Terminal, wireless base station, and wireless communication method

Abstract

This terminal receives setting information related to a learning model, and on the basis of the setting information, the terminal executes control using the learning model. The terminal receives setting information containing identification information for a session for the learning model, and the control unit selects a session on the basis of the identification information.

Description

Terminal, wireless base station, and wireless communication method

[0001] The present disclosure relates to a terminal, a radio base station, and a radio communication method that use an AI / ML model.

[0002] The 3rd Generation Partnership Project (3GPP: registered trademark) has developed specifications for Long Term Evolution (LTE) and 5th generation mobile communication systems (5G, also known as New Radio (NR) or Next Generation (NG)), and is also developing specifications for the next generation, known as Beyond 5G, 5G Evolution, or 6G.

[0003] 3GPP Release 18 has established a working item (WI) on the air interface for artificial intelligence / machine learning (AI / ML) models (Non-Patent Document 1). By using AI / ML models, it is possible to achieve terminal (User Equipment, UE) mobility, network-wide load balancing, and optimization of network power consumption.

[0004] For example, a UE that is in a connected state (RRC connected) in the radio resource control layer (RRC) can obtain configuration information (AIML config) related to the AI / ML model from the network and then perform various predictions (e.g., reception quality, beam direction) using the AI / ML model.

[0005] "New WID on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface", RP-234039, 3GPP TSG RAN Meeting #102, 3GPP, December 2023

[0006] As described above, a UE in the RRC connected state can make predictions using an AI / ML model, but after communication is completed, it may transition to an idle state (RRC idle). In this case, the AI / ML session established between the UE and the network (specifically, the radio base station (gNB)) cannot be maintained.

[0007] Therefore, even if the UE returns to the RRC connected state, the previous AIML session cannot be used.

[0008] Therefore, the following disclosure has been made in consideration of this situation, and aims to provide a terminal, a radio base station, and a radio communication method that can effectively utilize the established AIML session even when the UE transitions between the RRC connected state and the RRC idle state.

[0009] One aspect of the present disclosure is a terminal (UE200) that includes a receiving unit (AI / ML model unit 215) that receives configuration information regarding a learning model, and a control unit (control unit 240) that performs control using the learning model based on the configuration information, wherein the receiving unit receives the configuration information including identification information of a session for the learning model, and the control unit selects the session based on the identification information.

[0010] One aspect of the present disclosure includes a receiver (AI / ML model unit 130) that receives an initial context setting request message for a terminal from a network, the initial context setting request message including setting information related to a learning model, and a transmitter (AI / ML model unit 130) that transmits the setting information to the terminal in response to receiving the initial context setting request message, wherein the receiver receives the setting information including identification information associated with data collection related to the learning model, and the transmitter is a radio base station (gNB100) that transmits the setting information including the identification information.

[0011] One aspect of the present disclosure is a terminal (UE200) that includes a receiving unit (AI / ML model unit 215) that receives configuration information regarding a learning model, and a control unit (control unit 240) that performs control using the learning model based on the configuration information, wherein the receiving unit receives the configuration information including area information indicating a geographical area to which the learning model can be applied, and the control unit determines the geographical area to which the learning model is applied based on the area information.

[0012] One aspect of the present disclosure is a terminal (UE200) that includes a control unit (control unit 240) that controls the generation of prediction result data using a learning model, and a transmission unit (AI / ML model unit 215) that transmits a radio resource control layer message to the network that includes an indication that the data is being held.

[0013] One aspect of the present disclosure is a terminal (UE200) that includes a receiving unit (AI / ML model unit 215) that receives from a network a release message of a radio resource control layer that includes idle setting information of a learning model that is applied when the radio resource control layer is in an idle state, or system information that includes the idle setting information, and a control unit (control unit 240) that performs control using the learning model based on the idle setting information.

[0014] One aspect of the present disclosure includes a receiver (AI / ML model unit 130) that receives an initial context setting request message for a terminal from a network, the initial context setting request message including setting information related to a learning model, and a transmitter (AI / ML model unit 130) that transmits the setting information to the terminal in response to receiving the initial context setting request message, wherein the receiver receives the initial context setting request message including idle setting information of the learning model that is applied when the terminal is in an idle state in a radio resource control layer, and the transmitter is a radio base station (gNB100) that transmits the idle setting information to the terminal.

[0015] FIG. 1 is a diagram illustrating an overall schematic configuration of a wireless communication system 10. FIG. 2 is a functional block diagram of a gNB 100. FIG. 3 is a functional block diagram of a UE 200. FIG. 4 is a diagram illustrating an example of the functional architecture of an AI / ML model. FIG. 5 is a diagram illustrating an example of a sequence related to AIML configuration between a UE and a gNB according to operation examples 1 to 3. FIG. 6 is a diagram illustrating an example of a sequence related to AIML configuration in initial UE context setup according to operation examples 1 to 3. FIG. 7 is a diagram illustrating an example of a sequence related to AIML configuration in handover according to operation examples 1 to 3. FIG. 8 is a diagram illustrating an example of a sequence related to AIML configuration in a CU-DU separated configuration according to operation examples 1 to 3. FIG. 9 is a diagram illustrating an example of a sequence related to AIML configuration in UE context retrieval according to operation examples 1 to 3. FIG. 10 is a diagram illustrating an example of a sequence related to AIML configuration in dual connectivity according to operation examples 1 to 3. FIG. 11 is a diagram illustrating an example of a notification of an AIML configuration (AIMLAreaConfig) when an O-RAN architecture is applied according to operation examples 1 to 3. Fig. 12 is a diagram showing an example of the configuration of a UE-MeasurementsAvailable IE according to operation example 4. Fig. 13 is a diagram showing an example of a sequence related to AIMLDataAvailable between a UE and a gNB according to operation example 4. Fig. 14 is a diagram showing an example of a sequence related to AIMLDataAvailable in handover according to operation example 4. Fig. 15 is a diagram showing an example of a sequence related to AIMLDataAvailable in RRC reconnection according to operation example 4. Fig. 16 is a diagram showing an example of a sequence related to AIMLDataAvailable in CHO recovery according to operation example 4. Fig. 17 is a diagram showing an example of a sequence related to AIMLDataAvailable in LTM recovery according to operation example 4. Fig. 18 is a diagram showing an example of a sequence related to AIMLDataAvailable in dual connectivity according to operation example 4.FIG. 19 is a diagram showing an example of a sequence related to AIMLIdleConfig between a UE and a gNB according to Operation Example 5. FIG. 20 is a diagram showing an example of a sequence related to AIMLIdleConfig in initial UE context setup according to Operation Example 6. FIG. 21 is a diagram showing an example of a sequence related to AIMLIdleConfig in handover according to Operation Example 6. FIG. 22 is a diagram showing an example of a sequence related to AIMLIdleConfig in a CU-DU separated configuration according to Operation Example 6. FIG. 23 is a diagram showing an example of a sequence related to AIMLIdleConfig in UE context retrieval according to Operation Example 6. FIG. 24 is a diagram showing an example of a sequence related to AIMLIdleConfig in dual connectivity according to Operation Example 6. FIG. 25 is a diagram showing an example of notification of AIMLIdleConfig when an O-RAN architecture is applied according to Operation Example 6. FIG. 26 is a diagram showing an example of the hardware configuration of the gNB 100 and the UE 200. FIG. 27 is a diagram showing an example of the configuration of a vehicle 2001.

[0016] Hereinafter, embodiments will be described with reference to the drawings. Note that the same or similar reference numerals are used to designate the same functions or configurations, and descriptions thereof will be omitted as appropriate.

[0017] (1) Overall Schematic Configuration of Wireless Communication System Fig. 1 is a diagram showing the overall schematic configuration of a wireless communication system 10 according to this embodiment. The wireless communication system 10 is a wireless communication system conforming to 5G New Radio (NR) and includes a Next Generation-Radio Access Network 20 (hereinafter, NG-RAN 20) and a terminal 200 (User Equipment 200, hereinafter, UE 200).

[0018] The wireless communication system 10 may be a wireless communication system conforming to a standard called Beyond 5G, 5G Evolution, or 6G, or may include a wireless communication system conforming to a standard called Long Term Evolution (LTE) or 4G. The wireless communication system 10 may support functions related to the Industrial Internet of Things (IIoT) and Ultra-Reliable and Low Latency Communications (URLLC). The wireless communication system 10 may also be configured using multiple radio access technologies (RATs), for example, 4G / LTE and 5G.

[0019] The NG-RAN 20 includes a radio base station 100 (hereinafter, gNB 100). Note that the specific configuration of the radio communication system 10, including the number of gNBs (or eNBs, etc.) and UEs, is not limited to the example shown in FIG. 1 .

[0020] The gNB 100 may also employ a fronthaul (FH) interface defined by the Open Radio Access Network Alliance (O-RAN). The gNB 100 may include an O-RAN Distributed Unit (O-DU) and an O-RAN Radio Unit (O-RU). The gNB 100 can function as a type of NG-RAN node.

[0021] The NG-RAN 20 actually includes multiple NG-RAN nodes, specifically, gNBs (or ng-eNBs), and is connected to a 5G-compliant core network (5GC, not shown). In the 5GC, the concept of CUPS (Control and User Plane Separation) may be introduced, in which the functions of the user plane and the control plane are clearly separated.

[0022] The NG-RAN 20 may be connected to the OAM / RIC 40 and the NF 50 via 5GC or directly from the NG-RAN 20. The OAM / RIC 40 can provide functions related to operation and maintenance (OAM) of the wireless communication system 10. The OAM / RIC 40 can also provide functions related to control of the NG-RAN 20 (RIC: RAN Intelligent Controller). Specific functions of the RIC are defined by O-RAN specifications (e.g., O-RAN Architecture-Description 6.0). In this embodiment, the OAM / RIC 40 may constitute an entity that performs operation, maintenance, or control.

[0023] The NF 50 may be interpreted as a logical node that provides a network function. The NF 50 may include an Access and Mobility Management Function (AMF) that is included in the 5G system architecture and provides access and mobility management functions for the UE 200, a Session Management Function (SMF) that provides session management functions, and a Location Management Function (LMF) that controls communications related to location-based services defined in 5GC. A UDM / UDR (Unified Data Management / User Data Repository) may be connected to the AMF and / or SMF. The NG-RAN 20 and 5GC may be simply referred to as a "network." The OAM / RIC 40 and the NF 50 may be referred to as network devices.

[0024] In addition, the NG-RAN 20 may be connected to a server managed by a 3GPP service provider or a server (3GPP or non-3GPP server) managed by a party other than the provider.

[0025] The gNB100 is a radio base station conforming to NR and performs radio communication with the UE200 conforming to NR. The gNB100 may be configured with a CU (Central Unit) and a DU (Distributed Unit), and the DU may be separated from the CU and installed in a different geographical location. One or more DUs may be connected to the CU. The gNB100 (gNB-CU) may be connected to each other via an Xn interface, and the CU and DU may be connected to each other via an F1 interface.

[0026] The gNB 100 and the UE 200 can support Massive MIMO, which generates a more directional beam (BM) by controlling radio signals transmitted from multiple antenna elements, Carrier Aggregation (CA), which aggregates multiple component carriers (CCs), and Dual Connectivity (DC), which simultaneously communicates between the UE and multiple NG-RAN nodes. The UE 200 may also perform handover (HO) to a different RAT. The UE 200 may also perform handover between a serving cell or a neighboring cell.

[0027] The type of DC may be Multi-RAT Dual Connectivity (MR-DC) that uses multiple radio access technologies, or NR-NR Dual Connectivity (NR-DC) that uses only NR. For example, one gNB may constitute a master node (MN), and one or more other gNBs may constitute secondary nodes (SNs).

[0028] Any gNB 100 may be included in a master cell group (MCG), and another gNB 100 may be included in a secondary cell group (SCG). The other gNB 100 may be interpreted as an SN included in the SCG. The gNB 100 may also be referred to as a radio base station or a network device.

[0029] The wireless communication system 10 may support a conditional handover (CHO). The CHO can execute a handover initiated by the UE 200 when a specific execution condition is met. If the CHO is not applicable, a normal handover (which may be called a CHO recovery) may be executed.

[0030] Furthermore, the wireless communication system 10 may support conditional addition or change (CPAC) of a Primary SCell (PSCell). A PSCell is a type of secondary cell. A PSCell means a Primary SCell (secondary cell), and may be interpreted as corresponding to any one of a plurality of SCells.

[0031] The secondary cell may be referred to as a secondary node (SN) or a secondary cell group (SCG). The conditional PSCell addition / change can realize efficient and rapid addition or change of a secondary cell.

[0032] In the wireless communication system 10, not only mobility control of the UE 200 at layer 3 (which may be referred to as L3 Mobility), but also mobility control at layer 1 and / or layer 2 (which may be referred to as L1 / L2 Mobility or LTM) may be applied. L3 Mobility may be interpreted as mobility control at the Radio Resource Control layer (RRC). On the other hand, L1 / L2 Mobility may be interpreted as mobility control at the physical layer (PHY), medium access control layer (MAC), radio link control layer (RLC), and packet data convergence protocol layer (PDCP) (mobility control by a lower layer).

[0033] In addition, in UE-based LTM, like conditional handover (CHO), the UE receives a specific execution condition from the radio base station (gNB), monitors the status according to the execution condition, and if the execution condition is satisfied, it may execute LTM.

[0034] In the wireless communication system 10, artificial intelligence (AI) / machine learning (ML) may be applied in the NG-RAN 20. Specifically, a learning model (herein referred to as an AI / ML model) may be used to optimize the mobility or handover (which may also be read as transition, cell transition, cell selection, etc.) of the UE 200.

[0035] The AI / ML model may be expressed by another term meaning AI or ML, such as an artificial intelligence (AI) model or a machine learning (ML) model. In the wireless communication system 10, such an AI / ML model can be used to optimize the mobility or handover of the UE 200. The AI / ML model may be provided in the OAM / RIC 40 or the gNB 100. Alternatively, the AI / ML model may be provided in the UE 200.

[0036] In a broad sense, the mobility of UE200 may mean the ease of movement and maneuverability of UE200, but in this embodiment, it may also mean minimizing call drops, radio link (including beam) failures, unnecessary handovers, ping-pong states, etc.

[0037] In this embodiment, the channels include a control channel and a data channel, such as a physical downlink control channel (PDCCH), a physical uplink control channel (PUCCH), a physical random access channel (PRACH), and a physical broadcast channel (PBCH).

[0038] The data channels include a physical downlink shared channel (PDSCH) and a physical uplink shared channel (PUSCH).

[0039] The reference signal includes a Demodulation Reference Signal (DMRS), a Sounding Reference Signal (SRS), a Phase Tracking Reference Signal (PTRS), and a Channel State Information-Reference Signal (CSI-RS), and the signal includes a channel and a reference signal. Furthermore, the data may refer to data transmitted via a data channel.

[0040] (2) Functional Block Configuration of Wireless Communication System Next, the functional block configuration of the wireless communication system 10 will be described. Specifically, the functional block configuration of the gNB 100 and the UE 200 will be described. Fig. 2 is a functional block configuration diagram of the gNB 100. Fig. 3 is a functional block configuration diagram of the UE 200.

[0041] (2.1) gNB100 As shown in FIG. 2, the gNB100 includes a wireless communication unit 110, a handover processing unit 120, an AI / ML model unit 130, and a control unit 140.

[0042] The wireless communication unit 110 transmits downlink signals (DL signals) conforming to NR. The wireless communication unit 110 also receives uplink signals (UL signals) conforming to NR. The wireless communication unit 110 may transmit DL signals and receive UL signals using one or more transmission / reception points (TRPs). In this embodiment, a TRP may be interpreted as meaning multiple DL transmission antennas.

[0043] The handover processing unit 120 executes handover of the UE 200. Specifically, the handover processing unit 120 executes handover of the UE 200 from a serving cell to another nearby cell.

[0044] The serving cell may be simply interpreted as a cell to which the UE 200 is connected, but more precisely, in the case of an RRC_CONNECTED UE (connected state in the radio resource control layer) in which carrier aggregation (CA) is not configured, there is only one serving cell that constitutes the primary cell. In the case of an RRC_CONNECTED UE configured using CA, the serving cell may be interpreted as indicating a set of one or more cells including the primary cell and all secondary cells.

[0045] As described above, the handover may include a conditional handover (CHO) and / or a dual active protocol stack (DAPS) handover. A CHO can execute a handover initiated by the UE 200 when a specific execution condition is met. If a CHO is not applicable, a normal handover (which may be referred to as a CHO recovery) may be executed. In a CHO recovery, the UE 200 executes a cell selection after a CHO failure. If a CHO candidate cell is selected, the UE 200 can directly apply a conditional RRC reconfiguration of the selected cell to reconnect without transmitting an RRC reestablishment request to the candidate target cell.

[0046] The execution condition may consist of one or two trigger conditions (CHO event A3 / A5 specified in 3GPP TS38.331). A single reference signal (RS) type may be triggered, and up to two different trigger quantities (e.g., Reference Signal Received Power (RSRP) and Reference Signal Received Quality (RSRQ), RSRP and Signal-to-Interference plus Noise power Ratio (SINR)) may be simultaneously set for the evaluation of the CHO execution condition for a single candidate cell.

[0047] The AI / ML model unit 130 executes processing using a learning model (AI / ML model). Specifically, the AI / ML model unit 130 executes processing using an AI / ML model that is applied to optimization of mobility and / or handover of the UE 200, etc.

[0048] In particular, in this embodiment, the AI / ML model unit 130 may transmit setting information related to the AI / ML model to the UE 200. In this embodiment, the AI / ML model unit 130 may constitute a transmitting unit that transmits setting information related to the learning model to the UE 200.

[0049] The configuration information for an AI / ML model is typically called AIML config and may include configuration details for the AI / ML model. The configuration details may include, but are not limited to, model selection, the target of prediction using the model, and a reporting method for prediction results. The AIML config may also be called AIML data collection config.

[0050] The AI / ML model unit 130 may transmit configuration information including identification information of a session for the AI / ML model. Specifically, the AI / ML model unit 130 may transmit, to the UE 200, an AIML config including an AIML session reference ID that identifies the AIML session. The AIML session reference ID may be simply referred to as an AIML session ID. The AIML session may be interpreted as a logical communication path for transmitting and receiving configuration information related to the AI / ML model.

[0051] The AI / ML model unit 130 may receive an initial context setup request message for the UE 200, which includes configuration information (AIML config) related to the learning model, from the network. In this embodiment, the AI / ML model unit 130 may configure a receiving unit that receives an initial context setup request message for the UE 200, which includes configuration information related to the learning model, from the network. The initial context setup request message may mean an initial context setup request message, but it does not necessarily have to be at the initial stage, and may be a message requesting context setup for the UE 200.

