Mobile device, access network node, and methods thereof

Abstract

A user equipment (UE) receives an identification of at least one of the respective artificial intelligence or machine learning (AI / ML) models from an access network node and sends a request for a first AI / ML model to the access network node. The request includes the identification of the respective AI / ML model. The identification of the first AI / ML model is included in the identification of the at least one of the respective AI / ML models. The UE then receives the first AI / ML model from the access network node.

Description

[Technical Field]

[0001] This disclosure relates to communication systems. This disclosure has particular, but not exclusive, relevance to wireless communication systems and devices thereof that operate in accordance with the 3rd Generation Partnership Project (3GPP®) standards or equivalent or derivative standards (including LTE-Advanced, Next Generation, or 5G networks, future generations, and beyond). This disclosure has particular, but not necessarily exclusive, relevance to artificial intelligence and machine learning (AI / ML) models used in "New Radio" systems (also known as "Next Generation" systems) and similar systems. [Background technology]

[0002] Recent developments in the 3GPP standard are referred to as the Long-Term Evolution (LTE) of the Evolved Packet Core (EPC) network and the Evolved UMTS Terrestrial Radio Access Network (E-UTRAN), also commonly referred to as "4G." The terms "5G" and "new radio" (NR) refer to a new generation of communication technologies that are expected to support a variety of applications and services. Various details of 5G networks are described, for example, in Non-Patent Document 1. 3GPP plans to support 5G with the so-called 3GPP Next Generation (NextGen) radio access network (RAN) and 3GPP NextGen Core Network.

[0003] In 3GPP standards, a NodeB (or eNB in ​​LTE, gNB in ​​5G) is a Radio Access Network (RAN) node (or simply "access node," "access network node," or "base station") through which communication devices (user equipment or "UE") connect to the core network and communicate with other communication devices or remote servers. For simplicity, this application uses the terms RAN node, base station, or access network node to refer to such access nodes.

[0004] Additional developments in 3GPP involve the use of artificial intelligence (AI) and machine learning (ML), often abbreviated as AI / ML. Predictions or inferences generated using AI / ML models can be used as part of various techniques to improve the reliability and efficiency of communications in a network. For example, AI / ML models can be used to predict a UE's path based on the UE's past mobility, for beam management, or for how information is coded and transmitted. AI / ML models can be hosted in a base station, which may control communication resources or UE states (e.g., control UE mobility or control the UE's radio resource control (RRC) state) based on inferences (e.g., decisions or predictions) generated using the AI / ML models. The base station can also transmit inferences generated using the models to other nodes in the network for use by those other nodes. Alternatively, AI / ML models can be hosted in two nodes in the network, e.g., a base station and a UE. In this case, both the base station and the UE may use the models to make decisions or predictions. For example, a UE may use a model as part of its encoding process to encode (and / or compress) channel state information (CSI) for transmission to a base station, and the base station may use the same model as part of a corresponding decoding (and / or decompression) process to decode CSI received from the UE. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] NGMN Alliance, "NGMN 5G White Paper V1.0", February 2015 Summary of the Invention [Problem to be solved by the invention]

[0006] However, improved methods are needed for propagating AI / ML models and related information between nodes in a communications network. In some methods, the model used by the UE may need to be the same as the model used by the base station. For example, if inferences generated using the model are used as part of a communication method between the UE and the base station, the UE and base station may need to use the same version of the model. Improved methods are needed to obtain and maintain synchronization between the model used by the UE and the model used by the base station, for example, when the model is updated to a new version at the base station. Furthermore, some AI / ML models may be used by the UE while the UE is in a particular cell (or other location, such as a group of cells), and improved methods are needed for obtaining and using the corresponding AI / ML model at the UE, for example, after the UE moves to the cell.

[0007] Additionally, there is a need for improved methods for obtaining or updating AI / ML models in a UE when the UE transitions between an RRC connected state and an RRC idle state, and for determining which AI / ML model should be used at a node in a communication network when multiple AI / ML models are stored.

[0008] More generally, improved methods are needed to enable more efficient and reliable transmission of information related to AI / ML models between nodes in communication networks.

[0009] One of the objectives achieved by the embodiments disclosed herein is to provide an apparatus and method that at least partially addresses the needs and / or problems described above. [Means for solving the problem]

[0010] In one aspect, a method is provided for a user equipment (UE), the method comprising: receiving a broadcast or multicast transmission from an access network node, wherein the broadcast or multicast transmission includes an indication of identification of one or more models for generating decision, prediction, or output parameters; determining to obtain one of the one or more models based on the indication; transmitting a request for the model; and receiving the model.

[0011] The model may be an artificial intelligence or machine learning (AI / ML) model.

[0012] Sending the request for the model may include sending the request to the access network node; receiving the model may include receiving the model from the access network node.

[0013] Receiving the model from the access network node may include receiving the model in a Radio Resource Control (RRC) message when the UE is in an RRC connected state.

[0014] Sending the request for the model may include sending the request to the access network node, the core network node, or a server that stores the model; receiving the model may include receiving the model from the server.

[0015] Receiving the model from the server may include receiving the model from the server via the access network node, via the core network node, or directly from the server.

[0016] When the UE receives the broadcast or multicast transmission, the UE may be in an RRC inactive state or an RRC idle state, and the UE may send the request as part of a random access procedure.

[0017] The random access procedure may comprise transmitting a random access preamble to the access network node; receiving a random access response from the access network node comprising an indication of communication resources to be used by the UE to transmit an uplink transmission; and transmitting the uplink transmission to the access network node, wherein the uplink transmission may comprise the request for the model.

[0018] The uplink transmission may include a cause value indicating that the uplink transmission includes the request of the model.

[0019] Sending the request for the model may include sending the request for the model in an RRC message; the RRC message may be a dedicated RRC message for requesting the model.

[0020] The method may further comprise receiving an indication from the access network node indicating time and / or frequency resources to be used by the UE to receive the model when the UE is in an RRC inactive state or an RRC idle state; and receiving the model from the access network node using the indicated time and / or frequency resources when the UE is in the RRC inactive state or the RRC idle state.

[0021] The broadcast or multicast transmission may include a representation of at least one use case of the one or more models.

[0022] The broadcast or multicast transmission may include at least one of a model identification number or an indication of a model version of the one or more models.

[0023] The broadcast or multicast transmission may include the indication of the model version; and the decision to acquire the model may be based on a comparison of the indicated model version with a model version of a model stored in the UE.

[0024] Receiving the model may include receiving the model using a data radio bearer or logical channel, which may have an associated transmission priority or bit rate.

[0025] Receiving the model may include receiving the model using a dedicated data radio bearer or a dedicated logical channel.

[0026] Receiving the model may include receiving the model from a core network node using non-access stratum (NAS) signaling.

[0027] The indication of the identity of the one or more models may be included in system information transmitted in the broadcast or multicast transmission.

[0028] The system information may be on-demand system information, and the method may further comprise receiving an indication from the access network node indicating that the on-demand system information is transmittable by the access network node; sending a request for the on-demand system information to the access network node; and receiving the on-demand system information in the broadcast or multicast transmission.

[0029] The system information including the indication of the identification of the one or more models may be dedicated system information.

[0030] The broadcast or multicast transmission may be a group paging transmission.

[0031] The group paging transmission may include an indication that the version of the one or more models has been updated.

[0032] The group paging transmission may include a cause value indicating that the model of the one or more models has been updated to a newer version.

[0033] In another aspect, a method is provided in an access network node, the method comprising: sending a broadcast or multicast transmission to a user equipment (UE), wherein the broadcast or multicast transmission includes an indication of identification of one or more models for generating decision, prediction, or output parameters; and receiving a request for one of the one or more models from the UE.

[0034] The model may be an artificial intelligence or machine learning (AI / ML) model.

[0035] The method may further comprise transmitting the requested model to the UE.

[0036] A data radio bearer or logical channel for transmission of the requested model may have an associated transmission priority or bit rate; transmitting the requested model may include transmitting the model using the data radio bearer or logical channel based on the transmission priority or bit rate.

[0037] The method may comprise receiving the requested model from a central unit of a base station, a server, or a core network node before sending the requested model to the UE.

[0038] The method may further comprise sending to the UE an indication of a network node from which the UE obtains the requested model, or an indication network address to be used by the UE to obtain the requested model.

[0039] The method may comprise sending the broadcast or multicast transmission when the UE is in an RRC inactive state or an RRC idle state, and receiving the request may include receiving the request as part of a random access procedure.

[0040] The random access procedure may include receiving a random access preamble from the UE; transmitting a random access response to the UE that includes an indication of communication resources to be used by the UE to transmit an uplink transmission; and receiving the uplink transmission from the UE, where the uplink transmission includes the request for the model.

[0041] The uplink transmission may include a cause value indicating that the uplink transmission includes the request for the model; the method may further include determining an identity of the model requested by the UE based on the request.

[0042] The method may further comprise transmitting an indication to the UE indicating time and / or frequency resources to be used by the UE to receive the model when the UE is in an RRC inactive state or an RRC idle state; and transmitting the model to the UE using the indicated time and / or frequency resources when the UE is in the RRC inactive state or the RRC idle state.

[0043] The method may comprise receiving, prior to sending the broadcast or multicast transmission including the indication of the identification of one or more models, information indicative of the identification of the one or more models from a central unit of a base station.

[0044] Transmitting the broadcast or multicast transmission may include transmitting the broadcast or multicast transmission periodically or based on a timer.

[0045] The broadcast or multicast transmission may include a representation of at least one use case of the one or more models.

[0046] The broadcast or multicast transmission may include at least one of a model identification number or an indication of a model version of the one or more models.

[0047] The indication of the identity of the one or more models may be included in system information transmitted in the broadcast or multicast transmission.

[0048] The system information may be on-demand system information, and the method may further comprise: sending an indication to the UE indicating that the on-demand system information is transmittable by the access network node; receiving a request for the on-demand system information from the UE; and transmitting the on-demand system information in the broadcast or multicast transmission.

[0049] The system information including the indication of the identification of the one or more models may be dedicated system information.

[0050] The broadcast or multicast transmission may be a group paging transmission.

[0051] The group paging transmission may include an indication that the version of the one or more models has been updated.

[0052] The group paging transmission may include a cause value indicating that the model of the one or more models has been updated to a newer version.

[0053] In another aspect, a method is provided for a user equipment (UE), the method comprising: receiving an indication from an access network node that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; determining to request one of the one or more models based on the received indication; transmitting the request for the model; and receiving the model.

[0054] An area of ​​the one or more areas may include a group of cells, a radio access network-based notification area, or a registration area.

[0055] The indication that the cell is part of the one or more areas may be received in system information broadcast within the cell.

[0056] The method may further comprise receiving an indication of an identity of the one or more models from the access network node.

[0057] The method may further comprise receiving, from the access network node, an indication of one or more use cases of the one or more models.

[0058] The one or more models may be artificial intelligence or machine learning (AI / ML) models.

[0059] Sending the request for the model may include sending the request to the access network node; receiving the model may include receiving the model from the access network node.

[0060] Sending the request for the model may include sending the request to the access network node, the core network node, or a server that stores the model; receiving the model may include receiving the model from the server.

[0061] Receiving the model from the server may include receiving the model from the server via the access network node, via the core network node, or directly from the server.

[0062] In another aspect, a method is provided for a user equipment (UE), the method comprising: receiving, from an access network node, an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating determination, prediction, or output parameters; determining, based on the received indication, to obtain an indication of identity of at least one of the models; and obtaining the indication of the identity of at least one of the models.

[0063] Obtaining the indication of the identity of at least one of the models may include receiving system information broadcast in the cell by the access network node.

[0064] The method may further comprise determining to receive the system information periodically or based on a timer.

[0065] The model may be an artificial intelligence or machine learning (AI / ML) model.

[0066] The method may further comprise determining to acquire one of the one or more models based on the indication of the identification information of at least one of the models; sending a request for the model; and receiving the model.

[0067] Sending the request for the model may include sending the request to the access network node; receiving the model includes receiving the model from the access network node.

[0068] Sending the request for the model may include sending the request to the access network node, the core network node, or a server that stores the model; receiving the model may include receiving the model from the server.

[0069] Receiving the model from the server may include receiving the model from the server via the access network node, via the core network node, or directly from the server.

[0070] The method may further comprise, after obtaining the indication of the identity of at least one of the models, selecting a model from the one or more models stored in the UE for use in the cell; and using the model to generate decision, prediction, or output parameters.

[0071] The method may further comprise transmitting an indication of the selected model to the access network node.

[0072] Transmitting the indication of the selected model may include transmitting the indication of the selected model using a radio resource control (RRC) message.

[0073] In another aspect, there is provided a method in an access network node, the method comprising: transmitting an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; and receiving a request for one of the one or more models from a UE that has received the indication.

[0074] The model may be an artificial intelligence or machine learning (AI / ML) model.

[0075] The method may further comprise transmitting the requested model to the UE.

[0076] The method may further comprise transmitting to the UE an indication of a network node from which the UE obtains the requested model, or an indication network address to be used by the UE to obtain the requested model.

[0077] Transmitting the indication of the network node or network address may include transmitting the indication of the network node or network address in system information broadcast in the cell.

[0078] In another aspect, a method is provided for an access network node, the method comprising: transmitting an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; receiving a request for an identity of one of the one or more models from a UE that has received the indication; and transmitting an indication of the identity of the one or more models.

[0079] Transmitting the indication of the identity of one or more models used in the cell may include transmitting the indication of the identity of one or more models used in the cell in system information broadcast in the cell.

[0080] The method may further comprise transmitting the system information periodically or based on a timer.

[0081] The model may be an artificial intelligence or machine learning (AI / ML) model.

[0082] In another aspect, a method is provided for a user equipment (UE), the method comprising: transitioning from a Radio Resource Control (RRC) idle state or an RRC inactive state to an RRC connected state; and sending to an access network node an indication indicating at least one of identification of one or more models stored in the UE, a status of the one or more models stored in the UE, or version numbers of the one or more models stored in the UE, where the one or more models are for generating decision, prediction, or output parameters.

[0083] The one or more models may be artificial intelligence or machine learning (AI / ML) models.

[0084] The indication may be sent to the access network node using Layer 1 (L1) signaling, Layer 2 (L2) signaling, or Layer 3 (L3) signaling.

[0085] Sending the indication of the identity of the one or more models may include sending the indication of the identity of the one or more models in an RRC message after the UE enters an RRC connected state.

[0086] In another aspect, a method is provided for an access network node, the method comprising: receiving, from a user equipment (UE), an indication indicating at least one of: identification of one or more models stored in the UE, a status of the one or more models stored in the UE, or version numbers of the one or more models stored in the UE; and determining, based on the received indication, one or more of the one or more models to be used at the access network node, wherein the one or more models are for generating determination, prediction, or output parameters.

[0087] The method may further comprise transmitting an indication of the determined model to the UE.

[0088] The one or more models may be artificial intelligence or machine learning (AI / ML) models.

[0089] In another aspect, a method is provided for a user equipment (UE), the method comprising: storing a model for generating decision, prediction, or output parameters; transitioning from a Radio Resource Control (RRC) Connected state to an RRC Idle state or an RRC Inactive state; and continuing to store the model after transitioning from the RRC Connected state to the RRC Idle state or the RRC Inactive state.

[0090] The method may comprise storing the model for a predetermined duration after the UE enters the RRC idle state or the RRC inactive state.

[0091] In another aspect, a method is provided in an access network node, the method comprising: sending, to a user equipment (UE), in a first radio resource control (RRC) message, a request for an indication of an identity of a model stored in the UE, where the model is for generating decision, prediction, or output parameters; and receiving, from the UE, in a second RRC message, the indication of the identity of the model stored in the UE.

[0092] In another aspect, a method is provided for a user equipment (UE), the method comprising: receiving, in a first Radio Resource Control (RRC) message from an access network node, a request for an indication of an identity of a model stored in the UE, where the model is for generating decision, prediction, or output parameters; and sending, in a second RRC message to the access network node, the indication of the identity of the model stored in the UE.

[0093] In another aspect, a method is provided for a user equipment (UE), the method comprising: sending, to an access network node, a request in a first radio resource control (RRC) message for an indication of supported models for a use case, where the models are for generating decisions, predictions, or output parameters for the use case; and receiving, from the access network node, an indication of the identification of the models in a second RRC message.

[0094] In another aspect, there is provided a method in an access network node, the method comprising: receiving, from a user equipment (UE), a request in a first radio resource control (RRC) message for an indication of a supported model for a use case, where the model is for generating decisions, predictions, or output parameters for the use case; and sending to the UE, in a second RRC message, an indication of the identity of the model.

[0095] In another aspect, a user equipment (UE) is provided, comprising: means for receiving a broadcast or multicast transmission from an access network node, wherein the broadcast or multicast transmission includes an indication of identification of one or more models for generating decision, prediction, or output parameters; means for determining, based on the indication, to obtain one of the one or more models; and means for transmitting a request for the model, wherein the receiving means is configured to receive the model.

[0096] In another aspect, an access network node is provided, comprising: means for sending a broadcast or multicast transmission to a user equipment (UE), wherein the broadcast or multicast transmission includes an indication of identification of one or more models for generating decision, prediction, or output parameters; and means for receiving a request for one of the one or more models from the UE.

[0097] In another aspect, a user equipment (UE) is provided, comprising: means for receiving, from an access network node, an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating a decision, prediction, or output; means for determining, based on the received indication, to request one of the one or more models; and means for transmitting the request for the model, wherein the receiving means is configured to receive the model.

[0098] In another aspect, a user equipment (UE) is provided, comprising: means for receiving, from an access network node, an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating determination, prediction, or output parameters; means for determining, based on the received indication, to obtain an indication of identity of at least one of the models; and means for obtaining the indication of identity of at least one of the models.

[0099] In another aspect, an access network node is provided, comprising: means for transmitting an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; and means for receiving a request for one of the one or more models from a UE that has received the indication.

[0100] In another aspect, an access network node is provided, comprising: means for transmitting an indication that a cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; and means for receiving, from a UE that has received the indication, a request for an identity of one of the one or more models, wherein the transmitting means is configured to transmit an indication of the identity of the one or more models.

[0101] In another aspect, a user equipment (UE) is provided, comprising: means for transitioning from a Radio Resource Control (RRC) idle state or an RRC inactive state to an RRC connected state; and means for transmitting to an access network node an indication indicating at least one of: identification of one or more models stored in the UE, a status of the one or more models stored in the UE, or version numbers of the one or more models stored in the UE, wherein the one or more models are for generating decision, prediction, or output parameters.

[0102] In another aspect, an access network node is provided, comprising: means for receiving, from a user equipment (UE), an indication indicating at least one of: identification of one or more models stored in the UE, a status of the one or more models stored in the UE, or a version number of the one or more models stored in the UE; and means for determining, based on the received indication, a model of the one or more models to be used at the access network node, wherein the one or more models are for generating determination, prediction, or output parameters.

[0103] In another aspect, a user equipment (UE) is provided, comprising: means for storing a model for generating decision, prediction, or output parameters; and means for transitioning from a Radio Resource Control (RRC) Connected state to an RRC Idle state or an RRC Inactive state, wherein the UE is configured to continue to store the model after transitioning from the RRC Connected state to the RRC Idle state or the RRC Inactive state.

[0104] In another aspect, an access network node is provided, comprising: means for sending to a user equipment (UE) in a first radio resource control (RRC) message a request for an indication of an identity of a model stored in the UE, wherein the model is for generating decision, prediction, or output parameters; and means for receiving from the UE in a second RRC message the indication of the identity of the model stored in the UE.

[0105] In another aspect, a user equipment (UE) is provided, comprising: means for receiving, in a first Radio Resource Control (RRC) message from an access network node, a request for an indication of an identity of a model stored in the UE, where the model is for generating decision, prediction, or output parameters; and means for transmitting, in a second RRC message to the access network node, the indication of the identity of the model stored in the UE.

[0106] In another aspect, a user equipment (UE) is provided, comprising: means for sending, in a first Radio Resource Control (RRC) message to an access network node, a request for an indication of a supported model for a use case, wherein the model is for generating decisions, predictions, or output parameters for the use case; and means for receiving, in a second RRC message from the access network node, an indication of the identity of the model.

