Wireless terminal, radio access network node, and methods therefor

Abstract

A radio access network node according to the present invention transmits first information indicating a first additional condition on a network side for activating or enabling an AI / ML model or AI / ML functionality to a wireless terminal via a broadcast at a cell, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message. This is useful, for example, in enabling the radio access network node to, prior to receiving additional conditions on the wireless terminal side from the wireless terminal or prior to notifying the wireless terminal of other additional conditions on the network side, notify the wireless terminal of additional conditions on the network side for activating or enabling the AI / ML model or the AI / ML functionality.

Description

Wireless terminal, radio access network node, and methods thereof

[0001] The present disclosure relates to wireless communication networks, and more particularly to the application of artificial intelligence (AI) to wireless communication networks.

[0002] The 3rd Generation Partnership Project (3GPP®) is discussing the application or introduction of AI or machine learning (ML) to 5G. In particular, network-based AI / ML with User Equipment (UE) involvement and UE-based AI / ML are being considered for 3GPP Release 18 and beyond (see, for example, Non-Patent Documents 1-5).

[0003] AI / ML can be considered for both network internal functions and the air interface (i.e., Uu). Potential use cases of AI / ML for the air interface include Channel State Information (CSI) feedback compression, beam management (BM), and positioning accuracy enhancements (see, for example, Non-Patent Document 1).

[0004] Network-based AI / ML is also referred to as a network-side AI / ML model or network-side model. In network-based AI / ML, the network performs AI / ML inference. AI / ML inference refers to predictions or decisions using or based on a trained AI / ML model. The AI / ML inference function may be located in the Next Generation Radio Access Network (NG-RAN) (e.g., gNB). Alternatively, the AI / ML inference function may be located in a Near-Real-Time (Near-RT) RAN Intelligent Controller (RIC) coupled to the gNB. Training of the AI / ML model may be performed in the NG-RAN. Alternatively, an Operation, Administration, and Maintenance (OAM) server or a non-RT RIC may train the AI / ML model and provide the trained AI / ML model (e.g., trained parameters or an AI / ML application including the trained parameters) to the NG-RAN (e.g., gNB) or Near-RT RIC.

[0005] UE-based AI / ML is also referred to as a UE-side AI / ML model or UE-side model. In UE-based AI / ML, the UE performs AI / ML inference. In UE-based AI / ML, the UE runs an AI / ML model (i.e., a trained machine learning model) and obtains the AI ​​inference results locally. For example, the UE can predict future events or measurements based on past measurements. The UE can feed back the predicted results (e.g., mobility or beam predictions) to the network (e.g., gNB). Training of the AI / ML model for UE-based AI / ML may be performed by the UE or by the network (e.g., gNB, Near-RT RIC, Non-RT RIC, or other OAM server or controller).

[0006] In addition, a two-sided model may be used. A two-sided model is also called a two-sided AI / ML model. A two-sided model is a pair of AI / ML models in which joint inference is performed. Joint inference is AI / ML inference in which inference is performed jointly across the UE and the network. Specifically, the UE performs the first part of the inference and the gNB performs the rest, or vice versa.

[0007] One sub-use case for AI / ML BM involves downlink (DL) beam prediction in both UE-side and network-side models (see, for example, Non-Patent Documents 1-5). DL beam prediction includes spatial-domain beam prediction and temporal beam prediction. Temporal beam prediction may also be referred to as time-domain beam prediction. DL beam prediction includes prediction of DL transmission (Tx) beam, prediction of DL reception (Rx) beam, and prediction of beam pairs of DL Tx beam and DL Rx beam.

[0008] Spatial-domain DL beam prediction is a spatial-domain DL beam prediction of Set A of beams based on measurements of Set B of beams. Spatial-domain DL beam prediction is conveniently called BM-Case 1. Beam Set B is the set of beams whose measurements are taken as inputs to an AI / ML model. In spatial-domain DL beam prediction (i.e., BM-Case 1), Set A is different from Set B (i.e., Set B is not a subset of Set A), or Set B is considered to be a subset of Set A. There are four possible inputs to the AI / ML model for spatial domain DL beam prediction: Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; L1-RSRP measurements and assistance information based on set B; Channel Impulse Response (CIR) based on set B; L1-RSRP measurements based on set B and either or both of the corresponding DL Tx beam ID and Rx beam ID.

[0009] Temporal DL beam prediction is a temporal DL beam prediction of Set A of beams based on the historical measurement results of Set B of beams. Temporal DL beam prediction is conveniently called BM-Case 2. Beam Set B is the set of beams whose measurements are taken as inputs to the AI / ML model. In temporal DL beam prediction (i.e., BM-Case 2), Set A is considered to be different from Set B (i.e., Set B is not a subset of Set A), Set B is a subset of Set A (i.e., Set B is not identical to Set A), or Set A and Set B are considered to be the same. The input to the AI / ML model for temporal DL beam prediction is considered to be the measurement results of the K (K≧1) most recent measurement instances, with the following options: - Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; - L1-RSRP measurements based on set B and assistance information; - L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0010] Non-Patent Document 1 describes the life cycle management (LCM) of AI / ML models, particularly in Section 4.2. LCM includes, for example, model training, model deployment, model inference, model monitoring, and model update. More specifically, LCM considers the following aspects, including the definition and necessity of components (if necessary): data collection (including related assistance information, if applicable); model training; functionality or model identification; model delivery or transfer; model inference operation; functionality or model selection, activation, deactivation, switching, and fallback operations; functionality or model monitoring; model update; and UE capabilities.

[0011] LCM procedures are studied for either or both cases where AI / ML models have a model ID and associated information (i.e., model ID-based LCM) or where predetermined functionality is provided by AI / ML operations (i.e., function-based LCM). AI / ML models identified by model IDs are logical, and how they map to physical AI / ML models may be implementation-dependent. Where a distinction is necessary for discussion, the term logical AI / ML model may be used to refer to a model that has been identified and assigned a model ID, and the term physical AI / ML model may be used to refer to the actual implementation of such a model.

[0012] For the UE-side model and the UE part of the two-sided model, in the case of AI / ML functionality identification, the legacy 3GPP framework of features is used as the starting point, and the UE indicates the supported functionalities for a given sub-use case. Here, the UE capability reporting is used as the starting point. In the case of AI / ML model identification, for the UE-side model and the UE part of the two-sided model, the model is identified by a model ID in the network, and the UE indicates the supported AI / ML models.

[0013] In capability-based LCM, the network indicates activation, deactivation, fallback, or switching of AI / ML capabilities via 3GPP signaling. 3GPP signaling, for example, Radio Resource Control (RRC) signaling, Medium Access Control (MAC) Control Element (CE), or Downlink Control Information (DCI), may be used. Models may not be identified by the network, and the UE may perform model-level LCM. In functionality identification, one or more functionalities may be defined within an AI / ML-enabled feature. An AI / ML-enabled feature refers to a feature that is AI / ML-enabled. A UE may have one AI / ML model for a functionality, or multiple AI / ML models for a functionality.

[0014] In the AI / ML functionality identification and functionality-based LCM of the UE-side model and / or the UE portion of the dual-side model, functionality refers to an AI / ML-enabled feature or feature group (FG) that is enabled by a configuration. A configuration is supported based on conditions indicated by a UE capability. Correspondingly, functionality-based LCM operates based at least on a configuration of an AI / ML-enabled feature or feature group or a specific configuration of an AI / ML-enabled feature or feature group.

[0015] In model ID-based LCM, models are identified in the network. The network or UE can activate, deactivate, select, or switch between individual AI / ML models via model IDs. In AI / ML model identification and model ID-based LCM for the UE-side model and / or the UE portion of the dual-side model, model ID-based LCM operates based on the identified model. Here, the model is associated with specific configurations / conditions associated with the UE capability of an AI / ML-enabled feature or feature group, and additional conditions determined or specified between the UE and the network. The additional conditions may be or relate to, for example, scenarios, sites, and datasets.

[0016] In functionality-based LCM and model ID-based LCM, once functionalities or models are identified, the same or similar procedures can be used for their activation, deactivation, switching, fallback, and monitoring. Model IDs can be used for LCM operations on functions (defined in functionality-based LCM) if necessary.

[0017] Section 4.2.2 of 3GPP TS 365.1100 includes the following disclosure regarding model identification: In AI / ML model identification of the UE-side model or the UE portion of a dual-side model, the model can be identified to the network (if applicable) and the UE (if applicable) without over-the-air signaling (Type A). In Type A model identification, the model may be assigned a model ID during model identification, which may be referenced or used in over-the-air signaling after model identification. Alternatively, the model may be identified via over-the-air signaling (Type B). In Type B model identification, model identification is initiated by the UE, and the network assists with the remaining steps of model identification (if any) (Type B1). Alternatively, in Type B model identification, model identification is initiated by the network, and the UE responds with the remaining steps of model identification (if any) (Type B2). In Types B1 and B2 model identification, the model may be assigned a model ID during model identification.

[0018] Once the model is identified, the UE may indicate the supported AI / ML model IDs for a given AI / ML-enabled feature or feature group as a starting point in the UE capability report, at least for Type A. Note that model identification using the capability report is not excluded for Types B1 and B2 as well.

[0019] Section 4.2.3 of 3GPP TS 2.0 / 10.23 includes the following disclosure regarding additional conditions: Regarding an AI / ML-enabled feature or feature group, an additional condition refers to any aspect that is assumed for training an AI / ML model but is not part of the UE capabilities for that AI / ML-enabled feature or feature group. Additional conditions are divided into two categories: network-side additional conditions and UE-side additional conditions. For UE-side model inference, to ensure consistency between training and inference regarding network-side additional conditions (if identified), the following options (if feasible and necessary) can be taken as possible approaches: Model identification to achieve alignment on network-side additional conditions between the network and UE sides; Model training in the network and transfer to the UE, where the model is trained under the additional conditions; Information and / or indication regarding the network-side additional conditions being provided to the UE; Consistency assisted by monitoring (of the performance of UE-side candidate models or functions by the UE or the network to select a model or function).

[0020] Section 5.2 of Non-Patent Document 1 includes the following disclosure regarding additional conditions in BM-Case 1 (i.e., spatial domain DL beam prediction) and BM-Case 2 (i.e., temporal domain DL beam prediction): For BM-Case 1 and BM-Case 2 with UE-side AI / ML models, the necessity and possibility of BM-specific conditions or additional conditions on functionality(ies) and / or model(s) are considered from at least the following perspectives: Information on model inference, Configuration of Set A or Set B, Performance monitoring, Data collection, Assistance information.

[0021] Non-Patent Document 3 includes the following disclosure regarding additional conditions: Additional conditions, as the name suggests, are additional conditions that more dynamically limit the applicability of UE models. These additional conditions can be provided by the network or the UE. The network may provide "assistance information" to help the UE select an appropriate model. Since it is expected that the UE will not always be able to store all possible models for all network configurations, the UE's "internal conditions" should be able to provide additional conditions that indicate which models are available. In the case of model ID-based LCM, the additional conditions define the model ID (together with the conditions). In the case of function-based LCM, the UE can determine the additional conditions only based on the network assistance information. Applicable conditions are identified functionalities adjusted by the additional conditions. Applicable conditions define which features can be configured and activated. The UE provides the applicable conditions to the network. Additional conditions based on assistance information or internal conditions can be used to modify applicable conditions or models.

[0022] Non-Patent Document 4 includes the following disclosure regarding the transmission of additional conditions from a UE to a network: The UE Assistance Information procedure and the UE Information procedure can realize flexible information transfer from a UE to a gNB. If the network is responsible for controlling or managing the model and wants to have full control over whether and when to acquire the additional conditions, the UE Information procedure can be considered as an option. If the additional conditions are verified by the UE and the network is responsible for controlling or managing the model, the UE needs to indicate the availability of the model or function to the network. Because availability may change from time to time and may vary based on the current scenario, UEAssistanceInformation can be used to feedback an indication of availability.

[0023] Non-Patent Document 4 includes the following disclosure regarding the transmission of additional conditions from the network to the UE. Regarding the additional conditions and applicability from the network to the UE, two cases need to be considered: a UE-side model and a network-side model. If the network has model training for the UE-side model, the network should be responsible for transferring the model and providing the additional conditions to the UE. If there are additional conditions to be verified in the UE, such additional conditions can be provided during model transfer. In the case of a network-side model, the UE may be responsible for verifying whether certain conditions are met, and the UE is expected to indicate whether the corresponding model or function is applicable. For this purpose, the UE Assistance Information following RRC Reconfiguration can be used. That is, the RRC Reconfiguration message using otherconfig can be considered as an alternative to transferring additional conditions from the network to the UE, and the UE can feed back an indication of applicability to the network via UE Assistance Information.

[0024] Non-Patent Document 5 includes the following disclosure regarding AI / ML for beam management: For BM-Case 1 and BM-Case 2 with UE-side AI / ML models, for aspects related to the association or mapping of beams in Set A with beams in Set B, mechanisms to ensure consistency of beams in Set B with beams in Set A across training and inference need to be considered, including one or more of the following: Set size consistency between Set B and Set A: consistency in the number of beams and / or associated resources in Set B and Set A across training and inference; Order or index consistency: consistency in the ordering of resources for beams in Set B and beams in Set A across training and inference (e.g., consistency of resource index); Quasi Co-Location (QCL) consistency: consistency in the QCL relationship of beams in Set A to beams in Set B; Beam shape consistency: differences in relative pointing direction and beam width between physical beams for resources in Set A and Set B across training and inference must be within a predefined tolerance.

[0025] 3GPP TR 38.843 V18.0.0 (2023-12)Qualcomm, "New WID on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface", RP-234039, 3GPP TSG RAN Meeting #102, Edinburgh, Scotland, December 11-15, 2023Qualcomm Incorporated, "Towards one LCM: Merging Functionality and Model-ID based LCMs", R2-2312561, 3GPP TSG-RAN WG2 Meeting #123bis, Chicago, USA, November 13-17, 2023vivo, "Further discussion on additional conditions and applicability indication", R2-2313030, 3GPP TSG-RAN WG2 Meeting #124, Chicago, USA, November 13-17, 2023Qualcomm Incorporated, "Other aspects on AI / ML for beam management", R1-2307919, 3GPP TSG-RAN WG1 Meeting #114, Toulouse, France, August 21-25, 2023

[0026] The inventors have investigated the LCM of AI / ML models and found various issues. One of these issues relates to a mechanism for ensuring consistency of additional conditions between a UE and a network. As described above, in one example, additional conditions can be used or considered to determine the applicability of a UE-side AI / ML model or a network-side AI / ML model. The additional conditions can be conditions that are applied or used for training an AI / ML model and that also need to be applied or used for inference. To determine an applicable AI / ML model or function, the network can provide one or both of information and indication regarding the network-side additional conditions to the UE. Similarly, the UE can provide one or both of information and indication regarding the UE-side additional conditions to the network. Non-Patent Document 4 discloses that the UE Assistance Information procedure (UE Assistance Information message) and the UE Information procedure (UE Information Response message) can be used to transmit additional conditions from a UE to a network. Non-Patent Document 4 also discloses that the "otherconfig" included in the RRC Reconfiguration message can be used to transmit additional conditions from a network to a UE.

[0027] For example, in some implementations, the network may need to receive UE-side additional requirements from multiple UEs in a cell after receiving AI / ML capabilities from those UEs to determine whether to activate an AI / ML model or function for those UEs. However, this may increase the latency for determining whether to activate an AI / ML model or function. Alternatively, if the UE-side additional requirements of many UEs in a cell conflict with the network-side additional requirements (e.g., if there is no common subset between the UE-side additional requirements and the network-side additional requirements), the network's efforts to obtain the additional requirements from the UEs may be wasted.

[0028] To address or mitigate this problem, it may be preferable for the network to provide at least some of the network-side additional conditions to the UE prior to a procedure for informing the UE of other network-side additional conditions (e.g., an RRC Reconfiguration procedure, a UE Assistance Information procedure, or a UE Information procedure). Alternatively, it may be preferable for the network to provide at least some of the network-side additional conditions to the UE prior to a procedure for receiving UE-side additional conditions from the UE (e.g., a UE Assistance Information procedure or a UE Information procedure). Some of the network-side additional conditions provided to the UE in advance may be additional conditions that must be met for a particular AI / ML model or feature to be applicable.

[0029] Similarly, it may be preferable for the UE to provide at least some of the UE-side additional conditions to the network prior to a procedure for transmitting other additional conditions to the network (e.g., a UE Assistance Information procedure or a UE Information procedure). Alternatively, it may be preferable for the UE to provide at least some of the UE-side additional conditions to the network prior to a procedure for receiving network-side additional conditions from the network (e.g., an RRC Reconfiguration procedure, a UE Assistance Information procedure, or a UE Information procedure). Some UE-side additional conditions provided to the network in advance may be additional conditions that must be met for a particular AI / ML model or feature to be applicable, for example.

[0030] One of the objectives to be achieved by the embodiments disclosed in this specification is to provide an apparatus, a method, and a program that contribute to solving at least one of multiple problems related to LCM of AI / ML models or functions, including the problems described above. It should be noted that this objective is only one of multiple objectives to be achieved by the multiple embodiments disclosed in this specification. Other objectives or objectives and novel features will become apparent from the description of this specification or the accompanying drawings.

[0031] A first aspect is directed to a wireless terminal configured to receive, from a radio access network node via a cell broadcast, via an RRC Setup message, via an RRC Resume message, or via a UE Capability Enquiry message, first information indicating a first additional condition on the network side for activating or enabling an AI / ML model or AI / ML functionality.

[0032] A second aspect is directed to a method performed by a wireless terminal, the method including receiving, from a radio access network node via a cell broadcast, via an RRC Setup message, via an RRC Resume message, or via a UE Capability Enquiry message, first information indicating a first additional network-side condition for activating or enabling an AI / ML model or functionality.

[0033] A third aspect is directed to a radio access network node configured to transmit first information indicating a first additional condition on the network side for activating or enabling an AI / ML model or functionality to a wireless terminal via a cell broadcast, via an RRC Setup message, via an RRC Resume message, or via a UE Capability Enquiry message.

[0034] A fourth aspect is directed to a method performed by a radio access network node, the method including transmitting first information indicating a first additional network-side condition for activating or enabling an AI / ML model or functionality to a wireless terminal via a cell broadcast, via an RRC Setup message, via an RRC Resume message, or via a UE Capability Enquiry message.

[0035] A fifth aspect is directed to a wireless terminal configured to transmit first information indicating an additional condition on the wireless terminal side for activating or enabling an AI / ML model or an AI / ML capability to a radio access network node via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.

[0036] A sixth aspect is directed to a method performed by a wireless terminal, the method including transmitting first information indicating additional conditions on the wireless terminal side for activating or enabling an AI / ML model or AI / ML capability to a radio access network node via an RRC Setup Complete message or an RRC Resume Complete message, or via a PUSCH transmission in a random access procedure.

[0037] A seventh aspect is directed to a radio access network node configured to receive, from a radio terminal via an RRC Setup Complete message or an RRC Resume Complete message or via a PUSCH transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an AI / ML model or an AI / ML capability.

[0038] An eighth aspect is directed to a method performed by a radio access network node, the method including receiving, from a radio terminal via an RRC Setup Complete message or an RRC Resume Complete message or via a PUSCH transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an AI / ML model or AI / ML capability.

[0039] A ninth aspect is directed to a program, which includes a set of instructions (software code) that, when loaded into a computer, causes the computer to perform the method according to the second, fourth, sixth, or eighth aspect.

[0040] According to the above-described aspects, it is possible to provide an apparatus, a method, and a program that contribute to solving at least one of a plurality of problems related to LCM of AI / ML models or functions, including the above-described problems.

[0041] FIG. 1 illustrates an example configuration of a wireless communication system according to one or more embodiments. FIG. 2 illustrates an example configuration of a wireless communication system according to one or more embodiments. FIG. 3 illustrates an example configuration of a wireless communication system according to one or more embodiments. FIG. 4 illustrates an example format of an SIB information element according to one or more embodiments. FIG. 5 illustrates an example format of an RRCSetup message according to one or more embodiments. FIG. 6 illustrates an example format of an RRCCapabilityEnquiry message according to one or more embodiments. FIG. 7 illustrates an example format of an RRCSetupComplete message according to one or more embodiments. FIG. 8 illustrates an example format of an RRCSetupComplete message according to one or more embodiments. FIG. 9 illustrates an example format of an RRCSetupComplete message according to one or more embodiments.

[0042] Hereinafter, specific embodiments will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0043] The multiple embodiments described below may be used independently, or two or more embodiments may be combined as appropriate. These multiple embodiments may have different novel features. Therefore, these multiple embodiments may contribute to achieving different objectives or solving different problems, and may contribute to achieving different effects.

[0044] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate 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.

[0045] The following embodiments will be described with a focus on the 3GPP fifth generation mobile communication system (5G system), but may also be applied to other wireless communication systems that support AI / ML.

[0046] As used herein, depending on the context, "if" may be interpreted to mean "when," "while," "at or around the time," "after," "upon," "in response to determining," "in accordance with a determination," or "in response to detecting." These expressions may be interpreted to have the same meaning, depending on the context.

[0047] First, the configurations and operations of several network elements common to several embodiments will be described. Fig. 1 shows an example configuration of a wireless communication system related to several embodiments. In the example of Fig. 1, the wireless communication system includes a wireless terminal (i.e., UE) 1 and a Radio Access Network (RAN) node (e.g., gNB) 2. Each element (network function) shown in Fig. 1 can be implemented, for example, as a network element on dedicated hardware, as a software instance running on dedicated hardware, or as a virtualized function instantiated on an application platform.

[0048] The UE 1 has at least one radio transceiver and is configured to perform wireless communication with the RAN node 2. The UE 1 is connected to the RAN node 2 via an air interface 101. The UE 1 may be referred to by other terms such as a radio terminal, a mobile terminal, a mobile station, or a wireless transmit receive unit (WTRU). The RAN node 2 manages a cell and is configured to perform wireless communication with multiple UEs, including the UE 1, using a cellular communication technology (e.g., an NR Radio Access Technology (RAT)). The RAN node 2 may be referred to by other terms such as a base station, a radio station, or an access point. The UE 1 may be simultaneously connected to multiple RAN nodes, including the RAN node 2, for dual connectivity (DC).

