Communication control method and user device

The communication control method optimizes AI/ML model management in communication systems by coordinating timing for operations within the communication control method, reducing unnecessary data transmission and enhancing efficiency.

WO2024232434A1PCT designated stage expired Publication Date: 2024-11-14KYOCERA CORP

Patent Information

Application Number
PCT/JP2024/017462
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-11
Filing Date
2024-05-10
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

Current communication systems face inefficiencies in managing AI/ML model learning and inference processes, leading to wastage of communication resources due to frequent transmission of model learning history information.

Method used

A communication control method where a model management entity transmits timing information for predetermined operations to a model learning entity, allowing the entity to perform operations such as transmitting model learning history, updating AI/ML models, and identifying new models only at specified execution timings, reducing unnecessary data transmission.

Benefits of technology

This approach enhances communication efficiency by minimizing the frequency of model learning history transmissions, thereby optimizing resource usage and improving overall system performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024017462_14112024_PF_FP_ABST
    Figure JP2024017462_14112024_PF_FP_ABST
Patent Text Reader

Abstract

A communication control method according to one aspect of the present invention is used in a mobile communication system. The communication control method includes a step in which a model management entity transmits timing information indicating the timing for the execution of a prescribed operation to a model-training entity. The communication control method also includes a step in which the model-training entity executes the prescribed operation at the execution timing. The prescribed operation is at least one of: transmitting, to the model management entity, model training history information indicating a history of training a first AI / ML model; transmitting, to the model management entity, a second AI / ML model following training of the first AI / ML model; and updating model identification information for identifying the second AI / ML model.
Need to check novelty before this filing date? Find Prior Art

Description

Communication control method and user device

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

[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) in mobile communication systems.

[0003] 3GPP contribution: RP-213599, “New SI: Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface”

[0004] A communication control method according to a first aspect is a communication control method in a mobile communication system. The communication control method includes a step in which a model management entity transmits timing information indicating execution timing of a predetermined operation to a model learning entity. The communication control method also includes a step in which the model learning entity executes the predetermined operation at the execution timing. Here, the predetermined operation is at least one of transmitting, to the model management entity, model learning history information indicating a history of model learning performed on a first AI / ML model, transmitting, to the model management entity, a second AI / ML model after model learning has been performed on the first AI / ML model, and updating model identification information that identifies the second AI / ML model.

[0005] A user device according to a second aspect includes a receiving unit that receives timing information transmitted from a model management entity, the timing information indicating a timing for executing a predetermined operation. The user device also includes a control unit that executes the predetermined operation at the execution timing. Here, the predetermined operation is at least one of transmitting, to the model management entity, model learning history information indicating a history of model learning performed on a first AI / ML model, transmitting, to the model management entity, a second AI / ML model obtained after model learning on the first AI / ML model, and updating model identification information that identifies the second AI / ML model.

[0006] FIG. 1 is a diagram showing an example of the configuration of a mobile communication system according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of a UE (user equipment) according to the first embodiment. FIG. 3 is a diagram showing an example of the configuration of a gNB (base station) according to the first embodiment. FIG. 4 is a diagram showing an example of the configuration of a protocol stack according to the first embodiment. FIG. 5 is a diagram showing an example of the configuration of a protocol stack according to the first embodiment. FIG. 6 is a diagram showing an example of the configuration of functional blocks of the AI / ML technology according to the first embodiment. FIG. 7 is a diagram showing an example of operation in the AI / ML technology according to the first embodiment. FIG. 8 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIGS. 9A and 9B are diagrams showing an example of reducing CSI-RS according to the first embodiment. FIG. 10 is a diagram showing an example of operation according to the first embodiment. FIG. 11 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIG. 12 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. FIG. 13 is a diagram showing an example of the arrangement of functional blocks of the AI / ML technology according to the first embodiment. Fig. 14 is a diagram illustrating an example of an operation according to the first embodiment. Fig. 15 is a diagram illustrating an example of a setting message according to the first embodiment. Fig. 16 is a diagram illustrating an example of the configuration of a mobile communication system 1 according to the first embodiment. Fig. 17 is a diagram illustrating an example of an operation according to the first embodiment. Fig. 18 is a diagram illustrating an example of an operation according to the first embodiment. Fig. 19 is a diagram illustrating an example of an operation according to the second embodiment. Fig. 20 is a diagram illustrating an example of an operation according to the third embodiment.

[0007] The present disclosure aims to improve communication efficiency.

[0008] [First embodiment] A mobile communication system according to a 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] (Configuration of mobile communication system) 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 5GS will be described below 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 user equipment (UE) 100, a 5G radio access network (NG-RAN: Next Generation Radio Access Network) 10, and a 5G core network (5GC: 5G Core Network) 20. Hereinafter, the NG-RAN 10 may be simply referred to as the RAN 10. Furthermore, the 5GC 20 may be simply referred to as the core network (CN) 20.

[0011] The UE 100 is a mobile wireless communication device. The UE 100 may be any device that is used by a user. For example, the UE 100 may be a mobile phone terminal (including a smartphone) and / or a tablet terminal, a notebook PC, a communication module (including a communication card or a 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).

[0012] The NG-RAN 10 includes a base station (called a "gNB" in a 5G system) 200. The gNBs 200 are connected to each other via an Xn interface, which is an interface between base stations. The gNB 200 manages one or more cells. The gNB 200 performs wireless communication with a UE 100 that has established a connection with its own cell. The gNB 200 has a radio resource management (RRM) function, a routing function for user data (hereinafter simply referred to as "data"), a measurement control function for mobility control and scheduling, and the like. The term "cell" is used to indicate the smallest unit of a wireless communication area. The term "cell" is also used to indicate a function or resource for wireless communication with the UE 100. One cell belongs to one carrier frequency (hereinafter simply referred to as "frequency").

[0013] In addition, gNBs can also be connected to the Evolved Packet Core (EPC), which is the core network of LTE. LTE base stations can also be connected to 5GC. LTE base stations and gNBs can also be connected via an inter-base station interface.

[0014] The 5GC20 includes an AMF (Access and Mobility Management Function) and a UPF (User Plane Function) 300. The AMF performs various mobility controls for the UE 100. The AMF manages the mobility of the UE 100 by communicating with the UE 100 using NAS (Non-Access Stratum) signaling. The UPF controls data forwarding. The AMF and the UPF 300 are connected to the gNB 200 via an NG interface, which is an interface between a base station and a core network. The AMF and the UPF 300 may be core network devices included in the CN 20.

[0015] 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 constitute a communication unit that performs wireless communication with the gNB 200. The UE 100 is an example of a communication device.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 3 is a diagram showing an example of the configuration of a gNB 200 (base station) according to the first embodiment. The gNB 200 includes a transmitter 210, a receiver 220, a controller 230, and a backhaul communication unit 250. The transmitter 210 and the receiver 220 constitute a communication unit that performs wireless communication with the UE 100. The backhaul communication unit 250 constitutes a network communication unit that communicates with the CN 20. The gNB 200 is another example of a communication device.

[0020] 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.

[0021] 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.

[0022] The control unit 230 performs various controls and processes in the gNB 200. Such processes include processes for 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 gNB 200 may be performed by the control unit 230.

[0023] The backhaul communication unit 250 is connected to adjacent base stations via an Xn interface, which is an interface between base stations. The backhaul communication unit 250 is connected to the AMF / UPF 300 via an NG interface, which is an interface between a base station and a core network. The gNB 200 may be configured (i.e., functionally divided) with a central unit (CU) and a distributed unit (DU), and the two units may be connected via an F1 interface, which is a fronthaul interface.

[0024] 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.

[0025] 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.

