Communication method

Abstract

A communication method according to one embodiment of the present invention is used in a mobile communication system. The communication method includes a step in which a user device receives, from a network node, a message that includes a report prohibition timer associated with each function of an AI / ML model. In addition, the communication method includes a step in which the user device transmits, to the network node, a report indicating that the state of a function has changed in response to expiration of the report prohibition timer associated with said function after the state of the function has changed.

Description

Communication method

[0001] The present disclosure relates to a communication method used in a mobile communication system.

[0002] In recent years, in 3GPP (Third Generation Partnership Project) (registered trademark; the same shall apply hereinafter), which is a standardization project for mobile communication systems, studies have been conducted to apply artificial intelligence (AI: Artificial Intelligence) technology, particularly machine learning (ML: Machine Learning) technology, to the wireless communication (air interface) of mobile communication systems.

[0003] 3GPP TR 38.843 V18.0.0 (2023 - 12) 3GPP TS 38.000 V18.4.0 (2024 - 12) 3GPP TS 28.105 V19.1.0 (2024 - 12)

[0004] The communication method according to the first aspect is a communication method used in a mobile communication system. The communication method includes a step in which a user device receives a message including a report prohibition timer associated with each function of an AI / ML model from a network node. Further, the communication method includes a step in which, after the state of a function changes, the user device transmits a report indicating that the state of the function has changed to the network node in response to the expiration of the report prohibition timer associated with the function.

[0005] The communication method according to the second aspect is a communication method in a mobile communication system. The communication method includes a step in which a user device receives a message including a report prohibition timer associated with each reason for a change in the function of an AI / ML model from a network node. Further, the communication method includes a step in which, after the state of a function changes due to the reason, the user device transmits a report indicating that the function has changed to the network node in response to the expiration of the report prohibition timer associated with the reason.

[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 conditions for a prohibit timer according to the first embodiment. Figure 13 is a diagram illustrating an example of operation according to the first embodiment.

[0007] This disclosure aims to enable network devices to appropriately understand the functional status of AI / ML models held in user devices.

[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 Check) parity bit added, which is scrambled by the RNTI.

[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 configure, for example, 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 technology. Therefore, depending on virtual use cases, a part 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 the block configuration example, some functions (such as the model training unit A2 or the model inference unit A3, etc.) 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 becomes the data required for input when the AI / ML model performs learning. Also, the inference data becomes the data required for input when the AI / ML model performs inference. Furthermore, the monitoring data becomes the data required for input during the management of the AI / ML model.

[0044] Note that data collection (Data collection) may be, for example, a 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 training an AI / ML model based on 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 providing inputs (x) and outputs (y) (i.e., providing training data) can 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 learned from a large amount of training data, and the correct judgment (range estimation) is performed. Reinforcement learning is a method of learning a method that assigns a score to the output result and maximizes the score. In the following, supervised learning will be described, but as machine learning, unsupervised learning or reinforcement learning may also be applied.

[0048] The model learning unit A2 outputs the trained AI / ML 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 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) "Improved CSI Feedback" "Improved CSI Feedback" 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) (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. When a partial CSI is input, the output of the CSI generation inference unit 1010 will be a CSI with a larger number of CSIs than the partial CSI. Furthermore, the output of the CSI generation inference unit 1010 becomes a CSI when 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 is a diagram showing 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, a UE side model in which inference is performed at UE 100 may be applied, 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. The AI / ML model 103 that performs inference may reside at NW 10 (a network node 200 or CN device 300 included in NW 10).

[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. The AI / ML model 104 may reside 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. The AI / ML model 105 may reside in the NW 10. In the case of AI / ML assisted positioning, there are cases where one AI / ML model 105 is used for multiple inputs (Figure 9(B)), where the same AI / ML model is used for each of the multiple inputs (Figure 10(A)), and where 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] Specifically, the LCM of an AI / ML model may 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: 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 the deletion (or disposal) of AI / ML models. 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".

[0093] 3GPP specifies two types of LCM: function-based LCM and model ID-based LCM.

[0094] 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 messages, MAC CE, or DCI) to instruct the LCM operation on a function of an AI / ML model. In a function-based LCM, UE100 may have one AI / ML model for one function. UE100 may have multiple AI / ML models for a single function.

[0095] 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.

[0096] (Communication method according to the first embodiment) Next, the communication method according to the first embodiment will be described.

[0097] Currently, 3GPP is discussing a report prohibition timer. This timer prevents the UE100 from sending similar reports for a certain period of time, for example, when the functionality of an AI / ML model changes from an applicable state to a non-applicable state. Because the report prohibition timer prohibits report transmission for a certain period, it helps avoid the consumption of wireless resources due to frequent report transmission.

[0098] However, the report prohibition timer can cause the following situations, for example: If the functionality of the AI / ML model it holds changes from an applicable state to an inapplicable state, UE100 cannot send a report until the report prohibition timer expires. Therefore, network devices may not be able to properly understand the functionality status of the AI / ML model in UE100. Similarly, even if the functionality of the AI / ML model changes from an inapplicable state to an applicable state, UE100 cannot send a report to the network device until the report prohibition timer expires. In this case as well, network devices may not be able to properly understand the functionality status of the AI / ML model.

[0099] Therefore, the objective of the first embodiment is to enable the network device to appropriately grasp the functional status of the AI / ML model held in UE100.

[0100] Therefore, in the first embodiment, a report prohibition timer is set for each function of the AI / ML model. Specifically, firstly, the user device (e.g., UE100) receives a message from a network node (e.g., network node 200) that includes a report prohibition timer associated with each function of the AI / ML model. Secondly, after the state of a function changes, the user device sends a report to the network node indicating that the state of the function has changed, in response to the expiration of the report prohibition timer associated with that function.

[0101] As a result, for example, depending on the functionality of the AI / ML model, the expiration time indicated by the report prohibition timer may fall below a certain period, allowing the UE100 to send a report within that period. Therefore, the network device can appropriately understand the status of the AI / ML model's functionality.

[0102] Furthermore, for an AI / ML model's functions to be applicable, this means, for example, that the functions of the AI / ML model can actually be activated. For an AI / ML model's functions to be activatable, this means that they can be executed immediately when an execution command is issued for them. For an AI / ML model's functions to be applicable, if the AI / ML model has multiple functions, it is sufficient if at least one of those functions is applicable.

