公开(公告)号：US20240338530A1

公开(公告)日：2024-10-10

申请号：US18745550

申请日：2024-06-17

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Zhen GUO ,  Wenquan WU ,  Hua WU ,  Haifeng WANG

IPC: G06F40/35 ,  G06N20/00

CPC classification number: G06F40/35 ,  G06N20/00

Abstract: A generative dialog model training method in the fields of artificial intelligence, such as deep learning, natural language processing, intelligent dialogs, is disclosed. The generative dialog model training method may include: in response to determination of an update of a safety specification, taking an updated safety specification as a target safety specification, and determining a dialog input corresponding to a current optimization according to the target safety specification, the update being performed on a previous safety specification when a generative dialog model after last optimization is determined not to meet a launch requirement; and optimizing the generative dialog model according to the dialog input and a principle that a reply generated by the generative dialog model conforms to the target safety specification, the generative dialog model being configured to generate the reply corresponding to the dialog input.