[0107] In another aspect, an access network node is provided, comprising: means for receiving, from a user equipment (UE), a request in a first radio resource control (RRC) message for an indication of a supported model for a use case, wherein the model is for generating decisions, predictions, or output parameters for the use case; and means for sending, to the UE, an indication of the identity of the model in a second RRC message. [Effects of the Invention]

[0108] According to the above-described aspects, an apparatus, method, and program can be provided that contributes to at least partially resolving one or more of the above-described needs and / or problems. [Brief explanation of the drawings]

[0109] Several embodiments will now be described, by way of example only, with reference to the following drawings: [Figure 1] Figure 1 shows a schematic representation of a mobile ("cellular" or "wireless") communications system; [Figure 2] Figure 2 shows a typical frame structure used in the communication system of Figure 1; [Figure 3] FIG. 3 is a schematic block diagram illustrating the main components of a DU 50 that may be used as part of the RAN equipment 5 of the communication system 1 shown in FIG. 1 ; [Figure 4] FIG. 4 is a schematic block diagram illustrating the main components of a CU 60 that may be used as part of the RAN equipment 5 of the communication system 1 shown in FIG. 1 ; [Figure 5] Figure 5 shows the mobility procedure where handover occurs from a source (R)AN node to a target (R)AN node; [Figure 6] Figure 6 illustrates a random access (RA) procedure that may be performed in the system of Figure 1; [Figure 7] Figure 7 is a schematic diagram of point-to-point and point-to-multipoint transmission; [Figure 8] Figure 8 shows the framework for the AI / ML model; [Figure 9] Figure 9 is an illustration of how to train an AI / ML model and how to monitor the performance of an AI / ML model; [Figure 10] Figure 10 shows an example of an AI / ML request and an AI / ML response; [Figure 11] Figure 11 shows an example of AI / ML information update; [Figure 12] Figure 12 shows an example of UE mobility information feedback; [Figure 13] Figure 13 shows a further example of UE mobility information feedback; [Figure 14] Figure 14 shows an example of how a base station 5 may broadcast an indication of supported AI / ML models; [Figure 15] Figure 15 shows an example in which an AI / ML model is transmitted from an AI / ML server to a UE via a base station; [Figure 16] Figure 16 shows an example in which an AI / ML model is transmitted from a CU in a distributed base station to a UE via a DU; [Figure 17] FIG. 17 illustrates an example in which a network is configured to notify one or more UEs of an AI / ML model update using paging; [Figure 18] Figure 18 shows an example of functional areas of an AI / ML model; [Figure 19] Figure 19 shows how the UE receives AI / ML model area information; [Figure 20] FIG. 20 is a schematic block diagram showing the main components of a UE in the communication system of FIG. 1; [Figure 21] FIG. 21 is a schematic block diagram showing the main components of a base station in the communication system of FIG. 1; [Figure 22]FIG. 22 is a schematic block diagram illustrating the main components of a core network node or function in the communication system of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0110] The embodiments described below may be used individually, or two or more embodiments may be appropriately combined with each other. These embodiments may have different novel features. Therefore, these embodiments may contribute to achieving different objectives or solving different problems, and may contribute to obtaining different advantages.

[0111] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but also to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0112] overview An outline of a typical communication system will be described as an example with reference to FIGS. 1 and 2. FIG.

[0113] FIG. 1 shows a schematic diagram of a mobile (cellular or wireless) communication system 1 to which several embodiments are applicable.

[0114] In system 1, user equipment (UE) 3-1, 3-2, 3-3 (e.g., mobile phones and / or other mobile devices) can communicate with one another via radio access network (RAN) nodes 5 that operate according to one or more compatible radio access technologies (RATs). In the illustrated example, the RAN nodes 5 include NR / 5G base stations or gNBs 5 that operate one or more associated cells 9. Communications via the base stations 5 are typically routed through a core network 7 (e.g., a 5G core network or evolved packet core network (EPC)).

[0115] As will be appreciated by those skilled in the art, while Figure 5 shows three UEs 3 and one base station 5 for illustrative purposes, the system will typically include multiple other base stations 5 and multiple UEs 3 when implemented.

[0116] Each base station 5 controls one or more associated cells 9, either directly or indirectly via one or more other nodes (such as home base stations, relays, remote radio heads, distributed units, and / or the like). It will be appreciated that the base stations 5 may be configured to support 4G, 5G, 6G, and / or other 3GPP or non-3GPP communication protocols.

[0117] The UEs 3 and their serving base stations 5 are connected via a suitable air interface (such as, for example, the so-called Uu interface), and neighboring base stations 5 are connected to each other via a suitable inter-base station interface (such as, for example, the so-called X2 interface, Xn interface, etc.).

[0118] The core network 7 includes multiple logical nodes (or functions) for supporting communications in the communication system 1. In this example, the core network 7 includes a control plane function (CPF) 10 and one or more user plane functions (UPF) 11. The CPF 10 includes one or more access and mobility management functions (AMF) 10-1, one or more session management functions (SMF), and multiple other functions 10-n.

[0119] The base station 5 is connected to multiple core network nodes via appropriate interfaces (or reference points), such as the N2 reference point between the base station 5 and the AMF 10-1 for communication of control signaling, and the N3 reference point between the base station 5 and each UPF 11 for communication of user data. Multiple UEs 3 are each connected to the AMF 10-1 by a logical non-access stratum (NAS) connection via the N1 reference point (equivalent to the S1 reference point in LTE). It will be appreciated that N1 communications are transparently routed via the base station 5.

[0120] One or more UPFs 11 are connected to an external data network (eg, an IP network such as the Internet) via the N6 reference point for communication of user data.

[0121] The AMF 10-1 performs mobility management related functions, maintains non-NAS signaling connections with each UE 3, and manages UE registrations. The AMF 10-1 is also responsible for managing paging. The SMF 10-2 provides session management functions (which were part of the MME functions in LTE) and also integrates some control plane functions (which were provided by the Serving Gateway and Packet Data Network Gateway in LTE). The SMF 10-2 also assigns an IP address to each UE 3.

[0122] A base station 5 of the communication system 1 is configured to operate at least one cell 9 on an associated TDD carrier operated in unpaired spectrum. The base station 5 may also operate at least one cell 9 on an associated FDD carrier operated in paired spectrum.

[0123] The base station 5 is configured to transmit control information and user data via a plurality of downlink (DL) physical channels and to transmit a plurality of physical signals, which the UE 3 is configured to receive, the plurality of DL physical channels corresponding to resource elements (REs) carrying information originating from higher layers, and the DL physical signals corresponding to REs used by the physical layer and not carrying information originating from higher layers.

[0124] The multiple physical channels may include, for example, a physical downlink shared channel (PDSCH), a physical broadcast channel (PBCH), and a physical downlink control channel (PDCCH). The PDSCH carries data that shares the capacity of the PDSCH on a time and frequency basis. The PDSCH can carry various data, such as user data, UE-specific upper layer control messages mapped from higher channels, system information blocks (SIBs), paging, etc. The PDCCH carries downlink control information (DCI) to support various functions, such as scheduling downlink transmissions on the PDSCH and uplink data transmissions on the physical uplink shared channel (PUSCH). The PBCH provides a master information block (MIB) to the UE 3, which, in conjunction with the PDCCH, also supports time and frequency synchronization to aid in cell acquisition, selection, and reselection. The UE 3 may receive a synchronization signal block (SSB), and the UE 3 may assume that the reception opportunities for the PBCH, primary synchronization signal (PSS), and secondary synchronization signal (SSS) are consecutive symbols forming an SS / PBCH block. The base station 5 may transmit multiple synchronization signal (SS) blocks corresponding to different DL beams. The total number of SS blocks may be limited to, for example, a 5-millisecond duration as one SS burst.The periodicity of SSB transmissions may be indicated to the UE using any suitable signaling (e.g., per serving cell using ssb-periodicityServingCell). The value of the SSB periodicity may be, for example, 20 ms or greater. For initial cell selection, the UE 3 may be configured to assume that SS bursts occur with a periodicity of 2 frames. The UE 3 may further be provided with an indication of which SSBs are transmitted within a 5 ms duration (e.g., using ssb-PositionsInBurst).

[0125] The DL physical signals may include, for example, reference signals (RS) and synchronization signals (SSs). Reference signals (also called pilot signals) are signals with predefined special waveforms known to both the UE 3 and the base station 5. Reference signals may include, for example, cell-specific reference signals, UE-specific reference signals (UE-RS), downlink demodulation signals (DMRS), and channel state information reference signals (CSI-RS).

[0126] Similarly, the UE 3 is configured to transmit control information and user data over multiple uplink (UL) physical channels corresponding to REs carrying information originating from higher layers, and multiple UL physical signals corresponding to REs not carrying information originating from higher layers, and the base station 5 is configured to receive these. The physical channels may include, for example, a PUSCH, a physical uplink control channel (PUCCH), and / or a physical random-access channel (PRACH). The UL physical signals may include, for example, a demodulation reference signal (DMRS) for UL control / data signals and / or a sounding reference signal (SRS) used for UL channel measurement.

[0127] When a UE 3 first establishes a radio resource control (RRC) connection with a base station 5 via a cell 9, it registers with an appropriate core network node (e.g., AMF, MME). The UE 3 is in the so-called RRC connected state, and the associated UE context is maintained by the network. When the UE 3 is in the so-called RRC idle or RRC inactive state, the UE 3 selects a suitable cell to camp on, allowing the network to know the UE 3's approximate location (but not necessarily at cell level).

[0128] The base station 5 may be divided into one or more distributed units (DUs) 50 and a central unit (CU) 60. The CUs 60 typically perform higher level functions and communication with a next generation core, while the DUs 50 perform lower level functions and communication over the air interface with nearby UEs 3 (i.e., within the cell operated by the base station 5). This type of base station 5 is sometimes referred to as a "distributed" base station 5 or gNB 5. A distributed gNB 5 includes the following functional units:

[0129] gNB Central Unit (gNB-CU): A logical node that hosts the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) layers of a gNB (or the RRC and PDCP layers of an en-gNB) and controls the operation of one or more gNB-DUs. The gNB-CU terminates the so-called F1 interface connected to the gNB-DU.

[0130] gNB Distributed Unit (gNB-DU): A logical node that hosts the Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers of a gNB or en-gNB, and some of its operations are controlled by the gNB-CU. One gNB-DU supports one or more cells. One cell is supported by only one gNB-DU. The gNB-DU terminates the F1 interface connected to the gNB-CU.

[0131] gNB-CU-Control Plane (gNB-CPU-CP): A logical node that hosts the control plane part of the RRC and PDCP protocols of the gNB-CU of an en-gNB or gNB-CU. The gNB-CU-CP terminates the so-called E1 interface connected to the gNB-CU-UP and the F1-C (F1 Control Plane) interface connected to the gNB-DU.

[0132] gNB-CU-User Plane (gNB-CU-UP): A logical node that hosts the user plane part of the PDCP protocol of the gNB-CU in the case of an en-gNB, and the user plane part of the PDCP protocol of the gNB-CU and the SDAP protocol in the case of a gNB. The gNB-CU-UP terminates the E1 interface connected to the gNB-CU-CP and the F1-U (F1 User Plane) interface connected to the gNB-DU.

[0133] It will be appreciated that where a distributed base station or similar control plane-user plane (CP-UP) split is employed, the control plane entity and user plane entity may each include associated transceiver circuitry, antennas, network interfaces, controllers, memory, operating systems, and communication control modules. If the base station 5 includes a distributed base station, the network interface also includes an E1 interface and an F1 interface (F1-C for the control plane and F1-U for the user plane) for communicating signals between the respective functions of the distributed base station.

[0134] Frame structure Figure 2 shows a typical frame structure used in communication system 1. Base stations 5 and UEs 3 of communication system 1 communicate with each other using resources organized in the time domain into frames of 10 milliseconds in length. Each frame comprises 10 equally sized subframes of 1 millisecond in length. Each subframe is divided into one or more slots of 14 equally long orthogonal frequency-division multiplexing (OFDM) symbols.

[0135] As shown in FIG. 2, communication system 1 supports multiple different numerologies (subcarrier spacing (SCS), slot lengths, and resulting OFDM symbol lengths). Specifically, each numerology is identified by a parameter μ, where μ=0 represents 15 kHz (corresponding to LTE SCS). Currently, SCS for other values ​​of μ are effectively powers of 2 from μ=0 (i.e., SCS=15 x 2). μ The relationship between the parameter μ and SCS (Δf) is shown in Table 1: [Table 1]

[0136] RAN equipment DU Figure 3 is a schematic block diagram illustrating the main components of a DU 50 that may be used as part of the RAN equipment 5 in the communication system 1 shown in Figure 1. As shown, the DU 50 has transceiver circuitry 451 for transmitting and receiving signals to and from a plurality of communication devices (such as UE 3) via a radio unit (RU) and associated DU-RU interface 453; and for transmitting and receiving signals to and from the CU 60 of the RAN equipment 5 via a CU interface 454 (e.g., including an F1 interface that may be divided into an F1-U interface and an F1-C interface for user plane and control plane signaling, respectively).

[0137] The DU 50 has a controller 457 for controlling the operation of the DU 50. The controller 457 is associated with a memory 459. Software may be pre-installed in the memory 459 and / or may be downloaded, for example, via the communication system 1 or from a removable data storage device (RMD). The controller 457 is configured in this example to control the overall operation of the DU 50 by means of a plurality of program instructions or a plurality of software instructions stored in the memory 459.

[0138] As shown, these software instructions include, among other things, an operating system 461, a communication control module 463, an F1 module 465, a DU-RU module 468, a DU management module 472, a UE profile management module 473, and a mobility module 475.

[0139] The communication control module 463 is operable to control communication between the DU 50 and one or more RUs (and thus between the DU 50 and the UE 3), and communication between the DU 50 and the CU 60. The communication control module 463 is configured to generally control the reception of signals corresponding to uplink communication from the UE 3, and to handle the transmission of downlink communication to the UE 3.

[0140] The F1 module 465 is responsible for appropriate processing of signals received from or transmitted to the CU 60 via one or more CU (e.g., F1) interfaces 454. These signals may be separated into user plane signals received from or transmitted to the CU-UP portion of the CU 60 via the F1-U interface, and control plane signals received from or transmitted to the CU-CP portion of the CU 60 via the F1-C interface.

[0141] The DU-RU module 468 is responsible for proper processing of signals received from or transmitted to an RU via one or more RU (eg, DU-RU) interfaces 453.

[0142] The DU management module 472 is responsible for managing the overall operation of the DU 50 and the overall execution of tasks required of the DU 50. These tasks include, among other things, the generation and transmission of appropriate messages using an appropriate signaling application protocol depending on the division of functionality between the RU, DU 50, and CU 60, such as interpreting received MAC signaling and generating MAC signaling for transmission. The DU management module 472 may control the overall operation of the DU 50, as appropriate, according to any of the methods described below.

[0143] The UE profile management module 473 is responsible for performing functions related to UE profiles, including (if applicable): receiving and storing UE profiles or associated assistance / preference information from the UE 3 or elsewhere in the network; determining appropriate mobility-specific configurations based on the UE profile / assistance / preference information for implementation in the UE 3 and / or RAN equipment (if applicable); and / or providing configuration information for appropriately configuring the UE with mobility-based configurations (if applicable). The UE profile management module 473 may also store, for example, historical mobility information of the UE 3 (e.g., past movements of the UE 3 between different communication cells of the network). It will be understood that, depending on the implementation, the gNB-DU may not implement at least some of these functions.

[0144] The mobility module 475 is responsible for controlling mobility procedures for one or more UEs 3. For example, the mobility module 475 may be configured to perform one or more measurements for mobility of the UE 3 or to select a candidate cell for handover. It will be appreciated that the mobility module 475 may be configured to perform control in any of a number of mobility methods (e.g., handover) described below.

[0145] CU Figure 4 is a schematic block diagram illustrating the main components of the CU 60 of the RAN apparatus of the communication system 1 shown in Figure 1. As shown, the CU 60 has transceiver circuitry 551 for transmitting signals to and receiving signals from the DU 50 via one or more DU interfaces 554 (e.g., including an F1 interface that may be divided into an F1-U interface and an F1-C interface for user plane and control plane signaling, respectively); and for transmitting signals to and receiving signals from multiple functions of the core network 7 via one or more core network interfaces 555 (e.g., including an N2 and N3 interface, etc.).

[0146] The CU 60 has a controller 557 that controls the operation of the CU 60. The controller 557 is associated with a memory 559. Software may be pre-installed in the memory 559 and / or may be downloaded, for example, via the communication system 1 or from a removable data storage device (RMD). The controller 557 is configured, in this example, to control the overall operation of the CU 60 by means of program instructions or software instructions stored in the memory 559.

[0147] As shown, these software instructions include, among other things, an operating system 561, a communications control module 563, an F1 module 565, an E1 module 566, an N2 module 568, an N3 module 569, a CU-UP management module 571, a CU-CP management module 572, a UE profile management module 573, and a mobility module 575. The functionality of mobility module 575 is the same as that described above with reference to FIG.

[0148] The communication control module 563 is operable to control communication between the CU 60 and one or more DUs 50 (and thus communication between the CU 60 and the UE 3), and communication between the CU 60 and the core network 7. The communication control module 563 is configured to generally control the reception of signals corresponding to uplink communications from the UE 3, and to control the transmission of downlink communications.

[0149] The F1 module 565 is responsible for the appropriate processing of signals received from or transmitted to the DU 50 via one or more DU (e.g., F1) interfaces 554. These signals include user plane signals received at or transmitted by the CU-UP portion of the CU 60 via the F1-U interface, and control plane signals received at or transmitted by the CU-CP portion of the CU 60 via the F1-C interface.

[0150] The E1 module 566 is responsible for the proper processing of signals transmitted between the CU-UP portion of the CU 60 and the CU-CP portion of the CU 60 via the corresponding CU internal interface (eg, E1).

[0151] The N2 module 568 is responsible for the appropriate processing of signals received from or transmitted to the AMF 8-1 via a corresponding one of one or more core network interfaces (eg, N2) 555.

[0152] The N3 module 569 is responsible for the appropriate processing of signals received from or transmitted to one or more core network user plane functions via one or more corresponding core network interfaces (e.g., N3) 555.

[0153] The CU-UP management module 571 is responsible for managing the overall operation of the CU-UP portion of the CU 60 and the overall execution of tasks required of the CU-UP.

[0154] The CU-CP management module 572 is responsible for managing the overall operation of the CU-CP portion of the CU 60 and the overall execution of tasks required of the CU-CP. These tasks include, among other things, the generation and transmission of appropriate messages using the appropriate signaling application protocol depending on the division of functionality between the RUs, the DU 50, and the CU 60, such as interpreting received RRC signaling and generating RRC signaling for transmission.

[0155] The UE profile management module 573 is responsible for performing functions related to UE (mobility) profiles, including (where applicable): receiving and storing UE profiles or associated assistance / preference information from the UE 3 or elsewhere in the network; determining appropriate mobility-specific configurations based on the UE profile / assistance / preference information for implementation in the UE 3 and / or the RAN equipment 5; and / or providing configuration information for appropriately configuring the UE with mobility-based configurations. The UE profile management module 573 may also store historical mobility information of the UE 3 (e.g., past movements of the UE 3 between different communication cells of the network). It will be understood that, depending on the implementation, the gNB-CU 60 may not implement at least some of these functions.

[0156] System Information and SIB Transmissions in the cell 9 of the base station 5 may include one or more broadcast transmissions, one or more unicast transmissions for reception by a UE 3, and / or one or more multicast transmissions for reception by a group of UEs 3. System information (SI) transmitted in the cell may include a "minimum SI (MSI)" and an "other SI (OSI)." OSI may be broadcast in response to a request from a UE 3 in a radio resource control (RRC) idle or RRC inactive state. OSI may also be requested from a UE 3 in an RRC connected state, for example via one or more dedicated RRC transmissions.

[0157] The SI may include information to enable (e.g., configure) the UE 3 to complete a cell selection, may include information to enable the UE 3 to complete a cell reselection procedure, or may include information to enable the UE 3 to receive one or more paging messages transmitted in the cell. The SI may be broadcast using a Master Information Block (MIB) and one or more System Information Blocks (SIBs).

