Social Network Entity Discrimination via Context Overlap
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automating the generation of social networks is challenging due to difficulties in discriminating between entities with the same name across different documents, as existing methods rely heavily on human inference and intuition.
Innovation Solution
A computer-implemented system that uses social contexts to differentiate entities by analyzing digitally encoded documents, identifying significantly overlapping social contexts to determine if entities refer to the same individual, and generating a graphical network of entities and associations, while also computing risk factors based on the network structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated methods are used to generate social networks, then productivity is improved, but measurement precision deteriorates due to difficulty in discriminating entities with the same name
Solution Approach 1:
The patent introduces social context as an intermediary element to mediate entity discrimination. Instead of directly comparing entity names, the system extracts and compares social contexts (associations with other entities) as a mediator to determine entity identity, thereby enabling automated discrimination with high precision
Solution Approach 2:
The system implements feedback mechanisms by using extracted social contexts to refine entity identification. The entity matcher uses social context overlap information to feedback and adjust entity matching decisions, improving discrimination accuracy through iterative refinement
2Measurement precision
If manual methods are used to derive social networks, then measurement precision is improved through human inference, but productivity deteriorates due to extensive manual work
Solution Approach 1:
The system enables self-service by automating the entity discrimination process that previously required human inference. The automated entity matcher uses social context comparison to perform discrimination tasks independently, eliminating the need for manual intervention while maintaining high accuracy
Solution Approach 2:
The patent replaces the mechanical human inference process with an automated computational system. Instead of manual analysis of entity relationships, the system uses automated extraction of social contexts and algorithmic comparison to substitute human cognitive processes with machine-based operations
3Ease of operation
If entity names are used directly for identification, then ease of operation is improved, but measurement precision deteriorates due to similarly named entities referring to different people
Solution Approach 1:
The patent transitions from one-dimensional entity name matching to multi-dimensional identification by incorporating social context as an additional dimension. Instead of relying solely on entity names, the system compares associations with other entities, adding a new dimension of information for discrimination that resolves ambiguities of similarly named entities
Data Source
AI summary
A method and system for automated generation of social networks. A graphical user interface receives a user query for an entity of interest, and outputs a graphical network showing entities and associations related to the entity of interest. A search engine interface transmits the query to a search engine, and receives references to documents. A named entity extractor downloads a selection of the documents, and generates a list of named entities referenced in the downloaded documents. A network inference module receives each list of named entities, and generates associations between the named entities in each list. An entity matcher operates on the associations to consolidate them in instances wherein differently named entities are determined to be the same named entity, and provides a consolidated list of named entities and associations to the user interface for display as a graphical network.