Wireless base station and wireless communication method

Abstract

A wireless base station is provided with: a control unit that performs control pertaining to communication with a terminal using a learning model; and a reception unit that, when the learning model is used, receives learning model information relating to the learning model applied to the communication from the network. The control unit selects, on the basis of the learning model information, a learning model corresponding to a scene related to radio wave propagation or a channel between the terminals.

Description

Technical Field

[0001] The present disclosure relates to a radio base station and a wireless communication method using an AI / ML model (AI / ML Model). Background Art

[0002] The 3rd Generation Partnership Project (3GPP, registered trademark) has standardized the 5th generation mobile communication system (also referred to as 5G, New Radio (NR), or Next Generation (NG)), and has also standardized the next generation, which is called Beyond 5G, 5G Evolution, or 6G.

[0003] In 3GPP Release 17, both parties agreed to apply artificial intelligence (AI) / machine learning (ML) to the radio access network. In addition, in 3GPP Release 18, the optimization of the mobility of a terminal (User Equipment: UE) based on AI / ML was studied.

[0004] For example, scenarios and processes for using a learning model (AI / ML Model) to achieve the optimal mobility of a UE (minimization of call loss, radio link failure, unnecessary handovers, etc.) were studied (see Non-Patent Document 1).

[0005] In addition, both parties agreed to study the impact on 3GPP specifications and specific signaling, etc. in the case of using such an AI / ML model (AI / ML Model) (Non-Patent Document 2).

[0006] Prior Art Documents

[0007] Non-Patent Documents

[0008] Non-Patent Document 1: "Study on Artificial Intelligence(AI) / Machine Learning(ML) for NR Air Interface", RP-221348, 3GPP TSG RAN Meeting#96, 3GPP, June 2022

[0009] Non-Patent Document 2: "Draft Report of 3GPP TSG RAN WG1#110bis-e v0.1.0", 3GPP, October 2022 Summary of the Invention

[0010] In 3GPP, selecting a specific AI / ML model according to each scenario using an AI / ML model has been discussed. However, there is a problem as follows: it is not easy to select an appropriate AI / ML model for each scenario.

[0011] In addition, there is a problem as follows: in the case of performing dual connectivity (DC) in which communication is separately and simultaneously performed between a UE and multiple NG-RAN nodes (NG-RAN Node), it is difficult to select an appropriate AI / ML model and set the selected AI / ML model for the UE.

[0012] Therefore, the following disclosure has been completed in view of such a situation, and an object thereof is to provide a radio base station and a wireless communication method capable of selecting an appropriate AI / ML model corresponding to a scenario using an AI / ML model including during the execution of dual connectivity.

[0013] One aspect of the present disclosure is a terminal (UE 200), which includes: a control unit (control unit 240) that executes control regarding communication with a network using a learning model; and a transmission unit (AI / ML model unit 215) that, when using the learning model, transmits surrounding environment information indicating the surrounding environment of the terminal position to the network.

[0014] One aspect of the present disclosure is a radio base station (gNB 100), which includes: a control unit (control unit 140) that executes control regarding communication with a terminal using a learning model; and a reception unit (AI / ML model unit 130) that, when using the learning model, receives surrounding environment information indicating the surrounding environment of the terminal position from the terminal.

[0015] One aspect of the present disclosure is a radio base station (gNB 100), which includes a first device and one or more second devices connected to the first device. The first device includes: a control unit (control unit 140) that executes control regarding communication with a terminal using a learning model; and a transmission unit that, when using the learning model, transmits surrounding environment information indicating the surrounding environment of the terminal position to the second device. The second device includes: a reception unit that receives the surrounding environment information; and a control unit that selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and the radio base station based on the surrounding environment information.

[0016] One aspect of the present disclosure is a radio base station (gNB 100) including a first device and one or more second devices connected to the first device. The second device includes: a control unit (control unit 140) that executes control regarding communication with a terminal using a learning model; and a transmission unit (AI / ML model unit 130) that, when using the learning model, transmits surrounding environment information representing the surrounding environment of the terminal position to the first device. The first device includes: a reception unit (AI / ML model unit 130) that receives the surrounding environment information; and a control unit (control unit 140) that selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and the radio base station based on the surrounding environment information.

[0017] One aspect of the present disclosure is a radio base station (gNB 100) including: a control unit (control unit 140) that executes control regarding communication with a terminal using a learning model; and a reception unit (AI / ML model unit 130) that, when using the learning model, receives learning model information related to the learning model applied to the communication from a network. The control unit selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal based on the learning model information. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is an overall schematic configuration diagram of the wireless communication system 10.

[0019] Figure 2 is a functional block configuration diagram of gNB 100.

[0020] Figure 3 is a functional block configuration diagram of UE 200.

[0021] Figure 4 is a diagram showing a functional framework for RAN intelligence.

[0022] Figure 5 is a diagram showing a timing example (Part 1) of AI / ML model (AI / ML Model) selection related to Operation Example 1.

[0023] Figure 6 is a diagram showing a timing example (Part 2) of AI / ML model (AI / ML Model) selection related to Operation Example 1.

[0024] Figure 7 is a diagram showing a timing example (Part 3) of AI / ML model (AI / ML Model) selection related to Operation Example 1.

[0025] Figure 8It is a diagram showing an example of the timing of selecting an AI / ML model (AI / ML Model) related to Operation Example 1 (No. 4).

[0026] Figure 9 It is a diagram showing an example of the timing of selecting an AI / ML model (AI / ML Model) related to Operation Example 1 (No. 5).

[0027] Figure 10 It is a diagram showing an example of the timing of selecting an AI / ML model (AI / ML Model) related to Operation Example 1 (No. 6).

[0028] Figure 11 It is a diagram showing an example of the timing of selecting an AI / ML model (AI / ML Model) related to Operation Example 1 (No. 7).

[0029] Figure 12 It is a diagram showing an example of the handover timing of an AI / ML model (AI / ML Model) related to Operation Example 2.

[0030] Figure 13 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 3 (No. 1).

[0031] Figure 14 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 3 (No. 2).

[0032] Figure 15 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 3 (No. 3).

[0033] Figure 16 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 3 (No. 4).

[0034] Figure 17 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 4 (No. 1).

[0035] Figure 18 It is a diagram showing an example of the information exchange timing of an AI / ML model (AI / ML Model) related to Operation Example 4 (No. 2).

[0036] Figure 19 It is a diagram showing an example of the structure of a RIC based on the O-RAN architecture.

[0037] Figure 20This is a diagram showing an example of the information exchange timing diagram (Part 3) of the AI / ML model related to Operation Example 4.

[0038] Figure 21 This is a diagram showing an example of the hardware structure of gNB 100 and UE 200.

[0039] Figure 22 This is a diagram showing an example of the structure of vehicle 2001. Detailed Implementation Manner

[0040] Hereinafter, the implementation manner will be described based on the drawings. In addition, the same or similar reference numerals are assigned to the same functions and structures, and their descriptions are appropriately omitted.

[0041] (1) Overall Schematic Structure of the Wireless Communication System

[0042] Figure 1 This is an overall schematic structure diagram of the wireless communication system 10 according to this implementation manner. The wireless communication system 10 is a wireless communication system compliant with 5G New Radio (NR), and includes a Next Generation Radio Access Network 20 (hereinafter referred to as NG-RAN 20) and a terminal 200 (User Equipment 200, hereinafter referred to as UE 200).

[0043] In addition, the wireless communication system 10 may also be a wireless communication system compliant with a manner called Beyond 5G, 5G Evolution or 6G, and may also include a wireless communication system compliant with a manner called Long Term Evolution (LTE) or 4G. The wireless communication system 10 can support functions related to the Industrial Internet of Things (IIoT) and URLLC (Ultra-Reliable and Low Latency Communications).

[0044] NG-RAN 20 includes a radio base station 100 (hereinafter referred to as gNB 100). In addition, the specific structure of the wireless communication system 10, including the number of gNBs (which may be eNBs, etc.) and UEs, is not limited to Figure 1 the example shown.

[0045] In addition, gNB 100 may adopt a fronthaul (FH) interface specified by the O-RAN (Open Radio Access Network Alliance). gNB 100 may include an O-DU (O-RAN Distributed Unit) and an O-RU (O-RAN Radio Unit). gNB 100 may function as a type of NG-RAN node.

[0046] NG-RAN 20 actually includes a plurality of NG-RAN nodes, specifically, a plurality of gNBs (or ng-eNBs), and is connected to a 5G-compliant core network (5GC, not shown). In 5GC, the concept of CUPS (Control and User Plane Separation), in which the functions of the user plane and the control plane are clearly separated, can be introduced.

