Abstract: This application discloses a communication method and a communications apparatus. A first radio network management function network element that can provide a service-based interface is introduced between an access network element and a core network element. In this way, service invocation may be performed with the access network element by invoking a service-based interface of the first radio network management function network element, and service invocation may also be performed with the core network element by invoking a service-based interface of the first radio network management function network element.

Abstract: A multi-chip packaging method includes: flip-mounting a first chip on a substrate on which first metal posts are arranged; mold packaging the first metal posts and the first chip to obtain a first package; forming a first redistribution layer on the surface of the first package; flip-mounting a second chip on a surface of the first redistribution layer and mold packaging the second chip to obtain a second package; removing the substrate and forming a second redistribution layer on a surface of the first package; forming second metal posts spaced apart from each other and flip-mounting a third chip on a surface of the second redistribution layer, and mold packaging the third chip and the second metal posts to obtain a third package; forming solder balls on a surface of the third package, where the solder balls are electrically connected to the second redistribution layer through the second metal posts.

Abstract: An information transmission method and an apparatus are provided. The method includes: a first network device sends a first type of feedback information to a second network device, wherein the first type includes one or more of the following: a model evaluation indicator, operation indication information, and a network performance indicator. The first network device receives the feedback information from the second network device. The first network device determines the performance of the model based on the feedback information. According to this application, the first network device can configure a type of the feedback information according to a requirement of the first network device and a capability of the second network device, thereby improving flexibility of feedback.

Abstract: One example method includes receiving, by a first mobility management network element, a first cell identifier and a network identifier from a first network element, where the network identifier includes an identifier of a first private network and an identifier of a second private network. The first mobility management network element can then obtain information about a second network element based on the first cell identifier and the network identifier, where the first network element serves a terminal device in the first private network, and where the second network element serves the terminal device in the second private network. The first mobility management network element can then send the first cell identifier and the network identifier to the second network element indicated by the information about the second network element, where the first cell identifier and the network identifier are used to obtain downlink routing information.

Abstract: This application provides a method for enabling an intent and an apparatus. The method includes: A first network element obtains first information, where the first information indicates at least one intent, and the at least one intent is all intents that conflict with a first intent. When the first network element determines that a status of the at least one intent changes, the first network element initiates a procedure of enabling the first intent. According to the solution of this application, when the first intent is in a conflict state, the first network element may initiate the procedure of enabling the first intent after determining that statuses of all the intents that conflict with the first intent change. The solution in this application can be used to re-initiate, in a timely, accurate, and efficient manner, the procedure of enabling the first intent.

Abstract: This application provides a signaling transmission interface compatibility method and apparatus. The method includes: A first network element obtains capability information of an access and mobility management function network element, where the capability information is used to indicate that the access and mobility management function network element has a capability of performing signaling transmission with a radio access network through a target interface function network element. The first network element selects the target interface function network element based on the capability information, where the target interface function network element is used for signaling transmission between the access and mobility management function network element and the radio access network.

Abstract: Embodiments of this application provide for a communication method and a related apparatus. In the method, an access and mobility management function network element receives a first correspondence between a first identifier and a quality of experience (QoE) target. The first correspondence includes the first identifier, the first identifier indicates an identifier of a first terminal device at an application layer, and the QoE target indicates a service QoE target of the first terminal device. The access and mobility management function network element determines a second identifier based on the first identifier. The access and mobility management function network element sends a second correspondence between the second identifier and the QoE target, where the second identifier indicates an identifier of the first terminal device in a network. According to the foregoing method, a service QoE requirement for a specified terminal device can be met.

Abstract: A network management method and a related device are provided. The method includes: receiving first operation and maintenance service information and/or second operation and maintenance service information, determining a first correspondence between the first operation and maintenance service and the first network management device, and a second correspondence between the second operation and maintenance service and the second network management device; and receiving third operation and maintenance service information, and executing a third operation and maintenance service based on a correspondence between a network device and an operation and maintenance service. At least two network management devices collaborate to provide an operation and maintenance service for a user of an enterprise network.

Abstract: An intent negotiation method and apparatus are provided. The method includes: A first network element sends a first sub-intent of a first intent to a second network element, and sends a second sub-intent of the first intent and indication information to the second network element, where the indication information is used to indicate that the first sub-intent and the second sub-intent have a same action and a same object.

Abstract: This application provides a communication method, apparatus, and device. In the method, when a target tenant has a network operation and maintenance management requirement for accessing first information by using a first service, an NMS of the target tenant can successfully access the first information regardless of whether the target tenant has permission to invoke the first service. In addition, the first information is transmitted between an EMS and the tenant NMS of the target tenant without passing through an operator NMS. Therefore, security of the first information can be ensured.

