Entity Context Obfuscation via Correlation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing recommender systems fail to effectively obfuscate entity context in sensory environments, leading to unauthorized sharing of personal information due to lack of privacy protection.

Innovation Solution

A computer-implemented method and system that analyzes entity data and sensory environment data from multiple sources to determine a correlation score, recommending features to obfuscate the entity context based on this score, thereby protecting privacy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If multiple sensors and surveillance devices are deployed to monitor and track entities, then the ability to detect and track entities is improved, but privacy protection deteriorates due to unauthorized sharing of personal information

Engineering Contradiction:
Improveentity detection capabilityVSAvoidprivacy violation
Core Design Contradiction:
Difficulty of detecting and measuringVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary analysis of entity data and sensory environment data before actual tracking occurs. It proactively identifies features that could lead to personally identifiable information and recommends obfuscation measures in advance, preventing privacy violations before they happen rather than reacting after detection

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The recommendation system acts as an intermediary between the surveillance/detection system and the entity being monitored. It analyzes the correlation between entity features and sensory environment data, then provides recommendations to obfuscate identifying features, mediating between detection needs and privacy protection

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If entity context information is made accessible for analysis and tracking, then tracking accuracy is improved, but information security deteriorates due to dissemination of personally identifiable information

Engineering Contradiction:
Improvetracking accuracyVSAvoidinformation security
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The system applies partial action by selectively obfuscating only those features that correlate with personally identifiable information, while leaving other non-identifying features accessible for tracking purposes. This maintains sufficient tracking accuracy while protecting information security by removing only the excessive identifying portions

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If comprehensive entity data is collected from multiple sources, then entity characterization is improved, but the risk of unauthorized information sharing increases

Engineering Contradiction:
Improveentity characterization accuracyVSAvoidunauthorized information sharing
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system extracts and removes personally identifiable information from the comprehensive entity data set. By analyzing correlations between entity features and sensory environment data, it identifies and extracts only the identifying portions that need to be protected, while retaining the rest of the comprehensive data for reliable entity characterization

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3001347B1Systems and methods for providing recommendations to obfuscate an entity context
Publication Date: 2017.08.23 WIPRO LTD
  • EP3001347B1 patent drawingFigure 1(a)
  • EP3001347B1 patent drawingFigure 1(b)
  • EP3001347B1 patent drawingFigure 2

AI summary

Systems and methods for providing recommendations to obfuscate an entity context in a sensory environment are described. In one implementation, the method comprises receiving (202) entity data and sensory environment data from a plurality of sources. The entity data is analyzed (204) to obtain categorized entity data. The categorized entity data comprises a plurality of features indicating characteristics of the entity context. The sensory environment data is analyzed (206) to obtain categorized sensory environment data. A correlation score is determined (208) for each of the plurality of features by correlating the categorized entity data and the categorized sensory environment data. At least one of the plurality of features is recommended (210) based on the correlation score, to obfuscate the entity context in the sensory environment.