Question Answer Generation System for Document Content Revision

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional question answering systems are unable to propose and validate new questions not specified in the corpus of data, and they lack the capability to categorize questions based on content, which limits their accuracy and efficiency in identifying relevant documents.

Innovation Solution

A question/answer creation system that imports documents, automatically generates candidate questions, and provides answers using natural language processing, allowing content creators to verify the accuracy of questions and candidate questions, and stores verified questions for improved search functionality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional question answering systems are used, then the system structure is simple, but the system cannot propose and validate new questions not specified in the corpus of data

Engineering Contradiction:

Improvecapability to propose and validate new questionsVSAvoidsystem structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the question processing workflow into distinct modules: question proposal module, question validation module, and answer generation module. This segmentation enables the system to handle new questions not in the corpus while maintaining manageable system complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-processing document content to extract entities, relationships, and semantic structures before question generation. This preliminary analysis enables the proposal of novel questions without requiring complete re-processing when new questions arise.

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If conventional question answering systems are used, then the system is easy to operate, but the system lacks the capability to categorize questions based on content

Engineering Contradiction:

Improvequestion categorization capabilityVSAvoidsystem operation

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically categorizing questions based on content analysis without requiring manual intervention. The categorization is integrated into the question processing pipeline, allowing the system to autonomously organize questions while maintaining ease of operation through automated workflows.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where categorization results from previous questions inform the processing of subsequent questions. This feedback loop improves categorization accuracy over time while the automated nature maintains operational simplicity.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If manual question verification is performed, then question accuracy is high, but the processing time increases

Engineering Contradiction:

Improvequestion accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial verification by focusing manual review only on critical question aspects while relying on automated verification for routine checks. This selective approach maintains high accuracy for important elements while reducing overall processing time through automated handling of less critical verification tasks.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system replaces manual mechanical verification with automated computational verification for routine question validation tasks. This substitution handles time-consuming repetitive verification automatically, reserving human verification for cases requiring judgment, thereby reducing overall processing time while maintaining accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9965472B2Content revision using question and answer generation

Publication Date: 2018.05.08 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A question/answer creation system is described. The system includes a memory device and a processor connected to the memory device. The processor is configured to import a document having a set of questions based on content in the document, automatically create a candidate question from the content in the document, automatically generate answers for the set of questions and the candidate question using the content in the document, present the set of questions, the candidate question, and the answers to a content creator for user verification of accuracy, and store a verified set of questions in the document. The verified set of questions includes at least one verified question from the set of questions and the candidate question.