[0047] NG-RAN 20 may be connected to OAM / RIC 40 and NF 50 via 5GC, or directly connected to OAM / RIC 40 and NF 50 from NG-RAN 20. OAM / RIC 40 can provide functions related to the operation and maintenance of the wireless communication system 10 (OAM). In addition, OAM / RIC 40 can provide functions related to the control of NG-RAN 20 (RIC: RAN Intelligent Controller). The specific functions of the RIC are specified by the O-RAN specification (for example, O-RAN Architecture-Description 6.0). In the present embodiment, OAM / RIC 40 may constitute an entity that performs operation and maintenance or control.

[0048] The NF 50 can be interpreted as a logical node that provides network functions. The NF 50 can be included in the 5G system architecture and includes an Access and Mobility Management Function (AMF) that 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 is responsible for communication control related to location information services specified in the 5GC, etc. In addition, the UDM / UDR (Unified Data Management / User Data Repository) can also be connected in the AMF and / or SMF. Additionally, the NG-RAN 20 and 5GC can be simply expressed as "network".

[0049] In addition, the NG-RAN 20 can be connected to a server managed by a 3GPP-based service provider or a server managed outside of the provider (3GPP or non-3GPP server).

[0050] The gNB 100 is a radio base station that follows NR and performs NR-based wireless communication with the UE 200. In addition, the gNB 100 can be composed of a CU (Central Unit: central unit, the first device) and a DU (Distributed Unit: distributed unit, the second device), and the DU can be separately set in geographically different locations from the CU. The CU can be connected to one or more DUs. In addition, the gNB 100 (gNB-CU) can be connected through the Xn interface, and the CU and DU can be connected through the F1 interface.

[0051] The gNB 100 and the UE 200 can support Massive MIMO that generates beams with higher directivity by controlling wireless signals transmitted from multiple antenna elements, Carrier Aggregation (CA) that bundles the use of multiple Component Carriers (CCs), and Dual Connectivity (DC) that enables simultaneous communication between the UE and multiple NG-RAN nodes, etc.

[0052] In addition, in the wireless communication system 10, artificial intelligence (AI) / machine learning (ML) can be applied in the NG-RAN 20. Specifically, in order to optimize the mobility or handover of the UE 200 (which can also be replaced with migration, cell migration, cell selection, etc.), a learning model (hereinafter referred to as the AI / ML model) can be utilized.

[0053] The AI / ML model can also be expressed by other terms representing AI or ML, such as an artificial intelligence (AI) model or a machine learning (ML) model.

[0054] The mobility of the UE 200 can generally refer to the ease of movement or maneuverability of the UE 200, but in this embodiment, it can refer to the minimization of call drops, radio link (including beam) failures, unnecessary handovers, ping-pong states, etc.

[0055] 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 can be provided in the OAM / RIC 40 or in the gNB 100. In addition, the AI / ML model can also be provided in the UE 200.

[0056] (2) Functional block structure of the wireless communication system

[0057] Next, the functional block structure of the wireless communication system 10 will be described. Specifically, the functional block structures of the gNB 100 and the UE 200 will be described. Figure 2 This is the functional block structure diagram of the gNB 100. Figure 3 This is the functional block structure diagram of the UE 200.

[0058] (2.1) gNB 100

[0059] As Figure 2 shown, the gNB 100 includes a radio communication unit 110, a handover processing unit 120, an AI / ML model unit 130, and a control unit 140.

[0060] The radio communication unit 110 transmits a downlink signal (DL signal) compliant with NR. In addition, the radio communication unit 110 receives an uplink signal (UL signal) compliant with NR.

[0061] The handover processing unit 120 performs the handover of the UE 200. Specifically, the handover processing unit 120 performs the handover from the serving cell of the UE 200 to a neighboring other cell.

[0062] In addition, the serving cell can be interpreted as only the cell in the connection of UE 200. More strictly speaking, in the case of a UE in RRC_CONNECTED without carrier aggregation (CA) configured, there is only one serving cell that constitutes the primary cell. In the case of a UE in RRC_CONNECTED configured with CA, the serving cell can be interpreted as a set of one or more cells that includes the primary cell and all secondary cells.

[0063] Furthermore, handover can include conditional handover (CHO). When specific execution conditions are met, CHO can perform a handover initiated by UE 200. In cases where CHO cannot be applied, normal handover (which can also be referred to as CHO recovery) can be performed. In CHO recovery, after a CHO failure, UE 200 performs cell selection. If a CHO candidate cell is selected, instead of sending an RRC Reestablishment Request to the candidate target cell, the conditional RRC reconfiguration of this cell can be directly applied for reconnection.

[0064] The execution conditions can consist of one or two triggering conditions (CHO events A3 / A5 specified in 3GPP TS38.331). When a single reference signal (RS) type is triggered, up to two different triggering quantities (such as RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSRP and SINR (Signal-to-Interference plus Noise power Ratio), etc.) can be set simultaneously to evaluate the CHO execution conditions for a single candidate cell.

[0065] The AI / ML model unit 130 performs processing using a learning model (AI / ML Model). Specifically, the AI / ML model unit 130 performs processing using an optimized AI / ML model applied to the mobility and / or handover of UE 200.

[0066] For example, the AI / ML model unit 130 can determine the validity period of the learned (trained) AI / ML model. In addition, the AI / ML model unit 130 can evaluate the performance of the AI / ML model and determine whether the performance of the AI / ML model is lower than a specified level.

[0067] The AI / ML model unit 130 can re-learn (re-train) the AI / ML model when the validity period of the AI / ML model expires or when the performance of the AI / ML model is lower than the specified level. In addition, the AI / ML model itself can be mounted on the gNB 100 or on other network nodes (network devices) such as the OAM / RIC 40.

[0068] Whether the performance of the AI / ML model is lower than the specified level can be determined based on processes related to the optimization of the mobility and / or handover of the UE 200 using the AI / ML model, such as the above-mentioned call drop, radio link (including beam) failure, unnecessary handover, and the accuracy (achievement rate) of minimizing the ping-pong state.

[0069] In addition, when using the AI / ML model, the AI / ML model unit 130 can form a receiving unit that receives ambient environment information representing the ambient environment of the UE 200's location from the UE 200. Specifically, the AI / ML model unit 130 can receive information (scenario info) related to the scenario in which the AI / ML model is applied, site information (site info), the speed, altitude, location information, etc. of the UE 200 from the UE 200.

[0070] In addition, the AI / ML model unit 130 can form a transmitting unit that transmits at least a part of the ambient environment information to another radio base station (gNB) as the handover target when the UE 200 performs a handover.

[0071] As described above, the ambient environment information only needs to include at least any one of the scenario in which the AI / ML model is applied, the terminal location of the UE 200, and the movement state of the UE 200. The terminal location can be the moving longitude information or relative information based on the location of the gNB, etc.

[0072] In addition, the scenario refers to any situation as long as an AI / ML model is used, without specific limitations. Narrowly speaking, it can refer to a radio wave propagation model or a channel model between the UE 200 and the gNB 100. For example, from the perspective of the channel model, it can include scenarios such as indoor, outdoor, urban, rural, shopping mall, office, campus, train station, etc. Alternatively, it can include a high-speed mobile scenario where the UE 200 (user) moves on a high-speed railway such as the Shinkansen, and an aerial mobile communication scenario applied to the UE 200 carried by a drone, etc.

[0073] In the gNB 100 with a CU / DU structure, when using an AI / ML model, the AI / ML model unit 130 of the CU (the first device) can form a transmission unit that sends the surrounding environment information as described above to the DU (the second device).

[0074] Alternatively, in the gNB 100 with a CU / DU structure, when using an AI / ML model, the AI / ML model unit 130 of the DU can form a transmission unit that sends the surrounding environment information as described above to the CU. In addition, the AI / ML model units 130 of the CU and the DU can form a reception unit that receives this surrounding environment information.

[0075] When using an AI / ML model, the AI / ML model unit 130 can form a reception unit that receives learning model information from the network, and this learning model information is related to the AI / ML model applied to communicate with the UE 200. Specifically, the AI / ML model unit 130 can receive from the network the content of the AI / ML model (AI model), the identification information of the AI / ML model (AI model ID), the scenario applied to the AI / ML model, the mapping relationship between each AI model and the scenario, etc.

[0076] The learning model information can include at least any one of the identification information of the AI / ML model, the scenario, and the surrounding environment of the location of the UE 200 (the above-mentioned site information (site info), the speed, altitude, location information, etc. of the UE 200).

[0077] In addition, the AI / ML model unit 130 can form a transmission unit that sends the AI / ML model selected by the control unit 140 to the UE 200.

[0078] The control unit 140 controls each functional block that constitutes the gNB 100. In particular, in the present embodiment, the control unit 140 can perform mobility optimization or handover of the UE 200 (which can be interpreted as a mobility optimization process including them) using the results of the AI / ML model. In this way, the control unit 140 can perform control related to communication with the UE 200 using the AI / ML model.

[0079] Specifically, the control unit 140 can use the AI / ML model to determine the waiting cell of the UE 200 or the target cell and / or NG-RAN node to which the UE migrates. The control unit 140 can perform control to make the UE 200 wait or migrate to the waiting target or migration target of the UE 200 determined as such.

