Entity Relationship Discovery via Co-occurrence Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tools are inadequate for effectively discovering and managing entity-based data and relationships.
Innovation Solution
The system processes a collection of documents to identify co-occurring mentions of entities, visually representing these relationships in a user interface with graphical links that provide access to evidence within the documents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional information gathering tools are used, then basic information retrieval is possible, but effective discovery and management of entity-based data and relationships is not achieved
Solution Approach 1:
The system segments the complex task of relationship discovery into distinct operational phases: (1) automatic relationship detection from documents, (2) visual representation of relationships through graphical interfaces, (3) evidence retrieval and presentation. This segmentation allows users to interact with simplified, purpose-specific interfaces for each phase rather than navigating a monolithic complex system.
Solution Approach 2:
The patent introduces an intermediary graphical user interface layer that mediates between the complex underlying document processing systems and the user's information needs. This intermediary presents relationships as visual graphs with interactive elements, translating complex computational relationships into intuitive visual forms that are easy to explore and manage.
2Ease of operation
If graphical representation of relationships is implemented, then ease of exploring entity relationships is improved, but device complexity increases
Solution Approach 1:
The patent extracts the relationship management functionality from the broader information processing system and presents it as a dedicated graphical interface module. By separating the visual representation and exploration functions into a distinct interface layer, the system manages complexity through modular design while maintaining ease of use through specialized graphical tools.
Solution Approach 2:
The system transitions from text-based document representation to a two-dimensional graphical representation of relationships. This dimensional change allows complex relationship networks to be visualized spatially, making them easier to explore and understand without increasing the underlying computational complexity of the system.
3Productivity
If automatic processing of documents to identify relationships is implemented, then productivity is improved, but measurement precision of relationship identification may be compromised
Solution Approach 1:
The system incorporates feedback mechanisms where users can review automatically identified relationships and provide corrections or confirmations. This feedback loop allows the system to maintain high productivity through automated processing while improving measurement precision by incorporating user validation and refinement of relationship identifications.
Solution Approach 2:
The patent implements partial automation where the system automatically processes documents to generate initial relationship lists, but allows users to selectively review and refine specific relationships. This partial action approach maintains productivity benefits of automation while ensuring precision through targeted human review of critical relationships.
Data Source
AI summary
Connections among two different entities are identified by processing a collection of documents to identify one or more documents that contain co-occurring mentions of each of the two different entities. This relationship may be graphically displayed in a user interface with an icon or the like for each of the two entities, along with a graphical link interconnecting the entities. The graphical link can be an active element of the user interface that responds to user interactions by providing access to evidence within the collection of documents that substantiates the connection between the two entities. In one aspect, a search input form field in a user interface may be used to explicitly request documents that substantiate a relationship between two entities. In another aspect, a user may ground entity mentions by explicitly selecting documents that mention an entity of interest.