The system prepares alternative queries in advance by extracting and classifying keywords from the original query before executing the search. This preliminary processing of query transformation ensures that when no results are found, the system already has the framework needed to generate and execute alternative queries efficiently.
3Loss of time
If query rewriting is automated, then loss of time is reduced, but device complexity increases
Solution Approach 1:
The query rewriting system is segmented into distinct functional modules: keyword extraction module, keyword classification module (organizing keywords into schema categories), query generation module, and probability calculation module. This segmentation allows each component to handle a specific aspect of query transformation independently, making the overall complex system more manageable and maintainable.
Solution Approach 2:
The system manages complexity by changing the representation parameters of queries through structured classification. Keywords are organized into schema categories with defined relationships, and queries are generated by combining these classified keywords according to predefined schemas, which simplifies the transformation logic while maintaining effectiveness.
4Ease of operation
If product identifiers are used for comparison shopping, then ease of operation is improved, but search reliability deteriorates due to specification differences across sites
Solution Approach 1:
The query rewriting system provides universal functionality that works across different e-commerce sites with varying product identifier formats and specifications. By extracting semantic keywords and generating multiple alternative queries, the system adapts to different site-specific naming conventions and specification variations, making comparison shopping reliable across diverse platforms.
Data Source
AI summary
Methods and systems for handling queries include extracting keywords related to a first query from one or more information sources. The keywords are classified according to a plurality of categories defined by a query schema. A plurality of the keywords are combined into a second query according to the query schema. The second query is executed to generate one or more results.