Communication control method

Abstract

A communication control method according to one aspect of the present invention is a communication control method for a mobile communication system. The communication control method includes a step in which a user device transmits, to a network device: information relating to dynamic conditions, the information indicating conditions that change after a fixed time elapses, among additional conditions to be applied to functionalities of an artificial intelligence (AI) / machine learning (ML) model; and compatible functionality information indicating functionalities of the AI / ML model compatible with the user device.

Description

Communication Control Method

[0001] The present disclosure relates to a communication control method.

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

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

[0004] A communication control method according to a first aspect is a communication control method in a mobile communication system, the communication control method including a step of transmitting, by a user device, information on dynamic conditions indicating conditions that change after a certain period of time among additional conditions applied to functions of an AI / ML model, and supported function information indicating functions of the AI / ML model that can be supported by the user device, to a network device.

[0005] A communication control method according to a second aspect is a communication control method in a mobile communication system. The communication control method includes a step of receiving, from a user equipment, supported function information indicating AI / ML model functions that the user equipment can support and supportable conditions indicating conditions under which the AI / ML model functions are supported. The communication control method also includes a step of the first network node determining whether the supportable conditions are applicable to a second network node adjacent to the first network node. The communication control method further includes a step of the first network node transmitting the supported function information to the second network node in response to determining that the supportable conditions are applicable to the second network node, and not transmitting the supported function information to the second network node in response to determining that the supportable conditions are not applicable to the second network node.

[0006] FIG. 1 is a diagram illustrating an example of the configuration of a mobile communication system according to the first embodiment. FIG. 2 is a diagram illustrating an example of the configuration of a UE (user equipment) according to the first embodiment. FIG. 3 is a diagram illustrating an example of the configuration of a network node (base station) according to the first embodiment. FIG. 4 is a diagram illustrating an example of the configuration of a protocol stack according to the first embodiment. FIG. 5 is a diagram illustrating an example of the configuration of a protocol stack according to the first embodiment. FIG. 6 is a diagram illustrating an example of the configuration of functional blocks of AI / ML technology according to the first embodiment. FIG. 7(A) is a diagram illustrating an example of the configuration of functional blocks of a mobile communication system according to the first embodiment, and FIG. 7(B) is a diagram illustrating an example of the configuration of functional blocks of a UE according to the first embodiment. FIG. 8 is a diagram illustrating an example of the configuration of functional blocks of a mobile communication system according to the first embodiment. FIGS. 9(A) and 9(B) are diagrams illustrating an example of the configuration of functional blocks of a mobile communication system according to the first embodiment. FIGS. 10(A) and 10(B) are diagrams illustrating an example of the configuration of functional blocks of a mobile communication system according to the first embodiment. FIG. 11 is a diagram illustrating an example of function types according to the first embodiment. FIG. 12 is a diagram illustrating an example of additional conditions according to the first embodiment. FIG. 13 is a diagram showing an example of additional conditions according to the first embodiment. FIG. 14(A) is a diagram showing an example of supported function information according to the first embodiment, FIG. 14(B) is a diagram showing an example of a function ID including flag information according to the first embodiment, and FIG. 14(C) is a diagram showing an example of dynamic / static identification information according to the first embodiment. FIG. 15(A) is a diagram showing an example of a specification ID according to the first embodiment, and FIG. 15(B) is a diagram showing an example of a local value according to the first embodiment. FIG. 16 is a diagram showing a second operation example according to the first embodiment. FIG. 17 is a diagram showing a second operation example according to the first embodiment. FIG. 18 is a diagram showing another operation example 1 according to the first embodiment. FIG. 19 is a diagram showing another operation example 2 according to the first embodiment. FIG. 20 is a diagram showing an operation example according to the second embodiment.

[0007] The present disclosure aims to enable a user device to properly execute the functions of an AI / ML model that has been instructed to be activated.

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

[0009] [First Embodiment] The configuration of a mobile communication system according to the first embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of a 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. Although the following description will be given using 5GS as an example, the mobile communication system may also be at least partially applied to an LTE (Long Term Evolution) system. The mobile communication system may also be at least partially applied to a sixth generation (6G) system or later system.

[0010] The mobile communication system 1 includes a network (NW) 10 and a user equipment (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, and may be, for example, 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 provided in a sensor, a vehicle or a device provided in a vehicle (Vehicle UE), or an aircraft or a device provided in an aircraft (Aerial UE).

[0011] The NW 10 includes a radio access network (RAN) 20 and a core network (CN) 30. When the mobile communication system is a 5th generation system (5GS), the RAN 20 is referred to as a Next Generation Radio Access Network (NG-RAN), and the CN 30 is referred to as a 5G Core Network (5GC).

[0012] The RAN 20 includes a plurality of network nodes 200 (network nodes 200a to 200c in the example of FIG. 1). The network nodes 200 are connected to each other via inter-network node interfaces. The network nodes 200 may be referred to as base stations in the RAN 20. When the network node 200 is a base station, the network node 200 may be configured (i.e., functionally divided) with a CU (Central Unit) and a DU (Distribution Unit), and the two units may be connected by a fronthaul interface. When the mobile communication system 1 is 5GS, the network node 200 is referred to as a gNB, the inter-network node interface is referred to as an Xn interface, and the fronthaul interface is referred to as an F1 interface.

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

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

[0015] The CN 30 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 UE 100. The C-plane device communicates with the UE 100 using NAS (Non-Access Stratum) signaling. The U-plane device controls data forwarding. When the mobile communication system is 5GS, the C-plane device is called an AMF (Access and Mobility Management Function), the U-plane device is called a UPF (User Plane Function), and the interface between the network node 200 and the CN device 300 is called an NG interface.

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

[0017] 2 is a diagram showing an example of the configuration of a UE 100 (user equipment) according to the first embodiment. The UE 100 includes a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 configure a communication unit 140 that performs wireless communication with a network node 200. The UE 100 is an example of a communication device.

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

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

[0020] The control unit 130 performs various controls and processes in the UE 100. Such processes include processes of each layer described below. 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 the processes by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation / demodulation, encoding / decoding, etc. of baseband signals. The CPU executes programs stored in the memory to perform various processes. Note that the processes or operations performed in the UE 100 may be performed in the control unit 130.

[0021] 3 is a diagram showing an example of the configuration of the 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 a 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 transmissions under the control of the control unit 230. The transmitting unit 210 includes an antenna and a transmitter. The transmitter converts a baseband signal (transmission signal) output by the control unit 230 into a radio 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 a radio signal received by the antenna into a baseband signal (received signal) and outputs the baseband signal to the control unit 230.

[0024] The control unit 230 performs various controls and processes in the network node 200. Such processes include processes of each layer described below. 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 in the processes by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation / demodulation, encoding / decoding, etc. of baseband signals. The CPU executes programs stored in the memory to perform various processes. Note that the processes or operations performed in the network node 200 may be performed by the control unit 230.

[0025] The NW communication unit 240 is connected to adjacent network nodes via an Xn interface, which is an interface between network nodes. The NW communication unit 240 is connected to the CN device 300 via an NG interface, which is an interface between a network node and a core network. The network node 200 may be configured (i.e., functionally divided) with a central unit (CU) and a distributed unit (DU), and both units may be connected via an F1 interface, which is a fronthaul interface.

[0026] FIG. 4 is a diagram showing an example of the configuration of a protocol stack of a radio interface of a user plane that handles data.

[0027] The user plane air interface protocol includes 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 the UE 100 and the PHY layer of the network node 200 via a physical channel. The PHY layer of the UE 100 receives downlink control information (DCI) transmitted on a physical downlink control channel (PDCCH) from the network node 200. Specifically, the UE 100 performs blind decoding of the PDCCH using a radio network temporary identifier (RNTI) and acquires successfully decoded DCI as DCI addressed to the UE. The DCI transmitted from the network node 200 has a CRC (Cyclic Redundancy Code) parity bit scrambled by the RNTI added.

[0029] In NR, the UE 100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). The network node 200 configures the UE 100 with a bandwidth portion (BWP) consisting of contiguous PRBs (Physical Resource Blocks). The UE 100 transmits and receives data and control signals in the active BWP. For example, up to four BWPs may be configurable for the UE 100. Each BWP may have a different subcarrier spacing. The BWPs may overlap in frequency. When multiple BWPs are configured for the UE 100, the network node 200 can specify which BWP to apply by controlling the downlink. This allows the network node 200 to dynamically adjust the UE bandwidth according to the amount of data traffic of the UE 100, etc., 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 the serving cell. A CORESET is a radio resource for control information to be received by the UE 100. Up to 12 or more CORESETs may be configured for the UE 100 on the serving cell. Each CORESET may have an index of 0 to 11 or more. A CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive Orthogonal Frequency Division Multiplex (OFDM) symbols in the time domain.

[0031] The MAC layer performs data priority control, retransmission processing using Hybrid Automatic Repeat reQuest (HARQ), random access procedures, etc. Data and control information are transmitted between the MAC layer of the UE 100 and the MAC layer of the network node 200 via a transport channel. The MAC layer of the network node 200 includes a scheduler. The scheduler determines the uplink and downlink transport format (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to the UE 100.

[0032] The RLC layer transmits data to the RLC layer on the receiving side using the functions of the MAC layer and the PHY layer. Data and control information are transmitted between the RLC layer of the UE 100 and the RLC layer of the network node 200 via logical channels.

[0033] The PDCP layer performs header compression / decompression, encryption / decryption, and the like.

[0034] The SDAP layer maps IP flows, which are units for Quality of Service (QoS) control by the core network, to radio bearers, which are units for QoS control by the access stratum (AS). Note that if the RAN is connected to the EPC, SDAP may not be required.

[0035] FIG. 5 is a diagram showing the configuration of a protocol stack of a radio interface of a control plane that handles signaling (control signals).

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

[0037] RRC signaling for various settings is transmitted between the RRC layer of the UE 100 and the RRC layer of the network node 200. The RRC layer controls logical channels, transport channels, and physical channels in accordance with the establishment, re-establishment, and release of radio bearers. When there is a connection (RRC connection) between the RRC of the UE 100 and the RRC of the network node 200, the UE 100 is in an RRC connected state. When there is no connection (RRC connection) between the RRC of the UE 100 and the RRC of the network node 200, the UE 100 is in an RRC idle state. When the connection between the RRC of the UE 100 and the RRC of the network node 200 is suspended, the UE 100 is in an RRC inactive state.

[0038] The NAS, which is located above the RRC layer, performs session management, mobility management, etc. NAS signaling is transmitted between the NAS of the UE 100 and the NAS of the AMF. Note that the UE 100 has an application layer in addition to the radio interface protocol. Also, the layer below the NAS is called an Access Stratum (AS).

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

[0040] The functional block configuration example 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 storage unit (Model Storage) A6.

[0041] The functional block configuration example shown in FIG. 6 represents a functional framework of a general AI / ML technology. Therefore, depending on a hypothetical use case, some of the functional block configuration example (e.g., the model recording unit A6, etc.) may not be included in the functional block configuration example. The functional block configuration example shown in FIG. 6 may also be distributed between the UE 100 and the network device. Alternatively, some functions of the functional block configuration example (e.g., the model learning unit A2 or the model inference unit A3, etc.) may be located in both the UE 100 and the network device.

[0042] The data collection unit A1 provides input data to the model learning unit A2, the model inference unit A3, and the management unit A5. The input data includes training data for the model learning unit A2, inference data for the model inference unit A3, and monitoring data for the management unit A5.

[0043] The training data is data required as input when the AI / ML model is learning. The inference data is data required as input when the AI / ML model is inferring. The monitoring data is data required as input when the AI / ML model is managing.

[0044] In addition, data collection may refer to the process of collecting data at a network node, a management entity, or a UE 100, for example, to train an AI / ML model, manage an AI / ML model, and perform inference on 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 learning is the process of learning an AI / ML model from input / output relationships to obtain a trained AI / ML model to be used for inference. For example, considering y = ax + b, AI / ML model learning may be the process of optimizing a (slope) and b (intercept) by providing input (x) and output (y) (i.e., providing learning data).

[0047] Generally, machine learning includes supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data as training data. Unsupervised learning is a method that does not use correct answer data as training data. For example, unsupervised learning memorizes feature points from a large amount of training data and determines the correct answer (estimates the range). Reinforcement learning is a method that assigns a score to the output result and learns how to maximize the score. Although supervised learning will be described below, either unsupervised learning or reinforcement learning may be applied as machine learning.

[0048] The model learning unit A2 outputs a trained AI / ML model (Trained Model) obtained by AI / ML model learning to the model recording unit A6. The model learning unit A2 also outputs an updated AI / ML model (Updated Model) obtained by relearning the trained AI / ML model to the model recording unit A6.

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

[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 the trained AI / ML model (or updated AI / ML model) to obtain inference output data. For example, in the equation 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. There are various model 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, the management instructions include selection of an AI / ML model, activation (deactivation) of an AI / ML model, switching of an AI / ML model, and fallback (performing inference without using an AI / ML model). The model inference unit A3 performs model inference in accordance with the management instructions.

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

[0053] In the following, an AI / ML model that is currently being trained (or updated) may be referred to as a training AI / ML model (or an updating AI / ML model). In the following, when there is no need to distinguish between a training (or updating) AI / ML model and a trained (or updated) AI / ML model, they may be simply 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. The management unit A5 can also perform operations to ensure appropriate inference operations based on monitoring data and inference output data. To this end, the management unit A5 outputs a model transfer and / or model delivery request (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 be output to the model inference unit A3. The management unit A5 also outputs management instructions to the model inference unit A3 and supervises operations on the AI / ML model. Furthermore, the management unit A5 can output performance feedback and a re-learning request to the model learning unit A2, causing the model learning unit A2 to re-learn the AI / ML model (i.e., update the learned AI / ML model).

[0055] (Use Cases) Next, use cases to which the AI / ML technology is applied will be described. For example, there are the following three use cases to which the AI / ML technology is applied.

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

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

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

[0059] (X1.1) CSI Feedback Enhancement "CSI Feedback Enhancement" represents a use case in which, for example, AI / ML techniques are applied to CSI fed back from the UE 100 to the network node 200. The CSI is information about a channel state in a downlink between the UE 100 and the network node 200. The CSI includes at least one of a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), and a Rank Indicator (RI). The network node 200 performs, for example, downlink scheduling based on the CSI feedback from the UE 100.

[0060] The use case of "Improved CSI Feedback" has 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, CSI inferred in the UE 100 using a trained AI / ML model is compressed in the UE 100. The compressed CSI is transmitted from the UE 100 to the network node 200.

[0062] 7A is a diagram illustrating an example of a functional block configuration in a mobile communication system 1 when CSI compression is used. As shown in FIG. 7A, the UE 100 includes a CSI generating unit 101, and the network node 200 includes a CSI reconstructing 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) using a trained AI / ML model for input. The input to the CSI generation inference unit 1010 may be, for example, partial (or punctured) CSI. The partial CSI may be CSI measured using a CSI reference signal (CSI-RS) (or a demodulation reference signal (DMRS)) transmitted using resources equal to or less than a certain amount. The input to the CSI generation inference unit 1010 may also be a CSI reference signal. When partial CSI is input, the output of the CSI generation inference unit 1010 becomes CSI with a larger number of CSIs than the partial CSI. Furthermore, when a CSI reference signal is input, the output of the CSI generation inference unit 1010 becomes CSI. Hereinafter, the output of the CSI generation inference unit 1010 is referred to as full CSI. The quantization unit 1011 quantizes the full CSI. Compression is performed by 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 an inference unit for CSI reconstruction 2011. The inverse quantization unit 2010 receives CSI feedback, inverse quantizes the quantized full CSI, and outputs the full CSI. The inference unit for CSI reconstruction 2011 infers the reconstructed full CSI from the output (full CSI) of the inverse quantization unit 2010 using a trained AI / ML model. The reconstructed full CSI is output from the CSI reconstruction unit 201.

[0065] The quantization unit 1011 may be merged into the CSI generation inference unit 1010, and the inverse quantization unit 2010 may also be merged into the CSI reconstruction inference unit 2011. Also, a pre-processing unit may be provided in front of the CSI generation inference unit 1010, and a post-processing unit may be provided in back of the CSI reconstruction inference unit 2011.

[0066] As shown in Figure 7 (A), the CSI compression sub-use case is based on a two-sided model in which inference is performed using a trained AI / ML model on both the UE 100 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 CSI from the history of past CSI.

[0068] 7B is a diagram illustrating a configuration example of a functional block in the UE 100 when CSI prediction is used. The CSI prediction is based on a UE-sided model in which inference is performed in the UE 100 using a trained AI / ML model.

