Search Engine Query Simplification via Term Dropping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines often return irrelevant results or take a long time to respond to complex user queries, leading to poor user experience and negative perceptions due to their inability to effectively simplify difficult queries.
Innovation Solution
The implementation of query simplification using statistical models, such as condition random fields, maximum entropy, and machine translation, which analyze search engine logs to identify and drop unnecessary terms from long or hard queries, generating simplified queries that yield more relevant results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the search engine processes long or complex queries as submitted, then it attempts to maintain query accuracy, but it returns irrelevant results or takes a long time to respond
Solution Approach 1:
The system performs preliminary query simplification by analyzing the submitted query and automatically removing redundant or unnecessary terms before processing. This preliminary action transforms complex queries like 'ACME restaurant official website' into simplified versions, enabling faster processing while maintaining search accuracy and returning relevant results more quickly
Solution Approach 2:
The system extracts and removes unnecessary terms from the query string based on statistical models trained on query logs. By taking out redundant words that do not contribute to search effectiveness, the system reduces processing time and computational resources while preserving the core search intent and maintaining result relevance
2Ease of operation
If the search engine provides query formulation assistance with potential completions, then it offers guidance to users, but users ignore the suggestions and issue difficult queries anyway
Solution Approach 1:
The system introduces an intermediary query simplification process between the user's complex query and the search processing. This mediator automatically simplifies the query without requiring user interaction or acceptance of suggestions, thereby maintaining ease of operation while ensuring reliable, relevant results that improve user satisfaction
3Adaptability or versatility
If the search engine returns results for all terms in the query, then it comprehensively covers the search intent, but it returns documents that are not relevant to the expected result
Solution Approach 1:
The system applies local quality by selectively retaining only the most important terms from the query while removing less significant ones. Instead of treating all terms equally, it identifies and preserves key terms that carry the most search intent weight, thereby maintaining comprehensive coverage of essential search concepts while improving result relevance by eliminating noisy or redundant terms
Data Source
AI summary
Methods, systems, and computer-readable media for query simplification are provided. A search engine executed by a server receives a query. In response, the search engine determines whether the query is a long or hard query. For long or hard queries, the search engine drops one or more terms based on search engine logs. The search engine may utilize statistical models like machine translation, condition random fields, or max entropy, to identify the terms that should be dropped. The search engine obtains search results for the simplified query and transmits the results to a user that provided the query.