使用分词模糊查询优化医院的匹配

2024-08-16 16:04:59 +08:00
parent 729167abca
commit 478f98abfd
4 changed files with 68 additions and 19 deletions
--- a/util/data_util.py
+++ b/util/data_util.py
@@ -184,5 +184,6 @@ def parse_hospital(string):
    string = util.traditional_to_simple_chinese(string)
    string_without_brackets = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")
    string_without_company = string_without_brackets.replace("有限公司", "")
-    result += string_without_company.split(" ")
+    split_hospitals = string_without_company.replace("医院", "医院 ")
+    result += split_hospitals.strip().split(" ")
    return result