[0080] In addition, in the case of CHO, the control unit 140 can determine the probability of migrating to each candidate target cell (Estimated Arrival Probability) based on the behavior of the UE 200 (such as past cell residence history, UE speed, UE trajectory, shipping information, etc.) using the AI / ML model.

[0081] As described above, the gNB 100 can adopt a CU / DU structure. The gNB 100 can include a CU (the first device) and one or more DUs (the second device) connected to the CU, and the CU and the DU can be provided with a control unit 140 that uses the AI / ML model to perform control related to communication with the UE 200.

[0082] The control unit 140 can select an AI / ML model corresponding to the scenario related to radio wave propagation or the channel between the UE 200 and the gNB 100 based on the above-mentioned surrounding environment information.

[0083] In addition, the control unit 140 can select an AI / ML model corresponding to the scenario related to radio wave propagation or the channel between the UE 200 based on the above-mentioned learning model information.

[0084] In addition, as described above, the scenario can refer to a radio wave propagation model or a channel model between the UE 200 and the gNB 100.

[0085] In addition, in this embodiment, the channel includes a control channel and a data channel. The control channel includes a PDCCH (Physical Downlink Control Channel), a PUCCH (Physical Uplink Control Channel), a PRACH (Physical Random Access Channel), a PBCH (Physical Broadcast Channel), and the like.

[0086] In addition, the data channel includes a PDSCH (Physical Downlink Shared Channel), a PUSCH (Physical Uplink Shared Channel), and the like.

[0087] In addition, the reference signal includes a demodulation reference signal (DMRS), a sounding reference signal (SRS), a phase tracking reference signal (PTRS), a channel state information reference signal (CSI-RS), and the like. The signal includes a channel and a reference signal. In addition, the data may refer to the data transmitted via the data channel.

[0088] (2.2) UE 200

[0089] As Figure 3 shown, the UE 200 includes a wireless communication unit 210, an AI / ML model unit 215, a measurement report unit 220, a handover execution unit 230, and a control unit 240.

[0090] The wireless communication unit 210 transmits an uplink signal (UL signal) compliant with NR. In addition, the wireless communication unit 210 receives a downlink signal (DL signal) compliant with NR.

[0091] The AI / ML model unit 215 performs 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 may be provided in either the gNB 100 or the UE 200, or in both.

[0092] In the case of using an AI / ML model, the AI / ML model unit 215 may constitute a transmission unit that transmits surrounding environment information representing the surrounding environment of the terminal location of the UE 200 to the network.

[0093] The measurement report unit 220 can measure the quality of the serving cell of the UE 200 and the neighboring cells of the serving cell, and report the measurement results (Measurement Report) to the network. The measurement report unit 220 may perform measurement reports of the source cell and the target cell during handover.

[0094] The quality of the measurement object may refer to, for example, the quality included in the measurement report (Measurement Report) specified in 3GPP TS38.331 (e.g., reference signal received power (Reference Signal Received Power: RSRP), reference signal received quality (Reference Signal Received Quality: RSRQ), etc.).

[0095] The handover execution unit 230 performs the handover of the UE 200. Specifically, the handover execution unit 230 may perform a handover to the target cell (NG-RAN node) to be migrated based on the control of the gNB 100.

[0096] In addition, the handover execution unit 230 can perform processing related to normal handover (traditional handover) and conditional handover (CHO).

[0097] In the case of CHO, the handover execution unit 230 may migrate to a candidate cell when the execution condition is satisfied. As described above, the execution condition may be determined based on the quality of the reference signal (RS), specifically based on the values of RSRP, RSRQ, or SINR.

[0098] In addition, the migration target of CHO may or may not be accompanied by an SCG. In other words, the cell serving as the migration target based on CHO may be a single cell or may be composed of multiple cells (which may also be replaced by a cell group) following DC.

[0099] In addition, the handover execution unit 230 can receive a handover request (handover command) of the UE 200 from the network. In this embodiment, the handover execution unit 230 may constitute a receiving unit. The handover command may include an indication (indication) such as an indication to delete the AI / ML model (AI / ML Model) for the source cell of the handover source.

[0100] The control unit 240 controls each functional block that constitutes the UE 200. Specifically, the control unit 240 can execute control related to the registration of the UE 200 to the network (waiting in a specific cell), measurement reports, and handovers of the UE 200.

[0101] When the control unit 240 executes a handover of the UE 200, it can delete the AI / ML model held for handover. Specifically, the control unit 240 can determine whether to delete the AI / ML model held at the time of handover based on the indication included in the handover command.

[0102] The object to be deleted can be the AI / ML model (AI / ML Model) itself, or the AI input data (AI input data) or AI output data (AI output data). In addition, the AI / ML model can be set for each serving cell, or for multiple serving cells (which may include secondary cells). The AI / ML model to be deleted can target the source cell of the handover source, or can include cells other than the source cell.

[0103] In addition, the control unit 240 can use the AI / ML model to execute control related to communication with the network. Specifically, the control unit 240 can select the AI / ML model corresponding to the scenario in which the AI / ML model is applied, and control communication with the network. The control unit 240 can select the AI / ML model based on an indication from the network, or can select an arbitrary AI / ML model from multiple AI / ML models according to the state of the UE 200.

[0104] For example, the control unit 240 can select the AI / ML model corresponding to the scenario related to radio wave propagation or the channel between the UE 200 and the gNB 100 based on the above-mentioned surrounding environment information.

[0105] (3) Operation of the wireless communication system

[0106] Next, the operation of the wireless communication system 10 will be described. The operations related to the mobility control of the UE 200 using the AI / ML model, the selection of the AI / ML model, the sharing of information related to the AI / ML model, and the operations related to handovers will be described.

[0107] (3.1) Example of the structure of the AI / ML model

[0108] Figure 4 Shows a functional framework for RAN intelligence. Specifically, Figure 4Shows the functional framework for RAN intelligence specified in 3GPP TR37.817.

[0109] As Figure 4 shown, the framework may include the following functions.

[0110] · Data collection: Provide input data to model training and model inference functions.

[0111] · Model training: Perform the training, validation, and testing of the ML model. As part of the model testing process, performance metrics of the model may be generated.

[0112] The model training function may also be responsible for data preparation (data preprocessing and cleaning, formatting, conversion, etc.).

[0113] · Model inference: Provide AI / ML model inference output (predictions or decisions, etc.). The model inference function may provide feedback on the model performance to the model training function. The model inference function may also be responsible for data preparation (data preprocessing and cleaning, formatting, conversion, etc.).

[0114] · Participant: Receive the output from the model inference function and trigger or execute corresponding actions.

[0115] In addition, feedback can be interpreted as the information that may be required to derive feedback on training, inference data, or performance.

[0116] As described above, the AI / ML model can be carried on the OAM / RIC 40 (or gNB 100), but the AI / ML model trained in the OAM / RIC 40 has a validity period. In the case where this validity period has passed (or even within the validity period), the performance of the AI / ML model deteriorates and the AI / ML model needs to be retrained.

[0117] (3.2) Action examples

[0118] (3.2.1) Action example 1

[0119] In this action example, a specific AI / ML model (specific AI model) is selected for each scenario where the AI / ML model is applied. Below, examples of specific signaling and processes for AI / ML model selection are described.

[0120] Figure 5 Shows an example of the timing of AI / ML model (AI / ML Model) selection related to action example 1 (Part 1). Specifically, Figure 5Shows a timing example when an AI / ML model (hereinafter, appropriately abbreviated as an AI model) exists on the gNB side.

[0121] Figure 6 Shows the timing example (Part 2) of the selection of the AI / ML model related to Action Example 1. Specifically, Figure 6 Shows a timing example when the use case of AI / ML for NR Air is positioning and the AI model exists on the LMF side.

[0122] As Figure 5 and Figure 6 shown, the UE 200 can include the surrounding environment information in the assistance information.

[0123] When the AI model exists on the gNB side, the following process can be executed.

[0124] · Step 1: The UE can send its own surrounding environment information (scenario information, site information, speed, altitude, location information, etc.) to the gNB.

[0125] · Step 2: Based on the assistance information from the UE and the configuration information on the gNB side, determine the scenario.

[0126] · Step 3: Select the AI model according to the scenario (here, an example of selecting AI model 2 is shown, and the same applies hereinafter).

[0127] · Step 4: Send the inference result of the AI model to the UE.

[0128] When the AI model exists on the LMF side, the following process can be executed.

[0129] · Step 1: The UE sends its own surrounding environment information (scenario information, site information, speed, altitude, location information, etc.) to the LMF.

[0130] · Step 2: Based on the assistance information from the UE and the configuration information on the LMF side, determine the scenario.

[0131] · Step 3: Select an AI model according to the scenario.

[0132] · Step 4: Send the inference result of the AI model to the UE.

