Keyword Suggestion for Legal E-Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing electronic discovery processes for identifying relevant documents in litigation are cumbersome and costly due to the manual review of large document sets, often resulting in inclusion of non-relevant documents and exclusion of relevant ones, especially when using keyword-based search methods.
Innovation Solution
The system suggests new keywords and queries by analyzing the relevance of documents using a seed set, generating a set of discriminatory keywords and related keywords through algorithms like Random Walk, to improve the efficiency of document retrieval in litigation holds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual review process is used to determine document relevance, then accuracy of relevance determination is improved, but expense and time consumption increase
Solution Approach 1:
The patent introduces an automated keyword suggestion system as an intermediary between the initial keyword search and manual review. The system analyzes seed keywords, retrieves related documents, and generates new keyword suggestions based on relevance indications, thereby reducing the burden on manual reviewers while maintaining accuracy.
Solution Approach 2:
The patent replaces part of the manual mechanical review process with an automated computer-based system that uses algorithms to analyze documents, determine relevance, and generate keyword suggestions, thereby reducing time consumption while preserving accuracy through iterative refinement.
2Loss of energy
If automated keyword search is used to reduce expense, then cost is reduced, but relevance accuracy deteriorates due to inclusion of non-relevant documents and exclusion of relevant ones
Solution Approach 1:
The patent implements a feedback mechanism where the system retrieves documents based on seed keywords, receives relevance indications for those documents, and uses this feedback to generate improved keyword suggestions. This iterative feedback loop continuously refines the search accuracy while maintaining cost efficiency.
Solution Approach 2:
The patent performs preliminary automated keyword searching and document retrieval before manual review, using the results to generate improved keyword suggestions that guide subsequent searches. This preliminary action filters out obviously irrelevant documents while preserving potentially relevant ones for further review.
3Reliability
If thorough search of all computer systems is conducted to ensure compliance with litigation hold, then completeness of document retrieval is improved, but complexity and resource requirements increase
Solution Approach 1:
The patent segments the large-scale e-discovery process into manageable components: initial keyword search, document retrieval, relevance indication collection, keyword suggestion generation, and iterative refinement. This segmentation makes the complex compliance process more manageable and scalable.
Solution Approach 2:
The patent implements a dynamic, adaptive search system that evolves keyword suggestions based on feedback from relevance indications. Rather than using a static comprehensive search approach, the system dynamically adjusts its search strategy, making the compliance process more efficient while maintaining reliability.
Data Source
AI summary
Given a set of documents relevant to a litigation hold and a seed set of keywords, a second set of keywords can be generated and suggested to a user. Each document in a training set of documents is given an indication of relevance. Based on the indication of relevance, a set of further keywords relevant to the litigation is extracted from the documents and suggested to a user. The suggested set of keywords may or may not include keywords in the seed set. Additionally, the suggested set of keywords may be related to the seed set of keywords.