Abstract: This application provides a model data sending method and an apparatus. The method can reduce an accuracy loss of model data, and includes: A first device determines second information based on first information, where the second information is used by a second device to quantize first model data, the first information includes an evaluation loss corresponding to a current round of training, the second information includes a quantization error threshold, and the first model data is model data that is after the current round of training; the first device sends the second information to the second device; and the first device receives a first message sent by the second device, where the first message includes quantized first model data and first quantization configuration information.

Abstract: In a policy conflict management method, a first controller receives first policy information that comprises a first policy configured by a core network for UE. The first controller detects that a policy conflict occurs between the first policy information and second policy information, where the second policy information includes a second policy configured by a second controller for the UE, or a first decision result obtained after the first controller makes a policy decision according to the second policy. The first controller makes a policy decision according to the first policy and the second policy to obtain a second decision result. The first controller then sends the second decision result to a radio access network RAN network element for execution.

Abstract: An intent maintenance method and an apparatus provides a status awareness module that obtains a first duration corresponding to an intent. The status awareness module receives from a policy management module first information indicating that a first executable command corresponding to the intent starts to be executed. The status awareness module determines second duration when execution duration of the first executable command reaches the first duration and an object of the intent is not achieved, the second duration being greater than the first duration, and sends second information to the policy management module.

Abstract: A model distillation training method provides for establishment of a distillation training communication connection with a second device prior to performing distillation training on a neural network model. Based on exchange of distillation training information between the first device and the second device, the second device configures a first reference neural network model by using first configuration information sent by the first device. After configuring the first reference neural network model, the second device performs operation processing on first sample data in first data information based on the configured first reference neural network model by using the first data information to obtain first indication information, and sends the first indication information to the first device. The first device trains, by using the first indication information, a first neural network model designed by the first device.

Abstract: A federated learning method, apparatus, and system are disclosed. A first node obtains data distribution information of a plurality of second nodes based on a target data feature required by a training task; the first node selects at least two target second nodes from the plurality of second nodes based on a target data class required by the training task and the data distribution information of the plurality of second nodes; and the first node indicates the at least two target second nodes to perform federated learning, to obtain a federated learning model that is in the training task and that corresponds to the target data class. In this way, when participants have a plurality of data distributions, a trained model is prevented, as much as possible, from being affected by data poisoning.

Abstract: The technology of this application relates to a mobility management method. The method includes a first network device receiving a first message, where the first message includes information that indicates a target cell. The first network device determines, based on at least one of the following information, whether a terminal device is allowed to access the target cell: context information of the terminal device and resource status information of the target cell. It is determined, by using resource status information of a plurality of cells and/or the context information of the terminal device, whether the terminal device is allowed to access a cell, so that determining can be performed before the terminal device accesses the target cell, to improve an access success rate, avoid a resource waste, and implement centralized control on the plurality of cells.

Abstract: This application provides a service traffic steering method and an apparatus, to improve user experience. The method includes: A first network device determines at least one second terminal device, where first quality of experience corresponding to a first service flow of the second terminal device does not meet target quality of experience corresponding to the first service flow of the second terminal device. The first network device determines a target radio access network device, where the target radio access network device meets the target quality of experience corresponding to the first service flow of the at least one second terminal device. The first network device connects the first service flow of the at least one second terminal device to the target radio access network device.

Abstract: Embodiments of this application relate to the field of communication technologies, and provide a quality of service management method and an apparatus, to adjust a QoS parameter in real time based on a status of a radio network resource, and therefore maximize utilization of radio resources. A specific solution is as follows: A first network element receives a QoS parameter request sent by a second network element, where the QoS parameter request is for requesting a QoS parameter. The first network element determines a first QoS parameter based on at least one of service requirement information of a user, attribute information of the user, and a radio network resource of the second network element. The first network element sends the first QoS parameter to the second network element, to enable the second network element to allocate a radio network resource based on the first QoS parameter.

Abstract: Embodiments of the present disclosure provide a method, an apparatus and a system for data connection management. The method for data connection management includes: obtaining, by a user equipment UE, first instruction information, wherein the first instruction information is used for instructing to close or open a data connection; and transmitting, by the UE, the first instruction information to a packet data network gateway P-GW, for enabling the P-GW to stop or start data transmission of at least one bearer of the UE according to the first instruction information.

Abstract: An intent state management method, network element, and system are described. A first network element obtains a first network parameter value corresponding to an intent; and determines, based on the first network parameter value corresponding to the intent, that a condition for achieving the intent is not satisfied. In accordance with the determination, the first network element suspends execution of the intent, sends a first notification message to a second network element, where the first notification message notifies the intent to enter a sleep state; and sets the sleep state to an active state when the condition for achieving the intent is satisfied or the intent is modified. Network resources of the first network element can be saved. When the condition for achieving the intent is satisfied or the intent is modified, the intent enters the active state, so that a state of the intent can be adjusted in time.