[0133] Figure 7 Shows the timing example (No. 3) of the AI / ML model selection involved in Action Example 1. Specifically, Figure 7 Shows the timing example when the AI model exists on the gNB side. As Figure 7 shown, when the AI model exists on the gNB side, the following process can be executed.

[0134] · Step 0: Request an AI model from the UE to the gNB.

[0135] · Step 1: The gNB can send the AI model and the AI model ID to the UE. The scenario information applied to each AI model can be included. Or the mapping relationship between the AI model and each scenario can also be sent.

[0136] · Step 2: The UE can send the surrounding environment information (scenario information, site information, speed, altitude, location information, etc.) where the UE itself is located to the gNB.

[0137] · Step 3: Determine the scenario based on the assistance information from the UE and the configuration information on the gNB side.

[0138] · Step 4: Send an indication of the AI model selection to the UE according to the scenario.

[0139] · Step 5: The UE selects the AI model according to the indication from the gNB.

[0140] · Step 6: Send the inference result of the AI model to the gNB.

[0141] Figure 8 Shows the timing example (No. 4) of the AI / ML model selection involved in Action Example 1. As Figure 8As shown, when the AI model exists on the GPP or non-3GPP server side and is directly sent to the UE from the 3GPP server or non-3GPP server through the user plane (U-plane), the following process can be executed.

[0142] · Step 0: Download the AI model from the 3GPP or non-3GPP server through the user plane (U-plane).

[0143] · Step 1: The AI model and the AI model ID can be sent from the UE to the gNB. Scenario information applied to each AI model can be included. Or the mapping relationship between the AI model and each scenario can also be sent.

[0144] · Step 2: The UE's own surrounding environment information (scenario information, site information, speed, altitude, location information, etc.) can be sent from the UE to the gNB.

[0145] · Step 3: Determine the scenario based on the assistance information from the UE and the configuration information on the gNB side.

[0146] · Step 4: Send an indication of the selection of the AI model to the UE according to the scenario.

[0147] · Step 5: The UE selects the AI model according to the indication from the gNB.

[0148] · Step 6: Send the inference result of the AI model to the gNB.

[0149] Figure 9 Shows an example of the timing of the selection of the AI / ML model (AI / ML Model) involved in Action Example 1 (No. 5). Specifically, Figure 9 Shows a use case of AI / ML (AI / ML for NR Air) for NR Air as positioning (acquisition of location information), and an example of the timing between the UE and the LMF. As Figure 9 shown, when the AI model exists on the LMF side, the following process can be executed.

[0150] · Step 0: Request an AI model from the UE to the LMF.

[0151] · Step 1: The LMF may send the AI model and the AI model ID to the UE. Scenario information applicable to each AI model may be included. Alternatively, the mapping relationship between the AI model and each scenario may also be sent.

[0152] · Step 2: The UE may send its own surrounding environment information (scenario information, site information, speed, altitude, location information, etc.) to the LMF.

[0153] · Step 3: Determine the scenario based on the assistance information from the UE and the configuration information on the LMF side.

[0154] · Step 4: Send an indication of the selection of the AI model to the UE according to the scenario.

[0155] · Step 5: The UE selects the AI model according to the indication from the LMF.

[0156] · Step 6: Send the inference result of the AI model to the LMF.

[0157] Figure 10 Shows an example of the timing of selecting an AI / ML model (Example 6) involved in Action Example 1. Specifically, Figure 10 Shows an example of the timing when the AI model exists on both the UE and gNB sides. As Figure 10 shown, when the AI model exists on both the UE and gNB sides, the following process may be executed.

[0158] · Step 0: Request an AI model from the UE to the gNB.

[0159] · Step 1: The gNB may send the AI model and the AI model ID to the UE. Scenario information applicable to each AI model may be included. Alternatively, the mapping relationship between the AI model and each scenario may also be sent.

[0160] · Step 2: The UE can send the surrounding environment information (scenario info, site info, speed, altitude, location information, etc.) where the UE itself is located to the gNB.

[0161] · Step 3: Based on the assistance info from the UE and the configuration information on the gNB side, determine the scenario.

[0162] · Step 4: The gNB selects an AI model according to the scenario.

[0163] · Step 5: Send an AI model selection indication to the UE.

[0164] · Step 6: The UE selects an AI model according to the indication from the gNB.

[0165] · Step 7: Send the inference result of the AI model to the gNB.

[0166] Figure 11 Shows the timing example (No. 7) of the AI / ML model selection related to Action Example 1. Specifically, Figure 11 Shows the timing example when the AI model exists on both the UE and the LMF sides. As Figure 11 shown, when the AI model exists on both the UE and the LMF sides, the following process can be executed.

[0167] · Step 0: The UE requests an AI model from the LMF.

[0168] · Step 1: The LMF can send the AI model and the AI model ID to the UE. The scenario information applied to each AI model can be included. Or the mapping relationship between the AI model and each scenario can also be sent.

[0169] · Step 2: The UE can send the surrounding environment information (scenario info, site info, speed, altitude, location information, etc.) where the UE itself is located to the LMF.

[0170] · Step 3: Determine the scenario based on the assistance info from the UE and the configuration information on the LMF side.

[0171] · Step 4: The LMF selects an AI model according to the scenario.

[0172] · Step 5: Send an AI model selection indication to the UE.

[0173] · Step 6: The UE selects an AI model according to the indication from the LMF.

[0174] · Step 7: Send the inference result of the AI model to the LMF.

[0175] (3.2.2) Action Example 2

[0176] In this action example, when switching, the AI model applied at that time point is also handed over to the handover target.

[0177] Figure 12 An example of the handover timing sequence of the AI / ML model involved in Action Example 2 is shown. Specifically, the gNB (source node) of the handover source can send the AI model, the model ID assigned to each AI model, the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g. scenario ID, zone ID, site ID, configuration ID)), and the mapping relationship between the AI model and each scenario to the gNB (target node) of the handover target at the time of handover.

[0178] In addition, the source node can send the UE preferred model ID, or the preferred model ID in each scenario, and the AI model activation / deactivation state to the target node at the time of handover. The AI model activation / deactivation state means that, on the premise of the following situation, in order to save power of the UE, it can be deactivated when the AI model is not used.

[0179] The source node can send the preference of the UE to activate / deactivate the AI / ML model (e.g., deactivate the AI / ML model when the remaining battery of the UE is low) to the target node during handover.

[0180] (3.2.3) Action Example 3

[0181] In this action example, in the case where the NG-RAN 20 branches, that is, in the case of applying the CU / DU architecture, information related to the AI model is shared (exchanged) between the CU and the DU.

[0182] Specifically, the following process can be executed.

[0183] · When the AI model exists on the CU side and the AI model ID is assigned on the CU side, the CU can send the AI model, the AI model ID associated with each model, and the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g. scenario ID, zone ID, site ID, configuration ID)) to the DU.

[0184] · When the AI model exists on the DU side and the AI model ID is assigned on the DU side, the DU can send the AI model, the AI model ID associated with each model, and the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g. scenario ID, zone ID, site ID, configuration ID)) to the CU.

[0185] · When the control of the AI model is executed on the CU side, the CU can send the UE preferred model ID and the AI model activation / deactivation status to the DU.

[0186] · When the control of the AI model is executed on the DU side, the DU can send the UE preferred model ID and the AI model activation / deactivation status to the CU.

[0187] · The CU can send the preference of the UE to activate / deactivate the AI / ML model (e.g., deactivate the AI / ML model when the remaining battery of the UE is low) to the DU.

[0188] Figure 13 Shows the information exchange timing example (Part 1) of the AI / ML Model related to Action Example 3. Specifically, Figure 13 Shows the timing example when the AI model exists in the CU.

[0189] Figure 14 Shows the information exchange timing example (Part 2) of the AI / ML Model related to Action Example 3. Specifically, Figure 14 Shows the timing example when the AI model exists in the DU.

[0190] In Figure 13 and Figure 14 examples of the UE CONTEXT SETUP REQUEST and the UE CONTEXT SETUP RESPONSE are shown. As Figure 13 and Figure 14 shown, the AI model, the AI model ID associated with each model, and the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID) can be included in the UE CONTEXT SETUP REQUEST or the UE CONTEXT SETUP RESPONSE and shared between the CU and the DU.

[0191] Figure 15 Shows the information exchange timing example (Part 3) of the AI / ML Model related to Action Example 3. Specifically, Figure 15Shows a timing example when an AI model exists in the CU.

[0192] Figure 16 Shows an information exchange timing example (No. 4) of the AI / ML model involved in Action Example 3. Specifically, Figure 16 Shows a timing example when an AI model exists in the DU.

[0193] In Figure 15 and Figure 16 , examples of UE CONTEXT MODIFICATION REQUEST and UE CONTEXT MODIFICATION RESPONSE are shown. As Figure 13 and Figure 14 shown, the AI model, the AI model ID associated with each model, and the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g. scenario ID, zone ID, site ID, configuration ID)) can be included in the UE CONTEXT MODIFICATION REQUEST or UE CONTEXT MODIFICATION RESPONSE and shared between the CU and DU.