[0103] On the other hand, "non-applicable" in AI / ML model functionality means, for example, that the AI / ML model functionality cannot actually be activated. If an AI / ML model functionality is not applicable, it cannot be executed immediately even if instructed to do so. If an AI / ML model has multiple functionality, "non-applicable" may mean that at least one of those functionalityes is unavailable.

[0104] (Examples of operation according to the first embodiment) Next, examples of operation according to the first embodiment will be described. There are five examples of operation according to the first embodiment, from the first to the fifth. In addition, there are common examples of operation that are common to the first to the fifth examples of operation according to the first embodiment. First, the common examples of operation will be described, and then the first to the fifth examples of operation will be described in order.

[0105] (1) Common Operation Example Figure 11 is a diagram showing an example of operation according to the first embodiment. Of Figure 11, steps S10 to S21 represent the common operation example. The common operation example will be described below.

[0106] As shown in Figure 11, in step S10, the receiving unit 110 of the UE 100 receives an AI / ML model and model information of the AI / ML model from the OTT (Over The Top) server. The AI / ML model may be a trained AI / ML model. The AI / ML model may be a trained AI / ML model. The model information includes information about the AI / ML model. The information about the AI / ML model may include information indicating what kind of information is input to and output to the AI / ML model. The information about the AI / ML model may include identification information of the AI / ML model (e.g., model ID).

[0107] In step S11, the NW communication unit 240 of the network node 200 receives model information transmitted from the OTT server. The model information is model information relating to the AI / ML model (step S10), and may be the same as the model information transmitted in step S10.

[0108] In step S12, the transmitting unit 210 of the network node 200 sends a UE capability inquiry message to the UE 100. The UE capability inquiry message is used to request wireless access capability from the UE 100. The UE capability inquiry message may also be used to request capability for the AI / ML model (function) from the UE 100. The receiving unit 110 of the UE 100 receives the UE capability inquiry message.

[0109] In step S13, the transmitting unit 120 of UE 100 transmits a UE capability information message to the network node 200 in response to receiving a UE capability inquiry message. The UE capability information message is used to transmit the wireless access capability requested by the network 10. The UE capability information message may also be used to transmit the capability for the AI / ML model (function) requested by the network. The receiving unit 220 of the network node 200 receives the UE capability information message.

[0110] In step S14, the transmitting unit 210 of the network node 200 sends an RRC reconfiguration message to the UE 100 in response to receiving the UE capability information message. The RRC reconfiguration message includes query information inquiring whether the functions of the AI / ML model held by the UE 100 are applicable. Alternatively, the RRC reconfiguration message may include query information inquiring about the applicability of the said functions. The receiving unit 110 of the UE 100 receives the RRC reconfiguration message.

[0111] In step S15, the transmission unit 120 of UE 100 transmits Applicable Function Reporting information to the network node 200 in response to receiving the RRC reconfiguration message. The Applicable Function Reporting information includes information about applicable functions in UE 100. The Applicable Function Reporting information may also include information about non-applicable functions in UE 100. The Applicable Function Reporting information may also be an RRC message. The Applicable Function Reporting information may be transmitted included in an RRC message. Alternatively, the Applicable Function Reporting information may also be an RRC Reconfiguration Complete message. The Applicable Function Reporting information may also be any other RRC message. Alternatively, the applicable function report information may be transmitted in MAC CE or UCI (Uplink Control Information). The receiving unit 220 of the network node 200 receives the applicable function report information.

[0112] In step S16, the transmitting unit 210 of the network node 200 sends an RRC reset message to the UE 100 in response to receiving the applicable function report information. The RRC reset message may include instruction information that instructs activation of the AI / ML model (functions) considering the functions of the applicable AI / ML model reported in the applicable function report information. Specifically, it may include instruction information that instructs activation (startup) of a function selected from the functions of the applicable AI / ML model. The receiving unit 110 of the UE 100 receives the RRC reset message.

[0113] In step S17, the control unit 130 of UE100, upon receiving the RRC reset message (step S16), activates the AI / ML model (which has the function) instructed by the instruction information.

[0114] In the following example, the activation of the AI / ML model initiates inference, but the activation of the AI / ML model may also initiate training or monitoring of the AI / ML model. The instruction information may specify inference, training, or monitoring, and the control unit 130 may perform one of these actions according to the instruction information.

[0115] In step S18, the transmitter 120 of UE 100 sends an RRC Reconfiguration Complete message to the network node 200 in response to the activation of the AI / ML model. The RRC Reconfiguration Complete message may include information indicating that the activation of the AI / ML model instructed by the instruction information (step S16) has been started. The receiver 220 of the network node 200 receives the RRC Reconfiguration Complete message.

[0116] In step S19, the control unit 130 of the UE 100 detects that function #1, one of the functions executed in the activated AI / ML model (step S17), has become unavailable. The inability to use function #1 may also mean that inference using function #1 cannot be performed. The inability to use function #1 includes cases where function #1 changes from an applicable state to a non-applicable state.

[0117] In step S20, the transmitting unit 120 of the UE 100 transmits a UE Assistance Information (UAI) message. The UE Assistance Information message is used to notify the network 10 of the information that the UE 100 requests.

[0118] UE Assist information messages may include AI / ML function notifications that inform the user of the function (status) of the AI / ML model.

[0119] Firstly, the AI / ML function notification may include information indicating that a function of the AI / ML model (function #1 (step S19) in the example of Figure 11) has become unavailable. Alternatively, the AI / ML model function notification may include information indicating that the state of the AI / ML model's function has changed. A change in the state of the AI / ML model's function may mean that the function of the AI / ML model has changed from a non-applicable state to an applicable state. This change may mean that the state of the AI / ML model's function has changed from an applicable state to a non-applicable state. The AI / ML function notification may also be a report used to notify the state of the AI / ML model's function.

[0120] Secondly, the AI / ML function notification may be transmitted in an RRC message other than the UAI. The AI / ML function notification may also be transmitted in a MAC CE or UCI. Hereafter, a message containing the AI / ML function notification may be referred to as a "report". The UE assist information message in step S20 is an example of a "report".

[0121] The information included in the UE assist information message may be configured by configuration information (OtherConfig) sent from the network node 200 to the UE 100. This configuration information may also be included in the RRC reconfiguration message (for example, step S16). The UE 100 may send a UE assist information message including an AI / ML function notification in accordance with this configuration information.

