Conversation Graph Filtering With Others Node and Edge Directionality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional conversation graph systems struggle with efficiently representing large sets of communications in legal proceedings, requiring significant processing power and memory due to the inclusion of non-important communications, and lack flexibility in selecting and visualizing subsets of data.
Innovation Solution
The implementation of a conversation graph system that includes an 'others node' representing non-displayed communications, allows selection of non-adjacent nodes and edges, and provides visual indications of communication directionality and proportionality, enabling efficient processing and visualization of subsets of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all communications are represented in the conversation graph, then complete data representation is achieved, but processing power and memory requirements increase significantly
Solution Approach 1:
The patent extracts and removes non-important communications from the conversation graph representation. It identifies and filters out communications that do not contribute to relevant conversations, keeping only the essential data needed for legal review while discarding redundant information, thereby reducing processing and memory requirements without losing critical information.
Solution Approach 2:
The patent segments the set of communications into different categories: important communications that form relevant conversations are represented individually in the conversation graph, while non-important communications are excluded. This segmentation allows the system to process and display only the necessary subset of data, reducing computational burden while maintaining data completeness for relevant information.
2Loss of information
If conventional conversation graphs represent all communications simultaneously, then comprehensive data visualization is achieved, but efficiency decreases due to inclusion of non-important communications
Solution Approach 1:
The system extracts and removes non-important communications from the visualization. It applies filtering criteria to identify and exclude communications that do not contribute to relevant legal conversations, thereby improving processing efficiency while maintaining comprehensive visualization of all important communications through the conversation graph.
Solution Approach 2:
The patent applies different quality standards to different communications based on their importance. Important communications receive full representation in the conversation graph with complete visualization, while non-important communications are excluded entirely. This local differentiation optimizes efficiency by focusing computational resources on high-value data while maintaining comprehensive visualization for relevant information.
3Loss of information
If document review includes all communications, then complete analysis is achieved, but processing time and resources increase due to large volume of data
Solution Approach 1:
The patent extracts and removes non-important communications from the analysis set before constructing the conversation graph. By filtering out irrelevant communications upfront, the system reduces the total volume of data requiring processing and analysis, thereby decreasing processing time while maintaining complete analysis of all important communications that are relevant to the legal case.
Data Source
AI summary
Conversation graphing capabilities accommodate subsets of conversations to be examined or reviewed. An “others” node is included in a conversation graph displayed through a user interface representing, in one implementation, all conversations not shown on the graph. Individual nodes and/or edges can be selected regardless of whether they are adjacent or connected. Information related to the communications associated with the selected nodes and/or edges is displayed. Nodes associated with communications falling within a selected time range is included and emphasized in the conversation graph. Directionality (i.e., direction of majority of communications) and/or proportionality (i.e., fraction of communications flowing in one direction along an edge verses the opposite direction) is provided through a visual indication for individual edges in the conversation graph.