Open AccessA Retrieval Method for Chinese EMR Based on Semantic Knowledge Map
Author(s) -
Hao Li,
Runtong Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1861/1/012036
Subject(s) - computer science , information retrieval , explicit semantic analysis , semantic mapping , ranking (information retrieval) , semantic computing , semantic network , concept search , text retrieval , natural language , natural language processing , artificial intelligence , semantic technology , search engine , semantic web , web search query
Due to the diversity of natural language in Chinese electronic medical records, it is usually hard for traditional retrieval methods to provide ideal results. On this condition, this paper proposes a retrieval method for Chinese EMR based on semantic knowledge map. Through natural language processing and semantic analysis, we can build connections for medical knowledge, and organize all the entities into a visual knowledge map. After that, a novel retrieval method based on semantic knowledge map is proposed, which focuses on node connection of documents and terms. Through semantic extension and intention spread, the improved retrieval results are returned, and the results are reordered by correlation. Compared with general methods, this method can significantly improve the accuracy of Chinese EMR text retrieval and optimize the ranking strategy of retrieval results.