Knowledge Extraction Tree for Automated Follow-Up Questions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional knowledge construction and utilization systems provide only one response per question, leading to inefficient acquisition of specialized knowledge and increased labor for beginners investigating defect causes, as they need to repeatedly ask questions to gather comprehensive information.
Innovation Solution
A knowledge extracting device that includes a question input section, transmitting and generating new questions, acquiring responses, creating structured knowledge through a tree structure associating responses, and outputting this knowledge to efficiently organize and present a set of related questions and answers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If only one response is obtained for one question in the knowledge construction and utilization system, then the system is simple to operate, but the knowledge that the beginner really wants to know cannot be obtained efficiently
Solution Approach 1:
The question generation section automatically generates subsequent questions based on previous responses without requiring the beginner to manually create new questions. The system serves itself by extracting key points from responses and autonomously formulating follow-up questions to deepen the knowledge extraction.
Solution Approach 2:
The system performs preliminary actions by pre-generating a list of potential follow-up questions based on the response content before the beginner needs to ask additional questions. This preliminary question generation prepares the system to efficiently extract comprehensive knowledge without requiring manual intervention.
2Loss of information
If the beginner needs to generate subsequent questions many times while referring to previous responses, then more comprehensive knowledge can be obtained, but labor for the beginner is increased
Solution Approach 1:
The question generation section performs self-service by automatically creating subsequent questions based on the response content. The system analyzes the response, extracts key information, and generates appropriate follow-up questions without requiring the beginner to manually reference previous responses and create new questions.
Solution Approach 2:
The system implements feedback by using the response content to automatically generate the next set of questions. The response acquiring section obtains responses, the question generating section uses these responses as feedback to create subsequent questions, and this cycle continues until the beginner is satisfied with the knowledge extraction.
3Productivity
If a tree structure is used to organize responses, then structured knowledge is efficiently provided, but the device complexity increases
Solution Approach 1:
The system segments the knowledge extraction process into distinct functional sections: question input, response acquisition, question generation, and knowledge output. Each section handles a specific aspect of the process, making the overall system more manageable and easier to implement despite the added complexity of the tree structure.
Data Source
AI summary
A knowledge extracting device includes: a question input section which inputs a predetermined question; a question transmitting section which transmits the predetermined question and a new question generated by a question generating section to a respondent terminal; a response acquiring section which acquires a response to a question from the respondent terminal; a question generating section which generates a new question related to the response acquired by the response acquiring section; a relating section which generates, as structured knowledge, a tree structure in which a set of responses acquired by the response acquiring section is associated such that a previously obtained response is a superordinate element of the tree structure and a later obtained response is a subordinate element of the tree structure; and a knowledge output section which outputs the generated structured knowledge as a response to the predetermined question.