Conversational Thread Visualization for Team Data Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic communication systems face challenges in analyzing and visualizing team conversational data due to the large volume and heterogeneous nature of the data, particularly with interleaved conversational threads, making it difficult for users to grasp meaningful patterns and understand team collaboration and communication effectively.

Innovation Solution

A method and system for analyzing and visualizing conversational messages by receiving a query defining a timespan, retrieving relevant messages and authors, and generating a visualization of conversational threads organized into time intervals, using techniques such as de-threading and keyword extraction to disentangle interleaved conversations and provide a novel visual representation of overall activity trends and detailed information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional visualization methods are used for conversational data, then the system can display data in a simple format, but users cannot easily grasp meaningful patterns due to large volume and heterogeneous nature of data

Engineering Contradiction:

Improveease of grasping meaningful patternsVSAvoidvolume of conversational data

Core Design Contradiction:

Ease of operationVSQuantity of substance

Solution Approach 1:

The patent segments conversational data by extracting and separating different conversational threads from interleaved messages. Each thread is identified and organized independently, allowing users to analyze specific conversation flows without being overwhelmed by the entire dataset. This segmentation transforms the heterogeneous mass of messages into structured, manageable thread units.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary processing layer that performs de-threading and organization of conversational data before visualization. This intermediary system extracts meaningful patterns and structures from raw messages, acting as a mediator between the large volume of data and the user's need for comprehensible visual representation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If multiple topics are discussed simultaneously in team communication, then the conversation reflects real team dynamics, but individual conversational threads become interleaved and difficult to understand

Engineering Contradiction:

Improveability to handle multiple topicsVSAvoidcomplexity of conversational thread structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing interleaved conversational data into distinct thread segments. Each thread represents a separate topic or conversation flow, extracted and organized independently. This allows the system to handle multiple simultaneous topics while maintaining clear separation between them in the visualization.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent resolves interleaved threads by introducing an additional organizational dimension - threading structure. Instead of displaying messages chronologically in a single dimension, the system adds a thread identification dimension that groups related messages together, making it possible to distinguish and follow multiple concurrent conversation topics.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Loss of information

If detailed conversational data is analyzed, then comprehensive team collaboration insights can be obtained, but the analysis becomes non-trivial and problematic

Engineering Contradiction:

Improvecompleteness of team collaboration insightsVSAvoiddifficulty of analyzing conversational data

Core Design Contradiction:

Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent performs preliminary actions by automatically extracting, de-threading, and organizing conversational data before the analysis phase. This pre-processing establishes a structured foundation that simplifies subsequent analysis, allowing comprehensive insights to be obtained without the non-trivial difficulty of analyzing raw interleaved messages.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system performs self-service analysis by automatically identifying and extracting conversational threads without requiring manual intervention. The de-threading process autonomously separates interleaved messages into meaningful threads, enabling comprehensive analysis while reducing the complexity burden on users.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS10762116B2System and method for analyzing and visualizing team conversational data

Publication Date: 2020.09.01 FUJIFILM BUSINESS INNOVATION CORP

AI summary

A method of analyzing conversational messages may be provided. The method may include receiving a query defining a timespan of messages, retrieving at least one conversational message associated with the defined timespan from a plurality of interleaved messages, retrieving at least one message author associated with the defined timespan from a plurality authors associated with the plurality of interleaved messages, and generating a visualization of conversational threads based on the defined timespan, the at least one conversational message and the at least one message author, the visualization organized into time intervals based on the defined timespan.