Study on Knowledge Map Construction of Fu Xing Jue Based on OCR-NLP Collaborative Resolution Technology

Bo Hou; Hao Luo; Yang Li; HanYu Shi

doi:10.54097/nbfc1639

Authors

Bo Hou
Hao Luo
Yang Li
HanYu Shi

DOI:

https://doi.org/10.54097/nbfc1639

Keywords:

OCR technology, NLP technology, knowledge atlas, Fu xing formula Zangfu medicine essentials, Dunhuang medicine.

Abstract

Against the backdrop of the digitization and intelligence of traditional medicine, this study employs the collaborative technology of optical character recognition and natural language processing to address the inheritance challenge of the Dunhuang medical literature "fu Xing Jue Zang-fu Organ Medication Method Yao", and constructs a "prescription - drug" knowledge graph. It mainly expounds the processes of data preprocessing, knowledge extraction and fusion, as well as graph construction. Through the application of the two techniques, the role of the two techniques in the transformation of Dunhuang medicine was revealed. The research results show that the integrated architecture of the two technologies not only has significant value in medical research, but also provides a new paradigm for the modernization, inheritance and innovation of Dunhuang medicinet.

Downloads

Download data is not yet available.

References

[1] Zhang L. Research on "General Micro-Prescriptions for Pediatric Health" of the Southern Song Dynasty [D]. Zhengzhou University, 2018.

[2] Lin SY, Qu YQ, Liu C, et al. Review of the Development of Artificial Intelligence in Traditional Chinese Medicine and Discussion on the Trend of Technology Integration. [J]. Chinese Journal of Traditional Chinese Medicine, 2020, 35(11): 5384–5389.

[3] Xie T, Yang JA, Liu H. Fusion of Multiple Features BERT Model for Chinese Entity Relation Extraction. [J]. Computer System Applications, 2021, 30(5): 253–261.

[4] Zhou LJ, Li ZA, Li X, et al. Knowledge Graph Construction for Pressure Pipeline Safety Inspection Using BERT-BiLSTM-CRF. [J]. China Petroleum and Chemical Standards and Quality, 2024, 44(8): 182–186.

[5] Zhou X. Enhancement of License Plate Character Image Clarity Based on Analogical Thought. [D]. Xidian University, 2012.

[6] Li C, Zhen KH, Tang DX, et al. Research on the Construction of Knowledge Graph Based on Prescription Dataset. [J]. World of Traditional Chinese Medicine, 2024, 19(9): 1329–1333.

[7] Wei L, YaJun D, XianYong L, et al. UDBBC: Named Entity Recognition in Social Network Combined BERT-BiLSTM-CRF With Active Learning. [J]. Engineering Applications of Artificial Intelligence, 2022, 116: 115123.

[8] Feng WK. Design and Implementation of a Triple Semi-Automatic Labeling System. [D]. Beijing University of Posts and Telecommunications, 2023.

[9] Lin WY. Research and Design of a Question-Answering System Based on the Knowledge Atlas of Special Local Products. [D]. Xiamen University, 2020.

[10] Su SS, Yang Y, Cheng MT, et al. Research on Electronic Medical Record Information Extraction Based on Rule Base. [J]. Chinese Digital Medicine, 2014, 9(7): 12–13+51.

[11] Jiang LH, Zhao RX, Dong CY, et al. Construction and Verification of a Visual Knowledge Graph of Aquatic Diseases Based on Deep Learning. [J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(15): 259–267.

[12] Ander B, Aitor S, Eneko A. Towards Zero-Shot Cross-Lingual Named Entity Disambiguation. [J]. Expert Systems With Applications, 2021, 184: 115584.