NLP Task Extraction from Communication Messages

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual updating of task progress in business settings is cumbersome, time-consuming, and prone to inaccuracies, especially when tasks are assigned, delegated, or completed through various forms of communication like email, chat, or phone conversations.

Innovation Solution

A system utilizing natural language processing (NLP) and machine learning (ML) to identify tasks and commitments within communication messages by extracting features such as co-reference resolution, part-of-speech tags, and typed dependencies, enabling automatic classification of task status and commitment states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual updating of task progress is used, then system simplicity is maintained, but time consumption and labor effort increase significantly

Engineering Contradiction:

Improvetask management efficiencyVSAvoidtime consumed for manual updates

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system automatically extracts task information and updates task progress by processing communication messages through NLP and ML models, eliminating the need for manual updating while maintaining system simplicity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical updating processes are replaced with automated computational processes using NLP for information extraction and ML for classification, significantly reducing time consumption

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual task tracking is used, then system complexity is minimized, but accuracy and reliability of task status information deteriorate

Engineering Contradiction:

Improveaccuracy of task statusVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

NLP and ML models serve as intermediary components that automatically process communication messages and extract task information, ensuring accurate and reliable task status tracking without requiring complex manual tracking mechanisms

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system continuously processes communication messages to automatically update task status, providing real-time feedback that ensures accurate and reliable task tracking without increasing operational complexity

Inventive Principle:

Principle #23Feedback

3Productivity

If automatic NLP-based task identification is implemented, then productivity and accuracy improve, but computational resources and system complexity increase

Engineering Contradiction:

Improvetask management efficiencyVSAvoidcomputational resource consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system pre-processes communication messages and extracts relevant information using NLP models, preparing data for ML classification, which optimizes computational resource usage by performing preliminary actions that reduce processing requirements

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9170993B2Identifying tasks and commitments using natural language processing and machine learning

Publication Date: 2015.10.27 MICRO FOCUS LLC

AI summary

An example of identifying tasks and commitments can include receiving a communication message. A task and a parameter can be identified in the communication message. Information related to the task can be extracted from the communication message using natural language processing (NLP) and machine learning (ML). A commitment related to the task can be identified using NLP extracted information. A state of the commitment can be identified using NLP and ML based on the extracted information.