Message Conversion System for Group Chat Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In internal investigations and legal proceedings, data from various sources like instant messaging, chat, and group-based communication platforms is challenging to analyze due to lack of standardized formats, making it difficult to integrate with other data types and review effectively outside traditional eDiscovery platforms.
Innovation Solution
A system and method that uses an API to receive electronic message data from group-based communication platforms, generates a database in a message-per-row format, and employs a trained machine-learning model to group messages into conversations, outputting them in formats like HTML, CSV, or text files, enabling easier analysis and review.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional techniques are used to extract data from group-based communication platforms, then data can be obtained from these platforms, but the data lacks standardized format and conversational context, making it difficult to analyze and review
Solution Approach 1:
The system performs preliminary actions by extracting messages from multiple sources (Slack, Teams, SMS, WhatsApp) and pre-processing them into a standardized format with preserved conversational context before analysis is needed. This includes grouping messages by conversation threads and organizing them with metadata, so that when reviewers need to analyze the data, it is already in an analysis-ready state with context intact.
Solution Approach 2:
The patent introduces an intermediary processing system that acts as a mediator between raw message data from various platforms and the final analysis tools. This intermediary component standardizes the data format, preserves conversational context, and prepares the data for downstream analysis without requiring changes to the source platforms or the analysis tools.
2Adaptability or versatility
If data is extracted from multiple different data sources with different structured formats, then comprehensive data can be collected, but it becomes difficult to integrate and review due to lack of standardized format
Solution Approach 1:
The system implements a universal data processing framework that can handle multiple data sources (Slack, Microsoft Teams, SMS, WhatsApp) with different structured formats through a single standardized interface. The extraction module is designed to adapt to various platform formats and convert them into a common standardized format, eliminating the need for separate processing pipelines for each data source.
Solution Approach 2:
The patent applies parameter changes by transforming data from various source formats into a standardized format with consistent parameters. This includes standardizing message structure, timestamp formats, user identification, and conversation grouping parameters, allowing data from heterogeneous sources to be integrated without increasing system complexity.
3Reliability
If traditional eDiscovery platforms are used to review data, then data can be reviewed, but computing resources and human effort are significantly consumed
Solution Approach 1:
The system performs preliminary organization and standardization of data before it reaches the review stage. By pre-grouping messages into conversations, pre-standardizing formats, and pre-processing metadata, the system reduces the workload during actual review, thereby reducing both computing resources needed and human effort required while maintaining review accuracy.
4Quantity of substance
If data is exported from group-based communication platforms using existing APIs, then some data can be extracted, but the data is difficult to convert and display in a meaningful way for analysis across multiple tools
Solution Approach 1:
The patent introduces an intermediary conversion system that receives data from various APIs (Slack API, Teams API, SMS APIs, WhatsApp API) and converts it into a unified meaningful format. This intermediary layer handles the complexity of different API responses and converts them into a standardized structure that can be easily displayed and analyzed across multiple tools without requiring separate conversion processes for each data source.
Data Source
AI summary
A method of converting electronic messages into conversation data. The method comprises: receiving electronic message data from an externally shared communication channel in a group-based communication platform, wherein the electronic message data comprises: electronic messages; a respective user associated with each electronic message; a respective channel or group associated with each electronic message; and a respective time or date associated with each electronic message; generating a database that represents the electronic message data in a message per row format; generating conversation data by grouping the electronic messages in the database into one or more conversations based on the electronic message data; and outputting the generated conversation data in a form of one or more of: a conversational HTML file; a text file; a CSV file associated with each user associated with each electronic message; or a CSV file associated with each channel or group associated with each electronic message.