优化医院名繁简转换

docker-compose.yml

@@ -1,6 +1,6 @@
 x-env:
   &template
-  image: fcb_photo_review:1.12.2
+  image: fcb_photo_review:1.12.3
   restart: always
 
 services:

photo_review/__init__.py

@@ -69,6 +69,7 @@ HOSPITAL_ALIAS = {
     "江阴徐霞客医院": ["江阴市徐霞客医院"],
     "江阴北国医院": ["江阴市北国医院"],
     "溧阳茶亭医院": ["溧阳市茶亭医院"],
+    "南京市六合中医院": ["南京市六合区中医院"]
 }
 
 """

requirements.txt

@@ -1,5 +1,6 @@
 numpy==1.26.4
 onnxconverter-common==1.14.0
+OpenCC==1.1.9
 opencv-python==4.6.0.66
 paddle2onnx==1.2.3
 paddleclas==2.5.2

util/data_util.py

@@ -181,8 +181,8 @@ def parse_hospital(string):
     if not string:
         return result
 
+    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", "")
-    simple_chinese_string = string_without_company.replace("醫", "医")
+    result += string_without_company.split(" ")
-    result += simple_chinese_string.split(" ")
     return result

util/util.py

@@ -2,6 +2,8 @@ import logging
 import os
 from datetime import datetime
 
+from opencc import OpenCC
+
 from util import string_util
 
 
@@ -209,3 +211,9 @@ def chinese_money_to_number(chinese_money_amount):
     amount += j / 10
     amount += f / 100
     return round(amount, 2)
+
+
+# 将繁体字转换为简体字
+def traditional_to_simple_chinese(traditional_chinese):
+    converter = OpenCC('t2s')
+    return converter.convert(traditional_chinese)