Communication method and network device

Abstract

A communication method according to one aspect is for a mobile communication system. The communication method includes a step in which a network device transmits, to a user device, training data transmission setting information indicating that training data for training an artificial intelligence (AI) / machine learning (ML) model is to be transmitted, by using any signaling bearer (SRB) among a plurality of SRBs having different bearer priorities.

Description

Communication Method and Network Device

[0006]

[0001] The present disclosure relates to a communication method and a network device.

[0002] In recent years, in the 3GPP (Third Generation Partnership Project) (registered trademark; hereinafter the same), which is a standardization project for mobile communication systems, there has been a study on applying artificial intelligence (AI) technology, particularly machine learning (ML) technology, to the wireless communication (air interface) of mobile communication systems.

[0003] 3GPP TR 38.843 V18.0.0 (2023 - 12)

[0004] The communication method according to the first aspect is a communication method in a mobile communication system. The communication method includes a step in which a network device transmits learning data transmission setting information indicating that the network device transmits learning data used for learning an AI / ML model using any one of a plurality of signaling bearers (SRBs) having different bearer priorities to a user device.

[0005] The network device according to the second aspect is a network device in a mobile communication system. The network device includes a transmission unit that transmits learning data transmission setting information indicating that the network device transmits learning data used for learning an AI / ML model using any one of a plurality of signaling bearers (SRBs) having different bearer priorities to a user device.

[0006] Figure 1 is a diagram showing an example configuration of a mobile communication system according to the first embodiment. Figure 2 is a diagram showing an example configuration of a UE (User Equipment) according to the first embodiment. Figure 3 is a diagram showing an example configuration of a network node (base station) according to the first embodiment. Figure 4 is a diagram showing an example configuration of a protocol stack according to the first embodiment. Figure 5 is a diagram showing an example configuration of a protocol stack according to the first embodiment. Figure 6 is a diagram showing an example configuration of a functional block of AI / ML technology according to the first embodiment. Figure 7(A) is a diagram showing an example configuration of a functional block of a mobile communication system according to the first embodiment, and Figure 7(B) is a diagram showing an example configuration of a functional block of a UE according to the first embodiment. Figure 8 is a diagram showing an example configuration of a functional block of a mobile communication system according to the first embodiment. Figures 9(A) and 9(B) are diagrams showing examples configuration of functional blocks of a mobile communication system according to the first embodiment. Figures 10(A) and 10(B) are diagrams showing examples configuration of functional blocks of a mobile communication system according to the first embodiment. Figure 11 is a diagram showing an example of operation according to the first embodiment. Figure 12 is a diagram showing an example of operation according to the first embodiment. Figure 13 is a diagram illustrating an example of operation according to the second embodiment. Figure 14 is a diagram illustrating an example of operation according to the third embodiment. Figure 15 is a diagram illustrating another example of operation according to the third embodiment.

[0007] This disclosure aims to enable user devices to properly transmit training data.

[0008] The mobile communication system according to the first embodiment will be described with reference to the drawings. In the drawings, identical or similar parts are denoted by the same or similar reference numerals.

[0009] [First Embodiment] The configuration of the mobile communication system according to the first embodiment will now be described. Figure 1 is a diagram showing an example of the configuration of the mobile communication system 1 according to the first embodiment. The mobile communication system 1 conforms to the 5th generation system (5GS) of the 3GPP standard. In the following description, 5GS will be used as an example, but the mobile communication system may also have an LTE (Long Term Evolution) system applied to it at least partially. The mobile communication system may also have a 6th generation (6G) system or later system applied to it at least partially.

[0010] The mobile communication system 1 comprises a network (NW) 10 and a user device (UE) 100. The UE 100 is a mobile communication device that performs wireless communication with the NW 10. The UE 100 may be any device used by a user, such as a mobile phone terminal (including a smartphone) and / or a tablet terminal, a notebook PC (Personal Computer), a communication module (including a communication card or chipset), a sensor or a device installed on a sensor, a vehicle or a device installed on a vehicle (Vehicle UE), or an aircraft or a device installed on an aircraft (Aerial UE).

[0011] NW10 includes a radio access network (RAN) 20 and a core network (CN) 30. When the mobile communication system is a fifth-generation system (5GS), RAN20 is referred to as NG-RAN (Next Generation Radio Access Network) and CN30 is referred to as 5GC (5G Core Network).

[0012] RAN20 includes multiple network nodes 200 (network nodes 200a to 200c in the example in Figure 1). The network nodes 200 are interconnected via inter-network node interfaces. In RAN20, network nodes 200 are sometimes referred to as base stations. When a network node 200 is a base station, it consists of a CU (Central Unit) and a DU (Distribution Unit) (i.e., functionally divided), and the two units may be connected by a front-haul interface. When the mobile communication system 1 is 5GS, the network nodes 200 are referred to as gNBs, the inter-network node interfaces as Xn interfaces, and the front-haul interfaces as F1 interfaces.

[0013] Furthermore, if at least a part of the mobile communication system 1 is an LTE system, the network node 200 may be an eNB (evolved Node B) which is an LTE base station. Also, if the mobile communication system 1 is a sixth-generation system or later, the network node 200 has the function of a base station and may be a device equivalent to a gNB or eNB.

[0014] Each network node 200 manages one or more cells. Each network node 200 performs wireless communication with the UE 100 that has established a connection with its own cell. Each network node 200 has functions such as wireless resource management (RRM), routing of user data (also simply referred to as "data"), and measurement and control functions for mobility control and scheduling. The term "cell" is used to indicate the smallest unit of a wireless communication area. The term "cell" is also used to indicate a function or resource that performs wireless communication with the UE 100. One cell belongs to one carrier frequency. One cell may be associated with one downlink component carrier and one uplink component carrier. The bandwidth corresponding to one cell (system bandwidth) may be divided into multiple bandwidth parts (BWP: Bandwidth Part). In the following explanation, the gNB may be used as an example of a network node 200.

[0015] CN30 includes a CN (Core Network) device 300. The CN device 300 may include a C-plane device corresponding to the control plane (C-plane) and a U-plane device corresponding to the user plane (U-plane). The C-plane device performs various mobility controls and paging for the UE100. The C-plane device communicates with the UE100 using NAS (Non-Access Stratum) signaling. The U-plane device controls data transfer. When the mobile communication system is 5GS, the C-plane device is called AMF (Access and Mobility Management Function), the U-plane device is called UPF (User Plane Function), and the interface between the network node 200 and the CN device 300 is called the NG interface.

[0016] In the following, the network node 200 and the CN device 300 may be referred to as the network device. The network device may also be the network node 200. The network device may also be the CN device 300.

[0017] Figure 2 shows an example configuration of UE100 (user device) according to the first embodiment. UE100 comprises a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 constitute a communication unit 140 that performs wireless communication with the network node 200. UE100 is an example of a communication device.

[0018] The receiving unit 110 performs various types of reception under the control of the control unit 130. The receiving unit 110 includes an antenna and a receiver. The receiver converts the radio signal received by the antenna into a baseband signal (received signal) and outputs it to the control unit 130.

[0019] The transmitting unit 120 performs various types of transmissions under the control of the control unit 130. The transmitting unit 120 includes an antenna and a transmitter. The transmitter converts the baseband signal (transmission signal) output by the control unit 130 into a wireless signal and transmits it from the antenna.

[0020] The control unit 130 performs various control and processing operations in the UE 100. Such processing includes processing in each layer described later. The control unit 130 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in processing by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation, demodulation, encoding, and decoding of baseband signals. The CPU executes programs stored in memory and performs various processing operations. Note that processing or operations performed in the UE 100 may also be performed in the control unit 130.

[0021] Figure 3 shows an example configuration of a network node 200 according to the first embodiment. The network node 200 includes a transmitting unit 210, a receiving unit 220, a control unit 230, and an NW communication unit 240. The transmitting unit 210 and the receiving unit 220 constitute a communication unit 250 that performs wireless communication with the UE 100. The NW communication unit 240 constitutes a backhaul communication unit that communicates with the CN 30. The network node 200 is an example of a communication device.

[0022] The transmitting unit 210 performs various types of transmissions under the control of the control unit 230. The transmitting unit 210 includes an antenna and a transmitter. The transmitter converts the baseband signal (transmission signal) output by the control unit 230 into a wireless signal and transmits it from the antenna.

[0023] The receiving unit 220 performs various types of reception under the control of the control unit 230. The receiving unit 220 includes an antenna and a receiver. The receiver converts the radio signal received by the antenna into a baseband signal (received signal) and outputs it to the control unit 230.

[0024] The control unit 230 performs various control and processing operations on the network node 200. Such processing includes processing at each layer described later. The control unit 230 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used for processing by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation, demodulation, encoding, and decoding of baseband signals. The CPU executes programs stored in memory and performs various processing operations. Processing or operations performed at the network node 200 may also be performed by the control unit 230.

[0025] The NW communication unit 240 is connected to an adjacent network node via the Xn interface, which is an inter-network node interface. The NW communication unit 240 is connected to the CN device 300 via the NG interface, which is an inter-network node-core network interface. The network node 200 may consist of a central unit (CU) and a distributed unit (DU) (i.e., functionally divided), and the two units may be connected by the F1 interface, which is a front-haul interface.

[0026] Figure 4 shows an example of the protocol stack configuration for a user plane wireless interface that handles data.

[0027] The user plane radio interface protocol comprises a physical (PHY) layer, a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer.

[0028] The PHY layer performs encoding / decoding, modulation / demodulation, antenna mapping / demapping, and resource mapping / demapping. Data and control information are transmitted between the PHY layer of UE100 and the PHY layer of network node 200 via a physical channel. The PHY layer of UE100 receives downlink control information (DCI) transmitted from network node 200 on the physical downlink control channel (PDCCH). Specifically, UE100 performs blind decoding of the PDCCH using a Radio Network Temporary Identifier (RNTI) and acquires the successfully decoded DCI as the DCI addressed to its own UE. The DCI transmitted from network node 200 has a CRC (Cyclic Redundancy Code) parity bit, which is scrambled by the RNTI, added to it.

[0029] In NR, UE100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). Network node 200 configures UE100 with a bandwidth portion (BWP) consisting of consecutive PRBs (Physical Resource Blocks). UE100 sends and receives data and control signals in the active BWP. For example, up to four BWPs may be configured for UE100. Each BWP may have a different subcarrier spacing. The frequencies of these BWPs may overlap. If multiple BWPs are configured for UE100, network node 200 can specify which BWP to apply by controlling the downlink. This allows network node 200 to dynamically adjust the UE bandwidth according to the amount of data traffic on UE100, thereby reducing UE power consumption.

[0030] The network node 200 can, for example, configure up to three control resource sets (CORESETs) for each of up to four BWPs on a serving cell. A CORESET is a radio resource for control information that the UE 100 should receive. The UE 100 may have up to twelve or more CORESETs configured on a serving cell. Each CORESET may have an index from 0 to 11 or more. A CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive OFDM (Orthogonal Frequency Division Multiplex) symbols in the time domain.

[0031] The MAC layer performs data priority control, retransmission processing using Hybrid ARQ (HARQ: Hybrid Automatic Repeat reQuest), and random access procedures. Data and control information are transmitted between the MAC layer of UE100 and the MAC layer of network node 200 via the transport channel. The MAC layer of network node 200 includes a scheduler. The scheduler determines the transport format for the up and down links (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to UE100.

[0032] The RLC layer transmits data to the receiving RLC layer using the functions of the MAC layer and PHY layer. Data and control information are transmitted between the RLC layer of UE100 and the RLC layer of network node 200 via a logical channel.

[0033] The PDCP layer performs header compression / decompression, encryption / decryption, etc.

[0034] The SDAP layer maps IP flows, which are the units under which the core network performs QoS (Quality of Service) control, to wireless bearers, which are the units under which the access layer (AS: Access Stratum) performs QoS control. Note that if the RAN is connected to the EPC, the SDAP is not required.

[0035] Figure 5 shows the configuration of the protocol stack of the wireless interface of the control plane that handles signaling (control signals).

[0036] The protocol stack of the control plane's radio interface includes a Radio Resource Control (RRC) layer and a Non-Access Stratum (NAS) layer, instead of the SDAP layer shown in Figure 4.

[0037] RRC signaling for various settings is transmitted between the RRC layer of UE100 and the RRC layer of network node 200. The RRC layer controls the logical channel, transport channel, and physical channel in response to the establishment, re-establishment, and release of the wireless bearer. If there is a connection (RRC connection) between the RRC of UE100 and the RRC of network node 200, UE100 is in the RRC connected state. If there is no connection (RRC connection) between the RRC of UE100 and the RRC of network node 200, UE100 is in the RRC idle state. If the connection between the RRC of UE100 and the RRC of network node 200 is suspended, UE100 is in the RRC inactive state.

[0038] The NAS, located above the RRC layer, handles session management and mobility management, among other things. NAS signaling is transmitted between the UE100's NAS and the AMF's NAS. In addition to the wireless interface protocol, the UE100 also has an application layer, etc. Furthermore, the layer below the NAS is called the AS (Access Stratum).

[0039] (AI / ML Technology) Next, the AI / ML (Artificial Intelligence / Machine Learning) technology according to the embodiment will be described. Figure 6 is a diagram showing an example of the configuration of the functional block of the AI / ML technology in the mobile communication system 1 according to the first embodiment.

[0040] The block configuration example of the functions shown in FIG. 6 includes a data collection unit (Data Collection) A1, a model training unit (Model Training) A2, a model inference unit (Inference) A3, a management unit (Management) A5, and a model recording unit (Model storage) A6.

[0041] The block configuration example of the functions shown in FIG. 6 represents a functional framework of general AI / ML technologies. Therefore, depending on virtual use cases, some parts of the block configuration example (such as the model recording unit A6, etc.) may not be included in the block configuration example. Also, the block configuration example shown in FIG. 6 may be distributed and arranged between the UE 100 and the network device. Alternatively, for some functions of the block configuration example (such as the model training unit A2 or the model inference unit A3, etc.), they may be arranged in both the UE 100 and the network device.

[0042] The data collection unit A1 provides input data to the model training unit A2, the model inference unit A3, and the management unit A5. The input data includes training data (Training Data) for the model training unit A2, inference data (Inference Data) for the model inference unit A3, and monitoring data (Monitoring Data) for the management unit A5.

[0043] The training data serves as the data required for input when the AI / ML model performs learning. Also, the inference data serves as the data required for input when the AI / ML model performs inference. Furthermore, the monitoring data serves as the data required for input during the management of the AI / ML model.

[0044] Note that data collection (Data collection) may be, for example, the process of collecting data in a network node, a management entity, or the UE 100 for performing learning of an AI / ML model, management of an AI / ML model, and inference of an AI / ML model.

[0045] The model learning unit A2 performs AI / ML model training, AI / ML model validation, and AI / ML model testing.

[0046] AI / ML model training is a process of learning an AI / ML model from the relationship between inputs and outputs to obtain a trained AI / ML model for inference. For example, considering y = ax + b, the process of optimizing a (slope) and b (intercept) by giving an input (x) and an output (y) (that is, by giving training data) may be AI / ML model training.

[0047] Generally, machine learning includes supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct data for training data. Unsupervised learning is a method that does not use correct data for training data. For example, in unsupervised learning, feature points are memorized from a large amount of training data, and a correct judgment (estimation of range) is made. Reinforcement learning is a method of learning a method of attaching a score to an output result and maximizing the score. Hereinafter, supervised learning will be described, but as machine learning, unsupervised learning or reinforcement learning may be applied.

[0048] The model learning unit A2 outputs the trained AI / ML model (Trained Model) obtained by AI / ML model training to the model recording unit A6. Also, the model learning unit A2 outputs the updated AI / ML model (Updated Model) obtained by retraining the trained AI / ML model to the model recording unit A6.

[0049] Note that hereinafter, AI / ML model training may be referred to as "model training" or "training".

[0050] The model inference unit A3 performs AI / ML model inference. Specifically, the model inference unit A3 applies the inference data provided by the data collection unit A1 to a trained AI / ML model (or an updated AI / ML model) to obtain inference output data. For example, considering y = ax + b, x corresponds to the inference data and y corresponds to the inference output data. Note that "y = ax + b" is an AI / ML model. A model with optimized slope and intercept, for example "y = 5x + 3", is a trained AI / ML model. Here, there are various modeling methods (approaches), including linear regression analysis, neural networks, and decision tree analysis. The above "y = ax + b" can also be considered a type of linear regression analysis.

[0051] The model inference unit A3 outputs inference output data to the management unit A5. The model inference unit A3 also receives management instructions from the management unit A5. For example, management instructions include selecting an AI / ML model, activating (deactivating) an AI / ML model, switching between AI / ML models, and fallback (performing inference without using an AI / ML model). The model inference unit A3 performs model inference according to the management instructions.

[0052] AI / ML model inference refers to the process of obtaining a set of outputs from a set of inputs using, for example, a trained AI / ML model (or an updated AI / ML model). Alternatively, model inference may be the process of obtaining inference output data from inference data using a trained AI / ML model (or an updated AI / ML model). Hereafter, AI / ML model inference may be referred to as "model inference" or "inference."

[0053] In the following text, an AI / ML model that is being trained (or updated) may be referred to as a "Training AI / ML model" (or "Updating AI / ML Model"). Also, in the following text, if there is no distinction between an AI / ML model being trained (or updated) and an AI / ML model that has been trained (or updated), it may simply be referred to as an "AI / ML model."

[0054] The management unit A5 supervises operations on the AI / ML model (selection, activation, deactivation, switching, fallback, etc.). The management unit A5 also supervises monitoring of the AI / ML model. Based on monitoring data and inference output data, the management unit A5 can also perform actions to ensure appropriate inference operation. Therefore, the management unit A5 outputs a Model Transfer / Delivery Request to the Model Recording Unit A6, and causes the trained (or updated) AI / ML model recorded in the Model Recording Unit A6 to output to the Model Inference Unit A3. Furthermore, the management unit A5 outputs management instructions to the Model Inference Unit A3, supervising operations on the AI / ML model. Furthermore, the management unit A5 can output performance feedback and retraining requests to the model learning unit A2, which can then retrain the AI / ML model (i.e., update the trained AI / ML model).

[0055] (Use Cases) Next, we will explain use cases in which AI / ML technology is applied. For example, there are three use cases in which AI / ML technology is applied:

[0056] (X1.1) "CSI (Channel State Information) Feedback Improvement"

[0057] (X1.2) "Beam management"

[0058] (X1.3) “Positioning accuracy enhancement”

[0059] (X1.1) CSI Feedback Improvement "CSI feedback improvement" describes a use case where AI / ML technology is applied to the CSI that is fed back from UE100 to network node 200. CSI is information about the channel status in the downlink between UE100 and network node 200. CSI includes at least one of the following: Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI), and Rank Indicator (RI). Network node 200 performs, for example, downlink scheduling based on the CSI feedback from UE100.

[0060] In the "CSI Feedback Improvement" use case, there are two sub-use cases: CSI compression in the frequency domain and CSI prediction in the time domain.

[0061] (X1.1.1) Sub-use case: CSI compression In CSI compression, the CSI inferred using the trained AI / ML model in UE100 is compressed in UE100. The compressed CSI is transmitted from UE100 to network node 200.

[0062] Figure 7(A) is a diagram showing an example of the configuration of a functional block in the mobile communication system 1 when CSI compression is used. As shown in Figure 7(A), the UE 100 has a CSI generation unit 101, and the network node 200 has a CSI reconstruction unit 201.

[0063] The CSI generation unit 101 includes a CSI generation inference unit 1010 and a quantization unit 1011. The CSI generation inference unit 1010 infers CSI (inference output data) from the input using a trained AI / ML model. The input to the CSI generation inference unit 1010 may be, for example, a partial (or punctured) CSI. The partial CSI may be a CSI measured using a CSI reference signal (CSI-RS (Channel State Information-Reference Signal)) (or demodulation reference signal (DMRS)) transmitted using a certain amount of resources or less. Alternatively, the input to the CSI generation inference unit 1010 may be a CSI reference signal. The output of the CSI generation inference unit 1010 is a CSI with a larger number of CSIs than the partial CSI input, if a partial CSI is input. Also, the output of the CSI generation inference unit 1010 is a CSI if a CSI reference signal is input. Hereinafter, the output of the CSI generation inference unit 1010 will be referred to as the full CSI. The quantization unit 1011 quantizes the full CSI. Compression is performed through quantization. The quantization unit 1011 transmits the quantized full CSI to the network node 200 as CSI feedback.

[0064] The CSI reconstruction unit 201 includes an inverse quantization unit 2010 and a CSI reconstruction inference unit 2011. The inverse quantization unit 2010 receives CSI feedback, inverse quantizes the quantized full CSI, and outputs the full CSI. The CSI reconstruction inference unit 2011 uses a trained AI / ML model to infer the reconstructed full CSI from the output of the inverse quantization unit 2010 (full CSI). The reconstructed full CSI is output from the CSI reconstruction unit 201.

[0065] Furthermore, the quantization unit 1011 may be merged with the CSI generation inference unit 1010, and the inverse quantization unit 2010 may also be merged with the CSI reconstruction inference unit 2011. In addition, a pre-processing unit may be provided before the CSI generation inference unit 1010, and a post-processing unit may be provided after the CSI reconstruction inference unit 2011.

[0066] As shown in Figure 7(A), the sub-use case of CSI compression is based on a two-sided model in which inference is performed using a trained AI / ML model on both the UE100 side and the network node 200 side.

[0067] (X.1.1.2) Sub-use case: CSI prediction In CSI prediction, a trained AI / ML model is used to infer (predict) future CSIs from the history of past CSIs.

[0068] Figure 7(B) shows an example of the configuration of a functional block in UE100 when CSI prediction is used. CSI prediction is based on the UE-side model in UE100, where inference is performed using a pre-trained AI / ML model.

[0069] As shown in Figure 7(B), UE100 has a CSI prediction model 102. The CSI prediction model 102 has a trained AI / ML model that takes past CSI history as input and infers future CSI (predicted CSI). The CSI prediction model 102 may also be a CSI prediction inference unit. UE100 (CSI prediction model 102) transmits the predicted CSI as CSI feedback to the network node 200.

[0070] Furthermore, the CSI prediction model 102 may have a pre-processing unit before it, or a post-processing unit after it.

[0071] (X1.2) Beam Management In beam management use cases, there are two sub-use cases: spatial-domain downlink beam prediction, which performs beam prediction in the spatial direction, and temporal downlink beam prediction, which performs beam prediction in the temporal direction. Spatial-domain downlink beam prediction is called "BM Case 1" (BM-Case 1), and temporal downlink beam prediction is called "BM Case 2" (BM-Case 2).

[0072] Figure 8 shows an example of the configuration of a functional block in the mobile communication system 1 when BM case 1 is used. In the case of BM case 1, either a UE side model in which inference is performed at UE 100 or an NW side model in which inference is performed on the network side may be applied. Therefore, as shown in Figure 8, the AI / ML model 103 that performs inference may reside at UE 100 or at NW 10 (including the network node 200 or CN device 300).

[0073] In BM Case 1, the input to the AI / ML model 103 is the measured value for each beam included in beamset B. On the other hand, the output from the AI / ML model 103 (inference output data) is the probability that each (downstream) beam included in (predicted) beamset A will be the top beam. Beamset A and beamset B may be different. Alternatively, beamset B may be a subset of beamset A. The measured value of beamset B, which is the input to the AI / ML model 103, may be expressed as RSRP (Reference Signal Received Power).

[0074] Figure 8 also shows an example configuration of the mobile communication system 1 in the case of BM case 2. In the case of BM case 2, either the UE side model or the NW side model may be applied. In the case of BM case 2 as well, the AI / ML model 103 is located in either UE 100 or NW 10.

[0075] In BM Case 2, the input to the AI / ML model 103 is the history of measurements for each beam included in beamset B. The previously measured measurements for each beam are input to the AI / ML model 103. On the other hand, the output from the AI / ML model 103 (inference output data) is the probability that each (downstream) beam included in (predicted) beamset A will be the top beam, similar to BM Case 1. Beamset A and beamset B may be different, and beamset B may be a subset of beamset A. Also, in BM Case 2, beamset A and beamset B may be the same.

[0076] In both BM Case 1 and BM Case 2, the UE side model allows UE100 to report prediction results to NW10. Also, in both BM Case 1 and BM Case 2, the NW side model can predict the top beam based on the measured values ​​for each beam included in beamset B reported by UE100.

[0077] (X1.3) "Positioning Accuracy Enhancement" In the use case for improving positioning accuracy, there are two sub-use cases: Direct AI / ML positioning, which directly infers the position of UE100 using a trained AI / ML model, and AI / ML assisted positioning, which infers intermediate position measurements. In the latter, AI / ML assisted positioning, the position of UE100 is measured or inferred in the LMF (Location Management Function) using intermediate position measurements. Intermediate position measurements can serve as assisting information for measuring or inferring the position of UE100 in the LMF. The LMF may have a pre-trained AI / ML model, and uses this pre-trained AI / ML model to infer the position of UE100.

[0078] (X1.3.1) Sub-use case: Direct AI / ML positioning Figure 9(A) is a diagram showing an example of the configuration of a functional block in the mobile communication system 1 when direct AI / ML positioning is used. In the case of direct AI / ML positioning, the UE side model and the network side model are applied. Therefore, the AI / ML model 104 used for inference may reside in the UE 100 or in the NW 10.

[0079] In the case of direct AI / ML positioning, the input to the AI / ML model 104 is measured values ​​at each measurement point (TRP: Transmission and / or Reception Point). These measured values ​​may include, for example, channel impulse response (CIR), power delay profile (PDP), or fingerprint. For instance, both CIR and PDP represent the delay time for a signal at a specific frequency, but CIR represents the instantaneous delay time, while PDP represents the statistical delay time. On the other hand, the output from the AI / ML model 104 (inference output data) is the position information of the UE 100. This position information may also be represented by a fingerprint. The fingerprint, for example, represents the measurement information for the cells of the UE 100.

[0080] (X1.3.2) Sub-use case: AI / ML assisted positioning Figures 9(B) to 10(B) are diagrams showing examples of the configuration of functional blocks in the mobile communication system 1 when AI / ML assisted positioning is used. In the case of AI / ML assisted positioning, the UE side model and the network side model are also applied. Therefore, the AI / ML model 105 used for inference may reside in the UE 100 or in the NW 10. In the case of AI / ML assisted positioning, there are cases in which one AI / ML model 105 is used for multiple inputs (Figure 9(B)), cases in which the same AI / ML model is used for each of the multiple inputs (Figure 10(A)), and cases in which different AI / ML models are used for each of the multiple inputs (Figure 10(B)).

[0081] In either case, the input to the AI / ML model 105 is the channel measurement value at each measurement point (TRP). The channel measurement value may be CIR, PDP, or fingerprint, similar to direct AI / ML positioning. On the other hand, the output from the AI / ML model 105 (inference output data) is, in either case, an intermediate position measurement value used for position measurement. The intermediate position measurement value may be LOS or NLOS identification, measurement timing and / or measurement angle, or likelihood of measurement.

[0082] (LCM) Currently, 3GPP is discussing the Life Cycle Management (LCM) of the AI / ML model.

[0083] The LCM of an AI / ML model may specifically include at least one of the following actions:

[0084] (L1) Data collection

[0085] (L2) Model training

[0086] (L3) Identification

[0087] (L4) Model delivery or transfer

[0088] (L5) Model inference operation

[0089] (L6) Selection, Activation, Deactivation, Switching, and Fallback operations

[0090] (L7) Monitoring

[0091] (L8) Model update

[0092] (L9) UE capability

[0093] On the network side, for example, by controlling each operation of the LCM, it becomes possible to properly manage everything from the generation of AI / ML models to their deletion (or disposal). Fallback refers to switching from an AI / ML model to a model that does not use an AI / ML model. A model that does not use an AI / ML model is sometimes called a "legacy model."

