FAQ Database Routing for Accurate Automated Inquiry Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic answering technologies, or bots, struggle to provide accurate and user-intentioned responses to frequently asked questions, often requiring human intervention due to limitations in morphological analysis and database matching processes.
Innovation Solution
An information processing apparatus that performs morphological analysis on user inquiries, matches the analyzed morphemes with databases to determine the appropriate answer source, and switches to human interaction when bot responses are inadequate, utilizing a user authentication system to enhance response accuracy and relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single FAQ database is used for automatic answering, then the system structure is simple, but the answer accuracy and coverage are insufficient for unclear or diverse questions
Solution Approach 1:
The patent divides the FAQ system into multiple databases segmented by category or topic. Each database contains FAQs specific to its category, allowing the system to select the most relevant database based on the user's question. This segmentation improves answer accuracy by reducing the search space and focusing on category-specific FAQs, while the modular structure manages complexity through organized data architecture.
Solution Approach 2:
The patent creates a universal FAQ system that handles multiple types of questions across different categories through a single integrated framework. The system uses a category determination unit that can universally classify various user questions and route them to appropriate databases, making the system adaptable to diverse inquiry types without requiring separate systems for each category.
2Productivity
If the bot answers all questions automatically, then the productivity is high, but the reliability decreases when questions are unclear or not covered
Solution Approach 1:
The patent implements a feedback mechanism where the determination unit evaluates whether the selected FAQ database contains a suitable answer. When no appropriate answer is found or the question is determined to be unclear, the system provides feedback to transfer to human operator support. This feedback loop ensures high productivity for clear, covered questions while maintaining reliability by escalating uncertain cases to humans.
Solution Approach 2:
The system dynamically adjusts its operation mode based on the question characteristics. For clear, well-covered questions, it operates in automatic bot mode for high productivity. For unclear or uncovered questions, it dynamically switches to human operator mode for reliable handling. This dynamic adaptation resolves the contradiction by allowing the system to optimize for speed when possible and for accuracy when necessary.
3Adaptability or versatility
If multiple databases are searched exhaustively, then the answer coverage is comprehensive, but the processing time increases
Solution Approach 1:
By segmenting FAQs into category-specific databases, the system reduces the effective search space. Instead of searching all databases for every question, the determination unit first identifies the relevant category and searches only that specific database. This maintains comprehensive coverage within the appropriate category while significantly reducing processing time by avoiding unnecessary searches in unrelated databases.
Solution Approach 2:
The determination unit performs preliminary classification of the user's question to identify the relevant category before conducting the actual FAQ search. This preliminary action prepares the system by pre-selecting the appropriate database, ensuring comprehensive coverage of the relevant topic area while eliminating the time cost of searching unrelated databases.
Data Source
AI summary
An information processing apparatus outputs answer information corresponding to inquiry information that is input. The information processing apparatus includes a memory and circuitry. The memory is configured to store a plurality of databases each having at least a first field and a second field. The circuitry is configured to: perform morphological analysis on the inquiry information, to divide the inquiry information into morphemes; perform a first matching process based on the morphemes and the first field of each of the plurality of databases, to determine whether to adopt the database as an extraction source from which the answer information is to be extracted; and perform a second matching process based on the morphemes and the first field of the database, which is determined to be adopted as the extraction source, to output, as the answer information, data in the second field corresponding to data in the first field.