[0049] The RAN node 2 may be a Central Unit (CU) (e.g., gNB-CU) in a cloud RAN (C-RAN) deployment, or a combination of a CU and one or more Distributed Units (DUs) (e.g., gNB-DUs). Furthermore, the CU may include a Control Plane (CP) Unit (e.g., gNB-CU-CP) and one or more User Plane (UP) Units (e.g., gNB-CU-UP). Thus, the RAN node 2 may be a CU-CP or a combination of a CU-CP and a CU-UP. The CU may be a logical node that hosts the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) protocols of the gNB (or the RRC and PDCP protocols of the gNB). The DU may be a logical node that hosts the Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers of the gNB.

[0050] Specifically, as shown in Fig. 2, the RAN node 2 may include a CU 201 (e.g., gNB-CU) and one or more DUs 211 and 212 (e.g., gNB-DUs). The CU 201 is a logical node that controls the operation of the DUs 211 and 212. The CU 201 and each of the DUs 211 and 212 may also be referred to as a RAN node. Each of the DUs 211 and 212 is a logical node that hosts the RLC layer and MAC layer of the RAN node 2 and hosts part of the PHY layer of the RAN node 2, i.e., the upper PHY layer. The remaining signal processing of the PHY layer, i.e., the lower PHY layer, is located in Transmission Reception Points (TRPs) 231 to 235.

[0051] One DU may support one or more cells. One cell may be supported by only one DU. In the example of Figure 2, DU 211 is connected to TRPs 231 to 233, while DU 212 is connected to TRPs 234 and 235. TRPs 231 to 233 provide one cell 241, and TRPs 234 and 235 provide separate cells 242 and 243, respectively. In other words, DU 211 provides one cell 241, and TRPs 231 to 233 correspond to cell 241. DU 212 provides multiple cells 242 and 243, and TRPs 234 and 235 correspond to cells 242 and 243, respectively.

[0052] Each of the TRPs 231-235 can communicate with UE 1 using a beam. The TRPs 231-235 may also be called Radio Units (RUs), Remote Radio Heads (RRHs), access points (APs), or distributed antennas. Each TRP is a set of geographically co-located antennas (e.g., an antenna array with one or more antenna elements). Each TRP supports either or both Transmission Point (TP) and Reception Point (RP) functions.

[0053] The RAN node 2 may be connected to a RAN controller 3. The RAN controller 3 may be referred to by other terms, such as a control device or a control system. The RAN controller 3 may be integrated into the RAN node 2 (e.g., gNB). Alternatively, the RAN controller 3 may include one or both of a Non-RT RIC and a Near-RT RIC defined in the O-RAN Alliance technical specifications. In this case, the RAN node 2 may be connected to the RAN controller 3 via one or both of an O1 interface and an E2 interface. Alternatively, the RAN controller 3 may be an OAM server or another controller. In other words, the functions of the RAN controller 3 may be located in the RAN node 2, the Non-RT RIC, the Near-RT RIC, the OAM server, or another controller, or may be distributed across any combination thereof.

[0054] The UE 1 may perform AI / ML inference locally. In other words, the UE 1 may support UE-based AI / ML. UE-based AI / ML is also referred to as a UE-side AI / ML model or a UE-side model. This AI / ML inference may relate to RAN optimization. The UE 1 may run AI inference on a trained artificial intelligence or machine learning (AI / ML) model and take one or more actions according to a prediction or decision based on the AI ​​inference. The AI / ML model may be any model known in the field of machine learning, including deep learning. The AI / ML model may be, for example, but not limited to, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a K-nearest neighbor model.

[0055] By way of example and not limitation, the prediction or decision based on AI inference by UE1 and one or more actions triggered thereby may relate to beam management (BM) and include DL beam prediction. The one or more actions may include, for example, but not limited to, DL beam selection. The DL beam may include a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) block (SSB) beam, a Channel State Information (CSI) Reference Signal (CSI-RS) beam, or both. For example, the AI / ML model may output one or more candidate beams for DL ​​beam selection. Additionally or alternatively, the AI / ML model may predict or determine the timing of execution of an action for beam management. The DL beam prediction and selection by UE1 may be performed during a Beam Failure Recovery (BFR) procedure.

[0056] The training of the AI / ML model for AI / ML inference by the UE 1 may be performed by the UE 1 or by the network (e.g., RAN node 2, RAN controller 3, or OAM). The training method may be offline learning, online learning, or a combination thereof.

[0057] Similarly, the network, i.e., the RAN node 2 or the RAN controller 3, or other control system, or any combination thereof, may perform AI / ML inference. In other words, the network may support network-based AI / ML. Network-based AI / ML is also referred to as a network-side AI / ML model or network-side model. This AI / ML inference may relate to RAN optimization. The network may run AI inference on a trained AI / ML model and take one or more actions according to a prediction or decision based on the AI ​​inference. The AI / ML model may be any model known in the field of machine learning, including deep learning. The AI / ML model may be, for example, but not limited to, a neural network model, a support vector machine model, a decision tree model, a random forest model, or a k-nearest neighbor model.

[0058] By way of example and not limitation, the network-based AI inference-based prediction or decision and one or more actions triggered thereby may relate to beam management and include DL beam prediction. The one or more actions may include, for example and without limitation, DL beam selection. The DL beam may include an SSB beam, a CSI-RS beam, or both. For example, the AI / ML model may output one or more candidate beams for DL ​​beam selection. Additionally or alternatively, the AI / ML model may predict or determine when to perform an action for beam management. The network-based DL beam prediction and selection may be performed to determine the set of CSI-RS beams to be configured (or measured) by UE1.

[0059] Training of an AI / ML model for network-based AI / ML inference may be performed by any information processing system or computer system on the network side, and the training method may be offline learning, online learning, or a combination of these.

[0060] In addition, a two-sided model may be used. A two-sided model is also called a two-sided AI / ML model. A two-sided model is a pair of AI / ML models in which joint inference is performed. Joint inference is AI / ML inference in which inference is performed jointly across the UE and the network. Specifically, the UE performs the first part of the inference and the gNB performs the rest, or vice versa.

[0061] One sub-use case for AI / ML BM involves DL beam prediction in both the UE-side model and the network-side model. DL beam prediction includes spatial domain beam prediction and temporal beam prediction. Temporal beam prediction may also be referred to as time domain beam prediction. DL beam prediction includes DL Tx beam prediction, DL Rx beam prediction, and beam pair prediction of DL Tx beam and DL Rx beam.

[0062] Spatial-domain DL beam prediction is a spatial-domain DL beam prediction of Set A of beams based on measurements of Set B of beams. Spatial-domain DL beam prediction is conveniently called BM-Case 1. Beam Set B is the set of beams whose measurements are taken as inputs to an AI / ML model. In spatial-domain DL beam prediction (i.e., BM-Case 1), Set A is different from Set B (i.e., Set B is not a subset of Set A), or Set B is considered to be a subset of Set A. For example, there are four possible inputs to the AI / ML model for spatial domain DL beam prediction: Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; L1-RSRP measurements and assistance information based on set B; Channel Impulse Response (CIR) based on set B; L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0063] Temporal DL beam prediction is a temporal DL beam prediction of Set A of beams based on the historical measurement results of Set B of beams. Temporal DL beam prediction is conveniently called BM-Case 2. Beam Set B is the set of beams whose measurements are taken as inputs to the AI / ML model. In temporal DL beam prediction (i.e., BM-Case 2), Set A is considered to be different from Set B (i.e., Set B is not a subset of Set A), Set B is a subset of Set A (i.e., Set B is not identical to Set A), or Set A and Set B are considered to be the same. For example, the input to the AI / ML model for temporal DL beam prediction may be the measurement results of the K (K≧1) most recent measurement instances, with the following options: - Layer 1 (L1) Reference Signal Received Power (RSRP) measurements only based on set B; - L1-RSRP measurements based on set B and assistance information; - L1-RSRP measurements based on set B and one or both of the corresponding DL Tx beam ID and Rx beam ID.

[0064] The UE 1 and RAN node 2 support Life Cycle Management (LCM) of AI / ML models or AI / ML capabilities. LCM includes, for example, model training, model deployment, model inference, model monitoring, and model updates. More specifically, LCM may include one or more of the following: data collection (including associated assistance information, if applicable); model training; functionality or model identification; model delivery or transfer; model inference operations; functionality or model selection, activation, deactivation, switching, and fallback operations; functionality or model monitoring; model updates; and UE capabilities.

[0065] The LCM procedure relates to one or both of the cases where an AI / ML model has a model ID and related information (i.e., model ID-based LCM) and the case where predetermined functionality is provided by AI / ML operations (i.e., function-based LCM). The definitions and details of model ID-based LCM and function-based LCM are as explained in the Background Art section, so a duplicate explanation will be omitted here.

[0066] An AI / ML model or functionality is associated with specific configurations / conditions associated with a UE capability of an AI / ML-enabled feature or feature group. Furthermore, the AI / ML model or functionality is associated with additional conditions determined or specified between the UE 1 and the network (e.g., RAN node 2). The definition and details of the additional conditions may be similar to those described above in the Background section with reference to Non-Patent Documents 1 and 3-5.

[0067] With respect to an AI / ML-enabled feature or feature group, additional requirements refer to any aspects that are envisioned for training an AI / ML model but are not part of the UE capabilities for that AI / ML-enabled feature or feature group. Additional requirements are divided into two categories: network-side additional requirements and UE-side additional requirements.

[0068] In one example, the additional conditions may be used or considered to determine the applicability of the UE-side AI / ML model or the network-side AI / ML model. The additional conditions may be conditions that are applied or used for training the AI / ML model and that also need to be applied or used for inference. In other words, the additional conditions may include one or more conditions that are used for training the AI / ML model and that need to be consistent with the inference performed by the AI / ML model.

[0069] To determine the applicable AI / ML model or function, information and / or indication regarding the network-side additional requirements can be provided from the network (e.g., RAN node 2) to the UE 1. Similarly, information and / or indication regarding the UE-side additional requirements can be provided from the UE 1 to the network (e.g., RAN node 2).

[0070] With regard to AI / ML for beam management, additional conditions may include at least one of the following: Set size of Set B and Set A: e.g., number of beams and / or associated resources in Set B and Set A; Ordering of resources (e.g., resource index) of beams in Set B and beams in Set A; QCL relationship of beams in Set A to beams in Set B; Beam shapes (e.g., pointing direction and beam width) of Set A and Set B.

[0071] QCL is an index that indicates the statistical properties of a signal or channel. Two antenna ports are said to be QCLed (Quasi Co-located) if the characteristics of the channel through which symbols on one antenna port are transmitted can be inferred from the channel through which symbols on the other antenna port are transmitted. If two antenna ports or two signals transmitted on these two antenna ports are QCLed, it means that these two signals have passed through similar wireless channels that share similar characteristics in at least one of Doppler shift, Doppler spread, average delay, delay spread, and spatial reception (Rx) parameters. If two antenna ports are QCLed, the two signals transmitted on these two antenna ports can be considered to reach the receiver through similar channels. Therefore, if a receiver can detect one signal and understand the channel characteristics of that signal, the channel characteristics can be useful for detecting the other signal.