[0194] (3.2.4) Action Example 4

[0195] In this action example, an appropriate AI model can be set for the UE during dual connectivity (DC).

[0196] Figure 17 Shows an information exchange timing example (No. 1) of the AI / ML model involved in Action Example 4. Specifically, Figure 17 Shows a timing example when an AI model exists on the AMF side. As Figure 17 shown, when an AI model exists on the AMF side, the following process can be executed.

[0197] · Step 1: The AMF sends the AI model, the model ID assigned to each AI model, the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g., scenario ID, zone ID, site ID, configuration ID)), and the mapping relationship between the AI model and each scenario to the master node (MN) through an Initial Context Setup Request or a UE Context Modification Request.

[0198] · Step 2: The MN sends the AI model, the model ID assigned to each AI model, the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g., scenario ID, zone ID, site ID, configuration ID)), and the mapping relationship between the AI model and each scenario to the SN through an S-Node Addition Request or an S-Node Modification Request.

[0199] · Step 3: The SN sends an S-Node Addition Request Acknowledge or an S-Node Modification Request Acknowledge back to the MN.

[0200] · Step 4: MN sends the AI model on the MN side, the AI model on the SN side, the model ID assigned to each AI model, the scenario information associated with the AI model (e.g., scenario ID, zone ID, site ID, configuration ID (e.g., scenario ID, zone ID, site ID, configuration ID)), and the mapping relationship between the AI model and each scenario to the UE through RRC Reconfiguration.

[0201] · Step 5: The UE sends back RRC Reconfiguration Complete to MN.

[0202] Figure 18 Shows the information exchange timing example (Part 2) of the AI / ML model involved in Action Example 4. Specifically, Figure 18 Shows the timing example when the AI model exists on the OAM or RIC side.

[0203] Figure 19 Shows the structural example of the RIC based on the O-RAN architecture. As Figure 19 shown, the RIC can include Near-Real Time RIC and / or Non-Real Time RIC. The Near-Real Time RIC can be connected to the O-DU and the Non-Real Time RIC via interfaces (A1, E2).

[0204] In addition, the Near-Real Time RIC can be connected to the O-eNB (radio base station) via the interface (E2). The RIC included in such an O-RAN architecture can constitute the OAM / RIC 40.

[0205] In such a RIC architecture, the performance feedback of the AI / ML model can be provided to the Near-Real Time RIC or the Non-Real Time RIC.

[0206] Figure 20 Shows the information exchange timing example (Part 3) of the AI / ML model involved in Action Example 4. Specifically, Figure 20Shows a timing example when the AI model exists on the LMF side.

[0207] As Figure 18 and Figure 20 shown, even when the AI model exists on the OAM or RIC side or the LMF side, the information of the AI / ML model can be exchanged in the same way as when the AI model exists on the AMF side.

[0208] (4) Function and effect

[0209] According to the above embodiments, the following functions and effects can be obtained. Specifically, at the time of handover, the AI model can be handed over from the source node to the target node, so that the AI model can be used quickly after the handover.

[0210] In addition, since the information related to the AI model is exchanged quickly and reliably between the CU and the DU, AI / ML can be utilized even in the case of the NG-RAN 20 fork.

[0211] Moreover, even in the case of dual connectivity (DC), since the information associated with the AI model is provided quickly and reliably from the MN to the SN, AI / ML can be utilized in the DC.

[0212] (5) Other embodiments

[0213] The content of this proposal has been described above according to the embodiments, but this proposal is not limited to these descriptions, and various modifications and improvements are obvious to those skilled in the art.

[0214] For example, in the above embodiments, a specific AI / ML model is selected (associated) according to each scenario of using the AI / ML model, but such an association is not necessary. In addition, handover can also be interpreted as cell selection, cell reselection, cell migration, etc.

[0215] In the above descriptions, set (configure), activate, update, indicate, enable, specify, select can also be replaced with each other. Similarly, link, associate, correspond, map can be replaced with each other, and allocate, assign, monitor, map can also be replaced with each other.

[0216] Moreover, "specific", "dedicated", "UE-specific", and "UE-dedicated" can be used interchangeably. Similarly, "common", "shared", "group-common", "UE-common", and "UE-shared" can be used interchangeably.

[0217] 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", "transmission 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. can be used interchangeably.

[0218] In addition, the block structure diagrams ( Figure 2 , 3 ) used in the description of the above embodiments show blocks in terms of functions. These functional blocks (structural parts) are implemented by any combination of at least one of hardware and software. In addition, there is no particular limitation on the implementation method of each functional block. That is, each functional block can be implemented using one device physically or logically combined, or two or more physically or logically separated devices can be directly or indirectly (e.g., using wired, wireless, etc.) connected and these multiple devices can be used to implement it. The functional block can also be implemented by combining software in the above one device or the above multiple devices.

[0219] Functions include judgment, decision, determination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, establishment, comparison, assumption, expectation, regard as, broadcasting, notification, communication, forwarding, configuration, reconfiguration, allocation (allocating, mapping), assignment, etc., but are not limited to these. For example, a functional block (structural part) that performs a transmission function is called a transmitting unit or a transmitter. In short, as described above, there is no particular limitation on the implementation method.

[0220] Furthermore, the above-described gNB 100 and UE 200 (the device) can also function as a computer that processes the wireless communication method of the present disclosure. Figure 21 FIG. is an example of the hardware configuration of the device. As Figure 21 shown, the device can also 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.

[0221] In addition, in the following description, the term "device" can be replaced with "circuit", "device", "unit", etc. The hardware configuration of the device can be configured to include one or more of the illustrated devices, or can be configured not to include some of the devices.

[0222] Each functional block of the device (refer to Figure 2 , 3 ) is implemented by any hardware element in the computer device, or a combination of the hardware elements.

[0223] In addition, each function in the device is implemented by the following method: a predetermined software (program) is read into hardware such as the processor 1001 and the memory 1002, and thus the processor 1001 performs operations and controls at least one of the communication of the communication device 1004 or the reading and writing of data in the memory 1002 and the storage 1003.

[0224] The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 can also be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, registers, etc.

[0225] In addition, the processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and performs various processes based on this. As the program, a program that causes the computer to execute at least a part of the operations described in the above embodiments is used. And the above various processes can be executed by 1 processor 1001, or can be executed by 2 or more processors 1001 simultaneously or sequentially. The processor 1001 can also be implemented by 1 or more chips. In addition, the program can also be sent from a network via a telecommunication line.

[0226] The memory 1002 is a computer-readable recording medium, and may be constituted by at least one of, for example, a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable ROM), an electrically erasable programmable read-only memory (EEPROM: Electrically Erasable Programmable ROM), a random access memory (RAM: Random Access Memory), etc. The memory 1002 may be referred to as a register, a cache memory, a main memory (main storage device), etc. The memory 1002 can store a program (program code), software module, etc. that can execute the method according to an embodiment of the present disclosure.

[0227] The storage 1003 is a computer-readable recording medium, and may be constituted by at least one of, for example, optical discs such as a compact disc read-only memory (CD-ROM), a hard disk drive, a floppy disk, a magneto-optical disc (e.g., a compact disc, a digital versatile disc, a Blu-ray (registered trademark) disc), a smart card, a flash memory (e.g., a card, a stick, a key drive (Key drive)), a Floppy (registered trademark) disk, a magnetic stripe, etc. The 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, and other appropriate media including at least one of the memory 1002 and the storage 1003.

[0228] The communication device 1004 is a hardware (transceiver device) for communicating between computers via at least one of a wired network and a wireless network, and may also be referred to as a network device, a network controller, a network card, a communication module, etc.

[0229] The communication device 1004 may also be configured to include, for example, a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to implement at least one of frequency division duplex (FDD: Frequency Division Duplex) and time division duplex (TDD: Time Division Duplex).

[0230] The input device 1005 is an input device that accepts input from the outside (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.). The output device 1006 is an output device that performs output to the outside (e.g., a display, a speaker, an LED lamp, etc.). In addition, the input device 1005 and the output device 1006 may also be integrally formed (e.g., a touch panel).

[0231] In addition, devices such as the processor 1001 and the memory 1002 are connected via a bus 1007 for communicating information. The bus 1007 can be constituted by a single bus or by different buses between devices.

[0232] Moreover, the device can 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), a field programmable gate array (FPGA), etc., and part or all of the functional blocks can be implemented by this hardware. For example, the processor 1001 can also be implemented using at least one of these hardware components.

[0233] In addition, the notification of information is not limited to the forms / embodiments described in this disclosure, and other methods can also be used. For example, the notification of information can be implemented through physical layer signaling (e.g., downlink control information (DCI), uplink control information (UCI)), high 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. Moreover, RRC signaling can also be referred to as an RRC message. For example, it can also be an RRC connection setup message, an RRC connection reconfiguration message, etc.

