公开(公告)号：US20240419484A1

公开(公告)日：2024-12-19

申请号：US18817035

申请日：2024-08-27

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

Inventor： Haifeng WANG ,  Hua WU ,  Hao TIAN ,  Jing LIU ,  Hongyu LI ,  Yingqi QU ,  Qifei WU

IPC: G06F9/48

Abstract: A method for processing information is provided. The method includes obtaining input information to be processed. The method further includes determining execution information associated with processing of the input information. The execution information includes at least one of memory information to be retrieved or tool information to be invoked. The method further includes obtaining, by using the execution information, at least one piece of processing result information corresponding to the processing of the input information. The method further includes the at least one piece of processing result information to generate output information for feedback.

公开(公告)号：US20230061398A1

公开(公告)日：2023-03-02

申请号：US17984034

申请日：2022-11-09

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

Inventor： Shangwen LYU ,  Hongyu LI ,  Jing LIU ,  Hua WU ,  Haifeng WANG

IPC: G06V30/19 ,  G06V30/412 ,  G06V30/194 ,  G06F40/205

Abstract: A method for training a document reading comprehension model includes: acquiring a question sample and a rich-text document sample, in which the rich-text document sample includes a real answer of the question sample; acquiring text information and layout information of the rich-text document sample by performing OCR processing on image information of the rich-text document sample; acquiring a predicted answer of the question sample by inputting the text information, the layout information and the image information of the rich-text document sample into a preset reading comprehension model; and training the reading comprehension model based on the real answer and the predicted answer. The method may enhance comprehension ability of the reading comprehension model to the long rich-text document, and save labor cost.

公开(公告)号：US20250004771A1

公开(公告)日：2025-01-02

申请号：US18755148

申请日：2024-06-26

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

Inventor： Haifeng WANG ,  Hua WU ,  Dai DAI ,  Jing LIU ,  Hongyu LI ,  Gangqiang HU

IPC: G06F9/30 ,  G06F40/20

Abstract: A method, apparatus, device, and medium for generating instruction data is provided. The method includes: obtaining a natural language-based reference instruction to direct a large model to generate response data meeting multiple first requirements; obtaining a structured disassembly result of the reference instruction to derive several reference slots and slot values corresponding to these requirements; determining multiple sample slots and sample slot values based on the reference slots, slot values, and a predetermined rule; and generating a natural language-based sample instruction from these sample slots and values, which directs the large model to generate response data that fulfills multiple second requirements.