Abnormality Detection Using Dynamic Reference Information

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing abnormality detection techniques for computer systems rely on fixed rules, which are inadequate as they fail to account for varying circumstances, leading to inaccurate detection of system abnormalities.

Innovation Solution

An abnormality detection apparatus and method that includes a first detection unit for identifying the start of a predetermined operation, an acquisition unit for obtaining reference information specific to the context, and a second detection unit for detecting abnormalities using this context-specific information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a fixed rule is used as a reference for abnormality detection, then the detection system is simple to implement, but the detection accuracy deteriorates because it cannot adapt to varying operational circumstances

Engineering Contradiction:
Improveabnormality detection accuracyVSAvoiddetection system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies the dynamics principle by making the reference information dynamic rather than fixed. The system automatically acquires and updates reference information based on the current operational state of the terminal, allowing the abnormality detection criteria to adapt to different circumstances such as maintenance operations versus normal operations, thereby improving detection accuracy without requiring manual intervention

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements self-service by automatically acquiring reference information from the terminal itself based on its operational state. The terminal's own operation state serves as the basis for selecting appropriate reference information, eliminating the need for external manual configuration and enabling the system to self-adjust to different operational contexts

Inventive Principle:
Principle #25Self-service

2Reliability

If context-specific reference information is acquired and used for abnormality detection, then detection accuracy is improved, but the system complexity increases due to additional detection and acquisition units

Engineering Contradiction:
Improveabnormality detection reliabilityVSAvoiddetection apparatus structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges the first detection unit that detects operational state with the second detection unit that performs abnormality detection. Both functions are integrated into a unified detection apparatus that shares common resources and processing mechanisms, reducing overall system complexity while maintaining the ability to use context-specific reference information for improved reliability

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS11983064B2Abnormality detection apparatus, control method, and program
Publication Date: 2024.05.14 NEC CORP
  • US11983064B2 patent drawing
  • US11983064B2 patent drawing
  • US11983064B2 patent drawing

AI summary

An abnormality detection apparatus (2000) detects a start of a predetermined operation in a terminal (10). The abnormality detection apparatus (2000) acquires reference information (30) representing a reference of abnormality detection of the terminal (10) after the predetermined operation is started. After it is detected that the predetermined operation is started, the abnormality detection apparatus (2000) detects abnormality of the terminal (10) by using the acquired reference information (30).