Frame-Based Search for Concept Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Keyword-based search engines struggle to effectively retrieve records that express concepts, such as solving a problem, leading to large and off-topic search results, particularly in areas like technology scouting where specific keywords are inadequate.
Innovation Solution
The implementation of frame-based search and analysis techniques, which decompose concepts into roles and use linguistic rules to identify frame invocations in natural language discourse, allowing for the extraction and presentation of search results organized by relevant concepts like Benefit, Benefactor, and Instrument.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If keyword-based search is used to retrieve records, then the search coverage is broad, but the search result relevance deteriorates leading to large and off-topic results
Solution Approach 1:
The patent segments the search process into two distinct phases: first retrieving records using keyword-based search to ensure broad coverage, then applying frame-based analysis to segment and organize the results by conceptual roles (Benefit, Benefactor, Instrument, Problem). This segmentation allows the system to maintain both large result sets and high relevance by structuring results according to their functional roles rather than treating them as a flat list.
Solution Approach 2:
The patent introduces frame-based analysis as an intermediary processing layer between keyword search and result presentation. This intermediary extracts semantic roles from search results and reorganizes them into structured frames, acting as a mediator that transforms unstructured keyword matches into conceptually organized information while preserving both quantity and relevance.
2Measurement precision
If highly specific keyword terms are used to improve search precision, then the search result relevance improves, but the search coverage deteriorates returning too few results
Solution Approach 1:
The patent implements a dynamic search strategy where the system first performs a broad keyword search to capture all potentially relevant records, then dynamically applies frame-based analysis to identify and extract specific conceptual roles from the results. This dynamic two-stage approach allows the system to start with comprehensive coverage and then refine results based on semantic structure rather than relying solely on keyword specificity.
Solution Approach 2:
The patent adds a new dimension to search results by organizing them according to semantic roles (Benefit, Benefactor, Instrument, Problem) rather than just keyword matching. This dimensional transformation allows the system to maintain broad search coverage while improving effective precision through conceptual organization, as users can navigate results by role rather than by keyword relevance alone.
3Ease of operation
If frame-based analysis is applied to organize search results, then the information accessibility improves, but the processing complexity increases
Solution Approach 1:
The patent applies frame-based analysis as a preliminary organizational step that structures search results by semantic roles before presentation to the user. By performing this analysis upfront, the system creates a pre-organized result structure that improves accessibility without requiring complex real-time processing during user interaction, thus managing complexity through advance preparation.
Solution Approach 2:
The patent changes the organizational parameter of search results from keyword-based to role-based classification. This parameter change transforms the results into structured frames with defined roles (Benefit, Benefactor, Instrument, Problem), improving accessibility by allowing users to navigate results according to their information needs rather than keyword matches, while the complexity is managed through systematic role extraction.
Data Source
AI summary
A frame represents a concept with a set of roles and a set of linguistic rules. If a linguistic rule is satisfied, by a unit of natural language discourse (UNLD), the frame is invoked and a frame instance produced. A frame instance specifies how the UNLD, with particular values drawn from the UNLD, fulfills the roles of the frame. A frame-based search, of target content, is accomplished in response to a frame-based user query. The search result is comprised of records, where each record is a result of a match, of the frame-based query, at a location in the target content. If the frame-based query is implicit, a match requires only that the location of the target content invokes the appropriate frame. If the frame-based query is role-specific, in addition to invoking the appropriate frame, a query search term needs to be found in the value for a role of the frame instance produced.