FAQ Creation Assist Apparatus for User Support History Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for creating FAQs from user support histories are labor-intensive and costly, relying heavily on manual correction and maintenance, with automatically generated FAQs often requiring significant managerial effort and not meeting practical usability standards.
Innovation Solution
A knowledge information creation assist apparatus that filters and groups user support logs to extract relevant questions, allowing for manual creation of FAQs through a user interface, reducing the workload by automating the filtering of unnecessary utterances and classifying questions using a classification learner for efficient grouping and display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated methods are used to generate FAQs from user support histories, then productivity is improved, but manufacturing precision deteriorates because the automatically generated FAQs do not meet usability standards
Solution Approach 1:
The system performs preliminary actions by automatically extracting questions and grouping them before the FAQ creation process. The question utterance extraction section pre-processes user support histories to identify and extract question sentences, and the grouping control section pre-groups these questions by topic. This preliminary automation reduces the workload while maintaining quality through structured preparation.
Solution Approach 2:
The system introduces an intermediary structure between automated extraction and final FAQ creation. The grouping control section acts as an intermediary by organizing extracted questions into topic-based groups with representative questions. This intermediate structuring allows automated processing to feed into manual review more effectively, bridging the gap between automation and quality control.
2Manufacturing precision
If manual correction and maintenance are used to ensure FAQ quality, then manufacturing precision is improved, but productivity deteriorates due to labor-intensive processes
Solution Approach 1:
The system segments the FAQ creation process into distinct phases: automated question extraction, automatic grouping by topic, and selective manual review. The question utterance extraction section handles extraction automatically, the grouping control section handles classification automatically, and only the final review and answer creation require manual intervention. This segmentation reduces overall manual workload while maintaining quality.
Solution Approach 2:
The system enables self-service automation for the labor-intensive extraction and grouping tasks. The question utterance extraction section automatically identifies question sentences from user support histories without manual intervention. The grouping control section automatically classifies these questions into topic groups using classification models. This self-service automation handles the repetitive preliminary work, freeing human operators to focus on higher-value quality assurance tasks.
3Manufacturing precision
If all utterance sentences are processed manually, then manufacturing precision is improved, but productivity deteriorates due to the large volume of data
Solution Approach 1:
The system extracts only the relevant question sentences from the full user support histories, separating them from unnecessary utterances. The question utterance extraction section uses natural language processing to identify and extract only the question portions, discarding irrelevant conversational filler. This extraction focuses manual review efforts on only the essential content, improving both efficiency and precision.
Solution Approach 2:
The system replaces manual mechanical review of all utterances with automated computational processing. The question utterance extraction section uses automated text analysis to identify question sentences, and the grouping control section uses classification models to categorize them. This substitution of mechanical manual review with automated processing handles the large volume of data efficiently, reserving manual effort for verification rather than initial processing.
Data Source
AI summary
A knowledge information creation assist apparatus allowing knowledge information such as FAQs to be created from user support histories accumulated in the past with a reduced workload. A knowledge information creation assist apparatus performs processing of removing at least one unnecessary utterance sentence not related to questioning from a plurality of user support histories including input questions or processing of extracting at least one utterance sentence related to questioning from the user support histories and grouping processing of classifying the user support histories output as the result of the processing into a plurality of question groups according to a predetermined classification model. The knowledge information creation assist apparatus displays group information of each of the question groups on a question group creation screen and performs control to produce knowledge information in response to input performed by a creator to one of the question groups selected on the question group creation screen.