Beijing Baidu Netcom Science Technology Co., Ltd

Beijing Qihoo Technology Company Limited

State Grid Corporation of China (sgcc)

Guo Dian Tong Network Technology Company Limited

State Grid Information & Telecommunications Branch Ltd.

Liang Wu

Haifeng Wang

Errui Ding

Ning Li

Tian Wu

Huan Ren

Junyu Han

Jingdong Wang

Xiaoyan Wang

Chengquan Zhang

Shanshan Liu

Jianming Liu

Kun Yao

Pengyuan Lv

Fengyu Wang

Aimei Yan

Xiaobin Zong

Jiye Wang

Yangliu Xu

Meina Qiao

Yuanguo Wu

The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.

Character recognition model training method and apparatus, character recognition method and apparatus, device and storage medium

The invention discloses a method and apparatus for optimizing the running of a browser. The method comprises: obtaining information of browser processes at the browser side and their first resource occupation information; obtaining information of currently running processes of a computer system where the browser is located and their second resource occupation information through a browser interface; loading and displaying information of at least a part of processes which meet a preset resource occupation optimization setting in the obtained information of the browser processes and information of the currently running processes of the computer system where the browser is located and/or their resource occupation information at the browser side; and according to an optimization instruction triggered by a user, performing process optimization processing to the displayed at least a part of processes. By the invention, resource occupation situations of all processes to be optimized can be presented to a user, thereby facilitating the selection of the process optimization processing by the user, and then the optimization processing is performed to the process selected by the user, to increase the running speed of the browser.

Method and apparatus for displaying information to a user and the user optimizing running of the processes

A system for intelligent electric power utilization of park and a method thereof are provided. The system includes an acquisition system, a data processing system, an application system and a service system through which the acquisition system, the data processing system and the application system are connected to external system. The application system includes an intelligent interaction application subsystem, an electric power utilization monitoring application subsystem, an energy efficiency analysis application subsystem, an orderly electric power utilization application subsystem, a system security application subsystem and a man-machine interaction interface. Enterprise users are leaded to actively carry out requirement response. Energy conservation and emission reduction and peak shaving and valley filling are effectively realized in intelligent park. Capability of intelligent electric power utilization of the park is improved. Accordingly, load balancing capability of region is improved and safe and stable operation of the power grid is ensured.

Intelligent power utilization system and method for parks

Growing community of inventors

Beijing, China

Liang Wu