Beijing Boe Optoelectronics Technology Co., Ltd.

Boe Technology Group Co., Ltd.

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

Beijing Baidu Netcom Science Technology Co., Ltd

Boe Technology Groupco., Ltd.

China Aerospace Times Electronics Co., Ltd

Aerospace Internet of Things Technology Co., Ltd

Hao Dong

Jing Li

Peng Wang

Lei Jia

Yong Liu

Wenyu Zhang

Da Xu

Guibin Wang

Qinggeng Qian

Yaqian Zhang

Zhiheng Liu

Xuelin Yang

Liangjie Li

Shijun Cong

Fengting Shen

Junjun Li

Chunlei Zheng

Lin Gao

Xuedong Zhao

A method for compressing a neural network model includes acquiring a to-be-compressed neural network model. A first bit width, a second bit width and a target thinning rate corresponding to the to-be-compressed neural network model are determined. A target value is obtained according to the first bit width, the second bit width and the target thinning rate. Then the to-be-compressed neural network model is compressed using the target value, the first bit width and the second bit width to obtain a compression result of the to-be-compressed neural network model.

Method and apparatus for compressing neural network model

Disclosed is an intelligent scheduling table generation method based on multi-source data analysis of buses, including following steps: integrating business data and cashier data of a bus scheduling system, analyzing the running situation of each line by using an intelligent scheduling algorithm, calculating passenger flow data of boarding and dropping off buses according to cashier data of card swiping for boarding buses, and scientifically and reasonably obtaining the data of each line in the intelligent scheduling table, such as of the number of upgoing and downgoing vehicles, departure time periods, planned shifts, planned circle time, so as to obtain the intelligent scheduling table which accords with the characteristics of morning, midday and evening peak of each line and adjusts the departure interval in real time according to the actual running situation of the lines.

Intelligent scheduling table generation method based on multi-source data analysis of buses

A masking process and a mask set. The masking process includes: aligning a first mask with a stage carrying a substrate to be patterned; forming a first layer structure and a first overlay correction pattern on the substrate to be patterned by using the first mask; correcting with an image sensor and the first overlay correction pattern; aligning a second mask with the stage; forming a second layer structure and a second overlay correction pattern on the substrate to be patterned by using the second mask; and correcting with the image sensor and the second overlay correction pattern.

Masking process and mask set

Embodiments of the present disclosure disclose a method and apparatus for displaying an interface. A specific embodiment of the method comprises: acquiring device related information of a connected device; querying display interface information corresponding to the device related information of the connected device; and displaying a corresponding interface based on the display interface information. According to the embodiment, a smart terminal can display the corresponding interface according to the connected device, thereby improving the efficiency of acquiring the information by the user.

Method and apparatus for displaying interface

The present disclosure relates to a detection panel, a manufacturing method thereof and a detection device. The detection panel comprises: a base substrate and a photoelectric conversion structure located on the base substrate, and a display structure located on a side of the photoelectric conversion structure facing away from the base substrate and electrically connected to the photoelectric conversion structure; wherein the photoelectric conversion structure is configured to convert an optical signal into an electrical signal, and the display structure is configured to perform image display according to the electrical signal.

Detection panel, manufacturing method thereof and detection device

Growing community of inventors

Beijing, China

Hao Dong