[0234] Each form / embodiment described in the present disclosure can also be applied to at least one of systems using LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, the 4th generation mobile communication system (4G), the 5th generation mobile communication system (5G), the 6th generation mobile communication system (6G), the xth generation mobile communication system (xG) (where x is an integer or a decimal, for example), 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), other appropriate systems, and next-generation systems extended based on these systems. In addition, multiple systems can be combined (for example, a combination of at least one of LTE and LTE-A and 5G, etc.) and applied.

[0235] For the processing procedures, timings, flows, etc. of each form / embodiment described in the present disclosure, the order can be changed without contradiction. For example, for the methods described in the present disclosure, the order shown by way of example indicates the elements of various steps, but is not limited to the specific order shown.

[0236] In the present disclosure, specific actions performed by the base station may sometimes be performed by its upper node depending on the situation. In a network composed of one or more network nodes having a base station, it is obvious that various actions performed for communicating with a terminal can be performed by at least one of the base station and other network nodes other than the base station (for example, MME or S-GW is considered, but not limited to these). In the above, the case where there is one other network node other than the base station is exemplified, but it can also be a combination of multiple other network nodes (for example, MME and S-GW).

[0237] It is capable of outputting information, signals (such as information) from a higher layer (or a lower layer) to a lower layer (or a higher layer). Input and output can also be performed via multiple network nodes.

[0238] The input or output information can be stored in a specific location (e.g., memory), or can be managed using a management table. The input or output information can be rewritten, updated, or appended. The output information can also be deleted. The input information can also be sent to other devices.

[0239] The determination can be made by a value represented by 1 bit (0 or 1), can also be made by a Boolean value (true or false), and can also be made by a numerical comparison (e.g., comparison with a predetermined value).

[0240] Each form / embodiment described in the present disclosure can be used alone, can be used in combination, or can be switched according to the execution. In addition, the notification of predetermined information (e.g., the notification of "it is X") is not limited to being explicitly made, and can also be implicitly made (e.g., without making the notification of the predetermined information).

[0241] For software, no matter it is called software, firmware, middleware, microcode, hardware description language, or is called by other names, it should be broadly interpreted as referring to commands, command sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, processes, functions, etc.

[0242] In addition, software, commands, information, etc. can be transmitted and received via a transmission medium. For example, when using at least one of wired technologies (coaxial cables, fiber optic cables, twisted pairs, Digital Subscriber Line (DSL), etc.) and wireless technologies (infrared rays, microwaves, etc.) to send software from a web page, server, or other remote source, at least one of these wired technologies and wireless technologies is included in the definition of the transmission medium.

[0243] The information, signals, etc. described in the present disclosure can also be represented using any one of various different technologies. For example, the data, commands, instructions, information, signals, bits, symbols, chips, etc. that may be involved in the above description as a whole can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination of these.

[0244] In addition, terms described in this disclosure and terms required to understand 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 also be a signal (signaling). In addition, a signal may also be a message. In addition, a component carrier (CC) may also be referred to as a carrier frequency, a cell, a frequency carrier, etc.

[0245] Terms such as "system" and "network" used in this disclosure may be used interchangeably.

[0246] In addition, information, parameters, etc. described in this disclosure may be represented using absolute values, may be represented using relative values with respect to a predetermined value, or may also be represented using corresponding other information. For example, radio resources may be indicated using an index.

[0247] The names used for the above parameters are non-restrictive names in any aspect. Furthermore, mathematical expressions using these parameters may sometimes be different from the content explicitly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any appropriate name, and thus the various names assigned to these various channels and information elements are non-restrictive names in any aspect.

[0248] 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", "component carrier", etc. may be used interchangeably. Sometimes, terms such as macro cell, small cell, femto cell, pico cell, etc. are also used to refer to a base station.

[0249] A base station can accommodate one or more (e.g., 3) cells (also referred to as sectors). When a base station accommodates multiple cells, the entire coverage area of the base station can be divided into multiple smaller areas, and each of these smaller areas can also be provided with communication services by a base station subsystem (e.g., a small indoor base station (Remote Radio Head (RRH))).

[0250] Terms such as "cell" or "sector" refer to a part or the whole of the coverage area of at least one of a base station and a base station subsystem that provides communication services within that coverage range.

[0251] In the present disclosure, the base station sending information to the terminal may also be replaced by the base station instructing the terminal to perform control / action based on the information.

[0252] In the present disclosure, terms such as "Mobile Station (MS)", "user terminal", "User Equipment (UE)", "terminal", etc. may be used interchangeably.

[0253] Regarding the mobile station, those skilled in the art sometimes also refer to it using the following terms: subscriber station, mobile unit, subscriber unit, radio 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 appropriate terms.

[0254] At least one of the base station and the mobile station may also be referred to as a transmitting device, a receiving device, a communication device, etc. In addition, at least one of the base station and the mobile station may be a device mounted on a moving body, the moving body itself, etc. The moving body refers to an object that can move, and the moving speed is arbitrary. In addition, of course, the case where the moving body stops is also included. The moving body includes, for example, vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, rear cars, rickshaws, ships (ship and other watercraft: steamships and other vessels), airplanes, rockets, artificial satellites, Drone (registered trademark), multi-rotor helicopters, quad-rotor helicopters, balloons, and objects mounted on them, and is not limited thereto. In addition, the moving body may also be a moving body that autonomously travels based on an operation instruction. It may be a means of transportation (such as a car, an airplane, etc.), a moving body that moves in an unmanned manner (such as a drone, an autonomous vehicle, etc.), or a robot (humanoid or non-humanoid). In addition, at least one of the base station and the mobile station also includes a device that does not necessarily move during the communication operation. 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.

[0255] In addition, the base station in the present disclosure may also be replaced by a mobile station (user terminal, the same hereinafter). For example, with respect to a structure in which communication between a base station and a mobile station is replaced by communication between multiple mobile stations (for example, it may also be referred to as D2D (Device-to-Device), V2X (Vehicle-to-Everything), etc.), each form / embodiment of the present disclosure may also be applied. In this case, it may also be configured such that the mobile station has the functions of the base station. In addition, terms such as "uplink" and "downlink" may also be replaced by terms corresponding to inter-terminal communication (for example, "side"). For example, an uplink channel, a downlink channel, etc. may also be replaced by a side channel (or side link).

[0256] Similarly, the mobile station in the present disclosure may be replaced by a base station. In this case, it may also be configured such that the base station has the functions of the mobile station.

[0257] A radio frame may be composed of one or more frames in the time domain. In the time domain, each of the one or more frames may be referred to as a subframe. A subframe may also be composed of one or more time slots in the time domain. A subframe may have a fixed time length (for example, 1 ms) independent of the numerology.

[0258] The numerology may be communication parameters applied to at least one of transmission and reception of a certain signal or channel. The numerology may represent, for example, at least one of subcarrier spacing (SCS), bandwidth, symbol length, cyclic prefix length, transmission time interval (TTI), number of symbols per TTI, radio frame structure, specific filtering processing performed by a transceiver in the frequency domain, specific windowing processing performed by a transceiver in the time domain, etc.

[0259] A time slot may be composed of one or more symbols (OFDM (Orthogonal Frequency Division Multiplexing) symbols, SC-FDMA (Single Carrier Frequency Division Multiple Access) symbols, etc.) in the time domain. A time slot may be a time unit based on the numerology.

[0260] A time slot may include multiple mini - time slots. Each mini - time slot may be composed of one or more symbols in the time domain. In addition, a mini - time slot may also be referred to as a sub - time slot. A mini - time slot may be composed of fewer symbols than a time slot. A PDSCH (or PUSCH) transmitted in units of time larger than a mini - time slot may be referred to as PDSCH (or PUSCH) mapping type A. A PDSCH (or PUSCH) transmitted using a mini - time slot may be referred to as PDSCH (or PUSCH) mapping type B.

[0261] A radio frame, a sub - frame, a time slot, a mini - time slot, and a symbol all represent time units when transmitting signals. A radio frame, a sub - frame, a time slot, a mini - time slot, and a symbol may respectively use corresponding other names.

[0262] For example, 1 sub - frame may be called a transmission time interval (TTI), multiple consecutive sub - frames may also be called a TTI, 1 time slot or 1 mini - time slot may also be called a TTI. That is to say, at least one of the sub - frame and the TTI may be a sub - frame (1 ms) in the existing LTE, or a period shorter than 1 ms (for example, 1 - 13 symbols), or a period longer than 1 ms. In addition, the unit representing the TTI may not be called a sub - frame, but may be called a time slot, a mini - time slot, etc.

[0263] Here, the TTI is, for example, the minimum time unit for scheduling in wireless communication. For example, in an LTE system, the base station performs scheduling to allocate wireless resources (bandwidth that can be used in each user terminal, transmission power, etc.) to each user terminal in units of TTI. In addition, the definition of the TTI is not limited to this.