[0158] The MSI includes the MIB and System Information Block 1 (SIB1). The MIB includes information used by the UE 3 to receive SIB1, such as the subcarrier spacing of SIB1. The MIB provides information corresponding to the control resource set (CORESET) and search space. SIB1 may be referred to as the "remaining MSI (RMSI)." SIB1 may be transmitted in a dedicated RRC message, and other SIBs (e.g., SIB2 to SIB9) may be transmitted using one or more other appropriate RRC transmissions (e.g., another dedicated RRC message). The MIB and SIB1 may provide the UE 3 with scheduling information for receiving and decoding other SIBs, such as SIB2 to SIB9, and may provide information used by the UE 3 to receive one or more paging messages. The OSI may include, for example, SIB2 to SIB9 transmitted using the DL-SCH as SI messages. Mapping of SIB2 to SIB9 to corresponding SI messages may be provided to the UE 3 by the base station 5. The MIB and SIB1 to SIB9 are described in more detail, for example, in 3GPP TS 38.331. SIB2 provides information about intra-frequency, inter-frequency, and inter-system cell reselection. SIB3 provides cell-specific information about intra-frequency cell reselection. SIB4 provides information about inter-frequency cell reselection. SIB5 provides information about inter-system cell reselection for 4G (LTE). SIB6 and SIB7 provide information about the earthquake and tsunami warning system (ETWS). SIB8 provides information for commercial mobile alert service (CMAS) notifications, e.g., providing warning text messages to UE3. SIB9 contains information about coordinated universal time (UTC), GPS time (e.g., for global positioning system (GPS) initialization), and local time.

[0159] The SIBs may be broadcast periodically (e.g., according to a predetermined periodic pattern) or may be provided “on-demand,” for example, in response to a request from UE 3. For example, MIB may be transmitted at an 80-ms period and repeatedly transmitted within the 80 ms, while SIB1 may be transmitted at a 160-ms period and with a variable transmission repetition period (e.g., 20 ms) within the 160 ms. SIB1 may be used to indicate to UE 3 which SIBs are transmitted periodically and which SIBs are available on-demand in response to a request from UE 3. UE 3 may be configured to request on-demand SIBs using message 1 (MSG1), which may be referred to as an MSG1-based on-demand SI request, or may be configured to request on-demand SIBs using message 3 (MSG3), which may be referred to as an MSG3-based on-demand SI request.

[0160] A physical broadcast channel (PBCH) may be used to broadcast the MIB. Base station 5 may transmit the PBCH along with synchronization signals (SS) (e.g., primary synchronization signal (PSS) and secondary synchronization signal (SSS)) in an SS / PBCH block. An SS / PBCH block comprises four consecutive orthogonal frequency division multiplexing (OFDM) symbols that are mapped to the PSS, SSS, and PBCH associated with a demodulation reference signal (DM-RS). In the frequency domain, an SS / PBCH block comprises 240 consecutive subcarriers. When UE 3 is in an RRC connected state, base station 5 may provide UE 3 with an indication of the resources used for the SS / PBCH, for example, using dedicated signaling. SIB1 may be transmitted using a physical downlink shared channel (PDSCH). OSI may also be transmitted using, for example, the PDSCH. When one or more beamformed transmissions are transmitted in a cell served by base station 5, a portion of the SI (e.g., a portion of the SIB) may be transmitted only using a particular beam or using a particular transmission / reception point (TRP).

[0161] UE Mobility Figure 5 shows an overview of a mobility procedure that may be performed in a communications system 1 of the type shown in Figure 1. In this example, a handover of a UE 3 from a source base station 5 to a target base station 5 is performed.

[0162] In optional step S501, the UE 3 performs measurements. The measurements may be measurements of signals transmitted by the source (R)AN node 5 or may be measurements of signals transmitted by the target (R)AN node 5. The measurements may be measurements of signal strength that can be used as part of a decision that the UE 3 is handed over from the source (R)AN node 5 to the target (R)AN node. In optional step S502, the UE 3 sends a measurement report to the source (R)AN node 5 providing an indication of the results of the measurements. The measurement report may be sent from the UE 3 to the source base station 5 in an RRC message. In this example, the source (R)AN node uses information provided in the measurement report to determine that the UE 3 is handed over to the target (R)AN node 5. However, it will be appreciated that the decision that a handover to the target (R)AN node is to be performed may alternatively (or additionally) be based on measurements performed at the source (R)AN node 5 or the target (R)AN node 5. Alternatively, the determination that a handover of the UE 3 is to be performed may be based on factors other than signal measurements, such as congestion levels in a cell operated by the source (R)AN node 5, or inferences (e.g., decisions or predictions) generated using AI / ML models.

[0163] In step S503, the source (R)AN node 5 sends a handover request to the target (R)AN node 5, requesting handover of the UE 3 from the source (R)AN node 5 to the target (R)AN node 5. The handover request may include, for example, an identification of the source (R)AN node 5, a cause value for the handover, an identification of the target cell, context information of the UE 3 (e.g., the maximum bit rate of the UE 3 or the security capabilities of the UE 3), and an indication of UE history information. If the handover was triggered by a measurement report received by the source (R)AN node 5 in step S502, the cause value may indicate, for example, that the handover is desirable for radio reasons. Alternatively, if the handover was triggered to reduce the load at the source (R)AN node 5, the cause value may indicate that the handover is to reduce the load at the serving cell. The handover request message may also include an indication of the AMF 10-1 serving the UE 3.

[0164] In step S504, the target (R)AN node sends an acknowledgement of the handover request (sometimes referred to as a "handover request acknowledgement" message). The handover request acknowledgement message includes an indication of handover configuration information for the handover to be forwarded to the UE 3. The handover request acknowledgement message may include configuration information to enable the source (R)AN node 5 to initiate transfer of user plane data for the UE 3 to the target (R)AN node 5.

[0165] The transmissions of steps S503 and S504 may be performed over the Xn interface between the source (R)AN node 5 and the target (R)AN node 5 (hence the handover procedure in this example may be referred to as an Xn-based handover procedure). Steps S501 to S504 may be referred to as the "handover preparation phase."

[0166] In step S505, the source (R)AN node transmits handover configuration information to the UE 3. The handover configuration information may be, for example, an RRC configuration transmitted in an RRC configuration message or an RRC reconfiguration message. In step S506, the UE 3 applies the received handover configuration and transmits an indication to the target (R)AN node 5 that the handover configuration is complete. The message transmitted in step S505 may be, for example, an RRC Reconfiguration Complete message. Steps S505 and S506 may be referred to as the "handover execution phase".

[0167] After the handover execution phase, the UE 3 is operable to send uplink transmissions (e.g., uplink data) to the target (R)AN node 5 and receive downlink transmissions (e.g., downlink data) from the target (R)AN node 5.

[0168] It will be understood that the mobility method and handover procedure of the UE 3 are not limited to the example shown in Figure 5. For example, the UE 3 may be configured to perform a conditional handover (CHO), in which the UE 3 determines whether to perform a handover of the UE 3 to a candidate cell based on one or more execution conditions. It will also be understood that a handover in which the DU 50 is changed but the CU 60 remains the same (inter-DU intra-CU handover), a handover in which both the DU 50 and the CU 60 change (inter-DU inter-CU handover), or a handover between two cells operated by the same DU 50 may be performed.

[0169] Random Access Figure 6 illustrates a random access (RA) procedure that may be performed in the system of Figure 1. The RA procedure may be used, for example, for initial access by a UE 3 in RRC idle mode or for transitioning from an RRC inactive mode to an RRC connected mode. The RA procedure may also be used for initial access to a target base station 5 during handover of a UE 3 from a source base station to a target base station (e.g., the handover procedure described above with reference to Figure 5).

[0170] In step S601, the UE 3 transmits a random access preamble to the base station 5. In this example, the UE 3 selects the random access preamble to transmit from a group of random access preambles shared with other UEs 3. The transmission of step S601 may be referred to as Message 1 (MSG1) and is transmitted using the PRACH.

[0171] In step S602, the base station 5 transmits a random access response to the UE 3. The transmission of step S602 may be referred to as Message 2 (MSG2). The random access response indicates time and / or frequency resources (e.g., resource blocks and / or symbols) to be used by the UE 3 for sending subsequent transmissions to the base station 5. The random access response may include further information for the UE 3 to use in communicating with the base station 5, such as a timing advance (TA) value.

[0172] In step S603, the UE 3 transmits to the base station 5 using the indicated time and / or frequency resources. The transmission of step S603 may be referred to as Message 3 (MSG3). The transmission of step S603 may be a Layer 2 (L2) or Layer 3 (L3) message. The transmission of step S603 may include, for example, an RRC setup request, an RRC resume request, an RRC reestablishment request, or an RRC reconfiguration complete message.

[0173] If two UEs 3 select and transmit the same random access preamble in step S601 and receive and decode MSG2 transmitted by the base station 5 in step S602, the two UEs may transmit MSG3 using the same time and / or frequency resources. This situation may be referred to as "contention" or "collision." To resolve the contention, the base station 5 transmits a content resolution message to the UE 3 in step S604. The transmission in step S604 may be referred to as Message 4 (MSG4). MSG4 indicates to the UE 3 whether the MSG3 transmitted by the UE 3 in step S603 was received and successfully decoded by the base station. If the base station 5 decodes MSG3 transmitted by another UE 3 in contention with the UE 3, or if interference occurs between the MSG3 transmitted by the two UEs 3, the MSG3 transmitted in step S603 may not have been received or successfully decoded by the base station 5. If MSG3 sent by UE3 is not decoded by base station 5 (UE3 can determine this if UE3 does not receive MSG4 from base station 5), then UE3 returns to step S601 of the method and sends another MSG1 to base station 5 (e.g., after selecting a different random access).

[0174] The procedure shown in FIG. 6 is an example of a contention-based RA procedure in which UE 3 selects a random access preamble from a group of preambles that may also be used by other UEs 3 (thus, a conflict may occur if two of UEs 3 select the same random access preamble). Alternatively, base station 5 may send a random access preamble assignment to UE 3 before UE 3 sends MSG1 to base station 5, in which case the RA procedure is contention-free (conflict resolution in step S604 may not be performed). The random access preamble assignment may be sent to UE 3 using an RRC message or Layer 1 (L1) signaling (e.g., DCI carried by the PDCCH). In the method shown in FIG. 5, a random access preamble assignment for communication with target base station 5 may be sent to UE 3 in step S505.

[0175] MSG1 and / or MSG3 may be used by UE 3 to request any of the on-demand SIs described above from base station 5.

[0176] Broadcast and Multicast The base station 5 may transmit a broadcast intended for reception by any UE 3 within the cell of the base station 5, or may transmit a transmission intended for reception by a specific UE 3 (point to point (PTP) transmission). The base station 5 may also transmit a transmission intended for reception by a specific group of UE 3 (point to multiple (PTM) transmission). A transmission intended for reception by a single UE 3 may be referred to as a unicast transmission, and a transmission intended for reception by a group of UE 3 may be referred to as a multicast transmission.

[0177] A multicast service may include a PTP leg between a base station 5 and a single UE 3, and PTM legs between a base station 5 and multiple UEs 3. PTP and PTM transmissions are shown schematically in Figure 7. While multiple UEs 3 are shown separated in Figure 7, it will be understood that a UE 3 may receive both the PTP and PTM parts of a multicast. A PTP may be described as a PTP "leg" or "portion" of a multicast transmission. Similarly, a PTM may be described as a PTM "leg" or "portion" of a multicast transmission.

[0178] The PTM leg has an MBS radio bearer (MRB) with a corresponding MRB configuration. Each MRB may have an associated identifier (e.g., MRB-Identity) that can be used to identify the MRB. The MRB identity may be included in any appropriate transmission for MRB configuration. The multicast service may be suspended (the process by which an MRB is released) or reactivated based on multicast data activity (or inactivity). The configuration of one or more MRBs may be provided to the UE 3 and / or the base station using any appropriate radio link control (RLC) configuration signaling (e.g., in an RLC Bearer Configuration message).

[0179] The base station 5 may provide the multicast MRB configuration to the UE 3 through dedicated signaling. The multicast MRB may be configured in DL only RLC unacknowledge mode (RLC-UM) where no acknowledgement / negative-acknowledge (ACK / NACK) feedback is sent, or the MRB may have bidirectional RLC-UM for PTP transmission.

[0180] The multicast MRB configuration may include an RLC-acknowledge mode (RLC-AM) configuration for transmitting ACK / NACK feedback. The multicast MRB configuration may include an RLC-unacknowledge mode (RLC-UM) configuration in which ACK / NACK feedback is not transmitted.

[0181] The multicast MRB configuration may include an RLC-AM entity for PTP transmission. The multicast MRB configuration may include a DL only RLC-UM entity for PTM transmission.

[0182] A multicast MRB configuration may include two RLC-UM entities, one of which may be a DL-only RLC-UM entity for PTP transmissions and the other RLC-UM entity may be a DL-only RLC-UM entity for PTM transmissions.

[0183] A multicast MRB configuration may include three RLC-UM entities, one of which is a DL only RLC-UM entity, another of which is a UL RLC-UM entity for PTP transmission, and one RLC-UM entity is a DL only RLC-UM entity for PTM transmission.

[0184] A multicast MRB configuration may include two RLC entities, one of which is an RLC-AM entity for PTP transmission and the other RLC entity is a DL only RLC-UM entity for PTM transmission.

[0185] Logical Channel and Logical Channel Priority A logical channel (LCH) may be a control channel for transmitting control information and / or configuration information (control plane information), or may be a channel used for transmitting user data (user plane information). Logical channels that may be used in the system shown in FIG. 1 include a broadcast control channel (BCCH), a paging control channel (PCCH), a common control channel (CCCH) used by UE 3 during initial access, a dedicated control channel (DCCH), and a dedicated traffic channel (DTCH). One or more transport channels may also be used in the system of FIG. 1. Transport channels include a broadcast channel (BCH), a paging channel (PCH), a downlink shared channel (DLSCH), an uplink shared channel (ULSCH), and a random access channel (RACH). Mapping between logical channels and transport channels may be performed at the medium access control (MAC) layer, and multiple logical channels may be multiplexed for transmission using a transport channel (e.g., based on the priority of each logical channel, as described below). For example, the BCCH may be mapped to the BCH or DLSCH, and the PCCH may be mapped to the PCH. The transport channels are mapped to corresponding physical channels (e.g., PDCCH, PDSCH, or PBCH for downlink transmission, and PUSCH, PUCCH, or PUSCH for uplink transmission).

[0186] A logical channel may be identified using a corresponding logical channel ID (LCID). A set of logical channels may be grouped into a logical channel group (LCG) and identified using a corresponding index (e.g., an index between 0 and 7).

[0187] Logical channels may be assigned priorities (e.g., transmission priorities) by the network. For example, a logical channel used for part of a handover procedure may be assigned a relatively high transmission priority because transmission delays in the handover procedure increase the likelihood of handover failure. The base station 5 may determine to preferentially include data (or other information) corresponding to a logical channel with a relatively high priority in a medium access control (MAC) protocol data unit (PDU) to be transmitted to the UE 3, rather than including data or other information corresponding to a logical channel with a relatively low priority. The base station 5 may also control scheduling of uplink transmissions by the UE 3 based on the priorities of the logical channels.

[0188] A prioritized bit rate (PBR) may be defined for a logical channel. The prioritized bit rate may be set by the base station 5. The prioritized bit rate is a bit rate set for logical channels with a relatively high priority, and the remaining available bit rate (or a portion of the remaining available bit rate) is set for the transmission of logical channels with a relatively low priority. The use of PBR is beneficial to avoid a situation where only the highest priority logical channel is transmitted.

[0189] Artificial Intelligence (AI) / Machine Learning (ML) Figure 8 shows the framework for AI / ML models and how the various entities in the framework interact.

[0190] The entities include a data collection function 41, a model training function 43, a model inference function 45, and an actor 47. The data collection function 41 provides input data (training data) to the model training function 43 and the model inference function 45. The collected data may be, for example, data related to mobility (e.g., handover of the UE 3 or the location of the UE 3). For example, the data may be acquired by a base station 5 (e.g., by receiving measurement reports from the UE 3 or by receiving data from another base station 5 or core network node / function) or transmitted to another base station 5 that generates an AI / ML model inference output (alternatively, the same base station that acquires the data may generate the AI / ML model output). The model training function 43 may perform training, validation, and testing of the ML model and generate model performance metrics as part of the model testing procedure. The model reasoning function 45 provides the inference output (e.g., prediction or decision) of the AI / ML model, and the actor 47 is a function or node that receives the output from the model reasoning function 45 and triggers or performs a corresponding action (e.g., the base station 5 increasing / decreasing its transmit power, or the base station 5 initiating a handover procedure for the UE 3). The AI / ML model inference output may be, for example, a prediction of the mobility of the UE 3 (e.g., an expected path, route, or trajectory, inter-cell or inter-beam mobility, or an expected handover), or one or more parameters for use in encoding or decoding transmissions between the base station 5 and the UE 3. The functions illustrated in FIG. 8 may be co-located in a single node of the communications network (e.g., a base station 5 or a core network node / function) or distributed across multiple network nodes (e.g., multiple base stations 5).

[0191] Terms used by 3GPP in the context of this framework include:

[0192] AI / ML Training: The online or offline process of training an AI / ML model.

[0193] AI / ML Validation: A method for assessing the quality (e.g., predictive accuracy) of an AI / ML model using a dataset different from the one used to train the model.

[0194] AI / ML model testing: A method of evaluating the performance of the final AI / ML model using a dataset different from the dataset used for training and validation.

[0195] AI / ML Data Collection: The method by which data is collected by a network node, a management entity, and / or a UE3 for training an AI / ML model, for data analysis (e.g., monitoring model performance), and / or for generating inferences using an AI / ML model.

[0196] Model monitoring: A method for monitoring the inference performance (e.g., predictive accuracy) of AI / ML models.

[0197] Training data: Data used as input to the training function of an AI / ML model.

[0198] Supervised Learning: A method of training AI / ML models using labeled data.

[0199] Unsupervised Learning: A method of training AI / ML models using unlabeled data.

[0200] Semi-supervised learning: A method of training AI / ML models using both labeled and unlabeled data.

[0201] Inference data: Input data to an AI / ML model inference function to generate an inference.

[0202] Model Deployment / Update: How an AI / ML model is deployed to a model inference facility (e.g., sent to a network node) or how an updated model is delivered to a model inference facility.

[0203] The data collection 41 may be performed at various nodes of the communication network (eg one or more base stations 5 or UEs 3).

[0204] FIG. 9 is an illustration of a method for training an AI / ML model and a method for monitoring the performance of the AI / ML model. As shown in FIG. 9, first, in a data extraction step, stored data / features are extracted. In a data validation step, a decision is made (e.g., based on the extracted data) to proceed or retain training of the AI / ML model. In a data preparation step, data is prepared for use in training the AI / ML model. For example, the data may be cleaned (e.g., filtered), transformed, or modified in other suitable ways. Also, in the data preparation stage, the data may be divided into a training data set, a validation data set, and a test data set.

[0205] In the model training step, the AI / ML model is trained (or retrained) using the training data prepared in the data preparation step. It will be appreciated that any suitable training method can be used to train the AI / ML model (e.g., methods including supervised learning or unsupervised learning). In the model validation step, the AI / ML model is validated (e.g., the predictive accuracy of the AI / ML model is validated) using a test dataset (which may be generated in the data preparation step). In the model validation step, a determination is made (e.g., based on the results of the model validation step) as to whether the AI / ML model is suitable for deployment in a communications network.

[0206] In the model serving step, the AI / ML model is deployed for use in the communications network 1. Deploying the AI / ML model may include compiling the trained AI / ML model, packaging the model into an executable format, and distributing the AI / ML model to target devices. For example, the AI / ML model may be transmitted to the base station 5 and / or the UE 3 as part of the prediction serving step, as shown, for use by the base station and / or the UE to generate predictions or decisions using the AI / ML model. In the performance monitoring step, the performance of the deployed AI / ML model is monitored. The predictive performance of the AI / ML model may be monitored by comparing predictions generated using the model to one or more measurements. For example, if the AI / ML model is used to predict the location of the UE 3, the predictive accuracy of the AI / ML model may be evaluated using measurements of the actual location of the UE 3. Alternatively, if the AI / ML model is used to determine parameters used in encoding and decoding data transmitted between the base station 5 and the UE 3, the model may be evaluated based on the performance of the encoding and / or decoding process. In the retraining trigger step, retraining of the AI / ML model is triggered (e.g., because the predictive accuracy of the AI / ML model falls below an acceptable threshold accuracy, or because the performance of a method using inferences from the AI / ML model falls below an acceptable threshold performance), and the method returns to the data extraction step.

[0207] As described above with reference to Figure 8, each step of the method of Figure 9 may be performed at a single node of the communications network 1, or alternatively, multiple steps of the method may be distributed among multiple different nodes.