[0094] 3GPP specifies two types of LCM: function-based LCM and model ID-based LCM.

[0095] A function-based LCM may be an operation performed on a function of an AI / ML model. Specifically, a function-based LCM may perform one of the following operations on a function of an AI / ML model: activation, deactivation, switching, or fallback. The network side can, for example, use 3GPP signaling (RRC message, MAC CE, or DCI) to instruct the LCM operation on a function of an AI / ML model. In a function-based LCM, the UE 100 may have one AI / ML model for one function, or it may have multiple AI / ML models for one function.

[0096] On the other hand, a model ID-based LCM may be an operation performed on individual AI / ML models using the model ID. The model ID is identification information used to distinguish one AI / ML model from other AI / ML models. Specifically, a model ID-based LCM may use the model ID to perform one of the following operations on each AI / ML model: activation, deactivation, switching, or selection.

[0097] (SRB) UE100 establishes a radio bearer (RB) with the network node 200 to perform wireless communication. A radio bearer is a logical communication channel for transmitting data. There are two types of radio bearers: signaling radio bearers (SRBs) used for transmitting control data (or control signals), and data radio bearers (DRBs) used for transmitting user data. The following will explain SRBs.

[0098] An SRB is a wireless bearer used to transmit RRC and NAS messages. Currently, 3GPP defines six SRBs, SRB0, SRB1, SRB2, SRB3, SRB4, and SRB5, depending on the application.

[0099] SRB0 SRB0 is the SRB for the Common Control Channel (CCCH). For example, messages such as the RRC Setup Request message, which requests the establishment of an RRC connection; the RRC Setup message, which requests the establishment of SRB1; the RRC Re-establishment Request message, which requests the re-establishment of an RRC connection; or the RRC Resume Request message, which requests the resumption of an interrupted RRC connection, are transmitted using SRB0.

[0100] ・SRB1 SRB1 is an SRB transmitted using a Dedicated Control Channel (DCCH). For example, messages such as the RRC Setup Complete message, which confirms the successful establishment of an RRC connection, the RRC Resume message, which resumes an interrupted RRC connection, and the RRC Re-establishment message, which re-establishes SRB1, are transmitted using SRB1. As described above, SRB1 can be established when UE100 receives an RRC setup message from network node 200. SRB1 is also used for NAS messages before SRB2 is established, and for RRC messages that piggyback NAS messages.

[0101] • SRB2 SRB2 is an SRB that is transmitted using a separate control channel. SRB2 is used to transmit RRC messages containing logged measurement information. SRB2 is also used to transmit NAS messages. Note that SRB2 has a lower priority than SRB1. Basically, SRB2, SRB3, SRB4, and SRB5 are added after SRB1 is established by the Radio Bearer Config included in the RRC Reconfiguration message.

[0102] • SRB3 SRB3 is also an SRB that is transmitted using an individual control channel. SRB3 is used to transmit certain RRC messages in dual connectivity (DC). For example, it is used to transmit the Downlink Information Transfer MRDC (DL Information Transfer MRDC) message, which is used for downlink transfer of RRC messages during high-speed MCG (Main Cell Group) link recovery.

[0103] • SRB4 SRB4 is also an SRB transmitted using an individual control channel and is used to transmit RRC messages containing measurement report information at the application layer. Note that SRB4 has a lower priority than SRB1.

[0104] ・SRB5 Like SRB4, SRB5 is transmitted using an individual control channel and is used to transmit RRC messages containing measurement report information at the application layer. However, unlike SRB4, SRB5 is an SRB that can be configured by a secondary node providing an SCG (Secondary Cell Group) when UE100 is in DC state. Note that SRB5 has a lower priority than SRB1 and SRB3.

[0105] The above explains SRBs. In terms of bearer priority, SRB1 has the highest priority, so SRB1 > SRB2 > SRB4 holds true. Also, in DC, the bearer priority relationship between SRB3 and SRB5 is SRB3 > SRB5.

[0106] (Communication method according to the first embodiment) One of the LCM operations is data collection. As described above, the data collected during data collection may be used for training an AI / ML model. Here, we assume that training of the AI / ML model is performed on the network 10 side. In this case, the training data used for the training may be collected by UE 100 and transmitted from UE 100 to the network 10 side. On the network 10 side, training (or retraining) of the AI / ML model is performed using the training data collected by UE 100.

[0107] Currently, 3GPP has agreed that training data will not be transmitted from UE100 to network 10 using SRB1. However, 3GPP has not agreed on which SRB will be used to transmit the training data. Therefore, the following issues exist.

[0108] In other words, let's assume that UE100 uses SRB4 fixed to transmit training data. As mentioned above, SRB4 has the lowest bearer priority in relation to SRB1 and SRB2. Therefore, uplink resources may be preferentially allocated to messages transmitted using SRB1 and SRB2, and these uplink resources may not be allocated to the transmission of training data. Alternatively, uplink resources may be allocated to training data after a predetermined period of time has elapsed since the transmission of messages by SRB1 and SRB2 ceased.

[0109] In other words, when SRB4 is fixed to transmit training data, there is a problem that training data may not be transmitted or may be transmitted with a predetermined delay due to its lower bearer priority compared to SRB1 and SRB2. That is, there is a problem that training data may not be transmitted properly. Some training data may be of a certain level of importance in training the AI / ML model. In such cases, it may be better for the network to train the AI / ML model as quickly as possible with such training data. On the other hand, some training data may be of a level below importance, and in such cases, it may be acceptable for the AI / ML model to be trained with a predetermined delay.

[0110] Therefore, the objective of the first embodiment is to enable UE100 to appropriately transmit training data.

[0111] Therefore, in the first embodiment, the SRB used for transmitting training data is not fixed but is dynamically changed. Specifically, the network device sends training data transmission setting information to the user device (e.g., UE100) indicating that it will transmit training data used for training an AI / ML model using one of several signaling bearers (SRBs) with different bearer priorities.

[0112] Thus, in the first embodiment, the UE 100 can transmit learning data to the network device using any of the SRBs according to the learning data transmission setting information. Therefore, the UE 100 can transmit learning data using SRB2 or using SRB4. Consequently, in the first embodiment, since SRB2 may be used in addition to the case where SRB4 is fixed, the UE 100 can appropriately transmit learning data to the network device.

[0113] Figure 11 is a diagram illustrating an overview of an example of operation according to the first embodiment. In Figure 11, a network node 200 is used as an example of a network device. Figure 11 also shows an example in which an AI / ML model is trained using training data at the network node 200.

[0114] As shown in Figure 11, in step S1, the transmitting unit 210 of the network node 200 sends a message containing training data transmission setting information to the UE 100. The training data transmission setting information includes information indicating that training data will be transmitted using one of several SRBs with different bearer priorities, as described above. This message may also be an RRC message. This message may also be a message of a layer newly defined for AI / ML (hereinafter sometimes referred to as an "AI / ML message"). The receiving unit 110 of the UE 100 receives this message.

[0115] In step S2, the transmitting unit 120 of UE 100 transmits the training data acquired through data collection to the network node 200 using one of the SRBs, according to the training data transmission setting information. The training data may be transmitted as an RRC message, an AI / ML message, or a user plane message. The receiving unit 220 of the network node 200 receives the training data.

[0116] The following sections will describe specific examples of training data transmission settings. In the following explanation, training data may be referred to as "training data," and training data transmission settings as "training data transmission settings."

[0117] (First Embodiment) In the first embodiment, an example is described in which the SRB is changed according to the importance or priority of the training data. Specifically, the training data transmission setting information is described in an example in which the training data is transmitted using one of the SRBs among the multiple SRBs, according to the importance or priority of the training data. Specifically, the training data transmission setting information is described in which, when the importance or priority of the training data is below a threshold, the first SRB (e.g., SRB4) among the multiple SRBs is used to transmit the training data, and when the importance or priority is above the threshold, the second SRB (e.g., SRB2) which has a higher bearer priority than the first SRB is used to transmit the training data.

[0118] Upon receiving the training data transmission setting information, the UE100 determines, for example, whether to transmit the training data and sends it as follows:

[0119] In other words, UE100 determines the importance or priority of the acquired training data, and if it determines that the importance or priority is above a threshold (i.e., "data with high importance or priority"), it transmits the training data using SRB2. On the other hand, if UE100 determines that the importance or priority is below a threshold (i.e., "data with low importance or priority"), it transmits the training data using SRB4. In this case, the threshold used to determine importance or priority may be included in the training data transmission setting information.

[0120] Alternatively, the UE100 may include determination information in the training data transmission settings that indicates whether the data is of high importance or priority. The UE100 may use this determination information to determine the importance or priority of the collected training data.

[0121] (Importance of training data related to the first embodiment) Here, we will explain the importance of training data related to the first embodiment.

[0122] Firstly, ground truth data may be "high-importance data." Ground truth data refers to real-world data provided through direct observation, rather than, for example, the inference output data of an AI / ML model. Ground truth data may also be the correct data used as a comparison when monitoring the inference output data. The training data transmission setting information includes the type of data that may be ground truth data (determination information), and the control unit 130 of UE 100 may determine that data acquired through data collection is ground truth data and therefore high-importance data if it falls under that type. On the other hand, if the data does not fall under that type, the control unit 130 of UE 100 may determine that it is not ground truth data but "low-importance data."