[0052] Furthermore, in response to receiving an initial context setup request message, the AI / ML model unit 130 may transmit the AIML config to the UE 200. For example, when the AI / ML model unit 130 receives an initial context setup request message from the AMF, the AI / ML model unit 130 may transmit the AIML config to the UE 200.

[0053] The AI / ML model unit 130 may receive configuration information including identification information associated with data collection related to the learning model. Specifically, the AI / ML model unit 130 may receive an AIML config including an AIML session reference ID associated with the AIML data collection. The AI / ML model unit 130 may transmit the configuration information including the identification information (AIML session reference ID) to the UE 200.

[0054] The AI / ML model unit 130 may transmit a trigger for AIML data collection including the identification information (AIML session reference ID) to the UE 200. Specifically, when the AI / ML model unit 130 receives an initial context setup request message from the AMF, the AI / ML model unit 130 may trigger AIML data collection including the AIML session reference ID. The AIML data collection may mean that the UE 200 collects prediction results predicted using a learning model. The prediction results may include, for example, cell quality measurements (e.g., RSRP), handover failure (HOF) probability, and radio link failure (RLF) probability.

[0055] When the UE 200 is handed over to another radio base station (gNB), the AI / ML model unit 130 may transmit the above-described configuration information to the other radio base station. The other radio base station may refer to a radio base station to which the UE 200 is handed over, and may also be called a target gNB.

[0056] When the UE 200 reconnects to the network, the AI / ML model unit 130 may transmit the above-described setting information to the UE 200. The reconnection may mean that the UE 200 in an idle state (RRC idle) performs connection setup with the network and an RRC layer, and transitions to a connected state (RRC connected).

[0057] When the UE 200 executes dual connectivity (DC), the AI / ML model unit 130 may transmit the above-described setting information to the UE 200. As described above, the type of DC is not particularly limited.

[0058] The AI / ML model unit 130 may transmit configuration information including area information indicating a geographical area to which the learning model can be applied to the UE 200. Specifically, the AI / ML model unit 130 may transmit configuration information including AIMLAreaConfig to the UE 200. Note that the AIMLAreaConfig does not need to be included in the configuration information, and may be transmitted to the UE 200 independently or as a separate information element.

[0059] The AI / ML model unit 130 may receive an RRC message including an indication that data of a prediction result using the learning model is held from the UE 200. In this embodiment, the AI / ML model unit 130 may constitute a receiving unit that receives the RRC message from the UE 200.

[0060] Specifically, the AI / ML model unit 130 may receive an RRC message including AIMLDataAvailable from the UE 200. The target RRC message is not particularly limited as long as it is a message transmitted from the UE 200. Typical examples include RRC Setup Complete and RRC Reconfiguration Complete. The types of RRC messages that may be the target will be described further below.

[0061] The AI / ML model unit 130 may transmit to the UE 200 an RRC layer release message including idle setting information of a learning model that is applied when the radio resource control layer is in an idle state. The AI / ML model unit 130 may also transmit to the UE 200 system information (SIB: System Information Block) including the idle setting information. In this embodiment, the AI / ML model unit 130 may constitute a transmission unit that transmits the RRC layer release message or system information.

[0062] Specifically, the AI / ML model unit 130 may transmit an RRC Release or SIB including the AIMLIdleConfig to the UE 200. The AIMLIdleConfig may be referred to as a loggedAIMLConfig.

[0063] The AI / ML model unit 130 may receive an initial context setup request message including idle configuration information (AIMLIdleConfig) of a learning model that is applied when the UE 200 is in an idle state (RRC idle) in the RRC layer. The AI / ML model unit 130 may transmit the AIMLIdleConfig to the UE 200.

[0064] When the UE 200 is handed over to another radio base station (gNB), the AI / ML model unit 130 may transmit the AIMLIdleConfig to the other radio base station. As described above, the other radio base station may refer to a radio base station to which the UE 200 is handed over, and may also be called a target gNB.

[0065] When the UE 200 reconnects to the network, the AI / ML model unit 130 may transmit the AIMLIdleConfig to the UE 200. Furthermore, when the UE 200 executes dual connectivity (DC), the AI / ML model unit 130 may transmit the AIMLIdleConfig to the UE 200. The meaning of the reconnection and the type of DC may be as described above.

[0066] The control unit 140 controls each functional block constituting the gNB 100. Specifically, the control unit 140 may control the UE 200 based on the prediction result using the AI / ML model.

[0067] In particular, in this embodiment, the control unit 140 may use the AI / ML model unit 130 to obtain predicted values ​​such as cell quality measurements, HOF probability, and RLF probability, and perform control related to SON (Self-Organizing Networks) according to the predicted values ​​and the accuracy of the predicted values.

[0068] Furthermore, the control unit 140 may perform mobility control of the UE 200, including handover, based on the cell quality measurement results and HOF / RLF reports acquired from the UE 200. The measurement results and reports may be predicted using an AI / ML model.

[0069] The control unit 140 may control the UE 200 based on the data of the prediction result using the learning model. The data of the prediction result can be acquired from the UE 200 as described above. As described above, the control unit 140 can recognize that the UE 200 holds the data of the prediction result using the learning model by receiving an RRC message including AIMLDataAvailable from the UE 200.

[0070] (2.2) UE 200 As shown in FIG. 3 , the UE 200 includes a radio communication unit 210, an AI / ML model unit 215, a measurement processing unit 220, a handover execution unit 230, and a control unit 240.

[0071] The wireless communication unit 210 transmits an uplink signal (UL signal) conforming to NR. The wireless communication unit 210 also receives an uplink signal (DL signal) conforming to NR.

[0072] The AI / ML model unit 215 executes processing using a learning model (AI / ML model). The AI / ML model unit 215 may have the same functions as the AI / ML model unit 130 of the gNB 100. The AI / ML model unit may be provided in either the gNB 100 or the UE 200, or may be provided in both.

[0073] The AI / ML model unit 215 may receive configuration information (AIML config) related to the AI / ML model from a network. In this embodiment, the AI / ML model unit 215 may constitute a receiving unit that receives configuration information related to the learning model. The AI / ML model unit 215 may receive the AIML config including identification information (AIML session reference ID) of a session for the AI / ML model.

[0074] The AI / ML model unit 215 may receive an AIML config including the identification information (AIML session reference ID) and network information related to the network to which the UE 200 connects. The network information may include, for example, time information in the network, identification information (ID) of a PLMN (Public Land Mobile Network), three-dimensional location information, and the like.

[0075] The AI / ML model unit 215 may transmit a learning report including the prediction result using the AI / ML model and the identification information (AIML session reference ID) to the network. In this embodiment, the AI / ML model unit 215 may constitute a transmitting unit that transmits the learning report to the network.

[0076] Specifically, the AI / ML model unit 215 may execute an AIML reporting including the AIML session reference ID. More specifically, the AIML report may include the AIML session reference ID.

[0077] The AI / ML model unit 215 may transmit a learning report including identification information related to the AI / ML model. Specifically, the AI / ML model unit 215 may transmit an AIML report including an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment (AIML model training environment ID), and an ID for identifying the AIML model inference environment (AIML model inference environment ID).

[0078] The AI / ML model unit 215 may receive an AIML config including area information indicating a geographical area to which the AI / ML model can be applied from the UE 200. Specifically, the AI / ML model unit 215 may receive an AIML config including an AIMLAreaConfig. As described above, the AIMLAreaConfig does not need to be included in the configuration information, and may be a standalone or separate information element.

[0079] The AI / ML model unit 215 may receive an AIMLAreaConfig that includes at least one of a frequency band and a combination of frequency bands to which the AI / ML model can be applied. The frequency band (combination of frequency bands) may refer to a frequency band (band) that is a target of prediction using the AI / ML model, and may be indicated by a list of carrier frequencies or PCIs (Physical Cell IDs).

[0080] The AI / ML model unit 215 may receive AIMLAreaConfig including a bandwidth part (BWP) to which the AI / ML model can be applied. Note that the AIMLAreaConfig may include information indicating a resource block (RB) and a resource block group (RBG) instead of the BWP.

[0081] The AI / ML model unit 215 may receive AIMLAreaConfig including information about beams to which the AI / ML model can be applied. Specifically, AIMLAreaConfig may include a list of beams to be predicted. Note that, instead of beams, AIMLAreaConfig may include a list of SSBs (SS / PBCH Blocks), which are blocks of synchronization signals / broadcast channels configured from SSs (Synchronization Signals) and PBCHs (Physical Broadcast Channels), or a list of CSI-RSs.

[0082] The AI / ML model unit 215 may transmit a message of the RRC layer to the network indicating that it holds data of the prediction result using the learning model. In this embodiment, the AI / ML model unit 215 may constitute a transmitter that transmits the RRC message to the network.

[0083] Specifically, the AI / ML model unit 215 may transmit an RRC message including AIMLDataAvailable. As described above, the target RRC message is not particularly limited.

[0084] The AI / ML model unit 215 may transmit an RRC message including the indication (AIMLDataAvailable) at the timing of transition from an idle state (RRC idle) of the RRC layer to a connected state (RRC connected). The AI / ML model unit 215 may transmit an RRC message including the indication (AIMLDataAvailable) at the timing of handing over the UE 200 to another radio base station. The AI / ML model unit 215 may also transmit an RRC message including the indication (AIMLDataAvailable) at the timing of reconnecting the UE 200 to the network. The meaning of reconnection may be as described above.

