Boe Technology Group Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

International Business Machines Corporation

Chengdu Boe Optoelectronics Technology Co., Ltd.

Baidu USA LLC

Hefei Boe Optoelectronics Technology Co., Ltd.

Chongqing Boe Optoelectronics Technology Co., Ltd.

Baidu.com Times Technology (beijing) Co. Ltd.

Chongqing Boe Display Technology Co., Ltd.

The Procter Gamble Company

Baidu Online Network Technology (beijing) Co., Ltd.

Beijing Jingdong Qianshi Technology Co., Ltd.

Beijing Jiaotong University

Xu Liang Li

Jiangliang Guo

Minghao Liu

Jiabing Leng

Yawei Wen

Yulin Xu

Xin Zhang

Wei Shan Dong

Peng Gao

Chun Ma

Guo Qiang Hu

Chang Li

Liqiang Chen

Yang Liang

Yaming Wang

Shiming Yin

Shuangshuang Qiao

Xiangyue Lin

Shuo Li

Zhi Hu Wang

Jun Feng Liu

Zhi Jun Wang

Wentao Wang

Ping Li

Dawei Shi

Wei Dai

Lu Yang

Kun Liu

Mingming Sun

Faen Zhang

Pei Wang

Dingcheng Li

Chao Han

Can Huang

Yucheng Li

Zuojia Wang

Dongdong Zhao

Cenhong Duan

Hening Zhang

Jin Tang

Haibin Liu

Jinjun Wang

Shikang Ge

Jingbo Huang

Fei Pan

Xufeng Tu

Mingfa Zhu

Huihui Xiao

Bangwei Wu

Xueyan Liu

Ming Wang

Ping Zhang

Wei Chen

Jean-Luc Philippe Bettiol

Paulus Antonius Augustinus Hoefte

Xing Fan

Xinyu Wang

Zhihui Zhang

Penghao Gu

Yanxin Wang

Hongliang Fei

Rui Hou

Hua Chai

Huifeng Shen

Hao Gao

Yunfei Zhang

Le Chang

Wesley Yvonne Pieter Boers

Peter Vancampenhout

Gang Wu

Jinhong Zhang

Lei Nie

Jiali Wang

Chengcheng Wang

Yujie Wang

Chuntong Jiang

Jun Ge

Yinchu Zhao

Suxuan Gong

Xiangchao Chen

You Zheng

Olga Lahuerta Salas

Xinqing Zhu

Yongxing Li

Jun Xie

Siyu An

Zhuqing Zhang

Hilal Sahin Topkara

Ye Su

Yanan Liang

Zhongsen He

Xueqiang Gao

Emilie Hourcade

Zuoxiang He

Kweonho Park

Fuze Sun

Hang Jiang

Yunfeng Cai

A flexible display panel and a preparation method therefor, and a display device and a display module are provided. The flexible display panel includes a planar area, a first bending area, a second bending area and a corner bending area. The corner bending area is connected to a corner of the planar area and is connected between the first bending area and the second bending area, and is provided with a plurality of first hole groups, where the corner bending area is bent with a width of a first hole group in middle of the corner bending area increasing and a width of a first hole group in an edge area on a side of the corner bending area away from the planar area decreasing.

Flexible display panel and preparation method therefor, and display device and display module

A method for constructing a multistage network includes: deploying a plurality of nodes; constructing the upper network with at least one node of the plurality of nodes; and in response to determining there is an isolated node, determining an intermediate node for the isolated node and adding the isolated node into the upper network or one of the at least one sub-network according to the intermediate node.

Method for constructing multistage network, related method and device

A flexible display screen includes: a flexible substrate (); an OLED device layer () formed on the flexible substrate (); an encapsulation layer(), disposed on the OLED device layer() and encapsulating the OLED device layer (); and an encapsulation protection layer () formed on the encapsulation layer (). The embodiments of the present disclosure also provide a flexible display device and a manufacturing method of the flexible display screen.

Flexible display screen including encapsulation protection layer, flexible display device, and manufacturing method thereof

A method for discovering causality from data includes acquiring to-be-processed data, and obtaining a covariance matrix of the to-be-processed data; determining a first target column in the covariance matrix, taking the number of columns of the first target column as a first place in a rearrangement sequence, and obtaining a first upper triangular matrix according to the first target column; determining a position of the number of columns of the covariance matrix other than the first target column except the first place in the rearrangement sequence according to the first target column and the first upper triangular matrix, and obtaining an upper triangular matrix in each position determination; obtaining an adjacency matrix according to an upper triangular matrix and a rearrangement sequence obtained in final position determination; and generating directed acyclic graph (DAG) by using the adjacency matrix, and taking the DAG as causality discovery result of the to-be-processed data.

Method for discovering causality from data, electronic device and storage medium

Described herein are embodiments of a reinforcement learning based large-scale multi-objective ranking system. Embodiments of the system may be used for optimizing short-video recommendation on a video sharing platform. Multiple competing ranking objective and implicit selection bias in user feedback are the main challenges in real-world platform. In order to address those challenges, multi-gate mixture of experts (MMoE) and soft actor critic (SAC) are integrated together into a MMoE_SAC system. Experiment results demonstrate that embodiments of the MMoE_SAC system may greatly reduce a loss function compared to systems only based on single strategies.

