Dynamic Domain Grammar Query Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing query systems face challenges in handling terms with unknown definitions, requiring extensive training datasets or manual programming, which is time-consuming and inefficient, and do not allow for dynamic updates, leading to incomplete or inaccurate responses.
Innovation Solution
A system that receives user feedback to define unknown terms and integrates these definitions into a domain grammar, allowing for dynamic updates and structured storage, enabling the creation of complete queries for efficient search execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a system uses traditional query methods with pre-defined domain grammars, then it can provide accurate responses for known terms, but it cannot handle terms with unknown definitions, requiring extensive manual programming or training datasets
Solution Approach 1:
The system requests feedback from users when encountering unknown terms in queries. Users provide definitions for these terms, which are then added to the domain grammar. This feedback loop enables the system to dynamically expand its vocabulary without manual pre-programming, resolving the contradiction between handling unknown terms and reducing programming complexity
Solution Approach 2:
The system automatically parses user-provided definitions, extracts relevant expressions, and integrates them into the domain grammar structure without requiring extensive manual intervention. This self-service approach allows the system to autonomously improve its ability to handle unknown terms while minimizing the complexity of manual programming
2Reliability
If a system requires extensive training datasets and manual programming to define domain terms, then it can achieve comprehensive term coverage, but it becomes time-consuming and inefficient to maintain
Solution Approach 1:
The system automatically processes user feedback by parsing definitions, extracting expressions, and updating the domain grammar without requiring manual intervention for each term addition. This automation dramatically reduces the time and resources needed to maintain comprehensive term coverage while preserving definition accuracy through structured parsing
Solution Approach 2:
The system pre-processes user feedback by parsing definitions and extracting expressions before integrating them into the domain grammar. This preliminary action ensures that terms are properly structured and formatted upon addition, maintaining reliability while reducing subsequent maintenance time
3Productivity
If a system uses system-organized information structures, then it enables efficient system-wide information retrieval, but it makes it very difficult for users to manually find information
Solution Approach 1:
The system acts as an intermediary between the user's natural language query and the system-organized knowledge store. By parsing user queries, resolving unknown terms through feedback, and translating them into structured queries, the system enables users to find information using intuitive language while maintaining efficient system-wide retrieval through structured processing
Data Source
AI summary
One embodiment provides a method, including: receiving a query from a user; identifying that a desired definition of the at least one term is unknown, by determining that the at least one term does not map to a term having a known definition; receiving the definition of the at least one term from the user; adding the definition to a domain grammar comprising (i) domain-specific terminology and (ii) definitions corresponding to the terms within the domain grammar, wherein the adding comprises (a) extracting expressions from the requested definition and (b) adding, for the at least one term, the expressions into a structured format within the domain grammar; combining (iii) the requested definition and (iv) terms from the parsed query having previously known definitions into a complete query; and providing a response to the query by executing the complete query on a knowledge store.