收藏切换
Research on Multi-dimensional Named Entity Recognition in Traditional Chinese Medicine Cases
收藏切换
Junbai CHEN1, Fengying GUO1, Butian ZHAO1, Songxing DU2, Tian TIAN3, Zhanfeng YAN4, Li WANG1
Chinese Archives of Traditional Chinese Medicine | 2026, 44(2) : 17 - 23
Less
收藏切换
Chinese Archives of Traditional Chinese Medicine | 2026, 44(2): 17-23
• Digital Traditional Chinese Medicine •
Research on Multi-dimensional Named Entity Recognition in Traditional Chinese Medicine Cases
Full
Junbai CHEN1, Fengying GUO1, Butian ZHAO1, Songxing DU2, Tian TIAN3, Zhanfeng YAN4, Li WANG1
Affiliations
  • 1.Management school of Beijing University of Chinese Medicine,Beijing 102488,China
  • 2.Dongfang Hospital,Beijing University of Chinese Medicine,Beijing 100078,China
  • 3.School of Traditional Chinese Medicine,Beijing University of Chinese Medicine,Beijing 102488,China
  • 4.Dongzhimen Hospital,Beijing University of Chinese Medicine,Beijing 100700,China
Published: 2026-02-10 doi: 10.13193/j.issn.1673-7717.2026.02.004
Outline
收藏切换
Objective

To solve the problem of poor recognition performance of current traditional Chinese medicine case naming entity recognition models,and to improve the efficiency and accuracy of the structuring of traditional Chinese medicine cases.

Methods

A BDM-CRF named entity recognition neural network model was constructed to integrate multi-dimensional information. The model integrated Bidirectional Long Short-Term Memory(BiLSTM),Gated-Dilated Convolutional Neural Networks(DGCNN)and Multi-Head Attention(MHA)models for multi-dimensional feature extraction. The feature extraction results were constrained by the Conditional Random Field(CRF)model. The effectiveness of the model was verified through comparative experiments,ablation experiments,pre-training model comparison experiments and neural network structure comparison experiments,validating and demonstrating the extraction performance of the model through case analysis.

Results

The model proposed in this study achieved an average improvement of 2.30% in precision,4.73% in recall and 3.53% in F1 score compared to those of the control model. The case analysis results indicated that the model in this study can correctly identify most of the entity content in the text of traditional Chinese medicine medical cases.

Conclusion

The proposed model for the named entity recognition in traditional Chinese medicine(TCM)medical records,which integrates multi-dimensional information,can achieve better recognition results,effectively improve the accuracy and efficiency of TCM medical record structuring,and promote the intelligent processing of TCM medical records.

TCM case records  /  named entity recognition  /  neural network  /  model fusion
陈隽柏, 郭凤英, 赵步天, 杜松星, 田甜, 闫占峰, 王丽. 融合多维度信息的中医医案命名实体识别算法研究. 中华中医药学刊, 2026 , 44 (2) : 17 -23 . DOI: 10.13193/j.issn.1673-7717.2026.02.004
Junbai CHEN, Fengying GUO, Butian ZHAO, Songxing DU, Tian TIAN, Zhanfeng YAN, Li WANG. Research on Multi-dimensional Named Entity Recognition in Traditional Chinese Medicine Cases[J]. Chinese Archives of Traditional Chinese Medicine, 2026 , 44 (2) : 17 -23 . DOI: 10.13193/j.issn.1673-7717.2026.02.004
Year 2026 volume 44 Issue 2
89
12
Cite this Article
BibTeX
Article Info
doi: 10.13193/j.issn.1673-7717.2026.02.004
  • Online Date:2026-10-14
  • Published:2026-02-10
Article Data
Affiliations
History
Affiliations
    1.Management school of Beijing University of Chinese Medicine,Beijing 102488,China
    2.Dongfang Hospital,Beijing University of Chinese Medicine,Beijing 100078,China
    3.School of Traditional Chinese Medicine,Beijing University of Chinese Medicine,Beijing 102488,China
    4.Dongzhimen Hospital,Beijing University of Chinese Medicine,Beijing 100700,China
References
Share
https://castjournals.cast.org.cn/joweb/zhzyyxk/EN/10.13193/j.issn.1673-7717.2026.02.004
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT