Natural Language Query Parsing with Clarifying Questions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inexperienced users face challenges in effectively querying large databases due to lack of knowledge about database structure and information, leading to wasted time and resources, and existing automated systems often provide inconsistent or ineffective assistance.
Innovation Solution
A server computer-based system that receives initial questions, identifies ambiguous terms, presents clarifying questions to users, and determines answers using machine learning models, with the option to pass unclear questions to subject matter experts for assistance, refining the questioning process and improving answer accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If an inexperienced user attempts to query a large database without knowledge of database structure, then the user can access the database, but time and resources are wasted due to repeated failed calls
Solution Approach 1:
The patent introduces an automated assistant system that acts as an intermediary between the user and the database. This assistant translates natural language questions into proper database queries, eliminating the need for users to understand database structure while preventing wasted time from incorrect queries
Solution Approach 2:
The system enables users to query databases independently using natural language without requiring expert knowledge. The automated assistant provides self-service by automatically interpreting questions, identifying required information, and executing appropriate database calls
2Reliability
If subject matter experts assist users with queries, then accurate answers are provided, but experts cannot assist every user with every query
Solution Approach 1:
The system creates a copy of expert knowledge through an automated assistant that has been trained on expert responses and database structures. This digital twin can handle multiple queries simultaneously, maintaining expert-level accuracy while dramatically increasing query throughput
Solution Approach 2:
The query handling process is segmented into distinct components: natural language interpretation, query generation, database execution, and result delivery. The automated assistant handles routine segments, while expert intervention is reserved for complex cases, optimizing both accuracy and productivity
3Productivity
If an automated system assists users with database queries, then expert availability is increased, but results are inconsistent and ineffective
Solution Approach 1:
The system improves consistency by standardizing query parameters and execution protocols. The automated assistant uses consistent methods for interpreting natural language, generating queries, and formatting responses, eliminating the variability inherent in manual expert assistance
Solution Approach 2:
The system incorporates feedback mechanisms where user interactions with the automated assistant are analyzed to improve future responses. This learning loop enhances consistency over time while maintaining high productivity, as the system becomes more accurate through accumulated experience
Data Source
AI summary
Systems and methods of processing a query from a user. A method includes receiving, by a server computer, an initial question from a client computer. The initial question includes a plurality of words and the server computer can identify a set of words in the plurality of words. Then the server computer can determine a list of clarifying questions based on a subset of the set of words. The server computer presents the list of clarifying questions to the client computer and receiving clarifying answers to the clarifying questions. The server computer determines an answer to the initial question and presents the answer to the client computer.