Master Build Plan Adjustment via News Event Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current supply chain applications fail to account for real-time events such as severe weather and labor unrest, leading to production delays and inefficiencies in manufacturing, as they do not provide the ability to adjust production plans dynamically in response to unforeseen disruptions.

Innovation Solution

A machine learning system that analyzes news data using natural language processing and neural networks to identify critical events impacting supply chains, adjusting the master build plan by determining confidence scores for news items related to entities in the supply chain, allowing for automatic adjustments in replenishment planning and production schedules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional supply chain applications are used, then production planning is straightforward, but the system cannot respond to real-time events like severe weather and labor unrest, causing production delays

Engineering Contradiction:

Improveability to respond to real-time eventsVSAvoidproduction efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The master build plan is transformed from a static document to a dynamic one that automatically adjusts in response to real-time events. The system continuously monitors news data and confidence scores, enabling the production plan to adapt dynamically to supply chain disruptions such as severe weather and labor unrest, thereby resolving the contradiction between adaptability and productivity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements a feedback mechanism where news data is continuously collected, processed through natural language processing, and used to update confidence scores that trigger plan adjustments. This closed-loop feedback system enables real-time response to supply chain events while maintaining overall production efficiency through automated decision-making.

Inventive Principle:

Principle #23Feedback

2Reliability

If manual monitoring of supply chain events is implemented, then production plans can be adjusted, but the process requires human interaction and cannot respond in real-time

Engineering Contradiction:

Improvesupply chain disruption responseVSAvoidresponse time to events

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs self-service by automatically collecting news data, processing it through natural language processing algorithms, calculating confidence scores, and adjusting the master build plan without human intervention. This automation eliminates response delays while maintaining reliable supply chain monitoring and adjustment capabilities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical monitoring and adjustment processes are replaced with an automated electronic system that uses natural language processing and machine learning algorithms to monitor supply chain events and adjust production plans, eliminating human response time limitations while improving reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of information

If real-time news data processing is implemented, then the system can identify critical events, but the complexity of natural language processing and neural networks increases

Engineering Contradiction:

Improvecritical event detection accuracyVSAvoidmachine learning system complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system extracts only the critical and relevant features from news data using natural language processing, focusing specifically on supply chain-related entities and events. This selective extraction approach maintains high detection accuracy for critical events while reducing the overall processing complexity by filtering out irrelevant information.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms unstructured news text into structured parameters including confidence scores and event classifications that can be directly applied to production planning. This parameter transformation simplifies the complexity by converting complex natural language data into actionable quantitative metrics that drive automated decision-making.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11379767B2Adjusting a master build plan based on events using machine learning

Publication Date: 2022.07.05 DELL PROD LP

AI summary

As an example, a server may receive and/or retrieve news items and process the news items using natural language processing to identify news related to entities (e.g., people, locations, and organizations) extracted from an enterprise resource planning system. A term frequency-inverse document frequency algorithm may be used to identify critical news items that may impact one or more supply chains associated with at least one product that is to be manufactured. A long short-term memory artificial recurrent neural network may be used to determine a confidence score for each critical news item. The confidence scores of the critical news items may be used to adjust replenishment planning and a master build plan that includes a plan to build the at least one product. In this way, news items may be used to automatically (e.g., without human interaction) adjust the master build plan.