Communication method

Abstract

A communication method according to one aspect is used in a mobile communication system. The communication method includes a step in which a user equipment detects a function of a non-applicable artificial intelligence / machine learning (AI / ML) model. In addition, the communication method includes a step in which the user equipment transmits, to a first network device, auxiliary information including information pertaining to timing at which the function of the AI / ML model is applicable.

Description

Communication method

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

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

[0003] 3GPP TR 38.843 V18.0.0 (2023 - 12) 3GPP TS 38.000 V18.3.0 (2024 - 09) 3GPP TS 28.105 V19.0.0 (2024 - 09)

[0004] The communication method according to the first aspect is a communication method in a mobile communication system. The communication method includes a step in which a user device detects a function of an AI / ML model that is not applicable. Further, the communication method includes a step in which the user device transmits auxiliary information including information regarding a timing when the function of the AI / ML model becomes applicable to a first network device.

[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 detects a function of an AI / ML model that is applicable. Further, the communication method includes a step in which the user device transmits auxiliary information including information regarding a timing when the function of the AI / ML model is not applicable to a first network device.

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

[0007] This disclosure aims to enable a network device to instruct a user device to perform LCM operations regarding the functionality of an AI / ML model at an appropriate time.

[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 a plurality of network nodes 200 (network nodes 200a to 200c in the example of 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 be either the network node 200 or the CN device 300.

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

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

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

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

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

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

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

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

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

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

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

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

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

[0030] The network node 200 can 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, some parts of the block configuration example (such as the model recording unit A6, etc.) may not be included in the block configuration example. Also, the block configuration example shown in FIG. 6 may be distributed and arranged between the UE 100 and the network device. Alternatively, for some functions of the block configuration example (such as the model training unit A2 or the model inference unit A3, etc.), they may be arranged in both the UE 100 and the network device.

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

[0043] The training data 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, the process of collecting data in a network node, a management entity, or the UE 100 for performing learning of an AI / ML model, management of an AI / ML model, and inference of an AI / ML model.

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

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

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

[0048] The model learning unit A2 outputs the trained AI / ML model obtained by AI / ML model training to the model recording unit A6, and the model learning unit A2 also outputs the updated AI / ML model obtained by retraining the trained AI / ML model to the model recording unit A6.

[0049] In the following, AI / ML model training may be referred to as "model training" or "training".

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

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

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

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

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

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

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

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

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

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

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

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

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

[0063] The CSI generation unit 101 includes a CSI generation inference unit 1010 and a quantization unit 1011. The CSI generation inference unit 1010 infers CSI (inference output data) from the input using a trained AI / ML model. The input to the CSI generation inference unit 1010 may be, for example, a partial (or punctured) CSI. The partial CSI may be a CSI measured using a CSI reference signal (CSI-RS) (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 may reside at NW 10 (a network node 200 or CN device 300 included in it).

[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 values ​​of beamset B, which are the input to the AI / ML model 103, may be represented by 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 the measured value at each measurement point (TRP: Transmission and / or Reception Point). The measured value can be, for example, a Channel Impulse Response (CIR), a Power Delay Profile (PDP), or a fingerprint. For example, 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. The position information may also be represented by a fingerprint. The fingerprint represents, for example, the measurement information for the cell of the UE 100.

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

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

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

[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 message, MAC CE, or DCI) to instruct the LCM operation on a function of an AI / ML model. In a function-based LCM, the UE 100 may have one AI / ML model for one function, or it may have multiple AI / ML models for one function.

[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] For example, in a UE side model where model inference (hereinafter sometimes referred to as "inference") is performed on the UE100 side, the functions of the AI / ML model can be classified as follows:

[0098] Supported functions: Supported functions are those that UE100 can indicate using UE Capability Information messages. Functions of the AI / ML model that UE100 can report to network devices using UE Capability Information messages can be considered supported functions.

[0099] Applicable functions: Applicable functions are those that enable UE100 to perform inference using AI / ML models. A function that allows UE100 to perform AI / ML model inference upon instruction from a network device is considered an applicable function.

[0100] Activated functions: Activated functions are those in UE100 that perform inference using AI / ML models. In UE100, any function of the AI / ML model in which inference is performed can be considered an activated function.

[0101] In the first embodiment, applicable functions will be described.

[0102] Here, we assume the following scenario: UE100 detects that a certain AI / ML model's functionality was initially applicable, but subsequently became non-applicable. UE100 then reports to the network device that the AI / ML model's functionality is non-applicable.

[0103] In such cases, the network device can confirm that the function in question cannot be applied. However, it cannot confirm when the function will become applicable. Therefore, the network device may not be able to instruct the UE100 to activate the function at the appropriate time.

[0104] Therefore, the objective of the first embodiment is to enable the network device to instruct the UE100 to perform LCM operations regarding the functions of the AI / ML model at an appropriate timing.

