SERVICE OFFLOADING METHOD, DEVICE, AND SYSTEM
    2.
    发明申请
    SERVICE OFFLOADING METHOD, DEVICE, AND SYSTEM 审中-公开
    服务卸载方法,设备和系统

    公开(公告)号:US20160182313A1

    公开(公告)日:2016-06-23

    申请号:US15015863

    申请日:2016-02-04

    Abstract: The present application provides a service offloading method, a device, and a system, and relate to the mobile communications field. The method includes: sending attribute information of a first network to a network controller of a second network, where the attribute information includes identity information of the first network or a combination of identity information and status information of the first network; sending quality information of service to the network controller of the second network, receiving the service offloading indication fed back by the network controller; and selecting, according to the received service offloading indication, a bearer network for a service requested by user equipment, thereby achieving an effect that the network controller of the second network can perform service offloading appropriately according to a network status of the first network, the network status of the second network, and the quality information of service, so as to improve network utilization.

    Abstract translation: 本申请提供服务卸载方法,设备和系统,并且涉及移动通信领域。 该方法包括:向第二网络的网络控制器发送第一网络的属性信息,其中属性信息包括第一网络的身份信息或第一网络的身份信息和状态信息的组合; 向第二网络的网络控制器发送服务质量信息,接收由网络控制器反馈的服务卸载指示; 以及根据所接收的服务卸载指示,选择用户设备所请求的业务的承载网络,从而实现所述第二网络的网络控制器可以根据所述第一网络的网络状态适当地执行服务卸载的效果, 网络状态,服务质量信息,提高网络利用率。

    CALL PROCESSING METHOD AND SYSTEM, AND DEVICE

    公开(公告)号:US20240333819A1

    公开(公告)日:2024-10-03

    申请号:US18742483

    申请日:2024-06-13

    CPC classification number: H04L67/60 G06F9/547

    Abstract: Embodiments of this application provide a call processing method and system, and a device, to transfer call chain information during call. After obtaining a first call request, when receiving a second call request that carries a first thread identifier, a first agent server of a first node can input, into a header file of the second call request based on a first mapping relationship, second call chain information obtained through processing based on first call chain information, to obtain a third call request, where the first mapping relationship is a mapping relationship between the first call chain information and the first thread identifier. In this way, the first node does not need to perform call chain-related processing in a process of generating the second call request, thereby achieving zero intrusion of a service into a call chain.

    MEMORY MANAGEMENT METHOD AND APPARATUS
    4.
    发明公开

    公开(公告)号:US20230236971A1

    公开(公告)日:2023-07-27

    申请号:US18192175

    申请日:2023-03-29

    CPC classification number: G06F12/0802

    Abstract: This disclosure provides a memory management method and apparatus, to perform refined management on a process access status in a physical host, a virtual machine, or a container, and a traffic occupation status of each control group (cgroup). The method can includes a first record table corresponding to a target cache page is used to record all cgroups that have read or written target data from or into the target cache page and a quantity of times that the target data is read or written by all the cgroups, to improve accuracy of a traffic statistics result of a cgroup. In this case, throttling is performed on a first cgroup based on an updated first record table, so that throttling on the first cgroup can be more fair and accurate.

    METHOD AND APPARATUS FOR SEQUENCE PROCESSING

    公开(公告)号:US20230088915A1

    公开(公告)日:2023-03-23

    申请号:US17994068

    申请日:2022-11-25

    Abstract: This application provides a method and apparatus for sequence processing, relates to the field of artificial intelligence, and specifically relates to the field of sequence data processing. The method includes: receiving an input sequence (S410); performing self-attention calculation on a first element in the input sequence by using an element included in M windows, to obtain a representation of the first element, where each window includes one element or a plurality of consecutive elements in the input sequence, there is an interval of at least one element between different windows, at least one of the M windows does not include the first element, and M is an integer greater than or equal to 1 (S420); and obtaining, based on the representation of the first element, an output sequence corresponding to the input sequence (S430).

    MAN- MACHINE INTERACTION SYSTEM AND MULTI-TASK PROCESSING METHOD IN THE MAN-MACHINE INTERACTION SYSTEM

    公开(公告)号:US20210166693A1

    公开(公告)日:2021-06-03

    申请号:US17171166

    申请日:2021-02-09

    Abstract: The application relates to the field of man-machine interaction in artificial intelligence and provides a multi-task processing method. The method includes the following operations: determining a first task based on request information entered by a user; obtaining key information corresponding to the first task and executing the first task, where the key information includes one or more slots and values of the one or more slots; storing task status information of the first task, where the task status information includes the key information; and predicting and initiating a second task based on the task status information of the first task. A man-machine interaction system may predict a next task based on the stored task status information, and actively initiate the predicted task. This improves intelligence and efficiency of multi-task processing by the man-machine interaction system.

    METHOD FOR ACCESSING NETWORK BY USER EQUIPMENT, AND ACCESS DEVICE

    公开(公告)号:US20180199248A1

    公开(公告)日:2018-07-12

    申请号:US15917104

    申请日:2018-03-09

    CPC classification number: H04W36/0077 H04W36/14 H04W76/28 H04W88/06

    Abstract: Embodiments of the present invention provide a method for accessing a network by a UE, and an access device. The method includes: sending, by a source side access device, an access indication message to a UE, where the access indication message is used to instruct the UE to access a target side access device; or sending, by a source side access device, a first notification message to a target side access device, where the first notification message is used to instruct the target side access device to send, to a UE, access information used to instruct the UE to access the target side access device; and in a process in which the UE accesses the target side access device, maintains a connection between the UE and the source side access device, therefore, a service interruption is not caused.

    SYNTAX ANALYSIS METHOD AND APPARATUS
    8.
    发明申请

    公开(公告)号:US20180157634A1

    公开(公告)日:2018-06-07

    申请号:US15872993

    申请日:2018-01-17

    CPC classification number: G06F17/271 G06F17/2827 G06F17/2836

    Abstract: A syntax analysis method and apparatus are disclosed. The method includes: obtaining a source language sentence that is a translation of a target language sentence (S110); determining instances of state transition for the target language sentence according to the source language sentence and a correspondence between words of the target language sentence and words of the source language sentence (S120); and generating a syntax tree of the target language sentence according to the instances of state transition for the target language sentence (S130). The syntax analysis method and apparatus can improve efficiency of syntax analysis.

    TEXT PROCESSING METHOD, MODEL TRAINING METHOD, AND APPARATUS

    公开(公告)号:US20220147715A1

    公开(公告)日:2022-05-12

    申请号:US17526832

    申请日:2021-11-15

    Abstract: This application relates to the field of artificial intelligence, and provides a text processing method, a model training method, and an apparatus. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

    MODEL TRAINING METHOD AND APPARATUS
    10.
    发明公开

    公开(公告)号:US20230177410A1

    公开(公告)日:2023-06-08

    申请号:US18161620

    申请日:2023-01-30

    CPC classification number: G06N20/20 G06F9/54

    Abstract: A model training method applied to the field of artificial intelligence is disclosed. The method includes: sending a first submodel to a first device, where the first submodel is obtained by compressing a to-be-trained model; receiving a first gradient sent by the first device, where the first gradient is obtained when the first device trains the first submodel; and performing model training on the to-be-trained model based on at least the first gradient, to obtain an updated to-be-trained model. In the method, a server compresses the to-be-trained model and delivers the to-be-trained model to a terminal device, so that the terminal device does not need to train a large model with a same scale as that of the server.

Patent Agency Ranking