In order to prevent the occurrence of chemical accidents derived from storage and transportation accidents of hazardous chemicals, the accident risk identification process is optimized to reduce the reliance on manual work. Firstly, from the perspective of Chinese corpus, based on the incorporation of many semantic information, the hazardous chemicals accident entities are extracted by Multi-Granularity Dilated Convolution Networks using Co-Predictor Layer to infer the relationship between words; then, for the entities that have been extracted, positional coding is incorporated to recognize the object of each subject as well as the corresponding multiple relations to achieve the Hazardous Chemicals Incident Relationship Recognition. The results show that the F1 value of the Namedity Extraction model reaches 92.91% and 96.59% in the self-constructed and public datasets, respectively, and the F1 value of the Relation Recognition model reaches 76.04%; the performance of the two models improves compared with the existing methods, and the Relation Recognition model, in particular, has a clear advantage and achieves a performance lead of 6.28%. Named Entity Recognition of hazardous chemicals and Relation Extraction further establishes the hazardous chemicals Eventic Graph and early warning system.
CHENW J. A Case of the Environmental Risk Assessment of the Storage and Transportation of Chemical Hazardous Articles[J]. Fujian Environ, 2003(5): 27-30.
[4]
YUANC F, WANGH, CHENY. The Hierarchical Risk Source Identification Method Connected with Event Causal Chain in the Emergency Process of Fire Accident of Petroleum Storage and Transportation[J]. Appl Mech Mater, 2014, 501: 2411-2414. DOI:10.4028/www.scientific.net/amm.501-504.2411 .
WANGH Y, ZHAOD F, MENGY F, et al. Dynamic Risk Analysis Model for the Oil-container Overflow Scenario Based on the Bayesian Network and Precursor Events[J]. J Saf Environ, 2018, 18(2): 446-450. DOI: 10.13637/j.issn.1009-6094.2018.02.007 .
[7]
JEC H, STONER, OBERGS G. Development and Application of a Multi-channel Monitoring System for near Real-time VOC Measurement in a Hazardous Waste Management Facility[J]. Sci Total Environ, 2007, 382(2/3): 364-374. DOI:10.1016/j.scitotenv.2007.04.017 .
JIAJ Z, CHENY N. Fire Risk Assessment of the High-rise Buildings Based on the Network Hierarchical Analysis-gray Clustering Method[J]. J Saf Environ, 2020, 20(4): 1228-1235. DOI: 10.13637/j.issn.1009-6094.2019.0751 .
MAQ Y, ZHANGM S, DINGZ C, et al. The Building and Application of a New Model of Digital Intelligence Supervision and Control of Customs Hazardous Chemicals Based on Deep Learning[J]. China Port Sci Technol, 2024, 6(4): 41-48. DOI: 10.3969/j.issn.1002-4689.2024.04.008 .
[12]
SONGY X, SUNP L, LIUH Y, et al. Scene-driven Multimodal Knowledge Graph Construction for Embodied AI[J]. IEEE Trans Knowl Data Eng, 2024, 36(11): 6962-6976. DOI:10.1109/TKDE.2024.3399746 .
[13]
FANZ L, CHENC C. CuPe-KG: Cultural Perspective-Based Knowledge Graph Construction of Tourism Resources via Pretrained Language Models[J]. Inf Process Manag, 2024, 61(3): 103646. DOI:10.1016/j.ipm.2024.103646 .
[14]
LIUZ K, LUY Q. A Task-centric Knowledge Graph Construction Method Based on Multi-modal Representation Learning for Industrial Maintenance Automation[J]. Eng Rep, 2024, 6(12): e12952. DOI:10.1002/eng2.12952 .
[15]
GAOJ L, PENGP, LUF, et al. Mining Tourist Preferences and Decision Support via Tourism-oriented Knowledge Graph[J]. Inf Process Manag, 2024, 61(1): 103523. DOI:10.1016/j.ipm.2023.103523 .
[16]
LIUT. From Knowledge Graph to Event Evolutionary Graph[R]. Shanghai: CCF YOCSEF, 2017.
[17]
SUNX K, MENGY, WANGW L. Identifying Traffic Events from Weibo with Knowledge Graph and Target Detection[J]. Data Analysis and Knowledge Discovery, 4(12): 136-147. DOI: 10.11925/infotech.2096-3467.2020.0596 .
LIG, WANGS Y, MAOJ, et al. Construction of National Security Event Map and Its Application for Situation Awareness[J]. J China Soc Sci Tech Inf, 2021, 40(11): 1164-1175. DOI: 10.3772/j.issn.1000-0135.2021.11.004 .
LIS X, SHENY, WANGL, et al. Construction and Evolution Analysis of the Event Map for Mycoplasma Pneumonia Network Public Opinion[J/OL]. Inf Sci, 2024: 1-22. (2024-09-12).
[25]
LIJ Y, FEIH, LIUJ, et al. Unified Named Entity Recognition as Word-word Relation Classification[J]. Proc AAAI Conf Artif Intell, 2022, 36(10): 10965-10973. DOI:10.1609/aaai.v36i10.21344 .
[26]
DEVLINJ, CHANGM W, LEEK, et al. Bert: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, PA: ACL, 2019: 4171-4186. DOI: 10.18653/v1/N19-1423 .
[27]
CUIY M, CHEW X, WANGS J, et al. Lert: A Linguistically-motivated Pre-trained Language Model[EB/OL]. (2022-11-11)[2025-09-08].
[28]
WEIZ P, SUJ L, WANGY, et al. A Novel Cascade Binary Tagging Framework for Relational Triple Extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: ACL, 2020: 1476-1488. DOI:10.18653/v1/2020.acl-main.136 .
[29]
FUT J, LIP H, MAW Y. GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: ACL, 2019: 1409-1418. DOI:10.18653/v1/p19-1136 .
[30]
ZENGX R, ZENGD J, HES Z, et al. Extracting Relational Facts by an End-to-end Neural Model with Copy Mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: USA: ACL, 2018: 506-514. DOI:10.18653/v1/p18-1047 .