[0072] First Embodiment A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of signaling between a UE 1 and a RAN node 2 related to LCM of an AI / ML model or function.

[0073] In this embodiment, the RAN node 2 transmits information indicating one or more network side additional conditions to the UE 1 via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message. The UE 1 receives information indicating one or more network side additional conditions from the RAN node 2 via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message.

[0074] In other words, the RAN node 2 notifies the UE 1 of at least some of the network-side additional conditions before a procedure for notifying the UE 1 of other network-side additional conditions (e.g., an RRC Reconfiguration procedure, a UE Assistance Information procedure, or a UE Information procedure). Alternatively, the RAN node 2 notifies the UE 1 of at least some of the network-side additional conditions before a procedure for receiving information indicating the UE-side additional conditions from the UE 1 (e.g., a UE Assistance Information procedure or a UE Information procedure). At least some of the network-side additional conditions may be mandatory conditions for applying, activating, or enabling a specific AI / ML model or AI / ML function. The remaining network-side additional conditions may be preferred conditions (conditions that can be adjusted or omitted) that can be optionally used for applying, activating, or enabling a specific AI / ML model or AI / ML function.

[0075] In some implementations, the RAN node 2 may need to receive UE-side additional conditions from multiple UEs in a cell after receiving AI / ML capabilities from these UEs in order to determine whether to activate (or enable) an AI / ML model or function for the UEs in the cell. However, this may increase the latency for determining whether to activate (or enable) an AI / ML model or function. Alternatively, if the UE-side additional conditions of many UEs in a cell conflict with the network-side additional conditions (e.g., if there is no common subset between the UE-side additional conditions and the network-side additional conditions), the RAN node 2's efforts to obtain the additional conditions from the UEs may be wasted. The operations of the UE 1 and the RAN node 2 described above may help address or mitigate this issue.

[0076] In one example, in response to receiving the information indicating one or more network-side additional conditions, UE1 may send feedback to RAN node 2 informing RAN node 2 whether the received network-side additional conditions conflict with UE-side additional conditions for activating or enabling an AI / ML model or AI / ML function. RAN node 2 may use the feedback to determine whether to request UE1 to transmit information indicating UE-side additional conditions for activating or enabling an AI / ML model or AI / ML function. Alternatively, RAN node 2 may use the feedback to determine whether to transmit information indicating other network-side additional conditions to UE1. In other words, RAN node 2 may use the feedback to determine whether to activate (or enable) a particular AI / ML model or AI / ML function in or for UE1.

[0077] These operations, including the transmission of feedback by UE 1, enable UE 1 and RAN node 2 to know early whether there is consistency between the network-side addition conditions and the UE-side addition conditions. If there is a contradiction between the network-side addition conditions and the UE-side addition conditions (e.g., if there is no common subset between the UE-side addition conditions and the network-side addition conditions), RAN node 2 can omit or skip a procedure for obtaining the UE-side addition conditions from UE 1 (e.g., a UE Assistance Information procedure or a UE Information procedure). Alternatively, RAN node 2 can omit or skip a procedure for informing UE 1 of other network-side addition conditions (e.g., an RRC Reconfiguration procedure, a UE Assistance Information procedure, or a UE Information procedure).

[0078] If the RAN node 2 transmits the information indicating the network-side addition condition via broadcast, the UE 1 may transmit the feedback via an RRC Setup Request message, an RRC Setup Complete message, an RRC Resume Request message, or an RRC Resume Complete message. If the RAN node 2 transmits the information indicating the network-side addition condition via an RRC Setup message or an RRC Resume message, the UE 1 may transmit the feedback via an RRC Setup Complete message or an RRC Resume Complete message. If the RAN node 2 transmits the information indicating the network-side addition condition via a UE Capability Enquiry message, the UE 1 may transmit the feedback via a UE Capability Information message.

[0079] Additionally or alternatively, based on or taking into consideration the received network-side addition condition, UE1 may determine whether to report the UE-side addition condition for activating or enabling the AI / ML model or AI / ML function to RAN node 2. The reporting operation includes transmitting a UE Assistance Information message indicating the UE-side addition condition in a UE Assistance Information procedure, transmitting a UE Capability Information message indicating the UE-side addition condition in a UE capability transfer procedure, or transmitting a UE Information Response message indicating the UE-side addition condition in a UE Information procedure. Specifically, if the received network-side addition condition is consistent with the UE-side addition condition, UE1 may report the UE-side addition condition to RAN node 2. On the other hand, if the received network-side addition condition is inconsistent with the UE-side addition condition, UE1 may operate not to report the UE-side addition condition to RAN node 2. These operations enable the UE 1 and the RAN node 2 to omit or skip the procedure of transmitting information indicating the UE side addition conditions from the UE 1 to the RAN node 2 if there is a contradiction between the network side addition conditions and the UE side addition conditions (e.g., if there is no common subset between the UE side addition conditions and the network side addition conditions).

[0080] Additionally or alternatively, based on or taking into consideration the received network-side additional conditions, the UE 1 may determine whether to send information indicating that the UE 1 supports the AI / ML model or the AI / ML function to the RAN node 2. The information may be transmitted via a UE Assistance Information message in the UE Assistance Information procedure, a UE Capability Information message in the UE capability transfer procedure, or a UE Information Response message in the UE Information procedure. Specifically, if the received network-side additional conditions are consistent with the UE-side additional conditions, the UE 1 may transmit the information (indicating that the UE 1 supports the AI / ML model or the AI / ML function) to the RAN node 2. On the other hand, if the received network-side additional conditions are consistent with the UE-side additional conditions, the UE 1 may operate not to report the information to the RAN node 2. These operations enable the UE 1 and the RAN node 2 to omit or skip the procedure of transmitting information indicating the UE-side additional conditions from the UE 1 to the RAN node 2 if there is a contradiction between the network-side additional conditions and the UE-side additional conditions (e.g., if there is no common subset between the UE-side additional conditions and the network-side additional conditions). Alternatively, these operations allow UE1 and RAN node 2 to omit or skip procedures for informing UE1 of other network-side addition conditions if there is a contradiction between the network-side addition conditions and the UE-side addition conditions (e.g., if there is no common subset between the UE-side addition conditions and the network-side addition conditions).

[0081] Additionally or alternatively, the UE1 may determine the content of the UE capability information to be transmitted to the RAN node 2 in the UE capability transfer procedure depending on whether the received network-side additional conditions conflict with the UE-side additional conditions. If the received network-side additional conditions do not conflict with the UE-side additional conditions, the UE1 may include information indicating the UE-side additional conditions in the UE capability information. Otherwise, the UE1 may not include the UE-side additional conditions in the UE capability information. Alternatively, if the received network-side additional conditions do not conflict with the UE-side additional conditions, the UE1 may include information indicating that the UE1 supports an AI / ML model or AI / ML functions in the UE capability information. Otherwise, the UE1 may not include information indicating that the UE1 supports an AI / ML model or AI / ML functions in the UE capability information. Alternatively, if the received network-side additional conditions conflict with the UE-side additional conditions, the UE1 may include information indicating that the received network-side additional conditions conflict with the UE-side additional conditions if the first additional condition conflicts with the second additional condition in the UE capability information. These operations enable the UE 1 and the RAN node 2 to omit or skip the procedure of transmitting information indicating the UE side addition condition from the UE 1 to the RAN node 2 if there is a contradiction between the network side addition condition and the UE side addition condition (e.g., if there is no common subset between the UE side addition condition and the network side addition condition). Alternatively, these operations enable the UE 1 and the RAN node 2 to omit or skip the procedure of informing the UE 1 of other network side addition conditions if there is a contradiction between the network side addition condition and the UE side addition condition (e.g., if there is no common subset between the UE side addition condition and the network side addition condition).

[0082] 3 shows an example of signaling between UE1 and RAN node 2. In step 301, RAN node 2 transmits information indicating one or more network-side additional conditions to UE1 via a broadcast within its cell (e.g., a System Information Block (SIB) broadcast). UE1 receives the information indicating one or more network-side additional conditions via a broadcast within its cell. As described above, the network-side additional conditions transmitted in step 301 may be at least a portion of a plurality of network-side additional conditions. At least a portion of the plurality of network-side additional conditions may be required conditions for applying, activating, or enabling a particular AI / ML model or AI / ML function. Details of the transmission in step 301 and the operations of UE1 and RAN node 2 based thereon have been described above.

[0083] FIG. 4 shows an example of the format of the SIB information element (IE) transmitted in step 301 of FIG. 3. The SIBxy IE shown in FIG. 4 may be any of the existing SIBs or a newly defined SIB for AI / ML. The SIBxy IE shown in FIG. 4 may include an additionalconditionAIML field or IE 401. The additionalconditionAIML field or IE 401 indicates the additionalconditionAIML field or IE 402. The additionalconditionAIML field or IE 402 indicates one or more additional network-side conditions. The additionalconditionAIML field or IE 402 may be an OCTET STRING type.

[0084] 5 shows an example of signaling between UE1 and RAN node 2. In step 501, RAN node 2 transmits information indicating one or more network-side addition conditions to UE1 via an RRCSetup message. UE1 receives the information indicating one or more network-side addition conditions via the RRCSetup message. If an RRC Resume procedure is performed instead of the RRC Setup procedure, RAN node 2 may transmit information indicating one or more network-side addition conditions via an RRCResume message in step 501, and UE1 may receive the information indicating these network-side addition conditions via the RRCResume message. In other words, RAN node 2 transmits information indicating one or more network-side addition conditions to UE1 via an RRCSetup or RRCResume message, which is transmitted in or accompanying the fourth message (MSG4) of the four-step random access procedure. Alternatively, the RAN node 2 sends one or more additional network side conditions to the UE 1 via an RRCSetup or RRCResume message sent in or accompanying the second message (MSG B) of the two-step random access procedure.

[0085] As described above, the network-side additional condition transmitted in step 501 may be at least a part of a plurality of network-side additional conditions, which may be essential conditions for applying, activating, or enabling a particular AI / ML model or AI / ML function. Details of the transmission of step 501 and the operations of the UE 1 and the RAN node 2 based thereon have been described above.

[0086] Figure 6 shows an example of the format of the RRCSetup message sent in step 501 of Figure 5. The RRCSetup message shown in Figure 6 includes an rrcSetup field or IE 601. The rrcSetup field or IE 601 includes an RRCSetup-IEs field or IE. The RRCSetup-IEs field or IE may include an additionalconditionAIML field or IE 602. The additionalconditionAIML field or IE 602 indicates an additionalconditionAIML field or IE 603. The additionalconditionAIML field or IE 603 ​​indicates one or more additional conditions on the network side. The additionalconditionAIML field or IE 603 ​​may be an OCTET STRING type.