[0208] AI / ML for UE Mobility Next, several examples will be described in which the AI / ML model is used to predict the mobility of the UE 3 (e.g., predicted route / path, inter-cell or inter-beam mobility, or handover). Predicting the mobility or location of the UE 3 enables more efficient operation of the communication network. For example, radio resource management (such as selecting a target handover cell) can be performed more efficiently using the predicted mobility of the UE 3. The predicted mobility of the UE 3 can also be used for early data forwarding (e.g., used in a CHO procedure, such as one of the CHO procedures described above). However, as mentioned above, the AI / ML model is not limited to use for mobility prediction. Alternatively, for example, the AI / ML model may be used to determine parameters for encoding and / or decoding of data transmitted between the UE 3 and the base station 5.

[0209] As discussed above with reference to Figures 8 and 9, information collected by nodes / functions in a communication network can be used as training data for AI / ML models and as inference data used to generate one or more model inferences using the AI / ML models. Information used as training data and / or information for generating one or more model inferences may be referred to as "AI / ML information." Methods for requesting and transmitting AI / ML information are now described.

[0210] 10 is a diagram showing an example of an AI / ML information request and an AI / ML response. In step S1501, the first base station 5-1 transmits an AI / ML information request to the second base station 5-2. The AI / ML request is a request for AI / ML information (e.g., information related to the actual mobility of the UE 3) from the second base station 5-2.

[0211] After receiving the AI / ML information request in step S1501, the second base station 5-2 transmits an AI / ML information response including the AI / ML information to the first base station 5-1. In addition, the second base station 5-2 may start periodic reporting of the AI / ML information to the first base station 5-1 in response to receiving the AI / ML information request. The periodic reporting may be configured using a corresponding AI / ML information reporting configuration (e.g., including a reporting period, a number of reports, or a reporting duration / period) indicated by the AI / ML information request. The AI / ML information request may include an information element (IE) indicating that the second base station 5-2 should start or stop periodic reporting of the AI / ML information to the first base station 5-1. Alternatively, the AI / ML information request may be a request for a one-time report of the AI / ML information from the second base station 5-2, rather than a periodic report.

[0212] If the second base station 5-2 is unable to transmit the requested AI / ML information to the first base station 5-1 (e.g., because the requested information is unavailable at the second base station 5-2), the base station 5-2 may transmit a corresponding indication, e.g., an AI / ML information failure message, to the first base station 5-1 indicating that the second base station is unable to provide the requested information. The AI / ML information failure message may include an indication (e.g., a cause value) of the reason why the second base station 5-2 is unable to provide the requested AI / ML information.

[0213] Upon receiving the AI / ML information, the first base station 5-1 may use the AI / ML information to train (or update) a corresponding AI / ML model (e.g., for the mobility of the UE 3) or to generate a prediction (e.g., a prediction of the mobility of the UE 3). Alternatively, the first base station 5-1 may forward the AI / ML information to another network node for use in an AI / ML model in the other network node.

[0214] In the example shown in FIG. 10, the AI / ML information response may include the requested AI / ML information, but instead, the AI / ML information response may be an indication that the second base station 5-2 will transmit the AI / ML information in a subsequent AI / ML information update (e.g., an acknowledgement of the AI / ML information request). FIG. 11 shows an example of an AI / ML information update. In step S1601, the second base station 5-2 determines to transmit an AI / ML information update to the first base station 5. For example, the second base station 5-2 may determine to transmit an AI / ML information update to the first base station 5-2 based on the reporting period received by the second base station 5-2 in step S1501 of FIG. 10, or may determine to transmit an AI / ML information update based on a change in the AI / ML information stored in the second base station 5 (or based on new AI / ML information obtained at the second base station 5-2). In step S1602, the second base station 5-2 transmits the AI / ML information to the first base station 5-1 in an AI / ML information update.

[0215] Predicted UE Mobility Next, exemplary methods for transmitting the predicted mobility of the UE 3 to a node / function within a communications network are described. While these examples are described with reference to UE mobility information and corresponding mobility feedback, it will be understood that these methods are not limited to being used for mobility prediction and mobility feedback. For example, instead of mobility prediction, an AI / ML model may be used to generate one or more parameters for encoding and / or decoding of transmissions between the base station 5 and the UE 3. In this case, the feedback may correspond to an indication of the encoding and / or decoding performance.

[0216] The predicted mobility of UE 3 may be generated using an AI / ML model, for example, using the AI / ML information received in step S1602 of Figure 11. The predicted mobility of UE 3 (which may also be referred to as predicted mobility information or AI / ML model output information) may include a predicted route, path, trajectory, or direction of movement of UE 3, or may be an indication of the predicted inter-cell or inter-beam mobility of UE 3, for example.

[0217] Base Station Scenario In a handover scenario between base stations 5, the predicted mobility of UE3 can be included in the handover request message (e.g., in step S503 of Figure 5), allowing the target base station 5 to utilize the predicted mobility information of UE3 (e.g., for more efficient configuration of resources at the target base station 5).

[0218] The handover request message sent in step S503 may include predicted UE mobility information (e.g., predicted UE trajectory). As mentioned above, the predicted UE mobility information may indicate a predicted route, path, or future location of the UE 3, or a predicted inter-cell or inter-beam mobility of the UE 3.

[0219] The handover request message may include a predicted UE mobility accuracy indicating the accuracy of the prediction. The predicted UE mobility accuracy may be expressed, for example, as a percentage (e.g., as a percentage probability that the prediction is correct or accurate) or in any other suitable format (e.g., as a number of standard deviations). The prediction accuracy may indicate the accuracy of the prediction of the route, path, or location of the UE 3 and / or the accuracy of the prediction of the duration that the UE 3 will remain in a particular location (e.g., within a particular cell).

[0220] The handover request message may include UE history information. For example, the UE history information may include location history information of the UE 3 at the cell level, beam level, tracking area (TA) level, or RAN-based notification area (RNA) level. The handover request message may include an indication of the identity of the AI / ML model used to generate the predicted mobility of the UE 3. The handover request message may also include an indication of input to the AI / ML model used to generate the predicted mobility of the UE 3. For example, the handover request message may include an indication of the UE mobility type (e.g., high speed, low speed, medium speed), UE type (e.g., internet of things (IoT) UE, wearable UE, Redcap UE, stationary UE), and / or UE location information or UE fingerprint (e.g., radio frequency fingerprint) input into the AI / ML model.

[0221] Although this example regarding UE mobility information and prediction accuracy information has been described with reference to a handover request message, this is not necessarily the case. Alternatively, the UE mobility information and / or prediction accuracy information may be included in any other suitable type of transmission to the target base station (e.g., via the UE 3 and the handover configuration complete message of step S505). The received information may, for example, be used to train or retrain an AI / ML model at the target base station 5, beneficially enabling the target base station 5 to use the AI / ML model to determine a more accurate prediction of the future mobility of the UE 3.

[0222] DU-to-DU scenario During the inter-DU handover, the CU 60 may send a UE context setup / modification request message to the target DU 50. The UE context setup / modification request message may be used to set up signaling radio bearers (SRBs) and data radio bearers (DRBs) in the target base station 5 for communication between the target base station 5 and the UE 3. The UE context setup / modification request message may include cell-level, beam-level, TA-level, or RNA-level UE history information, which allows the target base station 5 to more efficiently configure resources (e.g., time or frequency radio resources) during the handover procedure.

[0223] The UE context setup / modify request message may include predicted mobility information for the UE 3, as described above for the inter-base station scenario. Similarly, the UE context setup / modify request message may include AI / ML model identification information, prediction accuracy, and / or AI model inputs, as described above for the inter-base station scenario.

[0224] NG Handover Scenario Next, an exemplary next generation (NG) handover (NGHO) scenario will be described. During NGHO, predicted UE mobility may be transmitted to a target base station via AMF. In a first example, the predicted UE mobility (or other inference, as described above, this example is not limited to mobility prediction) is forwarded in a transparent container via the source base station to the target base station (e.g., using a source NG-RAN Node to Target NG-RAN Node Transparent Container IE in a next generation application protocol (NGAP) handover required message). Alternatively, the predicted UE mobility information may be transmitted in an NGAP handover request message using an appropriate AI / ML prediction information element. The information transmitted to the target base station via AMF may include the UE's predicted mobility information, as described above for the inter-base station scenario. Similarly, the information transmitted to the target base station via AMF may include the AI / ML model identification, prediction accuracy, and / or AI model input, as described above for the inter-base station scenario.

[0225] As shown in Figures 8 and 9, feedback may be used to improve the AI / ML model (e.g., by training the AI / ML using the feedback) or to verify the accuracy of the AI / ML model. For example, feedback may be used to determine that the AI / ML model be retrained. In this example, feedback is returned to the source base station via the AMF. The feedback information may be transferred using an NGAP procedure, such as the RAN AI / ML information transfer procedure. This allows the source base station 5 to improve the accuracy of the AI / ML model or verify that the AI / ML model is operating as intended (e.g., within an acceptable accuracy range). The feedback sent to the source base station may include, for example, information indicating the actual location / mobility of the UE, or any other suitable information. Similarly, in the base station-to-base station and DU-to-DU examples described above, feedback may be sent from the target base station / DU to the source base station / DU (e.g., directly or via an intermediate network node) using any suitable message or transmission.

[0226] Beam level prediction / feedback information As described above, the UE mobility prediction may include a mobility prediction for the UE 3 at the cell level. Alternatively, the mobility prediction may be performed at the beam level. Beam-level mobility prediction allows for more efficient resource configuration at the target base station due to improved prediction accuracy. Similarly, feedback returned to the node operating the AI / ML model may be beam-level feedback rather than simply cell-level feedback, allowing the accuracy of the AI / ML model to be determined at the beam level rather than the cell level. For both the mobility prediction information and the mobility feedback information, beam-level information may be provided instead of, or in addition to, cell-level information. The level of granularity (e.g., cell level, beam level) may be configurable by the network.

[0227] UE Mobility Feedback After handover from the source base station to the target base station, mobility feedback information for the AI / ML model (e.g., the actual location or mobility of UE 3, which may be, for example, at the cell level or beam level) may be sent to the source base station 5 (e.g., from the target base station or another base station). As mentioned above, the feedback may be used at the source base station 5 to verify the accuracy of the AI / ML model, to trigger retraining of the AI / ML model, or to generate further predictions (or other types of inferences) using the AI / ML model. Because handover of UE 3 from the source base station 5 has occurred, the feedback information may not be directly available at the source base station 5, but may be sent to the source base station by another node in the communications network (e.g., another base station, such as the target base station or a further base station, or a core network node / function).

[0228] If the AI / ML architecture is centralized at a particular base station 5, the base station 5 at which the AI / ML model inferences are generated (and the AI / ML retrained, if necessary) may be referred to as the primary base station 5 (or primary RAN node 5). However, this need not necessarily be the case; instead, the AI / ML architecture may be located at another node / function within the communications network, such as a core network node / function. The primary base station 5 (or other network node hosting the AI / ML model) may request AI / ML information from other nodes within the communications network (e.g., other base stations 5) using the procedures described above with reference to Figures 10 and 11. Alternatively, or additionally, other nodes within the network may decide to transmit AI / ML information to the primary base station even if they have not received an AI / ML information request from the primary base station 5. For example, the target base station 5 may decide to transmit AI / ML mobility information to the primary base station 5 in response to handover of the UE 3 to the target base station (e.g., after a predetermined time after the handover or in response to a further handover of the UE 3 from the target base station).

[0229] The selection of the primary base station 5 (or another network node) may be configurable by the network. The primary base station 5 may be selected for a particular UE 3 based on, for example, one or more characteristics (e.g., mobility characteristics) of the UE 3. As an example, the UE 3 may typically travel between the user's home and office on a particular weekday. The home or office may be within the coverage area of ​​a particular base station 5, and this base station may be selected to serve as the primary base station for the UE 3's AI / ML model because it is most likely to have the greatest amount of information about the UE 3's mobility characteristics. During a handover procedure, if the UE 3 is handed over from the primary base station 5 to a target base station 5 (e.g., a base station serving a coverage area where a shopping center the user visits on weekends is located), the target base station may receive a mobility prediction generated using the AI / ML mobility model from the primary base station 5 during the handover procedure (e.g., in step S503 of FIG. 5). The target base station 5 may also feed back information regarding the actual mobility (e.g., trajectory) of the UE 3 to the primary base station 5 so that the primary base station 5 has improved knowledge regarding the mobility of the UE 3 (which may then be used in the primary base station 5, for example, to verify the accuracy of the predictions of the AI / ML model, as described above).

[0230] 12 and 13 show an example in which UE mobility information is fed back to the source base station 5-1 after handover of the UE 3 to a first target base station 5-2 and subsequent handover to a second target base station 5-2. It will be understood that the examples of Figures 12 and 13 are not limited to mobility prediction and mobility feedback. For example, an AI / ML model hosted at the source base station 5-1 may be configured to generate one or more parameters for encoding and / or decoding data transmitted between a base station (e.g., the source base station 5-1, the first target base station 5-2, or the second target base station 5-3) and the UE 3, and the feedback transmitted in step S1709 may include an indication of the performance of the encoding / decoding process or any other suitable feedback.

[0231] In this example, the source base station 5-1 is the primary base station and hosts the AI / ML model for predicting the mobility of the UE 3. Advantageously, information obtained at the second target base station 5-3 regarding the mobility of the UE 3 can be fed back to the source base station 5-1 even if the source base station 5-1 does not have a direct communication link with the second target base station 5-3.

[0232] Steps S1701 and S1702 are the same as steps S501 and S502 in Figure 5, and therefore will not be described again here. It should be noted that the measurements performed by the UE 3 may be generated in a time to trigger (TTT) manner, and the UE 3 may perform one or more additional measurements (shown within the dashed box in the figure), which may be transmitted to the source base station 5-1 or the target base stations 5-2, 5-3, if appropriate.

[0233] In step S1703, the source base station 5-1 (which is the primary base station of the AI / ML model in this example) sends a handover request to the first target base station 5-2. The handover request may include a transaction ID (sometimes called an "event ID" and identifying a particular "transaction" of the UE or a particular handover) or a UE ID (which may be an indication of the identity of the UE 3), and may also include an indication of the identity of the primary base station 5-1 (e.g., a primary base station ID or other suitable type of indication for identifying a node to which feedback should be sent, such as indicating that the handover request is being sent by the primary base station 5-1 hosting the AI / ML model).

[0234] The transaction ID or UE ID can be used to associate feedback regarding the AI / ML model with the UE 3. When the feedback is associated with the transaction ID or UE ID and returned to the source base station 5-1, the source base station 5-1 can determine that the feedback corresponds to mobility information for that particular UE 3. The transaction ID can also be used by the target base station to determine that feedback should be sent to the source base station 5-1.

[0235] The indication of the identity of the primary base station can be used by other network nodes (e.g., the first target base station 5-2 or the second target base station 5-3) to determine to which network node to send feedback. The indication of the identity of the primary network node / function allows the other network nodes / functions to determine which network node / function is the primary network node / function of the AI / ML model for the UE 3.

[0236] The handover request message sent in step S1703 may also include any of the information regarding the predicted mobility of UE 3 in the handover request message described above (e.g., as described above with reference to the inter-base station scenario, inter-DU scenario, and NG handover scenario). For example, the handover request may include predicted mobility information, AI / ML model identification information, prediction accuracy, and / or AI model input.

[0237] In step S1704, the first target base station 5-2 transmits a handover request acknowledgement to the source base station 5-1.

[0238] In step S1705, the source base station 5-1 transmits RRC reconfiguration information for handover (which may also be referred to as configuration information for handover) to the UE 3. The RRC reconfiguration information may include an indication instructing the UE 3 to include an indication of the additional measurement results in a subsequent transmission to the first target base station 5-2 (e.g., in an RRC reconfiguration complete message transmitted in step S1706). The indication instructing the UE 3 to include an indication of the additional measurement results may be referred to as an AI mobility enhancement report indication. In this example, if additional measurements have been performed after the measurement report was transmitted to the source base station in step S1702 (as illustrated by the dashed box in Figures 12 and 13), the UE 3 includes an indication of the additional measurement results in the RRC reconfiguration complete message of step S1706. Accordingly, measurement information corresponding to measurements taken by the UE 3 prior to handover may be transmitted to at least one of the base stations and fed back to the primary base station (e.g., as part of the performance monitoring step of FIG. 9 ) (e.g., to determine whether the decision to hand over the UE to the target base station 5-2 was made at the right time, appropriately or correctly). The target base station 5-2 may use the information to improve the handover decision process at the target base station 5-2. In this example, the AI ​​mobility improvement report indication is transmitted to the UE 3 within the RRC reconfiguration message, although this indication may alternatively be transmitted to the UE 3 in another suitable transmission (e.g., a dedicated transmission after receiving the handover request acknowledgment from the target base station 5-2 and before transmitting the RRC reconfiguration message to the UE 3).

[0239] In step S1706, the UE 3 sends an RRC reconfiguration complete message to the first target base station 5-2. The UE 3 also includes additional measurement reports as instructed by the source base station 5-1 in the RRC reconfiguration message of step S1705.

[0240] In step S1707, the first target base station 5-2 feeds back mobility information for the AI / ML mobility model to the source base station 5-1 (which is the primary base station of the AI / ML mobility model). The information transmitted in step S1701 may be, for example, information indicating the actual mobility (e.g., trajectory) of the UE 3 after handover. As mentioned above, the mobility information fed back to the primary base station 5-1 may be at the cell level, beam level, TA level, RNA level, or other level of granularity or precision. If an indication of the additional measurement results is received by the first target base station 5-2 from the UE 3 in step S1706, the first target base station 5-2 includes the indication of the additional measurement results in the information transmitted to the source base station 5-1. In this example, the UE mobility information is transmitted to the source base station 5-1 in association with the transaction ID or UE ID received in step S1703, allowing the source base station 5-1 to identify which UE 3 the feedback information relates to.

[0241] In step S1708, the first target base station 5-2 transmits a handover request to the second target base station 5-3. The first target base station 5-2 may decide to transmit the handover request based on, for example, the mobility prediction received from the primary base station 5-1 in step S1703 (e.g., indicating that the UE 3 is likely to move into the coverage area provided by the cell or beam of the second target base station 5-3). As described above with respect to step S1703, the first target base station 5-2 includes a transaction ID or UE ID and an indication of the identification information of the primary base station 5-1 in the handover request message. Thus, the second target base station 5-2 can determine which base station is the primary base station 5-1 and can transmit subsequent feedback information of the AI / ML model regarding the UE 3 in association with the transaction ID or UE ID (thereby allowing the primary base station 5-1 to determine which UE 3 the feedback relates to). In addition, the first target base station 5-2 may include any other information related to the AI / ML mobility model received from the source base station 5-1 in step S1703 (e.g., predicted UE mobility information, model ID, or model input).

[0242] In step S1709, since the second target base station 5-3 in this example has a direct communication link (e.g., an Xn interface) with the source base station 5-1, it transmits the UE mobility information feedback directly to the source base station 5-1. The second target base station 5-3 can identify the source base station 5-1 to which to send the feedback based on the indication of the primary base station identification information received from the first target base station 5-2 in step S1708. As mentioned above, the mobility information fed back to the source base station 5-1 may include the actual location or mobility of the UE 3 (e.g., cell level or beam level), or any other suitable information related to the mobility of the UE 3 that can be used with the AI / ML model at the source base station 5-1 (e.g., the time duration that the UE 3 is at a particular location).

[0243] Figure 13 shows a modification of the method of Figure 12, in which the second target base station 5-3 transmits UE mobility information feedback to the source base station 5-1 via the first target base station 5-2. For example, the second target base station 5-3 may transmit the UE mobility information feedback to the source base station 5-1 via the first target base station 5-2 because the second target base station 5-3 does not have a direct communication link with the source base station 5-1 (e.g., there is no Xn interface).

[0244] Steps S1801 to S1808 are the same as steps S1701 to S1708 described with reference to FIG. 12, so a repeated description will be omitted here.

[0245] In step S1809, the second target base station 5-3 transmits UE mobility information feedback to the first target base station 5-2. As mentioned above, the information transmitted in step S1809 may, for example, be information indicating the actual mobility (e.g., trajectory) of the UE 3 after handover to the second target base station 5-2, and the feedback information is transmitted in association with a transaction ID or UE ID (which allows the primary base station 5-1 to determine which UE 3 the feedback relates to). The transmission of step S1809 may further include an indication of the identity of the primary base station 5-1 (but does not necessarily have to, since the first target base station 5-2 has already received an indication of the identity of the primary base station 5-1 in step S1803 for the handover of the same UE 3).

