18060197. CREATING SETS OF HETEROGENEOUS INTERNET-OF-THINGS (IoT) DEVICES FROM WHICH TO UPLOAD DATA AS A PRE-STEP TO EDGE COMPUTING simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

CREATING SETS OF HETEROGENEOUS INTERNET-OF-THINGS (IoT) DEVICES FROM WHICH TO UPLOAD DATA AS A PRE-STEP TO EDGE COMPUTING

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Hemant Kumar Sivaswamy of Pune (IN)

Venkata Vara Prasad Karri of Visakhapatnam (IN)

Sarbajit K. Rakshit of Kolkata (IN)

Afroz Khan I of Davanagere (IN)

CREATING SETS OF HETEROGENEOUS INTERNET-OF-THINGS (IoT) DEVICES FROM WHICH TO UPLOAD DATA AS A PRE-STEP TO EDGE COMPUTING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18060197 titled 'CREATING SETS OF HETEROGENEOUS INTERNET-OF-THINGS (IoT) DEVICES FROM WHICH TO UPLOAD DATA AS A PRE-STEP TO EDGE COMPUTING

Simplified Explanation

The abstract describes a method, computer system, and computer program product for transmitting data from a set of edge devices, focusing on Internet-of-Things (IoT) devices within a structure. The process involves identifying and grouping IoT devices, selecting primary devices for each group, deploying machine learning models on the primary devices, and utilizing these models to activate other groups in response to events.

• Identifying and grouping Internet-of-Things (IoT) devices within a structure
• Selecting primary devices for each group of IoT devices
• Deploying tiny machine learning (ML) models on the identified primary devices
• Utilizing the ML models to select and activate other groups in response to events

Potential Applications

This technology could be applied in smart home systems, industrial automation, and smart city infrastructure to efficiently manage and control IoT devices based on real-time events.

Problems Solved

This technology solves the problem of effectively coordinating and managing a large number of IoT devices within a network or structure, ensuring optimal performance and responsiveness to events.

Benefits

The benefits of this technology include improved efficiency in data transmission, enhanced automation capabilities, and better utilization of IoT devices within a network.

Potential Commercial Applications

Potential commercial applications of this technology include smart home automation systems, industrial IoT solutions, and smart building management platforms.

Possible Prior Art

One possible prior art could be the use of machine learning models for device management and automation in IoT networks. Another could be the concept of grouping and coordinating IoT devices within a network for improved performance and responsiveness.

How does this technology ensure data security and privacy for the transmitted data?

The abstract does not provide details on how data security and privacy are maintained while transmitting data from IoT devices. It would be important to understand the mechanisms in place to protect sensitive information.

What are the scalability limitations of this technology when managing a large number of IoT devices?

The abstract does not address the scalability limitations of the proposed method when dealing with a significant number of IoT devices within a structure. Understanding the potential constraints in scalability is crucial for implementing this technology in large-scale deployments.

Original Abstract Submitted

According to one embodiment, a method, computer system, and computer program product for transmitting data from a set of edge devices is provided. The embodiment may include identifying one or more Internet-of-Things (IoT) devices within a structure. The embodiment may include combining the identified one or more IoT devices into one or more groups. The embodiment may include identifying a respective primary device for each group of the one or more groups. The embodiment may include deploying a tiny machine learning (ML) model on each identified respective primary device. In response to detection of an event within the structure by a group of the one or more groups, the embodiment may include utilizing the tiny ML model of a primary device of the group to select one or more other groups for activation.