Question Type and Domain Identifying Apparatus for Open Web Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional question and answer techniques are limited in processing questions for open domains and extracting accurate answers due to technical limitations, leading to inefficiencies in information searching and document retrieval on the web.
Innovation Solution
A question type and domain identifying apparatus and method that classify user questions into query or question and answer types, distribute them to specialized question and answer engines, and restrict search targets based on question subjects and area information to enhance answer retrieval efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional question and answer techniques are used for open domains, then the system can process questions, but the accuracy and efficiency of answer extraction is limited
Solution Approach 1:
The patent segments the question processing system into multiple domain-specific question and answer engines, each specialized in handling particular domains (e.g., sports, entertainment, technology). This segmentation allows each engine to focus on extracting answers accurately within its domain while maintaining overall system versatility through the ability to route questions to appropriate specialized engines based on domain identification.
2Productivity
If a single unified search engine is used for all query types, then the system is simple to operate, but it cannot efficiently distinguish between information searching and question answering needs
Solution Approach 1:
The patent implements a dynamic routing mechanism that analyzes the user's question and dynamically selects the appropriate processing path. The system determines whether to route to a question and answer engine or an information searching engine based on the question's characteristics, allowing the system to adapt its behavior based on input while maintaining operational simplicity for the user.
Solution Approach 2:
The patent introduces a question type identification module as an intermediary between the user input and the processing engines. This intermediary analyzes the question, determines its type (information searching or question answering), and routes it to the appropriate engine, thereby simplifying the user interface while managing system complexity through a dedicated routing layer.
3Measurement precision
If the system processes all questions without classification, then the operation is simple, but the accuracy of document retrieval and answer extraction decreases
Solution Approach 1:
The patent implements self-service through automatic question classification, where the system independently analyzes the user's input question, determines its type and domain, and selects the appropriate processing engine without requiring user intervention. This maintains ease of operation for users while achieving high document retrieval accuracy through automated intelligent routing.
Data Source
AI summary
A question type and domain identifying apparatus includes: a question type identifier for recognizing the number of words of a user's question to identify whether the user's question is a query for performing information searching or a question for performing a question and answer (Q&A); a question domain distributor for distributing one of plural preset domain specialized Q&A engines, as a Q&A engine of the user's question based on the recognized word number; and a Q&A engine block, including the domain specialized Q&A engines, for selectively performing information searching or a Q&A with respect to the user's question in response to the distribution of the question domain distributor.