Browse Prior Art Database

Cognitive Detector of Common Issues in IoT Devices (Hardware and Software)

IP.com Disclosure Number: IPCOM000249187D
Publication Date: 2017-Feb-09
Document File: 5 page(s) / 108K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed are a method and system to use information provided by similar Internet of Things (IoT) devices to detect common issues and facilitate early detection and rapid action to address problems.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.

1

Cognitive Detector of Common Issues in IoT Devices (Hardware and Software)

Manufacturers spend billions of dollars on warranties to address product issues. That cost increases with the addition of legal penalties associated with product malfunctions (e.g., medical equipment, cars, etc.). The early identification of known issues is critical in order to reduce negative customer impact (i.e., dissatisfaction) through early and voluntary recalls, early halt of manufacturing the malfunctioning devices, and acceleration of the root cause analysis (RCA) process.

The market for Internet of Things (IoT) is rapidly growing. A method and system are needed to detect common issues on IoT devices, both hardware (HW) and software (SW).

The novel contribution is a method and system to use some information provided by similar IoT devices to detect common issues . Examples of the information recorded include, but are not limited to:

• Device errors

• Performance deviations (e.g., loss of battery efficiency, signal range/strength, etc.)

• Unexpected device behaviors

• Unexpected device outputs

• Increased data processing time

• Increased device hard reboots This approach can help uncover usage patterns, defect detection, recalls, RCA of defects, etc.

Figure 1: Current model

2

Figure 2: Novel model

3

Figure 3: System diagram

Referring to Figure 3, the novel solution comprises an Inputs Module, a Cognitive Engine, and an Outputs Module, as well as databases for configuration, performance, and issues.

Inputs Module 1. Performance Measurements Module: The device has pre-configured performance measures defined (e.g., battery

performance, battery capacity, Central Processing Unit (CPU), Random Access Memory (RAM), Storage (read/ write speed), etc.

2. Baseline Configuration Module: Each measurement has a baseline of expected behaviors and thresholds (stored on the performance database (DB))

4

3. Update Module: The update model gets real time data from the device , as well as manual input/updates to the perfo...