A Shared-Task-State-Driven Multi-Agent Framework for Knowledge Graph Construction in Substation Operation and Maintenance
- 1Guangdong Power Grid Co., Ltd., Guangzhou 510600, China
- 2School of Artificial Intelligence and Robotics, Hunan University, Changsha 410082, China
Abstract
Knowledge graph construction typically involves data preprocessing, entity recognition, relation extraction, knowledge fusion, conflict resolution, and quality assessment. However, heterogeneous documents in substation operation and maintenance (O&M), including technical standards, defect records, work tickets, operational logs, and scanned or mixed-format documents, exhibit dense domain terminology, inconsistent expressions, cross-source conflicts, and incomplete provenance, which make accurate and traceable knowledge construction challenging. Existing large-language-model-based and pipeline-based methods have improved automatic knowledge extraction, but their processing stages are usually weakly coupled, making it difficult to reuse cross-stage evidence, trace downstream errors to responsible upstream tasks, and perform targeted rework. To address these limitations, this paper proposes a shared-task-state-driven multi-agent collaborative knowledge graph construction framework (MAC-CKG). The framework introduces a task orchestrator and a shared task-state pool to coordinate five agents for data processing, entity recognition, relation extraction, knowledge fusion, and quality assessment; provenance, confidence, conflict, and review information are preserved across stages, while ontology constraints, multifactor confidence, and the two-threshold quality-routing mechanism jointly support knowledge insertion, human review, and targeted rework. For evaluation, we constructed a heterogeneous substation O&M dataset comprising 96 heterogeneous source items (including documents and structured knowledge resources) and 17,220 standardized input units, yielding a provenance-verified candidate subset of 9519 entities and 9258 relations. An independently annotated 20-document end-to-end benchmark was separately used for raw-document extraction evaluation. Across three independent runs on this benchmark, MAC-CKG achieves mean entity, conditional relation, and strict triple F1 scores of 85.96%, 62.50%, and 62.31%, respectively, outperforming SAC-KG by 2.83, 5.77, and 6.34 percentage points and PiVe by 4.48, 8.32, and 8.94 percentage points. Independent-benchmark ablation further reduces triple F1 from 62.31% to 59.68% without task orchestration and to 57.41% without the shared task-state pool, showing sensitivity to these components under the evaluated configurations, with inference cost considered separately.
Related
- The construction and operation of type IV pili impose a variable energetic burden across phylogenetically distant bacteria
- STAMM: Soft sensor moniToring and mAintenance framework for Machine learning Models
- TRACE: a framework for traceable biomedical resource construction demonstrated through single-cell glaucoma data
- An integrated fuzzy multi-criteria decision making and mixed-integer linear programming optimization framework for project risk assessment and response strategy selection: A case study of a liquefied petroleum gas pipeline construction project
- Projecting the real through active inference: a unified model of reality construction from neuronal dynamics to social consensus a neuroscientific framework for psychopathology
BibTeX
@article{huang2026sharedtaskstatedriven,
title = {{A Shared-Task-State-Driven Multi-Agent Framework for Knowledge Graph Construction in Substation Operation and Maintenance}},
author = {Linqing Huang and Wenyong Chen and Shuo Yu and Chaoduan Deng and Bin Sun},
journal = {Applied Sciences},
year = {2026},
month = oct,
doi = {10.3390/app162010394},
url = {https://doi.org/10.3390/app162010394},
note = {CC BY},
}
RIS
TY - JOUR
TI - A Shared-Task-State-Driven Multi-Agent Framework for Knowledge Graph Construction in Substation Operation and Maintenance
AU - Linqing Huang
AU - Wenyong Chen
AU - Shuo Yu
AU - Chaoduan Deng
AU - Bin Sun
PY - 2026
DA - 2026/10/26
JO - Applied Sciences
DO - 10.3390/app162010394
UR - https://doi.org/10.3390/app162010394
AB - Knowledge graph construction typically involves data preprocessing, entity recognition, relation extraction, knowledge fusion, conflict resolution, and quality assessment. However, heterogeneous documents in substation operation and maintenance (O&M), including technical standards, defect records, work tickets, operational logs, and scanned or mixed-format documents, exhibit dense domain terminology, inconsistent expressions, cross-source conflicts, and incomplete provenance, which make accurate and traceable knowledge construction challenging. Existing large-language-model-based and pipeline-based methods have improved automatic knowledge extraction, but their processing stages are usually weakly coupled, making it difficult to reuse cross-stage evidence, trace downstream errors to responsible upstream tasks, and perform targeted rework. To address these limitations, this paper proposes a shared-task-state-driven multi-agent collaborative knowledge graph construction framework (MAC-CKG). The framework introduces a task orchestrator and a shared task-state pool to coordinate five agents for data processing, entity recognition, relation extraction, knowledge fusion, and quality assessment; provenance, confidence, conflict, and review information are preserved across stages, while ontology constraints, multifactor confidence, and the two-threshold quality-routing mechanism jointly support knowledge insertion, human review, and targeted rework. For evaluation, we constructed a heterogeneous substation O&M dataset comprising 96 heterogeneous source items (including documents and structured knowledge resources) and 17,220 standardized input units, yielding a provenance-verified candidate subset of 9519 entities and 9258 relations. An independently annotated 20-document end-to-end benchmark was separately used for raw-document extraction evaluation. Across three independent runs on this benchmark, MAC-CKG achieves mean entity, conditional relation, and strict triple F1 scores of 85.96%, 62.50%, and 62.31%, respectively, outperforming SAC-KG by 2.83, 5.77, and 6.34 percentage points and PiVe by 4.48, 8.32, and 8.94 percentage points. Independent-benchmark ablation further reduces triple F1 from 62.31% to 59.68% without task orchestration and to 57.41% without the shared task-state pool, showing sensitivity to these components under the evaluated configurations, with inference cost considered separately.
SN - 2076-3417
ER -