Document Search Query Expansion for Accurate IP Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document search systems lack the capability for highly accurate document search, particularly for intellectual property-related documents, and require complex input methods.
Innovation Solution
A document search system utilizing a processing portion with transistors having a metal oxide or silicon in the channel formation region, combined with a database that generates weight dictionary and thesaurus data based on reference documents, and updates thesaurus data according to user input, to enhance search accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional keyword-based search systems are used, then search functionality is provided, but search accuracy is insufficient and user skill dependency is high
Solution Approach 1:
The patent introduces an automatic keyword extraction mechanism that acts as an intermediary between the user's input and the search system. The system automatically extracts keywords from user input text using natural language processing and thesaurus data, eliminating the need for users to manually select keywords. This intermediary process improves search accuracy while reducing user skill dependency.
Solution Approach 2:
The system performs self-service by automatically generating search keywords from user input without requiring user expertise in keyword selection. The automatic keyword extraction and weighting mechanisms enable the system to serve itself in preparing search queries, thereby improving both accuracy and ease of operation.
2Measurement precision
If manual keyword selection is required, then search control is precise, but operation complexity increases
Solution Approach 1:
The system automatically extracts keywords and generates search queries from user input text without requiring manual user intervention for keyword selection. This self-service approach maintains search precision through automated keyword extraction and weighting while significantly reducing operation complexity.
Solution Approach 2:
The system performs preliminary keyword extraction and weighting actions automatically before the search execution. By pre-processing the user input to extract and weight keywords automatically, the system prepares precise search queries without requiring complex user operations.
3Ease of operation
If simple keyword input is accepted, then ease of operation improves, but search accuracy deteriorates
Solution Approach 1:
The automatic keyword extraction mechanism serves as an intermediary that transforms simple user input into precise search keywords. The system processes the simple input text through NLP and thesaurus-based keyword extraction to generate accurate search queries, thereby maintaining both ease of operation and search accuracy.
Solution Approach 2:
The system changes parameters by automatically assigning weights to extracted keywords based on their importance and relevance. This parameter transformation from simple text input to weighted keyword sets enables the system to maintain input simplicity while achieving high search accuracy through automated keyword weighting.
Data Source
AI summary
Highly accurate document search, especially intellectual property-related document search, is achieved with a simple input method. A processing portion has a function of generating text analysis data from text data input to an input portion; a function of extracting a search word from words included in the text analysis data; and a function of generating first search data from the search word on the basis of weight dictionary data and thesaurus data. A memory portion stores second search data generated when the first search data is modified by a user. The processing portion updates the thesaurus data in accordance with the second search data.