Vehicle Fault Knowledge Graph for Faster Diagnosis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional vehicle fault diagnostic methods rely heavily on personal experience and are time-consuming, costly, and fail to effectively consolidate repair knowledge, limiting their applicability and efficiency.

Innovation Solution

A knowledge graph is constructed using entity extraction and relationship recognition to integrate abnormal signal nodes, faulty component nodes, and repair suggestion nodes, with edge weights based on probability calculations to facilitate accurate and efficient fault diagnosis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional fault diagnostic methods relying on personal experience are used, then diagnostic accuracy depends on expert knowledge, but the process is time-consuming and costly

Engineering Contradiction:

Improvefault diagnosis accuracyVSAvoiddiagnosis time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-construction a knowledge graph from historical repair data before actual fault diagnosis occurs. The knowledge graph pre-stores relationships between fault symptoms, causes, and solutions, enabling rapid retrieval during diagnosis without requiring real-time expert analysis

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a digital copy of expert knowledge by extracting and structuring repair expertise into a machine-readable knowledge graph. This copying transforms implicit expert experience into explicit structured data that can be rapidly queried, replacing time-consuming human expert consultation with automated knowledge retrieval

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If traditional fault diagnostic methods are used, then repair knowledge cannot be effectively consolidated, but implementing a knowledge graph requires complex data processing

Engineering Contradiction:

Improveknowledge consolidation capabilityVSAvoiddata processing complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the complex knowledge consolidation process into distinct operational phases: data collection from multiple sources, entity extraction to identify key elements, relationship recognition to establish connections, and knowledge graph construction to organize the structured data. This segmentation makes the complex task manageable and systematic

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary entity extraction and relationship recognition module that acts as a mediator between raw repair data and the final knowledge graph. This intermediary layer processes unstructured data into structured formats, bridging the gap between complex source data and the organized knowledge representation

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12536231B2Method for constructing knowledge graph and method for diagnosing vehicle faults

Publication Date: 2026.01.27 CAROTA TECHNOLOGY CORPORATION

AI summary

The disclosure provides a method for constructing a knowledge graph for vehicle fault diagnosis. The method can comprise creating a database of vehicle components; creating a database of abnormal signals; creating a fault knowledge triple from existing unstructured fault diagnostic data and semi-structured fault diagnostic data; and associating the abnormal signal, the vehicle component and the repair suggestion based on the fault knowledge triples to construct the knowledge graph for vehicle fault diagnosis.