[0105] Therefore, in the first embodiment, when UE 100 detects that a function of the AI / ML model cannot be applied, it reports to the network device the timing at which that function will next become applicable. Specifically, firstly, the user device (e.g., UE 100) detects a non-applicable function of the AI / ML model. Secondly, the user device transmits auxiliary information, including information about the timing at which the function of the AI / ML model becomes applicable, to the first network device (e.g., network node 200).

[0106] The network device can confirm the timing at which the function becomes applicable, and by sending an activation instruction for the function to the UE100 at that timing, it becomes possible to instruct the LCM operation (in this case, activation) at the appropriate time.

[0107] (Example of operation according to the first embodiment) Next, an example of operation according to the first embodiment will be described.

[0108] Figure 11 is a diagram illustrating an example of operation according to the first embodiment. In Figure 11, a network node 200 is used as an example of a network device.

[0109] In the following explanation, messages or information are transmitted from the network node 200 to the UE 100, and these may be transmitted using RRC messages, MAC CE, or DCI (Downlink Control Information). Alternatively, they may be transmitted using AI / ML layer messages newly introduced for AI / ML models. Similarly, messages or information are transmitted from the UE 100 to the network node 200, and these may also be transmitted using RRC messages, MAC CE, UCI (Uplink Control Information), or new AI / ML layer messages. In all cases, the explanation will be omitted below.

[0110] As shown in Figure 11, in step S10, the NW communication unit 240 of the network node 200 receives a trained AI / ML model (hereinafter sometimes referred to as "AI / ML model") from the OTT (Over The Top) server. The NW communication unit 240 may receive multiple AI / ML models. The NW communication unit 240 may also receive the function ID of the AI / ML model along with the AI / ML model. The NW communication unit 240 may also receive usage conditions from the OTT server indicating the conditions for using the AI / ML model along with the AI / ML model. The usage conditions received from the OTT server may be represented by identification information that identifies the usage conditions.

[0111] In step S11, the transmitting unit 210 of the network node 200 forwards the received AI / ML model to the UE 100. The transmitting unit 210 may also forward the function ID and usage conditions to the UE 100. The receiving unit 110 of the UE 100 receives the AI / ML model.

[0112] In step S12, the transmission unit 210 of the network node 200 sends a UE Capability Query message. The UE Capability Query message may include information to inquire whether the functionality of the AI / ML model held by the UE 100 is applicable.

[0113] In step S13, the control unit 130 of the UE 100 determines whether the functions of the AI / ML model it holds are applicable in response to the UE capability inquiry message it has received. The control unit 130 may also determine whether the functions of the AI / ML model are applicable based on the usage conditions of the AI / ML model received in step S11. Here, we will continue the explanation assuming that the control unit 130 has determined that the functions of the AI / ML model (function ID = function #1) received in step S11 are applicable.

[0114] In step S14, the transmitting unit 120 of UE 100 transmits a UE Capability Information message to the control unit 130. The UE Capability Information message includes information indicating that function #1 is applicable ("function #1 = OK"). The UE Capability Information message is a response message to the UE Capability Inquiry message (step S12). The receiving unit 220 of the network node 200 receives the UE Capability Information message.

[0115] In step S15, the transmission unit 210 of the network node 200 sends an AI / ML Configuration message to the UE 100. The AI / ML Configuration message may be a message that instructs LCM operation for a function of the AI / ML model. Specifically, the AI / ML Configuration message can specify a function ID and instruct activation to instruct the UE 100 to activate the AI / ML model having that function ID. The network node 200 can use the AI / ML Configuration message to instruct the UE 100 to perform LCM operation on a function basis. In step S15, the AI / ML Configuration message does not specifically instruct LCM operation, but is used to check the state of the AI / ML model held by the UE 100. Alternatively, the AI / ML Configuration message may specify function ID = function #1 and be used to check the state of the AI / ML model having that function. Note that the AI / ML setting message may also be an RRC reconfiguration message. The receiving unit 110 of UE100 receives the AI / ML setting message.

[0116] In step S16, the control unit 130 of UE100 checks the status of the AI / ML model in response to receiving the AI / ML setting message and detects that function #1 of the AI / ML model is not applicable. The control unit 130 may detect that it is not applicable for the following reasons, for example:

[0117] - Insufficient memory; - Insufficient CPU resources; - Thermal conditions are met; - Insufficient battery level; - Does not meet usage conditions (e.g., location conditions, time conditions, wireless conditions (RSRP), network conditions (e.g., number of Set B beams), etc.); The AI / ML setting message received in step S15 may include information such as conditions and thresholds for determining whether or not it can be applied to the functions of the AI / ML model, and the control unit 130 may make a determination based on this information.

[0118] In step S17, the transmission unit 120 of UE 100 sends an AI / ML Configuration Complete message to the network node 200. The AI / ML Configuration Complete message may also be an RRC Reconfiguration Complete message or a UE Assistance Information message.

[0119] The AI / ML setup completion message may include information indicating that function ID = function #1 cannot be applied. In the example in Figure 11, "function ID #1 = NG (= non-applicable)" is included in the AI / ML setup completion message. The control unit 130 of UE 100 may set this information in the AI / ML setup completion message in response to its determination in step S16 that function #1 cannot be applied.

[0120] Additionally, the AI / ML setup completion message includes supplementary information.

[0121] Firstly, the auxiliary information includes information about when the AI / ML model's functionality will become applicable. Specifically, this timing information may be expressed in one of the following ways:

[0122] - Time (e.g., applicable from 15:00); - Elapsed time (e.g., applicable from 1 hour later); - Infinity (the timing of applicability is infinitely far in the future) or Unknown (the timing of applicability is unknown); Secondly, the auxiliary information may include reason information (cause) indicating why the AI / ML model's functions cannot be applied. The reason information may be, for example, the following:

[0123] - Insufficient remaining memory (e.g., 10% remaining); - Insufficient CPU resources (e.g., 5% remaining); - Thermal conditions not met (e.g., cooling required); - Usage conditions not met (e.g., geographical conditions not met, wireless conditions not met); Thirdly, the auxiliary information may include information regarding the reliability of the information contained in the auxiliary information. The reliability information may be represented, for example, by "high," "medium," and "low." "High" represents the highest reliability, and "low" represents the lowest reliability, respectively. The control unit 130 may determine the reliability information depending on the reason why it cannot be applied.

[0124] When the control unit 130 detects that the functions of the AI / ML model cannot be applied, it generates auxiliary information and sets this auxiliary information in the AI / ML setting completion message, so that the transmission unit 120 can send the AI / ML setting completion message including the auxiliary information. Figure 11 shows an example in which auxiliary information #1 is included in the AI / ML setting completion message as auxiliary information. The receiving unit 220 of the network node 200 receives the AI / ML setting completion message.

[0125] In step S18, the control unit 230 of the network node 200 waits until the timing for which it becomes applicable is reached, based on the information regarding the timing of applicability included in the auxiliary information (auxiliary information #1). That is, the network node 200 waits until the timing when the function (function #1) of the AI / ML model that was reported as not applicable becomes applicable.

[0126] In step S19, the transmission unit 210 of the network node 200 sends an AI / ML configuration message to the UE 100 at that time. The AI / ML configuration message includes information specifying a function ID (function #1) and instructing the UE 100 to activate the AI / ML model having that function. The network node 200 instructs the UE 100 to activate the function of the AI / ML model because the timing has come when the function of the AI / ML model is applicable. The UE 100 receives the AI / ML configuration message at that time. The UE 100 then activates the AI / ML model having function #1.

[0127] In the example of step S19, the network node 200 instructs activation at the time when it becomes applicable, but the network node 200 may also confirm whether or not it is permissible to activate the function. For example, the control unit 230 of the network node 200 may confirm whether or not it is permissible to activate the function based on the confidence level included in the auxiliary information, if the confidence level at the time of applicability is "low". Conversely, step S19 may be performed because the confidence level was "high," and the activation instruction is given without confirmation. Specifically, this confirmation is carried out by processing from step S20 onward.

[0128] In other words, in step S20, the transmission unit 210 of the network node 200 sends an AI / ML function inquiry message. The AI / ML function inquiry message is a message used by the network device to inquire about the function of the AI / ML model from the UE 100. The AI / ML function inquiry message may also be an RRC reconfiguration message. The AI / ML function inquiry message may include a function ID (=function #1) corresponding to auxiliary information #1. The AI / ML function inquiry message may also be used as a message to inquire about the status of function #1 in the UE 100.

[0129] In step S21, the transmission unit 120 of UE 100 sends a Function Reporting message to the network node 200 in response to receiving the AI / ML function inquiry message (step S20). The Function Reporting message may be an RRC Reconfiguration Complete message or a UE Assistance Information message. The Function Reporting message is used to report the status of the function inquired about in the AI / ML function inquiry message. The Function Reporting message may be a response message to the AI / ML function inquiry message. In the example shown in Figure 11, since function #1 is in a non-applicable state, the function report message includes information indicating that function #1 cannot be applied ("function ID = NG"), along with auxiliary information #2. Auxiliary information #2 includes information about when function #1 becomes applicable. The type of information included in auxiliary information #2 may be the same as that in auxiliary information #1. The receiving unit 220 of the network node 200 receives the function report message.

[0130] In step S22, the control unit 230 of the network node 200 waits until the timing is reached, based on the timing information contained in auxiliary information #2.

[0131] In step S23, the transmitting unit 210 of the network node 200 sends an AI / ML function inquiry message to the UE 100 again at that time to inquire about the status of function #1. The transmitting unit 210 may send the AI / ML function inquiry message because the confidence level included in auxiliary information #2 is "low". Alternatively, in this step, the transmitting unit 210 may send an AI / ML setting message including an activation instruction to the UE 100 instead of sending the AI / ML function inquiry message because the confidence level included in auxiliary information #2 is "high".

[0132] In step S24, the transmission unit 120 of UE 100 sends a function report message in response to receiving the AI / ML function inquiry message (step S23). In the example in Figure 11, UE 100 determines at this stage that the AI / ML model for function #1 is applicable. Therefore, UE 100 sends a function report message that includes information indicating that function #1 is applicable ("function #1 = OK").

[0133] In step S25, the transmitting unit 210 of the network node 200 sends an AI / ML configuration message to the UE 100 in response to receiving a function report message (step S24) containing information indicating that function #1 is applicable. The AI / ML configuration message includes an activation instruction for function #1.

[0134] [Second Embodiment] Next, a second embodiment will be described. The second embodiment will be described focusing on the differences from the first embodiment.

[0135] In the first embodiment, an example was described in which, when UE100 detects a function that cannot be applied (non-applicable), it transmits a timing when that function becomes applicable (applicable). In the second embodiment, conversely, an example is described in which, when UE100 detects an applicable (applicable) function, it transmits a timing when that function becomes non-applicable.

[0136] Specifically, firstly, the user device (e.g., UE100) detects the applicable functions of the AI / ML model. Secondly, the user device transmits auxiliary information, including information about non-applicable timings for which the AI / ML model functions cannot be applied, to the first network device (e.g., network node 200).

[0137] Conversely to the first embodiment, the network device can identify timings in which the function cannot be applied using auxiliary information. Therefore, the network device can instruct the UE 100 to deactivate the function at the appropriate timing, thereby enabling the LCM operation (in this case, deactivation) for the function to be performed at the appropriate time.

[0138] (Example of operation according to the second embodiment) Next, an example of operation according to the second embodiment will be described.

[0139] Figure 12 is a diagram illustrating an example of operation according to the second embodiment. In Figure 12, a network node 200 is used as an example of a network device.

[0140] Steps S30 to S34 are the same as steps S10 to S14 of the first embodiment (Figure 11), respectively. In step S33, the control unit 130 of UE100 detects the function (function #1) of an applicable AI / ML model.

[0141] In step S35, the transmitting unit 210 of the network node 200 receives a UE capability information message (step S34) indicating that function #1 is applicable, and sends an AI / ML configuration message to the UE 100 that includes an activation instruction for function #1.

[0142] In step S36, the control unit 130 of UE100, upon receiving the AI / ML setting message, starts inference using the AI / ML model having function #1.

[0143] In step S37, the control unit 130 of the UE 100 detects that the AI / ML model currently being inferred is applicable but will become non-applicable after a predetermined time has elapsed. This detection may be performed using any of the following methods, similar to the first embodiment (step S15).

[0144] - Insufficient memory; - Insufficient CPU resources; - Thermal conditions met; - Insufficient battery level; - Does not meet operating conditions; Information such as conditions or thresholds necessary for such detection may be included in the AI / ML setting information (step S35).

[0145] In step S38, the transmission unit 120 of UE 100 sends an AI / ML setting completion message to the network node 200. The control unit 130 of UE 100 may, upon detecting that there is a function #1 that is currently applicable but will not be applicable after a predetermined time has elapsed, set information indicating that the function #1 is currently applicable ("function #1 = OK") and auxiliary information #1 in the AI / ML setting completion message. The AI / ML setting completion message will include information indicating that function ID #1 is currently applicable ("function #1 = OK") and auxiliary information (auxiliary information #1).

[0146] Firstly, auxiliary information #1 includes information about the timing at which the functionality of the AI / ML model becomes non-applicable. This timing may be expressed, for example, as follows:

[0147] - Time (e.g., it cannot be applied from 15:00); - Elapsed time (e.g., it cannot be applied from 1 hour later); - Infinity (the timing at which it cannot be applied is infinitely far in the future) or Unknown (the timing at which it cannot be applied is unknown); Secondly, auxiliary information #1 may include reason information (cause) indicating the reason for the transition from an applicable state to an inapplicable state. Specifically, this may be expressed by any of the following:

[0148] - Insufficient remaining memory (e.g., 10% remaining); - Insufficient CPU resources (e.g., 5% remaining); - Thermal conditions not met (e.g., cooling required); - Usage conditions not met (e.g., geographical conditions not met, wireless conditions not met); Thirdly, the auxiliary information may include information regarding the reliability of the information contained in the auxiliary information. Similar to the first embodiment, the reliability information may be represented by, for example, "high," "medium," and "low." "High" represents the highest reliability, and "low" represents the lowest reliability, respectively. Similar to the first embodiment, the control unit 130 may determine the reliability information depending on the reason why it cannot be applied.

[0149] Thus, while the AI / ML configuration completion message includes information indicating that function #1 is applicable, it also includes supplementary information about the timing when it is not applicable (non-applicable). Therefore, the AI / ML configuration completion message effectively serves to notify the timing when function #1 cannot be applied.

[0150] The receiving unit 220 of the network node 200 receives the AI / ML setting completion message.

[0151] In step S39, the control unit 230 of the network node 200 decides to deactivate function #1 based on the auxiliary information.

[0152] In step S40, the transmitting unit 210 of the network node 200 sends an AI / ML configuration message to the UE 100 that includes a deactivation instruction for function #1. The transmitting unit 210 may also send the AI / ML configuration message because the reliability of the auxiliary information was "high". The transmitting unit 210 may also send the AI / ML configuration message at the timing included in auxiliary information #1. In this case, the UE 100 will receive the deactivation instruction at that timing.

[0153] In step S41, the control unit 130 of UE100 stops the inference of the AI / ML model of function #1 in response to receiving the AI / ML setting message (step S40).

[0154] In step S42, the transmission unit 210 of the network node 200 sends a UE capability inquiry message to the UE 100. The network node 200 may also send the UE capability inquiry message to check the status of function #1 of the AI / ML model that is not activated.

[0155] In step S43, the control unit 130 of UE 100 checks the status of the AI / ML model of function #1 in response to receiving the UE capability inquiry message. In the example in Figure 12, at this step, it is determined that function #1 is applicable. Therefore, the transmission unit 120 of UE 100 sends a UE capability information message to the network node 200 that includes information indicating that function #1 is applicable ("function #1 = OK").

[0156] In step S44, the transmission unit 210 of the network node 200 confirms that function #1 is applicable and sends an activation instruction (AI / ML setting message) for function #1 to the UE 100.

[0157] In step S45, the control unit 130 of UE100 starts inference of the AI / ML model of function #1 in accordance with the activation instruction.

[0158] In step S46, the transmitter 120 of the UE 100 sends an AI / ML setup completion message to the network node 200, which includes information indicating that the inference of the AI / ML model of function #1 is in progress ("function #1 = OK"). Upon receiving this message, the network node 200 can confirm that the AI / ML model of function #1, which was instructed to be activated in the UE 100, is performing inference appropriately.

[0159] (Other examples of operation according to the second embodiment) Next, other examples of operation according to the second embodiment will be described.

[0160] In the second embodiment, an example was described in which UE 100 transmits auxiliary information in an AI / ML setting completion message (step S38), which is a response message to the AI / ML setting message (step S35). For example, UE 100 may transmit auxiliary information spontaneously without receiving the AI / ML setting message. In another example of operation according to the second embodiment, an example in which UE 100 spontaneously transmits auxiliary information will be described.

[0161] Figure 13 is a diagram illustrating another example of operation according to the second embodiment. Figure 13 shows an example of operation after UE 100 transmits a UE capability information message (step S34) in Figure 12.

[0162] As shown in Figure 13, in step S50, the control unit 130 of the UE100 detects a function (function #1) that will no longer be applicable after a predetermined time has elapsed. The detection of this function itself may be the same as in step S37 of the second embodiment.

[0163] In step S51, the transmission unit 120 of UE 100 sends a function report message to the network node 200. The control unit 130 of UE 100 may, upon detecting that function #1 will become unapplicable after a predetermined time has elapsed, set information indicating that the function ID (function #1) of the function is currently applicable ("function #1 = OK") and auxiliary information (auxiliary information #2) in the function report message. Auxiliary information #2 includes information about the timing at which function #1 cannot be applied. Auxiliary information #2 may also include reason information and reliability information, similar to the second embodiment. The function report message, like the AI ​​setting completion message (step S38) in the second embodiment, is essentially a message to notify the timing at which function #1 cannot be applied (non-applicable). The receiving unit 220 of the network node 200 receives the function report message.

[0164] In step S52, the control unit 230 of the network node 200 decides to deactivate function #1 based on auxiliary information #2.

[0165] In step S53, the transmission unit 210 of the network node 200 may send an AI / ML configuration message including a proactive operation instruction to the UE 100. Proactive operation refers to, for example, an operation that predicts future operations and takes countermeasures in advance. Here, the network node 200 sends information about the timing and an instruction to deactivate function #1 along with the proactive operation instruction using an AI / ML configuration message, so that when the timing arrives, the UE 100 will deactivate function #1. In the example in Figure 13, in response to receiving the AI / ML configuration message, the UE 100 will stop the AI / ML inference operation of function #1 when the timing arrives (step S54).

[0166] In addition to proactive actions, there are also reactive actions. Reactive actions are actions that take countermeasures when a certain situation occurs, for example. Here, the system waits until the timing indicated by the auxiliary information, and at that timing (step S55), the network node 200 sends an AI / ML model configuration message including an instruction to deactivate function #1 (step S56). Then, the UE 100, upon receiving the activation instruction, performs the deactivation of function #1 (in this case, stopping the inference operation) (step S57).

[0167] [Third Embodiment] Next, a third embodiment will be described.

