E-discovery System Identifying Latent Custodians
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current e-discovery processes are inefficient and costly due to the manual and time-consuming identification of second-order documents and document custodians, which involves analyzing vast amounts of data and complex relationships within organizations, often leading to the loss of relevant evidence and increased legal risks.
Innovation Solution
A computer-implemented method that uses deep semantic, temporal, and spatial document relationships to automatically identify second-order documents and custodians by clustering first-order documents and custodians based on masked terms, generating ranked lists, and applying a litigation distance metric to determine relevant custodians, thereby reducing the scope of discovery and preserving evidence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of second-order documents and custodians is performed, then comprehensive evidence discovery is achieved, but time consumption and cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical review processes with automated computational systems. Machine learning models and algorithms automatically analyze document relationships, identify custodians, and rank relevance, substituting human analysts with computational processing that achieves comparable or superior precision without proportional time increases
Solution Approach 2:
The patent introduces intermediate computational layers including document embedding models, similarity calculation algorithms, and ranking systems that mediate between raw document data and final identification results. These intermediaries process and structure information to enable efficient automated discovery while maintaining comprehensive evidence identification
2Measurement precision
If manual analysis of complex organizational relationships is performed, then accurate custodian identification is achieved, but process complexity and cost increase
Solution Approach 1:
The patent replaces complex manual analysis of organizational relationships with automated graph-based algorithms and machine learning models that process document metadata, communication patterns, and relationship structures to identify custodians accurately without requiring manual process complexity
Solution Approach 2:
The patent transforms unstructured relationship data into structured parameters including document similarity scores, custodian relevance rankings, and relationship strength metrics. These quantified parameters enable automated processing while maintaining identification accuracy by converting qualitative relationship assessment into measurable computational variables
3Reliability
If comprehensive document review is conducted to avoid evidence loss, then evidence preservation is improved, but processing efficiency decreases
Solution Approach 1:
The patent applies partial action by using automated systems to perform comprehensive initial screening of all documents, then focusing detailed analysis only on high-probability candidates identified through ranking algorithms. This approach ensures no evidence is missed while avoiding unnecessary processing of clearly irrelevant materials, thereby maintaining reliability while improving efficiency
Solution Approach 2:
The patent performs preliminary automated processing including document ingestion, metadata extraction, embedding generation, and initial relevance scoring before human review or final decision-making. This preliminary action prepares and filters data in advance, ensuring comprehensive coverage for evidence preservation while reducing the scope and complexity of subsequent processing
Data Source
AI summary
Discovering second-order documents and latent custodians in an e-discovery system is provided. A list of first-order documents and document custodians within a base state of the e-discovery system are identified based on a plurality of terms corresponding to a meet and confer practice for a legal matter instance. The plurality of terms is masked within the first-order documents. The first-order documents having the plurality of terms masked are divided into groups. A list of second-order documents is generated from a group of documents. A list of second-order document custodians is generated based on corresponding custodian relationships to second-order documents. Finally, each second-order document custodian in the list of second-order document custodians that has a corresponding rank exceeding a defined rank threshold level is identified as an official document custodian in the e-discovery system.