[0264] The TTI may be a transmission time unit such as a data packet (transport block), a code block, a codeword, etc. after channel coding, or a processing unit such as scheduling and link adaptation. In addition, when the TTI is given, the actual time interval (for example, the number of symbols) to which the transport block, the code block, the codeword, etc. are mapped may be shorter than the TTI.

[0265] In addition, when 1 time slot or 1 mini - time slot is called a TTI, one or more TTIs (that is, one or more time slots or one or more mini - time slots) may become the minimum time unit for scheduling. In addition, the number of time slots (mini - time slots) constituting the minimum time unit for scheduling can be controlled.

[0266] A TTI with a time length of 1 ms can also be referred to as a normal TTI (TTI in LTE Rel.8-12), a normal TTI, a long TTI, a normal subframe, a normal subframe, a long subframe, a time slot, etc. A TTI shorter than the normal TTI can also be referred to as a shortened TTI, a short TTI, a partial or fractional TTI, a shortened subframe, a short subframe, a mini-slot, a sub-slot, a time slot, etc.

[0267] In addition, for a long TTI (e.g., a normal TTI, a subframe, etc.), it can be replaced with a TTI having a time length exceeding 1 ms. For a short TTI (e.g., a shortened TTI, etc.), it can be replaced with a TTI having a TTI length less than that of the long TTI and greater than or equal to 1 ms.

[0268] A resource block (RB) is a resource allocation unit in the time domain and the frequency domain. In the frequency domain, it can contain one or more consecutive subcarriers.

[0269] The number of subcarriers contained in an RB can be the same regardless of the parameter set, for example, it can be 12. The number of subcarriers contained in an RB can also be determined based on the parameter set.

[0270] In addition, the time domain of an RB can contain one or more symbols, and can be the length of 1 time slot, 1 mini-slot, 1 subframe, or 1 TTI. 1 TTI, 1 subframe, etc. can each be composed of one or more resource blocks.

[0271] In addition, one or more RBs can also be referred to as a Physical RB (PRB), a Sub-Carrier Group (SCG), a Resource Element Group (REG), a PRB pair, an RB pair, etc.

[0272] In addition, a resource block can be composed of one or more resource elements (REs). For example, 1 RE can be a radio resource area of 1 subcarrier and 1 symbol.

[0273] A Bandwidth Part (BWP) (which may also be referred to as partial bandwidth, etc.) represents a subset of consecutive common resource blocks (common RBs) used by a certain parameter set in a certain carrier. Herein, the common RBs can be determined by the indexes of the RBs based on the common reference point of the carrier. PRBs can be defined in a certain BWP and numbered within that BWP.

[0274] A BWP can include a BWP for UL (UL BWP) and a BWP for DL (DL BWP). One or more BWPs can be set for a UE within one carrier.

[0275] At least one of the set BWPs can be active, and the UE may not assume to transmit and receive predetermined signals / channels outside the active BWP. Additionally, terms such as "cell" and "carrier" in this disclosure can be replaced with "BWP".

[0276] The structures of the above-mentioned radio frames, subframes, time slots, mini time slots, and symbols, etc. are merely examples. For example, the number of subframes included in a radio frame, the number of time slots per subframe or radio frame, the number of mini time slots included in a time slot, the number of symbols included in a time slot or mini time slot, the number of RBs, the number of subcarriers included in an RB, and the number of symbols within a TTI, symbol length, cyclic prefix (CP) length, etc. of the structure can be changed in various ways.

[0277] Terms such as "connected" and "coupled" or all variations of these terms are intended to represent all direct or indirect connections or couplings between two or more elements, and can include cases where there is one or more intermediate elements between the two elements that are "connected" or "coupled" to each other. The coupling or connection between elements can be a physical coupling or connection, a logical coupling or connection, or a combination of these. For example, "access" can be used to replace "connected". When used in this disclosure, it can be considered that two elements "connect" or "couple" to each other using at least one of one or more electric wires, cables, and printed electrical connections, and as some non-limiting and non-inclusive examples, electromagnetic energy with wavelengths in the radio frequency domain, microwave region, and optical (both visible and invisible) region, etc. is used to "connect" or "couple" to each other.

[0278] The reference signal can be abbreviated as Reference Signal (RS), or can be called Pilot according to the applied standard.

[0279] As used in this disclosure, the recitation "based on" does not mean "based solely on" unless otherwise expressly recited. In other words, the recitation "based on" means both "based solely on" and "based at least on".

[0280] The "unit" in the structures of the above-described respective devices may also be replaced with a "section", "circuit", "device", or the like.

[0281] Any reference to an element using the designations "first", "second", etc. used in this disclosure does not entirely limit the number or order of these elements. These designations may be used in this disclosure as a convenient method for distinguishing between two or more elements. Thus, a reference to the first and second elements does not mean that only two elements can be employed there, or that the first element must precede the second element in some form.

[0282] When the terms "include", "including" and their variants are used in this disclosure, these terms are inclusive in the same manner as the term "comprising". Also, the term "or" used in this disclosure does not mean exclusive or.

[0283] In this disclosure, for example, when articles are added through translation as in the case of a, an, and the in English, this disclosure also includes cases where the noun following these articles is in the plural form.

[0284] As used in this disclosure, terms such as "determining" sometimes encompass a variety of actions. For example, "determining" may include considering as having been "determined" matters that have been judged, calculated, computed, processed, derived, investigated, looked up (e.g., searched in a table, database, or other data structure), or ascertained. Additionally, "determining" may include considering as having been "determined" matters that have been received (e.g., receiving information), transmitted (e.g., transmitting information), input, output, accessed (e.g., accessing data in memory), etc. Further, "determining" may include considering as having been "determined" matters that have been resolved, selected, chosen, established, compared, etc. That is, "determining" may include considering certain actions as having been "determined" matters. Additionally, "determining" may be replaced by "assuming", "expecting", "considering", etc.

[0285] In this disclosure, the phrase "A and B are different" may mean that A and B are distinct from each other. Additionally, this phrase may also mean that A and B are each different from C. Terms such as "separated" and "combined" may be interpreted in the same way as "different".

[0286] Figure 22 An exemplary structure of vehicle 2001 is shown. As Figure 22 shown, vehicle 2001 includes a drive unit 2002, a steering unit 2003, an accelerator pedal 2004, a brake pedal 2005, a gearshift 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 - 2029, an information service unit 2012, and a communication module 2013.

[0287] The drive unit 2002 is composed of, for example, an engine, a motor, or a hybrid of an engine and a motor.

[0288] The steering section 2003 includes at least a steering wheel (also referred to as a hand wheel), 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.

[0289] The electronic control unit 2010 is composed of a microprocessor 2031, a 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 referred to as an ECU (Electronic Control Unit).

[0290] As signals from various sensors 2021 to 2028, there are a current signal from a current sensor 2021 that senses the current of a motor, a rotational speed signal of the front wheels and the rear wheels obtained by a rotational speed sensor 2022, an air pressure signal of the front wheels and the 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, a depression amount signal of an accelerator pedal obtained by an accelerator pedal sensor 2029, a depression amount signal of a brake pedal obtained by a brake pedal sensor 2026, an operation signal of a shift lever obtained by a shift lever sensor 2027, a detection signal for detecting obstacles, vehicles, pedestrians, etc. obtained by an object detection sensor 2028, and the like.

[0291] The information service unit 2012 is composed of various devices such as a car navigation system, an audio system, a speaker, a television, and a radio for providing (outputting) various 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 obtained from an external device via a communication module 2013 or the like to provide various multimedia information and multimedia services to the passengers of the vehicle 1.

[0292] The information service unit 2012 may include an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, a touch panel, etc.) for accepting an input from the outside, and may also include an output device (for example, a display, a speaker, an LED lamp, a touch panel, etc.) for performing an output to the outside.

[0293] The driving assistance system unit 2030 is composed of various devices such as millimeter-wave radars, LiDAR (Light Detection and Ranging), cameras, locators for positioning (such as GNSS, etc.), map information (such as high-definition (HD) maps, autonomous vehicle (AV) maps, etc.), gyroscopic systems (such as IMU (Inertial Measurement Unit), INS (Inertial Navigation System), etc.), AI (Artificial Intelligence) chips, and AI processors, which are used to provide functions for preventing accidents in advance or reducing the driving load of the driver, and one or more ECUs that control these devices. In addition, the driving assistance system unit 2030 transmits and receives various information via the communication module 2013 to implement driving assistance functions or autonomous driving functions.

[0294] The communication module 2013 can communicate with the microprocessor 2031 and the components of the vehicle 1 via the communication port. For example, the communication module 2013 transmits and receives data between the drive unit 2002, steering unit 2003, accelerator pedal 2004, brake pedal 2005, gear shifter 2006, left and right front wheels 2007, left and right rear wheels 2008, axle 2009, the microprocessor 2031 and the memory (ROM, RAM) 2032, and the sensors 2021 - 2028 in the electronic control unit 2010 of the vehicle 2001 via the communication port 2033.