[0085] The AI / ML model unit 215 may receive from the network a radio resource control layer release message including idle setting information of a learning model that is applied when the UE 200 is in an idle state (RRC idle) in the RRC layer. The AI / ML model unit 215 may also receive from the network system information (SIB) including the idle setting information. In this embodiment, the AI / ML model unit 215 may constitute a receiving unit that receives the RRC layer release message or system information.

[0086] Specifically, the AI / ML model unit 215 may receive an RRC Release or SIB including an AIMLIdleConfig. The AI / ML model unit 215 may also receive an AIMLIdleConfig including identification information (AIML session reference ID) of a session for the AI / ML Model.

[0087] The AI / ML model unit 215 may receive an RRC release or SIB including an instruction to activate or deactivate the AI / ML model. The instruction may be interpreted as activating or deactivating the AI / ML model of the UE 200.

[0088] The measurement processing unit 220 can measure the quality of the serving cell of the UE 200 and neighboring cells of the serving cell and report the measurement result to the network (Measurement Report). The measurement processing unit 220 can perform measurement reporting of the source cell and the target cell during handover.

[0089] The quality to be measured may be, for example, the quality (for example, RSRP, RSRQ) included in the Measurement Report defined in 3GPP TS38.331.

[0090] The measurement processing unit 220 receives, from the network, a measurement configuration (MeasConfig) that configures measurements using an AI / ML model.

[0091] The measurement processing unit 220 may perform measurement using the AI / ML model unit 215 in accordance with the received measurement configuration and under the control of the control unit 240. Measurement using an AI / ML model may mean predicting cell quality (which may include beam quality) for future or different radio resources (e.g., frequencies) based on actual measurement values ​​of cell quality.

[0092] The measurement processing unit 220 may receive a measurement configuration including a measurement report condition. Note that the measurement report here may be a report related to AI / ML (AI / ML reporting) or a Measurement Report. The condition may be, for example, the reporting period of AI / ML reporting, the volume (amount) of AI / ML reporting, the number of reports, or whether a predetermined event is satisfied. The predetermined event may be, for example, an event related to an AI / ML model or an event related to cell quality.

[0093] The handover execution unit 230 executes handover of the UE 200. Specifically, the handover execution unit 230 may execute handover to a transfer destination cell (NG-RAN node) based on control by the gNB 100.

[0094] Furthermore, the handover execution unit 230 can execute processes related to normal handover (legacy handover) and conditional handover (CHO).

[0095] In the case of CHO, the handover execution unit 230 may transition to the candidate cell when an execution condition is satisfied. As described above, the execution condition may be determined based on the quality of the reference signal (RS), specifically, the value of RSRP, RSRQ, or SINR.

[0096] In addition, the destination of the CHO may or may not be accompanied by an SCG. In other words, the destination cell of the CHO may be a single cell or may be composed of multiple cells (which may be read as a cell group) according to the DC.

[0097] The control unit 240 controls each functional block constituting the UE 200. In particular, in this embodiment, the control unit 240 may use the AI / ML model unit 215 to perform control related to measurement configuration and measurement reporting by the measurement processing unit 220. The control unit 240 may also perform control using an AI / ML model based on configuration information (AIML config) processed by the AI / ML model unit 215. Furthermore, the control unit 240 may also perform control using an AI / ML model based on idle configuration information (AIMLIdleConfig) processed by the AI / ML model unit 215.

[0098] For example, the control unit 240 may select an AIML session in which setting contents related to the AI / ML model are sent and received based on identification information (AIML session reference ID) of the session (AIML session) for the AI / ML model.

[0099] The control unit 240 may also determine the geographical area to which the AI / ML model is applied based on area information (AIMLAreaConfig) indicating the geographical area to which the learning model can be applied. The geographical area may be based on a cell, a tracking area (TA), or the like.

[0100] The control unit 240 may use the AI / ML model to control the generation of data on prediction results using a learning model. Specifically, the control unit 240 may use the AI / ML model to generate various prediction results and provide the generated prediction results to the AI / ML model unit 215.

[0101] The control unit 240 may control the activation or deactivation of the AI / ML model based on an instruction to activate or deactivate the AI / ML model. Specifically, the control unit 240 may activate or deactivate the AI / ML model based on an RRC release or SIB including an instruction to activate or deactivate the AI / ML model received by the AI / ML model unit 215.

[0102] (3) Operation of the Wireless Communication System Next, we will explain the operation of the wireless communication system 10. Specifically, we will explain the operation of the UE performing various predictions using the AI / ML model based on setting information (AIML config, AIMLIdleConfig) related to the AI / ML model.

[0103] (3.1) Example of AI / ML Model Configuration Figure 4 shows an example of the functional architecture of an AI / ML model. As shown in Figure 4, the architecture may include the following functions:

[0104] Data collection: Providing input data for model training and model inference functions.

[0105] Model training: Train, validate, and test ML models. As part of the model testing procedure, model performance metrics may be generated.

[0106] The model training function may also be responsible for data preparation (data pre-processing and cleaning, formatting, transformation, etc.).

[0107] Model inference: Provides inference output (such as a prediction or decision). The model inference function may provide control of the model inference to the model management / performance monitoring function.

[0108] (3.2) Operation Example 1: A UE in the RRC connected state can perform various predictions using an AI / ML model after obtaining an AIML configuration from a radio base station (gNB). When data communication is completed, the UE may transition from an RRC connected state to an RRC idle state. In this case, it is desirable for the UE to store (retain) the AIML session with the gNB. This allows the UE to continuously perform predictions using an AI / ML model using the AIML configuration in the next RRC connected state.

[0109] In other words, switching between the RRC connected and RRC idle states may occur between the UE and gNB, but there is a request to continue the AIML session. Also, a session for AIML training and a session for AIML inference may be established between the UE and gNB, and an ID to identify each session is required.

[0110] By aligning the AIML training environment and the AIML inference environment, the UE can perform highly accurate AI predictions. To do this, an ID that distinguishes between the AIML training environment and the AIML inference environment is required.

[0111] In consideration of such a situation, in this operation example, the gNB may perform a setting (AIML configuration) related to the learning model for the UE. Specifically, the gNB may transmit the AIML config to the UE.

[0112] A concept of an AIML session may be established between the UE and the gNB (the definition of an AIML session may be as described above). An AIML session reference ID may be assigned to identify the AIML session.

[0113] The AIML config may include an AIML session reference ID, which may be configured in combination with other IDs as follows:

[0114] -Consists of PLMN ID and AIML session ID.

[0115] ・Consists of a TAC (Tracking Area Code) ID and an AIML session ID.

[0116] ・Consists of a cell ID and an AIML session ID.

[0117] ・Consists of a base station ID and an AIML session ID.

[0118] Additionally, the AIML session reference ID (or AIML config) may include the following IDs:

[0119] ・AIML data collection session ID ・AIML model training session ID ・AIML inference session ID ・AIML performance monitoring session ID ・ID for identifying the AIML model training environment (AIML model training environment ID) ・ID for identifying the AIML model inference environment (AIML model inference environment ID) In ​​addition, the AIML session reference ID (or AIML config) may include the following information:

[0120] Time information, PLMN ID list, AIML prediction duration (prediction period), 3D LocationInfo (latitude / longitude / altitude) When the UE executes AIML reporting, the UE may include the above-mentioned AIML session reference ID in the AIML report. Furthermore, when the UE executes AIML reporting, the UE may include the AIML data collection session ID, AIML model training session ID, AIML inference session ID, AIML model training environment ID, and AIML model inference environment ID in the AIML report. Furthermore, when the UE executes AIML reporting, the UE may include time information, a PLMN ID list, and 3D LocationInfo in the AIML report.

[0121] As mentioned above, AIML config may be read as AIML data collection config. The AIML model training environment and the AIML inference environment may relate to UE speed (mobility speed), channel model (e.g., Urban Macro (UMa), Urban Micro (UMi)), Inter-Site Distance (ISD), frequency, BWP, or antenna port layout.

[0122] Figure 5 shows an example sequence for AIML config between a UE and a gNB relating to operation examples 1 to 3.

[0123] FIG. 6 shows an example of a sequence relating to AIML config in the initial UE context setup according to operation examples 1 to 3.

[0124] FIG. 7 shows an example of a sequence relating to AIML configuration in handover according to operation examples 1 to 3.

[0125] FIG. 8 shows an example of a sequence relating to AIML config in a CU-DU separated configuration according to operation examples 1 to 3.

[0126] FIG. 9 shows an example of a sequence relating to AIML configuration in UE context retrieval according to operation examples 1 to 3.

[0127] FIG. 10 shows an example of a sequence relating to AIML configuration in dual connectivity according to operation examples 1 to 3.

[0128] FIG. 11 shows an example of notification of AIML config (AIMLAreaConfig) when the O-RAN architecture according to operation examples 1 to 3 is applied.

[0129] 5 to 11, information about the AIML config may be transmitted and received between the UE, the gNB (including the CU-DU separation configuration), and the AMF. The AIML config may include information such as the AIML session reference ID described above.

[0130] (3.3) Operation Example 2 When AIML data collection is triggered from the core network, the core network side and the RAN node side must similarly identify and track the AIML session by the AIML session reference ID.

[0131] In addition, when a UE performs handover, reconnection, or dual connectivity (DC) under the same RAN node (which may include a gNB), the RAN nodes must exchange the AIML session reference ID, AIML data collection session ID, AIML model training session ID, AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment in order to track the previous AIML configuration or continue the AIML session.

