Huawei Technologies Co., Limited

Yanming Li

Bin Wang

Renzhi Yang

Teng Fei Zhang

Li Zhou

Zhicheng Sui

Jiyong Jiang

A method for establishing an end-to-end network connection includes obtaining, by a first node, super node information from a server, obtaining, by the first node, a network address translation (NAT) type of the first node, obtaining, by the first node, a NAT type of a to-be-connected second node from the server, determining, by the first node based on the NAT type of the first node and the NAT type of the second node, whether to use a relay node, and selecting, by the first node, the relay node from super nodes to establish a connection to the second node.

Method and apparatus for establishing end-to-end network connection, and network system

Embodiments of this application disclose a communication method and a related device. The method includes: A symmetric device listens on N local public ports, where N is a natural number greater than 1; and when the symmetric device receives a hole punching packet from the N local public ports, the symmetric device sends a response packet to a cone device based on the hole punching packet, so that the symmetric device establishes a communication connection to the cone device, where the hole punching packet is sent by the cone device, and the response packet carries a first network information mapping relationship. The cone device may directly communicate with the symmetric device, so that there is no need for a server having a data relay function, and costs of deploying the server are reduced.

Communication method and related device

A voice information processing method includes: receiving, by a terminal, voice information, and converting the voice information into text information; obtaining a field probability that the text information belongs to each of preset M event fields; obtaining a prior probability that the text information belongs to each of N event fields, where N&#x2264;M; obtaining confidence that the text information belongs to each of the N event fields; calculating, based on the field probability, the prior probability, and the confidence that the text information belongs to each of the N event fields, values of N probabilities that the text information separately belongs to the N event fields; and outputting a semantic understanding result of performing semantic understanding based on an event field corresponding to a largest probability value in the N probability values.

Growing community of inventors

Shanghai, China

Yanming Li