[0168] For example, a handover may occur in UE100 while inference is being performed on an AI / ML model having a certain function. In the first embodiment, an example was described in which, when UE100 detects a function of an AI / ML model that cannot be applied (non-applicable), it sends the timing at which that function becomes applicable (applicable) to network node 200. In this case, if the destination of the transmission of that timing is not network node 200-2, the network node 200-2 may not be able to instruct UE100 to perform LCM operation for that function at the appropriate timing.

[0169] Similarly, even if UE100, which is in an RRC idle or RRC inactive state, performs a cell reselection procedure and selects a cell to be camped, if that cell does not know when the function becomes applicable, it cannot properly instruct UE100 to perform LCM operation for that function.

[0170] Therefore, in the third embodiment as well, the objective is to instruct the network node 200 to perform LCM operation at an appropriate timing. However, in the third embodiment, the target is the network node 200-2 to which the handover will occur, or the cell to which the cell reselection procedure will occur (and the network node 200-2 that houses that cell).

[0171] Therefore, in the third embodiment, firstly, the first network device (e.g., network node 200-1) receives auxiliary information from the user device (e.g., UE100) that includes information regarding the timing of applicability. Secondly, the first network device sends a handover request message containing the auxiliary information, or an Xn message containing the auxiliary information, to the second network device (e.g., network node 200-2), which is the handover destination or the cell reselection destination by the cell reselection procedure.

[0172] This allows the network node 200-2 to confirm when the function becomes applicable, or the cell to be re-selected (and the network node 200-2 that houses it), to instruct the UE 100 to perform LCM operation for the function at the appropriate time.

[0173] (Example of operation according to the third embodiment) Next, an example of operation according to the third embodiment will be described.

[0174] Figure 14 is a diagram illustrating an example of operation according to the third embodiment. Figure 14 shows an example of operation when a handover is performed in UE100. In Figure 14, network node 200-1 is an example of a first network device. Network node 200-1 is the network node from which the handover originates for UE100. Network node 200-2 is an example of a second network device. Network node 200-2 is the network node to which the handover destination occurs for UE100. In the third embodiment, there is an example in which an applicable timing (first embodiment) is transmitted from network node 200-1 to network node 200-2. In the third embodiment, there is also an example in which an inapplicable timing (second embodiment) is transmitted from network node 200-1 to network node 200-2. The former example of operation will be explained first.

[0175] As shown in Figure 14, in step S60, the transmission unit 120 of UE 100 sends an AI setting completion message to the network node 200, which includes information indicating that function #1 cannot be applied ("function #1 = NG") and auxiliary information. Step S60 is the same as step S17 in the first embodiment.

[0176] In step S61, the transmitter 120 of UE100 sends a Measurement Report message to the network node 200 in response to triggering an event indicated by the Measurement Configuration (ReportConfigNR). The Measurement Report message may serve as a trigger message for starting the handover procedure. The receiver 220 of network node 200-1 receives the Measurement Report message.

[0177] In step S62, the NW communication unit 240 of network node 200-1, upon receiving the measurement report message (step S61), sends a handover request message to network node 200-2, which houses the adjacent cell. The handover request message is an example of an Xn message. In the following steps as well, messages are sent and received between network nodes 200-1 and 200-2, and in all cases, Xn messages are used. The explanation of these will be omitted below.

[0178] Here, the control unit 230 of the network node 200-1 may set the UE-ID, information indicating that function #1 cannot be applied ("function #1 = NG"), and auxiliary information in the handover request message. The UE-ID is the identification information of the UE 100 that sent the measurement report message (step S61). The information indicating that function #1 cannot be applied ("function #1 = NG") is information included in the AI / ML setting completion message (step S60). The auxiliary information is also information included in the AI / ML setting completion message (step S60). As a result, a handover request message including the UE-ID, "function #1 = NG", and auxiliary information may be sent. In this case, the auxiliary information includes information about the timing of the transition from a state where it cannot be applied to a state where it can be applied. The auxiliary information may include reason information and reliability information, as in the first embodiment.

[0179] In step S63, the control unit 230 of network node 200-2 decides to accept the handover in response to receiving the handover request message (step S62). Then, the NW communication unit 240 of network node 200-2 sends a Handover Request Acknowledge message to network node 200-1.

[0180] In step S64, the transmitting unit 210 of network node 200-1, upon receiving a handover request permission message (step S63), sends a handover message (RRC Reconfiguration message) to UE 100. The receiving unit 110 of UE 100 receives the handover message. The transmitting unit 120 of UE 100 sends a handover completion message (RRC Reconfiguration Complete) to network node 200-2 and starts connecting to network node 200-2 (step S65).

[0181] In step S66, the control unit 230 of the network node 200-2 waits until the timing is reached, based on the timing information included in the auxiliary information.

[0182] Then, in step S67, the transmission unit 210 of the network node 200-2 sends an AI / ML setting message to the UE100, which includes an activation instruction for function #1.

[0183] In step S68, the control unit 130 of UE100 starts inference of the AI / ML model of function #1 in response to receiving the AI / ML setting message.

