Automated Privileged Information Redaction in E-Discovery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The high cost and complexity of manual review in electronic discovery processes, particularly in identifying and redacting privileged information from vast amounts of electronic documents in litigation, lead to inefficiencies and potential inadvertent disclosure of sensitive information.

Innovation Solution

An automated system and method for identifying and redacting privileged information in email threads by determining the last-in-time communication and marking or redacting accordingly, using a computer-implemented process with a server architecture that includes modules for privilege determination and output redaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual review is used to identify and redact privileged information, then accuracy in protecting privileged information is improved, but time consumption and cost increase significantly

Engineering Contradiction:

Improveaccuracy in protecting privileged informationVSAvoidtime consumption and cost

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent introduces an automated review system as an intermediary between the voluminous email data and human reviewers. This system uses computer algorithms to pre-analyze emails, identify potentially privileged communications, and rank them by privilege likelihood, thereby filtering the data before human review and reducing both time and cost while maintaining accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the purely mechanical manual review process with an automated computer-based system that uses algorithms to analyze email content, identify privileged information, and rank emails. This substitution reduces human labor time and cost while maintaining or improving the accuracy of privileged information identification

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual review of all electronic documents is conducted, then completeness of discovery is improved, but cost and resource expenditure increase

Engineering Contradiction:

Improvecompleteness of discoveryVSAvoidcost and resource expenditure

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent applies partial action by not requiring manual review of all electronic documents. Instead, the automated system performs initial screening and ranking, and only emails flagged as potentially privileged are subjected to detailed human review. This partial approach maintains completeness of discovery while significantly reducing costs and resource expenditure

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If automated systems are used to reduce review time, then productivity is improved, but risk of inadvertent disclosure of privileged information increases

Engineering Contradiction:

Improvereview time efficiencyVSAvoidrisk of inadvertent disclosure

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent incorporates feedback mechanisms where the automated system's outputs are reviewed and validated by human experts. The system learns from human corrections and adjustments, continuously improving its accuracy. This feedback loop ensures that automated processing maintains high reliability and minimizes the risk of inadvertent disclosure while preserving productivity gains

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS8752204B2Identifying and redacting privileged information

Publication Date: 2014.06.10 GOOGLE LLC

AI summary

Systems and methods for identifying and redacting privileged information automatically in electronic discovery documents such as emails are disclosed. In reviewing documents for discovery review, some documents have both privileged and non-privileged information. Significant cost savings are achieved in conducting electronic discovery by automatically identifying and redacting privileged content while preserving non-privileged information for production.