Privacy-Aware Data Discovery with AI Entity Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data privacy and security systems face challenges in identifying sensitive data, determining data ownership, and enforcing data policies across distributed systems, particularly in identifying entities and configuring policies specific to their needs.
Innovation Solution
A privacy-aware data discovery process utilizing multiple datasource processors and an AI engine to generate object summaries, which include entity mappings and attribute groups, with a global entity resolver to map local entities to global entities, and policy engines to evaluate and enforce security and privacy policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is stored and processed in distributed systems, then data accessibility and processing capability are improved, but data privacy and security risks increase
Solution Approach 1:
The patent segments data into structured components (entities, attributes, relationships) and processes them through modular AI components (text extractor, layout extractor, object classifier, attribute extractor, local entity resolver). This segmentation enables granular privacy control and security enforcement at each processing stage while maintaining overall system productivity.
Solution Approach 2:
The patent introduces an intermediary privacy-aware data discovery process that acts as a mediator between distributed data sources and policy enforcement mechanisms. This intermediary layer identifies sensitive data, determines data ownership, and enforces privacy policies without compromising the underlying distributed system's processing capabilities.
2Productivity
If automated AI processing is used to identify sensitive data, then processing efficiency is improved, but system complexity increases
Solution Approach 1:
The complex AI processing system is divided into five distinct modular components, each performing a specific function (text extraction, layout analysis, object classification, attribute extraction, entity resolution). This segmentation reduces system complexity by making each component independent and manageable while maintaining high processing efficiency through parallel operation.
Solution Approach 2:
The patent creates a universal AI processing framework that can handle multiple data types and formats through a single integrated system. The modular components work together to process diverse data sources (documents, images, structured data) using the same pipeline, reducing the need for multiple specialized systems and thereby reducing overall complexity.
3Measurement precision
If data is analyzed in detail to determine sensitivity and ownership, then privacy protection accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary actions by extracting and structuring data characteristics (text, layout, objects, attributes) before privacy evaluation. This preliminary structuring enables faster and more accurate privacy determination later, as the data is already organized in a format suitable for sensitivity analysis and ownership determination.
Solution Approach 2:
The patent segments the privacy analysis process into distinct stages (text extraction, layout analysis, object classification, attribute extraction, entity resolution), allowing parallel processing of different data aspects. This segmentation maintains high measurement precision for privacy protection while reducing overall processing time through concurrent execution of independent analysis tasks.
Data Source
AI summary
Datasource processors may communicate with an artificial intelligence (AI) engine in order to generate, in parallel, object summaries from datasource objects received from datasources. Each object summary may include an object identifier, one or more local entities, and a mapping from each of the one or more local entities to one or more attributes. A global entity resolver may augment the object summaries by mapping each of the local entities to a global entity. Policy engines may evaluate, in parallel, the object summaries with respect to a security and/or privacy policy. If a security and/or privacy violation is recognized, a remediation measure may be applied in connection with the datasource object for which the security and/or privacy violation exists.