Dell products l.p. (20240248836). BOOTSTRAP METHOD FOR CONTINUOUS DEPLOYMENT IN CROSS-CUSTOMER MODEL MANAGEMENT simplified abstract

BOOTSTRAP METHOD FOR CONTINUOUS DEPLOYMENT IN CROSS-CUSTOMER MODEL MANAGEMENT

Organization Name

dell products l.p.

Inventor(s)

Paulo Abelha Ferreira of Rio de Janeiro (BR)

Vinicius Michel Gottin of Rio de Janeiro (BR)

Pablo Nascimento Da Silva of Niterói (BR)

BOOTSTRAP METHOD FOR CONTINUOUS DEPLOYMENT IN CROSS-CUSTOMER MODEL MANAGEMENT - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240248836 titled 'BOOTSTRAP METHOD FOR CONTINUOUS DEPLOYMENT IN CROSS-CUSTOMER MODEL MANAGEMENT

Simplified Explanation

The patent application describes a method for determining model drift in a logistics system by analyzing data from near-edge nodes and deploying machine-learning models to address any drift detected.

• The method calculates a system aggregate drift metric score based on data from near-edge nodes.
• If the drift score exceeds a threshold, current datasets are collected from the nodes.
• A first dataset is created by combining the collected data, and a second dataset is received from each near-edge node.
• These datasets are used to select and deploy machine-learning models at each node to mitigate drift in the system.

Key Features and Innovation

• Determining system aggregate drift in a logistics system.
• Utilizing data from near-edge nodes to assess model drift.
• Deploying machine-learning models to address drift in the system.

Potential Applications

This technology can be applied in various industries such as supply chain management, transportation, and manufacturing to monitor and manage model drift in complex systems.

Problems Solved

• Detecting and addressing model drift in a logistics system.
• Improving the accuracy and reliability of machine-learning models in real-time applications.

Benefits

• Enhancing system performance and efficiency.
• Minimizing errors and disruptions in logistics operations.
• Optimizing decision-making processes based on accurate data analysis.

Commercial Applications

Title: Real-time Model Drift Detection and Mitigation in Logistics Systems This technology can be used by logistics companies to improve the reliability and effectiveness of their operations, leading to cost savings, improved customer satisfaction, and competitive advantages in the market.

Prior Art

Further research can be conducted in the field of real-time model drift detection and mitigation in logistics systems to explore existing technologies and methodologies.

Frequently Updated Research

Stay updated on advancements in machine learning, data analytics, and logistics management to enhance the effectiveness of this technology.

Questions about Model Drift Detection and Mitigation

1. How does this technology improve the efficiency of logistics systems? 2. What are the potential challenges in deploying machine-learning models at near-edge nodes in real-time applications?

Original Abstract Submitted

one example method includes determining a system aggregate drift metric score based on aggregate drift metric scores received from near-edge nodes associated with a central node. the system aggregate drift metric score indicates a level of model drift across a logistics system. the system aggregate drift metric score is compared with a system drift threshold. current datasets are received from the near-edge nodes when a system aggregate drift metric score is greater than the system drift threshold. a first dataset is generated comprising a joining of the current datasets received from the plurality of near-edge nodes. a second dataset is received from each the near-edge nodes. the first and second datasets are used to select a machine-learning (ml) model to deploy at each of the near-edge nodes.