[0132] Taking this situation into consideration, in this operation example, the AMF or OAM may trigger data collection for a target UE for AI / ML data collection. For example, the initial context setup request message may include an AIML config IE, and AIML data collection may be triggered for a target UE (specific UE ID). When triggering AIML data collection activation, an AIML session reference ID, an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment may be included.

[0133] Furthermore, when a handover request is sent from a source gNB to a target gNB during a UE handover, the handover request may include an AIML config, which may include an AIML session reference ID, an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment.

[0134] In the case of a CU-DU split gNB, when a UE context setup request is sent from a CU to a DU, the UE context setup request may include an AIML config. The AIML config may include an AIML session reference ID, an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment.

[0135] When the UE reconnects to a network (which may be a cell), the new gNB sends a Retrieve UE context request to the old gNB, and the old gNB sends a Retrieve UE context response to the new gNB. The AIML config may include an AIML session reference ID, an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment.

[0136] When a UE establishes dual connectivity (DC), an S-NODE ADDITION REQUEST is sent from the MN to the SN, and the S-NODE ADDITION REQUEST may include an AIML config. The AIML config may include an AIML session reference ID, an AIML data collection session ID, an AIML model training session ID, an AIML inference session ID, an ID for identifying the AIML model training environment, and an ID for identifying the AIML model inference environment.

[0137] Specifically, as shown in FIGS. 5 to 11, information such as an AIML session reference ID may be sent and received.

[0138] (3.4) Operation Example 3 From the viewpoint of an operator (mobile communications carrier), it is desirable for a UE to perform AIML prediction in a limited area or a specific frequency band. For example, in the case of a dual SIM (Subscriber Identity Module) UE, the UE may perform AIML prediction under the control of a gNB of an operator B based on an AIML configuration of an operator A. However, this situation is undesirable because there is a risk that cell-related information of an operator B may be collected by an operator A.

[0139] In other words, it is desirable that the AIML configuration of a UE be set only for a limited area (e.g., PLMN) or a specific frequency band. Also, when a UE performs handover, reconnection, or dual connectivity under the same RAN node, the area configuration needs to be exchanged between RAN nodes.

[0140] In consideration of such a situation, in this operation example, the gNB may configure AIMLAreaConfig when configuring the AIML config for the UE. Also, when the AIML config is configured from the core network, the AMF may configure AIMLAreaConfig together with the AIML config for the gNB.

[0141] Similarly, the OAM may configure the AIMLAreaConfig together with the AIML config for the gNB. Alternatively, the RIC or SMO (Service Management and Orchestration Framework, see FIG. 11) may configure the AIMLAreaConfig together with the AIML config for the gNB.

[0142] AIMLAreaConfig may contain the following information:

[0143] ・AIML prediction target frequency band list (Carrier Freq list, PCI list) ・AIML prediction target frequency band combination list (Carrier Freq list, PCI list) ・AIML prediction target BWP(s) ・Cell ID list (CGI (Cell Global Identifier) ​​list) ・Beam list (SSB list, CSI-RS list) or target Beam list (target SSB list, target CSI-RS list) ・Tracking Area ID list ・PLMN ID list ・TAC list ・CAG (Closed Access Group) config list (PLMN ID list, CAG ID list) (for Non-Public Network) ・SNPN config list (SNPN (Stand-alone Non-Public Network) CGI list, SNPN NID list, Tracking Area ID list, PLMN ID list) (for Non-Public Network) ・Base station ID list ・Physical location information list (three-dimensional location information of latitude, longitude, and altitude) In addition, when the source gNB of the handover source sends a handover request to the target gNB, the source gNB may include an AIML config in the handover request. The AIML config may include an AIMLAreaConfig.

[0144] In the case of a CU-DU split gNB, when a UE context setup request is sent from a CU to a DU, the UE context setup request may include an AIML config. The AIML config may include an AIMLAreaConfig.

[0145] When the UE reconnects to a network (which may be a cell), the new gNB sends a Retrieve UE context request to the old gNB, and the old gNB sends a Retrieve UE context response to the new gNB. The AIML config may be included in the message. The AIML config may include AIMLAreaConfig.

[0146] When the UE establishes dual connectivity (DC), the MN sends an S-NODE ADDITION REQUEST to the SN, and the S-NODE ADDITION REQUEST may include an AIML config. The AIML config may include an AIMLAreaConfig.

[0147] Specifically, as shown in FIGS. 5 to 11, information such as AIMLAreaConfig may be sent and received.

[0148] (3.5) Operation Example 4: The network collects AIML data held by the UE. However, in the following scenario, the gNB cannot recognize that the UE holds the AIML data. Therefore, the UE needs to inform the gNB that it holds the AIML data.

[0149] - When the UE transitions to RRC idle state and then transitions from RRC idle state to RRC connected state. - When the UE hands over from the source gNB to the target gNB (the target gNB is unaware that the UE holds AIML data). - When the UE reconnects to the network (for example, in a case where a radio link failure (RLF) occurs between gNB A and the UE reconnects to gNB B, gNB B is unaware that the UE holds AIML data). - During CHO recovery or LTM recovery (for example, when a CHO failure or LTM failure occurs in cell A and CHO recovery is successful in cell B). - When dual connectivity is established (for example, when gNB A is MN and gNB B is SN, gNB B is unaware that the UE holds AIML data). Taking these situations into consideration, in this operation example, the UE may send the following message to the gNB, which includes an indication indicating that it holds AIML data (for example, AIMLDataAvailable IE).

[0150] RRCSetupComplete RRCReconfigurationComplete RRCReestablishmnetComplete RRCResumeComplete Fig. 12 shows a configuration example of a UE-MeasurementsAvailable IE according to operation example 4. As shown in Fig. 12, the UE-MeasurementsAvailable IE may include AIMLDataAvailable-r19 indicating that AIML data is held.

[0151] Figure 13 shows an example sequence regarding AIMLDataAvailable between a UE and a gNB in ​​operation example 4.

[0152] FIG. 14 shows an example of a sequence relating to AIMLDataAvailable in a handover according to the fourth operation example.

[0153] FIG. 15 shows an example of a sequence relating to AIMLDataAvailable in RRC reconnection according to the fourth operation example.

[0154] FIG. 16 shows an example of a sequence relating to AIMLDataAvailable in CHO recovery according to the fourth operation example.

[0155] FIG. 17 shows an example of a sequence relating to AIMLDataAvailable in LTM recovery according to the fourth operation example.

[0156] FIG. 18 shows an example of a sequence relating to AIMLDataAvailable in dual connectivity according to the fourth operational example.

[0157] Specifically, as shown in FIG. 13, when a UE transitions from an RRC idle state to an RRC connected state, after receiving an RRC Setup message, the UE may include an AIMLDataAvailable IE in an RRC Setup Complete message that it sends to the gNB.

[0158] As shown in FIG. 14, after receiving the RRCReconfiguration message from the source gNB, the UE may include an AIMLDataAvailable IE in the RRCReconfigurationComplete message sent to the target gNB.

[0159] As shown in FIG. 15, after receiving the RRCReestablishment message from the gNB, the UE may include an AIMLDataAvailable IE in the RRCReestablishmentComplete message that it sends to the gNB.

[0160] As shown in FIG. 16, after successful CHO failure recovery, the UE may include an AIMLDataAvailable IE in the RRCReconfigurationComplete message that is sent to the recovery target cell.

[0161] As shown in FIG. 17, after successful LTM failure recovery, the UE may include an AIMLDataAvailable IE in the RRCReconfigurationComplete message that is sent to the recovery target cell.

[0162] As shown in Fig. 18, when executing the Dual connectivity setup / modification procedure or the PSCell change procedure, the UE may include an AIMLDataAvailable IE in the RRCReconfigurationComplete message sent to the MN. The information on AIMLDataAvailable may be transferred from the MN to the SN.

[0163] (3.6) Operation Example 5 When a UE is in the RRC idle state, the network cannot configure the UE regarding the AI / ML model. Furthermore, when the UE is in the RRC idle state, it is unclear whether the AIML functionality and the AI / ML model are in the active or de-active state. When the UE is in the RRC idle state, it is assumed that the AIML functionality and the AI / ML model may be in the active or de-active state. When the UE is in the RRC idle state, if the AIML functionality and the AI / ML model are in the de-active state, a reduction in UE power consumption is expected.

[0164] On the other hand, when the UE is in the RRC idle state, if the AIML functionality and AI / ML model are active, it can be useful for cell (re)selection in the RRC idle state. Because the UE performs cell quality measurements even in the RRC idle state, the use of AIML prediction can relax the measurement conditions.

[0165] Taking this situation into consideration, in this operation example, the gNB may include an AIML config (e.g., AIMLIdleConfig) in the RRCRelease message or SIB. The RRCRelease message may also instruct activation or deactivation of the AIML functionality and / or the AI ​​model. Alternatively, the SIB may instruct activation or deactivation of the AIML functionality and / or the AI ​​model.

[0166] 19 shows an example sequence related to AIMLIdleConfig between a UE and a gNB according to operation example 5. After receiving an AIML config (e.g., including AIMLIdleConfig and AIML measurement duration) from an RRCRelease message or SIB, the UE may start a new timer. The new timer may be a timer that manages the period of AIML idle measurement or prediction. When the new timer is stopped or expires, the UE may stop the AIML idle measurement or prediction. When the UE leaves the AIML validity area (when the cell is reselected to a non-target frequency / RAT), the UE may stop the AIML idle measurement or prediction.

