基于專業書籍和網頁數據的中醫藥知識圖譜設計與實現

摘要 中醫藥在中國有5 000多年的歷史，為中華民族的繁衍與健康發揮著重要作用。然而，中醫藥數據通常是非結構化的，這嚴重影響了中醫藥知識的普及與應用，因此將中醫藥數據進行結構化具有重要意義。對于中醫藥數據非結構化的問題，設計并實現了中醫知識圖譜。首先，選取了藥材、別名、功能主治等6種關系來構建中藥材知識圖譜的概念層；然后，利用6種關系從農業敘詞表等專業書籍和中醫藥網站上獲取數據，并對中醫藥知識進行數據處理，從而得到三元組形式的中醫藥知識；最終，將中醫知識存入Neo4j數據庫，并將其呈現出來。中醫藥知識圖譜的構建將大大提高中醫藥知識的可理解性和可訪問性，為后期臨床決策和中醫藥研究提供數據支持。

關鍵詞 中醫藥知識圖譜；關系；爬蟲技術；Neo4j

中圖分類號 S-058 文獻標識碼 A 文章編號 0517-6611（2024）21-0222-05

doi：10.3969/j.issn.0517-6611.2024.21.046

開放科學（資源服務）標識碼（OSID）：

Design and Implementation of TCM Knowledge Graph Based on Professional Books and Web Data

QIAO Bo， ZHOU Zi-hao， YUAN Quan

（College of Information and Intelligent Science and Technology， Hunan Agricultural University， Changsha， Hunan 410128）

Abstract Traditional Chinese medicine has a history of over 5000 years in China and plays an important role in the reproduction and health of the Chinese nation. However， traditional Chinese medicine data is usually unstructured， which seriously affects the popularization and application of traditional Chinese medicine knowledge. Therefore， structuring traditional Chinese medicine data is of great significance. For the problem of unstructured data in traditional Chinese medicine， we designed and implemented a knowledge graph of traditional Chinese medicine. Firstly， six relationships including medicinal herbs， aliases， and functional indications were selected to construct the conceptual layer of the knowledge graph of traditional Chinese medicine. Then， using six types of relationships， data was obtained from professional books such as agricultural lexicons and traditional Chinese medicine websites， and traditional Chinese medicine knowledge was processed to obtain triplet form of traditional Chinese medicine knowledge. Finally， the knowledge of traditional Chinese medicine would be stored in the Neo4j database and presented. The construction of a knowledge graph of traditional Chinese medicine would greatly improve the comprehensibility and accessibility of traditional Chinese medicine knowledge， providing data support for later clinical decision-making and traditional Chinese medicine research.

Key words A knowledge graph of traditional Chinese medicine;Relation;Crawler technique;Neo4j

基金項目 2022年度湖南省社會科學成果評審委員會課題（XSP22-YBZ024）。

作者簡介 喬波（1981—），男，湖南臨澧人，副教授，博士，碩士生導師，從事自然語言處理、農業知識圖譜與智慧農業研究。*通信作者，碩士研究生，研究方向：農業信息技術。

收稿日期 2024-06-30

中醫藥作為中國傳統醫學的重要組成部分，具有悠久的歷史和豐富的經驗。然而，隨著現代醫學的快速發展，中醫藥知識的傳承和發展面臨著諸多挑戰。目前，雖然存在很多中醫藥網站，但這些網站包含的中醫藥知識具有復雜的概念體系和龐大的知識量，而且這些知識往往呈現碎片化和信息孤島現象，導致用戶難以形成對中醫藥的全面認識［1］。……