Huawei Technologies Co., Limited

Zte Corporation

Tencent Technology (shenzhen) Company Limited

Webank Co., Ltd

Qiang Yang

Kai Chen

Yang Liu

Yang Gao

Chen Wang

Lu Zhang

Zhenwei Zhang

Zhuolin Jiang

Yangqiu Song

Wing Ki Leung

Zhengdong Lu

Yuchen Wang

Xiuqiang He

Tao Fan

Yanhui Geng

Fei Tang

Cairen Weng

Yan Kang

Ke Deng

Tianjian Chen

Yujia Weng

Yanping Cao

Dengjun Su

Chi-Yin Chow

A method for processing information by an intelligent agent and the intelligent agent, where the method comprises: a first intelligent agent sends a request message to a second intelligent agent, where the request message includes an invitation message or a recommendation message; the first intelligent agent receives a decision message fed back by the second intelligent agent, where the decision message is determined according to the invitation message or the recommendation message and a knowledge model of the second intelligent agent; and the first intelligent agent updates, according to the decision message, a knowledge model of the first intelligent agent or sends a notification message to a first user account corresponding to the first intelligent agent. By using these technical solutions, information on a social network may be learned and processed by means of interaction with another intelligent agent, thereby implementing mining of data on the social network.

Method for processing information by intelligent agent and intelligent agent

Disclosed are a model parameter training method and a terminal based on federation learning, and a medium. The method includes: determining a feature intersection of a first sample of the first terminal and a second sample of a second terminal, training the first sample based on the feature intersection to obtain a first mapping model, sending the first mapping model to the second terminal; receiving a second encryption mapping model sent by the second terminal, predicting a missing feature of the first sample of the first terminal according to the second encryption mapping model to obtain a first encryption supplementary sample; receiving a first encryption federation learning model parameter sent by a third terminal, training a federation learning model to be trained according to the first encryption federation learning model parameter, and calculating a first encryption loss value; and sending the first encryption loss value to the third terminal.

Model parameter training method, terminal, and system based on federation learning, and medium

A picture ranking method and a terminal comprises acquiring pictures stored in a terminal, detecting whether the pictures are first-type pictures, where a first-type picture refers to a picture including a human face, and when the pictures are first-type pictures, ranking the pictures according to a social relation model, or when the pictures are not first-type pictures, ranking the pictures according to a preset rule.

Picture ranking method, and terminal

A user behavior recognition method, a user equipment, a behavior recognition server, and a behavior recognition system are presented, where the method includes acquiring, by a first user equipment, statistical distribution information of a target parameter corresponding to a target user behavior, where the target parameter includes at least one parameter in a behavior recognition model of the target user behavior, and the statistical distribution information of the target parameter is determined according to values of the target parameters in behavior recognition models of the target user behavior that are respectively corresponding to multiple other user equipment; and creating and saving, according to the statistical distribution information, a behavior recognition model of the target user behavior, to recognize the target user behavior.

User behavior recognition method, user equipment, and behavior recognition server

An enhanced instant messaging processing method is presented to users in an instant messaging communication environment. For a user having two or more communication terminals that have logged into a same instant messaging account of the user, a communication server monitors invitations sent to the instant messaging account. Responsive to one communication terminal responding to the invitation and the type of the response, the communication server generates a response policy for each of other communication terminals of the user, where the response policy optimizes the instant communication performance and enhances the user experience. The disclosed embodiments also support simultaneous instant communications among a large number of users connected to multiple data processing servers. The disclosed solution for supporting simultaneous instant communications balances the load of the data processing servers while keeping multiple communication terminals of a user informed of the status of the instant communication.

Enhanced video instant messaging processing

The present application provides a path planning method and a controller. The method includes: acquiring data flow information of a to-be-transmitted job in a software-defined network, where the job includes at least one target data flow, and the data flow information of the job includes: a source address, a destination address, and a volume of each target data flow; and performing path planning according to the data flow information, and obtaining a job transmission path used to ensure that the job is transmitted in the software-defined network in a shortest job transmission time, where the job transmission path includes a transmission path corresponding to each target data flow in the job. The present application improves a data transmission speed of a job in an SDN network.