Video recommendation with multi-gate mixture of experts soft actor critic

Provided are a display substrate and a preparation method thereof, and a display apparatus. The display substrate includes a first display region and a second display region within the first display region, wherein the first display region includes a plurality of emitting units, and the second display region includes a plurality of electrophoretic units, the plurality of emitting units are configured to realize display, and the plurality of electrophoretic units are configured to realize switch between a display state and a transparent state.

Display substrate and preparation method thereof, and display apparatus

Embodiments of the disclosure provide a display panel and a display device. The display panel includes a substrate, a plurality of light emitting elements and at least one transmissive-reflective module, where the light emitting elements are arranged on the substrate; each of the light emitting elements includes a first electrode, a light emitting functional layer and a second electrode arranged along a direction vertical to the substrate and away from the substrate; the at least one transmissive-reflective module is arranged on a side, close to the substrate, of the first electrode of at least one of the light emitting elements, and/or on a side, away from the substrate, of the second electrode of at least one of the light emitting elements; the transmissive-reflective module is configured to switch between a transmissive state and a reflective state.

Display panel and display device

Embodiments of the present disclosure provide a method and a device for detecting defect of a meal box, a server, a device, and a storage medium. The method includes: receiving a detection request including an image of the meal box sent by a user terminal, the image of the meal box being obtained by an image acquirer of the user terminal; and performing defect recognition based on the image of the meal box and a defect detection model in response to the detection request.

Method and device for detecting defect of meal box, server, and storage medium

Described herein are embodiments for end-to-end reinforcement learning based coreference resolution models to directly optimize coreference evaluation metrics. Embodiments of a reinforced policy gradient model are disclosed to incorporate reward associated with a sequence of coreference linking actions. Furthermore, maximum entropy regularization may be used for adequate exploration to prevent a model embodiment from prematurely converging to a bad local optimum. Experiments on datasets compared with state-of-the-art methods verified the effectiveness of embodiments.

Systems and methods for end-to-end deep reinforcement learning based coreference resolution

The present disclosure provides an OLED display substrate, a fabricating method thereof and a display device. The OLED display substrate includes a substrate; an inorganic layer and a light-emitting unit on substrate, light-emitting unit being on a side of inorganic layer away from substrate and including a light-emitting structure; a camera on a side of substrate away from inorganic layer, and light-emitting unit being not in orthographic projection region; a protective layer in orthographic projection region and on side of inorganic layer away from substrate, wherein protective layer is configured to protect inorganic layer in orthographic projection region from warping or cracking in a process of removing part of light-emitting structure in orthographic projection region by laser cutting.

OLED display substrate comprising camera and protective layer, fabricating method thereof, and display device

Embodiments of the present disclosure provide a method and apparatus for predicting a severe convection weather. The method may include: acquiring a current radar echo map sequence, the current radar echo map sequence being a radar echo map sequence within a current time period; generating, based on the current radar echo map sequence, a future radar echo map sequence, the future radar echo map sequence being a radar echo map sequence within a future time period; and inputting the future radar echo map sequence into a pre-trained severe convection weather predicting model to obtain a severe convection weather intensity predicting map, where the severe convection weather predicting model is used to predict the intensity of a severe convection weather.

Method and apparatus for predicting severe convection weather

A method and an apparatus for generating a model are provided. The method includes: acquiring a sample set including sample sentences and labeling knowledge corresponding thereto; and selecting a sample from the sample set, and performing following training steps: inputting a sample sentence into a first initial model to generate first prediction knowledge corresponding to the sample sentence; inputting the first prediction knowledge into a second initial model to generate a first prediction sentence corresponding to the first prediction knowledge; inputting labeling knowledge into the second initial model to generate a second prediction sentence corresponding to the labeling knowledge; inputting the second prediction sentence into the first initial model to generate a second prediction knowledge corresponding to the second prediction sentence; determining a first reward signal; and training, using a reinforcement learning method based on the first reward signal to obtain a first model.

Method and apparatus for generating model

Provided are a method for detecting display screen quality, an apparatus, an electronic device and a storage medium. The method includes: receiving a quality detection request sent by a console deployed on a display screen production line, the quality detection request including a display screen image collected by an image collecting device on the display screen production line; inputting the display screen image into a defect detection model to obtain a defect detection result, the defect detection model being obtained by training historical defective display screen images using a structure of deep convolutional neural networks and an object detection algorithm; and determining, according to the defect detection result, a defect on a display screen corresponding to the display screen image, a defect category corresponding to the defect, and a position corresponding to the defect.

Method for detecting display screen quality, apparatus, electronic device and storage medium

Embodiments of the present disclosure provides a method and apparatus for inspecting burrs of an electrode slice. The method may include: acquiring a to-be-inspected electrode slice image; and inputting the to-be-inspected electrode slice image into a pre-trained burr instance segmentation model to obtain inspection result for characterizing whether the electrode slice displayed in the to-be-inspected electrode slice image has burrs and contour of the burrs, where the burr instance segmentation model is used to characterize the corresponding relationship between the electrode slice image and the inspection result and contour information. The method may further include: and outputting, in response to the inspection result for characterizing that the electrode slice displayed in the to-be-inspected electrode slice image has burrs, prompt information for characterizing that the electrode slice displayed in the to-be-inspected electrode slice image has burrs.

Method and apparatus for inspecting burrs of electrode slice

Growing community of inventors

Beijimg, China

Xu Liang Li