公开(公告)号：US20250117668A1

公开(公告)日：2025-04-10

申请号：US18987988

申请日：2024-12-19

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

Inventor： Xinran He ,  Xianwei Xue ,  Bolei He ,  Kunbin Chen ,  Jinchang Luo ,  Ruigao Li

IPC: G06N3/096 ,  G06N3/0475

Abstract: A method for model training based on a large model includes: determining a first large model as a teacher model of a language model, and performing distillation learning on the language model based on the first large model; inputting a first prompt text into the language model, and obtaining a plurality of first response texts for the first prompt text output by the language model; determining a reference response text for the first prompt text from the plurality of first response texts; and training the language model based on the reference response text for the first prompt text.

公开(公告)号：US20220358292A1

公开(公告)日：2022-11-10

申请号：US17813691

申请日：2022-07-20

Applicant: Beijing Baidu Netcom Science Technology Co., LTD.

Inventor： Fan Wang ,  Jinchang Luo ,  Jie Wang ,  Haiwei Wang ,  Kunbin Chen ,  Wei He

IPC: G06F40/295 ,  G06F16/33 ,  G06F16/35 ,  G06F16/31

Abstract: The disclosure provides a method for recognizing an entity, an electronic device and a storage medium. The method includes: obtaining message data to be processed; obtaining entity mention information by processing the message data to be processed according to a multi-pattern matching method; determining one or more candidate entities associated with the entity mention information and entity description information corresponding to the one or more candidate entities; and determining a target entity mentioned in the entity mention information according to the message data to be processed and the entity description information.