Morphological Analysis for Flexible User Input in Information Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information provision systems require users to limit their inputs to pre-defined answer candidates or request contents, leading to suboptimal response contents for users.
Innovation Solution
An information provision system that performs morphological analysis on user input text and pre-stored question text strings, calculates scores based on the analysis, and displays question text strings that satisfy predetermined conditions, allowing users to easily acquire desired knowledge data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the system requires users to limit inputs to pre-defined answer candidates or request contents, then the system structure remains simple and manageable, but the user cannot obtain desired response contents when their input does not match the pre-defined options
Solution Approach 1:
The patent introduces morphological analysis as an intermediary processing layer between user input and the question database. Instead of directly matching user input against pre-defined questions, the system analyzes the morphological structure of the input text and compares it with stored question patterns. This intermediary analysis enables flexible user input while maintaining a structured database, resolving the contradiction between adaptability and system complexity.
Solution Approach 2:
The system changes the parameter of question matching from exact string matching to morphological structure matching. By storing and comparing morphological analysis results (such as part-of-speech tags, grammatical structures, and semantic relationships) rather than raw text strings, the system allows users to input questions in natural language variations while still matching them against the pre-defined question database, thereby improving user input flexibility without proportionally increasing system complexity.
2Measurement precision
If the system performs detailed analysis on user input to improve response accuracy, then the quality of response content improves, but the processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary morphological analysis to all questions stored in the database before runtime operations. By pre-processing and storing the morphological structures of standard questions in advance, the system avoids performing complete morphological analysis on every user interaction. During actual operation, the system only needs to compare the user's input against the pre-analyzed question patterns, significantly reducing processing time while maintaining high accuracy in understanding user intent.
3Adaptability or versatility
If the system stores more question candidates to cover more user needs, then the coverage of desired responses improves, but the difficulty of finding the optimal answer increases
Solution Approach 1:
The patent replaces manual or simple keyword-based matching mechanisms with automated morphological analysis and scoring systems. The system automatically analyzes the morphological structure of user input, compares it with stored question patterns, calculates similarity scores, and ranks potential matches. This automated mechanism handles the complexity of selecting the optimal answer from numerous candidates, allowing the system to store a comprehensive question database without proportionally increasing the difficulty of answer selection, as the morphological comparison and scoring process is performed automatically.
Data Source
AI summary
An object of the present invention is to provide an information provision system and an information provision method by which a user is able to easily acquire desired knowledge data. In an information provision system 1, a suggestion server 400 stores question text strings associated with response contents in advance, receives an input text string input by a user 10 by using a user terminal 100, performs morphological analysis for the input text string and each of the question text strings, calculates a score indicating to what extent each of the question text strings is related to the input text string based on results of the morphological analysis for the question text strings and a result of the morphological analysis for the input text string, and causes the user terminal 100 to display at least one of the question text strings. The score of the at least one of the question text strings satisfies a predetermined condition.