A rule-based safety filter for Vietnamese home-robot commands.
The model flags commands that contain obviously dangerous actions such as
burning, destroying objects, or harming people.
This is a simple demonstration and should be combined with stronger safety systems in real robots.
1from model import check_safety
2
3print(check_safety("Bật đèn phòng khách"))
4print(check_safety("Đốt rèm cửa đi"))
