优化“病区”的处理

docker-compose.yml

@@ -1,6 +1,6 @@
 x-env:
   &template
-  image: fcb_photo_review:1.12.12
+  image: fcb_photo_review:1.12.13
   restart: always
 
 services:

photo_review/__init__.py

@@ -85,19 +85,16 @@ DEPARTMENT_ALIAS = {
 # 默认会过滤单字
 HOSPITAL_FILTER = ["医院", "人民", "第一", "第二", "第三", "大学", "附属"]
 
-DEPARTMENT_FILTER = ["医", "病", "病区", "伤", "西", "新"]
+DEPARTMENT_FILTER = ["医", "伤", "西", "新"]
 
 """
 分词配置
 """
 jieba.suggest_freq(("肿瘤", "医院"), True)
-jieba.suggest_freq(("心血管", "病"), True)
 jieba.suggest_freq(("骨", "伤"), True)
 jieba.suggest_freq(("感染", "性"), True)
 jieba.suggest_freq(("胆", "道"), True)
 jieba.suggest_freq(("脾", "胃"), True)
-jieba.suggest_freq(("肺", "病"), True)
-jieba.add_word("病区", 10000)
 
 """
 模型配置

util/data_util.py

@@ -106,6 +106,7 @@ def parse_department(string):
     string = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")  # 去除括号
     string = re.sub(r'[^⺀-鿿 ]', '', string)  # 去除非汉字字符，除了空格
     string = re.sub(r'[一二三四五六七八九十]', '', string)  # 去除中文数字
+    string = string.replace("病区", "").replace("病", "")  # 去除常见的无意义词
     string = string.replace("科", " ")  # 分离科室
     departments = string.strip().split(" ")
     for department in departments: