Graph-Based Search System for Free-Form Text Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engines are inadequate for retrieving information using free-form text queries, especially when complex queries with logic terms are involved, and they struggle to provide accurate results by considering relationships between entities, limiting their effectiveness in specific fields and dynamic query updates.
Innovation Solution
A method and system that utilize a graph-based approach to analyze free-form text queries by extracting keywords and logic terms, creating a graph of annotated entities and relationships, and filtering results based on relevance, allowing for dynamic updates and improvements in query responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional search engines are used for free-form text queries, then the search process is simple and fast, but the accuracy and relevance of results deteriorate when complex queries with logic terms are involved
Solution Approach 1:
The patent introduces an intermediary processing layer between the user's free-form text query and the search results. This layer includes components for extracting keywords and logic terms, parsing query structure, and generating refined search queries. The intermediary transforms unstructured free-form text into structured search queries that can be accurately processed, thereby improving result accuracy without requiring the entire search system to be fundamentally complex.
Solution Approach 2:
The search process is segmented into distinct functional modules: keyword extraction, logic term identification, query parsing, query refinement, and result generation. Each module handles a specific aspect of the query processing, allowing the system to manage complexity through modular design while maintaining high accuracy in handling complex queries with multiple conditions and logic terms.
2Reliability
If search engines consider relationships between entities, then the relevance of results improves, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and structuring the free-form text query into extracted keywords, logic terms, and parsed query components before the actual search execution. This preliminary structuring allows the search engine to efficiently utilize entity relationships during the search process, as the query is already organized in a format that facilitates relationship-based matching, thereby reducing processing time while maintaining high relevance.
Solution Approach 2:
The patent changes the parameter representation of the query from unstructured free-form text to structured parameters including extracted keywords, logic terms, and query components. This parameter transformation enables the system to efficiently process entity relationships by working with discrete, organized data structures rather than raw text, improving result relevance without proportionally increasing processing time.
3Adaptability or versatility
If the search system supports dynamic query updates, then the adaptability to user needs improves, but the system complexity and resource requirements increase
Solution Approach 1:
The search system implements dynamics by allowing queries to be updated and refined during the search process. The extracted keywords and logic terms can be modified, and the parsed query structure can be adjusted based on user feedback or additional requirements. This dynamic capability enables the system to adapt to changing user needs while maintaining a manageable architecture through the use of modular, reusable processing components.
Data Source
AI summary
A method, apparatus and computer program product, the method comprising: obtaining a graph having a multiple nodes and one or more edges, each node comprising a set of entities having a common property and a subject, and each edge connecting two nodes and indicating a relationship therebetween; obtaining a query from a user, wherein the search query comprises a free-form text; extracting from the free-form one or more keyword combinations and one or more logic terms; for each keyword combination, creating a list of nodes from the graph based on a relevancy of the subject of each of the nodes with respect to the keyword combination; creating a collection of entities comprised in the list of nodes, said creating comprises filtering out entities associated with a node that is excluded based on the logic term; and providing a response to the query, wherein the response comprises the collection of entities.