[0026] The PHY layer performs encoding / decoding, modulation / demodulation, antenna mapping / demapping, and resource mapping / demapping. Data and control information are transmitted between the PHY layer of UE100 and the PHY layer of gNB200 via a physical channel. The PHY layer of UE100 receives downlink control information (DCI) transmitted from gNB200 on a physical downlink control channel (PDCCH). Specifically, UE100 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 gNB200 has a CRC (Cyclic Redundancy Code) parity bit scrambled by the RNTI added.

[0027] In NR, UE100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). The gNB200 configures the UE100 with a bandwidth portion (BWP) consisting of contiguous PRBs (Physical Resource Blocks). The UE100 transmits and receives data and control signals in the active BWP. For example, up to four BWPs may be configurable for the UE100. Each BWP may have a different subcarrier spacing. The BWPs may overlap in frequency. When multiple BWPs are configured for the UE100, the gNB200 can specify which BWP to apply by controlling the downlink. This allows the gNB200 to dynamically adjust the UE bandwidth according to the amount of data traffic of the UE100, etc., thereby reducing UE power consumption.

[0028] The gNB 200 can configure, for example, up to three control resource sets (CORESETs) for each of up to four BWPs on the serving cell. The CORESET is a radio resource for control information to be received by the UE 100. Up to 12 or more CORESETs may be configured on the serving cell for the UE 100. Each CORESET may have an index of 0 to 11 or more. The CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive Orthogonal Frequency Division Multiplex (OFDM) symbols in the time domain.

[0029] 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 gNB 200 via a transport channel. The MAC layer of the gNB 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.

[0030] The RLC layer transmits data to the receiving RLC layer using the functions of the MAC layer and PHY layer. Data and control information are transmitted between the RLC layer of the UE 100 and the RLC layer of the gNB 200 via a logical channel.

[0031] The PDCP layer performs header compression / decompression, encryption / decryption, and the like.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] RRC signaling for various settings is transmitted between the RRC layer of UE100 and the RRC layer of gNB200. The RRC layer controls logical channels, transport channels, and physical channels according to the establishment, re-establishment, and release of radio bearers. When there is a connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC connected state. When there is no connection (RRC connection) between the RRC of UE100 and the RRC of gNB200, UE100 is in an RRC idle state. When the connection between the RRC of UE100 and the RRC of gNB200 is suspended, UE100 is in an RRC inactive state.

[0036] 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 300. Note that the UE 100 has an application layer and the like in addition to the radio interface protocol. Also, the layer below the NAS is called an Access Stratum (AS).

[0037] (AI / ML Technology) Next, the AI / ML technology according to the 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.

[0038] The functional block configuration example shown in FIG. 6 includes a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4.

[0039] The data collection unit A1 collects input data, specifically, data for learning and data for inference. The data collection unit A1 outputs the data for learning to the model learning unit A2. The data collection unit A1 also outputs the data for inference to the model inference unit A3. The data collection unit A1 may acquire data in the device in which the data collection unit A1 is provided as input data. The data collection unit A1 may acquire data in another device as input data. Data collection refers to a process of collecting data in a network node, a management entity, or a UE 100, for example, to perform AI / ML model learning, data analysis, and inference. Based on the data collected by the data collection unit A1, subsequent AI / ML model learning and AI / ML model inference are performed. Note that an AI / ML model refers to, for example, a data-driven algorithm that applies AI / ML technology to generate a series of outputs based on a series of inputs. Hereinafter, the terms "model" and "AI / ML model" may be used interchangeably.

[0040] The model learning unit A2 performs model learning. Specifically, the model learning unit A2 optimizes parameters of the learning model through machine learning using the learning data, and derives (or generates, or updates) a learned model. The model learning unit A2 outputs the derived learned model to the model inference unit A3. For example, considering y = ax + b, a (slope) and b (intercept) are parameters, and optimizing these corresponds to machine learning. Generally, machine learning is classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data as learning data. Unsupervised learning is a method that does not use correct answer data as learning data. For example, in unsupervised learning, feature points are memorized from a large amount of learning data, and the correct answer is determined (range estimation). Reinforcement learning is a method of assigning a score to an output result and learning how to maximize the score. Hereinafter, supervised learning will be described, but unsupervised learning may also be applied as machine learning. Reinforcement learning may also be applied as machine learning. This process of learning an AI / ML model (by learning the relationship between input and output) in a data-driven manner and acquiring a trained AI / ML model is referred to as AI / ML model learning, for example. Hereinafter, "AI / ML model learning" may also be referred to as "model learning." Furthermore, a trained AI / ML model may also be referred to as a "trained model."

[0041] The model inference unit A3 performs model inference. Specifically, the model inference unit A3 infers an output from inference data using a trained model and outputs the inference result data to the data processing unit A4. For example, in the equation y = ax + b, x corresponds to the inference data and y corresponds to the inference result data. Note that "y = ax + b" is a model. A model with optimized slope and intercept, for example, "y = 5x + 3," is a trained model. Various model approaches are available, including linear regression analysis, neural networks, and decision tree analysis. The above "y = ax + b" can be considered a type of linear regression analysis. The model inference unit A3 may provide model performance feedback to the model learning unit A2. This process of generating a series of outputs based on a series of inputs using a trained AI / ML model is referred to as AI / ML model inference. Hereinafter, "AI / ML model inference" may also be referred to as "model inference."

[0042] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0043] FIG. 7 is a diagram illustrating an example of operation in the AI / ML technique according to the first embodiment.

[0044] The transmitting entity TE is, for example, an entity in which machine learning is performed. The transmitting entity TE may perform machine learning to derive a trained model. The transmitting entity TE then generates inference result data as an inference result using the trained model. The transmitting entity TE transmits the inference result data to the receiving entity RE.

[0045] On the other hand, the receiving entity RE is, for example, an entity in which machine learning is not performed. The receiving entity RE receives the inference result data transmitted from the transmitting entity TE. The receiving entity RE performs various processes using the inference result data.

[0046] The entity may be, for example, a device, a functional block included in the device, or a hardware block included in the device.

[0047] For example, the transmitting entity TE may be the UE 100, and the receiving entity RE may be the gNB 200 or a core network device. Alternatively, the transmitting entity TE may be the gNB 200 or a core network device, and the receiving entity RE may be the UE 100.

[0048] As shown in Fig. 7, in step S1, a transmitting entity TE transmits control data related to AI / ML technology to a receiving entity RE and receives the control data from the receiving entity RE. The control data may be an RRC message, which is signaling of the RRC layer (i.e., Layer 3). The control data may be a MAC Control Element (CE), which is signaling of the MAC layer (i.e., Layer 2). The control data may be Downlink Control Information (DCI), which is signaling of the PHY layer (i.e., Layer 1). The downlink signaling may be UE-specific signaling. The control data may be broadcast signaling. The control data may be a control message in a control layer (e.g., an AI / ML layer) specialized for artificial intelligence or machine learning.

[0049] (Layout Examples and Use Cases) Next, a description will be given of how the functional blocks shown in Fig. 6 are arranged in the mobile communication system 1. Below, layout examples of the functional blocks will be described along with specific use cases.

[0050] For example, there are three use cases in which AI / ML technology is applied:

[0051] (1.1) "CSI (Channel State Information) Feedback Enhancement"

[0052] (1.2) "Beam management"

[0053] (1.3) "Positioning Accuracy Enhancement" Below, an example of the placement of functional blocks for each use case will be described.

[0054] (1.1) Example of functional block arrangement in "CSI feedback improvement" "CSI feedback improvement" represents a use case in which, for example, machine learning technology is applied to CSI fed back from UE100 to gNB200. CSI is information about the channel state in the downlink between UE100 and gNB200. The CSI includes at least one of a channel quality indicator (CQI), a precoding matrix indicator (PMI), and a rank indicator (RI). The gNB200 performs, for example, downlink scheduling based on the CSI feedback from UE100.

[0055] 8 is a diagram showing an example of the arrangement of each functional block in "CSI feedback improvement". In the example of "CSI feedback improvement" shown in FIG. 8, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are included in the control unit 130 of the UE 100. On the other hand, a data processing unit A4 is included in the control unit 230 of the gNB 200. That is, model learning and model inference are performed in the UE 100. FIG. 8 shows an example in which the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200.

[0056] In "CSI feedback improvement", the gNB 200 transmits a reference signal for the UE 100 to estimate the downlink channel state. As the reference signal, a CSI reference signal (CSI-RS) will be described as an example below, but the reference signal may be a demodulation reference signal (DMRS).

[0057] First, in model learning, UE100 (receiving unit 110) receives a first reference signal from gNB200 using a first resource. Then, UE100 (model learning unit A2) derives a learned model for inferring CSI from the reference signal using learning data including the first reference signal and CSI. Such a first reference signal is sometimes referred to as a full CSI-RS.

[0058] For example, the CSI generation unit 131 performs channel estimation using the received signal (CSI-RS) received by the receiving unit 110 to generate CSI. The transmitting unit 120 transmits the generated CSI to the gNB 200. The model learning unit A2 performs model learning using a set of the received signal (CSI-RS) and the CSI as learning data, and derives a learned model for inferring the CSI from the received signal (CSI-RS).

[0059] Second, in model inference, the receiver 110 receives a second reference signal from the gNB 200 using a second resource that is less than the first resource. Then, the model inference unit A3 uses the trained model to infer CSI as inference result data using the second reference signal as inference data. Hereinafter, such a second reference signal may be referred to as a partial CSI-RS or a punctured CSI-RS.

[0060] For example, the model inference unit A3 inputs the partial CSI-RS received by the receiving unit 110 as inference data into the trained model, and infers CSI from the CSI-RS. The transmitting unit 120 transmits the inferred CSI to the gNB 200.

[0061] This enables UE 100 to feed back (or transmit) accurate (complete) CSI to gNB 200 from the small amount of CSI-RS (partial CSI-RS) received from gNB 200. For example, gNB 200 can reduce (puncture) CSI-RS when intended to reduce overhead. In addition, UE 100 can respond to situations where the radio conditions deteriorate and some CSI-RS cannot be received normally.

[0062] 9A and 9B are diagrams illustrating an example of reducing CSI-RS according to the first embodiment.

[0063] FIG. 9(A) shows an example of reducing CSI-RS by reducing the number of antenna ports that transmit CSI-RS. For example, the gNB 200 performs the following process. That is, when the UE 100 is in a mode in which model learning is performed (hereinafter, sometimes referred to as the "learning mode"), the gNB 200 transmits CSI-RS from all antenna ports of the antenna panel. On the other hand, when the UE 100 is in a mode in which model inference is performed (hereinafter, sometimes referred to as the "inference mode"), the gNB 200 reduces the number of antenna ports that transmit CSI-RS and transmits CSI-RS from half the antenna ports of the antenna panel. This reduces overhead, improves antenna port utilization efficiency, and achieves a reduction in power consumption. Note that the antenna port is an example of a resource.

[0064] On the other hand, FIG. 9(B) shows an example in which the radio resources used for transmitting the CSI-RS, specifically, the gNB 200, reduces the time-frequency resources. For example, the gNB 200 performs the following process. That is, when the UE 100 is in learning mode, the gNB 200 transmits the CSI-RS using predetermined time-frequency resources. On the other hand, when the UE 100 is in inference mode, the gNB 200 transmits the CSI-RS using time-frequency resources that are less than the predetermined time-frequency resources. This reduces overhead, improves the utilization efficiency of radio resources, and reduces power consumption.

[0065] As shown in Figures 9(A) and 9(B), gNB200 transmits full CSI-RS using a predetermined amount of first resources and transmits partial CSI-RS using second resources which have a smaller amount of resources than the first resources.

[0066] FIG. 10 is a diagram illustrating an example of operation in "CSI feedback improvement" according to the first embodiment.

[0067] 10, in step S101, the gNB 200 may notify or set the CSI-RS transmission pattern (puncture pattern) in the inference mode to the UE 100 as control data. For example, the gNB 200 transmits to the UE 100 the antenna port and / or time-frequency resource that transmits or does not transmit the CSI-RS in the inference mode.

[0068] In step S102, gNB200 may send a switching notification to UE100 to start learning mode.

[0069] In step S103, the UE 100 starts the learning mode.

[0070] In step S104, the gNB 200 transmits the full CSI-RS. The receiver 110 of the UE 100 receives the full CSI-RS, and the CSI generator 131 generates (or estimates) CSI based on the full CSI-RS. In the learning mode, the data collector A1 collects the full CSI-RS and CSI. The model learning unit A2 creates a learned model using the full CSI-RS and the CSI as learning data.

[0071] In step S105, UE100 transmits the generated CSI to gNB200.

[0072] Thereafter, in step S106, when the model learning is completed, the UE 100 transmits a completion notification indicating that the model learning is completed to the gNB 200. The UE 100 may transmit a completion notification when the creation of the learned model is completed.

[0073] In step S107, in response to receiving the completion notification, gNB200 sends a switching notification to UE100 to switch UE100 from learning mode to inference mode.

[0074] In step S108, in response to receiving the switching notification, the UE 100 switches from the learning mode to the inference mode.

[0075] In step S109, the gNB 200 transmits a partial CSI-RS. The receiver 110 of the UE 100 receives the partial CSI-RS. In the inference mode, the data collector A1 collects the partial CSI-RS. The model inference unit A3 inputs the partial CSI-RS as inference data into the trained model, and obtains CSI as the inference result.

[0076] In step S110, the UE 100 feeds back (or transmits) the CSI, which is the inference result, to the gNB 200 as inference result data. In the UE 100, by repeating model learning in the learning mode, a trained model with a predetermined accuracy or higher can be generated. It is expected that the inference result using the trained model generated in this way will also have a predetermined accuracy or higher.

[0077] In addition, in step S111, if UE100 determines that model learning is necessary, it may send a notification indicating that model learning is necessary to gNB200 as control data.

[0078] In the example shown in Fig. 10, the training data is "(full) CSI-RS" and "CSI", and the inference data is "(partial) CSI-RS". Hereinafter, the training data and / or the inference data may be referred to as a "dataset".

[0079] In "improving CSI feedback," in addition to "CSI-RS" and "CSI," at least one of the following data or information may be used as a data set:

[0080] (X1) RSRP (Reference Signals Received Power), RSRQ (Reference Signal Received Quality), SINR (Signal-to-interference-plus-noise ratio), or AD converter output waveform (These measurements may be CSI-RS. These measurements may also be other received signals received from the gNB 200.)

[0081] (X2) Bit Error Rate (BER) or Block Error Rate (BLER) (The total number of transmitted bits (or the total number of transmitted blocks) is known, and the BER (or BLER) may be measured based on the CSI-RS.)

[0082] (X3) The movement speed of UE100 (which may be measured by a speed sensor within UE100). The data set to be used for machine learning may be set. For example, the following processing may be performed. That is, UE100 transmits capability information indicating which type of input data it can handle in machine learning to gNB200 as control data. The capability information may represent, for example, any of the data or information shown in (X1) to (X3). The capability information may be information in which learning data and inference data are separately specified. Then, gNB200 transmits data type information to be used as the data set to UE100 as control data. The data type information may represent, for example, any of the data or information shown in (X1) to (X3). Furthermore, the data type information may specify separately data type information to be used as learning data and data type information to be used as inference data.

[0083] (1.2) Example of functional block arrangement in "beam management" Next, an example of functional block arrangement in "beam management" will be described. "Beam management" represents a use case in which, for example, machine learning technology is used to manage which beam is the optimal beam among the beams transmitted from gNB200.

[0084] In "beam management," gNB200 sequentially transmits beams with different directivities. Each beam includes, for example, a reference signal. UE100 measures the reception quality of each beam using the reference signal included in each beam. UE100, for example, determines the beam with the best reception quality as the optimal beam.

[0085] Figure 11 is a diagram showing an example of the arrangement of each functional block in "beam management". In the example of "beam management" shown in Figure 11, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are included in the control unit 130 of UE100. On the other hand, a data processing unit A4 is included in the control unit 230 of gNB200. That is, Figure 11 shows an example in which model learning and model inference are performed in UE100. Figure 11 shows an example in which the transmitting entity TE is UE100 and the receiving entity RE is gNB200.

[0086] As shown in FIG. 11 , the UE 100 has an optimal beam determination unit 132. The optimal beam determination unit 132 determines the optimal beam based on, for example, the reception quality for the reference signal included in each beam. As with "CSI feedback," an example will be described in which a CSI-RS is used as the reference signal, but a demodulation reference signal (DMRS) may also be used as the reference signal. The transmitter 120 transmits information representing the determined optimal beam to the gNB 200 as the "optimal beam."

[0087] An example of the operation in "beam management" can be implemented by replacing "CSI feedback" with "optimal beam" in Figure 10.

[0088] In the learning mode (step S103), the gNB 200 sequentially transmits beams with different directivities to the UE 100 (step S104). Each beam includes a full CSI-RS. In the learning mode, the data collection unit A1 of the UE 100 collects the full CSI-RS and the optimal beam (information representing the optimal beam). The model learning unit A2 creates a learned model using the CSI-RS and the optimal beam (information representing the optimal beam) as learning data. The full CSI-RS is an example of a first reference signal, and the partial CSI-RS is an example of a second reference signal.

[0089] In the inference mode (step S108), the gNB 200 sequentially transmits beams with different directivities. Each beam includes a partial CSI-RS. In the inference mode, the data collection unit A1 collects the partial CSI-RS. The model inference unit A3 inputs the partial CSI-RS as inference data into the trained model, and obtains the optimal beam (information representing the optimal beam) as the inference result. The UE 100 transmits the inference result (optimal beam) to the gNB 200 as inference result data.

[0090] In "beam management," in addition to "CSI-RS" and "optimal beam," at least one of the following data or information may be used as data in the data set.

[0091] (Y1) SSB (Synchronization Signal Block) received from gNB200

[0092] (Y2) RSRP, RSRQ, SINR, or AD converter output waveform (these measurements may be CSI-RS. These measurements may also be other received signals received from gNB200)

[0093] (Y3) BER or BLER (BER (or BLER) may be measured based on CSI-RS with the total number of transmission bits (or the total number of transmission blocks) known)

[0094] (Y4) Number of beams or beam pattern

[0095] (Y5) Beam measurement value(s)

[0096] (Y6) UE100's movement speed (may be measured by a speed sensor within UE100) UE100 may transmit capability information indicating which type of input data it can handle in machine learning to gNB200 as control data. The capability information may include any of the information or data from (Y1) to (Y6). The capability information may include any of the information or data from (Y1) to (Y6), separating the learning data and the inference data. In addition, gNB200 may transmit data type information used as a data set to UE100 as control data. The data type information may include, for example, any of the data or information shown in (Y1) to (Y6). The data type information may include any of the information or data from (Y1) to (Y6), separating the learning data and the inference data.

[0097] (1.3) Example of Arrangement of Functional Blocks in "Improvement of Location Accuracy" Next, an example of arrangement of functional blocks in "Improvement of Location Accuracy" will be described. "Improvement of Location Accuracy" represents a use case in which, for example, the accuracy of location information measured by the UE 100 is improved by using machine learning technology.

[0098] Figure 12 is a diagram showing an example of the arrangement of each functional block in "improving location accuracy". In the example of "improving location accuracy" shown in Figure 12, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are included in the control unit 130 of the UE 100. On the other hand, a data processing unit A4 is included in the control unit 230 of the gNB 200. That is, Figure 12 shows an example in which model learning and model inference are performed in the UE 100. Figure 12 shows an example in which the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200.

[0099] As shown in FIG. 12 , the UE 100 includes a location information generation unit 133. The UE 100 may include a GNSS (Global Navigation Satellite System) receiver 150. The location information generation unit 133 generates location data for the UE 100 based on a positioning reference signal (PRS) (full PRS or partial PRS) received from the gNB 200. The location information generation unit 133 may receive a GNSS signal (full GNSS signal or partial GNSS signal) received by the GNSS receiver 150, and generate location data for the UE 100 based on the GNSS signal.

[0100] Note that the gNB 200 transmits the full PRS using a predetermined amount of first resources (for example, all antenna ports as shown in FIG. 9A, or a predetermined amount of time-frequency resources as shown in FIG. 9B), similar to the full CSI-RS. Also, the gNB 200 transmits the partial PRS using second resources (for example, half the antenna ports in the antenna panel as shown in FIG. 9A, or half the predetermined amount of time-frequency resources as shown in FIG. 9B) that have a smaller amount of resources than the first resources, similar to the partial CSI-RS.

[0101] The full GNSS signal may also be a GNSS signal that is received continuously over time by the GNSS receiver 150. Furthermore, the partial GNSS signal may also be a GNSS signal that is received intermittently by the GNSS receiver 150. That is, a predetermined amount of first resources may be used for the full GNSS signal, and second resources having a smaller amount than the first resources may be used for the partial GNSS signal.

[0102] An example of the operation for "improving location accuracy" can be implemented by replacing "full CSI-RS" with "full PRS," "partial CSI-RS" with "partial PRS," and "CSI feedback" with "location data" in Figure 10.

[0103] In the learning mode (step S103), the location information generation unit 133 generates location data for the UE 100 based on the full PRS received from the gNB 200. The location information generation unit 133 may receive a full GNSS signal received by the GNSS receiver 150 and generate location data for the UE 100 based on the full GNSS signal. The transmission unit 120 feeds back (or transmits) the location data to the gNB 200. The data collection unit A1 collects the full PRS (or full GNSS signal) and location data. The model learning unit A2 creates a learned model using the full PRS (or full GNSS signal) and location data as learning data.

[0104] In the inference mode (step S108), the data collection unit A1 collects the partial PRS received by the receiving unit 110 (or the partial GNSS signal received by the GNSS receiver 150). The model inference unit A3 inputs the partial PRS (or the partial GNSS signal) as inference data into the trained model, and obtains location data as an inference result. The UE 100 transmits the inference result (location data) to the gNB 200 as inference result data.

[0105] In "improving position accuracy," in addition to "PRS" (or "GNSS signal") and "position data," at least one of the following data or information may be used in the data set:

[0106] (Z1) RSRP, RSRQ, SINR (Signal-to-Interference-Plus-Noise Ratio), or AD converter output waveform (these measurements may be PRS. These measurements may also be other received signals received from gNB200)

[0107] (Z2) LOS (Line of Sight) or NLOS (Non Line of Sight)

[0108] (Z3) Measurement timing, accuracy, likelihood

[0109] (Z4) RF Fingerprint (Cell ID and reception quality in the cell of the cell ID)

[0110] (Z5) Angle of Arrival (AOA), reception level for each antenna, reception phase for each antenna, and observed time difference of arrival (OTDOA) for each antenna

[0111] (Z6) Received information of beacons used in wireless LANs (Local Area Networks) such as Wi-Fi (registered trademark) or short-range wireless communications such as Bluetooth (registered trademark)

[0112] (Z7) Movement speed of UE100 (The movement speed may be measured by the GNSS receiver 150. The movement speed may be measured by a speed sensor within UE100.) UE100 may transmit capability information indicating which type of input data it can handle in machine learning as control data to gNB200. The capability information may include any of the information or data from (Z1) to (Z7), or may include any of the information or data from (Z1) to (Z7) separately for learning data and inference data. In addition, gNB200 may transmit data type information to be used as a data set as control data to UE100. The data type information may include, for example, any of the data or information shown in (Z1) to (Z7). The data type information may include any of the information or data from (Z1) to (Z7) separately for learning data and inference data.

[0113] (1.4) Other Arrangement Examples Next, other arrangement examples will be described.

[0114] Fig. 13 is a diagram showing another example of the arrangement of "CSI feedback improvement" according to the first embodiment. Fig. 13 shows an example in which a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4 are included in a gN200. That is, Fig. 14 shows an example in which model learning and model inference are performed in a gNB200. Fig. 14 shows an example in which a transmitting entity TE is a gNB200 and a receiving entity RE is a UE100.

[0115] 13 shows an example in which AI / ML technology is introduced into CSI estimation performed by gNB200 based on SRS (Sounding Reference Signal). Therefore, gNB200 has a CSI generation unit 231 that generates CSI based on SRS. The CSI is information indicating the channel state of the uplink between UE100 and gNB200. gNB200 (e.g., data processing unit A4) performs, for example, uplink scheduling based on the CSI generated based on SRS.

[0116] (1.5) Model transfer example

[0117] In (1.1) to (1.4), examples of the arrangement of each functional block of AI / ML technology have been described. Below, model transfer will be described. The model to be transferred may be a trained model used in model inference. The model may also be an untrained (or training) model used in model training.

[0118] (1.6.1) First operation pattern related to model forwarding Figure 14 is a diagram showing an example of an operation of the first operation pattern related to model forwarding according to the first embodiment. In the example shown in Figure 14, the description will be given assuming that the receiving entity RE is mainly the UE 100, but the receiving entity RE may be the gNB 200 or the AMF 300. Also, in the example shown in Figure 14, the description will be given assuming that the transmitting entity TE is the gNB 200, but the transmitting entity TE may be the UE 100 or the AMF 300.

[0119] 14, in step S401, the gNB 200 transmits a capability inquiry message to the UE 100 to request transmission of a message including an information element (IE) indicating execution capability for machine learning processing. The UE 100 receives the capability inquiry message. However, the gNB 200 may transmit the capability inquiry message when executing the machine learning processing (when determining that the processing will be executed).

[0120] In step S402, the UE 100 transmits to the gNB 200 a message including an information element indicating execution capability for machine learning processing (or, from another perspective, the execution environment for machine learning processing). The gNB 200 receives the message. The message may be an RRC message (for example, a "UE Capability" message or a newly defined message (for example, a "UE AI Capability" message, etc.)). Alternatively, the transmitting entity TE may be the AMF 300, and the message may be a NAS message. Alternatively, if a new layer for performing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message of the new layer.

[0121] The information element indicating the execution capability related to the machine learning process may be an information element indicating the capability of a processor for executing the machine learning process and / or an information element indicating the capability of a memory for executing the machine learning process. Specifically, the information element indicating the processor capability may be an information element indicating the product number (or model number) of the AI ​​processor. Specifically, the information element indicating the memory capability may be information indicating the memory capacity.

[0122] Alternatively, the information element indicating the execution capability of machine learning processing may be an information element indicating the execution capability of inference processing (model inference). Specifically, the information element indicating the execution capability of inference processing may be an information element indicating whether a deep neural network model is supported. The information element may also be an information element indicating the time (or response time) required to execute the inference processing.

[0123] Alternatively, the information element indicating the execution capability related to the machine learning process may be an information element indicating the execution capability of the learning process (model learning). Specifically, the information element indicating the execution capability of the learning process may be an information element indicating the number of concurrent executions of the learning process. The information element may be an information element indicating the processing capacity of the learning process.

[0124] In step S403, gNB200 determines the model to be configured (or deployed) in UE100 based on the information elements contained in the message received in step S402.

[0125] In step S404, gNB200 transmits a message including the model determined in step S403 to UE100. UE100 receives the message and performs machine learning processing (i.e., model learning processing and / or model inference processing) using the model included in the message. A specific example of step S404 will be described in the following second operation pattern.

[0126] (1.6.2) Second operation pattern related to model transfer FIG. 15 is a diagram showing an example of a configuration message including a model and additional information according to the first embodiment. The configuration message may be an RRC message transmitted from the gNB 200 to the UE 100 (for example, an "RRC Reconfiguration" message, or a newly defined message (for example, an "AI Deployment" message or an "AI Reconfiguration" message, etc.). Alternatively, the configuration message may be a NAS message transmitted from the AMF 300 to the UE 100. Alternatively, when a new layer for performing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message of the new layer.

[0127] In the example of FIG. 15, the setting message includes three models (Model #1 to #3). Each model is included as a container in the setting message. However, the setting message may include only one model. The setting message further includes, as additional information, three individual additional information (Info #1 to #3) provided individually corresponding to each of the three models (Model #1 to #3), and common additional information (Meta-Info) commonly associated with the three models (Model #1 to #3). Each of the individual additional information (Info #1 to #3) includes information unique to the corresponding model. The common additional information (Meta-Info) includes information common to all models in the setting message.

[0128] The individual additional information may be a model index indicating an index (index number) assigned to each model, or may be a model execution condition indicating the performance (e.g., processing delay) required to apply (execute) the model.

[0129] The individual additional information or the common additional information may be a model usage that specifies a function to which a model is to be applied (e.g., "CSI feedback," "beam management," "positioning," etc.). The individual additional information or the common additional information may be a model selection criterion that applies (executes) a corresponding model depending on whether a specified criterion (e.g., a moving speed) is satisfied.

[0130] (2) Communication Control Method According to First Embodiment Next, a communication control method according to the first embodiment will be described.

[0131] Here, assume the following case: The transmitting entity TE performs model inference using a trained model A. After that, the transmitting entity TE determines that the inference result of the trained model A deviates from the result obtained by legacy operation (operation that obtains an inference result without using an AI / ML model), and performs model training (i.e., re-training) using the trained model A to create a new trained model A'.

[0132] In such cases, if a model management entity that manages an AI / ML model can manage the history of model learning, the AI / ML model can be managed appropriately. In particular, 3GPP is currently discussing life cycle management (LCM) (hereinafter, sometimes referred to as "LCM") for AI / ML models. LCM refers to, for example, managing the life cycle of an AI / ML model, from its generation to its management, operation, and deletion. By managing the AI / ML model appropriately, it is also possible to take an appropriate approach to LCM.

[0133] However, transmitting the history to the model management entity every time the transmitting entity TE performs model learning using the learned model A may waste communication resources. In particular, when the transmitting entity TE is the UE 100, transmitting the history to the model management entity every time model learning is performed using the learned model A may waste radio resources.

[0134] Therefore, the first embodiment aims to improve communication efficiency.

[0135] Therefore, in the first embodiment, first, the model management entity (e.g., gNB200) transmits timing information indicating the execution timing of a predetermined operation to the model learning entity (e.g., UE100). Second, the model learning entity executes the predetermined operation at the execution timing. Here, the predetermined operation is at least one of transmitting model learning history information indicating the history of model learning performed on the first AI / ML model (e.g., trained model A) to the model management entity, transmitting a second AI / ML model (e.g., trained model A') after model learning has been performed on the first AI / ML model to the model management entity, and updating model identification information that identifies the second AI / ML model.

[0136] In this way, in the first embodiment, the model management entity transmits timing information indicating the execution timing of a predetermined operation to the model learning entity, so that the model learning entity can perform the predetermined operation at that timing. Therefore, in the first embodiment, the number of times the model learning history information is transmitted is reduced compared to, for example, a case where the model learning entity transmits model learning history information every time it performs model learning. Therefore, in the first embodiment, it is possible to improve communication efficiency.

[0137] (2.1) Example of Configuration of Mobile Communication System 1 According to First Embodiment Next, an example of configuration of the mobile communication system 1 according to the first embodiment will be described.

[0138] FIG. 16 is a diagram illustrating an example of the configuration of a mobile communication system 1 according to the first embodiment.

[0139] As shown in FIG. 16, the mobile communication system 1 includes a model management entity MNE and a model learning entity MLE.

[0140] The model management entity MNE is, for example, an entity that manages AI / ML models used in the mobile communication system 1. The model management entity MNE holds a model management list in a memory, and identifies each AI / ML model in the model management list by a model ID. In the first embodiment, the model management entity MNE may assign a model ID (or model identification information; hereinafter, sometimes referred to as a "model ID") to an AI / ML model.

[0141] The model ID may be identification information that distinguishes at least the AI / ML model from other AI / ML models. The model ID may be global identification information. That is, the model ID may be identification information unique among PLMNs (Public Land Mobile Networks). Therefore, the model ID may include a PLMN ID. Alternatively, the model ID may be identification information unique among NPNs (Non-public networks). Therefore, the model ID may include an NPN ID. The NPN ID may be a PLMN ID and a Closed Access Group ID (CAG ID), or a PLMN ID and a Network ID (NID). Alternatively, the model ID may include a global gNB ID that can globally identify the gNB 200. Alternatively, the model ID may include an NCGI (NR Cell Global Identifier) ​​that can globally identify an NR cell.

[0142] The model learning entity MLE is, for example, an entity that performs model learning on an AI / ML model. The AI / ML model to be learned may be a trained AI / ML model. The model may also be an untrained AI / ML model. However, in the first embodiment, the model learning entity MLE will be described as performing model learning on a trained AI / ML model. Hereinafter, performing model learning on a trained AI / ML model may be referred to as "relearning." By relearning the trained AI / ML model, the model learning entity MLE derives an AI / ML model that is different from the trained AI / ML model. This is because, when model inference is performed on the AI / ML model before relearning and the AI / ML model after relearning, it is expected that different inference result data will be output. In the following, the AI / ML model before relearning may be referred to as "learned model A," and the AI / ML model after relearning may be referred to as "learned model A'."

[0143] The model learning entity MLE may perform model inference on the trained AI / ML model (which may be trained model A or trained model A'). In this case, the model learning entity MLE functions as a transmitting entity that transmits inference result data indicating the results of performing model inference.

[0144] In the first embodiment, whether or not a trained AI / ML model has been retrained is managed using model change information.

[0145] First, the model change information is, for example, information indicating whether or not a trained AI / ML model has been retrained (e.g., trained information). Alternatively, the model change information may be information indicating whether or not a trained AI / ML model has been changed by retraining the trained AI / ML model. The model change information may be represented as 1-bit flag information. Alternatively, the model change information may be represented by multiple bits and incremented each time retraining is performed. Hereinafter, the model change information will be described as 1-bit flag information. In this case, the model change information being on will indicate that retraining has been performed on the trained AI / ML model, and the model change information being off (or cleared) will indicate that retraining has not been performed on the trained AI / ML model. However, on and off may have opposite meanings. The flag information may indicate a toggle state. For example, if the initial value of the flag information is off, it will be turned on during the first retraining, off again during the second retraining, and off again during the third retraining. Thereafter, the flag information will be switched between on and off each time training is performed.

[0146] Second, the model change information may be included in the model ID that identifies the AI / ML model. That is, the model change information may be added to part of the model ID. Alternatively, the model change information may be included in additional information (FIG. 15) included in the setting message. Specifically, the model change information may be included in individual additional information (Info) added to the corresponding AI / ML model. Alternatively, the model change information may be included in the AI / ML model. Specifically, the model change information may be included in the model body of the AI / ML model. The model change information may be included in the model data of the AI / ML model.

[0147] In the first embodiment, an example will be described in which the model learning entity MLE is the UE 100 and the model management entity MNE is the gNB 200, but this is not limiting. For example, the model management entity MNE may be a core network device. The model management entity MNE may be an OTT (Over The Top) server device. The OTT server device is, for example, a device that exists outside the mobile communication system 1 and provides various content services, such as video distribution, to the UE 100. Alternatively, the model learning entity MLE may be the gNB 200, and the model management entity MNE may be a core network device or an OTT server device.

[0148] (2.1) Example of Operation According to First Embodiment Next, an example of operation according to the first embodiment will be described.

[0149] 17 is a diagram showing an example of operation according to the first embodiment. As described above, FIG. 17 shows an example in which the model learning entity MLE is UE100 and the model management entity MNE is gNB200. In UE100, reception of messages and the like may be performed by the receiving unit 110 of UE100, and transmission of messages and the like may be performed by the transmitting unit 120. Furthermore, processing or operation in UE100 may be performed by the control unit 130, and processing or operation in gNB200 may be performed by the control unit 230.

[0150] As shown in FIG. 17, in step S501, gNB200 transmits an RRC message including a trained AI / ML model (hereinafter referred to as "trained model A") to UE100. gNB200 may determine the trained model A to be transmitted based on an information element indicating the execution capability for machine learning processing received from UE100 (steps S402 and S403 in FIG. 14). gNB200 may transmit the model ID of the trained model A to UE100 along with the trained model A. In this case, gNB200 may transmit the model ID of the trained model A by including it in individual additional information (Info) (FIG. 15). UE100 receives the RRC message.

[0151] In step S502, the gNB 200 transmits timing information indicating the execution timing of a predetermined operation to the UE 100. The gNB 200 may transmit the timing information by transmitting control data including the timing information to the UE 100. The UE 100 receives the timing information.

[0152] The timing information may be represented by the elapsed time (e.g., 24 hours) since the trained model A was updated by relearning the trained model A. The elapsed time may be specified by a timer value. The timer may start when the model is relearned and indicate the execution timing by expiring. Alternatively, the timing information may be represented by a time period (e.g., a late-night time period) after the trained model A is updated. In this case, the execution timing indicates the time when the specified time period occurs after the trained model A is updated. Alternatively, the timing information may be represented as specifying the number of times an update (or relearning) is performed. For example, if the specified number of times is 10, this indicates that the execution timing is when the trained model A has been updated 10 times. The number of updates may be measured by a counter. The counter may be reset to an initial value (e.g., zero) when the trained model is received and incremented by one each time relearning is performed. Alternatively, the timing information may be specified by the operation after the update. For example, the operation may be handover, cell (re)selection, or redirection. In this case, the execution timing may be when handover is performed, cell (re)selection is performed, or redirection is performed after updating the learned model A.

[0153] Examples of predetermined actions that are the subject of timing information include the following.

[0154] First, the predetermined operation may be to transmit to the gNB 200 model learning history information indicating a history of model learning performed on the learned model A. In this case, the UE 100 will transmit the model learning history information to the gNB 200 when the execution timing arrives.

[0155] Secondly, the predetermined operation may be to transmit the trained model A′ after model training to the gNB 200. In this case, the UE 100 will transmit the trained model A′ to the gNB 200 when the execution timing arrives.

[0156] Third, the predetermined operation may be updating the model ID that identifies the trained model A′. In this case, the UE 100 updates the model ID of the trained model A′ at the execution timing.

