公开(公告)号：US20230195839A1

公开(公告)日：2023-06-22

申请号：US17555723

申请日：2021-12-20

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

Inventor： Binghong WU ,  Yehui YANG ,  DaLU YANG ,  Yanwu XU ,  Lei WANG ,  Qian LI

IPC: G06K9/62

CPC classification number: G06K9/6257 ,  G06K9/6232 ,  G06K9/6201

Abstract: Technical solutions relate to the field of artificial intelligence such as deep learning, computer vision and intelligent imaging. A method may includes during training of a one-stage object detecting model, acquiring values of a loss function corresponding to feature maps at different scales respectively in the case that classification loss calculation is required, and the loss function is a focal loss function; and determining a final value of the loss function according to the acquired values of the loss function, and training the one-stage object detecting model according to the final value of the loss function.

公开(公告)号：US20210263974A1

公开(公告)日：2021-08-26

申请号：US17173318

申请日：2021-02-11

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

Inventor： Qian LI ,  Yabing SHI ,  Ye JIANG ,  Chunguang CHAI ,  Yong ZHU

IPC: G06F16/9032 ,  G06N3/04 ,  G06F16/906 ,  G06F16/903 ,  G06F40/30

Abstract: Provided by the present disclosure is a new category tag mining method, involving the field of knowledge graph technology, and including: obtaining a plurality of queries during a current preset time period; labeling a category tag on each query of the plurality of queries, by using a pre-trained sequence labeling model, to extract the category tag currently corresponding to the query from the query; and removing a category tag already existing in a preset current category tag library from category tags currently corresponding to all the queries, and determining a remaining category tag as a new category tag. The present disclosure also provides an electronic device and a non-transitory computer-readable storage medium.