Social Graph Clustering for Selective Content Blocking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parental control software cannot effectively limit access to specific suspicious objects on social networks without restricting access to the entire social network, failing to protect users, especially children, from malicious content and actors.
Innovation Solution
A system and method that retrieves a social graph for a user profile, identifies clusters of user profiles with fewer connections, determines suspicious objects linked to these profiles, and limits access to those objects by storing them in a database of forbidden objects, thereby preventing exposure to malicious content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If parental control software limits access to the entire social network, then user security is improved, but user accessibility to the social network deteriorates
Solution Approach 1:
The patent segments the social network into individual objects (profiles, groups, content elements) and applies parental control selectively to specific suspicious objects rather than blocking the entire network. This allows children to access most of the social network while being protected from identified harmful content and users.
Solution Approach 2:
The patent implements local quality control by applying different access rules to different objects within the social network. Suspicious objects are identified and blocked individually, while non-suspicious objects remain accessible, creating localized security measures rather than global restrictions.
2Object-affected harmful factors
If parental control software blocks all suspicious objects, then exposure to malicious content is reduced, but the complexity of identifying and managing forbidden objects increases
Solution Approach 1:
The patent performs preliminary analysis of the social network structure before implementing blocking measures. By pre-identifying suspicious objects through automated analysis of user profiles, groups, and content elements, the system prepares a list of forbidden objects in advance, simplifying the subsequent blocking process and reducing manual intervention complexity.
Solution Approach 2:
The patent implements self-service mechanisms where the system automatically identifies, analyzes, and blocks suspicious objects without requiring continuous manual configuration by parents. The automated detection and classification of harmful content reduces the burden on users to manually manage forbidden objects.
Data Source
AI summary
Disclosed are systems and methods for limiting access of a user profile to dangerous content in a social network service. The described system produces a social graph for a given user profile in the social network service, and identifies clusters of objects (e.g., other user profiles, contents) within the social graph. The described system analyzes whether certain objects in the social graph should be characterized as suspicious based on their clustering and on a database of known forbidden objects. The described system may further learn and add unknown objects to the database of forbidden objects.