[0246] In step S1810, the first target base station 5-2 forwards the UE mobility information feedback to the source base station 5-1. Thus, even if the second target base station 5-3 does not have a direct communication link with the source base station 5-1 (e.g., there is no Xn interface), the source base station 5-1 (which is the primary base station in the AI / ML model and generates the mobility prediction) can receive the UE mobility feedback in the AI / ML model from the second target base station 5-3.

[0247] Distributed AI / ML Architecture While in the examples described above with reference to Figures 12 and 13, the network includes a primary node / function that hosts the AI / ML model and generates inferences for the AI / ML model, the AI / ML model may alternatively be distributed among various nodes within the network. For example, multiple base stations 5 may host the AI / ML model and generate inferences. While this may increase the processing required in some network nodes, distributing the AI / ML model among network nodes beneficially reduces the number of inferences sent between nodes. For example, with reference to Figure 12, if the first target base station 5-2 is configured to generate a prediction of the mobility of UE 3 using the AI / ML model, the first target base station 5-2 does not necessarily need to receive the mobility prediction from the source base station 5-1.

[0248] If an AI / ML model (or multiple AI / ML models, not necessarily the same model at each base station 5) is provided at multiple base stations 5, feedback information can be provided to each base station that generates inferences using the AI / ML model (e.g., to verify the accuracy of the model, as described above).

[0249] Configuration information for AI / ML Configuration information for an AI / ML model (which may be referred to as "AI / ML configuration information") may be exchanged between nodes in a communications network. For example, a core network node may send the AI / ML configuration information to a base station 5 that hosts the AI / ML model. The AI / ML configuration information may include a list of supported use cases for the AI / ML model (the AI / ML model is not necessarily for predicting UE mobility). The supported use cases may be, for example, energy saving, traffic steering, anomaly detection, quality of experience (QoE) optimization, mobility robustness optimization (MRO), RAN slice service level agreement (SLA) guarantee, massive multiple-input multiple-output (MIMO) beamforming optimization, network slice subnet instance (NSSI) resource allocation, coverage and capacity optimization (CCO), mobility load balancing (MLB), RACH optimization, or UE transmit power optimization. The AI / ML configuration information may include an indication of a particular AI / ML model to use for a particular use case. The AI / ML configuration information may further include an indication of whether feedback is required (e.g., from another network node, as described above with reference to step S1707 of FIG. 13). The feedback may include, for example, communication performance feedback (eg, indicating communication performance of communication between the UE 3 and the base station 5).

[0250] If multiple AI / ML models are stored in the base station (or other network node), the base station 5 may receive an indication of which AI / ML model to use. The base station 5 may also receive (e.g., from a core network node / function) an indication that use of a particular model is to be activated or deactivated (e.g., a particular AI / ML model is deactivated when prediction accuracy falls below an acceptable accuracy threshold in response to a determination in the performance monitoring step of FIG. 9). The base station 5 may be provided with multiple AI / ML models, each model being used in a particular scenario or setting.

[0251] Single-sided and two-sided models The AI / ML model may be hosted by both the base station 5 and the UE 3, or may be hosted only by the base station 5, or may be hosted only by the UE 3. When the AI / ML model is used only by the UE 3, the AI / ML model may be referred to as a "single-sided" model. For example, the UE 3 may host an AI / ML model for generating time (e.g., time resources) for communication using a particular beam transmitted by the base station 5. However, it should be understood that even if the model is a single-sided model, the model does not necessarily need to be trained on the UE 3. For example, the model may be trained on the base station 5 or another node in the network (e.g., a core network node / function) and then transmitted to the UE 3 for use by the UE 3. In other words, the AI / ML model may be trained on another network node and then transferred / deployed to the UE 3.

[0252] Alternatively, the AI / ML model may be a “two-sided” model in which an AI / ML model is hosted on the UE 3 and a corresponding AI / ML model is hosted on the base station 5 (however, the models do not necessarily have to be hosted on the UE 3 and the base station 5; any other suitable two network nodes may alternatively be used). The AI / ML model hosted on the UE 3 and the AI / ML model hosted on the base station 5 may be the same AI / ML model. The UE 3 may use the AI / ML model to generate a first inference, and the base station 5 may use the AI / ML model to generate a corresponding second inference. For example, the first inference may be an inference of parameters used to compress data (e.g., channel state information (CSI)) transmitted from the UE 3 to the base station 5, and the second inference may be an inference of parameters used to decompress the data at the base station 5. As with the one-sided model, the two-sided model (or models) may be trained on any suitable network node and then transmitted to the UE 3 and the base station 5.

[0253] AI / ML model acquisition A particularly advantageous method of AI / ML model deployment will now be described. In this example, the AI / ML model is transmitted to the UE 3 for use by the UE 3. The AI / ML model may be a two-sided model (in which case a corresponding or the same AI / ML model is used in the base station 5), but alternatively it may be an AI / ML model used only in the UE 3.

[0254] In this example, broadcast or multicast transmission is used to transmit the AI / ML model to UE 33 when UE 3 is in an RRC idle state or an RRC inactive state, and multicast transmission and / or RRC messages (e.g., dedicated RRC messages or other new RRC messages different from legacy RRC messages) are used to transmit the AI / ML model to UE 3 when UE 3 is in an RRC connected state.

[0255] FIG. 14 shows an example of how the base station 5 may broadcast an indication of the supported AI / ML models.

[0256] In step S1401, the base station 5 broadcasts an indication of the supported AI / ML models. In this example, the indication of the supported AI / ML models is included in system information (SI) broadcast within the base station's cell. The UE 3 in this example is in an RRC idle state or an RRC inactive state (although it could alternatively be in an RRC connected state). Advantageously, the UE 3 can therefore receive information indicating which AI / ML models are supported by the base station 5 even when the UE 3 is in an RRC idle state or an RRC inactive state.

[0257] The broadcast SI may include a list of AI / ML model IDs and / or version numbers of supported AI / ML models. The supported AI / ML models may be indicated per use case. For example, a first indication of supported AI / ML models for beam management may be provided, and a second indication of supported AI / ML models for encoding / decoding CSI may also be provided. The indication of supported AI / ML models may be periodically broadcast by the base station 5, or alternatively, may be broadcast on-demand in response to a request from the UE 3. In addition, the broadcast SI may include an indication of a method for obtaining the AI / ML models (e.g., signaling-based transmission between the UE 3 and the RAN node 5, or database-based transmission between the UE 3 and the AI / ML server 151). If the UE 3 obtains the AI / ML models from the AI / ML server 151, the identity and (IP) address of the AI / ML server 151 may also be included in the SI.

[0258] In step S1402, UE 3 determines whether to acquire one of the supported AI / ML models based on the indication of supported AI / ML models received from base station 5. In this example, UE 3 decides to acquire one of these models and, in step S1403, sends a request for the model to base station 5. Step S1403 may be performed when UE 3 is in an RRC idle state or an RRC inactive state (or as part of a transition from an RRC idle state or an RRC inactive state to an RRC connected state, e.g., using MSG3, as described in more detail below). In step S1404, base station 5 sends the requested model to UE 3. As described in more detail below, UE 3 may be in an RRC connected state, an RRC inactive state, or an RRC idle state when receiving the AI / ML model from the base station in step S1404.

[0259] In the example of FIG. 14, UE 3 sends a request for an AI / ML model to base station 5 and receives the requested AI / ML model from base station 5, but this is not necessarily the case. Alternatively, UE 3 can request and receive the AI / ML model from another appropriate node in the network (e.g., another base station 5 or a core network node / function / server) after receiving an indication of supported AI / ML models from base station 5. For example, FIG. 15 shows a modified version of FIG. 14 in which UE 3 requests an AI / ML model stored in AI / ML server 151. FIG. 15 includes new steps S1403b and S1403c. In step S1403b, base station 5 sends a request for the AI / ML model requested by UE 3 to AI / ML server 151. In step S1403c, AI / ML server 151 sends the requested model to base station 5 for forwarding to UE 3 in step S1404. The forwarding of the AI / ML model via the base station 5 in steps S1403c and S1404 may be transparent to the base station 5 (e.g., the AI / ML model may be transmitted using one or more transparent containers). In a further alternative, the UE 3 may obtain the AI / ML model from the AI / ML server 151 via the AMF 10-1, for example, using NAS-based signaling. For example, rather than sending a request for the AI / ML model to the base station 5, the UE 3 may send a request for the AI / ML model to the AMF 10-1. The AMF 10-1 may then request the model from the AI / ML server 151 and forward the AI / ML model from the AI / ML server 151 to the UE 3. In another alternative, the UE 3 may request the AI / ML model from the base station 5, which may then request the AI / ML model from the AI / ML server 151. However, rather than transmitting the AI / ML model to the UE 3 via the base station that received the request, the AI / ML model may be transmitted to the UE 3 via the AMF 10-1 (using corresponding NAS signaling).

[0260] When UE 3 requests an AI / ML model stored in AI / ML server 151, the UE 3's retrieval of the AI / ML model from server 151 may be transparent to the wireless network from a signaling perspective, since the transfer of the AI / ML model from server 151 to UE 3 may be a normal data transmission, etc. However, when UE 3 establishes an RRC connection with the wireless network for such data transmission, it may include an RRC establishment cause (e.g., for AI / ML model transfer) and / or an AI / ML server address in the RRC message. (R)AN node 5 may forward that information to the core network. Beneficially, this information helps RAN node 5 and / or a core network node to establish a subsequent user plane data tunnel for AI / ML model transmission between server 151 and UE 3.

[0261] The determination of whether to acquire an AI / ML model in step S1402 may be based on a comparison of the AI / ML model stored in the UE 3 with a supported AI / ML model. For example, the base station 5 may provide an indication of the model versions of the supported AI / ML models in the information broadcast in step S1401, and the UE 3 may compare the version number of the model stored in the UE 3 with the version number of one of the supported models and determine to acquire a newer version of the model. Alternatively, the UE 3 may determine that it does not store an AI / ML model for a particular use case (e.g., for encoding CSI) and therefore decide to acquire a supported AI / ML model for that use case. Additionally or alternatively, the UE 3 may determine to send the request for an AI / ML model based on a timer. Advantageously, the use of the timer allows the UE 3 to request a newer version of the AI / ML model even if the UE 3 has not received the indication of the supported AI / ML model in step S1401 (e.g., the UE 3 may send a request for the latest version of the AI / ML model stored in the UE 3 to the base station 5 based on the timer, regardless of whether the UE 3 received the transmission of step S1401). In a further alternative, the base station 5 may determine to send an updated version of the model to the UE 3 in step S1404 based on the timer. Thus, advantageously, the base station 5 can provide the latest version of the AI / ML model to the UE 3 even if it has not received a request for the latest version of the AI / ML model from the UE 3. This may be particularly beneficial for two-sided models, where the version of the model at the UE 3 (e.g., the version for encoding CSI) may need to match or correspond to the version of the model at the base station 5 (e.g., the version for decoding CSI).By transmitting the request for an AI / ML model in step S1403 or the transfer of the model in step S1404 based on a timer, the risk of the model in the UE 3 becoming inconsistent with the model in the base station 5 is reduced. It will be appreciated that even if a timer is used for the transmission of S1403, the UE 3 may decide to transmit a request for one or more AI / ML modes even if the time has not yet elapsed (e.g., based on information received in step S1401, as described above).

[0262] The UE 3 may perform a random access procedure (e.g., the RA procedure described above with reference to FIG. 6) to request an AI / ML model from the base station 5. In this example, the MSG 3 sent from the UE 3 to the base station 5 in the RA procedure advantageously includes an RRC establishment cause indicating that the UE 3 is requesting an AI / ML model (e.g., by including an indication of the identity of the requested AI / ML model or an indication that the UE 3 will enter an RRC connected state to download the AI / ML model from the base station 5). In either the example of FIG. 14 , in which the requested AI / ML model is initially stored in the base station 5, or the method of FIG. 15 , in which the AI / ML model is initially stored in the AI / ML server 151 (or other suitable network node), the UE 3 may request the AI / ML model using the RA procedure.

[0263] While the use of MSG3 and an RRC establishment cause provides a particularly efficient mechanism for indicating that the UE 3 is requesting an AI / ML model, the indication may alternatively be provided in any other suitable transmission from the UE 3 to the base station 5. For example, the UE 3 may use a new RRC message (e.g., a dedicated RRC message) to indicate that the UE 3 is requesting an AI / ML model. Other suitable methods of obtaining the AI / ML model could alternatively be used, and the UE 3 does not necessarily need to initiate an RA procedure to obtain the model.

[0264] In a further alternative, rather than UE 3 requesting the AI / ML model (by entering the RRC Connected state to receive the model) in response to the determination of step S1402, UE 3 may simply wait until UE 3 next enters the RRC Connected state before obtaining the AI / ML model from base station 5. In another alternative, rather than entering the RRC Connected state to receive the AI / ML model, UE 3 may receive the AI / ML model when UE 3 is in the RRC Idle state or the RRC Inactive state. In this case, base station 5 transmits an indication of the communication resources (e.g., time and frequency resources) to be used by UE 3 to receive the AI / ML model while UE 3 is in the RRC Idle state or the RRC Inactive state.

[0265] The AI / ML model may be transmitted from the base station 5 to the UE 3 in step S1404 using an RRC message or user plane transmission (e.g., using a DRB). Advantageously, a priority (e.g., transmission priority) may be assigned to the DRB or logical channel carrying the AI / ML model. As mentioned above, a logical channel may be assigned (e.g., by the base station 5) an index and / or prioritized bit rate (PBR) indicating the priority of the transmission of that logical channel. The priority or PBR set for the DRB or LCH carrying the AI / ML model may depend, for example, on the type of AI / ML model required (e.g., the AI / ML use case). For example, a DRB or LCH used to transmit an AI / ML model used as part of a handover procedure may be assigned a higher priority (or a higher PBR) than if the AI / ML model is used in a beam prediction procedure.

[0266] From the air interface perspective, when AIML model transfer is subject to user plane transmission as described above, it may differ from traditional user plane (UP) transmission. Traditional UP transmission requires two or more portion-based transmissions (air interface + backhaul-based fixed network). For example, in addition to a DRB on the air interface, a data tunnel established between the base station 5 and a UPF in the core network that bridges data toward a data server is required. In this traditional UP transmission method, the base station 5 is not a data producer but instead a data "consumer." This is because the base station simply converts one or more QoS flows to a DRB at the SDAP layer to support data transmission of a specific QoS service for a data radio bearer on the air interface. However, the inventors have realized that in the case of AIML model transfer, this traditional UP transmission can be advantageously modified. If the base station 5 itself holds an AIML model ready to be transferred to the UE, the base station 5 can become a data producer. If the base station 5 decides to transfer the AI / ML model to the UE 3 via a UP-based channel, the base station 5 can configure the data content of the AI / ML model as a service data unit (SDU) to the PDCP layer, which can be regarded as a special data radio bearer. In this case, in contrast to the conventional method, the data of the AI / ML model is not transmitted by the SDAP layer.

[0267] Step S1404 of Figures 14 and 15 may include transmitting the AI / ML model to UE 3 using a dedicated radio bearer (e.g., a bearer other than legacy SRB / DRB). A new logical channel (e.g., a dedicated logical channel) may be used to transmit the AI / ML model. This logical channel may be assigned a priority and / or PBR as described above, but alternatively, the logical channel may simply be transmitted separately without being multiplexed with other logical channels.

[0268] 16 is a diagram showing an example of a method by which the UE 3 acquires a requested AI / ML model when the requested AI / ML model is initially stored in the CU 60 of the distributed base station. Steps S601 to S603 are the same as steps S1401 to S1403 described above, and therefore will not be described again here. In step S604, the DU 50 transmits a request for the AI / ML model requested by the UE 3 to the CU 60, and in step S605, the CU 60 transmits the AI / ML model to the DU 50. Step S606, in which the DU 50 transmits the requested AI / ML model to the UE 3, is the same as step S1404 in FIGS. 14 and 15.

[0269] A new (e.g., dedicated) F1-application protocol (AP) message or procedure may be used to transmit the AI / ML models from the CU 60 to the DU 50 in step S605. Furthermore, the CU 60 may also transmit to the DU 50 an indication of the supported AI / ML models broadcast by the DU 50 in step S601. The indication of the supported AI / ML models (e.g., model IDs) may be transmitted from the CU 60 to the DU 50 using an F1-AP message (e.g., a dedicated F1-AP message). Thus, the DU 50 can determine the indication of the supported AI / ML models broadcast in step S601.

[0270] As described above, in step S1401 (or step S601), an indication of the supported AI / ML models may be transmitted using system information broadcast within the cell of the base station 5. A new SIB may be used to transmit the indication of the supported AI / ML models. This SIB may be referred to as an “AI / ML SIB.” SIB1 may be used to provide an indication that an AI / ML SIB is available for broadcast within the cell (the AI / ML SIB may be an on-demand SI transmitted in response to a request from the UE 3, not shown in FIG. 14 but transmitted by the UE 3 before step S1401). The MIB and SIB1 may provide the UE 3 with an indication of scheduling information for receiving and decoding the dedicated AI / ML SIB. The AI / ML SIB may include model IDs of supported (or “available”) AI / ML models. As described above, the AI / ML SIB may indicate the supported AI / ML models for each use case.

[0271] The AI / ML SIB may be broadcast periodically (e.g., according to a predetermined periodic pattern) or alternatively may be provided "on-demand," for example, in response to a request from UE 3. SIB1 may be used to indicate to UE 3 whether the AI / ML SIB is transmitted periodically or is available on-demand.

[0272] If an AI / ML SIB is available on demand, the base station 5 provides, in the system information SIB1, an indication of the availability of the AI / ML SIB or information indicating the AI / ML model IDs supported for a particular feature (e.g., beam management). The UE 3 may be configured to request the AI / ML SIB using message 1 (MSG1), which may be referred to as an MSG1-based on-demand SI request for the AI / ML SIB, or message 3 (MSG3), which may be referred to as an MSG3-based on-demand SI request for the AI / ML SIB. Furthermore, the UE 3 may use another type of uplink message to indicate that it is requesting information (e.g., AI / ML model IDs) about one or more AI / ML models supported by the base station. When the network receives the UE 3's request for information (e.g., AI / ML IDs), the network broadcasts (e.g., using the system information block, AI / ML SIB) the AI / ML information (e.g., AI / ML model IDs) supported for the one or more features requested by the UE 3. UE3 can then obtain the AI / ML information by receiving and decoding the broadcasted message (e.g., AI / ML SIB). These steps can be performed before and / or during step S1401 of Figures 14 and 15.

[0273] In the example described above with reference to FIGS. 14 to 16, the UE 3 may request a single AI / ML model in step S1403 (or step S603), or may request multiple AI / ML models.

[0274] Figure 17 shows a modification of the method of Figure 14 in which the network is configured to use paging transmissions to notify one or more UEs 3 of updates to the AI / ML model.

[0275] In step S701, the base station 5 obtains an updated AI / ML model. The updated AI / ML model may be generated at the base station 5, or the updated AI / ML model may be received from another node in the network (e.g., the AI / ML server 151 or a core network node / function). In step S702, the base station transmits a paging transmission including an indication that the AI / ML model has been updated. The paging transmission may be a group paging transmission (a paging transmission intended for reception by a specific group of UEs 3).

[0276] The paging transmission of step S702 may include an indication from where UE 3 should obtain the updated AI / ML model. For example, if the updated AI / ML model is stored in AI / ML server 151, the paging transmission may provide an indication that UE 3 should obtain the updated AI / ML model directly from AI / ML server 151 (or from any other suitable network node). The paging transmission may also include an indication of the UE 3 from which to obtain the updated AI / ML model (e.g., an indication of the identity of the UE 3 from which to obtain the updated AI / ML model).

[0277] The paging transmission may include an indication that the page is for notification of an updated AI / ML model. For example, the paging transmission may include a cause value indicating that the page is for notification of an updated AI / ML model. The paging transmission may include an indication of identification information (e.g., a model ID number) of the updated AI / ML model and / or a version number of the updated AI / ML model.

