Search Query Expansion via Contextual Semantic Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engines struggle to effectively expand search queries to find alternate terms that are semantically similar to the original query without changing its focus, often producing irrelevant results due to techniques like stemming and synonym-based methods that fail to account for context-specific semantics.
Innovation Solution
A method that determines alternate terms by building a query context from relevant documents, using techniques like stemming and thesaurus lookups, and filters these terms to ensure semantic similarity, incorporating valid alternate terms into the search query to expand its scope while maintaining relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If stemming and synonym-based techniques are used to expand search queries, then the scope of search results is increased, but the relevance and accuracy of results deteriorates due to context-specific semantics being ignored
Solution Approach 1:
The patent performs preliminary actions by first identifying the stem of search terms and looking up synonyms before filtering them through context-based validation. This preliminary expansion followed by filtering resolves the contradiction by first increasing scope then restoring precision.
Solution Approach 2:
The patent uses feedback mechanisms by comparing candidate alternate terms against the original query context and document relevance to determine whether to include them. This feedback loop ensures that only contextually appropriate terms are added, maintaining semantic accuracy while expanding search scope.
2Productivity
If alternate terms are added to expand search scope, then more documents are found, but irrelevant results increase reducing search quality
Solution Approach 1:
The patent introduces an intermediary filtering mechanism that acts as a mediator between the expanded search terms and the final result set. This intermediary layer validates each alternate term against the original query context, ensuring that only relevant documents are retrieved while maintaining high productivity.
Solution Approach 2:
The patent changes parameters by dynamically adjusting which alternate terms are included based on their contextual relevance to the original query. This parameter-based filtering allows the system to retrieve more documents when appropriate while maintaining reliability by excluding irrelevant matches.
3Measurement precision
If context-based filtering is applied to ensure semantic similarity, then search accuracy is improved, but processing complexity and time increase
Solution Approach 1:
The patent segments the query processing into distinct stages: stem identification, synonym lookup, context-based filtering, and final result compilation. This segmentation reduces processing complexity by breaking down the complex task into manageable, independent steps that can be executed efficiently.
Solution Approach 2:
The patent performs preliminary actions by pre-identifying query stems and preparing context representations before the actual filtering process. This preliminary preparation simplifies the subsequent filtering operation, reducing overall processing complexity while maintaining high semantic accuracy.
4Adaptability or versatility
If multiple alternate terms are generated and filtered, then search coverage is improved, but processing time increases
Solution Approach 1:
The patent applies partial action by generating a limited set of the most relevant alternate terms rather than exhaustively processing all possible synonyms and stems. This selective approach maintains good search coverage while significantly reducing processing time compared to exhaustive methods.
Data Source
AI summary
A search query for a search engine may be improved by incorporating alternate terms into the search query that are semantically similar to terms of the search query, taking into account information derived from the search query. An initial set of alternate terms that may be semantically similar to the original terms in the search query is generated. The initial set of alternate terms may be compared to information derived from the original search query. One example of such information is a set of documents retrieved in response to a search performed using the initial search query. One or more of the alternate terms may be added to the original search query based on their relationship to the information derived from the original search query.