Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm
Given the unstructured nature of text data related to hidden dangers in coal mine accidents, extracting latent knowledge is crucial for constructing a knowledge graph of hidden dangers in coal mine accidents. This study proposes annotation types for knowledge entities to describe hidden dangers in c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Emergency Management Press
2024-12-01
|
| Series: | 矿业科学学报 |
| Subjects: | |
| Online Access: | http://kykxxb.cumtb.edu.cn/en/article/doi/10.19606/j.cnki.jmst.2024915 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537089997373440 |
|---|---|
| author | LI Jing LI Zequan SHI Futai HAO Qiang |
| author_facet | LI Jing LI Zequan SHI Futai HAO Qiang |
| author_sort | LI Jing |
| collection | DOAJ |
| description | Given the unstructured nature of text data related to hidden dangers in coal mine accidents, extracting latent knowledge is crucial for constructing a knowledge graph of hidden dangers in coal mine accidents. This study proposes annotation types for knowledge entities to describe hidden dangers in coal mine accidents by analyzing the characteristics and latent information in the texts of hidden dangers based on their propagation patterns. Using the Brat annotation tool, we annotated the text data related to hidden dangers of coal mine accidents to construct a dataset for knowledge extraction model. We proposes a BERT-IDCNN-CRF model based on dynamic fusion and introduced a probabilistic fusion algorithm based on Newton's law of cooling. The results indicate that with the incorporation of the probabilistic fusion algorithm, the dynamically weighted BERT-IDCNN-CRF model achieved the best performance in the task of knowledge entity extraction from hidden danger texts. Its precision, recallrate, and F1-score improved by 8.93%, 5.28%, and 7.51%, respectively, significantly enhancing the model's prediction accuracy and stability, while demonstrating excellent adaptability. |
| format | Article |
| id | doaj-art-0722ce5b170845e096c3fcedd6f607a7 |
| institution | Kabale University |
| issn | 2096-2193 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Emergency Management Press |
| record_format | Article |
| series | 矿业科学学报 |
| spelling | doaj-art-0722ce5b170845e096c3fcedd6f607a72025-01-14T08:46:55ZengEmergency Management Press矿业科学学报2096-21932024-12-01961007101610.19606/j.cnki.jmst.2024915kykxxb-9-6-1007Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithmLI Jing0LI Zequan1SHI Futai2HAO Qiang3School of National Safety and Emergency Management, Qinghai Normal University, Xining Qinghai 810016, ChinaNorth China University of Science and Technology, Langfang Hebei 065201, ChinaHuating Coal Industry Group Co., Ltd., Pingliang Gansu 744100, ChinaHuaneng Coal Technology Research Co., Ltd., Beijing 100070, ChinaGiven the unstructured nature of text data related to hidden dangers in coal mine accidents, extracting latent knowledge is crucial for constructing a knowledge graph of hidden dangers in coal mine accidents. This study proposes annotation types for knowledge entities to describe hidden dangers in coal mine accidents by analyzing the characteristics and latent information in the texts of hidden dangers based on their propagation patterns. Using the Brat annotation tool, we annotated the text data related to hidden dangers of coal mine accidents to construct a dataset for knowledge extraction model. We proposes a BERT-IDCNN-CRF model based on dynamic fusion and introduced a probabilistic fusion algorithm based on Newton's law of cooling. The results indicate that with the incorporation of the probabilistic fusion algorithm, the dynamically weighted BERT-IDCNN-CRF model achieved the best performance in the task of knowledge entity extraction from hidden danger texts. Its precision, recallrate, and F1-score improved by 8.93%, 5.28%, and 7.51%, respectively, significantly enhancing the model's prediction accuracy and stability, while demonstrating excellent adaptability.http://kykxxb.cumtb.edu.cn/en/article/doi/10.19606/j.cnki.jmst.2024915hidden dangers in coal mine accidentsknowledge entity extractionk-fold cross-validationprobabilistic fusion |
| spellingShingle | LI Jing LI Zequan SHI Futai HAO Qiang Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm 矿业科学学报 hidden dangers in coal mine accidents knowledge entity extraction k-fold cross-validation probabilistic fusion |
| title | Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| title_full | Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| title_fullStr | Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| title_full_unstemmed | Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| title_short | Textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| title_sort | textual knowledge entity extraction of hidden dangers in coal mine accidents based on probabilistic fusion algorithm |
| topic | hidden dangers in coal mine accidents knowledge entity extraction k-fold cross-validation probabilistic fusion |
| url | http://kykxxb.cumtb.edu.cn/en/article/doi/10.19606/j.cnki.jmst.2024915 |
| work_keys_str_mv | AT lijing textualknowledgeentityextractionofhiddendangersincoalmineaccidentsbasedonprobabilisticfusionalgorithm AT lizequan textualknowledgeentityextractionofhiddendangersincoalmineaccidentsbasedonprobabilisticfusionalgorithm AT shifutai textualknowledgeentityextractionofhiddendangersincoalmineaccidentsbasedonprobabilisticfusionalgorithm AT haoqiang textualknowledgeentityextractionofhiddendangersincoalmineaccidentsbasedonprobabilisticfusionalgorithm |