Document Management System Thread Classification for Legal Review

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing document management systems require significant effort and time for reviewers to classify large amounts of digital document information for relevance to a lawsuit, leading to a high review load and inefficiency.

Innovation Solution

A document management system that classifies digital information into threads based on supplementary information, analyzes similarity between threads, and integrates them, including features like document data classification, extraction, and score calculation to automate the review process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a huge amount of digital document information is collected from multiple computers and servers, then the completeness of evidence collection is improved, but the review load and time required for classification increases significantly

Engineering Contradiction:

Improvecompleteness of evidence collectionVSAvoidtime required for classification

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the huge amount of digital document information into multiple threads based on supplementary information such as metadata, document properties, and contextual data. This segmentation allows the review process to be divided into manageable units, reducing the overall review load while maintaining complete evidence collection from multiple computers and servers.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces the manual mechanical classification process with an automated analysis system that uses computational methods to examine supplementary information, extract key elements, and perform similarity analysis. This substitution dramatically reduces the time required for classification while maintaining the completeness of evidence collection.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual classification of each piece of document information is performed by a reviewer, then the accuracy of relevance determination is improved, but the productivity and efficiency of the review process deteriorates

Engineering Contradiction:

Improveaccuracy of relevance determinationVSAvoidproductivity of review process

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual reviewer classification with an automated system that analyzes supplementary information and performs similarity comparisons. This substitution maintains accuracy by using systematic analysis methods while dramatically improving productivity by processing large volumes of documents simultaneously without human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an automated analysis system as an intermediary between the collected digital information and the final classification decision. This intermediary processes supplementary information and generates similarity scores, providing an objective basis for relevance determination that maintains accuracy while enabling high-volume processing.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If supplementary information is used to classify document data into threads, then the organization and manageability of information is improved, but the device complexity and processing requirements increase

Engineering Contradiction:

Improveorganization and manageability of informationVSAvoidprocessing system complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent uses supplementary information to segment document data into organized threads, improving manageability by grouping related documents together. This segmentation approach balances the increased processing complexity with significant gains in organization, allowing reviewers to navigate and manage large volumes of information more effectively.

Inventive Principle:

Principle #1Segmentation

4Measurement precision

If similarity analysis is performed between threads to integrate them, then the accuracy of relevant document identification is improved, but the computational time and resources required increase

Engineering Contradiction:

Improveaccuracy of relevant document identificationVSAvoidcomputational time required

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary extraction of key elements from supplementary information before conducting similarity analysis between threads. This preliminary action reduces the computational burden by focusing analysis on the most relevant features, thereby maintaining high accuracy in relevant document identification while reducing the overall computational time and resources required.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9594757B2Document management system, document management method, and document management program

Publication Date: 2017.03.14 FRONTEO INC

AI summary

It is possible to reduce a review load of a reviewer. A document management system acquires digital information recorded in a plurality of computers or a server and analyzes the acquired digital information for relevance to a lawsuit. The document management system includes a thread classification unit that verifies supplementary information of each piece of document data included in the digital information and classifies the document data into threads based on the supplementary information, a similarity analysis unit that extracts elements included in the supplementary information of the classified document data for each thread and analyzes similarity between the threads based on the extracted elements, and an integration unit that integrates the threads based on the similarity.