[0087] As mentioned above, an RRCResume message may be used instead of an RRCSetup message for transmission in step 501. In this case, the RRCResume message may include, in its RRCResume-IEs field or IE, a field or IE similar to the additionalconditionAIML field or IE 602 shown in Fig. 6 .

[0088] 7 shows an example of signaling between UE1 and RAN node 2. In step 701, RAN node 2 sends information indicating one or more network-side additional conditions to UE1 via a UECapabilityEnquiry message. UE1 receives the information indicating one or more network-side additional conditions via the UECapabilityEnquiry message. The UECapabilityEnquiry message is sent in a UE capability transfer procedure. RAN node 2 can initiate a UE capability transfer procedure for UE1 in an RRC_CONNECTED state if (additional) UE radio access capability information is required. In the UE capability transfer procedure, RAN node 2 sends a UECapabilityEnquiry message. UE1 sends a UECapabilityInformation message to RAN node 2 according to the indication or request in the received UECapabilityEnquiry message.

[0089] As described above, the network-side additional condition transmitted in step 701 may be at least a part of a plurality of network-side additional conditions, which may be prerequisites for applying, activating, or enabling a particular AI / ML model or AI / ML function. Details of the transmission of step 701 and the operations of UE 1 and RAN node 2 based thereon have been described above.

[0090] Figure 8 shows an example of the format of the UECapabilityEnquiry message sent in step 701 of Figure 7. The UECapabilityEnquiry message shown in Figure 8 includes a ueCapabilityEnquiry field or IE 801. The ueCapabilityEnquiry field or IE 801 includes a UECapabilityEnquiry-IEs field or IE. The UECapabilityEnquiry-IEs field or IE may include an additionalconditionAIML field or IE 802. The additionalconditionAIML field or IE 802 indicates an additionalconditionAIML field or IE 803. The additionalconditionAIML field or IE 803 indicates one or more additional network-side conditions. The additionalconditionAIML field or IE 803 may be an OCTET STRING type.

[0091] Second Embodiment A configuration example of a wireless communication system according to this embodiment is similar to the configuration example described with reference to Figures 1 and 2. This embodiment provides details of signaling between a UE 1 and a RAN node 2 related to LCM of an AI / ML model or function.

[0092] In this embodiment, the UE 1 transmits information indicating one or more UE-side addition conditions to the RAN node 2 via an RRC Setup Complete message or an RRC Resume Complete message. The RAN node 2 receives information indicating one or more UE-side addition conditions from the UE 1 via an RRC Setup Complete message or an RRC Resume Complete message.

[0093] Alternatively, in this embodiment, UE1 transmits information indicating one or more UE-side addition conditions to RAN node 2 via a (first) Physical Uplink Control Channel (PUSCH) transmission in a four-step random access procedure or a two-step random access procedure. Specifically, UE1 transmits information indicating one or more UE-side addition conditions to RAN node 2 in or accompanying the third message (MSG3) of the four-step random access procedure, or in or accompanying the first message (MSG A) of the two-step random access procedure. RAN node 2 receives information indicating one or more UE-side addition conditions from UE1 in or accompanying the third message (MSG3) of the four-step random access procedure, or in or accompanying the first message (MSG A) of the two-step random access procedure.

[0094] Specifically, the UE 1 transmits the information to the RAN node 2 via a PUSCH, a MAC subheader, or an initial RRC message transmitted in or accompanying the third message of the four-step random access procedure or the first message of the two-step random access procedure. The initial RRC message is, for example, an RRC Setup Request message or an RRC Resume Request message.

[0095] The UE 1 may use a Logical Channel ID (LCID) field or an extended LCID (eLCID) field included in the MAC subheader to indicate information indicating one or more UE-side additional conditions to the RAN node 2. In this case, a value, index, or codepoint of the LCID or eLCID associated with each of the one or more UE-side additional conditions may be defined.

[0096] In other words, the UE1 notifies the RAN node 2 of at least some of the UE-side additional conditions before a procedure for notifying the UE of information indicating other UE-side additional conditions (e.g., a UE Assistance Information procedure or a UE Information procedure). Alternatively, the UE1 notifies the RAN node 2 of at least some of the UE-side additional conditions before a procedure for receiving information indicating network-side additional conditions from the network (e.g., an RRC Reconfiguration procedure, a UE Assistance Information procedure, or a UE Information procedure). At least some of the UE-side additional conditions may be mandatory conditions for applying, activating, or enabling a specific AI / ML model or AI / ML function. The remaining UE-side additional conditions may be preferred conditions (conditions that can be adjusted or omitted) that can be optionally used for applying, activating, or enabling a specific AI / ML model or AI / ML function.

[0097] In some implementations, the RAN node 2 may determine whether to request the UE 1 to transmit information indicating other UE-side additional conditions based on information received from the UE 1 indicating one or more UE-side additional conditions. The other UE-side additional conditions may be transmitted in a UE Assistance Information procedure, a UE capability transfer procedure, or a UE Information procedure. In other words, the other UE-side additional conditions may be transmitted via a UEAssistanceInformation message, a UECapabilityInformation message, or a UEInformationResponse message. Specifically, if the UE-side additional conditions reported by the UE 1 are consistent with the network-side additional conditions, the RAN node 2 may request the UE 1 to transmit information indicating the other UE-side additional conditions. On the other hand, if the UE-side additional conditions reported by the UE 1 are inconsistent with the network-side additional conditions, the RAN node 2 may operate not to request the UE 1 to transmit information indicating the other UE-side additional conditions. These operations allow the UE 1 and the RAN node 2 to omit or skip the procedure for informing the RAN node 2 of other UE side addition conditions if there is a contradiction between the UE side addition conditions and the network side addition conditions (e.g., if there is no common subset between the UE side addition conditions and the network side addition conditions).

[0098] 9 shows an example of signaling between UE1 and RAN node 2. In step 901, UE1 transmits information indicating one or more UE-side addition conditions to RAN node 2 via an RRCSetupComplete message. RAN node 2 receives the information indicating one or more UE-side addition conditions via the RRCSetupComplete message. If an RRC Resume procedure is performed instead of the RRC Setup procedure, UE1 may transmit information indicating one or more UE-side addition conditions via an RRCResumeComplete message in step 901, and RAN node 2 may receive the information indicating these UE-side addition conditions via the RRCResumeComplete message. In other words, RAN node 2 transmits information indicating one or more UE-side addition conditions to RAN node 2 via an RRCSetupComplete or RRCResumeComplete message, which is transmitted after the fourth message (MSG4) of the four-step random access procedure.

[0099] As described above, the UE-side additional condition transmitted in step 901 may be at least a part of a plurality of UE-side additional conditions, which may be prerequisites for applying, activating, or enabling a particular AI / ML model or AI / ML function. Details of the transmission of step 901 and the operations of the UE 1 and the RAN node 2 based thereon are as described above.

[0100] The operations of the UE 1 and the RAN node 2 described with reference to Fig. 9 can be appropriately combined with the operations of the UE 1 and the RAN node 2 described in the first embodiment. Specifically, for example, the UE 1 may transmit an RRCSetupComplete message in step 901 as a response to the RRCSetup message in the first embodiment (e.g., step 501 in Fig. 5). That is, the UE 1 may receive an RRCSetup message including information indicating one or more network-side addition conditions from the RAN node 2, and then transmit an RRCSetupComplete message including information indicating one or more UE-side addition conditions.

[0101] Figure 10 shows an example of the format of the RRCSetupComplete message sent in step 901 of Figure 9. The RRCSetupComplete message shown in Figure 10 may include an rrcSetupComplete field or IE 1001. The rrcSetupComplete field or IE 1001 includes an RRCSetupComplete-IEs field or IE. The RRCSetupComplete-IEs field or IE may include an additionalconditionAIML field or IE 1002. The additionalconditionAIML field or IE 1002 indicates an additionalconditionAIML field or IE 1003. The additionalconditionAIML field or IE 1003 indicates one or more additional conditions on the UE side. The additionalconditionAIML field or IE 1003 may be an OCTET STRING type.

[0102] As described above, an RRCResumeComplete message may be used instead of an RRCSetupComplete message for transmission in step 901. In this case, the RRCResumeComplete message may include, in its RRCResumeComplete-IEs field or IE, a field or IE similar to the additionalconditionAIML field or IE 1002 shown in Fig. 9 .

[0103] 11 shows an example of signaling between UE1 and RAN node 2. In step 1101, UE1 transmits information indicating one or more UE-side addition conditions to RAN node 2 via the third message of the four-step random access procedure, i.e., scheduled PUSCH transmission (MSG3). RAN node 2 receives the information indicating one or more UE-side addition conditions via the scheduled PUSCH transmission (MSG3). If a two-step random access procedure is used instead of the four-step random access procedure, UE1 may also transmit information indicating one or more UE-side addition conditions to RAN node 2 via a PUSCH transmission in the first message (MSG A) in step 1101.

[0104] As described above, the UE-side additional condition transmitted in step 1101 may be at least a part of a plurality of UE-side additional conditions, which may be essential conditions for applying, activating, or enabling a particular AI / ML model or AI / ML function. Details of the transmission of step 1101 and the operations of the UE 1 and the RAN node 2 based thereon are as described above.

[0105] The operations of the UE1 and the RAN node 2 described with reference to Figure 11 can be appropriately combined with the operations of the UE1 and the RAN node 2 described in the first embodiment. Specifically, for example, the UE1 may transmit the scheduled PUSCH transmission in step 1101 in response to or based on receiving an SIB broadcast (e.g., step 301 in Figure 3) in the first embodiment. That is, the UE1 may transmit a scheduled PUSCH transmission including information indicating one or more UE-side addition conditions after receiving an SIB broadcast including information indicating one or more network-side addition conditions from the RAN node 2.

[0106] Next, exemplary configurations of a UE 1 and a RAN node 2 related to the above-described embodiments will be described. FIG. 12 is a block diagram showing an exemplary configuration of a UE 1. An RF transceiver 1201 performs analog RF signal processing for communication with a RAN node 2. The RF transceiver 1201 may include multiple transceivers. The analog RF signal processing performed by the RF transceiver 1201 includes frequency up-conversion, frequency down-conversion, and amplification. The RF transceiver 1201 is coupled to an antenna array 1202 and a baseband processor 1203. The RF transceiver 1201 receives modulation symbol data (or orthogonal frequency-division multiplexing (OFDM) symbol data) from the baseband processor 1203, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 1202. The RF transceiver 1201 also generates a baseband receive signal based on the receive RF signal received by the antenna array 1202 and provides the baseband receive signal to the baseband processor 1203. The RF transceiver 1201 may include an analog beamformer circuit for beamforming, which may include, for example, multiple phase shifters and multiple power amplifiers.

[0107] The baseband processor 1203 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communications. Digital baseband signal processing includes (a) data compression / decompression, (b) data segmentation / concatenation, (c) transmission format (transmission frame) generation / decomposition, (d) transmission path coding / decoding, (e) modulation (symbol mapping) / demodulation, and (f) generation of OFDM symbol data (baseband OFDM signal) using Inverse Fast Fourier Transform (IFFT). Meanwhile, control plane processing includes communication management for Layer 1 (e.g., transmit power control), Layer 2 (e.g., radio resource management and hybrid automatic repeat request (HARQ) processing), and Layer 3 (e.g., signaling related to attachment, mobility, and call management).