[0122] In step S21, UE100 activates the report prohibition timer. The report prohibition timer is a timer that prohibits the transmission of reports for a certain period of time.

[0123] Firstly, the report prohibition timer may be activated in response to the transmission of a UE assist information message (step S20) that includes an AI / ML function notification. That is, the start condition for the report prohibition timer may be when a UE assist information message that includes an AI / ML function notification is transmitted.

[0124] Secondly, the report disable timer may be set by the network node 200. Specifically, the report disable timer setting information may be included in an RRC message (for example, an RRC reset message) sent from the network node 200. The report disable timer setting information may be included in "OtherConfig" and sent in an RRC reset message (step S16) that includes "OtherConfig". Specific examples of the report disable timer setting information will be explained in each of the operation examples from the first to the fifth operation examples.

[0125] Figure 12 is a diagram showing an example of the conditions for the report prohibition timer according to the first embodiment. As shown in Figure 12, the start condition for the report prohibition timer may be when UE 100 transmits UE assist information (i.e., a "report") including an AI / ML function notification, as described above. The end condition may be when the report prohibition timer is deactivated from the network node 200 to UE 100. The deactivation of the report prohibition timer may be performed by UE 100 receiving an RRC message (e.g., an RRC reset message) from the network node 200 that includes information indicating the deactivation. The information indicating the deactivation may be transmitted via MAC CE or DCI (Downlink Control Information). The expiration operation of the report prohibition timer may be when UE 100 transmits an AI / ML function notification to the network node 200. At least one of the start condition, end condition, and expiration operation may be specified and hardcoded in UE 100. Alternatively, at least one of the start condition, end condition, and expiration action may be included in the report prohibition timer configuration information.

[0126] In the following explanation, the setting information for the report prohibition timer is assumed to be included in the RRC reset message in step S16. However, this setting information may also be included in messages other than the RRC reset message in step S16.

[0127] (1.1) First Operation Example The first operation example is one in which a report prohibition timer, which is associated with each function of the AI / ML model, is used.

[0128] The setting information for the report disable timer (e.g., OtherConfig) is included in the RRC reset message in step S16 (Figure 11).

[0129] Firstly, the report disable timer configuration information may include a format that allows the relationship between each function and each report disable timer to be understood. Specifically, this relationship may be represented by a list format (for example, "ToAddModList") that represents the report disable timer for each function. For example, it may be represented as "Function #1: 12 seconds, Function #2: 10 seconds, ...". A report disable timer may be represented for each function for all functions. The report disable timer may be partially abbreviated and represented as "Function #1: 12 seconds, others: 10 seconds". Alternatively, this relationship may be represented by a mapping format that includes a default report disable timer. For example, it may be represented as "Function #1: 12 seconds, others: default value (30 seconds)". Note that the relationship between each function and each report disable timer may be created by the control unit 230 of the network node 200.

[0130] Secondly, the report prohibition timer settings may specify the signaling used to send reports. The signaling may be an RRC message, MAC CE, or UCI.

[0131] In Figure 11, UE100 activates the report prohibition timer (step S21). This report prohibition timer is assumed to be the report prohibition timer associated with function #1 (hereinafter sometimes referred to as "report prohibition timer #1"), and will be explained below accordingly.

[0132] Furthermore, because function #1 of the AI / ML model becomes unavailable (step S19), function #1 changes from an applicable state to a non-applicable state. UE100 sends a report indicating this change in state (step S20), and the sending of this report satisfies the start condition for report prohibition timer #1, causing report prohibition timer #1 to start (step S21).

[0133] In step S30, the control unit 130 of UE100 detects that function #1, which had been in an unapplicable state, has changed to an applicable state.

[0134] In step S31, the control unit 130 of UE100 checks the report prohibition timer #1.

[0135] In step S32, the transmission unit 120 of UE100 transmits a report indicating that function #1 of the AI / ML model has changed from an unapplicable state to an applicable state, in response to the expiration of report prohibition timer #1. Report prohibition timer #1 is the report prohibition timer associated with function #1, and since this report prohibition timer #1 has expired, UE100 can transmit the report.

[0136] The report may also include information indicating the reason for the change in state. For example, this reason might be that the buffer is full, or that the UE100 has detected low power.

[0137] Furthermore, in UE100, the start condition for report prohibition timer #1 is met by the report transmission (step S32), and therefore report prohibition timer #1 starts up again.

[0138] In step S33, the control unit 130 of UE100 detects that the function #1 of the AI / ML model has changed from an applicable state to a non-applicable state.

[0139] In step S34, the control unit 130 of UE100 checks the report prohibition timer #1.

[0140] In step S35, the transmitter 120 of UE100 transmits a report indicating that the AI / ML function #1 has changed from an applicable state to a non-applicable state, in response to the expiration of the report prohibition timer #1. This report may also include the reason for the change in state. This reason may be, for example, that there is free space in the buffer, or that UE100 is no longer low power.

[0141] Furthermore, the reason for the change in state will be included in the report sent by UE100 in the second operation example and beyond, and therefore, the explanation may be omitted in the second operation example and beyond.

[0142] From this point onward, the report prohibition timer #1 is activated, and the process described above from step S31 onward is repeated.

[0143] Thus, in the first operational example, after the function of the AI / ML model changes, a report indicating that the state of the function has changed is sent from UE100 to network node200 in response to the expiration of the report prohibition timer corresponding to that function.

[0144] (1.2) Second Operation Example Next, a second operation example according to the first embodiment will be described. The second operation example is an example in which, for a specific function of the AI / ML model, a report can be sent from the UE100 even if a report prohibition timer is linked to other functions.

[0145] Specifically, firstly, the user device (e.g., UE100) receives a message from a network node (e.g., network node 200) containing first permission information indicating that the first function may send a report. Secondly, even if a report prohibition timer is associated with a function other than the first function, the user device sends a first report indicating that the state of the first function has changed, in response to a change in the state of the first function.

[0146] As a result, for example, UE100 can send a report to network node 200 regardless of the report prohibition timer when the state of a specific function (e.g., the first function) changes, allowing network node 200 to properly understand the state of that function.

[0147] Figure 13 is a diagram showing an example of operation of the first embodiment. Steps S40 to S42 in Figure 13 represent a second example of operation.

