Huawei Technologies Co., Limited

Future Wei Technologies, Inc.

Huawei Cloud Computing Technologies Co., Ltd.

Shenzhen Shijinyuan Technology Co., Ltd.

Pu Chen

Guangsong Xia

Tianxi Xu

Fei Wang

Wei Yan

Qiang Zheng

Xiucheng Yuan

Qiaobo Liao

Kaizhi Wei

Trap

A model training system includes a cloud data storage platform and a cloud model training platform. The cloud data storage platform is configured to: store training data; and receive a training data calling request, and export training data corresponding to a data calling instruction to the cloud model training platform based on the training data calling request. The cloud model training platform is configured to: receive a model training creation instruction to obtain a to-be-trained model; generate the training data calling request, and send the training data calling request to the cloud data storage platform; and train the to-be-trained model by using the training data exported from the cloud data storage platform, to obtain a training result model. In the technical solutions of the present invention, a risk of leaking training data can be reduced.

Model training system and method, and storage medium

Fly repellent fan

An algorithm download method, a device, and a related product. The method includes: obtaining an algorithm identifier of an algorithm and a capability description of a client; sending the algorithm identifier and the capability description to a cloud; and receiving a version code that is of the algorithm and that is returned by the cloud, where the version code is obtained by the cloud by searching based on the algorithm identifier and the capability description. According to the foregoing solution, an algorithm can be easily downloaded.

Algorithm downloading method, device, and related product

Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components access to communicate with a GPU at a different component or physical machine in a data center or a network. A first physical machine starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The rendered graphics is then sent to the client via the gateway.

System for distributed virtualization of GPUs in desktop cloud

A redirection method and apparatus, and a system, where the method includes capturing, by a virtual machine running on a server, an interface invocation request initiated by an application program, encapsulating, by the virtual machine, a serialization result into a data packet, sending the data packet to a client device, where the serialization result is obtained after serialization of an interface name and an interface parameter included in the interface invocation request, reconstructing, by the client device based on the serialization result and the interface name that are included in the data packet, the interface invocation request, and accessing a human interface device based on the interface invocation request to implement redirection for the human interface device. Hence, the redirection method improves stability of a redirection process.

Redirection method and apparatus, and system

A data communication method, and a user equipment relate to the communications field and implement isolation for programs using a container technology. The user equipment includes a host machine running on a hardware layer of the user equipment, and at least one container running on the host machine, where each container corresponds to a different container instance. The user equipment determines whether an application program runs in a safe mode when a start instruction for running the application program is received, and performs security authentication with a server when the application program runs in the safe mode. The user equipment starts the application program in a container instance selected by a user when the security authentication succeeds, and performs data communication with the server using a communication channel corresponding to the selected container instance.

Data communication method, user equipment, and server

The application relates to an image display method, apparatus, and system. An application program running on a server initiates an image display instruction for displaying an image on a remote client. The image is processed at the server according to an image processing policy which corresponds to the type or the name of the application program, and the processed image is sent to the remote client for display. The image processing policy takes into consideration of requirements of the client, thus the problem of mismatching between the processed image and the capacities of the client is avoided.

Image display method and apparatus

Embodiments are provided to enable graphic processing unit (GPU) virtualization for high bandwidth or rate demanding applications, such as 3D gaming, where a client communicates with a host via a virtual desktop infrastructure (VDI). The distributed GPU virtualization allows one or more VMs or comparable hosts or components without GPU access to communicate with a GPU at a different component or physical machine in a data center or a network using remote direct memory access (RDMA). A first physical machine that excludes a GPU starts a remote display driver function to handle a request to render graphics from a client via gateway. A second physical machine that comprises a GPU is instructed to start a render function for the client using the GPU. The render function communicates with the remote display driver function at the first physical machine. The rendered graphics is then sent to the client via the gateway.

System and method for distributed virtualization of GPUs in desktop cloud

A method for remotely running an application program. A client acquires an application program from a server, runs the application program on the client, and detects whether the application program triggers an application programming interface (API) invocation request. If the application program triggers the API invocation request, the client determines that the client or the server executes API invocation according to a preset invocation policy. A device resource of the client can be used to execute a part of the API invocation, which enhances efficiency in remote running of the application program and improves user experience. In addition, the latest data obtained according to a result of application program running can be saved onto the server, which ensures data access security.

Method and apparatus for remotely running application program

The time required to login to a remote or virtual desktop can be reduced by caching image data in a persistent memory location in-between remote desktop sessions. For instance, image data related to an image displayed on a client device during a first virtual desktop session may be cached after terminating the first virtual desktop session. The cached data can then be used to display the same image, or a correlated image, on the client device during a subsequent remote desktop session, thereby avoiding the need to re-transport the image data over a network. In a similar manner, cached image data can be shared between multiple users sharing a common local area network (LAN) in order to improve collective virtual desktop performance.

Virtual desktop infrastructure (VDI) login acceleration

A method for scheduling distributed buffer resources is provided, where in the distributed buffer system, each buffer node is distributed on a virtual circle that is based on a consistent hashing algorithm, and the method includes: monitoring a load value of each buffer node in the distributed buffer system; judging whether a load exception exists in the current distributed buffer system according to the load value; and if the load exception exists in the current distributed buffer system, adjusting a layout of the buffer nodes in the distributed buffer system.

Method, apparatus, and system for scheduling distributed buffer resources

Embodiments of the present invention provide an image display method, apparatus, and system. After an image display instruction is obtained, an application program that triggers the image display instruction is determined, and an image is processed according to the application program and is sent to a client for display. Because image processing is performed according to an application program currently triggered by the client, a determined image processing policy meets current application requirements of the client, which avoids the problem in the prior art that an image finally displayed on the client does not meet current application requirements of the client when an image processing policy is determined according to image type recognition.

Growing community of inventors

Shenzhen, China

Pu Chen