[0069] As shown in Fig. 7(B), the UE 100 has a CSI prediction model 102. The CSI prediction model 102 has a trained AI / ML model that uses a past history of CSI as an input and infers future CSI (predicted CSI). The CSI prediction model 102 may be a CSI prediction inference unit. The UE 100 (CSI prediction model 102) transmits the predicted CSI to the network node 200 as CSI feedback.

[0070] Note that a pre-processing unit may be provided in front of the CSI prediction model 102 , and a post-processing unit may be provided in the rear of the CSI prediction model 102 .

[0071] (X1.2) Beam management The beam management use case has 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 time direction. The spatial-domain downlink beam prediction is called "BM Case 1" (BM-Case 1), and the temporal downlink beam prediction is called "BM Case 2" (BM-Case 2).

[0072] 8 is a diagram showing an example of the configuration of functional blocks 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 in the UE 100 may be applied, or a NW-side model in which inference is performed on the network side may be applied. Therefore, as shown in FIG. 8, the AI / ML model 103 that performs the inference may be present in the UE 100, or may be present in the NW 10 (or in the network node 200 or CN device 300 included in the NW 10).

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

[0074] 8 also shows a configuration example 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, the AI / ML model 103 is present in the UE 100 or the NW 10.

[0075] In BM case 2, the input to the AI / ML model 103 is the history of measurement values ​​for each beam included in beam set B. Measurement values ​​measured in the past for each beam are input to the AI / ML model 103. On the other hand, the output (inference output data) from the AI / ML model 103, as in BM case 1, is the probability that each (downstream) beam included in (predicted) beam set A will be the top beam. Beam set A and beam set B may be different, or beam set B may be a subset of beam set A. Also, in BM case 2, beam set A and beam set B may be the same.

[0076] In both BM Case 1 and BM Case 2, the UE-side model allows UE 100 to report the prediction results to NW 10. Also, in both BM Case 1 and BM Case 2, the NW-side model allows the top beam to be predicted based on measurements for each beam included in beam set B reported from UE 100.

[0077] (X1.3) "Positioning accuracy enhancement" In the use case of positioning accuracy enhancement, there are two sub-use cases: direct AI / ML positioning, which directly infers the position of UE 100 using a learned AI / ML model, and AI / ML assisted positioning, which infers intermediate position measurements. In the latter AI / ML assisted positioning, the position of UE 100 is measured or inferred in an LMF (Location Management Function) using intermediate position measurements. The intermediate position measurements can be assist information for measuring or inferring the position of UE 100 in the LMF. The LMF may have a trained AI / ML model and uses the trained AI / ML model to infer the location of the UE 100.

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

[0079] In the case of direct AI / ML positioning, the input to the AI / ML model 104 is a measurement value at each measurement point (TRP: Transmission and / or Reception Point). The measurement value may be, for example, a channel impulse response (CIR), a power delay profile (PDP), or a fingerprint. For example, both the CIR and the PDP represent the delay time for a signal at a specific frequency, but the CIR represents the instantaneous delay time, and the PDP represents the statistical delay time. Meanwhile, the output (inference output data) from the AI / ML model 104 is the location information of the UE 100. The location information may be represented by a fingerprint. The fingerprint represents, for example, measurement information for the cell of the UE 100.

[0080] (X1.3.2) Sub-Use Case: AI / ML-Assisted Positioning FIGS. 9(B) to 10(B) show examples of functional block configurations in the mobile communication system 1 when AI / ML-assisted positioning is used. In the case of AI / ML-assisted positioning, a UE-side model and a network-side model are also applied. Therefore, the AI / ML model 105 used for inference may reside in the UE 100 or the NW 10. In the case of AI / ML-assisted positioning, there are three cases: one AI / ML model 105 is used for multiple inputs ( FIG. 9(B) ); the same AI / ML model is used for each of the multiple inputs ( FIG. 10(A) ); and different AI / ML models are used for each of the multiple inputs ( FIG. 10(B) ).

[0081] In either case, the input to the AI / ML model 105 is a channel measurement at each measurement point (TRP). The channel measurement may be a CIR, PDP, or fingerprint, as in direct AI / ML positioning. Meanwhile, the output (inference output data) from the AI / ML model 105 is intermediate position measurements used for positioning. The intermediate position measurements may include LOS or NLOS identification, measurement timing and / or measurement angle, or likelihood associated with the measurement.

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

[0083] Specifically, the LCM of the AI / ML model may include at least one of the following operations.

[0084] (L1) Data collection

[0085] (L2) Model training

[0086] (L3) Identification

[0087] (L4) Model delivery / transfer

[0088] (L5) Model inference operation

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

[0090] (L7) Monitoring

[0091] (L8) Model updating

[0092] (L9) UE capability

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

[0094] Regarding LCM, 3GPP defines functionality-based LCM and model ID-based LCM.

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

[0096] On the other hand, model ID-based LCM may be an operation performed on an individual AI / ML model using a model ID. The model ID is identification information for distinguishing an AI / ML model from other AI / ML models. Specifically, model ID-based LCM may be an operation of activating, deactivating, switching, or selecting an AI / ML model using the model ID.

[0097] (Types of Functions According to the First Embodiment) Each AI / ML model has functionality as an AI / ML model. When an AI / ML model realizes a certain function by executing inference in the AI / ML model, the function may represent a function in the AI / ML model. The function of the AI / ML model may represent a feature or a feature group that is enabled by the AI / ML model. The process of identifying the function of an AI / ML model is called functional identification.

[0098] Currently, 3GPP is discussing the type of function. Using the type of function, for example, the following control is possible. That is, UE 100 notifies network 10 of the type of function of the AI / ML model. When network 10 determines, based on the type of function, that UE 100 can apply the function of the AI / ML model, it can instruct UE 100 to activate the function. On the other hand, when network 10 determines, based on the type of function, that UE 100 supports the function of the AI / ML model but does not hold an AI / ML model having the function and therefore is not available, it can also perform control such that it does not instruct UE 100 to activate the function. In this way, network 10 can instruct or not instruct activation of the function depending on the type of function, thereby enabling appropriate control of UE 100.

[0099] 11 is a diagram showing examples of function types according to the first embodiment. As shown in FIG. 11, the following are examples of function types.

[0100] Supported functionality: The supported functionality indicates, for example, the maximum functionality that can be theoretically supported. The supported functionality may indicate the functionality of the AI / ML model that the UE 100 can indicate using a signal indicating the capability of the UE 100 (capability signaling). The supported functionality may indicate that the UE 100 can support the functionality of the AI / ML model, but it is not necessarily required that the UE 100 hold an AI / ML model having the functionality.

[0101] Available functionality: The available functionality indicates, for example, a function that can be supported based on conditions of hardware and / or software. The available functionality may indicate a function of an AI / ML model that can be used in the UE 100.

[0102] Applicable functions: Applicable functions refer to, for example, functions that can actually be activated. Applicable functions may refer to at least one function of an applicable AI / ML model that is available for use. Applicable functions may also refer to functions of an AI / ML model that are applicable in the UE 100.

[0103] Configured functionality: The configured functionality indicates, for example, the functionality of the AI / ML model that the network 10 (or a network device) configures for the UE 100.

[0104] Activated functionality: Activated functionality refers to, for example, functionality of an AI / ML model that has already been activated.

[0105] As shown in FIG. 11, the supported functions have the widest range compared to the other function types, and the activated functions have the narrowest range compared to the other function types.

[0106] (Model usage conditions for the first embodiment) Whether or not a function of an AI / ML model is applicable (Applicable) is based on: - Whether or not UE100 or a network device has an AI / ML model with the function; - Whether or not the AI / ML model with the function has been properly trained; and - Whether or not the usage conditions for using the function are met.

[0107] Focusing on the third "use conditions," the use conditions may be conditions specific to the UE 100 (or network device), such as memory capacity or CPU processing speed, or conditions determined by the surrounding environment, such as use in a specific area (e.g., a cell). As such, various conditions are conceivable for the use conditions. When the use conditions are satisfied together with the other two conditions, for example, the function of the AI / ML model can be applied (applicable) for the first time in the UE 100, and the AI / ML model having the function can be used (specifically, inference, etc.).

[0108] The use conditions may be applied to the functions of the AI / ML model, or may be applied to the AI / ML model itself.

[0109] (Additional Conditions According to the First Embodiment) Meanwhile, in 3GPP, additional conditions are being discussed. What conditions the additional conditions indicate is currently under discussion in 3GPP, but they can generally be defined as follows.

[0110] That is, the additional conditions indicate conditions additional to the use conditions applied to the functions of the AI / ML model, for example. Alternatively, the additional conditions may be included in the use conditions. The additional conditions may be part of the use conditions. That is, the additional conditions applied to the functions of the AI / ML model may indicate the use conditions applied to the functions. The additional conditions may indicate, for example, any aspect that may be used for training the AI / ML model but is not part of the UE capabilities related to a feature (or a group of features) usable in the AI / ML model. The additional conditions may be applied not only to the functions of the AI / ML model but also to the AI / ML model itself. However, in the first embodiment, the additional conditions will be described as being applied to the functions of the AI / ML model.

[0111] 12 and 13 are diagrams illustrating examples of additional conditions according to the first embodiment. In particular, as illustrated in Fig. 13, the additional conditions include additional conditions on the UE 100 side and additional conditions on the network 10 side.

[0112] (Communication control method according to the first embodiment) For example, assume the following scenario: UE 100 transmits additional conditions for a function of the AI / ML model to a network device. The network device receives the additional conditions and instructs UE 100 to activate the function of the AI / ML model.

[0113] In such a scenario, for example, even if UE100 is instructed to activate a function of the AI / ML model, the activation may not be executed because the additional conditions cannot be satisfied. That is, even if there are various types of additional conditions, it is assumed that there are additional conditions. Therefore, even if the network device evaluates the additional conditions and instructs activation, it may not be able to evaluate the continuity of the additional conditions, and even if the activation is instructed, the UE100 may immediately return deactivation.

[0114] Therefore, the first embodiment aims to enable the UE 100 to appropriately execute the function of the AI / ML model for which activation has been instructed.

[0115] Therefore, in the first embodiment, the UE 100 transmits information about the dynamic condition among the additional conditions to the network device. The dynamic condition indicates, for example, a condition that changes after a certain time has elapsed among the additional conditions applied to the function of the AI / ML model.

[0116] For example, if "maximum CPU power" is an additional condition, the CPU power may exceed the maximum value over time, or may not reach the maximum value. Therefore, this additional condition can be considered a dynamic condition. On the other hand, if "a value that can always be secured in CPU power" is an additional condition, this additional condition can be satisfied over time, and therefore is not a dynamic condition. Among additional conditions, a condition that can be maintained without change even after a certain period of time is called a static condition. If "a value that can always be secured in CPU power" is an additional condition, this additional condition can be considered a static condition.

[0117] 12, if the antenna height is an additional condition imposed on the network node 200 side, the antenna height will not change even after a certain time has passed, and therefore the antenna height will be a static condition. On the other hand, if the antenna height is an additional condition imposed on the UE 100 side, it may change after a certain time has passed, and therefore it may be a dynamic condition.

[0118] That is, in the first embodiment, a user device (e.g., UE 100) transmits to a network device (e.g., network node 200 or CN device 300) information regarding dynamic conditions that indicate conditions that change after a certain period of time among additional conditions applied to the functions of the AI / ML model, and supported function information that indicates functions that can be supported by the user device.

[0119] The network device can appropriately evaluate the additional condition based on information about the dynamic condition. For example, if the additional condition is a dynamic condition, the network device can refrain from instructing the UE 100 to activate, and if the additional condition is not a dynamic condition, the network device can instruct the UE 100 to activate. The network device can appropriately determine whether or not to activate depending on whether or not the additional condition is a dynamic condition. Therefore, the network device can avoid a situation where deactivation occurs even when instructing the UE 100 to activate, and can appropriately execute the function of the AI / ML model for which activation is instructed in the UE 100.

[0120] (Supported Function Information) UE100 can transmit supported function information to a network device. The supported function information is information indicating functions that UE100 can support. Dynamic conditions are associated with the supported function information. That is, it indicates that dynamic conditions are imposed on the functions indicated in the supported function information. For example, if a sub-use case of a beam management use case called "BM Case 1" is expressed as a function, a dynamic condition such as "antenna height of 1.5 m or more" is imposed on UE100 for "BM Case 1". In this case, it indicates that an AI / ML model having the function of "BM Case 1" can be used in UE100 when "antenna height is 1.5 m or more".

[0121] FIG. 14(A) is a diagram showing an example of supported function information according to the first embodiment. As shown in FIG. 14(A), the supported function information includes information indicating whether each function of the AI / ML model is supported in the UE 100. In the example shown in FIG. 14(A), the supported function information includes a function ID, a function type, and information indicating whether the function is supported. The function ID indicates function identification information that identifies the function of the AI / ML model. The function type may represent the name of the function. FIG. 14(A) shows that "BM-Case 1" (beam case 1) with function ID = 1 is supported, and that "BM-Case 2" (beam case 2) with function ID = 2 is also supported.

[0122] As mentioned above, there are five levels of functionality. The example shown in Fig. 14(A) shows the "applicable functionality" among them. Therefore, the example shown in Fig. 14(A) shows that it is compatible with two functions, "BM-Case 1" and "BM-Case 2," i.e., it is "applicable."

[0123] In the supported function information, the "Applicable functionality" portion shown in Fig. 14(A) may indicate any one of the five levels of function shown in Fig. 11. A function indicated as "supported" in the supported function information indicates that it is compatible with any one of the five levels of function. This will be specifically explained in the following operation example.

[0124] (Example of Operation According to First Embodiment) Next, an example of operation according to the first embodiment will be described.

[0125] In the first embodiment, first, a data structure of information related to a dynamic condition will be described as a first operation example. Next, as a second operation example, an example of communication between the UE 100 and a network device using information indicating the dynamic condition will be described.

[0126] (First Operation Example) First, the data structure of information relating to dynamic conditions will be described.

[0127] First, information about dynamic conditions may be indicated by flag information. Flag information is, for example, information indicating whether or not dynamic conditions are included in supported function information. Flag information may be included in a function ID. FIG. 14(B) is a diagram showing an example of a function ID including flag information. As shown in FIG. 14(B), flag information is included in a bit string representing a function ID. In the example shown in FIG. 14(B), flag information is included in the last bit of the bit string representing a function ID, but flag information may be included in any bit of the bit string of a function ID. Note that the function ID may be included in the supported function information (FIG. 14(A)). The flag information indicates whether or not a dynamic condition is applied to each function.

[0128] Second, information about dynamic conditions may be represented by the number of dynamic conditions. The number of dynamic conditions may indicate the number of dynamic conditions applied to the function. For example, the number of dynamic conditions for one function may be represented as "5". The number of dynamic conditions may also be included in the bit string of the function ID. The number of dynamic conditions may be represented by any bit in the bit string representing the function ID.

[0129] Third, information about a dynamic condition may be indicated by identification information (hereinafter referred to as "dynamic / static identification information") indicating whether the additional condition is a dynamic condition or a static condition. FIG. 14C is a diagram showing an example of dynamic / static identification information according to the first embodiment. As shown in FIG. 14C, information indicating "dynamic" is shown as dynamic / static identification information for the additional condition "CPU power." The dynamic / static identification information may also be information indicating "static." The example shown in FIG. 14C represents an example in which dynamic / static identification information is included in meta information of corresponding function information.

[0130] The meta information indicates, for example, information other than the information included in the supported function information. As shown in Fig. 14(C), the meta information may include additional conditions and dynamic / static identification information. Furthermore, as shown in Fig. 14(C), the meta information may be linked to the supported function information.

[0131] Fourth, the information related to the dynamic condition may be dynamic condition identification information that identifies the dynamic condition. An example of dynamic condition identification information is a specification ID. FIG. 15(A) is a diagram showing an example of a specification ID according to the first embodiment. As shown in FIG. 15(A), the specification ID is an ID that identifies the dynamic condition expressed as a standardized fixed value. An additional condition corresponding to the specification ID represents the dynamic condition. The specification ID may be included in meta information. The specification ID may be included in corresponding function information. The dynamic condition identification information indicates what kind of condition the dynamic condition indicates.

[0132] The dynamic condition identification information may be indicated by a local value that can be used within a specific region. The specific region may be a specific cell. The specific region may be within a specific Tracking Area (TA). This is because the functions of an AI / ML model may be used in the specific region. FIG. 15(B) is a diagram showing an example of a local value according to the first embodiment. In FIG. 15(B), a local ID is shown instead of a local value. For example, a dynamic condition with a specification ID of 1 is represented as a local ID of 1. In this case, in a certain region, an additional condition whose dynamic condition identification information is indicated as "1" is the same as an additional condition whose specification ID is "1". The dynamic condition identification information may be represented by a mapping between a specification ID and a local value.

[0133] In this way, whether or not a dynamic condition is included is linked to the supported function information. The linking to the supported function information may be based on flag information, as described above. The linking may be based on number information. The linking may be based on dynamic / static identification information (or meta information). The linking may be based on dynamic condition identification information (or meta information). Whether or not a dynamic condition is included may be linked to the supported function information on the UE side, or whether or not a dynamic condition is included may be linked to the supported function information on the network device (e.g., network node 200) side.

[0134] (Second Operation Example) Next, a second operation example will be described.

[0135] In the second operation example, how information about dynamic conditions is transmitted and received between the UE 100 and the network device will be described.

[0136] As shown in Fig. 11, there are five levels of functions. Assuming a situation in which a message related to each function in the five levels is sent, the communication direction of the message related to each function is, for example, as follows:

[0137] Supported functions: from the UE 100 to the network 10 Available functions: from the UE 100 to the network 10 Applicable functions: from the UE 100 to the network 10 Configured functions: from the network 10 to the UE 100 Activated functions: from the UE 100 to the network 10 Taking these communication directions into consideration, a second operation example will be described.

[0138] 16 and 17 are diagrams showing a second operation example according to the first embodiment. Note that in Fig. 16 and 17, the network node 200 will be used as an example of the network device.

[0139] As shown in FIG. 16 , in step S10, the transmission unit 120 of the UE 100 transmits a message regarding supported functions to the network node 200. The message regarding supported functions may be a message for notifying the network node 200 of functions supported in the UE 100. The message regarding supported functions includes supported function information (e.g., FIG. 14(A)). The supported function information may be such that "Applicable functionality" is set to "Supported functionality" in FIG. 14(A). The supported function information may include function IDs and function types ( FIG. 14(A)) of functions that are compatible, i.e., supported, in the UE 100. The message regarding supported functions includes information regarding dynamic conditions. In the second operation example, an example will be described in which information about dynamic conditions is included in the supported function information (for example, flag information is included in the function ID). The receiving unit 220 of the network node 200 receives a message about supported functions.

[0140] The message regarding the supported capabilities may be an RRC message (e.g., a UE Capability Information message). The message may be a MAC Control Element (MAC CE). Alternatively, the message regarding the supported capabilities may be a message of a layer newly defined for AI / ML (e.g., an AI / ML capability information notification message). In the following, messages are transmitted and received between the UE 100 and the network node 200, and these messages may also be an RRC message, a MAC CE, or a message of a new layer.

[0141] In step S11, the control unit 230 of the network node 200 checks the functions of the AI / ML model supported by the UE 100 based on the function IDs included in the supported function information. Then, the control unit 230 checks whether or not an operating condition is associated with the function based on information related to dynamic conditions (e.g., flag information). The control unit 230 stores in a memory whether or not there is a dynamic condition for the function.

[0142] In step S12, the transmitting unit 210 of the network node 200 transmits a message regarding the configured functions (Configured functionality) to the UE 100. The message regarding the configured functions may be a message for notifying the UE 100 of the functions to be configured. The message regarding the configured functions includes supported function information. The supported function information included in the message may be "Configured functionality" instead of "Applicable functionality" shown in FIG. 14(A). The supported function information notifies the UE 100 of the function ID and function type (FIG. 14(A)) of the function to be configured. The function ID included in the message may be selected from the function IDs included in the message regarding the supported functions (step S10). The receiving unit 110 of the UE 100 receives the message regarding the configured functions.

[0143] In step S13, the control unit 130 of the UE 100 stores in memory the presence or absence of a dynamic condition for the set function based on the function ID and information on the dynamic condition (e.g., flag information) included in the supported function information. As in step S11, the control unit 130 may check whether an operating condition is associated with the function based on the information on the dynamic condition (e.g., flag information).

[0144] In step S14, the transmission unit 120 of the UE 100 transmits a message related to available functions (Available functionality) to the network node 200. The message related to available functions may be a message for notifying the network node 200 of functions available in the UE 100. The control unit 130 of the UE 100 may select a function ID of an available function from the function IDs (i.e., functions set by the network node 200) included in the message related to the set functions (step S12). The message related to available functions includes supported function information ( FIG. 14(A) ). In the supported function information, "Applicable functionality" may be changed to "Available functionality" in FIG. 14(A) . The supported function information may include function IDs and function types ( FIG. 14(A) ) of functions that are supported, i.e., available, in the UE 100. The supported function information included in the message regarding available functions includes information regarding dynamic conditions (e.g., flag information). The receiving unit 220 of the network node 200 receives the message regarding available functions.

[0145] In step S15, the NW communication unit 240 of the network node 200 transmits a model transfer instruction to an OTT (Over-The-Top) server. The model transfer instruction is a message specifying a model ID and instructing the transfer of the AI / ML model indicated by the model ID. The transmission unit 210 may select the model ID of the model to be transferred from among the functions available in the UE 100 (step S14), and transmit the model transfer instruction including the model ID.

[0146] Steps S10 to S15 may be referred to as a capability notification phase.

[0147] In step S16, the OTT server transfers (or transmits) the AI / ML model specified in the model transfer instruction to the UE 100. The AI / ML model may be a trained AI / ML model or an AI / ML model currently being trained. The receiving unit 110 of the UE 100 receives the transferred AI / ML model.

[0148] In step S17, the OTT server transmits the transfer model information of the AI / ML model transferred in step S16 to the network node 200. The transfer model information includes the model ID (e.g., model ID="a") of the AI / ML model transferred in step S16. The NW communication unit 240 of the network node 200 receives the transfer model information.

[0149] In step S18, the transmitting unit 120 of the UE 100 transmits a message related to applicable functions (Applicable Functions). The message related to applicable functions (Applicable Functions) may be a message for notifying the network node 200 of functions applicable in the UE 100. The transmitting unit 120 may transmit a message related to the applicable functions if the functions are applicable to the AI / ML model (step S16) transferred by model transfer. The message related to the applicable functions includes supported function information ( FIG. 14(A) ). The supported function information may include function IDs and function types ( FIG. 14(A) ) of functions that are supported, i.e., applicable, in the UE 100. The supported function information includes information related to dynamic conditions (e.g., flag information). The receiving unit 220 of the network node 200 receives the message related to the applicable functions.

[0150] In step S19, the control unit 230 of the network node 200 checks the applicable functions in the UE 100 based on the function IDs included in the supported function information, and checks whether or not the functions are associated with operating conditions. The control unit 230 stores in a memory whether or not there are dynamic conditions for the functions.

[0151] The processes from step S16 to step S19 are called a model transfer phase.

[0152] In step S20 (FIG. 17), the control unit 230 of the network node 200 decides to activate an AI / ML model having function #A. Function #A may represent the function of the AI / ML model (model ID=a) transferred in the model transfer (step S16).

[0153] In step S21, the control unit 230 of the network node 200 checks the ownership status of the AI / ML model in the UE 100. The control unit 230 checks the ownership status of the AI / ML model having the function #A determined to be activated in step S20. For example, the control unit 230 can check each AI / ML model having the function #A applicable to the UE 100 in the message regarding applicable functions received in step S18, and may thereby check the ownership status of the AI / ML model. The control unit 230 may check the ownership status based on any of the function ID included in the message regarding supported functions (step S10), the function ID included in the message regarding available functions (step S14), and the function ID included in the message regarding applicable functions (step S18). Here, the following description will be given assuming that the control unit 230 checks the ownership status of the AI / ML model having the function #A determined to be activated in step S20.

[0154] In step S22, the control unit 230 of the network node 200 checks whether or not there are dynamic conditions for the AI / ML model held by the UE 100. The control unit 230 may check based on whether or not there are dynamic conditions stored in the memory in steps S11 and S19. If there are no dynamic conditions as a result of the check, the processes of steps S23 and S24 are performed. On the other hand, if there are dynamic conditions, the processes of steps S26 to S30 are performed.

[0155] If there is no dynamic condition, in step S23, the transmitter 210 of the network node 200 instructs the UE 100 to activate the function (e.g., function #A having function ID = A) whose activation was decided in step S20. The network node 200 may determine that there is no dynamic condition for the AI / ML model function possessed by the UE 100 and that it can be used, and may instruct the activation.

[0156] In step S24, the control unit 130 of the UE 100 activates the AI / ML model having the function instructed in step S23 (for example, function #A with function ID = A) and starts inference of the AI / ML model.

[0157] In step S25, the transmission unit 120 of the UE 100 transmits a message related to the activated functions (Activated Functionalities) to the network node 200. The message related to the activated functions may be a message for notifying the network node 200 of the functions that have actually been activated in the UE 100. The transmission unit 120 of the UE 100 may transmit the message including information related to the functions that have actually been activated by starting inference in step S28. The message related to the activated functions includes supported function information ( FIG. 14(A) ). In the supported function information, in FIG. 14(A) , "Applicable functions" may be "Activated Functions". The supported function information may include a function ID (e.g., function ID=A) and a function type of a function that is supported, i.e., activated, in the UE 100. The supported function information included in the message related to the activated function includes information related to dynamic conditions (e.g., flag information). The receiving unit 220 of the network node 200 receives the message related to the activated function.

[0158] On the other hand, if there is a dynamic condition, in step S26, the control unit 230 of the network node 200 checks the content of the dynamic condition and checks whether the dynamic condition immediately affects the function to be activated. The control unit 230 may determine, with respect to the function ID and the dynamic condition included in the message regarding the applicable function (step S18), whether the dynamic condition can be immediately executed (or whether inference can be executed) in the UE 100 when applied to the AI / ML model having the function of the function ID. For example, the following determination may be made.

[0159] That is, when a dynamic condition of "minimum or maximum CPU power of 300 MFLOPS" (here, for example, either the minimum or maximum value may be selected) is applied to a function called "Beam Case 1," the following determination is made. That is, if the "minimum CPU power" in UE 100 is "300 MFLOPS," the control unit 230 determines that the function "Beam Case 1" will not be immediately affected. On the other hand, if the "maximum CPU power" in UE 100 is "300 MFLOPS," the control unit 230 determines that the function "Beam Case 1" will be immediately affected. The dynamic condition (here, "minimum or maximum CPU power of 300 MFLOPS") may be included in another message (one of steps S10, S14, and S18).

[0160] If it is determined that the application of the dynamic condition will not have an immediate effect, the processes from step S27 to step S29 are performed. On the other hand, if it is determined that the application of the dynamic condition will have an immediate effect, the process of step S30 is performed.

[0161] If there is no immediate impact, in step S27, the transmitter 210 of the network node 200 instructs activation of the function determined to be activated in step S20 (for example, function #A having function ID = A). Note that, when the network node 200 wants to acquire detailed dynamic conditions in the determination of step S26, it may make a request to the UE 100 to acquire the dynamic conditions, and acquire the detailed dynamic conditions from the UE 100.

[0162] In step S28, the control unit 230 of the UE 100 starts inference of the AI / ML model having the function that has been instructed to be activated.

[0163] In step S29, the transmitter 120 of the UE 100 transmits a message regarding the activated function. The message includes supported function information, and the supported function information includes the function ID of the function of the AI / ML model that started inference in step S28.

[0164] If the effect is immediate, the control unit 230 of the network node 200 does not activate the function determined to be activated in step S20. Specifically, the transmission unit 210 of the network node 200 does not instruct the UE 100 to activate the function.

[0165] (Another Operation Example 1 According to First Embodiment) In the second operation example, an example (steps S20 to S30 in FIG. 17 ) has been described in which the decision to activate a function is made by the network node 200. For example, the decision to activate a function may be made by the UE 100.

[0166] Fig. 18 is a diagram showing another operation example 1 according to the first embodiment. It is assumed that the capability notification phase (steps S10 to S15) and model transfer phase (steps S16 to S19) shown in Fig. 16 have been performed before the operation shown in Fig. 18 is started.

[0167] 18, in step S40, control unit 130 of UE 100 determines to activate an AI / ML model having function #B. The function ID of function #B will be described below as "B".

[0168] In step S41, the control unit 130 of the UE 100 checks the setting state (Configure state) and checks whether function #B is supported in the network node 200. For example, the control unit 130 may check whether function #B is supported in the network node 200 by checking whether an AI / ML model having the function #B is included in the functions set in step S12.

[0169] In step S42, the control unit 130 of the UE 100 checks whether or not there is a dynamic condition for function #B determined in step S40. For example, in step S13, the control unit 130 checks whether or not there is a dynamic condition for function #B based on the information stored in the memory (step S13). If there is no dynamic condition for function #B, the control unit 130 performs the processes from step S43 to step S445. On the other hand, if there is a dynamic condition for function #B, the control unit 130 performs the processes from step S45 to step S48.

[0170] If there is no dynamic condition, in step S43, the control unit 130 of the UE 100 activates the AI / ML model having the function #B (step S40) whose activation has been determined. If there is no dynamic condition for the function #B, the control unit 130 may determine that the function #B is inferable and decide to activate it.

[0171] In step S44, the control unit 130 of the UE 100 starts inference of the AI / ML model having the activated feature #B (feature ID="B"). In step S445, the transmission unit 120 of the UE 100 transmits to the network node 200 a message regarding the activated feature, which message includes the feature ID and dynamic conditions of the activated feature.

[0172] If there is a dynamic condition, in step S45, the control unit 130 of the UE 100 checks the content of the dynamic condition. The control unit 130 checks the content of the dynamic condition associated with function #B, and the checking method may be the same as the check (step S26) performed by the network node 200. That is, the control unit 130 determines whether or not the dynamic condition will have an immediate effect on function #B. If the result of the determination is that there will be no immediate effect, the processes of steps S46 to S475 are performed.

[0173] If there is no immediate impact, similar to steps S43 to S445, UE 100 activates function #B (step S46), starts inference of the AI / ML model having function #B (step S47), and sends a message regarding the activated function to network node 200 (step S475).

[0174] On the other hand, if the effect is immediate, the control unit 130 of the UE 100 does not activate function #B.

[0175] (Another Operation Example 2 According to the First Embodiment) For example, even if a function is activated in the UE 100, the function may become unusable as time passes. Alternatively, even if the dynamic conditions are initially satisfied in the UE 100, the dynamic conditions may no longer be satisfied as time passes. Alternatively, in the network node 200, the dynamic conditions may change due to a change in settings, or the function may become unusable.

[0176] Therefore, in another operation example 2 according to the first embodiment, updating of functions or dynamic conditions will be described. Specifically, the UE 100 or the network node 200 notifies the updated status, and the network node 200 or the UE 100 that receives the notification can grasp available functions and / or current dynamic conditions, etc. For example, the network node 200 can also appropriately instruct the UE 100 to activate.

[0177] FIG. 19 is a diagram illustrating another operation example 2 according to the first embodiment.

[0178] 19 , in the network node 200, function C becomes unavailable (step S50), and the dynamic condition of function A changes (step S51). Therefore, the transmitting unit 210 of the network node 200 transmits a message regarding the set functions to the UE 100. The message includes information regarding functions in the supported function information excluding function #C that has become unavailable. The message may also include the changed dynamic condition in meta information linked to the supported function information. The receiving unit 110 of the UE 100 receives the message. The UE 100 can grasp the updated functions and dynamic conditions in the network node 200.

[0179] Meanwhile, in the UE 100, function D becomes unavailable (step S60), and the dynamic condition of function B changes (step S61). Therefore, the transmitter 120 of the UE 100 transmits a message related to each function (steps S62, S63, and S64). The message also includes information related to functions excluding function D, which has become unavailable, in the supported function information. The message may also include the changed dynamic condition in meta information linked to the supported function information. The receiver 220 of the network node 200 receives the message. The network node 200 can also grasp the updated functions and dynamic conditions of the UE 100.

[0180] (Another Operation Example 3 According to the First Embodiment) In the operation examples (FIGS. 16 to 19) described in the first embodiment, the network node 200 may be another network device. For example, an AMF may be used as the network device. In this case, a NAS message is transmitted and received between the UE 100 and the AMF.

[0181] Second Embodiment Next, a second embodiment will be described, focusing on the differences from the first embodiment.

[0182] For example, assume the following case: UE 100 moves from source network node 200-1 to target network node 200-2 by handover. Since UE 100 satisfied certain conditions in source network node 200-1, it was able to perform inference using an AI / ML model having specific functions. However, since UE 100 did not satisfy the conditions in target network node 200-2, it was unable to perform inference using an AI / ML model having specific functions.

[0183] As shown in this case, due to changes in the radio environment, etc., UE100 may not be able to use the functions of the AI / ML model that were usable in one location when moving to another location.

[0184] In such a situation, if the source network node 200-1 can notify the target network node 200-2 of the conditions to be used when the AI / ML model is utilized, the target network node 200-2 can check whether the conditions are met and can also provide some kind of notification to the UE 100.

[0185] However, even if the target network node 200-2 receives notification of the condition, it may be clear that the condition is not met, and the target network node 200-2 may immediately notify the source network node 200-1 that the condition cannot be met. Therefore, the notification of the condition may be wasted. On the other hand, it may not be realistic for the source network node 200-1 to transmit all of the condition to the target network node 200-2.

[0186] Therefore, the second embodiment aims to improve the efficiency of notification of conditions between network nodes 200.

[0187] The conditions used in the second embodiment are supportable conditions. The supportable conditions may indicate supportable conditions for the functions of the AI / ML model. In other words, the supportable conditions may indicate conditions for supporting the functions of the AI / ML model. Alternatively, the supportable conditions may be usage conditions when the functions of the AI / ML model are used. Alternatively, the supportable conditions may be additional conditions that are added in addition to the usage conditions of the functions of the AI / ML model. The additional conditions may be the additional conditions described in the first embodiment. The supportable conditions may be supportable conditions that can be supported in the UE 100. The supportable conditions may be supportable conditions that can be supported in the network node 200.

[0188] In the second embodiment, a network node 200-1 determines whether a supportable condition is applicable to an adjacent network node 200-2 adjacent to the network node 200-1, and if applicable, transmits the supportable condition to the adjacent network node 200-2, and if not applicable, does not transmit the supportable condition.

[0189] Specifically, first, a first network node (e.g., network node 200-1) receives from a user equipment (e.g., UE 100) supported function information indicating AI / ML model functions that can be supported in the user equipment, and supportable conditions indicating conditions under which the AI / ML model functions are supported. Second, the first network node determines whether the supportable conditions are applicable to a second network node (e.g., network node 200-2) adjacent to the first network node. Third, in response to the first network node determining that the supportable conditions are applicable to the second network node, the first network node transmits the supported function information to the second network node, and in response to the supportable conditions not being applicable to the second network node, does not transmit the supported function information to the second network node.

[0190] As a result, for example, in network node 200-1, if a compatible condition is not applicable to adjacent network node 200-2, the compatible condition is not transmitted to adjacent network node 200-2, thereby making it possible to improve the efficiency of notification of conditions between network nodes 200 compared to when compatible conditions are always transmitted.

[0191] (Example of Operation According to Second Embodiment) Next, an example of operation according to the second embodiment will be described.

[0192] Fig. 20 is a diagram illustrating an example of operation according to the second embodiment. In Fig. 20, a network node 200-1 and a network 200-2 are adjacent to each other.

[0193] As shown in FIG. 20, the NW communication unit 240 of the network node 200-2 transmits the availability condition implementation information to the network node 200-1.

[0194] First, the supportable condition implementation information is, for example, information indicating the implementation status of the supportable condition. For example, if the supportable condition is "ordering of the mapping relationship between set A (beam) and set B (reference beam)," the "beam pattern" of the beam transmitted by network node 200-2 corresponds to the supportable condition implementation information. For example, if the supportable condition is "transmission power of 20 dBm or more," the "minimum transmission power" of the transmission signal transmitted from network node 200-2 corresponds to the supportable condition implementation information. The supportable condition implementation information may be information indicating the implementation status in network node 200-2.

[0195] Second, the availability condition implementation information may be transmitted as part of an Xn message. The availability condition implementation information may be transmitted in response to a request from network node 200-1. The request may be a availability condition implementation information request message. In the following description, messages are transmitted and received between network node 200-1 and network node 200-2, and these messages may be Xn messages.

[0196] The NW communication unit 240 of the network node 200-1 receives the availability condition implementation information.

[0197] In step S71, the transmitting unit 120 of the UE 100 transmits a message regarding functionality.

[0198] First, the message regarding functionality may be a message regarding supported functionality described in the first embodiment. The message may be a message regarding available functionality. Alternatively, the message regarding functionality may be a message regarding applicable functionality or a message regarding activated functionality.

[0199] Second, the message regarding the function includes supported function information ( FIG. 14A ) as in the first embodiment. As in the first embodiment, the supported function information includes information indicating which functions are supported in the UE 100 (i.e., information on supportable functions, information on available functions, information on applicable functions, or information on activated functions).

[0200] Third, the message regarding the function includes a support condition. In UE 100, the support condition is the support condition for each function indicated in the support function information. The support condition may be linked to each function included in the support function information (FIG. 14(A)). The support condition may be, for example, the above-mentioned "ordering of the mapping relationship between set A (beam) and set B (reference beam)" or "transmission power of 20 dBm or more."

[0201] Fourth, the message related to the function may be an RRC message, a MAC CE, a message of a new layer for AI / ML, etc., as in the first embodiment. The receiving unit 220 of the network node 200-1 receives the message related to the function.

[0202] In step S72, the control unit 230 of the network node 200-1 checks whether the supportable conditions are included in the message regarding the function. If the supportable conditions are not included in the message regarding the function, the process proceeds to step S73. On the other hand, if the supportable conditions are not included in the message regarding the function, the process proceeds to step S74.

[0203] If the compatibility condition is not included, in step S73, the NW communication unit 240 of the network node 200-1 transmits a function information message to the network node 200-2. Since the compatibility condition is not included, the network node 200-1 determines that the AI / ML model having the function indicated by the function ID (step S71) is also compatible with the network node 200-2, and transmits the function information message.

[0204] The function information message is a message used when transmitting and receiving information related to functions between network nodes 200. The function information message includes the supported function information (FIG. 14(A)) received in step S71. The function information message also includes identification information (UE-ID) of the UE 100 that transmitted the supported function information.

[0205] On the other hand, if a compatible condition is included, in step S74, the control unit 230 of network node 200-1 checks the contents of the compatible condition and determines whether the compatible condition is applicable (or can be handled) by network node 200-2 based on the compatible condition implementation information received in step S70 and the compatible condition received in step S71.

[0206] For example, when the supportable condition implementation information (step S70) is "beam pattern" and the supportable condition (step S71) is "ordering of the mapping relationship between set A (beam) and set B (reference beam)," the following processing may be performed. That is, the control unit 230 of the network node 200-1 may determine that the supportable condition is applicable to the network node 200-2 if a "beam pattern" is included in a beam including set A and set B transmitted from the network node 200-1, and may determine that the supportable condition is not applicable if a "beam pattern" is not included in the beam including set A and set B.

[0207] Alternatively, if the compatible condition implementation information is "minimum transmission power" and the compatible condition is "transmission power of 20 dBm or more," the control unit 230 may determine that the compatible condition is applicable to network node 200-2 if the "minimum transmission power" is "transmission power of 20 dBm or more," and may determine that the compatible condition is not applicable to network node 200-2 if the "minimum transmission power" is less than "20 dBm."

[0208] If it is determined that the supportable condition is applicable, in step S75, the NW communication unit 240 of the network node 200-1 transmits a function information message to the network node 200-2. Since the supportable condition can be applied in the network node 200-2, the network node 200-1 determines that the AI / ML model having the function indicated by the function ID (step S71) is also supportable in the network node 200-2, and transmits the function information message to the network node 200-2.

[0209] On the other hand, if it is determined that the supportability condition is not applicable, in step S76, the control unit 230 of the network node 200-1 does not transmit a function information message to the network node 200-2. The network node 200-1 determines that the AI / ML model having the function indicated by the function ID (step S71) is not supportable in the network node 200-2, and does not transmit a function information message to the network node 200-2.

[0210] (Another Operation Example According to the Second Embodiment) The operation example shown in Fig. 20 may be executed in the handover procedure. For example, the message regarding capabilities (step S71) may correspond to a measurement report. The measurement report is an RRC message transmitted from the UE 100 when a trigger condition based on radio quality or the like is satisfied in the UE 100. Furthermore, the capability information message (steps S73 and 75) may correspond to a handover request. The handover request message is a message transmitted when the network node 200-1, which is the source network node, makes a handover decision based on the measurement report. Therefore, the network node 200-1 can be the source network node, and the network node 200-2 can be the target network node.

[0211] [Other Embodiments] In the first embodiment described above, supervised learning has been mainly described, but the present invention is not limited to this. For example, unsupervised learning or reinforcement learning may be applied to the first embodiment.

[0212] The above-described operational flows are not limited to being implemented independently, but can be implemented by combining two or more operational flows. For example, some steps of one operational flow may be added to another operational flow, or some steps of one operational flow may be replaced with some steps of another operational flow. In each flow, it is not necessary to execute all steps, and only some steps may be executed. Furthermore, the order of steps in each flow may be changed as appropriate.

[0213] In the above embodiment, an example in which the base station is an NR base station (gNB) has been described, but the base station may be an LTE base station (eNB) or a 6G base station. 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 the IAB node. The UE 100 may also be an MT (Mobile Termination) of the IAB node. That is, the UE 100 may be a terminal function unit (a type of communication module) for the base station to control a relay that relays signals. Such a terminal function unit is referred to as an MT. Examples of MTs include, in addition to IAB-MT, NCR (Network Controlled Repeater)-MT and RIS (Reconfigurable Intelligent Surface)-MT.

[0214] 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). A network node may also be configured by a combination of at least a part of a core network device and at least a part of a base station.

[0215] A program may be provided that causes a computer to execute each process according to the above-described embodiments. The program may be recorded on a computer-readable medium. The computer-readable medium can be used to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory storage medium. The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a CD-ROM and / or a DVD-ROM. Furthermore, circuits that execute each process performed by the device according to the above-described embodiments may be integrated, and at least a part of the device may be configured as a semiconductor integrated circuit (chipset, SoC: System on a Chip).

[0216] The functions performed by the apparatus according to the above-described embodiments may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a central processing unit (CPU), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and / or other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes a program stored in a memory. In this disclosure, circuitry, units, and means refer to hardware that is programmed to perform or executes the described functions. The hardware may be any hardware disclosed herein or any hardware known to be programmed or capable of performing the described functions. If the hardware is a processor, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0217] As used in this disclosure, the terms "based on" and "depending on / in response to" do not mean "based only on" or "depending only on," unless expressly stated otherwise. The term "based on" means both "based only on" and "based at least in part on." Similarly, the term "depending on" means both "depending only on" and "depending at least in part on." The terms "include," "comprise," and variations thereof do not mean including only the listed items, but may mean including only the listed items or may include additional items in addition to the listed items. Additionally, the term "or," as used in this disclosure, is not intended to mean an exclusive or. Furthermore, 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 method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way. In this disclosure, where articles are added by translation, such as a, an, and the in English, these articles shall include the plural unless the context clearly indicates otherwise.

[0218] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes can be made within the scope of the gist. Furthermore, the embodiments, operation examples, and processes can be combined as appropriate within the scope of not causing any contradiction.

[0219] This application claims priority from Japanese Patent Application No. 2024-132034 (filed August 8, 2024), the entire contents of which are incorporated herein by reference.

[0220] (Additional Notes) The above can be summarized as in the additional notes, but the additional notes do not limit the embodiments.

[0221] (Supplementary Note 1) A communication control method in a mobile communication system, comprising the step of a user device transmitting, to a network device, information on dynamic conditions that indicate conditions that change after a certain period of time among additional conditions applied to functions of an AI / ML model, and supported function information that indicates functions of the AI / ML model that can be supported by the user device.

[0222] (Supplementary Note 2) The information regarding the dynamic condition is flag information indicating whether the dynamic condition is included in the corresponding function information, the flag information is included in function identification information that identifies the function of an AI / ML model, and the function identification information is included in the corresponding function information. A communication control method as described in Supplementary Note 1.

[0223] (Supplementary Note 3) The communication control method according to Supplementary Note 1 or Supplementary Note 2, wherein the information regarding the dynamic conditions is quantity information indicating the number of the dynamic conditions, the quantity information is included in function identification information that identifies functions of an AI / ML model, and the function identification information is included in the corresponding function information.

[0224] (Appendix 4) The information regarding the dynamic condition is dynamic / static identification information indicating whether the additional condition is the dynamic condition or a static condition indicating a condition that can be maintained without change after a certain period of time has passed, and the dynamic / static identification information is included in the meta information of the corresponding function information, in a communication control method described in any of Appendices 1 to 3.

[0225] (Supplementary Note 5) The communication control method according to any one of Supplementary Notes 1 to 4, wherein the information regarding the dynamic condition is dynamic condition identification information that identifies the dynamic condition, and the dynamic condition identification information is included in meta information of the corresponding function information.

[0226] (Supplementary Note 6) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 5, wherein the dynamic condition identification information is indicated by a local value that can be used within a specific area.

[0227] (Supplementary Note 7) A communication control method according to any one of Supplementary Notes 1 to 6, comprising the steps of: the network device receiving the supported function information and information relating to the dynamic condition from the user device; the network device determining whether the dynamic condition will have an immediate effect on a function in response to confirming, based on the information relating to the dynamic condition, that the dynamic condition is included in the supported function information; and the network device instructing the user device to activate the function in response to determining that the dynamic condition will not have an immediate effect, and not instructing the user device to activate the function in response to determining that the dynamic condition will have an immediate effect.

[0228] (Supplementary Note 8) A communication control method in a mobile communication system, comprising: a step in which a first network node receives, from a user equipment, supported function information indicating functions of an AI / ML model that can be supported in the user equipment, and supportable conditions indicating conditions under which the functions of the AI / ML model can be supported; a step in which the first network node determines whether the supportable conditions are applicable to a second network node adjacent to the first network node; and a step in which the first network node, in response to determining that the supportable conditions are applicable to the second network node, transmits the supported function information to the second network node, and in response to determining that the supportable conditions are not applicable to the second network node, does not transmit the supported function information to the second network node.

[0229] (Supplementary Note 9) The communication control method according to Supplementary Note 8, further comprising a step in which the first network node receives from the second network node supportable condition implementation information indicating the implementation status of the supportable condition, and the determining step includes a step in which the first network node determines whether the supportable condition is applicable to the second network node based on the supportable condition implementation information and the supportable condition.

[0230] 1: Mobile communication system 20: RAN 30: CN 100: UE 110: Receiving unit 120: Transmitting unit 130: Control unit 200: Network node 210: Transmitting unit 220: Receiving unit 230: Control unit 240: NW communication unit 300: CN device

Claims

1. A communication control method in a mobile communication system, comprising: a user device transmitting, to a network device, information regarding dynamic conditions that indicate conditions that change after a certain period of time among additional conditions applied to functions of an AI (Artificial Intelligence) / ML (Machine Learning) model, and supported function information that indicates functions of the AI / ML model that can be supported by the user device.

2. A communication control method according to claim 1, wherein the information regarding the dynamic condition is flag information indicating whether the dynamic condition is included in the corresponding function information, the flag information being included in function identification information that identifies the function of the AI / ML model, and the function identification information being included in the corresponding function information.

3. A communication control method according to claim 1, wherein the information regarding the dynamic conditions is quantity information indicating the number of the dynamic conditions, the quantity information being included in function identification information that identifies the functions of the AI / ML model, and the function identification information being included in the corresponding function information.

4. The communication control method according to claim 1, wherein the information regarding the dynamic condition is dynamic / static identification information indicating whether the additional condition is the dynamic condition or a static condition indicating a condition that can be maintained without change after a certain period of time has elapsed, and the dynamic / static identification information is included in the meta information of the corresponding function information.

5. A communication control method according to claim 1, wherein the information relating to the dynamic condition is dynamic condition identification information for identifying the dynamic condition, and the dynamic condition identification information is included in meta information of the corresponding function information.

6. A communication control method according to claim 5, wherein the dynamic condition identification information is indicated by a local value that can be used within a specific area.

7. A communication control method as described in claim 1, comprising: the network device receiving the supported function information and information regarding the dynamic condition from the user device; the network device determining whether the dynamic condition will have an immediate effect on a function in response to confirming that the dynamic condition is included in the supported function information based on the information regarding the dynamic condition; and the network device instructing the user device to activate the function in response to determining that the dynamic condition will not have an immediate effect, and not instructing the user device to activate the function in response to determining that the dynamic condition will have an immediate effect.

8. A communication control method in a mobile communication system, comprising: a first network node receiving, from a user equipment, supported function information indicating AI / ML model functions that the user equipment can support, and supportable conditions indicating conditions under which the AI / ML model functions are supportable; the first network node determining whether the supportable conditions are applicable to a second network node adjacent to the first network node; and the first network node transmitting the supported function information to the second network node in response to determining that the supportable conditions are applicable to the second network node, and not transmitting the supported function information to the second network node in response to determining that the supportable conditions are not applicable to the second network node.

9. A communication control method as described in claim 8, further comprising the first network node receiving from the second network node supportable condition implementation information indicating the implementation status of the supportable condition, and wherein the determining step includes the first network node determining whether the supportable condition is applicable to the second network node based on the supportable condition implementation information and the supportable condition.

Images