Path planning method and controller

A method and a system for processing lifelong learning of a terminal, and an apparatus is presented. The method for processing lifelong learning of a terminal according to the present disclosure includes sending, to a server, a request for downloading a function module, where the download request includes description information of the function module; receiving the function module that is sent by the server and is corresponding to the description information; and using the function module to expand and/or update a local function. According to the embodiments of the present disclosure, the lifelong learning of the terminal is implemented, and a problem in the prior art that the terminal cannot perform function expansion and updating is resolved.

Method and system for processing lifelong learning of terminal and apparatus

Embodiments of the present disclosure disclose a picture ranking method and a terminal. The picture ranking method comprises acquiring pictures stored in a terminal, detecting whether the pictures are first-type pictures, where the first-type picture refers to a picture including a human face, and when the pictures are first-type pictures, ranking the pictures according to a social relation model, or when the pictures are not first-type pictures, ranking the pictures according to a preset rule.

An enhanced instant messaging processing method is presented to users in an instant messaging communication environment. For a user having two or more communication terminals that have logged into a same instant messaging account of the user, a communication server monitors invitations sent to the instant messaging account. Responsive to one communication terminal responding to the invitation and the type of the response, the communication server generates a response policy for each of other communication terminals of the user, where the response policy optimizes the instant communication performance enhances the user experience. The disclosed embodiments also support simultaneous instant communications among a large number of users connected to multiple data processing servers. The disclosed solution for support simultaneous instant communications balances the load of the data processing servers while keeping multiple communication terminals of a user informed of the status of the instant communication.

A method for recognizing a target object in an image, and an apparatus, where the method includes extracting feature data from an image, and transforming the extracted feature data into a uniform expression, performing automatic clustering for features in the image according to the feature data in the uniform expression and a historical clustering result, grouping a target object of a known class included in an automatic clustering result into the corresponding known class, in order to recognize a target object of the known class in the image, and training a classifier in a machine learning manner, for a target object of an unknown class included in the automatic clustering result, in order to recognize a target object of an unknown class in the image. In the embodiments of the present invention, recognizing a target object of an unknown class can be implemented.

Method for recognizing target object in image, and apparatus

A method for determining virtual machine migration relates to the field of communications and can reduce a deployment cost. The method includes a client in a host machine obtains a unique identifier of a virtual machine on the host machine and an address of the host machine; and if the unique identifier of the virtual machine does not exist in a local record of the client, the client sends a packet to a server in a network in which the host machine is located, where the packet carries the unique identifier of the virtual machine and the address of the host machine, so that the server determines, according to the unique identifier of the virtual machine and the address of the host machine, whether the virtual machine is migrated; and the client adds the unique identifier of the virtual machine to the local record to update the local record.

Method and apparatus for determining virtual machine migration

A method for switching a session of an IP Multimedia Subsystem (IMS) network and an Emergency Access Transfer Function (EATF) entity are disclosed. The method includes: the EATF entity anchoring a call sent by a network element in a call initiation domain, and routing the call to an Emergency-Call Session Control Function (E-CSCF); the EATF entity receiving call transfer invite message sent by a network element in a call termination domain; and if identifying that the call transfer invite message is an invite message inviting to perform transfer of the call, the EATF entity performing media negotiation, and sending a response message carrying media information to the network element in the call termination domain.

Method for switching session of IMS network and EATF

The disclosure discloses a method for a service access of a user in an Access Gateway Control Function (AGCF) entity, wherein a corresponding relationship between a logic number and a physical number of the user in the AGCF entity is stored in a Home User Server (HSS), the method includes that: in a registration process initiated by the user, the AGCF entity acquires the corresponding relationship between the physical number of the user and the logic number of the user from the HSS and stores it. The disclosure further discloses a system for a service access of a user in an AGCF entity, the system includes: a first storage unit, located in the HSS and configured to store a corresponding relationship between the logic number of the user and the physical number of the user in the AGCF entity; a registration unit, configured to register the user; a first acquisition unit, configured to acquire the corresponding relationship between the physical number of the user and the logic number of the user from the HSS in a registration process initiated by the user; and a second storage unit, located in the AGCF entity and configured to store the corresponding relationship between the logic number of the user and the physical number of the user. The disclosure realizes very low maintenance cost during a diversion and other operation.

Growing community of inventors

Shenzhen, China

Qiang Yang