Forensic System Automating Document Relevance Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current forensic systems require significant effort and time for a reviewer to classify large amounts of digital document information as evidence in lawsuits, as they lack efficient methods to automatically determine relevant documents connected to the lawsuit.
Innovation Solution
A forensic system that analyzes digital information from multiple computers or servers by calculating evaluation values of common elements in document groups, assigning scores to documents, and calculating recall ratios to automatically determine connections to a lawsuit, thereby reducing the burden on reviewers and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a huge amount of document information is collected from multiple computers and servers, then the completeness of evidence is improved, but the time and effort required for classification increases significantly
Solution Approach 1:
The patent segments the document classification task into two parts: automated scoring of documents based on extracted elements (words, phrases, concepts) and manual review only of documents above a threshold score. This segmentation allows the system to handle large volumes of documents while reducing the time reviewers must spend on manual classification.
Solution Approach 2:
The patent introduces an intermediary scoring system that acts between the collected document information and the final classification decision. The scoring unit calculates relevance scores based on extracted elements and their weights, serving as a mediator that filters and prioritizes documents before human review, thereby reducing the time and effort required for classification.
2Measurement precision
If manual classification of each document is performed, then the accuracy of relevance determination is improved, but the operational burden on reviewers increases
Solution Approach 1:
The patent applies partial automation where not all documents require full manual review. Documents scoring above a threshold are flagged for review, while documents below the threshold can be automatically excluded. This partial action approach maintains accuracy for critical documents while significantly reducing the operational burden on reviewers.
Solution Approach 2:
The patent implements feedback through the scoring system that continuously refines its element extraction and weighting based on review results. The system learns from reviewer feedback to improve future scoring accuracy, thereby maintaining high accuracy in relevance determination while reducing the manual effort required through increasingly intelligent automation.
3Productivity
If automated scoring based on extracted elements is implemented, then the productivity of document review is improved, but the complexity of the system increases
Solution Approach 1:
The patent extracts key elements (words, phrases, concepts) from documents and separates them from the full document text for analysis. By taking out only the essential elements needed for scoring, the system achieves improved productivity while keeping the complexity manageable, as it only processes and stores these extracted elements rather than entire documents.
Solution Approach 2:
The patent changes parameters by assigning weights to different elements based on their relevance to the lawsuit. Instead of treating all text equally, the system adjusts parameters (element weights) to prioritize certain keywords and concepts. This parameter change approach improves productivity by focusing review effort on high-relevance documents while the complexity is managed through configurable rather than fixed complex logic.
Data Source
AI summary
A forensic system includes a result information receiving unit that receives result information which is a determination result of connection between a lawsuit and a document group including a predetermined number of documents, which is extracted from document data included in digital information, by a user, an element selection unit that calculates evaluation values of elements which commonly appear in the document group in each result information item from the characteristics of the elements and selects the elements on the basis of the evaluation values, a score calculation unit that calculates a score of each document in the document data from the selected elements included in each document of the document data and the evaluation values of the selected elements, and a recall ratio calculation unit that calculates a recall ratio related to the determination of the connection to the lawsuit on the basis of the score.