Semantic Graph Query Reformulation for Domain Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computerized search engines often return irrelevant results in domain-specific contexts due to the lack of understanding of proper domain-specific terms, as they cannot assess user intent and rephrase queries effectively.
Innovation Solution
The use of semantic graph data models, trained using machine learning on domain-specific documents and queries, to establish semantic relationships between words, allowing for the substitution of query words with alternative terms that better match user intent, thereby improving search relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional keyword-based search is used, then the search engine can process queries quickly, but it returns irrelevant results in domain-specific contexts because it cannot understand user intent
Solution Approach 1:
The patent introduces an intermediary component (query reformulation module with semantic graph) between the user's natural language query and the search engine. This intermediary transforms the query into domain-specific terms by establishing semantic relationships between words, enabling the search engine to understand user intent without requiring the search engine itself to be complex
Solution Approach 2:
The system performs preliminary query reformulation before executing the search. By pre-processing the query to substitute natural language terms with domain-specific terms using the semantic graph, the system prepares the query in advance, allowing the search engine to process it efficiently while returning relevant results
2Measurement precision
If the search engine tries to understand domain-specific terms and user intent, then search result accuracy improves, but the system complexity increases significantly
Solution Approach 1:
The patent segments the complex task of understanding user intent into manageable components: a semantic graph construction phase (using machine learning on domain documents) and a query reformulation phase (substituting terms based on semantic relationships). This segmentation allows each component to focus on a specific function, reducing overall system complexity while improving accuracy
Solution Approach 2:
The system changes the parameter of term representation from simple keywords to semantically-enriched terms derived from the semantic graph. By transforming the query parameters (natural language terms → domain-specific terms with semantic relationships), the system achieves better understanding accuracy without fundamentally changing the search engine architecture
Data Source
AI summary
A method for executing a computerized query includes receiving a new query from a user device. The query includes natural language text. Based on a type of user, and using an alternative term generator, a selected data model is selected from among pre-determined data models. The selected data model is particular to the type of user. Each of the pre-determined data models includes a corresponding semantic graph data model that establishes semantic relationships between words. Query words in the natural language text are compared to the selected data model using the alternative term generator to find at least one alternative term. The alternative term has a semantic relationship to a query word in query words. The semantic relationship exceeds a first threshold value. The alternative term is substituted for a query word to form a revised query. The revised query is executed on a search engine using the alternative terms.