[0167] AIMLIdleConfig may contain information such as:

[0168] ・AIML session reference ID, AIML data collection session ID, AIML model training session ID, AIML inference session ID, AIML model training environment ID, AIML model inference environment ID ・AIML target frequency ・CarrierFreq ・SCS (Sub-Carrier Spacing) ・FrequencyBandList ・AIML measurement cell List ・AIML prediction cell List ・AIML target RAT type (NR, LTE, 6G, etc.) ・AIML target cell list ・AIML target beam list ・AIML measurement validity duration or AIML measurement duration ・AIML prediction validity duration (prediction period) ・AIML validityArea ・AIML prediction's target frequency band list (Carrier Freq list, PCI list) ・AIML prediction's target frequency band combination list (Carrier Freq list, PCI list) ・AIML prediction's target BWP(s) ・Cell ID list (CGI list) or validityCellList ・Beam list (SSB list, CSI-RS list) or target Beam list (target SSB list,target CSI-RS list) ・Tracking Area ID list ・PLMN ID list ・TAC list ・CAG config list (PLMN ID list, CAG ID list) (for Non-Public Network) ・SNPN config list (SNPN CGI list, SNPN NID list, Tracking Area ID list, PLMN ID list) (for Non-Public Network) ・Base station ID list ・Physical location information list (three-dimensional location information of latitude, longitude, and altitude) ・Time information ・PLMN ID list ・3D LocationInfo list (latitude / longitude / altitude) In the RRC idle state, the UE may send UE capability to the network that can perform AIML prediction / AIML inference / AIML model training.

[0169] In the RRC idle state, the UE may transmit to the network a UE capability that can execute AIML prediction / AIML inference / AIML model training and store the acquired AIML data.

[0170] In the RRC idle state, the UE may transmit to the network a UE capability that can perform AIML prediction / AIML inference / AIML model training and report AIML data upon request from the network.

[0171] (3.7) Operation Example 6 The above-mentioned AIMLIdleConfig can be configured from the core network or OAM, RIC, or SMO, but a specific configuration procedure has not been established. Also, the AIMLIdleConfig needs to be exchanged between gNBs when a UE performs handover, reconnection, or dual connectivity, but a specific exchange procedure has not been established.

[0172] In consideration of this situation, in this operation example, the AMF or OAM may trigger AI / ML data collection for the AI / ML data collection target UE. For example, AIMLIdleConfig may be included in the initial context setup request message, and AIML data collection may be triggered for the target UE (specific UE ID).

[0173] When a handover request is sent from the source gNB to the target gNB during a UE handover, the AIMLIdleConfig may be included in the handover request.

[0174] In the case of a CU-DU split gNB, when a UE context setup request is sent from the CU to the DU, the AIMLIdleConfig may be included in the UE context setup request.

[0175] When the UE reconnects to the network (which may be a cell), the new gNB sends a Retrieve UE context request to the old gNB, and the old gNB sends a Retrieve UE context response to the new gNB, and the AIMLIdleConfig may be included in this message.

[0176] When the UE establishes dual connectivity (DC), the MN transmits an S-NODE ADDITION REQUEST to the SN, and the S-NODE ADDITION REQUEST may include an AIMLIdleConfig.

[0177] In addition, the RIC or SMO may trigger AI / ML data collection for the UE that is the target of AI / ML data collection. Note that, as described above, *AIMLIdleConfig may be read as loggedAIMLConfig.

[0178] FIG. 20 shows an example of a sequence relating to AIMLIdleConfig in the initial UE context setup according to the sixth operation example.

[0179] FIG. 21 shows an example of a sequence relating to AIMLIdleConfig in a handover according to the sixth operation example.

[0180] FIG. 22 shows an example of a sequence related to AIMLIdleConfig in a CU-DU separated configuration according to the sixth operation example.

[0181] FIG. 23 shows an example of a sequence relating to AIMLIdleConfig in UE context retrieval according to the sixth operation example.

[0182] FIG. 24 shows an example of a sequence related to AIMLIdleConfig in dual connectivity according to the sixth operation example.

[0183] FIG. 25 shows an example of notification of AIMLIdleConfig when the O-RAN architecture according to the sixth operation example is applied.

[0184] As shown in Figures 20 to 25, AIMLIdleConfig may be transmitted and received between the UE, gNB (including CU-DU separation configuration), and AMF.

[0185] According to the operational example described above, when configuring an AI / ML model from the network to a UE, specifically when configuring an AIML config, the AIML session reference ID, AIML data collection session ID, AIML model training session ID, AIML inference session ID, AIML model training environment ID, AIML model inference environment ID, and AIML prediction in a specific area (AIMLAreaConfig) can be used to identify and track the AIML session.

[0186] Furthermore, according to the above-described operation example, when the UE transitions to the RRC idle state and then returns to the RRC connected state from the RRC idle state, the UE can notify the network that it holds the AIML data. Also, the AIML configuration can be applied to the UE in the RRC idle state, and even when the UE performs handover, reconnection, or dual connectivity, the contents of the AIML configuration can be reliably handed over to the associated RAN node.

[0187] That is, according to the above-described operational example, control utilizing AI / ML models can be performed reliably over a wider range, which can contribute to improving the quality and capacity of the wireless communication system 10 as a whole.

[0188] (4) Other Embodiments Although the embodiments have been described above, it will be obvious to those skilled in the art that the present invention is not limited to the description of the embodiments, and that various modifications and improvements are possible.

[0189] For example, in the above-described embodiment, operation examples 1 to 6 have been described, but only operations according to some of the operation examples may be applied.

[0190] In the above description, configure, activate, update, indicate, enable, specify, and select may be interchangeable. Similarly, link, associate, correspond, and map may be interchangeable, and allocate, assign, monitor, and map may be interchangeable.

[0191] Furthermore, specific, dedicated, UE-specific, and UE-dedicated may be interchangeable. Similarly, common, shared, group-common, UE-common, and UE-shared may be interchangeable.

[0192] In the present disclosure, terms such as "precoding," "precoder," "weight (precoding weight)," "Quasi-Co-Location (QCL)," "Transmission Configuration Indication state (TCI state)," "spatial relation," "spatial domain filter," "transmit power," "phase rotation," "antenna port," "antenna port group," "layer," "number of layers," "rank," "resource," "resource set," "resource group," "beam," "beam width," "beam angle," "antenna," "antenna element," "panel," etc. may be used interchangeably.

[0193] Furthermore, the block diagrams (FIGS. 2 and 3) used in the description of the above-described embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0194] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how each is implemented.

[0195] Furthermore, the above-described gNB100 and UE200 (the devices) may function as a computer that performs processing of the wireless communication method of the present disclosure. Figure 26 is a diagram showing an example of the hardware configuration of the devices. As shown in Figure 26, the devices may be configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0196] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the apparatus may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0197] Each functional block of the device (see FIGS. 2 and 3) is realized by any hardware element of the computer device or a combination of the hardware elements.

[0198] In addition, each function of the device is realized by loading specified software (programs) onto hardware such as processor 1001 and memory 1002, causing processor 1001 to perform calculations, control communication via communication device 1004, and control at least one of reading and writing data in memory 1002 and storage 1003.

[0199] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, and registers.

[0200] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. Furthermore, the various processes described above may be executed by a single processor 1001, or may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0201] The memory 1002 is a computer-readable recording medium and may be configured by at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store a program (program code), a software module, etc., capable of executing a method according to an embodiment of the present disclosure.

[0202] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a Compact Disc ROM (CD-ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned recording medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0203] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0204] The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize, for example, at least one of Frequency Division Duplex (FDD) and Time Division Duplex (TDD).

[0205] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0206] Furthermore, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0207] Furthermore, the device may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0208] Furthermore, the notification of information is not limited to the aspects / embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., RRC signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0209] Each aspect / embodiment described in the present disclosure may be applied to at least one of a system using Long Term Evolution (LTE), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, a 4th generation mobile communication system (4G), a 5th generation mobile communication system (5G), a 6th generation mobile communication system (6G), an xth generation mobile communication system (xG) (where x is, for example, an integer or a decimal), Future Radio Access (FRA), New Radio (NR), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), or other suitable system, and a next-generation system extended based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G) may also be applied.

[0210] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0211] In the present disclosure, a specific operation described as being performed by a base station may also be performed by its upper node in some cases. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal may be performed by at least one of the base station and another network node other than the base station (e.g., MME or S-GW, etc., but are not limited to these). Although the above example illustrates a case where there is one other network node other than the base station, a combination of multiple other network nodes (e.g., MME and S-GW) may also be used.

[0212] Information, signals (information, etc.) may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer), or may be input and output via multiple network nodes.

[0213] The input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added. The output information may be deleted. The input information may be transmitted to another device.

[0214] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0215] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0216] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0217] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0218] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0219] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0220] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0221] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0222] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0223] In this disclosure, terms such as "base station (BS)," "radio base station," "fixed station," "NodeB," "eNodeB (eNB)," "gNodeB (gNB)," "access point," "transmission point," "reception point," "transmission / reception point," "cell," "sector," "cell group," "carrier," and "component carrier" may be used interchangeably. Base stations may also be referred to by terms such as macrocell, small cell, femtocell, and picocell.

[0224] A base station can accommodate one or more (e.g., three) cells (also called sectors). When a base station accommodates multiple cells, the overall coverage area of ​​the base station can be divided into multiple smaller areas, and each smaller area can be provided with communication services by a base station subsystem (e.g., a small indoor base station (Remote Radio Head: RRH)).