[0278] In step S703, the UE 3 determines to acquire an updated AI / ML model based on the information received in step S702. For example, the UE 3 may determine to acquire an updated AI / ML model based on the difference between the version number of the model stored in the UE 3 and the version number of the updated AI / ML model. Alternatively, the UE 3 may determine to acquire an updated AI / ML model based on an explicit indication in the paging transmission of step S702 indicating that the UE 3 should acquire an updated AI / ML model. Steps S704 and S705 are the same as steps S1403 and S1404 described above with reference to FIG. 14, and therefore will not be described again here.

[0279] In this example, the paging transmission is used to notify one or more UEs 3 that the AI / ML model has been updated, but alternatively (or additionally), the paging transmission can be used to request identification information of the AI / ML model stored in the UE 3, in which case the UE 3, after receiving the request, transmits an indication of the AI / ML model stored in the UE 3 to the base station 5. Alternatively, or additionally, the paging transmission can be used to request history information of the AI / ML model or other information regarding the status of the AI / ML model (e.g., the execution history of the model) from the UE 3, in which case the UE 3, after receiving the request, transmits the AI / ML model history information to the base station 5.

[0280] Area-Based AI / ML Models Next, methods related to area-based AI / ML models are described. An AI / ML model may be used in a specific area or location. The AI / ML model may be for use in a specific cell or group of cells that may be operated by one or more base stations 5. For example, the AI / ML model may be for use in a group of cells for beam management.

[0281] The area in which an AI / ML model is used may be defined as one or more cells, one or more RAN-based notification areas (RNAs), or a registration area (RA). However, it will be understood that any other area suitable for use of an AI / ML model may be defined. An area in which an AI / ML model is used for a particular function (e.g., beam management, CSI encoding / decoding, or mobility) may be referred to as an AI / ML model function area.

[0282] A cell provided by a base station 5 may be part of multiple AI / ML model functional areas. FIG. 18 shows an example in which a first base station 5-1 provides a first cell 180 and a second cell 181, and a second base station 5-2 provides a third cell 181. In this example, a first AI / ML model is used in the first cell 180 and the second cell 181 for a first function (e.g., beam management). Thus, the AI / ML model functional area of ​​the first AI / ML model includes the first cell 180 and the second cell 181. A second AI / ML model is used in the second cell 181 and the third cell 182 for a second function (e.g., CSI encoding / decoding). Thus, the AI / ML model functional area of ​​the second AI / ML model includes the second cell 181 and the third cell 182.

[0283] In this example, the second cell 181 belongs to both the AI / ML model functional area of ​​the first AI / ML model and the AI / ML model functional area of ​​the second AI / ML model. In this example, one AI / ML model is used for each function in each area. Alternatively, multiple AI / ML models may be available for one function in a specific area (e.g., multiple AI / ML models may be available for UE mobility inference in a specific cell).

[0284] In this example, base station 5-1 is configured to transmit a broadcast transmission in a first cell 180 indicating that first cell 180 belongs to an AI / ML model functional area of ​​a first AI / ML model, and to further transmit a broadcast transmission in a second cell 181 indicating that the second cell belongs to both the AI / ML model functional area of ​​the first AI / ML model and the AI / ML model functional area of ​​a second AI / ML model. The indication of which AI / ML model functional area a cell belongs to may be referred to as AI / ML model area information. UEs 3 in base station 5-1's cell can thus determine which AI / ML model to use for a particular function in that cell. Base station 5 may be configured to indicate, in the broadcast transmission, the model functional area to which the cell belongs, either for each AI / ML model or for each function. For example, base station 5 may support two AI / ML features / functions, with AI / ML model X being used for the first function and AI / ML model Y being used for the second function. From a network deployment perspective, AI / ML model X for a first function may belong to area N (e.g., which may be a relatively small area), and AI / ML model Y for a second function may belong to area M (e.g., which may be a relatively large area). The broadcast information may indicate that the cell supports AI / ML models X and Y, or that the cell supports the first function with AI / ML model X and the second function with AI / ML model Y, or that the cell belongs to corresponding areas N and M (for different models).

[0285] 19 shows how the AI / ML model area information is received by the UE 3. In step S1901, the base station 5 broadcasts the AI / ML model area information within the cell of the base station 5, and the information is received by the UE 3 within the cell.

[0286] In step S1902, the UE 3 determines to use a specific AI / ML model based on the AI / ML model area information. For example, if the UE 3 is located in the second cell 181 of FIG. 18 and receives AI / ML model area information indicating that a first AI / ML model is to be used for a first function in the second cell 181, the UE 3 determines to use the first AI / ML model for the first function in the second cell 181. If the UE 3 does not support the AI / ML model indicated in the AI / ML model area information, the UE 3 may simply ignore the AI / ML model area information. After the UE 3 determines to use a specific AI / ML model, the UE 3 may acquire the AI / ML model (if it is not already stored in the UE 3) according to any of the methods described above (e.g., any of the methods shown in FIGS. 14 to 17). For example, the UE 3 may use a random access procedure including MSG3 as part of the method for acquiring the AI / ML model, as described above. As described above, the UE 3 may obtain the AI / ML model directly from the base station 5 or from another node in the network (e.g., the AI / ML server 151 (via the AMF 10-1), an operations, administration, and maintenance server (OAM), or other suitable node / function in the network).

[0287] Alternatively, rather than the AI / ML model area information indicating which AI / ML models are supported for a particular function, the AI / ML model area information may include only information indicating that a particular function is supported in that area. In this case, after receiving the AI / ML model area information, the UE 3 may decide to acquire system information broadcast in the cell to determine the AI / ML model to use. For example, as described above, the UE 3 may request an on-demand SIB indicating the AI / ML models supported for a particular function in the cell. The UE 3 may decide to acquire an AI / ML model after moving to a new cell and receiving the transmission of step S1901 (e.g., after a cell reselection procedure) or when the AI / ML model used for a particular function in the cell has changed (the UE 3 may also identify this based on the transmission of step S1901). The UE 3 may be configured to periodically check the transmission of the AI / ML model area information by the base station 5 (e.g., by receiving and decoding the corresponding SI) based on a timer. Similarly, the base station 5 may be configured to periodically broadcast the AI / ML model area information in one or more cells based on a timer.

[0288] If the AI / ML models supported for use in a particular area of ​​functionality are updated, the UE 3 may obtain the updated models using any of the methods described above (e.g., the methods described with reference to FIG. 17).

[0289] The UE 3 may store multiple AI / ML models that can be used for a particular function, and the UE 3 may select one from the multiple AI / ML models based on the AI / ML model area information received in step S1901. For example, the UE 3 may store a first AI / ML model for beam management in a first area and a second AI / ML model for beam management in a second area, and may determine to use the first AI / ML model based on an indication in the AI / ML model area information that the cell belongs to the first area. If the cell belongs to both the first area and the second area, the UE 3 may notify the network (e.g., the base station 5) whether to use the first AI / ML model or the second AI / ML model (e.g., which model is preferred by the UE 3). Thus, advantageously, when multiple models are supported for the same function in a particular area, a mismatch between the model used by the base station 5 and the model used by the UE 3 can be avoided. The UE 3 may indicate which AI / ML model to use (or which AI / ML model is preferred to use) using the first RRC message that the UE 3 sends to the base station 5. The UE 3 may include an indication in the MSG 3 as described above with reference to Figure 6.

[0290] In the example of FIG. 18 , the UE 3 may move from the second cell 181 to the third cell 182. While in the second cell 181, the UE 3 uses a first AI / ML model for the first function. However, in this example, the third cell 182 does not support the first function. Therefore, the UE 3 may determine not to use (or disable) the first AI / ML model for the first function after moving to the second cell 5-2. For example, the UE 3 may determine not to use (or disable) the first AI / ML model in response to receiving a broadcast transmission from the second base station 5-2 indicating the AI / ML models supported in the third cell 182 (or the AI / ML model functional area to which the third cell 182 belongs). Furthermore, the UE 3 may determine not to use (or disable) the first AI / ML model in the third cell 182 even if it does not receive a broadcast transmission from the second base station 5-2. For example, the UE 3 may decide not to use (or disable) the first AI / ML model in the third cell 182 as a default option, and may decide to use the first AI / ML model in the third cell 182 only if the UE 3 receives an indication that the first AI / ML model is available for use in the third cell 182. Thus, advantageously, even if the base station 5-2 is a legacy base station that does not support transmission of AI / ML-related information such as the transmission of step S1901 of FIG. 19 , the use of an unsupported AI / ML model or AI / ML model function can be avoided.

[0291] Model Updates and RRC State Transitions When UE 3 transitions from an RRC idle state or an RRC inactive state to an RRC connected state, UE 3 may use Layer 1 (L1), Layer 2 (L2), or Layer 3 (L3) signaling to indicate to the network the AI / ML models stored in UE 3 (e.g., by sending associated AI / ML model IDs). UE 3 may also use L1 / L2 / L3 signaling to inform the network of the versions of the AI / ML models stored in UE 3. L1 / L2 / L3 signaling may also be used to inform the network of historical information related to the AI / ML models (e.g., the execution history of the models).

[0292] Based on the L1 / L2 / L3 signaling, the network (e.g., base station 5) may determine a specific AI / ML model to be used for a specific function. For example, based on the L1 / L2 / L3 signaling, base station 5 may determine that UE 3 stores an AI / ML model that is also supported by base station 5 and may decide to use the AI / ML model for a specific function (e.g., beam management or CSI encoding / decoding). The base station 5 may decide to send an AI / ML model to UE 3 if the AI / ML model is not already stored in UE 3, or may decide to send a different version of the AI / ML model stored in UE 3 to UE 3. The base station 5 may send the AI / ML model to UE 3 after UE 3 transitions to an RRC connected state (e.g., immediately after UE 3 transitions to an RRC connected state).

[0293] To avoid mismatches between the AI / ML model used by the UE 3 and the AI / ML model used by the base station 5 (in the case of a two-sided AI / ML model), the base station 5 may be configured not to use the AI / ML model until the AI / ML model is transmitted to the UE 3 or until the base station 5 receives an acknowledgment from the UE 3 indicating that the AI / ML model has been acquired. For example, the base station 5 may use an algorithm other than AI / ML for compressing / decompressing CSI. The base station 5 may use a DCI or a medium access control (MAC) control element (CE) to control activation of the use of the AI / ML model in the UE 3 (e.g., for a particular function).

[0294] The base station 5 may also receive information in the L1 / L2 / L3 signaling indicating the performance of the AI / ML model being used by the UE 3. The model performance information may be the model performance feedback of Figure 8, or may for example be information for use in the performance monitoring step of Figure 9.

[0295] When the UE 3 transitions from the RRC connected state to the RRC idle state or the RRC inactive state, the UE 3 may be configured to continue to store one or more AI / ML models stored in the UE 3. The UE 3 may be configured to continue to store the AI / ML models for a predefined period, for example, based on a timer. However, if the UE 3 receives more AI / ML models and there is not enough memory to store both models, the UE 3 may be configured to delete or overwrite the AI / ML models stored in the memory of the UE 3. It will be understood that if the UE 3 is configured to continue to store one or more AI / ML models after transitioning from the RRC connected state to the RRC idle state or the RRC inactive state, the AI / ML models are not part of the UE context for the RRC connected state, because the UE context for the RRC connected state is deleted after the UE transitions from the RRC connected state to the RRC idle state or the RRC inactive state.

[0296] RRC Procedures RRC procedures may be used for AI / ML-related inquiries sent between the network and the UE 3 when the UE 3 is in an RRC connected state. For example, the network may request (e.g., via the base station 5) information indicating the identity of one or more AI / ML models stored in the UE 3 using an RRC message (e.g., a dedicated RRC message or other non-legacy RRC message). The network may request the identity of one or more AI / ML models stored in the UE 3 related to a particular function or feature. The UE 3 may send a corresponding RRC message containing the requested information to the base station 5. For example, the UE 3 may send an RRC message to the base station 5 containing an indication of the AI / ML model IDs of the AI / ML models stored in the UE 3.

[0297] Similarly, the UE 3 may request AI / ML-related information from the network (e.g., the base station 5) using an RRC message (e.g., a dedicated RRC message or other non-legacy RRC message). For example, the UE 3 may request identification information of AI / ML models supported by the base station 5 for a particular function, or may request version numbers of AI / ML models available at the base station 5 (e.g., the UE 3 may request the current version number of an AI / ML model to obtain the latest version of the model).

[0298] User Equipment FIG. 20 is a schematic block diagram showing the main components of the UE 3 shown in FIG.

[0299] As shown, the UE 3 includes transceiver circuitry 310 operable to transmit signals to and receive signals from a base station 5 via one or more antennas 330 (e.g., comprised of one or more antenna elements). The UE 3 includes a controller 370 that controls the operation of the UE 3. The controller 370 is associated with a memory 390 and is connected to the transceiver circuitry 310. Although not necessary for its operation, the UE 3 will of course include all of the conventional functionality of an existing UE 3 (e.g., including a user interface 350, such as a touchscreen / keypad / microphone / speaker, allowing direct user control and interaction), which may be provided by any one or any combination of hardware, software, and firmware, as appropriate. Software may be pre-installed in the memory 390 and / or downloaded, for example, via a telecommunications network or from a removable data storage device (RMD).

[0300] Controller 370, in this example, is configured to control the overall operation of UE 3 via program or software instructions stored in memory 390. As shown, these software instructions include, among other things, an operating system 410, a communications control module 430, and an AI / ML module 450.

[0301] The communications control module 430 is operable to control communications between the UE 3 and its one or more serving base stations 5 (as well as other communications devices connected to the base stations 5, such as further UEs and / or core network nodes). The communications control module 430 is configured for overall processing of uplink communications over associated uplink channels (e.g., over the Physical Uplink Control Channel (PUCCH), Random Access Channel (RACH), and / or Physical Uplink Shared Channel (PUSCH)), including both dynamic and semi-static signaling (e.g., SRS). The communications control module 430 is also configured for overall processing of reception of downlink communications over associated downlink channels (e.g., over the Physical Downlink Control Channel (PDCCH) and / or Physical Downlink Shared Channel (PDSCH)), including both dynamic and semi-static signaling (e.g., CSI-RS). The communication control module 430 is responsible for, for example, determining where to monitor downlink control information (e.g., the location of the CSS / USS, CORESET, and associated PDCCH candidates to monitor); determining the resources (including interleaved resources and resources subject to frequency hopping) to be used by the UE 3 for transmitting / receiving UL / DL communications; managing frequency hopping at the UE side; determining how slots / symbols are configured (e.g., for UL, DL, or SBFD communications, or the like); determining which one or more bandwidth parts are configured for the UE; determining how uplink transmissions should be encoded; appropriately applying SBFD-specific communication configurations, etc. The communication control module 430 may be configured to control communications according to any of the methods described above (e.g., to send measurement reports according to any of the methods described above).

[0302] AI / ML module 450 is operable to control the use of AI / ML models (e.g., to generate one or more inferences using the models) in UE 3. AI / ML module 450 may be configured to perform any of the AI / ML-related functions of UE 3 in any of the ways described above.

[0303] base station FIG. 21 is a schematic block diagram illustrating the main components of a base station 5 of the communication system 1 shown in FIG. 1. As shown, the base station 5 includes a transceiver circuit 510 for transmitting and receiving signals to and from a communication device (e.g., UE 3) via one or more antennas 530 (e.g., a single or multiple panel antenna array / massive antenna), and a core network interface 550 (e.g., including N2, N3, or other reference points / interfaces) for transmitting and receiving signals to and from network nodes in the core network 7. Although not shown, the base station 5 may also be connected to other base stations via appropriate interfaces (e.g., so-called "Xn" interfaces in NR). The base station 5 includes a controller 570 that controls the operation of the base station 5. The controller 570 is associated with a memory 590. Software may be pre-installed in the memory 590 and / or downloaded, for example, via the communication system 1 or from a removable data storage device (RMD). The controller 570 is configured to control the overall operation of the base station 5 via program instructions or software instructions stored in the memory 590, in this example.

[0304] As shown, these software instructions include, among other things, an operating system 610 and a communications control module 630 .

[0305] The communications control module 630 is operable to control communications between the base station 5 and the UEs 3 and other network entities connected to the base station 5. The communications control module 630 is configured to provide overall control of the reception and decoding of uplink communications over associated uplink channels (e.g., over the Physical Uplink Control Channel (PUCCH), Random Access Channel (RACH), and / or Physical Uplink Shared Channel (PUSCH)), including both dynamic and semi-static signaling (e.g., SRS). The communications control module 630 is also configured to provide overall handling of the transmission of downlink communications over associated downlink channels (e.g., over the Physical Downlink Control Channel (PDCCH) and / or Physical Downlink Shared Channel (PDSCH)), including dynamic and semi-static signaling (e.g., CSI-RS). The communications control module 630 is responsible for managing full-duplex (e.g., SBFD) communications, including separating UL and DL communications over different physical antenna elements, as necessary. The communications control module 630 is responsible for, for example, determining where the UE 3 should monitor downlink control information (e.g., the locations of the CSS / USS, CORESET, and associated PDCCH candidates to monitor); determining resources (including interleaved resources and resources subject to frequency hopping) to schedule for the UE transmission / reception of UL / DL communications; managing frequency hopping at the base station side; configuring slots / symbols appropriately (e.g., for UL, DL, or SBFD communications); configuring one or more bandwidth portions for the UE 3; providing associated configuration signaling to the UE 3, etc. The communications control module 43 may be configured to control communications (e.g., receive or send UE 3 mobility information or handover requests) according to any of the methods described above.

[0306] The AI / ML module 630 may be configured to perform any of the AI / ML-related functions of the UE 3 in any of the ways described above. The base station 5 may be configured to train or re-train the AI / ML models as described above (e.g., in response to UE mobility information fed back to the base station 5 from another node in the network, such as another base station 5).

[0307] Core Network Nodes / Functions 22 is a block diagram illustrating the main components of a core network node or function, such as the AMF, CPF, UPF, SMF, or OAM. As shown, the core network function includes a transceiver circuit 710 operable to transmit signals to and receive signals from other nodes (including UE 3, base stations 5, and other core network nodes) via a network interface 720. A controller 730 controls the operation of the core network function in accordance with software stored in memory 740. The software may be pre-installed in memory 740 and / or may be downloaded, for example, via the communication system 1 or from a removable data storage device (RMD). The software includes, among other things, an operating system 750 and a communication control module 760.

[0308] The communication control module 760 is responsible for handling (generating / sending / receiving) signaling between the core network functions and other nodes such as the UE 3, the base station 5, and other core network nodes. The signaling may include, for example, UE context / UE capability indications of the UE 3 related to energy saving.

[0309] As shown in Figure 21, the core network node / function may also include an AI / ML module 770. If present, the AI / ML module 770 is operable to perform any of the AI / ML-related functions of the core network node / function according to any of the methods described above. The core network node / function may be configured to train or retrain the AI / ML model as described above (e.g., in response to UE mobility information being fed back to the core network node / function from another node in the network, such as base station 5).

[0310] Modifications and Alternatives As can be understood by those skilled in the art, many modifications and alternatives can be made to the above embodiments while benefiting from the technical solutions or contributions embodied therein.

[0311] While the above examples have been described with reference to AI / ML models, it will be understood that the above-described methods are advantageous even when the model is not an AI / ML model. Any other suitable type of model or function may be used to generate inferences (e.g., decisions or predictions). For example, the methods shown in FIGS. 12 and 13 are useful even when the model is not an AI / ML model to ensure that mobility information is fed back to a node / function that generates mobility prediction information using a predictive model (e.g., to verify the accuracy of the model even when training or retraining the model is not possible). However, the methods are particularly advantageous when the model is an AI / ML model because the information fed back to the primary network node / function can be used to iteratively update / train the model or trigger retraining.

[0312] For example, while terminology specific to a cellular communication generation (2G, 3G, 4G, 5G, 6G, etc.) may be used to refer to a particular communication entity for clarity, it will be understood that technical features described for any entity are not limited to devices of that particular communication generation. Technical features may be implemented in functionally equivalent communication entities regardless of the terminology used to refer to them.

[0313] In the above description, the UE and base station are described for ease of understanding as having a number of separate functional components or modules. While these modules may be provided in this manner in certain use cases, such as when an existing system is modified to implement one or more of the technical solutions and contributions described above, in other use cases, such as systems designed from the beginning with innovative features in mind, these modules may be incorporated into an overall operating system or code and therefore may not be identifiable as separate entities.