[0148] In addition, similar to the first operation example, in step S16 of the common operation example (Figure 11), the setting information for the report prohibition timer is transmitted from the network node 200 to the UE100 using the RRC reset message.

[0149] Firstly, the report prohibition timer configuration information may include a format that allows the relationship between each function and each report prohibition timer to be understood. Specifically, functions to which the report prohibition timer does not apply may be specified, and for functions to which the report prohibition timer does apply, a report prohibition timer may be associated with each function, similar to the first example of operation. For example, it may be in a list format such as "Function #1: No report prohibition timer applied, Function #2: 13 seconds, Function #3: 10 seconds, ...", or it may be in a mapping format such as "Function #1: No report prohibition timer applied, Functions other than Function #1: Default value (30 seconds)". "No report prohibition timer applied" may be permission information (e.g., first permission information) indicating that the function may send a report. The default value may be a common report prohibition timer.

[0150] Secondly, the report prohibition timer settings may also specify, as in the first example, whether RRC messages, MAC CE, or UCI are used as the signaling for sending reports. The signaling specification is the same for subsequent examples (third to fifth examples), so the explanation will be omitted thereafter.

[0151] In step S40, the control unit 130 of UE100 detects that the state of function #1 has changed from non-applicable to applicable.

[0152] In step S41, the transmitting unit 120 of UE100 transmits a report indicating that the state has changed from non-applicable to applicable because the report prohibition timer for function #1 has not been set according to the setting information (step S16).

[0153] In step S42, the control unit 130 of UE100, for functions other than function #1, has set a report prohibition timer for each function according to the setting information (step S16). Therefore, even if a change in the state of the function is detected, no report will be sent until the report prohibition timer expires. Once the report prohibition timer expires, the report can be sent.

[0154] Furthermore, if permission information for sending reports is set for function #1, UE100 can still send reports even if function #1 changes from an applicable state to a non-applicable state.

[0155] (1.3) Third Operation Example Next, the third operation example will be explained. In the third operation example, when the functional state of the AI / ML model changes from one state to another, the UE100 can send a report regardless of the report prohibition timer.

[0156] Specifically, firstly, if the user device (e.g., UE100) has changed its functionality from a non-applicable state to an applicable state, or if its functionality has changed from an applicable state to a non-applicable state, it receives a message containing second permission information indicating that it may send a report. Secondly, if the user device detects that its functionality has changed from a non-applicable state to an applicable state, or if its functionality has changed from an applicable state to a non-applicable state, it sends a report regardless of the report prohibition timer.

[0157] Thus, when the AI / ML model's functionality changes from one state to another, UE100 can send a report regardless of the report prohibition timer, allowing network node 200 to understand the change in the function's state. Therefore, network node 200 can properly understand the AI / ML model's functionality.

[0158] Steps S50 and S51 shown in Figure 13 illustrate a third example of operation.

[0159] However, similar to the first and second operation examples, in step S16 of the common operation example (Figure 11), the report prohibition timer setting information is transmitted from the network node 200 to the UE 100 using the RRC reset message.

[0160] The report prohibition timer settings may include permission information (e.g., second permission information) indicating that if the AI / ML model functionality changes from a non-applicable state to an applicable state, it may send a report even if the report prohibition timer is set for that function. Alternatively, the report prohibition timer settings may include permission information (e.g., second permission information) indicating that if the AI / ML model functionality changes from an applicable state to a non-applicable state, it may send a report even if the report prohibition timer is set for that function.

[0161] In addition, the report prohibition timer settings may be linked to each function, similar to the first example of operation.

[0162] In step S50, the control unit 130 of UE100 detects that the state of function #1 has changed from a non-applicable state to an applicable state.

[0163] In step S51, the transmitter 120 of UE100 can send a report regardless of the report prohibition timer because permission information is set to allow the report to be sent even if a report prohibition timer is set for function #1. For other functions, the transmitter 120 of UE100 cannot send a report until the report prohibition timer expires, even if it detects that the state has changed from non-applicable to applicable, because the report prohibition timer is set and permission information to send a report is not set for other functions. In this case, the transmitter 120 of UE100 can send the report once the report prohibition timer expires.

[0164] Furthermore, if a report prohibition timer is set for function #1, and permission information is configured to allow the sending of a report when the state changes from applicable to non-applicable, then UE100 can send a report regardless of the report prohibition timer when it detects such a state change.

[0165] (1.4) Fourth Operation Example Next, the fourth operation example will be described. The fourth operation example is an example in which UE100 requests the network node 200 to release the report prohibition timer.

[0166] Specifically, firstly, the user device (e.g., UE100) sends request information (e.g., report prohibition timer release request) to the network node (e.g., network node 200) requesting the release of the report prohibition timer. Secondly, after sending the request information, the user device sends a report to the network node.

[0167] In this way, after UE100 sends a release request, it can send a report to network node 200, which enables network node 200 to properly understand the functions of the AI / ML model.

[0168] Steps S60 to S64 in Figure 13 represent the fourth example of operation.

[0169] However, similar to the first to third operation examples, in step S16 of the common operation example (Figure 11), the report prohibition timer setting information is transmitted from the network node 200 to the UE 100.

[0170] The report prohibition timer configuration information may include authorization information indicating permission to send a report prohibition timer release request (or request information). The authorization information may include identification information (function ID) of the function to which the report prohibition timer release request applies. In this case, UE100 may send a report prohibition timer release request when the state of the function changes. In this case, the conditions for sending the report prohibition timer release request may be specified as a change from an applicable state to a non-applicable state, a change from a non-applicable state to an applicable state, or both. Alternatively, the authorization information may specify the reason for the change in state (for example, UE100 has fallen into a low power state) as the condition for sending the report prohibition timer release request. Alternatively, if the authorization information does not include identification information of the function to which the report prohibition timer release request applies, UE100 may make all functions subject to the report prohibition timer release request. Alternatively, the authorization information may include identification information of a UE 100 that is authorized to request the release of the report prohibition timer. The UE 100 to which this identification information pertains may send the request to release the report prohibition timer. Alternatively, it may be implied that the UE 100 that receives the authorization information is a UE 100 authorized to send a request to release the report prohibition timer. Alternatively, the authorization information may include information indicating the time frame during which a request to release the report prohibition timer can be sent. In addition, the report prohibition timer setting information may be associated with each function, similar to the first example of operation.

