Abnormal Message Identification Using Difference-Class Inputs

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing abnormal message identification models in vehicle communications networks are not accurate due to the simplification of using only a difference value, such as an arrival time interval, between message feature values, which does not account for the variability in message transmission times.

Innovation Solution

The method involves dividing the value range of difference values into multiple difference classes, and using the identifier of the corresponding difference class in the abnormal message identification model to determine whether a message is abnormal or not, thereby improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If only the difference value between message feature values is used as input for the abnormal message identification model, then the model training and operation is simple, but the identification accuracy is reduced

Engineering Contradiction:
Improvemodel input complexityVSAvoidabnormal message identification accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the continuous difference value into discrete difference classes by dividing the value range into multiple intervals. Each interval represents a difference class, and the specific difference value is mapped to its corresponding class. This segmentation transforms a single continuous parameter into multiple discrete categories, enabling the model to capture the variability in message transmission times while maintaining computational efficiency.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If the difference value is divided into multiple difference classes, then the abnormal message identification accuracy is improved, but the data processing complexity increases

Engineering Contradiction:
Improveabnormal message identification accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary classification of difference values into difference classes before feeding them into the abnormal message identification model. By pre-dividing the value range and establishing mapping relationships between difference values and their corresponding classes, the system prepares the data in advance. This preliminary action simplifies the main identification process, as the model only needs to process discrete class identifiers rather than continuous values, reducing computational complexity during runtime.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3979590B1Method and device for identifying abnormal message
Publication Date: 2025.06.11 HUAWEI TECH CO LTD
  • EP3979590B1 patent drawingFigure 1
  • EP3979590B1 patent drawingFigure 2
  • EP3979590B1 patent drawingFigure 3

AI summary

This application provides a method for identifying an abnormal message, a method and an apparatus for training an abnormal message identification model. The methods in the embodiments of this application are applicable to the field of automobiles or ships. The method for identifying an abnormal message includes: A security enforcement unit SEU receives a first message, and determines a first difference value between a feature value of the first message and a feature value of a second message, where the second message is a message that is received before the first message is received; the SEU determines, from a plurality of preset difference classes, a difference class corresponding to the first difference value, where different difference classes in the plurality of difference classes correspond to different value ranges of a difference value; and the SEU inputs an identifier of the difference class corresponding to the first difference value into a pre-stored abnormal message identification model, to determine whether the first message is the abnormal message or a non-abnormal message. This helps improve accuracy of identifying the abnormal message based on the abnormal message identification model.