[0225] The terms "cell" or "sector" refer to part or all of the coverage area of ​​a base station and / or base station subsystem that provides communication services within that coverage area.

[0226] In the present disclosure, the base station transmitting information to a terminal may be interpreted as the base station instructing the terminal to control or operate based on the information.

[0227] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," etc. may be used interchangeably.

[0228] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0229] At least one of the base station and the mobile station may be referred to as a transmitting device, a receiving device, a communication device, etc. At least one of the base station and the mobile station may be a device mounted on a mobile object, the mobile object itself, etc. The mobile object refers to a movable object, and may move at any speed. Naturally, this also includes cases where the mobile object is stationary. Examples of the mobile object include, but are not limited to, vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, handcars, rickshaws, ships and other watercraft, airplanes, rockets, satellites, drones (registered trademark), multicopters, quadcopters, balloons, and objects mounted thereon. The mobile object may also be a mobile object that moves autonomously based on an operational command. It may be a vehicle (e.g., a car, an airplane, etc.), an unmanned mobile object (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). At least one of the base station and the mobile station may be a device that does not necessarily move during communication operations. For example, at least one of the base station and the mobile station may be an IoT (Internet of Things) device such as a sensor.

[0230] Furthermore, a base station in the present disclosure may be read as a mobile station (user terminal, the same applies hereinafter). For example, the aspects / embodiments of the present disclosure may be applied to a configuration in which communication between a base station and a mobile station is replaced with communication between multiple mobile stations (which may be called, for example, Device-to-Device (D2D) or Vehicle-to-Everything (V2X)). In this case, the mobile station may be configured to have the functions of a base station. Furthermore, terms such as "uplink" and "downlink" may be read as terms corresponding to terminal-to-terminal communication (for example, "side"). For example, terms such as an uplink channel and a downlink channel may be read as a side channel (or sidelink).

[0231] Similarly, a mobile station in the present disclosure may be interpreted as a base station, in which case the base station may have the functions of a mobile station.

[0232] A radio frame may be composed of one or more frames in the time domain. Each of the one or more frames in the time domain may be called a subframe. A subframe may further be composed of one or more slots in the time domain. A subframe may have a fixed time length (e.g., 1 ms) that is independent of numerology.

[0233] Numerology may be communication parameters that apply to the transmission and / or reception of a signal or channel, such as subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame structure, specific filtering operations performed by the transceiver in the frequency domain, and specific windowing operations performed by the transceiver in the time domain.

[0234] A slot may consist of one or more symbols in the time domain (such as an Orthogonal Frequency Division Multiplexing (OFDM) symbol, a Single Carrier Frequency Division Multiple Access (SC-FDMA) symbol, etc.) A slot may be a numerology-based time unit.

[0235] A slot may include multiple minislots. Each minislot may consist of one or more symbols in the time domain. A minislot may also be called a subslot. A minislot may consist of fewer symbols than a slot. A PDSCH (or PUSCH) transmitted in a time unit larger than a minislot may be called PDSCH (or PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using a minislot may be called PDSCH (or PUSCH) mapping type B.

[0236] The radio frame, subframe, slot, minislot, and symbol all represent time units for transmitting signals, and may be referred to by other names corresponding to the radio frame, subframe, slot, minislot, and symbol.

[0237] For example, one subframe may be referred to as a transmission time interval (TTI), multiple consecutive subframes may be referred to as a TTI, or one slot or one minislot may be referred to as a TTI. That is, at least one of the subframe and the TTI may be a subframe (1 ms) in existing LTE, a period shorter than 1 ms (e.g., 1-13 symbols), or a period longer than 1 ms. Note that the unit representing the TTI may be called a slot, minislot, etc., instead of a subframe.

[0238] Here, TTI refers to, for example, the smallest time unit for scheduling in wireless communication. For example, in an LTE system, a base station schedules each user terminal to allocate radio resources (such as frequency bandwidth and transmission power that can be used by each user terminal) in TTI units. Note that the definition of TTI is not limited to this.

[0239] The TTI may be a transmission time unit for a channel-encoded data packet (transport block), a code block, a code word, etc., or may be a processing unit for scheduling, link adaptation, etc. When a TTI is given, the time interval (e.g., the number of symbols) to which a transport block, a code block, a code word, etc. is actually mapped may be shorter than the TTI.

[0240] In addition, when one slot or one minislot is called a TTI, one or more TTIs (i.e., one or more slots or one or more minislots) may be the minimum time unit for scheduling, and the number of slots (minislots) constituting the minimum time unit for scheduling may be controlled.

[0241] A TTI having a time length of 1 ms may be referred to as a regular TTI (TTI in LTE Rel. 8-12), normal TTI, long TTI, regular subframe, normal subframe, long subframe, slot, etc. A TTI shorter than a regular TTI may be referred to as a shortened TTI, short TTI, partial or fractional TTI, shortened subframe, short subframe, minislot, subslot, slot, etc.

[0242] In addition, a long TTI (e.g., a normal TTI, a subframe, etc.) may be interpreted as a TTI having a time length of more than 1 ms, and a short TTI (e.g., a shortened TTI, etc.) may be interpreted as a TTI having a TTI length shorter than the TTI length of a long TTI and equal to or greater than 1 ms.

[0243] A resource block (RB) is a resource allocation unit in the time domain and the frequency domain, and may include one or more consecutive subcarriers in the frequency domain. The number of subcarriers included in an RB may be the same regardless of numerology, for example, 12. The number of subcarriers included in an RB may be determined based on numerology.

[0244] The time domain of an RB may include one or more symbols and may have a length of one slot, one minislot, one subframe, or one TTI, each of which may consist of one or more resource blocks.

[0245] Note that one or more RBs may also be called a physical resource block (PRB), a sub-carrier group (SCG), a resource element group (REG), a PRB pair, an RB pair, etc.

[0246] Furthermore, a resource block may be composed of one or more resource elements (REs). For example, one RE may be a radio resource region of one subcarrier and one symbol.

[0247] A Bandwidth Part (BWP) (which may also be referred to as a fractional bandwidth) may represent a subset of contiguous common resource blocks (RBs) for a given numerology on a given carrier, where the common RBs may be identified by their index relative to a common reference point of the carrier. PRBs may be defined in a given BWP and numbered within that BWP.

[0248] The BWP may include a BWP for UL (UL BWP) and a BWP for DL ​​(DL BWP). One or more BWPs may be configured for a UE within one carrier.

[0249] At least one of the configured BWPs may be active, and the UE may not expect to transmit or receive a given signal / channel outside the active BWP. Note that the terms "cell," "carrier," etc. in this disclosure may be read as "BWP."

[0250] The above-described structures of the radio frame, subframe, slot, minislot, and symbol are merely examples. For example, the number of subframes included in a radio frame, the number of slots per subframe or radio frame, the number of minislots included in a slot, the number of symbols and RBs included in a slot or minislot, the number of subcarriers included in an RB, the number of symbols in a TTI, the symbol length, the cyclic prefix (CP) length, and other configurations may be changed in various ways.

[0251] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0252] The reference signal may also be abbreviated as Reference Signal (RS) and may be called a pilot depending on the applicable standard.

[0253] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0254] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0255] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0256] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0257] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0258] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0259] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0260] 27 shows an example of the configuration of a vehicle 2001. As shown in Fig. 27, the vehicle 2001 includes a drive unit 2002, a steering unit 2003, an accelerator pedal 2004, a brake pedal 2005, a shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, an axle 2009, an electronic control unit 2010, various sensors 2021 to 2029, an information service unit 2012, and a communication module 2013.

[0261] The drive unit 2002 is composed of, for example, an engine, a motor, or a hybrid of an engine and a motor. The steering unit 2003 includes at least a steering wheel (also called a handle) and is configured to steer at least one of the front wheels and the rear wheels based on the operation of the steering wheel operated by the user. The electronic control unit 2010 is composed of a microprocessor 2031, memory (ROM, RAM) 2032, and a communication port (IO port) 2033. Signals from various sensors 2021 to 2027 provided in the vehicle are input to the electronic control unit 2010. The electronic control unit 2010 may also be called an ECU (Electronic Control Unit).

[0262] The signals from the various sensors 2021 to 2028 include a current signal from a current sensor 2021 that senses the current of the motor, a rotation speed signal of the front and rear wheels obtained by a rotation speed sensor 2022, an air pressure signal of the front and rear wheels obtained by an air pressure sensor 2023, a vehicle speed signal obtained by a vehicle speed sensor 2024, an acceleration signal obtained by an acceleration sensor 2025, an accelerator pedal depression amount signal obtained by an accelerator pedal sensor 2029, a brake pedal depression amount signal obtained by a brake pedal sensor 2026, a shift lever operation signal obtained by a shift lever sensor 2027, and a detection signal for detecting obstacles, vehicles, pedestrians, etc. obtained by an object detection sensor 2028.

[0263] The information service unit 2012 is composed of various devices, such as a car navigation system, an audio system, speakers, a television, and a radio, for providing (outputting) various types of information, such as driving information, traffic information, and entertainment information, and one or more ECUs for controlling these devices. The information service unit 2012 uses information acquired from external devices via the communication module 2013, etc., to provide various types of multimedia information and multimedia services to the occupants of the vehicle 1.

[0264] The information service unit 2012 may include input devices (e.g., keyboards, mice, microphones, switches, buttons, sensors, touch panels, etc.) that accept input from the outside, and may also include output devices (e.g., displays, speakers, LED lamps, touch panels, etc.) that output to the outside.