[0171] In step S60, the control unit 130 of UE100 detects that the AI / ML model function #1 has changed from a state where the AI / ML model function is not applicable (non-applicable) to a state where it is applicable (applicable).

[0172] In step S61, the transmitter 120 of UE 100 sends a report prohibition timer release request to the network node 200. The transmitter 120 may send the report prohibition timer release request according to the permission information included in the report prohibition timer setting information. The report prohibition timer release request may include the reason for the state change (a change from a state where the AI / ML model's function is not applicable (non-applicable) to a state where it is applicable (applicable)). Alternatively, the report prohibition timer release request may include the report described in the first operation example. Alternatively, the report prohibition timer release request may be included in the report prohibition timer release request. Alternatively, the report prohibition timer release request may include the function ID of the target function. The report prohibition timer release request may include the reason for sending the request. The transmitter 120 may send the report prohibition timer release request using an RRC message, MAC CE, or UCI. The receiver 220 of the network node 200 receives the report prohibition timer release request.

[0173] In step S62, the transmitting unit 210 of the network node 200 sends a message indicating permission to send the report in response to receiving a request to release the report prohibition timer. This information may include the wireless resources used for sending the report. This information may be transmitted using an RRC message, MAC CE, or DCI. The receiving unit 110 of the UE 100 receives this message.

[0174] In step S63, the transmission unit 120 of the UE 100 transmits a report in response to receiving information indicating permission to transmit the report.

[0175] On the other hand, if UE100 receives a message indicating that report transmission is not permitted after sending a request to release the report prohibition timer (step S64), it cannot send a report.

[0176] (1.5) Fifth Operation Example Next, the fifth operation example will be explained. The fifth operation example is an example in which a report prohibition timer is set for each reason why the state of the AI / ML model's functionality has changed.

[0177] Specifically, firstly, the user device (e.g., UE100) receives a message from a network node (e.g., network node 200) that includes a report prohibition timer associated with each reason for the change in the AI / ML model's functionality. Secondly, after the functionality state has changed for a reason, the user device sends a report to the network node indicating that the functionality has changed, in accordance with the expiration of the report prohibition timer associated with that reason.

[0178] In this way, for example, UE100 can send reports depending on the reason why the functional state of the AI / ML model has changed, so the network node 200 can properly understand the functional state of the AI / ML model by receiving the reports.

[0179] A fifth example of operation can be shown by step S16, steps S19 to S21, and steps S30 to S35 shown in Figure 11.

[0180] In other words, in step S16, the UE100 receives the setting information for the report prohibition timer.

[0181] The report prohibition timer settings include a link between each reason and each report prohibition timer. Specifically, the information may be included in a format that allows the relationship between each reason and each report prohibition timer to be understood. For example, as in the first example, each reason may be associated with a report prohibition timer. Alternatively, it may be in a list format such as "Reason #1: 10 seconds, Reason #2: 13 seconds, ..." or in a mapping format such as "Reason #1: 10 seconds, Other reasons: default value (e.g., 30 seconds)". Depending on the reason, "Report prohibition timer not applied" may be associated, as in the second example. In this case, if the function of the AI / ML model changes due to the reason, it may be possible to send reports regardless of the report prohibition timer.

[0182] In UE100, the inability to use function #1 triggers a change in state (a change from an applicable state to a non-applicable state), and the reason for this change in state #1 is detected (step S19).

[0183] Then, UE100 sends a report (step S20) and activates the report prohibition timer #1 associated with reason #1 (step S21).

[0184] In step S30, the control unit 130 of the UE100 detects a change in the state of function #1 of the AI / ML model (a change from an unapplicable state to an applicable state) and also detects the reason for the change in state.

[0185] In step S31, the control unit 130 of UE100 checks the report prohibition timer #1. The reason for the state change in step S19 and the reason for the state change in step S30 are basically expected to be inversely related. For example, in step S19, the buffer becomes full, resulting in a non-applicable state, and in step S30, free space becomes available in the buffer, resulting in an applicable state. The control unit 130 of UE100 may also assume that the reasons for the two state changes are the same and check the report prohibition timer #1 associated with reason #1 (the report prohibition timer #1 started in step S21).

[0186] In step S32, the transmission unit 120 of UE100 transmits a report because the report prohibition timer #1 has expired.

[0187] Subsequently, the report transmission (step S32) restarts the report prohibition timer #1, and in response to the detection of a state change in function #1 (a change from an applicable state to an inapplicable state) in UE 100 (step S33), the report prohibition timer #1 is checked (step S34). Here, the reason for the state change is assumed to be reason #1, as in steps S19 and S31. Then, the transmission unit 120 of UE 100 can transmit a report in response to the expiration of the report prohibition timer #1 associated with reason #1 (step S35).

[0188] (2) Other Operation Examples According to the First Embodiment In the first embodiment, the transmission of reports (e.g., steps S20 and S32) was described in an example where the reports were transmitted using RRC messages, MAC CE, or UCI. For example, the transmission of a report may be sent as a new message (e.g., an AI / ML layer message) for a newly defined layer (e.g., an AI / ML layer) for the AI / ML model. The ApplicableFunctionalityReporting message (step S15) and the RRC reset message (step S16) including the report disable timer setting information may also be sent as AI / ML layer messages.

[0189] Furthermore, in the first embodiment, the applicability (applicable or non-applicable) of a function was described, but the scope of applicability may not be limited to functions, but may also be the use cases of the AI / ML model. Alternatively, the scope of applicability may be the sub-use cases of the AI / ML model. In other words, when the applicability of a use case or sub-use case changes, UE100 should send a report indicating that the applicability of the use case or sub-use case has changed, depending on whether the report prohibition timer associated with each use case or each sub-use case has expired.

[0190] Alternatively, the AI / ML model may be the subject of applicability. In this case, if the applicability of the AI / ML model changes, UE100 should send a report indicating that the applicability of the AI / ML model has changed, in accordance with the expiration of the report prohibition timer associated with the AI / ML model.