[0123] Secondly, training data that is ground truth data and has a certain level of reliability may also be considered "high-importance data." For example, assuming that the GNSS (Global Navigation Satellite System) data acquired using a GNSS receiver includes information indicating the type of satellite, the control unit 130 of the UE100 may determine that the acquired GNSS data (training data) is "high-importance data" if that information indicates a specific satellite (e.g., "Michibiki"). On the other hand, if the type of satellite included in the GNSS data is not a specific satellite, the control unit 130 of the UE100 may determine that the GNSS data is "low-importance data." Information representing the type of a specific satellite may become "determination information" and be included in the training data transmission setting information.

[0124] Alternatively, the control unit 130 of the UE 100 may determine that the acquired GNSS data (training data) indicates the location of a specific building (for example, a network node 200) and that the GNSS data indicates a location other than a specific building and may determine that the GNSS data indicates a location other than a specific building and that the GNSS data indicates a location other than a specific building. In this case, the location information of the specific building becomes "determination information" and may be included in the training data transmission setting information.

[0125] Alternatively, the control unit 130 of the UE100 may determine the importance of the data based on the GNSS data. For example, if the received electric field strength of the GNSS data is within a certain range, it may be determined to be high-importance data, and if it is outside that range, it may be determined to be low-importance data. Alternatively, the control unit 130 of the UE100 may determine the importance of the GNSS data based on the DOP (Dilution of Precision) value. The DOP value is an index representing the positioning accuracy calculated based on the position of the satellite from which the GNSS data is acquired and the position of the receiver.

[0126] Thirdly, unique or rare data may also be considered "high-importance data." Unique or rare data, as training data, has a certain level of potential to influence the AI / ML model, and therefore, it may be desirable to train it as quickly as possible as "high-importance data." On the other hand, if non-unique or non-rare data is used as training data for an AI / ML model, overfitting may occur, causing the AI / ML model to become overfit to the training data and thus losing its versatility.

[0127] For example, assuming that the training data follows a normal distribution, UE100 determines that the training data is specific or rare, i.e., highly important, when the absolute value of the Z-value shown in equation (1) below is greater than or equal to a predetermined value (e.g., "2"). On the other hand, UE100 may determine that the training data is not specific or rare, i.e., not highly important, when the absolute value of the Z-value for the training data is less than the predetermined value. This predetermined value becomes the "threshold" for importance determination and is included in the training data transmission setting information.

[0128] Z = (xi - μ) / σ ... (1) In equation (1), xi represents the value of a specific data point, μ represents the mean of the entire dataset, and σ represents the standard deviation of the entire dataset. UE100 uses equation (1) to calculate the Z value of the training data, and then compares the calculated Z value with a predetermined value to determine its importance.

[0129] (Priority of training data related to the first embodiment) Next, the priority of training data related to the first embodiment will be explained.

[0130] Firstly, the aforementioned "data of high importance" may also be "data of high priority," and the aforementioned "data of low importance" may also be "data of low priority."

[0131] Secondly, training data with a certain level of real-time capability is considered "high-priority data," while training data with a level of real-time capability below a certain point may be considered "low-priority data." Training data with a certain level of real-time capability may affect the learning of the AI / ML model depending on the type of model, so it may be desirable to perform learning as quickly as possible. On the other hand, training data with a level of real-time capability below a certain point may be acceptable even if there is a transmission delay, depending on the type of AI / ML model.

[0132] For example, UE100 may determine that training data acquired during movement is data with a real-time quality above a certain level, and training data acquired while stationary may determine that training data has a real-time quality below a certain level. UE100 has a GNSS receiver, and if the temporal change in GNSS data acquired by the GNSS receiver is greater than or equal to a "threshold," it may determine that the training data acquired during that time is training data acquired during movement, and if the temporal change is less than the "threshold," it may determine that the training data acquired during that time is training data acquired while stationary. This "threshold" may be included in the training data transmission setting information.

[0133] Alternatively, training data acquired at a specific time may be determined to have a certain level of real-time capability, while training data acquired at times other than the specific time may be determined to have a lower level of real-time capability. The training data transmission setting information includes "determination information" indicating the specific time, and the UE100 can determine whether or not the training data was acquired at the specific time based on whether or not the acquisition time of the training data falls within that time.

[0134] Alternatively, UE100 may determine that training data with a real-time capability above a certain level is "high-priority data," and training data with a real-time capability below a certain level is "low-priority data."

[0135] Thirdly, UE100 may determine that data has a high priority if the KPI is above a certain level, and low priority if the KPI is below a certain level. For example, UE100 may further train an existing AI / ML model to create a trained AI / ML model, and then use this trained AI / ML model to determine the KPI.

[0136] (Example of operation according to the first embodiment) Next, an example of operation according to the first embodiment will be described.

[0137] Figure 12 is a diagram illustrating an example of operation according to the first embodiment. The example shown in Figure 12 illustrates an example in which an AI / ML model is generated on an OTT server. Furthermore, the example shown in Figure 12 illustrates an example of a network node 200 as a network device. In addition, the example shown in Figure 12 illustrates an example in which learning is performed on the network node 200 (network-side model learning).

[0138] As shown in Figure 12, in step S10, the NW communication unit 240 of the network node 200 receives the AI / ML model transmitted from the OTT server.

[0139] In step S11, the NW communication unit 240 of the network node 200 receives information regarding the importance or priority of the AI / ML model from the OTT server. The information regarding importance or priority may be a threshold or determination information used in UE 100 to determine the importance or priority of the training data. Since the AI / ML model is generated in the OTT server, information regarding the importance or priority of the training data used to train the AI / ML model is also generated in the OTT server. Note that the information regarding importance or priority may also be generated in the network node 200.

[0140] In step S12, the transmission unit 210 of the network node 200 sends a message containing training data transmission setting information to the UE 100. The training data transmission setting information includes information indicating that when the importance or priority of the training data is below a threshold, SRB4 out of multiple SRBs will be used to transmit the training data, and when the importance or priority is above the threshold, SRB2 out of multiple SRBs will be used to transmit the training data. The training data transmission setting information may also include a threshold or determination information for the UE 100 to determine the importance or priority of the training data. The message may be an RRC message or an AI / ML message. Alternatively, the transmission unit 210 may transmit the training data using MAC CE. The transmission unit 210 may also transmit using DCI (Downlink Control Information). The reception unit 110 of the UE 100 receives the training data transmission setting information.

[0141] In addition, messages may be sent from network node 200 to UE100 in the following steps, but these messages will also be RRC messages or AI / ML messages, and explanations may be omitted.

[0142] In step S13, the control unit 130 of the UE100 acquires training data and stores the training data in memory.

[0143] In step S14, the control unit 130 of the UE 100 determines the importance or priority of the training data based on the training data transmission setting information. Specifically, as described above, the control unit 130 uses the threshold or determination information included in the training data transmission setting information to determine the importance or priority of the training data acquired in step S13. Here, the control unit 130 determines that the training data is "data with low importance or priority".

[0144] In step S15, the transmitting unit 120 of UE 100, in accordance with the training data transmission setting information, transmits the training data to the network node 200 using SRB4, based on the determination in step S14 that the importance or priority of the training data is low. The transmitting unit 120 may also transmit the training data using user plane messages. The receiving unit 220 of the network node 200 receives the training data.

[0145] In subsequent steps, training data may be transmitted from UE100 to network node 200. In all cases, this transmission may be done using the user plane, and the explanation may be omitted.

[0146] In step S16, the control unit 230 of the network node 200 performs learning (i.e., model training) using the training data received in step S15 at any time. Since this training data is "data of low importance or priority," learning is performed at any time at the network node 200.

[0147] In step S17, the control unit 130 of the UE 100 acquires and saves training data. Then, in step S18, the control unit 130 of the UE 100 determines the importance or priority of the training data acquired in step S17. Here, the control unit 130 determines that the training data is "data with high importance or priority".

[0148] In step S19, the transmitting unit 120 of UE 100, in accordance with the training data transmission setting information (step S12), transmits the training data acquired in step S17 to the network node 200 using SRB2, based on its determination that the data is of high importance or priority. The transmitting unit 120 may also transmit the training data using MAC CE or UCI (Uplink Control Information). The receiving unit 220 of the network node 200 receives the training data.

[0149] In step S20, the control unit 230 of the network node 200 immediately performs training using the training data. Since the training data is "data of high importance or priority," when the network node 200 receives the training data, it immediately performs training on the AI / ML model.

[0150] (Another Operation Example 1 related to the First Embodiment) In the first embodiment, a network node 200 was used as an example of a network device, but a CN device 300 may also be used as the network device. In this case, in the example shown in Figure 12, step S12 is performed by the CN device instead of the network node 200. If the CN device is an AMF, step S12 may be performed using a NAS message.

[0151] Alternatively, an LMF may be used as an example of a network device. In this case, in the example shown in Figure 12, step S12 is replaced by an LMF instead of a network node 200. Step S12 may use an LPP message via LPP (LTE Positioning Protocol).

[0152] Alternatively, in the example shown in Figure 12, an OTT server may be used instead of the network node 200. In this case, in the example shown in Figure 12, step S12 becomes the OTT server instead of the network node 200. Step S12 may use IP messages via the IP (Internet Protocol) protocol.