[0108] For example, the digital baseband signal processing by the baseband processor 1203 may include signal processing of a PDCP layer, an RLC layer, a MAC layer, and a PHY layer. Also, the control plane processing by the baseband processor 1203 may include processing of a Non-Access Stratum (NAS) protocol, an RRC protocol, MAC CEs, and Downlink Control Information (DCIs).

[0109] The baseband processor 1203 may perform multiple-input multiple-output (MIMO) encoding and precoding for beamforming.

[0110] The baseband processor 1203 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a Central Processing Unit (CPU) or a Micro Processing Unit (MPU)) that performs control plane processing. In this case, the protocol stack processor that performs control plane processing may be shared with the application processor 1204, which will be described later.

[0111] The application processor 1204 is also referred to as a CPU, MPU, microprocessor, or processor core. The application processor 1204 may include multiple processors (multiple processor cores). The application processor 1204 executes a system software program (operating system (OS)) and various application programs (e.g., a calling application, a web browser, a mailer, a camera operation application, and a music playback application) read from the memory 1206 or other memories, thereby realizing various functions of the UE 1.

[0112] In some implementations, the baseband processor 1203 and the application processor 1204 may be integrated on a single chip, as indicated by the dashed line (1205) in Figure 12. In other words, the baseband processor 1203 and the application processor 1204 may be implemented as a single System on Chip (SoC) device 1205. An SoC device is sometimes called a system Large Scale Integration (LSI) or chipset.

[0113] The memory 1206 is volatile memory, nonvolatile memory, or a combination thereof. The memory 1206 may include multiple physically independent memory devices. The volatile memory may be, for example, static random access memory (SRAM), dynamic RAM (DRAM), or a combination thereof. The nonvolatile memory may be mask read only memory (MROM), electrically erasable programmable ROM (EEPROM), flash memory, a hard disk drive, or any combination thereof. For example, the memory 1206 may include an external memory device accessible from the baseband processor 1203, the application processor 1204, and the SoC 1205. The memory 1206 may also include an internal memory device integrated within the baseband processor 1203, the application processor 1204, or the SoC 1205. Furthermore, the memory 1206 may include memory within a Universal Integrated Circuit Card (UICC).

[0114] The memory 1206 may store one or more software modules (computer programs) 1207 containing instructions and data for processing by the UE 1. In some implementations, the baseband processor 1203 or the application processor 1204 may be configured to read and execute the software modules 1207 from the memory 1206 to perform the processing of the UE 1 described in one or more of the embodiments.

[0115] It should be noted that the control plane processing and operations performed by UE 1 described in the above embodiment can be realized by elements other than the RF transceiver 1201 and the antenna array 1202, namely, at least one of the baseband processor 1203 and the application processor 1204, and the memory 1206 storing the software module 1207.

[0116] FIG. 13 is a block diagram showing an example configuration of a RAN node 2. Referring to FIG. 13, the RAN node 2 includes an RF transceiver 1301, a network interface 1303, a processor 1304, and a memory 1305. The RF transceiver 1301 performs analog RF signal processing for communication with UEs 1. The RF transceiver 1301 may include multiple transceivers. The RF transceiver 1301 is coupled to an antenna array 1302 and a processor 1304. The RF transceiver 1301 receives modulation symbol data from the processor 1304, generates a transmit RF signal, and provides the transmit RF signal to the antenna array 1302. The RF transceiver 1301 also generates a baseband receive signal based on the receive RF signal received by the antenna array 1302 and provides the baseband receive signal to the processor 1304. The RF transceiver 1301 may include an analog beamformer circuit for beamforming. The analog beamformer circuit may include, for example, multiple phase shifters and multiple power amplifiers.

[0117] The network interface 1303 is used to communicate with network nodes (e.g., other RAN nodes, and control and forwarding nodes of the core network), and may include, for example, a network interface card (NIC) compliant with the IEEE 802.3 series.

[0118] The processor 1304 performs digital baseband signal processing (data plane processing) and control plane processing for wireless communication. The processor 1304 may include multiple processors. For example, the processor 1304 may include a modem processor (e.g., a Digital Signal Processor (DSP)) that performs digital baseband signal processing and a protocol stack processor (e.g., a CPU or MPU) that performs control plane processing. The processor 1304 may include a digital beamformer module for beamforming. The digital beamformer module may include a MIMO encoder and a precoder.

[0119] The memory 1305 is configured by a combination of volatile memory and non-volatile memory. The volatile memory is, for example, SRAM or DRAM, or a combination thereof. The non-volatile memory is, for example, MROM, EEPROM, flash memory, or a hard disk drive, or any combination thereof. The memory 1305 may include storage located remotely from the processor 1304. In this case, the processor 1304 may access the memory 1305 via the network interface 1303 or other I / O interface.

[0120] The memory 1305 may store one or more software modules (computer programs) 1306 containing instructions and data for processing by the RAN node 2. In some implementations, the processor 1304 may be configured to read and execute the software modules 1306 from the memory 1305 to perform the processing of the RAN node 2 described in one or more of the embodiments.

[0121] It should be noted that the control plane processing and operations performed by the RAN node 2 described in the above embodiment can be realized by elements other than the RF transceiver 1301 and the antenna array 1302, namely the processor 1304 and the memory 1305 storing the software module 1306.

[0122] As described with reference to Figures 12 and 13, each of the processors included in the UE 1 and the RAN node 2 according to the above-described embodiments may execute one or more programs including instructions for causing a computer to perform the algorithms described with reference to the drawings. The programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disk (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0123] The above-described embodiments are merely examples of application of the technical ideas obtained by the inventors of the present invention. In other words, the technical ideas are not limited to the above-described embodiments, and various modifications are possible.

[0124] For example, 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 devices (e.g., wireless terminals, RAN nodes) may naturally also be described as appendices directed to methods and programs. For example, some or all of the elements described in appendices 2-19, which are dependent on appendices 1, may also be described as appendices dependent on appendices 20 and 21, due to the same dependency relationship as appendices 2-19. Similarly, some or all of the elements described in appendices 23-40, which are dependent on appendices 23-40, may also be described as appendices dependent on appendices 41 and 42, due to the same dependency relationship as appendices 23-40. Some or all of the elements described in any appendice may be applicable to various hardware, software, recording means for recording software, systems, and methods.

