Traditional Chinese medicine case modeling method based on semantic grammar and fault-tolerant analyzer

• Main Authors: WANG DONGSHENG, FENG YUE, TANG KANGJIE, ZENG JUN, PAN YUE, ZHOU MIAOMIAO
• Format: Patent
• Language: Chinese; English
• Published: 26.03.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a traditional Chinese medicine case modeling method based on a semantic grammar and a fault-tolerant analyzer. The method comprises the following steps: step 1, preprocessing a traditional Chinese medicine case text by a natural language processing method; 2, constructing a semantic grammar of a traditional Chinese medicine case through an FSTD method, and screening subsets to be matched and analyzed; step 3, forming a target semantic parsing tree through the optimized Earley parser; 4, obtaining word classes and grammar production forms of the candidate vocabulary entries according to the parse tree, and performing filtering and semantic correction; 5, performing structured extraction to obtain a structured traditional Chinese medicine case; step 6, decomposing the fact set and the judgment set containing multiple meanings into multiple fact sets and judgment sets only having single meanings; and 7, constructing a traditional Chinese medicine case model through the fact set and the ju