Document Search Term Weighting for Accurate Prior Art Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document search systems require searcher expertise and time to perform efficient and accurate searches, particularly for invalidating patent grounds, lacking a simple and effective method for high-quality retrieval.
Innovation Solution
A document search system and method utilizing a database and processing portion that extracts terms, weights them based on reference data, and calculates similarity, incorporating morphological analysis and machine learning to enhance search efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual formation of retrieval expressions is used, then search accuracy can be improved through searcher experience and comprehension, but search time and operational difficulty increase significantly
Solution Approach 1:
The system performs automatic term extraction and weighting without requiring manual intervention from the searcher. The processing portion autonomously analyzes document data, identifies relevant terms, and calculates their weights based on document characteristics, eliminating the need for searchers to manually construct retrieval expressions while maintaining high search accuracy
Solution Approach 2:
The system automatically adjusts term weights as parameters based on document analysis results. By calculating weights according to document data characteristics and prosecution history information, the system dynamically optimizes search parameters without requiring manual adjustment, thereby reducing search time while preserving accuracy
2Measurement precision
If manual formation of retrieval expressions is used, then search accuracy can be improved through searcher experience and comprehension, but ease of operation deteriorates
Solution Approach 1:
The system performs automatic term extraction and weighting without requiring manual intervention from the searcher. The processing portion autonomously analyzes document data, identifies relevant terms, and calculates their weights based on document characteristics, eliminating the need for searchers to manually construct retrieval expressions while maintaining high search accuracy
Solution Approach 2:
The system divides the complex search process into independent automated modules: term extraction, weight calculation, and similarity computation. Each module operates independently on specific aspects of the search task, making the overall system easier to operate while maintaining the complexity needed for accurate results through automated processing
3Ease of operation
If automatic term extraction and weighting is used, then ease of operation and search speed improve, but search accuracy may deteriorate without searcher expertise
Solution Approach 1:
The system uses feedback from document analysis results to refine term weighting. By analyzing the relationship between terms and document characteristics, as well as incorporating prosecution history information, the system continuously adjusts weight calculations to ensure high accuracy while maintaining ease of operation through automated processing
Solution Approach 2:
The system combines multiple types of information (document data, term frequencies, document characteristics, prosecution history) to create a composite weighting mechanism. This composite approach integrates diverse data sources to achieve high search accuracy while maintaining automated operation, overcoming the limitation of simple automatic extraction
4Measurement precision
If comprehensive document analysis is performed, then search accuracy improves, but processing time and system complexity increase
Solution Approach 1:
The system extracts only the essential information needed for accurate searching from comprehensive document data. By identifying and isolating key terms and their relationships, the system performs detailed analysis only on relevant portions of documents rather than processing entire documents uniformly, thereby achieving high accuracy while managing processing time and system complexity
Solution Approach 2:
The system performs preliminary term extraction and weighting calculations during document indexing rather than during the actual search operation. This preliminary processing stores pre-computed term weights and document characteristics, allowing fast search operations without requiring complex real-time analysis, thus reducing system complexity during user interaction
Data Source
AI summary
A document search system that enables efficient document search regardless of the ability of a user is achieved. Document search is performed using a document search system in which database document data is stored. After first document data and second document data are input to the document search system, the document search system extracts a plurality of terms from the first document data. The extraction of the terms is performed using morphological analysis, for example. Next, the extracted terms are weighted on the basis of the second document data. For example, texts included in a document represented by the second document data are classified into first and second texts. Among the terms extracted from the first document data, the weight of the term included in the first text is set larger than the weights of the other terms. The classification of the texts can be performed in accordance with a rule basis or using machine learning. After that, the similarity of the database document data to the first document data is calculated on the basis of the weighted term.