[0314] In the above embodiments, a number of software modules have been described. As will be understood by those skilled in the art, these software modules may be provided in compiled or uncompiled form, or may be provided as signals over a computer network or on a recording medium. Furthermore, the functions performed by some or all of these software modules may be implemented using one or more dedicated hardware circuits. However, the use of software modules is preferred because it facilitates updates to update the functionality of the base station or UE.

[0315] Each controller may comprise any suitable form of processing circuitry, including, but not limited to, one or more hardware-implemented computer processors, microprocessors, central processing units (CPUs), arithmetic logic units (ALUs), input / output (IO) circuitry, internal memory / cache (program and / or data), processing registers, communication buses (e.g., control buses, data buses and / or address buses), direct memory access (DMA) facilities, hardware or software-implemented counters, pointers and / or timers, and / or other various modifications will be apparent to those skilled in the art and will not be described in further detail herein.

[0316] A base station may include a "distributed" base station having a central unit (CU) and one or more individual distributed units (DUs).

[0317] User Equipment ("UE," "mobile station," "mobile device," or "wireless device") in this disclosure is an entity connected to a network via a wireless interface.

[0318] It should be noted that the present disclosure is not limited to dedicated communication devices, but is applicable to any device with communication capabilities, as described in the following paragraphs.

[0319] The terms "User Equipment" or "UE" (as this term is used by 3GPP), "mobile station," "mobile device," and "wireless device" are generally intended to be synonymous with each other and include standalone mobile stations such as terminals, cell phones, smartphones, tablets, cellular IoT devices, IoT devices, and machines. It will be understood that the terms "mobile station" and "mobile device" also encompass devices that remain stationary for extended periods of time.

[0320] The UE may be, for example, equipment or machinery for production or manufacturing and / or energy-related machinery (e.g., equipment or machinery such as boilers; engines; turbines; solar panels; wind turbines; hydroelectric generators; thermal generators; nuclear generators; batteries; nuclear systems and / or related equipment; heavy electrical equipment; pumps including vacuum pumps; compressors; fans; blowers; hydraulic equipment; pneumatic equipment; metalworking machinery; manipulators; robots and / or application systems thereof; tools; molds or dies; rolls; material handling equipment; textile machinery; sewing machines; printing and / or related machinery; paper converting machinery; chemical machinery; mining and / or construction machinery and / or related facilities; machinery and / or implements for agriculture, forestry and / or fisheries; safety and / or environmental protection equipment; tractors; precision bearings; chains; gears; power transmission equipment; lubrication equipment; valves; pipe fittings; and / or application systems for any of the foregoing equipment or machinery, etc.).

[0321] The UE may be, for example, a transportation equipment item (e.g., transportation equipment such as railcars; automobiles; motorcycles; bicycles; trains; buses; carts; rickshaws; ships and other watercraft; aircraft; rockets; satellites; drones; balloons, etc.). The UE may be, for example, an information and communications equipment item (e.g., information and communications equipment such as electronic computers and related equipment; communications and related equipment; electronic components, etc.).

[0322] The UE may be, for example, a refrigerator, a refrigerator application product, a goods and / or service industry equipment item, a vending machine, an automated service machine, an office machine, a consumer electronic device and an appliance (e.g., consumer appliances such as audio equipment; video equipment; speakers; radios; televisions; microwave ovens; rice cookers; coffee machines; dishwashers; washing machines; dryers; electronic fans or related appliances; vacuum cleaners, etc.).

[0323] The UE may be, for example, an electrical application system or device (eg, an electrical power application system or device such as an x-ray system; a particle accelerator; a radioisotope device; a sonic device; an electromagnetic application device; an electrical power application device, etc.).

[0324] The UE may be, for example, an electronic lamp, a lighting fixture, a measuring instrument, an analyzer, a tester, or a surveying or sensing device (e.g., a surveying or sensing device such as a smoke detector; a motion alarm sensor; a radio frequency tag; etc.), a wristwatch or watch, an inspection device, an optical device, a medical device and / or system, a weapon, a cutlery item, a hand tool, etc.

[0325] A UE may be, for example, a wireless-equipped personal digital assistant or related equipment, such as a wireless card or module designed to be attached to or inserted into another electronic device (e.g., a personal computer, an electrical measuring instrument), etc.

[0326] The UE may be part of a device or system that uses various wired and / or wireless communication technologies to provide the applications, services, and solutions described below with respect to the "Internet of Things" (IoT).

[0327] Internet of Things devices (or "Things") may be equipped with appropriate electronics, software, sensors, network connections, etc. that enable these devices to collect and exchange data with each other and other communicating devices. IoT devices may comprise automated machinery that follows software instructions stored in internal memory. IoT devices may operate without the need for human supervision or interaction. IoT devices may also remain stationary and / or inactive for extended periods of time. IoT devices may be implemented as part of (generally) stationary equipment. IoT devices may also be incorporated into non-stationary equipment (e.g., vehicles) or attached to animals or people to be monitored / tracked.

[0328] It will be appreciated that IoT technology can be implemented on any communication device that can connect to a communication network to send / receive data, whether such communication device is controlled by human input or software instructions stored in memory.

[0329] IoT devices are sometimes referred to as Machine-Type Communication (MTC) devices or Machine-to-Machine (M2M) communication devices. A UE may support one or more IoT or MTC applications. Some examples of MTC applications are listed in the table below. This list is not exhaustive and is intended to illustrate some examples of machine-type communication applications. [Table 2]

[0330] The applications, services, and solutions may be Mobile Virtual Network Operator (MVNO) services, emergency wireless communication systems, Private Branch eXchange (PBX) systems, PHS / digital cordless telecommunications systems, Point of sale (POS) systems, advertising call systems, Multimedia Broadcast and Multicast Service (MBMS), Vehicle to Everything (V2X) systems, train radio systems, location-related services, disaster / emergency wireless communication services, community services, video streaming services, femtocell application services, Voice over LTE (VoLTE) services, billing services, wireless on-demand services, roaming services, activity monitoring services, telecommunications carrier / communication network selection services, function restriction services, Proof of Concept (PoC) services, personal information management services, ad hoc networks / Delay Tolerant Networking (DTN) services, and the like.

[0331] Furthermore, the above-mentioned UE categories are merely examples of application of the concepts and exemplary embodiments described herein, and it should be understood that these concepts and embodiments are not limited to the above-mentioned UEs and may be modified in various ways.

[0332] Various other modifications will be apparent to those skilled in the art and will not be described in further detail here.

[0333] While the present disclosure has been particularly shown and described with reference to several embodiments thereof, the disclosure is not limited to these embodiments. Those skilled in the art will understand that various changes in form and details may be made therein without departing from the spirit and scope of the present disclosure as defined by the claims. Each embodiment may be suitably combined with at least one of the other embodiments.

[0334] Some or all of the above embodiments may also be described as, but are not limited to, the following appendices. Some or all of the elements (e.g., configurations and functions) described in appendices directed to a method (e.g., a user equipment method) may naturally also be described as appendices directed to a device (e.g., a user equipment) or a program. For example, some or all of the elements described in appendices 2 to 20 dependent on appendice 1 may also be described as appendices dependent on appendice 65 due to the same dependency relationship as appendices 2 to 20. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0335] (Appendix 1) 1. A method for a user equipment (UE), comprising: receiving a broadcast or multicast transmission from an access network node, wherein the broadcast or multicast transmission includes an indication of an identification of one or more models for generating the determination, prediction, or output parameters; determining, based on the indication, to acquire one model of the one or more models; transmitting a request for said model; and receiving the model; A method comprising: (Appendix 2) 2. The method of claim 1, wherein the model is an artificial intelligence or machine learning (AI / ML) model. (Appendix 3) transmitting the request for the model includes transmitting the request to the access network node; receiving the model includes receiving the model from the access network node. 3. The method according to claim 1 or 2. (Appendix 4) 4. The method of claim 3, wherein receiving the model from the access network node comprises receiving the model in a radio resource control (RRC) message when the UE is in an RRC connected state. (Appendix 5) sending the request for the model comprises sending the request to the access network node, the core network node, or a server that stores the model; receiving the model includes receiving the model from the server; 3. The method according to claim 1 or 2. (Appendix 6) 6. The method of claim 5, wherein receiving the model from the server comprises receiving the model from the server via the access network node, via the core network node, or directly from the server. (Appendix 7) When the UE receives the broadcast or multicast transmission, the UE is in an RRC inactive state or an RRC idle state; the UE sending the request as part of a random access procedure; 10. The method of any preceding claim. (Appendix 8) The random access procedure comprises: transmitting a random access preamble to said access network node; receiving, from the access network node, a random access response including an indication of communications resources to be used by the UE to transmit an uplink transmission; and sending the uplink transmission to the access network node; Equipped with the uplink transmission includes the request for the model. The method described in Appendix 7. (Appendix 9) 9. The method of claim 8, wherein the uplink transmission includes a cause value indicating that the uplink transmission includes the request of the model. (Appendix 10) transmitting the request for the model includes transmitting the request for the model in an RRC message; 10. The method of any preceding claim, wherein the RRC message is a dedicated RRC message for requesting the model. (Appendix 11) receiving an indication from the access network node indicating time and / or frequency resources used by the UE to receive the model when the UE is in an RRC inactive state or an RRC idle state; and receiving the model from the access network node using the indicated time and / or frequency resources when the UE is in the RRC inactive state or the RRC idle state; 10. The method of any preceding clause, further comprising: (Appendix 12) 10. The method of any preceding clause, wherein the broadcast or multicast transmission includes an indication of at least one use case of the one or more models. (Appendix 13) The method of any preceding clause, wherein the broadcast or multicast transmission includes at least one of a model identification number or an indication of a model version of the one or more models. (Appendix 14) the broadcast or multicast transmission includes the indication of the model version; the decision to acquire the model is based on a comparison of the displayed model version with a model version of a model stored in the UE; The method described in Appendix 13. (Appendix 15) 10. The method of any preceding claim, wherein receiving the model includes receiving the model from a core network node using non-access stratum (NAS) signaling. (Appendix 16) 10. The method of any preceding clause, wherein the indication of the identity of the one or more models is included in system information transmitted in the broadcast or multicast transmission. (Appendix 17) the system information is on-demand system information, and the method comprises: receiving an indication from the access network node that the on-demand system information is available for transmission by the access network node; sending a request for the on-demand system information to the access network node; and receiving the on-demand system information in the broadcast or multicast transmission; Further provided with The method described in Appendix 16. (Appendix 18) 10. The method of any preceding clause, wherein the broadcast or multicast transmission is a group paging transmission. (Appendix 19) 19. The method of claim 18, wherein the group paging transmission includes an indication that the version of the one or more models has been updated. (Appendix 20) 20. The method of claim 19, wherein the group paging transmission includes a cause value indicating that the model of the one or more models has been updated to a newer version. (Appendix 21) 1. A method of an access network node, comprising: sending a broadcast or multicast transmission to user equipment (UE), wherein the broadcast or multicast transmission includes an indication of an identification of one or more models for generating the decision, prediction, or output parameters; and receiving a request for one of the one or more models from the UE; A method comprising: (Appendix 22) 22. The method of claim 21, further comprising sending the requested model to the UE. (Appendix 23) a data radio bearer or logical channel for transmission of the requested model having an associated transmission priority or bit rate; transmitting the requested model includes transmitting the model using the data radio bearer or logical channel based on the transmission priority or bit rate. 23. The method described in Appendix 22. (Appendix 24) 24. The method of claim 22 or 23, comprising receiving the requested model from a central unit of a base station, a server, or a core network node before sending the requested model to the UE. (Appendix 25) 22. The method of claim 21, further comprising sending to the UE an indication of a network node from which the UE obtains the requested model, or an instruction network address to be used by the UE to obtain the requested model. (Appendix 26) transmitting the broadcast or multicast transmission when the UE is in an RRC inactive state or an RRC idle state; receiving the request includes receiving the request as part of a random access procedure. The method according to any one of appendices 21 to 25. (Appendix 27) The random access procedure comprises: receiving a random access preamble from the UE; transmitting a random access response to the UE that includes an indication of communication resources to be used by the UE to transmit an uplink transmission; and receiving the uplink transmission from the UE; Equipped with the uplink transmission includes the request for the model. 26. The method described in Appendix 26. (Appendix 28) transmitting an indication to the UE indicating time and / or frequency resources used by the UE to receive the model when the UE is in an RRC inactive state or an RRC idle state; and transmitting the model to the UE using the indicated time and / or frequency resources when the UE is in the RRC inactive state or the RRC idle state; The method according to any one of appendices 21 to 27, further comprising: (Appendix 29) 29. The method of any one of Supplementary Notes 21 to 28, comprising receiving, before transmitting the broadcast or multicast transmission including the indication of the identification of one or more models, information indicating the identification of the one or more models from a central unit of a base station. (Appendix 30) 30. The method of any one of Supplementary Notes 21 to 29, wherein transmitting the broadcast or multicast transmission comprises transmitting the broadcast or multicast transmission periodically or based on a timer. (Appendix 31) 31. The method of any one of appendices 21 to 30, wherein the broadcast or multicast transmission includes an indication of at least one use case of the one or more models. (Appendix 32) 32. The method of any one of appendices 21 to 31, wherein the broadcast or multicast transmission includes at least one of a model identification number or a model version indication of the one or more models. (Appendix 33) 33. The method of any one of appendices 21 to 32, wherein the indication of the identity of the one or more models is included in system information transmitted in the broadcast or multicast transmission. (Appendix 34) the system information is on-demand system information, and the method comprises: transmitting an indication to the UE that the on-demand system information is available for transmission by the access network node; receiving a request for the on-demand system information from the UE; and transmitting the on-demand system information in the broadcast or multicast transmission; Further provided with 34. The method described in Appendix 33. (Appendix 35) 35. The method according to any one of Supplementary Notes 21 to 34, wherein the broadcast or multicast transmission is a group paging transmission. (Appendix 36) 36. The method of claim 35, wherein the group paging transmission includes an indication that the version of the one or more models has been updated. (Appendix 37) 37. The method of claim 36, wherein the group paging transmission includes a cause value indicating that the model of the one or more models has been updated to a newer version. (Appendix 38) 1. A method for a user equipment (UE), comprising: receiving an indication from an access network node that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions, or outputs; determining, based on the received indication, to request one model of the one or more models; sending a request for said model; and receiving the model; A method comprising: (Appendix 39) 39. The method of claim 38, wherein one of the one or more areas comprises a group of cells, a radio access network-based notification area, or a registration area. (Appendix 40) 40. The method of claim 38 or 39, wherein the indication that the cell is part of the one or more areas is received in system information broadcast in the cell. (Appendix 41) 41. The method of any one of claims 38 to 40, further comprising receiving an indication of the identity of the one or more models from the access network node. (Appendix 42) 42. The method of any one of claims 38 to 41, further comprising receiving from the access network node an indication of one or more use cases of the one or more models. (Appendix 43) 1. A method for a user equipment (UE), comprising: receiving an indication from an access network node that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating determination, prediction, or output parameters; determining, based on the received representation, to obtain a representation of identity of at least one of the models; and obtaining the representation of the identification information of at least one of the models; A method comprising: (Appendix 44) 44. The method of claim 43, wherein obtaining the indication of the identification of at least one of the models comprises receiving system information broadcast in the cell by the access network node. (Appendix 45) 45. The method of claim 44, further comprising determining to receive the system information periodically or based on a timer. (Appendix 46) determining to acquire one model of the one or more models based on the indication of the identity of at least one of the models; sending a request for said model; and receiving the model; 46. ​​The method according to any one of appendices 43 to 45, further comprising: (Appendix 47) After obtaining said representation of said identification information of at least one of said models, selecting a model stored in the UE from the one or more models for use in the cell; and using said model to generate decisions, predictions, or output parameters; 47. The method according to any one of appendices 43 to 46, further comprising: (Appendix 48) 48. The method of claim 47, further comprising sending an indication of the selected model to the access network node. (Appendix 49) 49. The method of claim 48, wherein transmitting the indication of the selected model includes transmitting the indication of the selected model using a radio resource control (RRC) message. (Appendix 50) 1. A method of an access network node, comprising: transmitting an indication that the cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating a decision, prediction, or output; and receiving a request for one of the one or more models from a UE that has received the indication; A method comprising: (Appendix 51) 1. A method of an access network node, comprising: transmitting an indication that the cell served by the access network node is part of one or more areas each associated with a respective set of one or more models for generating a decision, prediction, or output; receiving a request for identification information of one of the one or more models from a UE that received the indication; and transmitting an indication of said identification information of one or more models; A method comprising: (Appendix 52) 52. The method of claim 51, wherein transmitting the indication of the identity of one or more models used in the cell comprises transmitting the indication of the identity of one or more models used in the cell in system information broadcast in the cell. (Appendix 53) 53. The method of claim 52, further comprising transmitting the system information periodically or based on a timer. (Appendix 54) 1. A method for a user equipment (UE), comprising: Transitioning from a Radio Resource Control (RRC) idle state or an RRC inactive state to an RRC connected state; and In the access network node, Identification of one or more models stored in the UE; the status of the one or more models stored in the UE; or the version number of the one or more models stored in the UE; transmitting an indication indicating at least one of: Equipped with the one or more models are for generating decisions, predictions, or output parameters; method. (Appendix 55) 55. The method of claim 54, wherein the indication is sent to the access network node using Layer 1 (L1) signaling, Layer 2 (L2) signaling, or Layer 3 (L3) signaling. (Appendix 56) 56. The method of claim 54 or 55, wherein sending the indication of the identity of the one or more models comprises sending the indication of the identity of the one or more models in an RRC message after the UE enters an RRC connected state. (Appendix 57) 1. A method of an access network node, comprising: From the user equipment (UE), Identification of one or more models stored in the UE; the status of the one or more models stored in the UE; or the version number of the one or more models stored in the UE; receiving an indication indicating at least one of: determining, based on the received indication, which of the one or more models to use in the access network node; Equipped with the one or more models are for generating decisions, predictions, or output parameters; method. (Appendix 58) 58. The method of claim 57, further comprising sending an indication of the determined model to the UE. (Appendix 59) 1. A method for a user equipment (UE), comprising: storing the model for generating decisions, predictions, or output parameters; Transitioning from a Radio Resource Control (RRC) Connected state to an RRC Idle state or an RRC Inactive state; and continuing to store the model after a transition from the RRC connected state to the RRC idle state or the RRC inactive state; A method comprising: (Appendix 60) 59. The method of claim 59, comprising storing the model for a predetermined duration after the UE enters the RRC idle state or the RRC inactive state. (Appendix 61) 1. A method of an access network node, comprising: sending, to a user equipment (UE), in a first radio resource control (RRC) message, a request for an indication of an identity of a model stored in the UE, where the model is for generating decision, prediction, or output parameters; and receiving, in a second RRC message from the UE, the indication of the identity of the model stored in the UE; A method comprising: (Appendix 62) 1. A method for a user equipment (UE), comprising: receiving, in a first radio resource control (RRC) message from an access network node, a request for an indication of an identity of a model stored in the UE, where the model is for generating decision, prediction, or output parameters; and sending, in a second RRC message to the access network node, the indication of the identity of the model stored in the UE; A method comprising: (Appendix 63) 1. A method for a user equipment (UE), comprising: sending, to an access network node, in a first radio resource control (RRC) message, a request for an indication of a supported model for a use case, wherein the model is for generating decisions, predictions, or output parameters for the use case; and receiving, from the access network node, in a second RRC message, an indication of the identity of the model; A method comprising: (Appendix 64) 1. A method of an access network node, comprising: receiving, in a first radio resource control (RRC) message from a user equipment (UE), a request for an indication of a supported model for a use case, where the model is for generating decisions, predictions, or output parameters for the use case; and sending, to the UE, in a second RRC message, an indication of the identity of the model; A method comprising: (Appendix 65) A user equipment (UE), means for receiving a broadcast or multicast transmission from an access network node, wherein said broadcast or multicast transmission includes an indication of an identification of one or more models for generating decision, prediction, or output parameters; means for determining to acquire one of the one or more models based on the indication; means for transmitting a request for said model; Equipped with the receiving means is configured to receive the model; UE. (Appendix 66) an access network node, means for transmitting a broadcast or multicast transmission to user equipment (UE), wherein the broadcast or multicast transmission includes an indication of an identification of one or more models for generating decision, prediction, or output parameters; means for receiving a request for one of the one or more models from the UE; An access network node comprising: (Appendix 67) A user equipment (UE), means for receiving an indication from an access network node that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions or outputs; means for determining, based on the received indication, to request one model of the one or more models; means for transmitting a request for said model; Equipped with the receiving means is configured to receive the model; UE. (Appendix 68) A user equipment (UE), means for receiving an indication from an access network node that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating determination, prediction or output parameters; means for determining, based on the received representation, to obtain a representation of the identity of at least one of the models; means for obtaining said representation of said identification information of at least one of said models; UE equipped with. (Appendix 69) an access network node, means for transmitting an indication that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions or outputs; means for receiving a request for one of the one or more models from a UE that has received the indication; An access network node comprising: (Appendix 70) an access network node, means for transmitting an indication that a cell served by said access network node is part of one or more areas each associated with a respective set of one or more models for generating decisions, predictions or outputs; means for receiving, from a UE that has received the indication, a request for identification information of one of the one or more models; Equipped with the transmitting means is configured to transmit an indication of the identification of one or more models. Access network node. (Appendix 71) A user equipment (UE), means for transitioning from a Radio Resource Control (RRC) idle state or an RRC inactive state to an RRC connected state; In the access network node, Identification of one or more models stored in the UE; the status of the one or more models stored in the UE; or the version number of the one or more models stored in the UE; means for transmitting an indication of at least one of Equipped with the one or more models are for generating decisions, predictions, or output parameters; UE. (Appendix 72) an access network node, From the user equipment (UE), Identification of one or more models stored in the UE; the status of the one or more models stored in the UE; or the version number of the one or more models stored in the UE; means for receiving an indication of at least one of: means for determining, based on the received indication, which of the one or more models to use in the access network node; Equipped with the one or more models are for generating decisions, predictions, or output parameters; Access network node. (Appendix 73) A user equipment (UE), means for storing a model for generating decisions, predictions, or output parameters; a means for transitioning from a Radio Resource Control (RRC) Connected state to an RRC Idle state or an RRC Inactive state; Equipped with The UE is configured to continue to store the model after a transition from the RRC connected state to the RRC idle state or the RRC inactive state. UE. (Appendix 74) an access network node, means for transmitting, to a user equipment (UE), in a first radio resource control (RRC) message, a request for an indication of an identity of a model stored in the UE, wherein the model is for generating decision, prediction, or output parameters; means for receiving, in a second RRC message from the UE, the indication of the identity of the model stored in the UE; An access network node comprising: (Appendix 75) A user equipment (UE), means for receiving, from an access network node, in a first radio resource control (RRC) message, a request for an indication of an identity of a model stored in the UE, wherein the model is for generating decision, prediction, or output parameters; means for transmitting, in a second RRC message to the access network node, the indication of the identity of the model stored in the UE; UE equipped with. (Appendix 76) A user equipment (UE), means for transmitting, to an access network node, in a first Radio Resource Control (RRC) message, a request for an indication of a supported model for a use case, wherein the model is for generating decisions, predictions, or output parameters for the use case; means for receiving, from the access network node, in a second RRC message, an indication of the identity of the model; UE equipped with. (Appendix 77) an access network node, means for receiving, from a user equipment (UE), in a first radio resource control (RRC) message, a request for an indication of a supported model for a use case, wherein the model is for generating decisions, predictions, or output parameters for the use case; means for sending, to the UE, in a second RRC message, an indication of the identity of the model; An access network node comprising:

