Document Retrieval Using Model-Specific Similar Word Dictionaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in retrieving desired documents related to industrial machines and equipment due to the use of unique technical terms, which are not recognized in keyword searches, especially when different models and manufacturers employ distinct terminology.
Innovation Solution
A document retrieval apparatus and method that includes a storage system for documents and dictionaries, allowing for the selection of a model, specification of corresponding documents and dictionaries, extraction of search keywords from user queries using these dictionaries, and retrieval of relevant documents, enabling efficient retrieval of target documents without requiring users to be aware of specific model terms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a keyword search is used to retrieve documents, then the search process is simple and fast, but the user cannot find desired descriptions when the document uses different technical terms than the search keyword
Solution Approach 1:
The patent introduces a similar word dictionary as an intermediary between the user's search keyword and the document content. The dictionary stores relationships between different technical terms (e.g., mapping 'xxxx' to 'yyyy'), allowing the search system to automatically expand keywords into multiple equivalent terms. This mediator resolves the contradiction by maintaining simple keyword-based search while improving accuracy through automatic term substitution.
2Adaptability or versatility
If a similar word dictionary is provided for each category (field), then the retrieval system can handle general technical terms, but it fails when terms differ between models and manufacturers
Solution Approach 1:
The patent segments the similar word dictionary into multiple model-specific dictionaries, each tailored to the terminology of a particular model or manufacturer. Instead of using a single generic dictionary, the system selects and applies the appropriate dictionary based on the target model, thereby maintaining both broad category coverage and model-specific accuracy.
3Ease of operation
If the user inputs queries in natural language, then the input is easy and intuitive, but the system cannot retrieve documents when the document uses different terminology
Solution Approach 1:
The patent performs preliminary action by pre-building model-specific similar word dictionaries that map various user input terms to the actual terminology used in documents. Before the search executes, the system automatically expands the user's natural language query using the appropriate dictionary, converting intuitive but imprecise input into accurate search terms without requiring the user to learn model-specific vocabulary.
Data Source
AI summary
A document retrieval apparatus includes: a storage unit that stores documents and dictionaries applied to a model, a correspondence between a model and documents applied to the model, and a correspondence between a document and dictionaries applied to the dictionary; a model selecting unit that selects a model; a search target document specifying unit that specifies documents applied to the model selected by the model selecting unit as search target documents; a dictionary specifying unit that specifies dictionaries applied to the search target document; a query receiving unit that inputs a query; a search keyword extraction unit that extracts a search keyword group by applying the dictionary specified by the dictionary specifying unit to the query; a retrieving unit that retrieves the search target document using the search keyword group; and a retrieval result presenting unit that displays search results retrieved by the retrieving unit.