Keyword Group Retrieval for Machine Tool Failure Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional keyword-based retrieval methods struggle to efficiently retrieve documents related to machine tool failures, as users may express the same phenomenon using different keywords, leading to increased retrieval complexity and inaccurate results.
Innovation Solution
A retrieving device and method that classifies document data based on the degree of matching of symbol strings, extracts related keywords, and manages multiple databases to retrieve documents using synonyms, allowing for efficient retrieval of related documents using a single keyword.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If users input different keywords for the same phenomenon, then retrieval coverage increases, but retrieval complexity increases and accuracy decreases
Solution Approach 1:
The system performs preliminary classification of document data into groups based on symbol string matching before retrieval operations. This pre-grouping allows the system to automatically handle multiple keywords for the same phenomenon without requiring users to construct complex retrieval expressions, thereby increasing retrieval coverage while maintaining simplicity.
Solution Approach 2:
The patent introduces keyword groups as an intermediary layer between user input and document retrieval. Instead of directly searching individual keywords, the system maps keywords to pre-defined groups, which then retrieve related documents. This intermediary mechanism handles synonym variation automatically, improving coverage without increasing user burden or system complexity.
2Adaptability or versatility
If users input different keywords for the same phenomenon, then retrieval coverage increases, but retrieval accuracy decreases
Solution Approach 1:
The system pre-classifies document data into groups based on symbol string matching before retrieval operations. This pre-grouping allows the system to automatically handle multiple keywords for the same phenomenon without requiring users to construct complex retrieval expressions, thereby increasing retrieval coverage while maintaining simplicity.
Solution Approach 2:
The patent introduces keyword groups as an intermediary layer between user input and document retrieval. Instead of directly searching individual keywords, the system maps keywords to pre-defined groups, which then retrieve related documents. This intermediary mechanism handles synonym variation automatically, improving coverage without increasing user burden or system complexity.
3Measurement precision
If complex logical operation expressions are used for retrieval, then retrieval accuracy improves, but ease of operation decreases
Solution Approach 1:
The system automatically performs the retrieval operation using pre-defined keyword groups without requiring user intervention for complex logical expressions. When a user inputs a keyword, the system self-service retrieves all documents associated with that keyword's group, eliminating the need for users to construct OR/AND expressions while maintaining high retrieval accuracy.
Solution Approach 2:
The patent introduces keyword groups as an intermediary layer between user input and document retrieval. Instead of directly searching individual keywords, the system maps keywords to pre-defined groups, which then retrieve related documents. This intermediary mechanism handles synonym variation automatically, improving coverage without increasing user burden or system complexity.
4Adaptability or versatility
If the number of retrieval operations increases, then retrieval coverage improves, but loss of time increases
Solution Approach 1:
The system performs preliminary classification of document data into groups based on symbol string matching before retrieval operations. This pre-grouping allows the system to automatically handle multiple keywords for the same phenomenon without requiring users to construct complex retrieval expressions, thereby increasing retrieval coverage while maintaining simplicity.
Solution Approach 2:
The patent merges multiple retrieval operations into a single unified process by using keyword groups. Instead of performing separate retrieval operations for each keyword variation, the system combines them into one group-based retrieval operation, significantly reducing retrieval time while maintaining comprehensive coverage.
Data Source
AI summary
A retrieving device includes: a classifying unit that classifies document data made up of a plurality of items on the basis of a degree of matching of a first item in which a combination of one or more symbol strings is described in a database in which the document data is stored; and an extracting unit that extracts a group of keywords included in a second item from pieces of document data in a same group classified by the classifying unit as related words for retrieval. Moreover, when the retrieving device is implemented as a distributed system on a network, it is possible to create related words for a plurality of machines and to store the related word data and to enable a plurality of users to use the distributed system.