A Semantic Analysis and Community Detection-Based Artificial Intelligence Model for Core Herb Discovery from the Literature: Taking Chronic Glomerulonephritis Treatment as a Case Study

Algorithm 1

CHDSC.

Input: the collected literature, standard herb name dictionary D, the size of context windows , filtering threshold R;

Output: core herb set ;

Stage 1 Corpus construction

C₁ = Word-segmentation ();

C₂ = Font-conversion (C₁);

C = Redundant-information-removal (C₂);

Stage 2 Herb network establishment

Step 1 Semantic analysis

;

Step 2 Name entity recognition

;

For each word in C

 If

   and ;

End For

Step 3 Semantic similarity calculation

 Calculate by equation (12);

Step 4 Herb network establishment

;

For each herb in

 If

  ;

End For

Stage 3 Core herb discovery

Step1 Herb community discovery

;

Step 2 Core herb discovery

For each community in

  herbs represented by the nodes having top-8 degree in ;

 ;

End For

Return