Ontology-Based Query Refinement for Self-Service Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated self-service software applications are less effective in processing user inquiries due to mismatched terminology between user descriptions and system-centric categories, leading to inefficiencies in providing accurate support.
Innovation Solution
A method involving natural language analysis and ontology processing to identify relevant terms and relationships, refining user queries to align with domain-specific information, and determining whether queries are better suited for service actions or information searches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If self-service applications use formal system-centric categories to describe domain information, then the applications can be integrated with back-end support systems, but the user interface becomes less effective because terminology does not match user descriptions
Solution Approach 1:
The patent introduces an intermediary layer consisting of ontology analysis and natural language processing components that translate between user-friendly free-form text and system-centric formal categories. This mediator enables both effective user interaction and reliable back-end integration without requiring users to learn system terminology.
Solution Approach 2:
The patent segments the query processing into distinct stages: natural language analysis to extract substrings, ontology analysis to map terms to domain concepts, and query analysis to determine service vs. search intent. This segmentation allows each component to specialize in one aspect of the translation process.
2Measurement precision
If users are required to formulate questions using specific system terminology, then query accuracy may improve, but users cannot effectively describe their problems because they are unfamiliar with domain terms and attributes
Solution Approach 1:
Instead of requiring users to adapt to system terminology, the patent inverts the approach by having the system adapt to user terminology. The ontology analysis component maps user-friendly terms to system categories, allowing users to describe problems in natural language while maintaining accurate query processing.
3Productivity
If self-service applications assume users know formal categories and can formulate complete problem descriptions, then processing efficiency improves, but the applications become less accessible to general users
Solution Approach 1:
The patent changes the parameter of user input from structured formal categories to unstructured free-form text. The system then performs parameter transformation through natural language analysis and ontology mapping, maintaining processing efficiency while dramatically improving accessibility to general users.
Data Source
AI summary
A method for providing information to a user in response to a received user query. A natural language analysis generates substrings relevant to an input user query pertaining to a problem a user experiences with a product or service. An ontology analysis outputs: terms of an ontology matching the relevant generated substrings; and relationships between the terms. Elements of a perfect or complete query are captured and include information pertaining to the user's problem. The input user query is refined based on the outputted terms and relationships between the terms. A search query is performed, based on the refined user query. The results of the search are provided to the user.