[0184] Next, we will describe an example where a non-applicable timing is sent from network node 200-1 to network node 200-2.

[0185] An example of the operation in this case is shown in steps S70 to S78, but is basically almost identical to steps S60 to S68. However, the auxiliary information (steps S70 and S72) includes information about the timing of the transition from an applicable state to an inapplicable state. The auxiliary information may also include reason information and reliability information, as in the second embodiment. Another difference is that the AI / ML setting message (step S70) and the handover request message (step S72) include information indicating that function #1 is applicable ("function #1 = OK"). The two messages are essentially messages to notify the timing at which function #1 cannot be applied. Another difference is that in step S77, network node 200-2 sends an AI / ML setting message that includes a non-activation instruction. In this case, UE 100 stops the inference of the AI / ML model for function #1 (step S78).

[0186] (Another example of operation according to the third embodiment) In the third embodiment, a handover was used as an example, but in the case of a cell reselection procedure, for example, it would be as follows.

[0187] In other words, upon receiving an AI / ML setting completion message (step S60) from UE100, network node 200-1 sends an Xn message to an adjacent network node (for example, network node 200-2) containing the UE-ID, information indicating that function #1 cannot be applied ("function #1 = NG"), and auxiliary information. As a result, if the adjacent network node that receives the Xn message has performed a cell reselection procedure in UE100 and has become the network node (cell) to be reselected, it can send an activation instruction for function #1 (AI / ML setting message) at the timing indicated in the auxiliary information.

[0188] Furthermore, upon receiving an AI / ML configuration completion message (step S70) from UE100, network node 200-1 sends an Xn message to its neighboring network node containing the UE-ID, information indicating that function #1 is applicable ("function #1 = OK"), and auxiliary information. As a result, when a neighboring network node receives the Xn message and the cell re-selection procedure is performed at UE100, and it becomes the network node (cell) to be re-selected, it can send a deactivation instruction (AI / ML configuration message) for function #1 to UE100 at the timing specified in the auxiliary information.

[0189] (Another example of operation according to the third embodiment 2) In the third embodiment, network node 200-1 and network node 200-2 were used as examples for the description, but for example, network node 200-1 may be replaced with CU#1, and network node 200-2 may be replaced with CU#2.

[0190] [Other Embodiments] In the first and second embodiments, a network node 200 was used as an example of a network device. For example, the network device may be a CN device 300. If the CN device is an AMF, the network node 200 may be replaced with the AMF in Figures 11 to 13. In this case, NAS messages may be used for messages between the AMF and the UE 100.

[0191] Alternatively, the network device may be an LMF. In this case, the network node 200 in Figures 11 to 13 may be replaced with an LMF. LPP messages using LPP (LTE Positioning Protocol) may be used between the LMF and the UE 100.

[0192] Alternatively, the network device may be an OTT server. In this case, the network node 200 in Figures 11 to 13 may be replaced with an OTT server. Messages between the OTT server and the UE 100 may use IP messages via the IP (Internet Protocol) protocol.

[0193] Furthermore, in the second and third embodiments, the deactivation instructions for function #1 (steps S40, S53, S56, S67, and S77) were described. For example, instead of the deactivation instructions, a fallback instruction or a switching instruction may be used.

[0194] Furthermore, although the first to third embodiments described function-based examples, the model-based approach is also possible. In this case, the "applicable function" in the first to third embodiments is replaced with "applicable model," and the "non-applicable function" is replaced with "non-applicable model." Instead of processing being performed on a function ID basis in the UE100 and network node 200, processing is performed on a model ID basis.

[0195] Furthermore, in the first to third embodiments, examples in which usage conditions are used have been described (steps S10 and S11, steps S30 and S31). Instead of, or together with, usage conditions, an Associated ID may be used. The Associated ID is used as identification information to identify additional conditions. Additional conditions represent, for example, conditions added to the usage conditions. Additional conditions may include usage conditions. The Associated ID may be used together with a Function ID between UE100 and network node 200 (or network nodes 200-1 and 200-2).

[0196] The above-described operation flows can be performed not only independently, but also in combination of two or more operation flows. For example, some steps of one operation flow may be added to another operation flow, or some steps of one operation flow may be replaced with some steps of another operation flow. It is not necessary to execute all steps in each flow; only some steps may be executed. Furthermore, the order of steps in each flow may be changed as appropriate.

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] This application claims priority to U.S. Provisional Application No. 63 / 717142 (filed November 6, 2024), the entirety of which is incorporated into the specification of this application.

[0204] (Note) The above embodiments can be summarized as shown in the note, but the note does not limit the embodiments.

[0205] (Note 1) A communication method in a mobile communication system, comprising the steps of: a user device detecting a function of an AI / ML model that is not applicable; and the user device transmitting auxiliary information to a first network device, including information regarding the timing at which the function of the AI / ML model becomes applicable.

