公开(公告)号：US20240371259A1

公开(公告)日：2024-11-07

申请号：US18393376

申请日：2023-12-21

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

Inventor： Yixiong XIAO ,  Hao YUAN ,  Jingbo ZHOU

IPC: G08G1/01

Abstract: Provided is a source tracing method for traffic congestion, an electronic device and a storage medium, relating to the field of smart transportation, traffic management, traffic information processing and other technologies. The method includes: determining an undetermined road section and at least two reference road sections related to the undetermined road section from a target road network; obtaining a congestion infection distance between the undetermined road section and the reference road section within a target period; calculating a congestion time difference between a first congestion moment of the undetermined road section within the target period and a second congestion moment of the reference road section within the target period; and determining the undetermined road section as a congestion source of the target road network within the target period when determining that a correlation between the congestion infection distance and the congestion time difference meets a preset correlation requirement.

公开(公告)号：US20250139369A1

公开(公告)日：2025-05-01

申请号：US18956107

申请日：2024-11-22

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

Inventor： Jingbo ZHOU ,  Congxi XIAO ,  Yixiong XIAO ,  Jizhou HUANG

IPC: G06F40/284 ,  G06N20/00

Abstract: A method is provided that includes: obtaining first urban data of a first sample urban region; inputting the first urban data into a multi-modal foundation model to obtain respective predicted vector representations of a plurality of first data segments; obtaining a plurality of general-purpose foundation models that are pre-trained; for each general-purpose foundation model: generating a vector representation label of a first data segment of a corresponding data modality by using the general-purpose foundation model; and determining a knowledge distillation loss of the general-purpose foundation model based on the vector representation label and a predicted vector representation of the first data segment; and adjusting parameters of the multi-modal foundation model based on at least respective knowledge distillation losses of the plurality of general-purpose foundation models.

公开(公告)号：US20250103589A1

公开(公告)日：2025-03-27

申请号：US18974155

申请日：2024-12-09

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

Inventor： Yixiong XIAO ,  Jingbo ZHOU

IPC: G06F16/242

Abstract: Data query method and apparatus based on large model, an electronic device, and a storage medium are disclosed, which relates to the field of artificial intelligence, specifically in natural language processing, deep learning, and large model technologies, applicable to scenarios such as dialogue systems and information retrieval. The method includes: performing entity recognition on a query to obtain the target entity in the query; obtaining a first related content associated with the target entity from internal information, and performing data analysis on the first related content using a large language model (LLM) to obtain a data analysis result; obtaining a second related content associated with the target entity from external information, and performing data generation on the second related content using the LLM to obtain a data generation result; obtaining a query result corresponding to the query based on the data analysis result and the data generation result.