A Novel Dual-Strategy Approach for Constructing Knowledge Graphs in the Home Appliance Fault Domain

• Published in: Algorithms Vol. 18; no. 8; p. 485
• Main Authors: Zhang, Daokun, Zhang, Jian, Jia, Yanhe, Liao, Mengjie
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2025
• Subjects: Alignment; Datasets; Decision making; Fault diagnosis; home appliance faults; Home appliances; Household appliances; knowledge graphs; Knowledge representation; Large language models; Machine learning; Maintenance and repair; Manufacturing; named entity recognition; Recognition; relationship extraction; Texts; Unstructured data; China
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a18080485

Knowledge graph technology holds significant importance for efficient fault diagnosis in household appliances. However, the scarcity of public fault diagnosis data and the lack of automated knowledge extraction pose major challenges to knowledge graph construction. To address issues such as ambiguous entity boundaries, severe entity nesting, and poor entity extraction performance in fault diagnosis texts, this paper proposes a dual-strategy progressive knowledge extraction framework. First, to tackle the high complexity of fault diagnosis texts, an entity recognition model named RoBERTa-zh-BiLSTM-MUL-CRF is designed, improving the accuracy of nested entity extraction. Second, leveraging the semantic understanding capability of large language models, a progressive prompting strategy is adopted for ontology alignment and relation extraction, achieving automated knowledge extraction. Experimental results show that the proposed named entity recognition model outperforms traditional models, with improvements of 3.87%, 5.82%, and 2.05% in F1-score, recall, and precision, respectively. Additionally, the large language model demonstrates better performance in ontology alignment compared to traditional machine learning models. The constructed knowledge graph for household appliance fault diagnosis integrates structured fault diagnosis information. It effectively processes unstructured fault texts and supports visual queries and entity tracing. This framework can assist maintenance personnel in making rapid judgments, thereby improving fault diagnosis efficiency.