[0336] (Appendix A1) 1. A method for a user equipment (UE), comprising: receiving, from the access network node, at least one identification of a respective artificial intelligence or machine learning (AI / ML) model; sending a request for a first AI / ML model to the access network node, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and receiving the first AI / ML model from the access network node; A method comprising: (Appendix A2) determining whether the UE needs to send the request for the first AI / ML model based on comparing the at least one identification information of the respective AI / ML model with at least one AI / ML model stored in the UE; transmitting the request when the UE determines that the UE needs to transmit the request; The method described in Appendix A1. (Appendix A3) transmitting the request by transmitting a random access procedure message or a Radio Resource Control (RRC) message including the request; The method according to appendix A1 or A2. (Appendix A4) a causal value indicating an intent to receive the first AI / ML model is transmitted with the request; The method described in Appendix A3. (Appendix A5) sending the request is performed after connecting to the access network node. A method according to any one of Appendices A1 to A4. (Appendix A6) Receiving the AI / ML model includes at least one of the following: a broadcast message when the UE is in an RRC idle state or an RRC inactive state; a multicast message when the UE is in an RRC inactive state or an RRC connected state; a dedicated RRC message when the UE is in an RRC Connected state; User plane data transmitted over a data radio bearer, or Data transmitted via radio bearers dedicated to the transmission of AI / ML models, The method according to any one of Appendices A1 to A5. (Appendix A7) receiving the AI / ML model included in the broadcast message or the multicast message; The method includes receiving information about a resource for receiving the AI / ML model, the resource being included in the broadcast message or the multicast message; receiving the AI / ML model using the resource; The method described in Appendix A6. (Appendix A8) receiving the AI / ML model is included in the user plane data transmitted over the data radio bearer; a specific priority is assigned to the logical channel carrying the data radio bearer or the first AI / ML model; The method described in Appendix A6. (Appendix A9) receiving the AI / ML model is included in the data transmitted over the radio bearer dedicated to transmitting the AI / ML model; a logical channel carrying the first AI / ML model is subject to multiplexing constraints with other logical channels carrying signaling radio bearers and / or data radio bearers; The method described in Appendix A6. (Appendix A10) the first AI / ML model stores another entity; the request is forwarded through the access network node; receiving the first AI / ML model from the other entity via the access network node; The method according to any one of Appendices A1 to A9. (Appendix A11) The other entity includes an upper server connected to a mobility management core network node; receiving the first AI / ML model from the upper server via the mobility management core network node using a non-access stratum (NAS) message; The method described in Appendix A10. (Appendix A12) The access network node comprises a central unit and a distributed unit; the at least one identification of the respective artificial intelligence or machine learning (AI / ML) model is transmitted from the central unit via the distributed units; the first AI / ML model is transmitted from the central unit via the distributed units; The method according to any one of Appendices A1 to A11. (Appendix A13) Receiving the at least one identification of the respective AI / ML model includes at least one of the following: a broadcast message when the UE is in an RRC idle state or an RRC inactive state; a multicast message when the UE is in an RRC Inactive state or an RRC Connected state; or a dedicated RRC message when the UE is in an RRC Connected state; The method according to any one of Appendices A1 to A12. (Appendix A14) receiving the at least one identification of the respective AI / ML model included in the broadcast message; The method comprises: receiving a system information block indicating availability of the at least one identification of the respective AI / ML model; and determining whether to receive the at least one identification of the respective AI / ML model; Equipped with The method described in Appendix A13. (Appendix A15) The broadcast message is transmitted periodically or on demand. The method described in Appendix A14. (Appendix A16) The broadcast message includes the at least one identification of the respective AI / ML models and information indicating a respective version of the at least one identification of the respective AI / ML models. determining based on the information indicating a version of the first AI / ML model; The method according to appendix A14 or A15. (Appendix A17) determining whether to send the request based on the version of the first AI / ML model and a timer value stored in the UE. The method described in Appendix A16. (Appendix A18) receiving a first message; and Based on the first message, requesting said access network node to provide at least one updated AI / ML model; or transmitting information indicating a version of each of the at least one AI / ML model stored in the UE; Do at least one of the following: Equipped with The method according to appendix A16 or A17. (Appendix A19) The first message comprises: At least one identification of at least one AI / ML model; or a respective version of said at least one AI / ML model; and The above-mentioned actions include: the at least one identification of the at least one AI / ML model; or said respective versions of said at least one AI / ML model; Based on at least one of the following: The method described in Appendix A18. (Appendix A20) The first message includes information indicating a group of UEs. The method according to appendix A18 or A19. (Appendix A21) the first message includes a cause value indicating that at least one AI / ML model needs to be updated; The method according to any one of Appendices A18 to A20. (Appendix A22) The first message includes at least one of an RRC message or a paging message. A method according to any one of Appendices A18 to A21. (Appendix A23) at least one model area corresponding to each of the AI / ML models is transmitted along with the at least one identification of the respective AI / ML model; A method according to any one of Appendices A1 to A22. (Appendix A24) each of the at least one model area is represented by at least one of at least one cell, a Radio Access Network (RAN) Notification Area (RNA), or a Registration Area; The method described in Appendix A23. (Appendix A25) a cell operated by said access network node is covered by at least one model area; The method according to appendix A23 or A24. (Appendix A26) Each model area to which the respective AI / ML model is applied is transmitted together with the at least one identification of the respective AI / ML model. A method according to any one of Appendices A1 to A25. (Appendix A27) each model area is represented by at least one of a list of at least one cell, a Radio Access Network (RAN)-based Notification Area (RNA), or at least one Registration Area; The method described in Appendix A26. (Appendix A28) each said model area being operator or vendor specific; A method according to appendix A26 or A27. (Appendix A29) Detecting that a model area corresponding to an AI / ML model has been updated when the UE is in an RRC idle state or an RRC inactive state; and requesting the access network node to transmit an AI / ML model corresponding to the update of the model area if the UE intends to use the AI / ML model; Further provided with A method according to any one of Appendices A23 to A28. (Appendix A30) and requesting the access network node to update a model area during a cell selection or cell reselection procedure when the UE is in an RRC idle state or an RRC inactive state. A method according to any one of Appendices A23 to A28. (Appendix A31) Further comprising switching the AI / ML model to be used based on an update of the model area after a cell selection procedure or a cell reselection procedure. A method according to any one of Appendices A23 to A28. (Appendix A32) each of the respective AI / ML models corresponds to a respective characteristic related to the use of the respective AI / ML model; The method according to any one of Appendices A1 to A31. (Appendix A33) the at least one identification information of each AI / ML model is transmitted for each feature of the use or for each AI / ML model; The method described in Appendix A32. (Appendix A34) An AI / ML model with specific characteristics regarding the use of said AI / ML model corresponds to a model area. A method according to appendix A32 or A33. (Appendix A35) each of the plurality of AI / ML models having the specific characteristics related to the use of the AI / ML model corresponds to a respective model area; the method comprising transmitting, to the access network node, information indicating a preference by the UE to use a particular AI / ML model from the plurality of AI / ML models with respect to the particular characteristic related to use of the AI / ML model; The method described in Appendix A34. (Appendix A36) the information indicating the preference is sent in an initial RRC message upon connecting to the access network node. The method described in Appendix A35. (Appendix A37) and transmitting, when the UE transitions from an RRC idle state to an RRC connected state, information indicating at least one identification of each AI / ML model to the access network node. A method according to any one of Appendices A1 to A36. (Appendix A38) The information indicating the at least one identification of the respective AI / ML model, Information indicating the version of each of the AI / ML models; The status of the respective AI / ML model for all features supported by the UE; and Including, The method described in Appendix A37. (Appendix A39) The method further comprises retaining at least one AI / ML model stored by the UE for a predetermined period when the UE transitions from an RRC connected state to an RRC idle state or an RRC inactive state. A method according to any one of Appendices A1 to A38. (Appendix A40) sending an RRC message to the access network node to request the at least one identity of the respective AI / ML model; receiving the at least one identification of the respective AI / ML model in response to the request. A method according to any one of Appendices A1 to A39. (Appendix A41) 1. A method of an access network node, comprising: transmitting to a user equipment (UE) at least one identification of each artificial intelligence or machine learning (AI / ML) model; receiving a request for a first AI / ML model from the UE, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and transmitting the first AI / ML model to the UE; A method comprising: (Appendix A42) A user equipment (UE), means for receiving, from the access network node, at least one identification of a respective artificial intelligence or machine learning (AI / ML) model; means for sending a request for a first AI / ML model to the access network node, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and means for receiving the first AI / ML model from the access network node; UE equipped with. (Appendix A43) an access network node, means for transmitting to a user equipment (UE) an identification of at least one of the respective artificial intelligence or machine learning (AI / ML) models; means for receiving a request for a first AI / ML model from the UE, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the identification of the at least one of the respective AI / ML models; and means for transmitting the first AI / ML model to the UE; An access network node comprising:

[0337] This application is based on and claims priority from UK Patent Application No. 2302234.6, filed February 16, 2023, the disclosure of which is incorporated herein by reference in its entirety.

Claims

1. 1. A method for a user equipment (UE), comprising: receiving, from the access network node, at least one identification of a respective artificial intelligence or machine learning (AI / ML) model; sending a request for a first AI / ML model to the access network node, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and receiving the first AI / ML model from the access network node; A method comprising:

2. determining whether the UE needs to send the request for the first AI / ML model based on comparing the at least one identification information of the respective AI / ML model with at least one AI / ML model stored in the UE; transmitting the request when the UE determines that the UE needs to transmit the request; The method of claim 1.

3. transmitting the request by transmitting a random access procedure message or a Radio Resource Control (RRC) message including the request; 3. The method according to claim 1 or 2.

4. a causal value indicating an intent to receive the first AI / ML model is transmitted with the request; The method of claim 3.

5. sending the request is performed after connecting to the access network node. The method according to any one of claims 1 to 4.

6. Receiving the AI / ML model includes at least one of: a broadcast message when the UE is in an RRC idle state or an RRC inactive state; a multicast message when the UE is in an RRC inactive state or an RRC connected state; a dedicated RRC message when the UE is in an RRC Connected state; User plane data transmitted over a data radio bearer, or Data transmitted via radio bearers dedicated to the transmission of AI / ML models, The method according to any one of claims 1 to 5.

7. receiving the AI / ML model included in the broadcast message or the multicast message; The method includes receiving information about a resource for receiving the AI / ML model, the resource being included in the broadcast message or the multicast message; receiving the AI / ML model using the resource; The method of claim 6.

8. receiving the AI / ML model is included in the user plane data transmitted over the data radio bearer; a specific priority is assigned to the logical channel carrying the data radio bearer or the first AI / ML model; The method of claim 6.

9. receiving the AI / ML model is included in the data transmitted over the radio bearer dedicated to transmitting the AI / ML model; a logical channel carrying the first AI / ML model is subject to multiplexing constraints with other logical channels carrying signaling radio bearers and / or data radio bearers; The method of claim 6.

10. the first AI / ML model stores another entity; the request is forwarded through the access network node; receiving the first AI / ML model from the other entity via the access network node; The method according to any one of claims 1 to 9.

11. The other entity includes an upper server connected to a mobility management core network node; receiving the first AI / ML model from the upper server via the mobility management core network node using a non-access stratum (NAS) message; The method of claim 10.

12. The access network node comprises a central unit and a distributed unit; the at least one identification of the respective artificial intelligence or machine learning (AI / ML) model is transmitted from the central unit via the distributed units; the first AI / ML model is transmitted from the central unit via the distributed units; The method according to any one of claims 1 to 11.

13. Receiving the at least one identification of the respective AI / ML model includes at least one of the following: a broadcast message when the UE is in an RRC idle state or an RRC inactive state; a multicast message when the UE is in an RRC Inactive state or an RRC Connected state; or a dedicated RRC message when the UE is in an RRC Connected state; The method according to any one of claims 1 to 12.

14. receiving the at least one identification of the respective AI / ML model included in the broadcast message; The method comprises: receiving a system information block indicating availability of the at least one identification of the respective AI / ML model; and determining whether to receive the at least one identification of the respective AI / ML model; Equipped with The method of claim 13.

15. The broadcast message is transmitted periodically or on demand.

15. The method of claim 14.

16. The broadcast message includes the at least one identification of the respective AI / ML models and information indicating a respective version of the at least one identification of the respective AI / ML models. the determining is based on the information indicating a version of the first AI / ML model.

16. The method of claim 14 or 15.

17. determining whether to send the request based on the version of the first AI / ML model and a timer value stored in the UE.

17. The method of claim 16.

18. receiving a first message; and Based on the first message, requesting the access network node to provide at least one updated AI / ML model; or transmitting information indicating a respective version of at least one AI / ML model stored in the UE; Doing at least one of the following: Equipped with 18. The method of claim 16 or 17.

19. The first message comprises: At least one identification of at least one AI / ML model; or a respective version of said at least one AI / ML model; and The above-mentioned actions include: the at least one identification of the at least one AI / ML model; or the respective versions of the at least one AI / ML model; is performed based on at least one of 20. The method of claim 18.

20. the first message includes information indicating a group of UEs; 20. The method of claim 18 or 19.

21. the first message includes a cause value indicating that at least one AI / ML model needs to be updated. The method according to any one of claims 18 to 20.

22. the first message includes at least one of an RRC message or a paging message; The method according to any one of claims 18 to 21.

23. at least one model area corresponding to each of the AI / ML models is transmitted along with the at least one identification of the respective AI / ML model; The method according to any one of claims 1 to 22.

24. each of the at least one model area is represented by at least one of at least one cell, a Radio Access Network (RAN) Notification Area (RNA), or a Registration Area; 24. The method of claim 23.

25. a cell operated by said access network node is covered by at least one model area; 25. The method of claim 23 or 24.

26. Each model area to which the respective AI / ML model is applied is transmitted together with the at least one identification of the respective AI / ML model. The method according to any one of claims 1 to 25.

27. each model area is represented by at least one of a list of at least one cell, a Radio Access Network (RAN)-based Notification Area (RNA), or at least one Registration Area; 27. The method of claim 26.

28. each said model area being operator or vendor specific; 28. The method of claim 26 or 27.

29. Detecting that a model area corresponding to an AI / ML model has been updated when the UE is in an RRC idle state or an RRC inactive state; and requesting the access network node to transmit an AI / ML model corresponding to the update of the model area if the UE intends to use the AI / ML model; Further provided with The method according to any one of claims 23 to 28.

30. and requesting the access network node to update a model area during a cell selection or cell reselection procedure when the UE is in an RRC idle state or an RRC inactive state. The method according to any one of claims 23 to 28.

31. Further comprising switching the AI / ML model to be used based on an update of the model area after a cell selection procedure or a cell reselection procedure. The method according to any one of claims 23 to 28.

32. each of the respective AI / ML models corresponds to a respective characteristic related to the use of the respective AI / ML model; The method according to any one of claims 1 to 31.

33. the at least one identification information of each AI / ML model is transmitted for each feature of the use or for each AI / ML model; 33. The method of claim 32.

34. An AI / ML model with specific characteristics regarding the use of said AI / ML model corresponds to a model area.

34. The method of claim 32 or 33.

35. each of the plurality of AI / ML models having the specific characteristics related to the use of the AI / ML model corresponds to a respective model area; the method comprising transmitting, to the access network node, information indicating a preference by the UE to use a particular AI / ML model from the plurality of AI / ML models with respect to the particular characteristic related to use of the AI / ML model; 35. The method of claim 34.

36. the information indicating the preference is sent in an initial RRC message upon connecting to the access network node.

36. The method of claim 35.

37. and transmitting, when the UE transitions from an RRC idle state to an RRC connected state, information indicating at least one identification of each AI / ML model to the access network node.

37. The method according to any one of claims 1 to 36.

38. The information indicating the at least one identification of the respective AI / ML model, Information indicating the version of each of the AI / ML models; The status of the respective AI / ML model for all features supported by the UE; and Including, 38. The method of claim 37.

39. The method further comprises retaining at least one AI / ML model stored by the UE for a predetermined period when the UE transitions from an RRC connected state to an RRC idle state or an RRC inactive state.

39. The method of any one of claims 1 to 38.

40. sending an RRC message to the access network node to request the at least one identity of the respective AI / ML model; receiving the at least one identification of the respective AI / ML model in response to the request.

40. The method of any one of claims 1 to 39.

41. 1. A method of an access network node, comprising: transmitting to a user equipment (UE) at least one identification of each artificial intelligence or machine learning (AI / ML) model; receiving a request for a first AI / ML model from the UE, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and transmitting the first AI / ML model to the UE; A method comprising:

42. A user equipment (UE), means for receiving, from the access network node, at least one identification of a respective artificial intelligence or machine learning (AI / ML) model; means for sending a request for a first AI / ML model to the access network node, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and means for receiving the first AI / ML model from the access network node; UE equipped with.

43. an access network node, means for transmitting to a user equipment (UE) an identification of at least one of the respective artificial intelligence or machine learning (AI / ML) models; means for receiving a request for a first AI / ML model from the UE, wherein the request includes an identification of the first AI / ML model, and the identification of the first AI / ML model is included in the at least one identification of the respective AI / ML model; and means for transmitting the first AI / ML model to the UE; An access network node comprising:

Images