fix(auto_reply): 添加连词/副词到停用词列表
- 新增"所以""应该""但是""如果"等连词到_STOPWORDS - 新增"哪里""呢"等疑问词到停用词 - 修复'所以那登录插件应该去哪里下载呢?'被误过滤问题 - 核心词从5个降到2个(登录、下载),核心词覆盖阈值从3降到1
This commit is contained in:
+4
-2
@@ -89,12 +89,14 @@ class AutoReply:
|
||||
"给","把","被","让","请","该","此","为","等","其","将","时","后","前",
|
||||
"会","能","要","想","没","不","别","快","如","若","知","都","也","就",
|
||||
"已","再","更","最","很","太","较","但","却","因","故","则","且",
|
||||
# 连词/副词:这些词不应参与核心词匹配
|
||||
"所以", "应该", "但是", "如果", "因为", "而且", "或者", "即使",
|
||||
# 方言语气词(东北话等)——用户常问"那搁哪儿"、"咋整"等,这些不应参与核心词匹配
|
||||
"那搁", "搁哪儿", "去哪儿", "哪儿", "哪能", "咋地", "咋整", "咋说",
|
||||
# 疑问代词
|
||||
"哪个", "那个", "这个", "哪些", "什么",
|
||||
"哪个", "那个", "这个", "哪些", "什么", "哪里",
|
||||
# 语气助词
|
||||
"啊", "呀", "么", "嘛",
|
||||
"啊", "呀", "么", "嘛", "呢",
|
||||
# 通用名词,出现在太多文档中导致误匹配
|
||||
"服务器","玩家","游戏","世界","地图","技能","装备","物品","命令","指令",
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user