[0157] In the first embodiment, such a predetermined operation is not performed every time the trained model A is re-trained, but is performed at the execution timing specified by the timing information.

[0158] Regarding the predetermined action, for example, information indicating which predetermined action it is may be included in the timing information.

[0159] In step S503, gNB200 transmits a switching notification to UE100 to switch from learning mode to inference mode. The switching notification may include the model ID of trained model A (step S501). UE100 receives the switching notification.

[0160] In step S504, the UE 100 switches to the inference mode in response to receiving the switching notification.

[0161] In step S505, UE100 performs model inference on the trained model A received in step S501.

[0162] In step S506, the UE 100 evaluates the inference result of the model inference (step S505).

[0163] First, the UE 100 may evaluate the inference result by comparing it with a legacy operation. For example, the UE 100 performs a legacy operation that does not use an AI / ML model during model inference and acquires operation result data. The UE 100 may then compare the operation result data with inference result data obtained by model inference to evaluate the inference result. The UE 100 may determine that re-learning of the trained model A is not necessary if the difference between the operation result data and the inference result data is within a threshold value; otherwise, it may determine that re-learning is necessary.

[0164] Second, the UE 100 may evaluate the inference result by performing a likelihood determination on the inference result data. Specifically, the UE 100 may apply a likelihood function to the inference result data at a certain timing, compare the inference result data with the inference result data immediately before the timing, and evaluate the inference result. For example, the UE 100 may determine that re-learning of the trained model A is not necessary if the difference between the data to which the likelihood function is applied and the inference result data is within a threshold value, and may otherwise determine that re-learning is necessary.

[0165] In this way, the UE 100 determines whether or not re-learning of the learned model A is necessary based on the inference result of the model inference using the learned model A. In the following, it is assumed that the UE 100 has evaluated the inference result and determined that re-learning of the learned model is necessary.

[0166] In step S507, the UE 100 switches to the learning mode. The UE 100 may use control data to transmit a notification to the gNB 200 that the learning mode will be switched.

[0167] In step S508, UE100 performs model learning (i.e., re-learning) on ​​learned model A.

[0168] In step S509, UE100 transmits a learning execution notification to gNB200 indicating that re-learning of trained model A has been performed. UE100 may transmit the learning execution notification by transmitting an RRC message including the learning execution notification. Alternatively, when a new layer for performing or controlling machine learning processing (AI / ML processing) is defined, UE100 may transmit the learning execution notification by including the learning execution notification in a message of the new layer and transmitting the message. gNB200 receives the learning execution notification.

[0169] In step S510, UE100 turns on the model change information of the learned model A. Alternatively, UE100 may turn on the model change information in response to receiving, from gNB200, configuration information (control data) indicating that the model change information of the learned model A is to be turned on. UE100 may send a change flag on notification indicating that the model change information has been turned on to the model management entity MNE. The change flag on notification may also be sent using an RRC message or a new message for machine learning processing (AI / ML processing).

[0170] In step S511, in response to receiving the learning implementation notification (step S509), gNB200 turns on the model change information of the trained model A. gNB200, which is a model management entity MNE, stores a model management list in memory. gNB200 may register the trained model A by recording "on" in the model change information of the trained model A in the model management list.

[0171] In step S512 of FIG. 18, the UE 100 detects that it is time to perform a predetermined operation.

[0172] First, the UE 100 may detect the timing of transmitting model learning history information as the timing of executing a predetermined operation. The model learning history information may include information regarding the history of model learning. The model learning history information may include, for example, the time when the model learning was performed, or the learning data (and / or the type of learning data) used for model learning. The model learning history information may include information regarding the history for each trained model. The target of the model learning history information may be trained model A before re-learning.

[0173] Second, UE 100 may detect the transmission timing (or transfer timing) of learned model A' as the execution timing of the predetermined operation. In this case, UE 100 is assumed to have derived learned model A' at this point as a result of model training of learned model A (step S508). Therefore, the transmission target may be learned model A'.

[0174] In step S513, the UE 100 may transmit model learning history information.

[0175] In step S514, the UE 100 may transmit the learned model A′. Both the model learning history information and the learned model A′ may be transmitted using an RRC message or a new message for machine learning processing (AI / ML processing).

[0176] In step S515, the UE 100 detects the update timing of the model ID as the execution timing of the predetermined operation.

[0177] First, the UE 100 may be configured to execute a process of acquiring a model ID for the trained model A', triggered by the detection of update timing. As the process of acquiring the model ID, the UE 100 may transmit a request to acquire a model ID to the gNB 200. The acquisition request may include the model ID of the trained model A before re-learning. Alternatively, the acquisition request may include model change information (step S510). The acquisition request may also be transmitted using an RRC message or a new message for machine learning processing (AI / ML processing). In response to receiving the acquisition request, the gNB 200 issues a new model ID and transmits the new model ID to the UE 100. The new model ID may be transmitted using control data.

[0178] Second, the model ID acquisition process itself may be performed before step S512. For example, the acquisition request may be transmitted at the timing when UE100 re-learns the trained model A (step S508). The learning execution notification (step S509) may also serve as (or imply) the acquisition request. In response to receiving the acquisition request, gNB200 issues a new model ID and transmits the new model ID to UE100. UE100 may store the new model ID acquired from the model management entity MNE in memory, and update the model ID by applying it to trained model A' when it detects the update timing (step S515).

[0179] (Another operation example 1 according to the first embodiment) In the first embodiment, an example has been described in which the model management entity MNE is the gNB 200, but the model management entity MNE is not limited to the gNB 200. The model management entity MNE may be a core network device.

[0180] In this case, this can be implemented by replacing gNB200 with a core network device in the operation examples shown in Figures 17 and 18. In this case, between UE100 (model learning entity MLE) and core network device (model management entity MNE), steps S501, S502, S503, S509, S513, and S514 may be performed using a message available between UE100 and the core network device (for example, if the core network device is AMF300, a NAS message).

[0181] (Another operation example 2 according to the first embodiment) Furthermore, the model management entity MNE may be an OTT server device. In this case, in the operation examples shown in Figures 17 and 18, this can be implemented by replacing gNB200 with an OTT server device. In this case, steps S501, S502, S503, S509, S513, and S514 may be performed between UE100 (model learning entity MLE) and the OTT server device (model management entity MNE) using messages that can be used between UE100 and the OTT server device.

[0182] (Another Operation Example 3 According to First Embodiment) In the first embodiment, an example has been described in which the model learning entity MLE is the UE 100, but the model learning entity MLE is not limited to the UE 100. For example, the model learning entity MLE may be the gNB 200. In this case, the model management entity MNE may be a core network device. The model management entity MNE may be an OTT server device.

[0183] When the model learning entity MLE is gNB200 and the model management entity MNE is a core network device, in the operation examples shown in Figures 17 and 18, UE100 (model learning entity) can be read as gNB and gNB200 (model management entity) can be read as core network device. In this case, steps S501, S502, S503, S509, S513, and S514 may be performed between gNB200 (model learning entity) and the core network device (model management entity) using messages (e.g., NG messages) available between these devices.

[0184] Also, when the model learning entity MLE is gNB200 and the model management entity MNE is an OTT server device, in the operation example shown in Figure 17, UE100 (model learning entity) can be read as gNB200 and gNB200 (model management entity) can be read as OTT server device, and this can be implemented. In this case, steps S501, S502, S503, S509, S513, and S514 may be performed between the gNB200 (model learning entity) and the OTT server device (model management entity) using messages available between these devices.

[0185] Second Embodiment Next, a second embodiment will be described, focusing on the differences from the first embodiment.

[0186] In the first embodiment, an example has been described in which the UE 100 (model learning entity MLE) evaluates a result of model inference, and thereby the UE 100 itself determines whether to re-learn the trained model A. In the second embodiment, an example will be described in which the UE 100 performs re-learning of the trained model A in accordance with a re-learning instruction from the model management entity MNE.

