公开(公告)号：US20250077780A1

公开(公告)日：2025-03-06

申请号：US18748642

申请日：2024-06-20

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

Inventor： Yongkang Xie ,  Guming Gao ,  Penghao Zhao ,  Xue Xiong ,  Qian Wang ,  Dongze Xu ,  En Shi ,  Yuxuan Li ,  Sheng Zhou ,  Shupeng Li ,  Yao Wang ,  Zhou Xin

IPC: G06F40/30 ,  G06F40/40

Abstract: A method for invoking a plugin of a large language model includes: acquiring natural language content; performing semantic understanding on the natural language content and detecting whether the natural language content hits a plugin to obtain a first plugin pointed to by the plugin hit result; comparing the first plugin with a second plugin corresponding to the current session understanding task to determine a to-be-executed session understanding task and a third plugin corresponding to the to-be-executed session understanding task; acquiring the language understanding content of the to-be-executed session understanding task and sending the language understanding content to the large language model to obtain the input parameter of the third plugin; and calling the third plugin according to the input parameter of the third plugin to obtain the calling result of the to-be-executed session understanding task.

公开(公告)号：US20230065354A1

公开(公告)日：2023-03-02

申请号：US18049318

申请日：2022-10-25

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

Inventor： Fengzhi Qiu ,  Kai Zhou ,  Qian Wang ,  Quan Sun ,  Kai He ,  Heng Zhang ,  Guming Gao ,  Jing Yu

IPC: G06F9/50 ,  G06N3/04

Abstract: A method for sharing a resource, includes: generating, by a first AI node, an association relation between the first AI node and at least one other AI node, in which the association relation is configured to generate an AI federal network; receiving, by the first AI node, resource sharing information; determining, by the first AI node, a target AI node of sharing resources with the first AI node based on the resource sharing information; determining, by the first AI node, a target resource to be shared based on the resource sharing information; and sharing, by the first AI node, the target resource with the target AI node through the AI federal network. Therefore, AI nodes realize resource sharing through the AI federal network, which is suitable for resource sharing scenarios of multiple different AI nodes and has good scalability, thereby greatly reducing the development difficulty and cost of resource sharing.