Short Message Normalization and Threaded E-Discovery Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in civil and criminal litigation is the vast amount of irrelevant digital data on electronic devices, making it difficult to identify relevant evidence, especially with the rise of short communications and social media.
Innovation Solution
A system that imports messages from multiple devices and applications, normalizes and combines them, allowing for search queries with boolean logic and proximity indicators, and displays relevant messages in chronological order, with features like emoji and keyword clouds, and single conversation threads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If messages from multiple devices and applications are collected and stored, then the quantity of available evidence increases, but the complexity of managing and searching through the data increases
Solution Approach 1:
The system segments the large volume of collected messages by organizing them into individual conversation threads, grouping related messages together. This segmentation transforms the overwhelming bulk of data into manageable, contextually-related units that are easier to navigate and review during e-discovery processes.
Solution Approach 2:
The system introduces an intermediary processing layer that normalizes messages from different devices and applications into a unified format. This intermediary layer handles the complexity of data integration, applying consistent formatting and structure to messages regardless of their source, thereby simplifying subsequent search and analysis operations.
2Measurement precision
If advanced search queries with boolean logic and proximity indicators are implemented, then the precision of finding relevant messages improves, but the complexity of the search system increases
Solution Approach 1:
The search system implements dynamic query processing that adapts to different search needs. Users can construct queries with varying levels of complexity using boolean logic and proximity indicators, and the system dynamically adjusts its processing based on the query parameters provided, allowing for precise searches without requiring a permanently complex system architecture.
Solution Approach 2:
The system performs preliminary indexing and organization of messages during the data collection phase, preparing the data structure in advance to support advanced search operations. This preliminary action enables the system to efficiently handle complex boolean and proximity queries without requiring complex processing during the actual search execution.
3Loss of information
If messages are displayed in chronological order with context messages, then the completeness of information is improved, but the time required to review messages increases
Solution Approach 1:
The system applies local quality enhancement by selectively displaying context messages adjacent to search results. Rather than displaying all messages uniformly, the system provides additional contextual information locally around relevant findings, giving users just enough surrounding context to understand the significance of each result without requiring review of the entire message set.
Solution Approach 2:
The system implements partial action by displaying a limited number of context messages (e.g., a few before and after each result) rather than displaying all chronological messages. This partial display provides sufficient context for understanding search results while significantly reducing the total review time compared to displaying complete chronological sequences.
Data Source
AI summary
The discovery process in criminal and civil litigation frequently produces a large body of digital data. The digital data may come from computers, smartphones and other electronic devices (sources) of one or more people related to the litigation. Each source may have digital data from one or more applications and/or programs (platforms). The digital data may include, as non-limiting examples, contact lists, messages (possibly with emojis), photos, videos, audio and/or location data as non-limiting examples. The digital data from the various sources and platforms may be normalized and combined into a corpus of digital data. Digital forensic tools, possibly even an artificial intelligence (AI) may then be used to analyze the corpus of digital data.