[0153] Alternatively, UE100 may be connected by DC to two cells: a master cell belonging to MCG and a secondary cell belonging to SCG. In this case, the network node 200 on the master cell side sends training data transmission setting information to UE100 indicating that training data will be transmitted using SRB2 or SRB4 depending on the importance or priority of the training data, similar to the first embodiment. On the other hand, the network node 200 on the secondary cell side sends training data transmission setting information to UE100 indicating that training data will be transmitted using SRB3 or SRB5 depending on the importance or priority of the training data. As a result, for example, UE100 can transmit data with high importance or priority using SRB2 on the master cell side and using SRB3 on the secondary cell side. On the other hand, UE100 can transmit data with low importance or priority using SRB4 on the master cell side and using SRB5 on the secondary cell side.

[0154] (Another example of operation related to the first embodiment 2) As shown in the first embodiment, when different SRBs are used depending on the importance or priority of the training data, "data with low importance or priority" may be transmitted from UE100 later than "data with high importance or priority". For example, in the example shown in Figure 12, UE100 transmits training data using SRB4 (step S15), but due to insufficient uplink resources, this may be delayed compared to the transmission of training data in step S19. In some cases, it is desirable for AI / ML models to be trained in chronological order, so if training is performed in an order that is not chronological, it may not be possible to generate an AI / ML model with accuracy above a certain level.

[0155] Therefore, when UE100 acquires training data, it adds information that allows it to determine the acquisition order to the training data and sends it to network node 200. The information that allows it to determine the acquisition order may be a sequential number indicating the order in which UE100 acquired the training data (for example, "001", "002", etc.). Alternatively, the information that allows it to determine the acquisition order may be a timestamp representing the time when UE100 acquired the training data (for example, "20240829"). Network node 200 uses the information that allows it to determine the acquisition order to rearrange the training data in chronological order and perform training on the AI / ML model.

[0156] (Second Embodiment) Next, a second embodiment will be described. In the first embodiment, the settings were configured in advance by notifying the UE 100 of the training data transmission setting information, and thereafter, an example was described in which the training data was transmitted using SRB2 or SRB4 according to the result of the UE 100's determination of the importance or priority of the training data. In the second embodiment, an example will be described in which the SRB to be used is directly specified by the training data transmission setting information, and the UE 100 transmits the training data using the specified SRB. That is, in the second embodiment, an example will be described in which the SRB is specified each time by the training data transmission setting information.

[0157] Specifically, firstly, the network device sends first learning data transmission setting information to the user device (e.g., UE100) indicating that it will transmit the learning data using a first SRB (e.g., SRB4) among the multiple SRBs. Secondly, in response to the network device determining that the importance or priority of the learning data is above a threshold, it sends second learning data transmission setting information to the user device indicating that it will transmit the learning data using a second SRB (e.g., SRB2) among the multiple SRBs that has a higher bearer priority than the first SRB.

[0158] As a result, UE100 can transmit training data using SRB4 according to the first training data transmission setting information, and transmit training data with "high importance or priority" that is above a threshold using SRB2 according to the second training data transmission setting information.

[0159] (Example of operation according to the second embodiment) Figure 13 is a diagram showing an example of operation according to the second embodiment. In the example shown in Figure 13, a network node 200 is used as the network device, and it shows an example in which learning is performed on the network node 200. In the example of operation shown in Figure 13, the explanation of operations that are the same as in the first embodiment (Figure 12) may be omitted.

[0160] The transmitting unit 210 of the network node 200 transmits a message containing training data transmission setting information (for example, first training data transmission setting information) (step S32). This training data transmission setting information includes information indicating that training data will be transmitted using SRB4 out of a plurality of SRBs. In other words, it is training data transmission setting information that instructs which SRB to use to transmit the training data. The receiving unit 110 of the UE 100 receives this training data transmission setting information.

[0161] When the control unit 130 of UE100 acquires and stores training data (step S33), it transmits the training data via SRB4 (step S34) according to the training data transmission setting information (step S32). The receiving unit 220 of the network node 200 receives the training data.

[0162] In step S35, the control unit 230 of the network node 200 determines the importance or priority of the training data. Here, the content of the training data acquired by the UE 100 is basically known by the UE 100. Therefore, in the first embodiment, the importance or priority of the training data could be determined by the UE 100. However, in the second embodiment, the importance or priority of the training data is not determined by the UE 100, but is determined by the network node 200. Therefore, in the second embodiment, the network node 200 uses, for example, information on the movement status of the UE 100 to determine whether the training data was acquired while moving or while stationary. The network node 200 may then determine, as in the first embodiment, that if the data was acquired while moving, it is "high-priority data" (i.e., "data whose importance or priority is above a threshold") if its real-time performance is above a certain level, and that if the data was acquired while stationary, it is "low-priority data" (i.e., "data whose importance or priority is below a threshold") if its real-time performance is below a certain level. Alternatively, the network node 200 may determine that data acquired during movement is "low-priority data" and training data acquired while stationary is "high-priority data".

[0163] Regarding information about the movement status, for example, if the "speedStateReselectionPars" of SIB2 is set for UE100, UE100 will determine the movement status (mobility state: normal, medium, or high) based on the number of cell reselections within a certain period, and will send the movement status (mobility state: normal, medium, or high) along with the RRC setup completion message. Network node 200 may obtain information about the movement status based on this movement status.

[0164] Alternatively, the information regarding the movement status may be the Timing Advance (TA) value sent to the UE 100 during the random access procedure. The network node 200 can determine the movement status of the UE 100 by observing the temporal change in the TA value.

[0165] Alternatively, information regarding the movement status may be provided by the RSRP value included in the measurement report. The network node 200 can determine the movement status of the UE 100 by observing the temporal changes in the RSRP value.

[0166] Alternatively, the information regarding the movement status may be the location information of UE100. Network node 200 can determine the movement status of UE100 by observing the temporal changes in the location information of UE100. Network node 200 may obtain the location information of UE100 from UE100. Network node 200 may also obtain it from LMF.

[0167] In step S36, the transmission unit 210 of the network node 200 determines that the training data acquired in step S34 is "data of high importance or priority" and sends a message to the UE 100 containing training data transmission setting information (for example, second training data transmission setting information). The training data transmission setting information includes information indicating that the training data will be transmitted using the SRB2.

[0168] Furthermore, if the control unit 230 of the network node 200 determines that the training data acquired in step S34 is "data of low importance or priority," it will not transmit the training data transmission setting information. This is because there is no need to perform learning immediately for training data of low importance or priority, and therefore there is no need to change from SRB4 to SRB2 and transmit the training data.

[0169] In step S37, the control unit 230 of the network node 200 performs training using the training data acquired in step S34. Because this training data has high importance or priority, it is used to train the AI / ML model.

[0170] In step S38, the control unit 230 of UE100 acquires and stores the training data, and in step S39, transmits the training data using SRB2 according to the training data transmission setting information (step S36). The receiving unit 220 of the network node 200 receives the training data.

[0171] In step S40, the control unit 230 of the network node 200 determines the importance or priority of the training data received in step S39. If it determines that the data is "high importance or priority," it executes (or continues) learning in step S41.

[0172] (Other operation examples related to the second embodiment) Similar to other operation example 1 of the first embodiment, the network node 200 may be replaced with a CN device 300, an LMF, or an OTT server. The training data transmission setting information related to the second embodiment may be transmitted using NAS messages, LPP messages, or IP messages.

[0173] Furthermore, similar to other operation examples 1 of the first embodiment, UE100 may be connected to two cells, a master cell and a secondary cell, by a DC. The master cell side is the same as in the second embodiment, and the network node 200 on the secondary cell side only needs to send training data transmission setting information specifying SRB5 in step S32, and send training data transmission setting information specifying SRB3 in step S36. UE100 should send training data to the secondary cell using an SRB (SRB3 or SRB5) according to the training data transmission setting information (step S34 or step S39).

[0174] Furthermore, similar to other operation examples 2 of the first embodiment, UE100 may add information that allows the acquisition order to be determined to the training data and transmit it to the network node 200 (steps S34 and S39).

[0175] (Third Embodiment) Next, a third embodiment will be described.

[0176] In the first and second embodiments, examples were described in which different SRBs are used depending on the importance or priority of the training data. In the third embodiment, an example is described in which training data is transmitted using one of several SRBs depending on whether or not the training data is transmitted periodically.

[0177] Specifically, in the third embodiment, the training data transmission setting information includes information indicating that when training data is transmitted via an event trigger, the first SRB (e.g., SRB4) among the multiple SRBs is used, and when training data is transmitted periodically, the second SRB (e.g., SRB2) with a higher bearer priority than the first SRB among the multiple SRBs is used.

[0178] For example, let's assume that UE100 periodically transmits training data using SRB4. In such a case, as mentioned above, the bearer priority of SRB4 is lower than that of SRB1 and SRB2, so transmission may be delayed. Due to such delays, the training data that should be transmitted periodically may not be transmitted periodically, rendering the purpose of periodic transmission meaningless. Therefore, in the third embodiment, SRB2 is used for periodic transmission and SRB4 is used for event-triggered transmission to ensure that periodic transmission occurs.

