公开(公告)号：US20210383233A1

公开(公告)日：2021-12-09

申请号：US17101748

申请日：2020-11-23

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

Inventor： Weiyue SU ,  Shikun FENG ,  Zhifan ZHU ,  Weibin LI ,  Jingzhou HE ,  Shiwei HUANG

IPC: G06N3/08 ,  G06N3/04

Abstract: The disclosure discloses a method for distilling a model, an electronic device, and a storage medium, and relates to the field of deep learning technologies. A teacher model and a student model are obtained. The second intermediate fully connected layer is transformed into an enlarged fully connected layer and a reduced fully connected layer based on a first data processing capacity of a first intermediate fully connected layer of the teacher model and a second data processing capacity of a second intermediate fully connected layer of the student model. The second intermediate fully connected layer is replaced with the enlarged fully connected layer and the reduced fully connected layer to generate a training student model. The training student model is distilled based on the teacher model.

公开(公告)号：US20210397947A1

公开(公告)日：2021-12-23

申请号：US17116291

申请日：2020-12-09

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

Inventor： Weibin LI ,  Zhifan ZHU ,  Shikun FENG ,  Jingzhou HE ,  Shiwei HUANG

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments of the present disclosure provide a method for generating a model for representing heterogeneous graph node. A specific implementation includes: acquiring a training data set, wherein the training data set includes node walk path information obtained by sampling a heterogeneous graph according to different meta paths; and training, based on a gradient descent algorithm, an initial heterogeneous graph node representation model with the training data set as an input of the initial heterogeneous graph node representation model, to obtain a heterogeneous graph node representation model.

公开(公告)号：US20210397794A1

公开(公告)日：2021-12-23

申请号：US17249718

申请日：2021-03-10

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

Inventor： Xuyi CHEN ,  Shiwei HUANG

IPC: G06F40/30 ,  G06N3/04 ,  G06N3/08

Abstract: Embodiments of a method and an apparatus for improving a model based on a pre-trained semantic model are provided. The method may include: based on the pre-trained semantic model, obtaining an initial improved model, where semantic result information of an input vector is determined in the initial improved model based on a hash search method; and based on a model distillation method, training the initial improved model to obtain an improved model. Some embodiments can obtain the semantic result information of the input vector by performing the hash search method on the input vector, replace the original complex iterative calculation process of a semantic model, and obtain the improved model with few model parameters and high compression ratio.

公开(公告)号：US20180181628A1

公开(公告)日：2018-06-28

申请号：US15845713

申请日：2017-12-18

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

Inventor： Jiaxin LIN ,  Wei BI ,  Tixi HE ,  Zhisheng WANG ,  Yingbin SU ,  Yuhui CAO ,  Rui CHEN ,  Zhihui LIU ,  Yan ZHANG ,  Chao ZHOU ,  Shuo HUANG ,  Jingzhou HE ,  Guyue ZHOU ,  Shiwei HUANG ,  Di JIANG ,  Lei SHI

IPC: G06F17/30 ,  G06N3/08

CPC classification number: G06F16/248 ,  G06F16/2457 ,  G06F16/337 ,  G06F16/9535 ,  G06K9/00442 ,  G06K9/627 ,  G06N3/0427 ,  G06N3/08

Abstract: The present disclosure provides a method and an apparatus for providing information based on artificial intelligence. The method includes: determining a characteristic of interest of the user according to historical access records of the user; and displaying an information card matched with the characteristic of interest in an information displaying interface, the information card including core contents of news matched with the characteristic of interest determined by analyzing news in a database.

公开(公告)号：US20170255879A1

公开(公告)日：2017-09-07

申请号：US15392017

申请日：2016-12-28

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

Inventor： Li CHEN ,  Qian XU ,  Hao TIAN ,  Jingzhou HE ,  Lei SHI ,  Fan WANG ,  Shiwei HUANG ,  Derong ZHENG

IPC: G06N99/00 ,  G06F17/30

CPC classification number: G06N20/00 ,  G06F16/90335 ,  G06F16/904 ,  G06N7/005

Abstract: A searching method and device based on artificial intelligence is provided in the present disclosure. The searching method includes: obtaining a query; obtaining a first search result corresponding to the query according to a Markov Decision Process MDP model; displaying the first search result; and obtaining a reward for the first search result from a user so as to obtain a second search result according to the MDP model, and displaying the second search result. According to the searching method, the interaction with the user may be more effective, the user's demand is better satisfied, and the user experience is improved.