[0125] (Supplementary Note 1) A radio terminal comprising: means for receiving, from a radio access network node via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, first information indicating a first additional condition on a network side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality. (Supplementary Note 2) The radio terminal of Supplementary Note 1, comprising means for transmitting feedback generated based on reception of the first information to the radio access network node, the feedback informing the radio access network node whether the first additional condition conflicts with a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML functionality. (Supplementary Note 3) The radio terminal of Supplementary Note 2, wherein the feedback is used by the radio access network node to determine whether to request the radio terminal to transmit second information indicating a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML functionality. (Supplementary Note 4) The wireless terminal according to Supplementary Note 2 or 3, wherein the receiving means is configured to receive the first information via the broadcast, and the transmitting means is configured to transmit the feedback via an RRC Setup Request message, an RRC Setup Complete message, an RRC Resume Request message, or an RRC Resume Complete message. (Supplementary Note 5) The wireless terminal according to Supplementary Note 2 or 3, wherein the receiving means is configured to receive the first information via the RRC Setup message or the RRC Resume message, and the transmitting means is configured to transmit the feedback via an RRC Setup Complete message or an RRC Resume Complete message.(Supplementary Note 6) The radio terminal according to Supplementary Note 2 or 3, wherein the receiving means is configured to receive the first information via the UE Capability Enquiry message, and the transmitting means is configured to transmit the feedback via a UE Capability Information message. (Supplementary Note 7) The radio terminal according to Supplementary Note 1, further comprising: means for determining whether to perform an operation of reporting a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function to the radio access network node, taking the first additional condition into consideration. (Supplementary Note 8) The radio terminal according to Supplementary Note 7, wherein the reporting operation includes transmitting a UE Assistance Information message indicating the second additional condition in a UE Assistance Information procedure, transmitting a UE Capability Information message indicating the second additional condition in a UE capability transfer procedure, or transmitting a UE Information Response message indicating the second additional condition in a UE Information procedure. (Supplementary Note 9) The wireless terminal according to Supplementary Note 7 or 8, wherein the determining means is configured to: report the second additional condition to the radio access network node if the first additional condition does not contradict the second additional condition, and not report the second additional condition to the radio access network node if the first additional condition contradicts the second additional condition. (Supplementary Note 10) The wireless terminal according to Supplementary Note 1, further comprising: means for determining whether to send third information indicating that the wireless terminal supports the AI / ML model or the AI / ML function to the radio access network node, taking into account the first additional condition.(Supplementary Note 11) The radio terminal according to Supplementary Note 10, wherein the third information is transmitted via a UE Assistance Information message in a UE Assistance Information procedure, a UE Capability Information message in a UE capability transfer procedure, or a UE Information Response message in a UE Information procedure. (Supplementary Note 12) The radio terminal according to Supplementary Note 10 or 11, wherein the determining means is configured to: transmit the third information to the radio access network node if the first additional condition does not contradict a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function, and not report the third information to the radio access network node if the first additional condition contradicts the second additional condition. (Supplementary Note 13) The radio terminal according to Supplementary Note 1, further comprising: means for determining content of UE capability information to be transmitted to the radio access network node in a UE capability transfer procedure, depending on whether the first additional condition contradicts a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function. (Supplementary Note 14) The wireless terminal according to Supplementary Note 13, wherein the determining means is configured to: include the second additional condition in the UE capability information if the first additional condition does not contradict the second additional condition; and not include the second additional condition in the UE capability information if the first additional condition contradicts the second additional condition.(Supplementary Note 15) The radio terminal according to Supplementary Note 13, wherein the determining means is configured to: include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function if the first additional condition does not contradict the second additional condition; and not include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function if the first additional condition contradicts the second additional condition. (Supplementary Note 16) The radio terminal according to Supplementary Note 13, wherein, if the first additional condition contradicts the second additional condition, the determining means is configured to include, in the UE capability information, information indicating that the first additional condition contradicts the second additional condition. (Supplementary Note 17) The radio terminal according to any one of Supplements 1 to 16, wherein the first additional condition is taken into consideration for determining whether the AI / ML model or the AI / ML function is applicable. (Supplementary Note 18) The wireless terminal according to any one of Supplements 1 to 17, wherein the first additional condition includes one or more conditions that are used to train the AI / ML model and that need to be consistent in inference by the AI / ML model. (Supplementary Note 19) The AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; an ordering of the first set and the second set; a Quasi Co-Location (QCL) relationship between the first set and the second set; or beam shapes of the first set and the second set.(Supplementary Note 20) A method performed by a wireless terminal, comprising receiving, from a radio access network node via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality. (Supplementary Note 21) A program causing a computer to perform a method for a wireless terminal, comprising receiving, from a radio access network node via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality. (Supplementary Note 22) A radio access network node comprising: means for transmitting, to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, first information indicating a first additional condition on the network side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.(Supplementary Note 23) The radio access network node according to Supplementary Note 22, comprising: means for receiving from the radio terminal feedback generated based on reception of the first information, the feedback informing the radio access network node whether the first additional condition conflicts with a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function. (Supplementary Note 24) The radio access network node according to Supplementary Note 23, further comprising means for determining, using the feedback, whether to request the radio terminal to transmit second information indicating a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function. (Supplementary Note 25) The radio access network node according to Supplementary Note 23 or 24, wherein the transmitting means is configured to transmit the first information via the broadcast, and the receiving means is configured to receive the feedback via an RRC Setup Request message, an RRC Setup Complete message, an RRC Resume Request message, or an RRC Resume Complete message. (Supplementary Note 26) The radio access network node according to Supplementary Note 23 or 24, wherein the transmitting means is configured to transmit the first information via the RRC Setup message or the RRC Resume message, and the receiving means is configured to receive the feedback via an RRC Setup Complete message or an RRC Resume Complete message. (Supplementary Note 27) The radio access network node according to Supplementary Note 23 or 24, wherein the transmitting means is configured to transmit the first information via the UE Capability Enquiry message, and the receiving means is configured to receive the feedback via a UE Capability Information message.(Supplementary Note 28) The radio access network node according to Supplementary Note 22, wherein the first information causes the radio terminal to decide whether to perform an operation of reporting a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function to the radio access network node, taking the first additional condition into consideration. (Supplementary Note 29) The radio access network node according to Supplementary Note 28, wherein the operation of reporting includes transmitting a UE Assistance Information message indicating the second additional condition in a UE Assistance Information procedure, transmitting a UE Capability Information message indicating the second additional condition in a UE capability transfer procedure, or transmitting a UE Information Response message indicating the second additional condition in a UE Information procedure. (Supplementary Note 30) The radio access network node according to Supplementary Note 28 or 29, wherein the first information causes the radio terminal to report the second additional condition to the radio access network node if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal to not report the second additional condition to the radio access network node if the first additional condition contradicts the second additional condition. (Supplementary Note 31) The radio access network node according to Supplementary Note 22, wherein the first information causes the radio terminal to decide whether to send third information indicating that the radio terminal supports the AI / ML model or the AI / ML function to the radio access network node, taking into account the first additional condition.(Supplementary Note 32) The radio access network node according to Supplementary Note 31, wherein the third information is transmitted via a UE Assistance Information message in a UE Assistance Information procedure, a UE Capability Information message in a UE capability transfer procedure, or a UE Information Response message in a UE Information procedure. (Supplementary Note 33) The radio access network node according to Supplementary Note 31 or 32, wherein the first information causes the radio terminal to transmit the third information to the radio access network node if the first additional condition does not contradict a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function, and the first information causes the radio terminal not to report the third information to the radio access network node if the first additional condition contradicts the second additional condition. (Supplementary Note 34) The radio access network node according to Supplementary Note 22, wherein the first information causes the radio terminal to determine content of UE capability information to be transmitted to the radio access network node in a UE capability transfer procedure depending on whether the first additional condition contradicts a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function. (Supplementary Note 35) The radio access network node according to Supplementary Note 34, wherein the first information causes the radio terminal to include the second additional condition in the UE capability information if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal to not include the second additional condition in the UE capability information if the first additional condition contradicts the second additional condition.(Supplementary Note 36) The radio access network node according to Supplementary Note 34, wherein the first information causes the radio terminal to include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function, if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal not to include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function, if the first additional condition contradicts the second additional condition. (Supplementary Note 37) The radio access network node according to Supplementary Note 34, wherein the first information causes the radio terminal to include, in the UE capability information, information indicating that the first additional condition contradicts the second additional condition, if the first additional condition contradicts the second additional condition. (Supplementary Note 38) The radio access network node according to any one of Supplements 22 to 37, wherein the first additional condition is taken into consideration for determining whether the AI / ML model or the AI / ML function is applicable. (Supplementary Note 39) The radio access network node according to any one of Supplements 22 to 38, wherein the first additional condition includes one or more conditions that are used to train the AI / ML model and that need to be consistent in inference by the AI / ML model. (Supplementary Note 40) The AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; an ordering of the first set and the second set; a Quasi Co-Location (QCL) relationship between the first set and the second set; or beam shapes of the first set and the second set.(Supplementary Note 41) A method performed by a radio access network node, comprising: transmitting a first additional condition on the network side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message. (Supplementary Note 42) A program causing a computer to perform a method for a radio access network node, comprising: transmitting a first additional condition on the network side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message. (Supplementary Note 43) A radio terminal comprising: means for transmitting, to a radio access network node, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure. (Supplementary Note 44) The radio terminal of Supplementary Note 43, wherein the first information is used by the radio access network node to decide whether to request the radio terminal to transmit second information indicating other additional conditions on the radio terminal side.(Supplementary Note 45) The radio terminal according to Supplementary Note 44, wherein the first information causes the radio access network node to request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information does not contradict an additional condition on the network side for activating or enabling the AI / ML model or the AI / ML function, and the first information causes the radio access network node to not request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information contradicts an additional condition on the network side. (Supplementary Note 46) The radio terminal according to Supplementary Note 44 or 45, wherein the second information is transmitted in a UE Assistance Information procedure, a UE capability transfer procedure, or a UE Information procedure. (Supplementary Note 47) The radio terminal according to any one of Supplements 43 to 46, wherein the transmitting means is configured to transmit the first information via the PUSCH transmission in the random access procedure. (Supplementary Note 48) The radio terminal according to Supplementary Note 47, wherein the first information is included in a Logical Channel ID (LCID) field or an extended LCID (eLCID) field included in the PUSCH transmission. (Supplementary Note 49) The radio terminal according to any one of Supplements 43 to 48, wherein the additional condition on the radio terminal side is taken into consideration to determine whether the AI / ML model or the AI / ML function is applicable. (Supplementary Note 50) The radio terminal according to any one of Supplements 43 to 49, wherein the additional condition on the radio terminal side includes one or more conditions used for training the AI / ML model and which need to ensure consistency in inference with the AI / ML model.(Supplementary Note 51) The radio terminal according to Supplementary Note 50, wherein the AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; an order of leasing the first set and the second set; a Quasi Co-Location (QCL) relationship between the first set and the second set; or beam shapes of the first set and the second set. (Supplementary Note 52) A method performed by a radio terminal, comprising transmitting, to a radio access network node, first information indicating an additional condition on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure. (Supplementary Note 53) A program causing a computer to perform a method for a wireless terminal, comprising: transmitting, to a radio access network node, first information indicating additional conditions on the wireless terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.(Supplementary Note 54) A radio access network node comprising: means for receiving, from a radio terminal, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure. (Supplementary Note 55) The radio access network node according to Supplementary Note 54, further comprising means for determining whether to request the radio terminal to transmit second information indicating other additional conditions on the radio terminal side, using the first information. (Supplementary Note 56) The radio access network node according to Supplementary Note 55, wherein the determining means is configured to: request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information does not contradict an additional condition on the network side for activating or enabling the AI / ML model or the AI / ML function, and not request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information contradicts an additional condition on the network side. (Supplementary Note 57) The radio access network node according to Supplementary Note 55 or 56, wherein the second information is transmitted in a UE Assistance Information procedure, a UE capability transfer procedure, or a UE Information procedure. (Supplementary Note 58) The radio access network node according to any one of claims 54 to 57, wherein the receiving means is configured to receive the first information via the PUSCH transmission in the random access procedure. (Supplementary Note 59) The radio access network node according to claim 58, wherein the first information is included in a Logical Channel ID (LCID) field or an extended LCID (eLCID) field included in the PUSCH transmission.(Supplementary Note 60) The radio access network node according to any one of Supplements 54 to 59, wherein the additional condition on the radio terminal side is taken into consideration to determine whether the AI / ML model or the AI / ML function is applicable. (Supplementary Note 61) The radio access network node according to any one of Supplements 54 to 60, wherein the additional condition on the radio terminal side includes one or more conditions that are used for training the AI / ML model and that need to be consistent in inference by the AI / ML model. (Supplementary Note 62) The AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; an ordering of the first set and the second set; a Quasi Co-Location (QCL) relationship between the first set and the second set; or beam shapes of the first set and the second set. (Supplementary Note 63) A method performed by a radio access network node, comprising receiving, from a radio terminal, via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.(Supplementary Note 64) A program causing a computer to perform a method for a radio access network node, comprising: receiving, from a radio terminal, via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

[0126] This application claims priority based on Japanese Patent Application No. 2024-035473, filed March 8, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0127] 1 UE 2 RAN node 3 RAN controller 201 CU 211, 212 DU 231-235 TRP 241-243 Cell 1103 Baseband processor 1104 Application processor 1106 Memory 1107 Modules 1204 Processor 1205 Memory 1206 Modules

Claims

1. A wireless terminal comprising: means for receiving, from a radio access network node via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, first information indicating a network-side first additional condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

2. The wireless terminal of claim 1, further comprising: means for transmitting feedback to the radio access network node generated based on receipt of the first information, the feedback informing the radio access network node whether the first additional condition conflicts with a second additional condition on the wireless terminal side for activating or enabling the AI / ML model or the AI / ML function.

3. The wireless terminal of claim 2, wherein the feedback is used by the radio access network node to determine whether to request the wireless terminal to transmit second information indicating a second additional condition on the wireless terminal side for activating or enabling the AI / ML model or the AI / ML function.

4. The wireless terminal according to claim 2 or 3, wherein the receiving means is configured to receive the first information via the broadcast, and the transmitting means is configured to transmit the feedback via an RRC Setup Request message, an RRC Setup Complete message, an RRC Resume Request message, or an RRC Resume Complete message.

5. The radio terminal according to claim 2 or 3, wherein the receiving means is configured to receive the first information via the RRC Setup message or the RRC Resume message, and the transmitting means is configured to transmit the feedback via an RRC Setup Complete message or an RRC Resume Complete message.

6. The wireless terminal according to claim 2 or 3, wherein the receiving means is configured to receive the first information via the UE Capability Enquiry message, and the transmitting means is configured to transmit the feedback via a UE Capability Information message.

7. The wireless terminal of claim 1, further comprising: means for determining whether to perform an operation of reporting a second additional condition on the wireless terminal side for activating or enabling the AI / ML model or the AI / ML function to the radio access network node, taking into account the first additional condition.

8. The wireless terminal according to claim 7, wherein the reporting operation includes transmitting a UE Assistance Information message indicating the second additional condition in a UE Assistance Information procedure, transmitting a UE Capability Information message indicating the second additional condition in a UE capability transfer procedure, or transmitting a UE Information Response message indicating the second additional condition in a UE Information procedure.

9. The radio terminal according to claim 7 or 8, wherein the determining means is configured to: report the second additional condition to the radio access network node if the first additional condition does not contradict the second additional condition; and not report the second additional condition to the radio access network node if the first additional condition contradicts the second additional condition.

10. The wireless terminal of claim 1, further comprising: means for determining whether to send third information indicating that the wireless terminal supports the AI / ML model or the AI / ML function to the radio access network node, taking into account the first additional condition.