[0179] (Example of operation according to the third embodiment) Figure 14 is a diagram showing an example of operation according to the third embodiment. Similar to the first embodiment, the example shown in Figure 14 also uses a network node 200 as a network device and shows an example where learning is performed on the network node 200. Similar to the first embodiment, the example shown in Figure 14 also shows an example of pre-configuration. In Figure 14, the event is "just before the memory of UE 100, which stores the training data, overflows" (i.e., "just before bufferful"). When the "just before bufferful" event occurs in UE 100, the training data is sent triggered by this event.

[0180] As shown in Figure 14, when the receiving unit 220 of the network node 200 receives the AI / ML model from the OTT server (step S50), in step S51, the transmitting unit 210 of the network node 200 sends a message containing training data transmission setting information (step S51). The training data transmission setting information includes information indicating that SRB4 should be used when training data is transmitted via an event trigger, and SRB2 should be used when training data is transmitted periodically.

[0181] In step S52, the transmitting unit 210 of the network node 200 sends a message containing training data transmission setting information to the UE 100. This training data transmission setting information includes information instructing the transmission of training data periodically. This training data transmission setting information may also include Periodic setting information indicating the period. The receiving unit 110 of the UE 100 receives this message.

[0182] In step S53, the control unit 130 of the UE100 acquires training data and stores it in memory.

[0183] In step S54, the control unit 130 of UE100 determines whether or not the period indicated by the Periodic setting information has been reached.

[0184] In step S55, when the transmission unit 120 of UE 100 reaches the period indicated by the Periodic setting information, it transmits the training data acquired in step S53 using SRB2 according to the training data transmission setting information received in step S51. The receiving unit 220 of the network node 200 receives the training data.

[0185] In step S56, the control unit 230 of the network node 200 trains the AI / ML model using the training data received in step S55.

[0186] Meanwhile, in step S57, the transmitting unit 210 of the network node 200 sends a message containing training data transmission setting information to the UE 100. This training data transmission setting information includes information instructing the UE to transmit training data when an event trigger occurs. In the example shown in Figure 14, the event trigger is "just before Bufferful". The receiving unit 110 of the UE 100 receives this message.

[0187] In step S58, the control unit 130 of the UE100 acquires training data and stores it in memory.

[0188] In step S59, the control unit 130 of the UE 100 determines whether the amount of training data stored in memory is about to overflow (i.e., "just before bufferful"). Since the control unit 130 knows the memory capacity of the memory, it can determine that it is "just before bufferful" when the amount of training data stored in step S58 is about to reach the memory capacity. The memory capacity may be included in the training data transmission setting information. Alternatively, the free space relative to the memory capacity may be included in the training data transmission setting information. In this case, the control unit 130 of the UE 100 may calculate the free space in memory and determine that it is "just before bufferful" when that free space reaches the free space included in the training data transmission setting information.

[0189] In step S60, the transmitting unit 120 of UE 100 transmits the training data acquired in step S58 using SRB4 according to the training data transmission setting information (step S51) in response to the memory being "just before bufferful". The receiving unit 220 of network node 200 receives the training data.

[0190] In step S61, the control unit 230 of the network node 200 uses the training data to train the AI / ML model.

[0191] (Another Operation Example 1 Related to the Third Embodiment) In the third embodiment, as in the second embodiment, it is possible to set the transmission settings for training data each time. Specifically, firstly, when the network device transmits training data triggered by an event, it transmits first training data transmission setting information to the user device (e.g., UE100) indicating that it will use the first SRB (e.g., SRB4) among the multiple SRBs. Secondly, when the network device transmits training data periodically, it transmits second training data transmission setting information to the user device indicating that it will use the second SRB (e.g., SRB2) among the multiple SRBs which has a higher bearer priority than the first SRB.

[0192] As a result, when UE100 receives the first learning data transmission setting information, for example, when an event such as "just before Bufferful" occurs, it can use SRB4 to transmit the learning data stored in the buffer to the network device according to the first learning data transmission setting information. Furthermore, when UE100 receives the second learning data transmission setting information, it can use SBR2 to periodically transmit learning data to the network device according to the second learning data transmission setting information.

[0193] Figure 15 shows another example of operation according to the third embodiment. Similar to the third embodiment, Figure 15 uses a network node 200 as an example of a network device and shows an example in which learning is performed on the network node 200. In the operation example shown in Figure 15, the parts that are the same as those in the third embodiment (Figure 14) will not be explained.

[0194] As shown in Figure 15, in step S71, the transmission unit 210 of the network node 200 sends a message containing training data transmission setting information to the UE 100. Here, the training data transmission setting information includes information instructing the UE to periodically transmit training data using the SRB 2.

[0195] Then, UE100 acquires and saves the training data (step S72), and when it confirms that the time indicated in the Periodic setting information has been reached (step S73), it receives a message (step S71) and transmits the training data using SRB2 according to the training data transmission setting information (step S71) (step S74).

[0196] Meanwhile, in step S76, the transmission unit 210 of the network node 200 sends a message (for example, a third message) containing training data transmission setting information to the UE 100. Here, the training data transmission setting information includes information instructing that the training data be transmitted using the SRB4 as an event trigger ("just before Bufferful").

[0197] Then, UE100 acquires and saves the training data (step S77), and when it confirms that the memory is "just before buffering" (step S78), it receives a message (step S76) and transmits the training data using SRB4 according to the training data transmission setting information (step S76) (step S79).

[0198] (Another Operation Example 2 in the Third Embodiment) In the third embodiment as well, the network node 200 may be replaced with a CN device 300, an LMF, or an OTT server. The training data transmission setting information in the third embodiment may be transmitted using NAS messages, LPP messages, or IP messages. The same applies to the operation example in which the training data transmission setting information is set each time (Another Operation Example 1 in the Third Embodiment).

[0199] Furthermore, UE100 may be connected to two cells, a master cell and a secondary cell, by a DC. The master cell side is the same as in the third embodiment (Figure 14). Regarding the secondary cell side, the training data transmission setting information in step S51 includes information instructing that the data be transmitted using SRB3 if transmitted periodically, and using SRB5 if transmitted by an event trigger. Then, the network node 200 on the secondary cell side transmits training data transmission setting information instructing periodic transmission in step S52, and transmits training data transmission setting information instructing transmission by an event trigger ("just before Bufferful") in step S57. When UE100 reaches the time indicated by the Periodic setting information, it transmits the training data to the secondary cell using SRB3 (step S55), and when it is "just before Bufferful", it transmits the training data to the secondary cell using SRB5 (step S60).

[0200] The DC connection example is also applicable to the operation example where training data transmission settings are set each time (Other Operation Example 1 related to the Third Embodiment: Figure 15). The master cell side is the same as Other Operation Example 1 related to the Third Embodiment (Figure 15).

[0201] With respect to the secondary cell, the training data transmission setting information in step S71 will include information instructing it to transmit the data periodically using the SRB3. The UE100 then periodically transmits the training data to the secondary cell using the SRB3 in accordance with the training data transmission setting information.

[0202] Furthermore, with respect to the secondary cell, the training data transmission setting information in step S76 includes information instructing it to transmit the data using the SRB5 triggered by an event ("just before Bufferful"). The UE100 transmits the training data to the secondary cell using the SRB5 triggered by an event, in accordance with the training data transmission setting information.

[0203] Furthermore, in the third embodiment, UE100 may also add information that allows the acquisition order to be determined to the training data and transmit it to the network node 200 (steps S55 and S60 in Figure 14, and steps S74 and S79 in Figure 15).

[0204] [Other Embodiments] In the first embodiment, two examples of training data transmission setting information were described: SRB2 or SRB4 (or SRB3 or SRB5). For example, there may be three types of configurable SRBs, including SRB1. In this case, the training data transmission setting information may include thresholds (two thresholds) or judgment information to which each SRB applies. The UE100 applies the thresholds or judgment information and transmits the training data using SRB1 for the training data with the highest importance or priority, SRB2 (or SRB3) for the training data with the next highest importance or priority, and SRB4 (or SRB5) for the training data with the lowest importance or priority. Alternatively, there may be four or more types of configurable SRBs, and thresholds (three or more thresholds) to which each SRB applies may be included. Note that training data may also be transmitted by MAC CE or UCI in addition to SRB. Furthermore, training data may be transmitted using the user plane. The training data may be transmitted using a data bearer (DRB).

[0205] Furthermore, while the first embodiment described an example of determining importance and priority for a single instance, if the importance or priority is detected to be above a threshold multiple times, a second SRB (e.g., SRB2) with a higher bearer priority than the first SRB (e.g., SRB4) may be used. Alternatively, if the importance or priority is detected to be below a threshold multiple times, the first SRB (e.g., SRB4) may be used.

[0206] Furthermore, if the importance or priority level exceeds a threshold for a certain period of time, a second SRB (e.g., SRB2) with a higher bearer priority than the first SRB (e.g., SRB4) may be used, and if the importance or priority level falls below the threshold for a certain period of time, the first SRB (e.g., SRB4) may be used.

[0207] The first embodiment described above primarily focuses on supervised learning, but is not limited to this. For example, the first embodiment may also apply to unsupervised learning or reinforcement learning.

[0208] The above-described operation flows can be performed not only independently, but also in combination of two or more operation flows. For example, some steps of one operation flow may be added to another operation flow, or some steps of one operation flow may be replaced with some steps of another operation flow. It is not necessary to execute all steps in each flow; only some steps may be executed. Furthermore, the order of steps in each flow may be changed as appropriate.