[0191] Alternatively, the Associated ID may be the target of the applicability. The Associated ID is, for example, an ID set for each CSI report setting. Alternatively, the Associated ID may represent identification information at the report configuration level. Alternatively, the Associated ID may represent identification information at the resource configuration level. Alternatively, the Associated ID may represent identification information at the resource set level. In UE100, if the applicability of an Associated ID changes, a report indicating that the applicability of the Associated ID has changed should be sent in accordance with the expiration of the report prohibition timer associated with each Associated ID.

[0192] Furthermore, instead of applicability, the term "Supported Functionality" may be used for a function. In this case, when the supportability changes, the UE100 should send a report indicating that the supportability has changed, in accordance with the expiration of the prohibition timer associated with each function. Instead of supportability, "Configured Functionality" (whether the function is configurable or not) or "Available Functionality" (whether the function is usable or not) may also be used.

[0193] [Other Embodiments] The above-described operation flows are not limited to being performed separately and independently; two or more operation flows can be combined and performed. 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. Also, the order of steps in each flow may be changed as appropriate.

[0194] In the embodiments and examples described above, an example in which the base station is an NR base station (gNB) was described, 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. Furthermore, 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.

[0195] 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.

[0196] A program may be provided that causes a computer to execute each process performed by the UE 100 or the network node 200. 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 recording medium. The non-transient recording medium is not particularly limited, but may be a recording medium such as a CD-ROM and / or DVD-ROM. Alternatively, the circuits that execute each process performed by the UE 100 or the network node 200 may be integrated, and at least a part of the UE 100 or the network node 200 may be configured as a semiconductor integrated circuit (chipset, SoC: System on a chip).

[0197] The functions realized by the above-described communication device (UE100 or network node 200, etc.) 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 circuitry, and / or a combination thereof, programmed to realize the described functions. The processor includes transistors and / or other circuits and is considered a circuit or processing circuit. The processor may also be a programmed processor that executes a program stored in memory. In this specification, circuit, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If such hardware is a processor that is considered to be of the type of circuit, such circuit, means, or unit is a combination of hardware and software used to constitute such hardware and / or processor.

[0198] 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.

[0199] 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 invention.

[0200] This application claims priority to U.S. Provisional Application No. 63 / 754157 (filed February 5, 2025), the entirety of which is incorporated into the specification of this application.

[0201] (First Note) The embodiments described above can be summarized as shown in the note, but the note does not limit the embodiments.

[0202] (Note 1) A communication method in a mobile communication system, comprising the steps of: a user device receiving a message from a network node that includes a report prohibition timer associated with each function of an AI / ML model; and the user device sending a report to the network node indicating that the state of the function has changed, in response to the expiration of the report prohibition timer associated with the function after the state of the function has changed.

[0203] (Note 2) The communication method described in Note 1, wherein the report prohibition timer associated with each function is represented by either a list format representing the report prohibition timer for each function, or a mapping format including the default report prohibition timer.

[0204] (Note 3) The communication method according to Note 1 or Note 2, wherein the start condition for the report prohibition timer is when the user device transmits the report, and the end condition for the report prohibition timer is when the network node cancels the setting of the report prohibition timer for the user device.

[0205] (Note 4) The communication method according to any one of Notes 1 to 3, wherein the receiving step includes the step of the user device receiving the message from the network node, which includes first permission information indicating that the first function may transmit the report, and the transmitting step includes the step of the user device transmitting a first report indicating that the state of the first function has changed, in response to a change in the state of the first function, even if the report prohibition timer is associated with a function other than the first function.

[0206] (Note 5) The communication method according to any one of Notes 1 to 4, wherein the receiving step includes receiving a message containing second permission information indicating that the user device may send the report if the function has changed from a non-applicable state to an applicable state, or if the function has changed from an applicable state to a non-applicable state, and the transmitting step includes sending the report regardless of the report prohibition timer in response to the user device detecting that the function has changed from a non-applicable state to an applicable state, or if the function has changed from an applicable state to a non-applicable state.

[0207] (Note 6) The communication method according to any one of Notes 1 to 5, further comprising the steps of: the user device sending request information to the network node requesting the release of the report prohibition timer; and the user device sending the report to the network node after sending the request information.

[0208] (Note 7) A communication method in a mobile communication system, comprising the steps of: a user device receiving a message from a network node including a report prohibition timer associated with each reason for a change in the function of an AI / ML model; and the user device sending a report to the network node indicating that the function has changed after the state of the function has changed due to the reason, in response to the expiration of the report prohibition timer associated with the reason.

[0209] (Note 8) The report is a communication method described in any one of Notes 1 to 3, which includes an AI / ML model function notification that notifies the functions of the AI / ML model.

[0210] 1: Mobile communication system 10: NW 20: RAN 30: CN A1: Data acquisition unit A2: Model learning unit A3: Model inference unit A5: Management unit A6: Model recording unit 100: UE 102: CSI prediction model 103: AI / ML model 104: AI / ML model 105: AI / ML model 101: CSI generation unit 1010: Inference unit for CSI generation 1011: Quantization unit 110: Receiving unit 120: Transmitting unit 130: Control unit 140: Communication unit 200: Network node 201: CSI reconstruction unit 2010: Inverse quantization unit 2011: Inference unit for CSI reconstruction 200a-200c: Network node 210: Transmitting unit 220: Receiving unit 230: Control unit 240: Network Communications Unit 250: Communications Unit 300: CN Equipment

[0211] (Second Addendum) 1. Introduction This addendum discusses the LCM (Lifecycle Management) of the UE-side model in beam management use cases, the applicable functions, the reasons for the changes in applicability, and remaining issues regarding the UAI prohibition timer.

[0212] 2. Discussion 2.1 Remaining Issues 2.1.1 Applicable Functions This section examines how applicable functions are defined. The response LS from RAN1 includes the following description regarding applicable functions.

[0213] Response LS from RAN1 (R1-2410898) (omitted) - The concept / term "function" of applicable functionality may refer to a CSI-ReportConfig for inference configuration, or a set of inference-related parameters. (omitted) - In step 3, the following configuration is provided from NW to UE: - UE is permitted to perform UAI reporting via OtherConfig. - Applicability reporting is based on A) and / or B) below: - Container design is left to RAN2. A) One or more CSI-ReportConfig for inference configuration (where AssociatedID may be set in the CSI framework as applicable working assumptions). Note: CSI report configuration for inference of the UE-side model cannot be activated immediately after receiving step 3. B) One or more sets of inference-related parameters for applicability reporting only (not for inference). • Container design is left to RAN2. • The set of inference-related parameters is selected as a starting point from information elements (IEs) within or referenced by CSI-ReportConfig. For example: • Associated ID • Note: This does not mean that Associated ID is required. • Set A related information • Set B related information • Report content related information • In the case of BM-Case 2, • Time instance related information regarding measurement • Time instance related information regarding prediction

[0214] From the above, it can be understood that the applicability report is based on A) and B).