11. The wireless terminal according to claim 10, wherein the third information is transmitted via a UE Assistance Information message in a UE Assistance Information procedure, a UE Capability Information message in a UE capability transfer procedure, or a UE Information Response message in a UE Information procedure.

12. The wireless terminal according to claim 10 or 11, wherein the determining means is configured to: transmit the third information to the radio access network node if the first additional condition does not contradict a second additional condition on the wireless terminal side for activating or enabling the AI / ML model or the AI / ML function; and not report the third information to the radio access network node if the first additional condition contradicts the second additional condition.

13. The wireless terminal of claim 1, further comprising: means for determining content of UE capability information to be transmitted to the radio access network node in a UE capability transfer procedure depending on whether the first additional condition contradicts a second additional condition on the wireless terminal side for activating or enabling the AI / ML model or the AI / ML function.

14. The wireless terminal according to claim 13, wherein the determining means is configured to: include the second additional condition in the UE capability information if the first additional condition does not contradict the second additional condition; and not include the second additional condition in the UE capability information if the first additional condition contradicts the second additional condition.

15. The wireless terminal according to claim 13, wherein the determining means is configured to: if the first additional condition does not contradict the second additional condition, include information indicating that the wireless terminal supports the AI / ML model or the AI / ML function in the UE capability information; and if the first additional condition contradicts the second additional condition, not include information indicating that the wireless terminal supports the AI / ML model or the AI / ML function in the UE capability information.

16. The wireless terminal according to claim 13, wherein the determining means is configured to, if the first additional condition conflicts with the second additional condition, include information indicating that the first additional condition conflicts with the second additional condition in the UE capability information.

17. The wireless terminal according to any one of claims 1 to 16, wherein the first additional condition is taken into account to determine whether the AI / ML model or the AI / ML function is applicable.

18. The wireless terminal according to any one of claims 1 to 17, wherein the first additional condition includes one or more conditions that are used in training the AI / ML model and that must be consistent in inference using the AI / ML model.

19. The wireless terminal of claim 18, wherein the AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; the order of allocation of the first set and the second set; the Quasi Co-Location (QCL) relationship of the first set with respect to the second set; or the beam shapes of the first set and the second set.

20. A method performed by a wireless terminal, comprising receiving a network-side first additional condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality from a radio access network node via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message.

21. A program causing a computer to perform a method for a wireless terminal, comprising: receiving, from a radio access network node, via a cell broadcast, via an RRC Setup message, via an RRC Resume message, or via a UE Capability Enquiry message, a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

22. A radio access network node comprising: means for transmitting, to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message, first information indicating a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

23. The radio access network node of claim 22, further comprising: means for receiving feedback from the radio terminal generated based on receipt of the first information, the feedback informing the radio access network node whether the first additional condition conflicts with a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function.

24. The radio access network node of claim 23, further comprising: means for determining, using the feedback, whether to request the radio terminal to transmit second information indicating a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function.

25. A radio access network node according to claim 23 or 24, wherein the transmitting means is configured to transmit the first information via the broadcast, and the receiving means is configured to receive the feedback via an RRC Setup Request message, an RRC Setup Complete message, an RRC Resume Request message, or an RRC Resume Complete message.

26. A radio access network node according to claim 23 or 24, wherein the transmitting means is configured to transmit the first information via the RRC Setup message or the RRC Resume message, and the receiving means is configured to receive the feedback via an RRC Setup Complete message or an RRC Resume Complete message.

27. A radio access network node according to claim 23 or 24, wherein the transmitting means is configured to transmit the first information via the UE Capability Enquiry message, and the receiving means is configured to receive the feedback via a UE Capability Information message.

28. The radio access network node according to claim 22, wherein the first information causes the radio terminal to decide, taking into account the first additional condition, whether to perform an operation of reporting a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function to the radio access network node.

29. The radio access network node according to claim 28, wherein the reporting operation comprises: transmitting a UE Assistance Information message indicating the second additional condition in a UE Assistance Information procedure; transmitting a UE Capability Information message indicating the second additional condition in a UE capability transfer procedure; or transmitting a UE Information Response message indicating the second additional condition in a UE Information procedure.

30. A radio access network node according to claim 28 or 29, wherein the first information causes the radio terminal to report the second additional condition to the radio access network node if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal not to report the second additional condition to the radio access network node if the first additional condition contradicts the second additional condition.

31. The radio access network node of claim 22, wherein the first information causes the radio terminal to decide, taking into account the first additional condition, whether to send third information to the radio access network node indicating that the radio terminal supports the AI / ML model or the AI / ML function.

32. The radio access network node according to claim 31, wherein the third information is transmitted via a UE Assistance Information message in a UE Assistance Information procedure, a UE Capability Information message in a UE capability transfer procedure, or a UE Information Response message in a UE Information procedure.

33. The radio access network node according to claim 31 or 32, wherein the first information causes the radio terminal to transmit the third information to the radio access network node if the first additional condition does not contradict a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function, and the first information causes the radio terminal not to report the third information to the radio access network node if the first additional condition contradicts the second additional condition.

34. The radio access network node according to claim 22, wherein the first information causes the radio terminal to determine the content of UE capability information to be transmitted to the radio access network node in a UE capability transfer procedure depending on whether the first additional condition contradicts a second additional condition on the radio terminal side for activating or enabling the AI / ML model or the AI / ML function.

35. The radio access network node according to claim 34, wherein the first information causes the radio terminal to include the second additional condition in the UE capability information if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal not to include the second additional condition in the UE capability information if the first additional condition contradicts the second additional condition.

36. The radio access network node of claim 34, wherein the first information causes the radio terminal to include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function, if the first additional condition does not contradict the second additional condition, and the first information causes the radio terminal not to include, in the UE capability information, information indicating that the radio terminal supports the AI / ML model or the AI / ML function, if the first additional condition contradicts the second additional condition.

37. The radio access network node according to claim 34, wherein the first information causes the radio terminal to include, if the first additional condition contradicts the second additional condition, information indicating that the first additional condition contradicts the second additional condition in the UE capability information.

38. A radio access network node according to any one of claims 22 to 37, wherein the first additional condition is taken into account to determine whether the AI / ML model or the AI / ML function is applicable.

39. A radio access network node according to any one of claims 22 to 38, wherein the first additional condition includes one or more conditions that are used in training the AI / ML model and that need to be consistent in inference by the AI / ML model.

40. The radio access network node of claim 39, wherein the AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; the leasing order of the first set and the second set; the Quasi Co-Location (QCL) relationship of the first set with respect to the second set; or the beam shapes of the first set and the second set.

41. A method performed by a radio access network node, comprising: transmitting a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message.

42. A program causing a computer to perform a method for a radio access network node, comprising: transmitting a first additional network-side condition for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio terminal via a cell broadcast, an RRC Setup message, an RRC Resume message, or a UE Capability Enquiry message.

43. A radio terminal comprising: means for transmitting first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio access network node via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.

44. The wireless terminal of claim 43, wherein the first information is used by the radio access network node to determine whether to request the wireless terminal to transmit second information indicating other additional conditions on the part of the wireless terminal.

45. The wireless terminal of claim 44, wherein the first information causes the radio access network node to request the wireless terminal to transmit the second information if the additional conditions on the wireless terminal side reported in the first information do not contradict additional conditions on the network side for activating or enabling the AI / ML model or the AI / ML function, and the first information causes the radio access network node not to request the wireless terminal to transmit the second information if the additional conditions on the wireless terminal side reported in the first information contradict additional conditions on the network side.

46. ​​The radio terminal according to claim 44 or 45, wherein the second information is transmitted in a UE Assistance Information procedure, a UE capability transfer procedure, or a UE Information procedure.

47. A radio terminal according to any one of claims 43 to 46, wherein the transmitting means is configured to transmit the first information via the PUSCH transmission in the random access procedure.

48. The wireless terminal of claim 47, wherein the first information is included in a Logical Channel ID (LCID) field or an extended LCID (eLCID) field included in the PUSCH transmission.

49. A wireless terminal according to any one of claims 43 to 48, wherein the additional conditions on the wireless terminal side are taken into account to determine whether the AI / ML model or the AI / ML function is applicable.

50. A wireless terminal according to any one of claims 43 to 49, wherein the additional conditions on the wireless terminal side include one or more conditions that are used in training the AI / ML model and that must also be consistent in inference using the AI / ML model.

51. The wireless terminal of claim 50, wherein the AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; the order of allocation of the first set and the second set; the Quasi Co-Location (QCL) relationship of the first set with respect to the second set; or the beam shapes of the first set and the second set.

52. A method performed by a wireless terminal, comprising: transmitting first information indicating additional conditions on the wireless terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio access network node via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.

53. A program causing a computer to perform a method for a wireless terminal, comprising: transmitting first information indicating additional conditions on the wireless terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality to a radio access network node via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.

54. A radio access network node comprising: means for receiving, from a radio terminal, via an RRC Setup Complete message or an RRC Resume Complete message or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

55. A radio access network node according to claim 54, further comprising means for determining, using said first information, whether to request said radio terminal to transmit second information indicating other additional conditions on the part of said radio terminal.

56. The radio access network node according to claim 55, wherein the determining means is configured to: request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information does not contradict an additional condition on the network side for activating or enabling the AI / ML model or the AI / ML function; and not request the radio terminal to transmit the second information if the additional condition on the radio terminal side reported in the first information contradicts an additional condition on the network side.

57. A radio access network node according to claim 55 or 56, wherein the second information is transmitted in a UE Assistance Information procedure, a UE capability transfer procedure, or a UE Information procedure.

58. A radio access network node according to any one of claims 54 to 57, wherein the means for receiving is configured to receive the first information via the PUSCH transmission in the random access procedure.

59. The radio access network node of claim 58, wherein the first information is included in a Logical Channel ID (LCID) field or an extended LCID (eLCID) field included in the PUSCH transmission.

60. A radio access network node according to any one of claims 54 to 59, wherein the additional conditions on the radio terminal side are taken into account to determine whether the AI / ML model or the AI / ML function is applicable.

61. A radio access network node according to any one of claims 54 to 60, wherein the additional conditions on the radio terminal side include one or more conditions used in training the AI / ML model and which must also be consistent in inference by the AI / ML model.

62. The radio access network node of claim 61, wherein the AI / ML model is an AI / ML model that predicts a first set of beams from measurement results of a second set of beams, and the one or more conditions include at least one of the following: the number of beams included in the first set and the number of beams included in the second set; the leasing order of the first set and the second set; the Quasi Co-Location (QCL) relationship of the first set with respect to the second set; or the beam shapes of the first set and the second set.

63. A method performed by a radio access network node, comprising receiving, from a radio terminal, via an RRC Setup Complete message or an RRC Resume Complete message or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality.

64. A program causing a computer to perform a method for a radio access network node, comprising: receiving, from a radio terminal, first information indicating additional conditions on the radio terminal side for activating or enabling an artificial intelligence or machine learning (AI / ML) model or AI / ML functionality via an RRC Setup Complete message or an RRC Resume Complete message, or via a Physical Uplink Control Channel (PUSCH) transmission in a random access procedure.

Images