[0206] (Note 2) The communication method described in Note 1, wherein the auxiliary information includes reason information indicating why the function of the AI / ML model cannot be applied, information regarding the timing, and information regarding the reliability of the reason information.

[0207] (Note 3) The communication method according to Note 1 or Note 2, further comprising the step of the user device receiving an activation instruction from the first network device at the timing that instructs the activation of the functions of the AI / ML model.

[0208] (Note 4) The communication method according to any one of Notes 1 to 3, further comprising the steps of: the first network device receiving the auxiliary information from the user device; and the first network device transmitting a handover request message containing the auxiliary information, or an Xn message containing the auxiliary information, to a second network device which is a handover destination or a cell reselection destination by a cell reselection procedure.

[0209] (Note 5) The communication method according to any one of Notes 1 to 4, further comprising the step of the user device receiving an activation instruction from the second network device at the timing that instructs the activation of the functions of the AI / ML model.

[0210] (Note 6) A communication method in a mobile communication system, comprising the steps of: a user device detecting an applicable AI / ML model function; and the user device transmitting auxiliary information to a first network device, including information regarding a non-applicable timing for which the AI / ML model function cannot be applied.

[0211] (Note 7) The communication method according to any one of Notes 1 to 6, wherein the auxiliary information includes reason information indicating the reason for the transition from a state in which the function of the AI / ML model can be applied to a state in which it cannot be applied, information regarding the timing, and information regarding the reliability of the reason information.

[0212] (Note 8) The communication method according to any one of Notes 1 to 7, further comprising the step of the user device receiving a deactivation instruction from the first network device at the timing that instructs the deactivation of the functions of the AI / ML model.

[0213] (Note 9) The communication method according to any one of Notes 1 to 8, further comprising the steps of: the first network device receiving the auxiliary information from the user device; and the first network device transmitting a handover request message containing the auxiliary information, or an Xn message containing the auxiliary information, to a second network device which is a handover destination or a cell reselection destination by a cell reselection procedure.

[0214] (Note 10) The communication method according to any one of Notes 1 to 9, further comprising the step of the user device receiving a deactivation instruction from the second network device at the timing that instructs the deactivation of the functions of the AI / ML model.

[0215] 1: Mobile communication system 20: RAN 30: CN 100: UE 101: CSI generation unit 102: CSI prediction model 103, 104, 105: AI / ML model 110: Receiving unit 120: Transmitting unit 130: Control unit 200: Network node 201: CSI reconstruction unit 210: Transmitting unit 220: Receiving unit 230: Control unit 240: NW communication unit 300: CN device 1010: Inference unit for CSI generation 1011: Quantization unit 2010: Inverse quantization unit 2011: Inference unit for CSI reconstruction A1: Data acquisition unit A2: Model learning unit A3: Model inference unit A5: Management unit A6: Model recording unit

Claims

1. A communication method in a mobile communication system, comprising: a user device detecting a function of an AI / ML (Artificial Intelligence / Machine Learning) model that is not applicable; and the user device transmitting auxiliary information to a first network device, including information regarding the timing at which the function of the AI / ML model becomes applicable.

2. The communication method according to claim 1, wherein the auxiliary information includes reason information indicating why the function of the AI / ML model cannot be applied, information regarding the timing, and information regarding the reliability of the reason information.

3. The communication method according to claim 1, further comprising: the user device receiving an activation instruction from the first network device at the timing that instructs the activation of the functions of the AI / ML model.

4. The communication method according to claim 1, further comprising: the first network device receiving the auxiliary information from the user device; and the first network device transmitting a handover request message containing the auxiliary information, or an Xn message containing the auxiliary information, to a second network device which is a handover destination or a cell reselection destination by a cell reselection procedure.

5. The communication method according to claim 4, further comprising the user device receiving an activation instruction from the second network device at the timing that instructs the activation of the functions of the AI / ML model.

6. A communication method in a mobile communication system, comprising: a user device detecting the functions of an applicable AI / ML (Artificial Intelligence / Machine Learning) model; and the user device transmitting auxiliary information to a first network device, including information regarding non-applicable timings in which the functions of the AI / ML model cannot be applied.

7. The communication method according to claim 6, wherein the auxiliary information includes reason information indicating the reason for the transition from a state in which the function of the AI / ML model can be applied to a state in which it cannot be applied, information regarding the timing, and information regarding the reliability of the reason information.

8. The communication method according to claim 6, further comprising the user device receiving a deactivation instruction from the first network device at the timing that instructs the deactivation of the functions of the AI / ML model.

9. The communication method according to claim 6, further comprising: the first network device receiving the auxiliary information from the user device; and the first network device transmitting a handover request message containing the auxiliary information, or an Xn message containing the auxiliary information, to a second network device which is a handover destination or a cell reselection destination by a cell reselection procedure.

10. The communication method according to claim 9, further comprising the user device receiving a deactivation instruction from the second network device at the timing that instructs the deactivation of the functions of the AI / ML model.

Images