[0215] The AssociatedID in A) (i.e., the ID linked to CSI-ReportConfig) is appropriate to apply as an applicable function and is considered an obvious conclusion. However, it should be noted that RAN1 treats this as a Working Assumption.

[0216] Proposal 1: Considering that RAN1 defined this as a working assumption, RAN2 should adopt AssociatedID in A) as an applicable function and treat it as a working assumption.

[0217] In case B), it is not necessarily associated with the AssociatedID, but instead involves signaling some related parameters to the UE. These parameters may or may not include the AssociatedID, and can potentially be classified into the following three cases: A) Use the AssociatedID B) Use the AssociatedID + related information C) Do not use the AssociatedID, and use only the related information Related information: • Set A related information • Set B related information • Report content related information • In the case of BM case 2 • Time instance related information for measurement • Time instance related information for prediction

[0218] Focus 1: Whether or not to use IDs The first focus is whether to assign IDs to "related information" or to use it as is. When deciding whether or not to use IDs, the following criteria should be considered: • Reusability: If the information is shared among multiple UEs, assigning IDs can reduce the amount of information required for transmission. • Scalability: Evaluate whether assigning IDs makes it easier to add new information or to accommodate specification changes. • Transmission efficiency: Quantitatively evaluate how much signal overhead can be reduced by assigning IDs. • Uniqueness: If the information is unique to a specific UE (e.g., related information for set A), assigning IDs may not improve transmission efficiency and may have limited value.

[0219] Focus 2: Who Should Assign the ID? The next focus is to determine which working group (WG) should assign the ID to this information. For example: • When it should be requested to RAN1: • When the information is handled at the physical layer (PHY) (e.g., CSI measurement-related information). • When it should be handled by RAN2: • When the information is handled at the higher layer (RRC) (e.g., information in applicability reports). • Handling of ambiguous information: • For information that is relevant to both the PHY and RRC layers, it is necessary to discuss and clarify which WG should take the lead.

[0220] Based on the above, we propose the following:

[0221] Proposal 2: RAN2 should consider criteria such as reusability, scalability, and transmission efficiency, and discuss whether it should assign IDs related to the information in B) (e.g., set A / B related information, time related information, etc.).

[0222] Proposal 3: Based on the division of roles between the physical layer (PHY) and the upper layer (RRC), RAN2 should clarify which group (RAN1 or RAN2) is responsible for assigning IDs related to the information in B).

[0223] Proposal 4: RAN2 should discuss how to handle ambiguous information (e.g., function-related information).

[0224] Proposal 5: RAN2 should discuss which working group (WG) should handle ambiguous information, such as that between PHY and RRC.

[0225] 2.1.2 Reporting of Applicable Features 2.1.2.1 Reasons for Changes in Applicability In RAN2#128, RAN2 reached the following agreement regarding how inapplicable features should be reported:

[0226] "Agreement (RAN2#128): Whether the UE will explicitly report 'non-applicable' features in the event of a change in applicability is a matter for consideration."

[0227] During the RAN2 #128 meeting, the discussion on whether UEs should explicitly or implicitly report unapplicable features to the NW was divided between companies supporting explicit reporting and those supporting implicit reporting, making it a matter for further consideration. Simultaneously, there was a discussion on whether it is necessary to include the reason when a feature changes. Here, we will examine whether it is necessary to provide a reason when an applicable feature becomes unapplicable.

[0228] 1. Positive Impact of Providing Reasoning Information By providing reasoning information, the network can clearly understand why the applicability of a function has changed on the UE side. This enables specific actions such as: A) Hardware limitations on the UE side (e.g., computing resources, power) For example, if the UE is constrained by computing resources or memory, providing reasoning information allows the network to dynamically evaluate the situation and optimize its response. This applies to scenarios where the network's actions are not predetermined and can be adjusted based on specific computing resource limitations, such as selectively disabling AI / ML functions. B) Suitability or Non-suitability of Conditions For example, if the UE no longer meets certain conditions, such as additional conditions on the network side, the network can decide to apply alternative functions. By obtaining reasoning information, the network can be notified of the specific reasons. C) Compatibility or Incompatibility with Conditions For example, if the conditions required by the UE do not match the network's conditions, providing reasoning information allows the network to identify the mismatched parameters and quickly adjust the conditions as needed.

[0229] 2. Cases where reason information is unnecessary On the other hand, the following scenarios are considered cases where reason information is unnecessary: ​​1) If a hardware limitation on the UE side is detected and the network cannot apply the AI / ML function due to a predetermined response, reason information is unnecessary. This applies to scenarios where the network action is fixed and cannot be adjusted based on the specific reasons behind the hardware limitation. 2) If the conditions are determined to be incompatible, the UE cannot use the corresponding function regardless of the reason. Therefore, in such cases, providing reason information is considered unnecessary. 3) Through inference results and monitoring-based decisions, the network may be able to estimate changes in the UE's applicability status. For example, if the UE does not meet the signal strength or throughput requirements, the network can infer the reason from the monitoring data. If the monitoring results are sufficient, it may not be necessary to have the UE explicitly send reason information. Furthermore, if such a reason is included in the inference results, the network can identify the cause that led to the UE being in an unapplicable state and make a decision to apply an alternative function. Thus, there are scenarios in which reason information is not necessarily required.

[0230] 3. RAN1 Response LS (Reply LS) and its Impact As discussed in Section 2.1.1 of this document, applicable features may be linked to AssociatedID, and consequently, to CSIReportConfig and various types of related information. These can be considered to represent the conditions for applicability and non-applicability.

[0231] Therefore, if non-compliance with these conditions determines applicability or non-applicability, it is not necessary to submit reason information.

[0232] The above discussion concerns the change from "applicable" to "inapplicable." However, the same reasoning can be applied to the change from "inapplicable" to "applicable."

