Search Query Concept Segmentation for Substitution Rules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional search systems are limited in determining context due to high computation complexity, typically only considering one or two query terms, which restricts the ability to identify more specific substitution rules and improve search results.
Innovation Solution
The method involves identifying concepts in search queries that consist of multiple sequential terms, collecting query term substitution data, and determining substitution rules in the context of these concepts, allowing for the consideration of more query terms without excessive computational complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of query terms considered in determining context is increased beyond unigram or bigram, then the ability to identify more specific substitution rules and improve search results is enhanced, but the computation complexity increases significantly
Solution Approach 1:
The patent segments the query into concepts, where each concept is a grouping of sequential query terms that share a common meaning or refer to a specific entity. By treating concepts as atomic units rather than individual terms, the system can consider multiple terms (beyond traditional unigram/bigram) without proportionally increasing computation complexity, as concepts are processed as single entities in the substitution rule determination.
2Productivity
If traditional unigram or bigram context limits are applied, then computation complexity is kept manageable, but the ability to capture more specific contextual relationships and improve substitution accuracy is restricted
Solution Approach 1:
The patent performs preliminary action by pre-defining concepts and their associated query terms before the actual substitution rule determination process. Concepts are established in advance with their constituent terms, allowing the system to quickly reference and apply these pre-organized units during query processing, thereby improving query refinement capability without increasing real-time computation complexity.
3Measurement precision
If more query terms are considered in context determination, then more specific substitution rules can be identified, but the time required for processing increases
Solution Approach 1:
By segmenting queries into pre-defined concepts, the system can efficiently determine substitution rules for multiple terms simultaneously. The concept-based approach allows parallel processing of term substitutions within a concept, reducing overall processing time while maintaining high substitution rule specificity, as all terms within a concept are processed together rather than sequentially.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collecting query term substitution data based on one or more identified concepts. According to one implementation, a method includes receiving a query that includes at least three sequential query terms; determining that the sequential query terms represent a concept; and in response to determining that the sequential query terms represent a concept, collecting query term substitution data for one or more query terms that occur in queries that include the concept.