[0209] In the above embodiment, an example was described in which the base station is an NR base station (gNB), but the base station may also be an LTE base station (eNB) or a 6G base station. Furthermore, the base station may also be a relay node such as an IAB (Integrated Access and Backhaul) node. The base station may also be a DU of an IAB node. Additionally, UE100 may be an MT (Mobile Termination) of an IAB node. That is, UE100 may be a terminal function unit (a type of communication module) for the base station to control a relay device that performs signal relay. Such a terminal function unit is referred to as an MT. Examples of multi-transmission architectures (MTs) include IAB-MT, NCR (Network Controlled Repeater)-MT, and RIS (Reconfigurable Intelligent Surface)-MT.

[0210] Furthermore, the term "network node" primarily refers to a base station, but may also refer to a core network device or a part of a base station (CU, DU, or RU). Additionally, a network node may consist of a combination of at least a part of the core network device and at least a part of a base station.

[0211] A program is provided that causes a computer to execute each of the processes according to the above embodiment. The program may be recorded on a computer-readable medium. Using a computer-readable medium, it is possible to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transient storage medium. The non-transient storage medium is not particularly limited, but for example, it may be a storage medium such as a CD-ROM and / or DVD-ROM. Furthermore, the circuits that execute each of the processes performed by the apparatus according to the above embodiment may be integrated, and at least a part of the apparatus may be configured as a semiconductor integrated circuit (chipset, SoC: System on a chip).

[0212] The functions realized by the apparatus according to the above-described embodiment may be implemented in a circuit or processing circuit, including a general-purpose processor, application-specific processor, integrated circuit, ASICs (Application Specific Integrated Circuits), CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, which are programmed to realize the described functions. The processor includes transistors and / or other circuits and is considered to be a circuit or processing circuit. The processor may be a programmed processor that executes a program stored in memory. In this disclosure, circuit, unit, and means are hardware programmed to realize or execute the described functions. The hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If the hardware is a processor that is considered to be of the type of circuit, the circuit, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0213] The phrases “based on” and “depending on / in response to” as used in this disclosure do not mean “based solely on” or “in response solely” unless otherwise specified. “Based on” means both “based solely on” and “at least partially on.” Similarly, “depending” means both “at least partially on” and “at least partially on.” The terms “include,” “comprise,” and variations thereof do not mean that they include only the listed items, but may include only the listed items or may include additional items in addition to the listed items. Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR. Additionally, any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient way to distinguish between two or more elements. Therefore, references to the first and second elements do not imply that only two elements may be adopted therein, or that the first element must precede the second element in any way. In this disclosure, where articles are added by translation, such as a, an, and the in English, these articles shall be plural unless it is clearly indicated from the context that they are not.

[0214] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to those described above, and various design changes can be made without departing from the gist of the work. Furthermore, each embodiment, each operation example, or each process can be combined as appropriate, as long as they do not contradict each other.

[0215] This application claims priority to Japanese Patent Application No. 2024-171548 (filed September 30, 2024), the entirety of which is incorporated into the specification of this application.

[0216] (Note) The above can be summarized as stated in the note, but the note does not limit the embodiments.

[0217] (Note 1) A communication method in a mobile communication system, comprising the step of a network device transmitting training data transmission setting information to a user device, indicating that the network device transmits training data used for training an AI / ML model using one of a plurality of signaling bearers (SRBs) with different bearer priorities.

[0218] (Note 2) The communication method according to Note 1, wherein the learning data transmission setting information includes information indicating that the learning data is transmitted using one of the SRBs according to the importance or priority of the learning data.

[0219] (Note 3) The communication method according to Note 1 or Note 2, wherein the learning data transmission setting information includes information indicating that the learning data is transmitted using the first SRB among the plurality of SRBs when the importance or priority is less than the threshold, and using the second SRB among the plurality of SRBs which has a higher bearer priority than the first SRB when the importance or priority is equal to or greater than the threshold.

[0220] (Note 4) The communication method according to any one of Notes 1 to 3, wherein the transmission step includes: transmitting first learning data transmission setting information to the user device indicating that the network device transmits the learning data using a first SRB among the plurality of SRBs; and transmitting second learning data transmission setting information to the user device indicating that the network device transmits the learning data using a second SRB among the plurality of SRBs which has a higher bearer priority than the first SRB, in response to the network device determining that the importance or priority of the learning data is above a threshold.

[0221] (Note 5) The communication method according to any one of Notes 1 to 4, further comprising the step of the user device transmitting the learning data to the network device in accordance with the learning data transmission setting information, wherein the step of transmitting the learning data includes the step of the user device transmitting information to the network device that allows the acquisition order of the learning data to be determined.

[0222] (Note 6) The communication method according to any one of Notes 1 to 5, wherein the learning data transmission setting information includes information indicating that the learning data is transmitted using one of the SRBs among the plurality of SRBs depending on whether or not the learning data is transmitted periodically.

[0223] (Note 7) The communication method according to any one of Notes 1 to 6, wherein the learning data transmission setting information includes information indicating that when the learning data is transmitted by an event trigger, the first SRB among the plurality of SRBs is used, and when the learning data is transmitted periodically, the second SRB among the plurality of SRBs with a higher bearer priority than the first SRB is used.

[0224] (Note 8) The communication method according to any one of Notes 1 to 7, wherein the transmission step includes: transmitting first learning data transmission setting information to the user device indicating that when the network device transmits the learning data in response to an event trigger, it will use the first SRB among the plurality of SRBs; and transmitting second learning data transmission setting information to the user device indicating that when the network device transmits the learning data periodically, it will use the second SRB among the plurality of SRBs which has a higher bearer priority than the first SRB.

[0225] (Note 9) The communication method according to any one of Notes 1 to 8, wherein the user device acquires the training data and the network device performs training of the AI / ML model using the training data.

[0226] (Note 10) A network device in a mobile communication system, comprising a transmitting unit that transmits training data transmission setting information to a user device, indicating that training data used for training an AI / ML model will be transmitted using one of a plurality of signaling bearers (SRBs) with different bearer priorities.

[0227] 1: Mobile communication system 10: NW 20: RAN 30: CN 100: UE 101: CSI generation unit 102: CSI prediction model 103, 104, 105: AI / ML model 110: Receiving unit 120: Transmitting unit 130: Control unit 140: Communication unit 200: Network node 201: CSI reconstruction unit 210: Transmitting unit 220: Receiving unit 230: Control unit 240: NW communication unit 250: Communication unit 300: CN device A1: Data acquisition unit A2: Model learning unit A3: Model inference unit A5: Management unit A6: Model recording unit 1010: Inference unit for CSI generation 1011: Quantization unit 2010: Inverse quantization unit 2011: Inference unit for CSI reconstruction

Claims

A communication method in a mobile communication system, The network device transmits training data transmission setting information to the user device, indicating that it will transmit training data used for training an AI (Artificial Intelligence) / ML (Machine Learning) model using one of several signaling bearers (SRBs) with different bearer priorities. Communication method. 　 The aforementioned learning data transmission setting information includes information indicating that the learning data will be transmitted using one of the SRBs according to the importance or priority of the learning data. The communication method according to claim 1. 　 The learning data transmission setting information includes information indicating that when the importance or priority is below a threshold, the first SRB among the multiple SRBs will be used to transmit the learning data, and when the importance or priority is equal to or greater than the threshold, the second SRB among the multiple SRBs with a higher bearer priority than the first SRB will be used to transmit the learning data. The communication method according to claim 2. 　 The aforementioned transmission is, The network device transmits to the user device first learning data transmission setting information indicating that it will transmit the learning data using the first SRB among the plurality of SRBs, The network device, upon determining that the importance or priority of the training data is above a threshold, transmits a second training data transmission setting information to the user device indicating that the training data will be transmitted using a second SRB, which has a higher bearer priority than the first SRB among the plurality of SRBs. The communication method according to claim 2. 　 The user device further includes transmitting the learning data to the network device in accordance with the learning data transmission setting information. Transmitting the aforementioned learning data includes the user device transmitting information to the network device that allows the user device to determine the order in which the learning data was acquired. The communication method according to claim 1. 　 The aforementioned learning data transmission setting information includes information indicating whether or not the learning data is transmitted periodically, and whether or not the learning data is transmitted using one of the SRBs among the plurality of SRBs. The communication method according to claim 1. 　 The aforementioned learning data transmission setting information includes information indicating that when the learning data is transmitted by an event trigger, the first SRB among the plurality of SRBs is used, and when the learning data is transmitted periodically, the second SRB among the plurality of SRBs, which has a higher bearer priority than the first SRB, is used. The communication method according to claim 6. 　 The aforementioned transmission is, When the network device transmits the learning data in response to an event trigger, it transmits first learning data transmission setting information to the user device indicating that it will use the first SRB among the multiple SRBs. The network device transmits to the user device second learning data transmission setting information indicating that when it periodically transmits the learning data, it will use a second SRB among the plurality of SRBs that has a higher bearer priority than the first SRB. The communication method according to claim 6. 　 The user device acquires the training data, and the network device performs training on the AI ​​(Artificial Intelligence) / ML (Machine Learning) model using the training data. The communication method according to claim 1. 　 The user device further includes, when it acquires training data, adding information that allows the acquisition order to be determined to the training data and transmitting it to the network device. The communication method according to claim 1. 　 A network device in a mobile communication system, The device includes a transmission unit that transmits training data transmission setting information to a user device, indicating that training data used for training an AI / ML model will be transmitted using one of several signaling bearers (SRBs) with different bearer priorities. Network device.

Images