[0233] Overall, there doesn't seem to be a clear justification for introducing reasoning information at this stage. Therefore:

[0234] Proposal 6: RAN2 should agree that it is not required to provide reasons when reporting changes in functionality.

[0235] 2.1.2.2 Explicit or Implicit Representations Regarding explicit or implicit representations, it is possible to effectively convey both meanings by, for example, using bitmaps. Through the work in Stage 3, it is important to determine the final specific representation and finalize the appropriate specifications, as the representation itself can have both implicit and explicit meanings.

[0236] Proposal 7: Regarding the consideration of explicit or implicit methods of expression, since these methods can have both implicit and explicit meanings, it is considered appropriate to address this in Stage 3.

[0237] 2.1.3 UAI Disable Timer In RAN2#127-bis, RAN2 reached the following agreement regarding how inapplicable functions should be reported:

[0238] "Agreement (RAN2#127-bis): UAI is supported, and the RRCReconfigurationComplete message can be used to report applicable features. We should aim to standardize the design regarding how applicable features are signaled. The content of the applicability report is a matter for consideration."

[0239] To date, UAI-related functions (e.g., DelayBudgetReport, OverheatingAssistance, etc.) have been equipped with a prohibition timer, which has been shown to be effective in suppressing unnecessary short-term reports and reducing network load. This note examines the possibility of applying a similar prohibition timer to applicable function reports.

[0240] First, let's consider the advantages and disadvantages of introducing a ban timer.

[0241] Advantages and Disadvantages of Prohibition Timers: Advantages: By limiting the continuous transmission of UAIs for short periods, prohibition timers reduce network load and enable efficient signal transmission. Applying mechanisms already used in other functions to AI / ML functions standardizes system behavior and reduces operational complexity. Disadvantages: In scenarios requiring rapid response to environmental or conditional changes, the introduction of prohibition timers can cause notification delays, potentially impacting model applicability and system adaptability. If state transitions are infrequent, the effect of introducing timers may be limited, risking reduced flexibility. When fine granularity is required, it may be necessary to configure multiple timers, raising concerns about increased operational complexity. A disadvantage of using timers is that the network (NW) must decide how to set the appropriate timer value. This process is not always straightforward, as some of the factors influencing the decision depend on the UE.

[0242] From the above, it can be understood that the drawback of introducing a prohibit timer is its inability to handle frequent changes between applicable and inapplicable states. However, legacy UAI prohibit timers allow setting timer values ​​within a range such as 0, 0.4, 0.8, 1.6, 3, 6, 12, and 30 seconds, for example, as DelayBudgetReportingProhibitTimer, making it possible to select an appropriate value even in scenarios where responsiveness is required. Based on this, it is considered that there are no major problems associated with introducing a prohibit timer. Therefore, the introduction of a prohibit timer is recommended.

[0243] Next, we will consider the granularity of the prohibition timer.

[0244] The feasibility of implementing a prohibit timer in applicable functional reporting depends heavily on the requirements for timer granularity and responsiveness. • Coarse granularity (e.g., use case level, sub-use case level): In this case, timers are set for larger functional units, so responsiveness requirements are lower. Implementing a prohibit timer is expected to be effective. • Fine granularity (e.g., applicable functional levels such as report configuration level, resource configuration level, or resource set level): In this case, frequent state changes may occur, and responsiveness may be extremely important. In such scenarios, timer values ​​need to be set flexibly.

[0245] Discussion on the Granularity of Applicable Functions in RAN1 As discussed in Section 2.1.1 of this document, the granularity of applicable functions is based on the following: A) Using AssociatedID B) Using AssociatedID + related information C) Using related information only, without AssociatedID

[0246] In this sense, the granularity of the applicable functions can be considered relatively fine.

[0247] However, when using multiple timers, responsiveness may improve if they are divided, for example, by the granularity of AssociatedID, but this is likely to increase the complexity of the specification and add overhead.

[0248] On the other hand, setting timers at the use-case level may result in too coarse a granularity, making control difficult. Therefore, defining timers at the sub-use-case level is a feasible approach, but it is suggested that this should be addressed in Stage 3.

[0249] Proposal 8: RAN2 should introduce an optional disable timer related to changes in applicable functionality, similar to legacy UAI settings.

[0250] Proposal 9: The number of timers and the detailed settings of the timer values ​​should be determined in Stage 3, assuming that flexible timer value settings will be used in scenarios where responsiveness is required.

Claims

1. A communication method in a mobile communication system, comprising: a user device receiving a message from a network node that includes a report prohibition timer associated with each function of an AI / ML model; and the user device transmitting a report to the network node indicating that the state of the function has changed, in response to the expiration of the report prohibition timer associated with the function after the state of the function has changed.

2. The communication method according to claim 1, wherein the report prohibition timer associated with each function is represented by either a list format representing the report prohibition timer for each function, or a mapping format including the default report prohibition timer.

3. The communication method according to claim 1, wherein the start condition for the report prohibition timer is when the user device transmits the report, and the end condition for the report prohibition timer is when the network node cancels the setting of the report prohibition timer for the user device.

4. The communication method according to claim 1, wherein the receiving includes the user device receiving the message from the network node, which includes first permission information indicating that the first function may transmit the report, and the transmitting includes the user device transmitting a first report indicating that the state of the first function has changed, in response to a change in the state of the first function, even if the report prohibition timer is associated with a function other than the first function.

5. The communication method according to claim 1, wherein the receiving includes receiving the message containing second permission information indicating that the user device may transmit the report if the function has changed from a non-applicable state to an applicable state, or if the function has changed from an applicable state to a non-applicable state; and the transmitting includes transmitting the report regardless of the report prohibition timer in response to the user device detecting that the function has changed from a non-applicable state to an applicable state, or if the function has changed from an applicable state to a non-applicable state.

6. The communication method according to claim 5, further comprising: the user device transmitting request information to the network node requesting the release of the report prohibition timer; and the user device transmitting the report to the network node after transmitting the request information.

7. A communication method in a mobile communication system, comprising: a user device receiving a message from a network node that includes a report prohibition timer associated with each reason for a change in the function of an AI / ML model; and the user device transmitting a report to the network node indicating that the function has changed after the state of the function has changed due to the reason, in response to the expiration of the report prohibition timer associated with the reason.

8. The communication method according to claim 1 or 7, wherein the report includes an AI / ML model function notification that notifies the function of the AI / ML model.

Images