[0295] The communication module 2013 can be controlled by the microprocessor 2031 of the electronic control unit 2010 and is a communication device capable of communicating with external devices. For example, it transmits and receives various information with external devices via wireless communication. The communication module 2013 can be located inside or outside the electronic control unit 2010. External devices can also be, for example, base stations, mobile stations, etc.

[0296] The communication module 2013 can send at least one of the signals from the various sensors 2021 - 2028 input to the electronic control unit 2010, the information obtained based on this signal, and the information based on the input from the external (user) obtained via the information service unit 2012 to an external device via wireless communication. The electronic control unit 2010, the various sensors 2021 - 2028, the information service unit 2012, etc. can also be referred to as input units that accept input. For example, the PUSCH sent by the communication module 2013 can contain the information based on the above input.

[0297] The communication module 2013 receives various information (traffic information, signal information, vehicle-to-vehicle information, etc.) sent from an external device and displays it on the information service unit 2012 provided in the vehicle. The information service unit 2012 can also be referred to as an output unit that outputs information (for example, outputs information to devices such as a display and a speaker based on the PDSCH received by the communication module 2013 (or data / information decoded from the PDSCH)). In addition, the communication module 2013 stores various information received from the external device in the memory 2032 that can be utilized by the microprocessor 2031. The microprocessor 2031 can also control the drive unit 2002, steering unit 2003, accelerator pedal 2004, brake pedal 2005, gear lever 2006, left and right front wheels 2007, left and right rear wheels 2008, axle 2009, sensors 2021 to 2028, etc. provided in the vehicle 2001 based on the information stored in the memory 2032.

[0298] (Supplementary Note)

[0299] The above disclosure can also be expressed as follows. The first feature is a terminal, which includes: a control unit that executes control regarding communication with a network using a learning model; and a transmission unit that, when using the learning model, transmits surrounding environment information representing the surrounding environment of the terminal position to the network.

[0300] The second feature is that, in the first feature, the control unit selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and a radio base station based on the surrounding environment information.

[0301] The third feature is that, in the first or second feature, the surrounding environment information includes at least any one of the scenario, the terminal position, and the moving state of the terminal.

[0302] The fourth feature is a radio base station, which includes: a control unit that executes control regarding communication with a terminal using a learning model; and a reception unit that, when using the learning model, receives surrounding environment information representing the surrounding environment of the terminal position from the terminal.

[0303] The fifth feature is that, in the fourth feature, a transmission unit is provided, and this transmission unit transmits at least a part of the surrounding environment information to another radio base station as a handover target when the terminal performs a handover.

[0304] The sixth feature is a wireless communication method performed by a terminal, which includes the following steps: executing control regarding communication with a network using a learning model; and when using the learning model, transmitting surrounding environment information representing the surrounding environment of the terminal position to the network.

[0305] The 7th feature is a radio base station, which includes a first device and one or more second devices connected to the first device. The first device includes: a control unit that executes control for communicating with a terminal using a learning model; and a transmission unit that, when using the learning model, transmits ambient environment information representing the ambient environment of the terminal position to the second device. The second device includes: a reception unit that receives the ambient environment information; and a control unit that selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and the radio base station based on the ambient environment information.

[0306] The 7th feature is a radio base station, which includes a first device and one or more second devices connected to the first device. The second device includes: a control unit that executes control for communicating with a terminal using a learning model; and a transmission unit that, when using the learning model, transmits ambient environment information representing the ambient environment of the terminal position to the first device. The first device includes: a reception unit that receives the ambient environment information; and a control unit that selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and the radio base station based on the ambient environment information.

[0307] The 8th feature is that, in the 6th or 7th feature, the ambient environment information includes at least any one of the scenario, the terminal position, and the moving state of the terminal.

[0308] The 9th feature is a wireless communication method performed by a radio base station, which includes a first device and one or more second devices connected to the first device. The wireless communication method includes the following steps: the first device executes control for communicating with a terminal using a learning model; the first device, when using the learning model, transmits ambient environment information representing the ambient environment of the terminal position to the second device; the second device receives the ambient environment information; and the second device selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the terminal and the radio base station based on the ambient environment information.

[0309] The 10th feature is a wireless communication method performed by a wireless base station, which includes a first device and one or more second devices connected to the first device. The wireless communication method includes the following steps: the second device executes control for communicating with a terminal using a learning model; the second device, when using the learning model, sends surrounding environment information representing the surrounding environment of the terminal's location to the first device; the first device receives the surrounding environment information; and the first device selects the learning model corresponding to the scenario related to radio wave propagation or channel between the terminal and the wireless base station based on the surrounding environment information.

[0310] The 11th feature is a wireless base station, which includes: a control unit that executes control for communicating with a terminal using a learning model; and a receiving unit that, when using the learning model, receives learning model information related to the learning model applied to the communication from a network. The control unit selects the learning model corresponding to the following scenario based on the learning model information, and the scenario is related to radio wave propagation or channel between the control unit and the terminal.

[0311] The 12th feature is that, in the 11th feature, the wireless base station includes a transmitting unit that transmits the learning model selected by the control unit to the terminal.

[0312] The 13th feature is that, in the 11th or 12th feature, the learning model information includes at least any one of the identification information of the learning model, the scenario, and the surrounding environment of the terminal's location.

[0313] The 14th feature is a wireless communication method performed by a wireless base station, which includes the following steps: executing control for communicating with a terminal using a learning model; when using the learning model, receiving learning model information related to the learning model applied to the communication from a network; and selecting the learning model corresponding to the following scenario based on the learning model information, and the scenario is related to radio wave propagation or channel between the control unit and the terminal.

[0314] As described above, the present disclosure has been described in detail. However, for those skilled in the art, it should be clear that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented in the form of modifications and changes without departing from the gist and scope of the present disclosure determined by the claims. Therefore, the purpose of the description of the present disclosure is to illustrate, and it has no restrictive meaning for the present disclosure.

[0315] Reference Signs Explanation

[0316] 10: Wireless communication system

[0317] 20: NG-RAN

[0318] 40: OAM / RIC

[0319] 50: NF

[0320] 100: gNB

[0321] 110: Radio Communication Unit

[0322] 120: Handover Processing Unit

[0323] 130: AI / ML Model Unit

[0324] 140: Control Unit

[0325] 200: UE

[0326] 210: Radio Communication Unit

[0327] 215: AI / ML Model Unit

[0328] 220: Measurement Report Unit

[0329] 230: Handover Execution Unit

[0330] 240: Control Unit

[0331] 1001: Processor

[0332] 1002: Memory

[0333] 1003: Storage

[0334] 1004: Communication Device

[0335] 1005: Input Device

[0336] 1006: Output Device

[0337] 1007: Bus

[0338] 2001: Vehicle

[0339] 2002: Driving Unit

[0340] 2003: Steering Unit

[0341] 2004: Accelerator Pedal

[0342] 2005: Brake Pedal

[0343] 2006: Gear Lever

[0344] 2007: Left and Right Front Wheels

[0345] 2008: Left and Right Rear Wheels

[0346] 2009: Axle

[0347] 2010: Electronic Control Unit

[0348] 2012: Information Service Unit

[0349] 2013: Communication Module

[0350] 2021: Current Sensor

[0351] 2022: Rotational Speed Sensor

[0352] 2023: Air Pressure Sensor

[0353] 2024: Vehicle Speed Sensor

[0354] 2025: Acceleration Sensor

[0355] 2026: Brake Pedal Sensor

[0356] 2027: Gear Shift Lever Sensor

[0357] 2028: Object Detection Sensor

[0358] 2029: Accelerator Pedal Sensor

[0359] 2030: Driver Assistance System Unit

[0360] 2031: Microprocessor

[0361] 2032: Memory (ROM, RAM)

[0362] 2033: Communication Port

Claims

1. A radio base station, comprising: a control unit that executes control for communicating with a terminal using a learning model; and a receiving unit that, when using the learning model, receives learning model information related to the learning model applied to the communication from a network, wherein the control unit selects the learning model corresponding to a scenario related to radio wave propagation or a channel between the control unit and the terminal based on the learning model information.

2. The radio base station according to claim 1, wherein the radio base station includes a transmitting unit that transmits the learning model selected by the control unit to the terminal.

3. The radio base station according to claim 1, wherein the learning model information includes at least any one of identification information of the learning model, the scenario, and the surrounding environment of the position of the terminal.

4. A wireless communication method performed by a radio base station, comprising the following steps: executing control for communicating with a terminal using a learning model; when using the learning model, receiving learning model information related to the learning model applied to the communication from a network; and selecting the learning model corresponding to a scenario related to radio wave propagation or a channel between the radio base station and the terminal based on the learning model information.

Images