Abstract: A model configuration method and an apparatus are provided. The method includes: Operations, administration and maintenance (OAM) receives a first model request message from a first access network device. The OAM determines a first model based on the first model request message and a first mapping relationship, where the first mapping relationship includes a mapping relationship between a model, a model application scenario, and a model function, or the first mapping relationship includes a mapping relationship between a model, a model performance level, and a model function. The OAM sends information about the first model to the first access network device.

Abstract: Example methods and apparatuses are provided. An example method includes receiving first indication information. The first indication information indicates that a trajectory of a first terminal device matches a trajectory of a second terminal device. The method further includes sending second indication information to the first terminal device. The second indication information indicates to change a trajectory information reporting periodicity to a second periodicity, or the second indication information indicates to suspend trajectory information reporting. The second periodicity is greater than a first periodicity, and the first periodicity is the trajectory information reporting periodicity before the first indication information is sent.

Abstract: A method and apparatus for training an artificial intelligence AI model in a wireless network are provided. The method includes: sending first configuration information to a terminal participating in federated learning, where the first configuration information is used to configure at least one of the following: training duration, a time-frequency resource, and a reporting moment; and same training duration, a same time-frequency resource, and a same reporting moment are configured for different terminals participating in federated learning; and receiving a signal obtained through over-the-air superposition of gradients reported by the terminals, where the gradients are gradients that are of an AI model whose training is completed within the training duration and that are reported by the terminals at the reporting moment by using the time-frequency resource.

Abstract: Embodiments of this application provide a cell handover method and a communication apparatus. The first network element receives a first random access request message from the terminal, where the first random access request message includes information indicating the second network element, and a first cell group managed by the first network element and a second cell group managed by the second network element belong to a dynamic cell set DCS. The first network element sends, to a core network element, a first connection request message including first DCS indication information, and the first DCS indication information indicates the core network element to deactivate a connection to a network element to which a cell group that is in the DCS and that was accessed by the terminal belongs. The first network element receives a first connection acknowledgment message from the core network element.

Abstract: Embodiments of this application provide a method for configuring a dynamic cell set, and a communication apparatus. A first network element sends a first request message to a second network element. The first request message is used to request to establish a connection to the second network element. A first cell group managed by the first network element and a second cell group managed by the second network element belong to a candidate cell set of a dynamic cell set (DCS). The first network element receives, from the second network element, a first response message in response to the first request message. Before a terminal is handed over, the first network element requests to establish the connection to the second network element to configure the dynamic cell set for the terminal.