[0265] The driving assistance system unit 2030 is composed of various devices that provide functions for preventing accidents and reducing the driver's driving burden, such as millimeter-wave radar, LiDAR (Light Detection and Ranging), cameras, positioning locators (e.g., GNSS, etc.), map information (e.g., high-definition (HD) maps, autonomous vehicle (AV) maps, etc.), gyro systems (e.g., IMU (Inertial Measurement Unit), INS (Inertial Navigation System), etc.), AI (Artificial Intelligence) chips, and AI processors, as well as one or more ECUs that control these devices. The driving assistance system unit 2030 also transmits and receives various information via the communication module 2013 to realize driving assistance functions or autonomous driving functions.

[0266] The communication module 2013 can communicate with the microprocessor 2031 and components of the vehicle 1 via the communication port. For example, the communication module 2013 transmits and receives data via the communication port 2033 to and from a driving unit 2002, a steering unit 2003, an accelerator pedal 2004, a brake pedal 2005, a shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, an axle 2009, a microprocessor 2031 and memory (ROM, RAM) 2032 in the electronic control unit 2010, and sensors 2021 to 2028, which are provided in the vehicle 2001.

[0267] The communication module 2013 is a communication device that can be controlled by the microprocessor 2031 of the electronic control unit 2010 and can communicate with an external device. For example, it transmits and receives various information to and from the external device via wireless communication. The communication module 2013 may be located either inside or outside the electronic control unit 2010. The external device may be, for example, a base station, a mobile station, or the like.

[0268] The communication module 2013 may transmit at least one of signals from the above-mentioned various sensors 2021 to 2028 input to the electronic control unit 2010, information obtained based on the signals, and information based on input from the outside (user) obtained via the information service unit 2012 to an external device via wireless communication. The electronic control unit 2010, the various sensors 2021 to 2028, the information service unit 2012, etc. may be referred to as input units that accept input. For example, the PUSCH transmitted by the communication module 2013 may include information based on the above-mentioned input.

[0269] The communication module 2013 receives various information (traffic information, traffic signal information, vehicle-to-vehicle information, etc.) transmitted from external devices and displays it on an information service unit 2012 provided in the vehicle. The information service unit 2012 may also be called an output unit that outputs information (for example, outputs information to a device such as a display or speaker based on the PDSCH (or data / information decoded from the PDSCH) received by the communication module 2013). The communication module 2013 also stores the various information received from external devices in a memory 2032 that can be used by the microprocessor 2031. Based on the information stored in the memory 2032, the microprocessor 2031 may control the drive unit 2002, steering unit 2003, accelerator pedal 2004, brake pedal 2005, shift lever 2006, left and right front wheels 2007, left and right rear wheels 2008, axles 2009, sensors 2021 to 2028, and the like provided in the vehicle 2001.

[0270] (Supplementary Note 1) The above disclosure may be expressed as follows: A first feature is a terminal including a receiving unit that receives setting information related to a learning model, and a control unit that executes control using the learning model based on the setting information, wherein the receiving unit receives the setting information including identification information of a session for the learning model, and the control unit selects the session based on the identification information.

[0271] In a second feature based on the first feature, the receiving unit receives the setting information including the identification information and network information related to a network to which the terminal is connected.

[0272] A third feature, in the first or second feature, further includes a transmission unit that transmits a learning report including a prediction result using the learning model and the identification information to a network.

[0273] A fourth feature is any one of the first to third features, wherein the transmission unit transmits the learning report including identification information related to the learning model.

[0274] (Supplementary Note 2) The above disclosure may be expressed as follows: A first feature is a wireless base station including: a receiver that receives, from a network, an initial context setting request message for a terminal, the initial context setting request message including setting information related to a learning model; and a transmitter that transmits the setting information to the terminal in response to receiving the initial context setting request message, wherein the receiver receives the setting information including identification information associated with data collection related to the learning model, and the transmitter transmits the setting information including the identification information.

[0275] In a second feature based on the first feature, the transmission unit transmits the trigger for data collection, which includes the identification information, to the terminal.

[0276] A third feature based on the first or second feature is that, when the terminal performs a handover to another radio base station, the transmitter transmits the setting information to the other radio base station.

[0277] A fourth feature is the first to third feature, wherein the transmission unit transmits the setting information to the terminal when the terminal reconnects to the network.

[0278] A fifth feature, in any one of the first to fourth features, is that the transmission unit transmits the setting information to the terminal when the terminal executes dual connectivity.

[0279] (Supplementary Note 3) The above disclosure may be expressed as follows: A first feature is a terminal including a receiving unit that receives setting information related to a learning model, and a control unit that executes control using the learning model based on the setting information, wherein the receiving unit receives the setting information including area information indicating a geographical area to which the learning model can be applied, and the control unit determines the geographical area to which the learning model is applied based on the area information.

[0280] A second feature is the first feature, wherein the receiving unit receives the area information including at least one of a frequency band and a combination of frequency bands to which the learning model can be applied.

[0281] A third feature is the first or second feature, wherein the receiving unit receives the area information including a bandwidth portion to which the learning model can be applied.

[0282] A fourth feature is the first to third feature, wherein the receiving unit receives the area information including information about a beam to which the learning model can be applied.

[0283] (Supplementary Note 4) The above disclosure may be expressed as follows: A first feature is a terminal including: a control unit that controls generation of prediction result data using a learning model; and a transmission unit that transmits, to a network, a radio resource control layer message including an indication that the data is held.

[0284] In a second feature based on the first feature, the transmitter transmits the message including the indication at a timing when the radio resource control layer transitions from an idle state to a connected state.

[0285] A third feature based on the first or second feature is that the transmitter transmits the message including the indication at a timing when the terminal is handed over to another radio base station.

[0286] A fourth feature based on the first to third features is that the transmission unit transmits the message including the indication at a timing when the terminal reconnects to the network.

[0287] (Supplementary Note 5) The above disclosure may be expressed as follows: A first feature is a terminal including: a receiver that receives, from a network, a release message of a radio resource control layer including idle setting information of a learning model that is applied when the radio resource control layer is in an idle state, or system information including the idle setting information; and a controller that executes control using the learning model based on the idle setting information.

[0288] A second feature is the first feature, wherein the receiving unit receives the release message or the system information including an instruction to activate or deactivate the learning model, and the control unit controls the activation or deactivation of the learning model based on the instruction.

[0289] A third feature is, in the first or second feature, the receiving unit receives the idle setting information including identification information of a session for the learning model, and the control unit selects the session based on the identification information.

[0290] (Supplementary Note 6) The above disclosure may be expressed as follows: A first feature is a radio base station including: a receiver that receives, from a network, an initial context setting request message for a terminal, the initial context setting request message including setting information related to a learning model; and a transmitter that transmits the setting information to the terminal in response to reception of the initial context setting request message, wherein the receiver receives the initial context setting request message including idle setting information of the learning model to be applied when the terminal is in an idle state in a radio resource control layer, and the transmitter transmits the idle setting information to the terminal.

[0291] A second feature based on the first feature is that, when the terminal performs a handover to another radio base station, the transmitter transmits the idle setting information to the other radio base station.

[0292] A third feature based on the first or second feature is that the transmitter transmits the idle setting information to the terminal when the terminal reconnects to the network.

[0293] A fourth feature, in any one of the first to third features, is that the transmitter transmits the idle setting information to the terminal when the terminal executes dual connectivity.

[0294] 10 Wireless communication system 20 NG-RAN 40 OAM / RIC 50 NF 100 gNB 110 Wireless communication unit 120 Handover processing unit 130 AI / ML model unit 140 Control unit 200 UE 210 Wireless communication unit 215 AI / ML model unit 220 Measurement processing unit 230 Handover execution unit 240 Control unit 1001 Processor 1002 Memory 1003 Storage 1004 Communication device 1005 Input device 1006 Output device 1007 Bus 2001 Vehicle 2002 Drive unit 2003 Steering unit 2004 Accelerator pedal 2005 Brake pedal 2006 Shift lever 2007 Left and right front wheels 2008 Left and right rear wheels 2009 Axle 2010 Electronic control unit 2012 Information service section 2013 Communication module 2021 Current sensor 2022 RPM sensor 2023 Air pressure sensor 2024 Vehicle speed sensor 2025 Acceleration sensor 2026 Brake pedal sensor 2027 Shift lever sensor 2028 Object detection sensor 2029 Accelerator pedal sensor 2030 Driving assistance system section 2031 Microprocessor 2032 Memory (ROM, RAM) 2033 Communication port

Claims

a receiving unit that receives setting information related to a learning model; a control unit that executes control using the learning model based on the setting information; Equipped with The receiving unit receives the setting information including identification information of a session for the learning model, The control unit is a terminal that selects the session based on the identification information. 　 The terminal according to claim 1 , wherein the receiving unit receives the setting information including the identification information and network information related to a network to which the terminal is connected. 　 The terminal according to claim 1 , further comprising a transmitting unit configured to transmit a learning report including a prediction result using the learning model and the identification information to a network. 　 The terminal according to claim 3 , wherein the transmission unit transmits the learning report including identification information related to the learning model. 　 a transmission unit that transmits setting information related to the learning model to the terminal; a control unit that controls the terminal based on a prediction result using the learning model; Equipped with The transmitter is a radio base station that transmits the setting information including identification information of a session for the learning model. 　 receiving configuration information for a learning model; executing control using the learning model based on the setting information; Including, In the receiving step, the setting information including identification information of a session for the learning model is received; In the step of executing the control, the terminal selects the session based on the identification information.

Images