Search Query Mapping Disambiguation via User Behavior Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic commerce search systems often fail to provide accurate search results due to uncommon terminology, typographical or grammatical errors in search queries, leading to mismatched user intent, and struggle with balancing precision and recall in query mapping.
Innovation Solution
A system that generates and validates mappings between search queries to represent the same user intent by leveraging user behavior data, language mappings, and behavioral purchase data, automatically detecting and eliminating poor mappings to improve search result relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results are based on exact text matching in item descriptions, then precision is improved, but recall deteriorates because uncommon terminology and typos are not matched
Solution Approach 1:
The patent introduces query mappings as an intermediary layer between the user's search query and the item database. Instead of directly matching search queries to item descriptions, the system maps queries to canonical forms using pre-generated mappings that account for synonyms, typos, and uncommon terminology. This intermediary mapping mechanism resolves the contradiction by enabling flexible query interpretation while maintaining precise item matching.
2Adaptability or versatility
If search results leverage user behavior data from previous queries, then recall is improved, but precision deteriorates due to potential mismatches in user intent
Solution Approach 1:
The patent implements a feedback mechanism where user behavior data from previous searches is continuously analyzed to generate and refine query mappings. The system monitors which mapped queries lead to successful purchases and conversions, then uses this feedback to improve future mappings. This closed-loop feedback system resolves the contradiction by leveraging behavioral data to enhance recall while maintaining precision through iterative optimization based on actual user outcomes.
3Adaptability or versatility
If comprehensive query mapping is implemented to handle various search variations, then recall is improved, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-generating and storing query mappings before actual search operations occur. The system creates a comprehensive mapping database in advance that captures relationships between various query formulations and their canonical forms. During search operations, the system simply looks up pre-computed mappings rather than performing complex real-time analysis, thus resolving the contradiction by shifting computational complexity from runtime to setup time.
4Adaptability or versatility
If query mappings are continuously updated with new user behavior data, then adaptability is improved, but loss of time occurs due to processing overhead
Solution Approach 1:
The patent implements periodic action by updating query mappings at scheduled intervals rather than continuously in real-time. The system collects user behavior data and processes mapping updates periodically (e.g., daily or weekly), allowing batch processing of large datasets without impacting real-time search performance. This periodic update strategy resolves the contradiction by maintaining adaptability through regular updates while avoiding the time loss associated with continuous real-time processing.
Data Source
AI summary
Systems and methods are provided for generating query mapping information that associates each of a number of search queries to a corresponding preferred query form to be used in generating search results. A number of queries previously submitted by users may be normalized, then grouped together with other queries sharing the same normalized form. A preferred query form for each group may then be selected. One or more inaccurate mappings may be identified in the initial mapping results based on an analysis of the user behavior of users who previously submitted the search queries included in a given query mapping. A final set of mapped queries may then be generated for use in responding to subsequent search requests, where the final set includes a number of mappings that each associate a particular user-submitted query with a corresponding preferred query form.