Natural Language Query Parsing via Mashup Tree Structure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing natural language processing technologies face challenges in accurately determining user intent and providing relevant search results for sense-tagged natural language queries with complex sentence structures, leading to user frustration and low utilization of ontology-based information retrieval systems.
Innovation Solution
A method and system that analyze sense-tagged natural language queries to generate a mashup query language with a tree structure, determining linked levels and searching data hierarchically from an upper entity to a lower entity in a knowledge database, thereby deriving and presenting main and entity information in a structured search result screen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If natural language processing technology is used to convert user queries to ontology query language, then user convenience is improved, but accuracy in determining user intent deteriorates due to errors in analyzing complex sentence structures
Solution Approach 1:
The patent segments the natural language query into multiple sense tags representing different semantic components (e.g., subject, object, relation, attribute). Each sense tag is processed independently to extract meaningful information, allowing the system to handle complex sentence structures by breaking them down into manageable semantic units that can be accurately mapped to ontology query language.
2Adaptability or versatility
If general natural language processing technology is used, then accessibility is improved, but reliability deteriorates due to missing language resources and grammatical errors
Solution Approach 1:
The patent implements error tolerance mechanisms that anticipate and compensate for potential NLP failures before they affect the final query conversion. The system uses multiple alternative parsing strategies and fallback mechanisms to ensure reliable ontology query generation even when general NLP technology encounters grammatical errors or missing language resources.
3Measurement precision
If ontology query language is used for information retrieval, then information accuracy is improved, but ease of use deteriorates because users must learn complex query structures
Solution Approach 1:
The patent introduces an intermediary natural language processing layer that translates between user-friendly natural language queries and precise ontology query language. This intermediary system automatically converts simple natural language input into structured ontology queries, allowing users to benefit from accurate ontology-based information retrieval without needing to learn complex query languages.
4Quantity of substance
If comprehensive ontology information is provided, then information completeness is improved, but system complexity increases making the system harder to utilize
Solution Approach 1:
The patent implements a selective information retrieval strategy that provides comprehensive ontology information only when necessary to answer the user's query. The system analyzes the query's information needs and retrieves only the relevant portion of ontology data required, avoiding the overhead of processing and presenting all available ontology information while still ensuring completeness for the specific query context.
Data Source
AI summary
A method of searching for and providing information about a natural language query having a simple or complex sentence structure, includes: generating a mashup query language having a tree structure in a plurality of levels based on at least one query entity included in a natural language query language via a semantic analysis of the natural language query language; determining whether the plurality of levels are linked through a query entity forming each of the plurality of levels based on attribute information of the mashup query language; searching for data corresponding to the query entity forming each of the plurality of levels from a knowledge database based on a result of the determining, and deriving main information and at least one piece of entity information corresponding to the natural language query language from found data; and laying out a search result screen including the main information and the at least one piece of entity information.