Biology Data Mining via Morphological Segmentation and Entity Tagging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biology-related documents are complex and difficult for novices to access and search due to their professional and abstruse nature, making it challenging to retrieve relevant information using general search terms.
Innovation Solution
A method involving a server that divides documents into morphological segments, parses named biological entities, tags them, and generates a database for efficient searching, allowing users to input search terms based on these entities and segments to mine for relevant documents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general search terms are used to search biology-related documents, then the search process is simple, but the search accuracy is low and relevant information cannot be retrieved effectively
Solution Approach 1:
The system performs preliminary actions by automatically dividing biology-related documents into morphological segments, parsing named biological entities, and tagging them before the search process. This preprocessing creates a structured database with annotated entities and segments, enabling accurate search without requiring complex user input. The tagging component assigns tags to named entities and morphological segments in advance, so when users search, they can retrieve relevant information precisely using simple terms.
Solution Approach 2:
The system introduces an intermediary layer between the user's simple search terms and the complex biology documents. The mining component acts as a mediator that receives simple search terms, queries the pre-processed database with tagged entities and segments, and retrieves relevant documents. This intermediary structure allows users to search with general terms while the system translates these into precise queries against the structured, tagged database, resolving the contradiction between search simplicity and accuracy.
2Loss of information
If biology-related documents are processed with detailed segmentation and tagging, then information retrieval accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs document segmentation, entity parsing, and tagging as preliminary actions during an offline preprocessing phase. By completing these computationally intensive tasks before the actual search operation, the system avoids time-consuming processing during user queries. The pre-constructed database with tagged morphological segments and named entities enables fast, efficient retrieval without repeating the heavy processing work, thus reducing perceived processing time while maintaining high information retrieval effectiveness.
Solution Approach 2:
The system segments biology-related documents into morphological segments and further identifies named biological entities within them. This hierarchical segmentation structure organizes the complex information into manageable units that can be efficiently stored and queried. By dividing documents into segments and tagging specific entities, the system enables targeted searches that only process relevant portions of the database, reducing overall processing time while improving information retrieval precision.
3Adaptability or versatility
If a comprehensive database with tagged entities and segments is created, then search capability is enhanced, but database construction complexity increases
Solution Approach 1:
The system segments the database construction process into distinct functional components: a morpheme divider that splits documents into morphological segments, a parsing component that identifies named biological entities, and a tagging component that assigns tags to segments and entities. This modular segmentation of the construction process makes the complex task manageable and allows each component to be optimized independently, enhancing search capability while controlling construction complexity through structured modularity.
Solution Approach 2:
The created database serves multiple functions: it stores the original biology-related documents, contains divided morphological segments, identifies named biological entities, and provides tagged structures for various search operations. This multi-functional database construction, while complex, enables versatile search capabilities including entity-based search, segment-based search, and combination queries, justifying the construction complexity through the broad adaptability and search versatility it provides.
Data Source
AI summary
In one example embodiment, a server may divide documents into a plurality of morphological segments, parse, from the plurality of morphological segments, a plurality of named biological entities, tag the plurality of named biological entities and the plurality of morphological segments, generate a database that includes the tagged named biological entities and the tagged morphological segments, receive a first search term including one or more of the tagged named biological entities or one or more of the tagged morphological segments, search the database for at least one result phrase that includes at least one occurrence of the first search term, receive an input to retrieve a second search term including at least one morphological segment from one of the result phrases, store the second search term as a mining search term, and mine for the one or more documents based on the mining search term.