[0187] (Example of operation according to the second embodiment) Figure 19 is a diagram showing an example of operation according to the second embodiment. Figure 19 shows an example in which the model learning entity MLE is UE100 and the model management entity MNE is gNB200. In Figure 19, reception of messages etc. in UE100 may be performed by the receiving unit 110 of UE100, and transmission of messages etc. may be performed by the transmitting unit 120. Also, in Figure 19, processing or operation in UE100 may be performed by the control unit 130, and processing or operation in gNB200 may be performed by the control unit 230.

[0188] As shown in FIG. 19, steps S501 to S505 are the same operations as those in the first embodiment.

[0189] In step S601, the gNB 200 transmits a switching notification to the UE 100 to cause the UE 100 to switch from the inference mode to the learning mode. The switching notification may be a switching notification to cause the UE 100 to start re-learning the trained model A transmitted in step S501. The switching notification may include the model ID of the trained model A to be switched. The UE 100 receives the switching notification.

[0190] In step S602, in response to sending a switching notification (step S601), gNB200 turns on the model change information of the learned model A.

[0191] In step S603, in response to receiving the switching notification, the UE 100 switches to the learning mode.

[0192] In step S604, the UE 100 turns on the model change information. The UE 100 may transmit a change flag on notification indicating that the model change information has been turned on to the model management entity MNE. The change flag on notification may be transmitted using an RRC message or a new message for machine learning processing (AI / ML processing).

[0193] Thereafter, steps S512 to S516 in FIG. 18 are executed in the same manner as in the first embodiment.

[0194] (Another operation example 1 according to the second embodiment) In the second embodiment, an example in which the model management entity MNE is gNB200 is described, but the model management entity MNE may also be a core network device.

[0195] In this case, in the operation example shown in Figure 19, this can be implemented by replacing gNB200 (model management entity MNE) with a core network device. In this case, between UE100 (model learning entity MLE) and the core network device (model management entity MNE), step S601 etc. may be performed using a message available between UE100 and the core network device (for example, if the core network device is AMF300, a NAS message).

[0196] (Another operation example 2 according to the second embodiment) Furthermore, the model management entity MNE may be an OTT server device. In this case, in the operation example shown in FIG. 19, this can be implemented by replacing gNB200 (model management entity MNE) with an OTT server device. In this case, between UE100 (model learning entity MLE) and the OTT server device (model management entity MNE), step S601 and the like may be performed using messages that can be used between UE100 and the OTT server device.

[0197] (Another operation example 3 according to the second embodiment) In the second embodiment, an example has been described in which the model learning entity MLE is the UE 100, but the model learning entity MLE is not limited to the UE 100. For example, the model learning entity MLE may be the gNB 200. In this case, the model management entity MNE may be a core network device. The model management entity MNE may be an OTT server device.

[0198] When the model learning entity MLE is the gNB200 and the model management entity MNE is a core network device, in the operation example shown in Figure 19, the UE100 (model learning entity) can be read as the gNB200 and the gNB200 (model management entity) can be read as the core network device. In this case, step S601 and the like may be performed between the gNB200 and the core network device using a message (e.g., an NG message) that can be used between these devices.

[0199] Also, when the model learning entity MLE is gNB200 and the model management entity MNE is an OTT server device, in the operation example shown in Figure 17, UE100 (model learning entity) can be read as gNB200 and gNB200 (model management entity) can be read as OTT server device, and this can be implemented. In this case, step S601 and the like may be performed between the gNB200 and the OTT server device using messages that can be used between these devices.

[0200] Third Embodiment Next, a third embodiment will be described, focusing on the differences from the first and second embodiments.

[0201] In the first embodiment, an example has been described in which the model learning entity MLE evaluates an inference result and re-learns a trained model. In the second embodiment, an example has been described in which the model learning entity MLE receives a re-learning instruction from the model management entity MNE and re-learns a trained model.

[0202] In the third embodiment, an example will be described in which the model management entity MNE evaluates the inference results of model inference executed by the model learning entity MLE and causes the model learning entity MLE to re-learn the learned model.

[0203] (Example of operation according to the third embodiment) Figure 20 is a diagram showing an example of operation according to the third embodiment. Figure 20 also shows an example in which the model learning entity MLE is UE100 and the model management entity MNE is gNB200. In Figure 20, reception of messages etc. in UE100 may be performed by the receiving unit 110 of UE100, and transmission of messages etc. may be performed by the transmitting unit 120. Also, in Figure 20, processing or operation in UE100 may be performed by the control unit 130, and processing or operation in gNB200 may be performed by the control unit 230.

[0204] Steps S501 to S505 are the same as those in the first embodiment.

[0205] In step S701, UE100 transmits inference result data for the learned model A received in step S501 to gNB200. The inference result data may be transmitted using an RRC message or a new message for machine learning processing (AI / ML processing).

[0206] In step S702, the gNB 200 evaluates the inference result. The method for evaluating the inference result itself may be the same as that of the first embodiment (step S506 in FIG. 17). When evaluating the inference result by comparison with legacy operation, the gNB 200 may use operation result data from legacy operation received from another UE under the same conditions as the UE 100 (or at the same timing as the inference) as the comparison target. In the following description, it is assumed that the gNB 200 determines, as a result of the evaluation, that re-learning of the trained model A is necessary.

[0207] In step S703, gNB200 sends a switching notification to UE100 to switch from inference mode to learning mode.

[0208] Then, upon receiving the switching notification, UE100 switches to learning mode (step S704), performs model learning (i.e., re-learning) for the learned model A (step S705), and sends a learning execution notification to gNB200 (step S706).

[0209] Then, in step S707, UE100 turns on the model change information for the learned model A.

[0210] Meanwhile, in step S708, gNB200 turns on the model change information of learned model A in response to sending a switching notification (step S703).

[0211] Thereafter, steps S512 to S516 in FIG. 18 are executed in the same manner as in the first embodiment.

[0212] (Another operation example 1 according to the third embodiment) In the third embodiment, an example in which the model management entity MNE is gNB200 has been described, but the model management entity MNE may also be a core network device.

[0213] In this case, in the operation example shown in Figure 20, gNB200 (model management entity MNE) can be replaced with a core network device. In this case, between UE100 (model learning entity MLE) and the core network device (model management entity MNE), steps S701 and S703 may be performed using a message available between UE100 and the core network device (for example, if the core network device is AMF300, a NAS message).

[0214] (Another operation example 2 according to the third embodiment) Furthermore, the model management entity MNE may be an OTT server device. In this case, in the operation example shown in FIG. 20, this can be implemented by replacing gNB200 (model management entity MNE) with an OTT server device. In this case, steps S701 and S703 may be performed between UE100 (model learning entity MLE) and the OTT server device (model management entity MNE) using messages that can be used between UE100 and the OTT server device.

[0215] (Another Operation Example 3 According to the Third Embodiment) In the third embodiment, an example has been described in which the model learning entity MLE is the UE 100, but the model learning entity MLE is not limited to the UE 100. For example, the model learning entity MLE may be the gNB 200. In this case, the model management entity MNE may be a core network device. The model management entity MNE may be an OTT server device.

[0216] When the model learning entity MLE is gNB200 and the model management entity MNE is a core network device, in the operation example shown in Figure 20, UE100 (model learning entity) can be read as gNB200 and gNB200 (model management entity) can be read as a core network device, and this can be implemented. In this case, steps S701 and S703 may be performed between the gNB200 and the core network device using a message (e.g., an NG message) that can be used between these devices.

[0217] Also, when the model learning entity MLE is gNB200 and the model management entity MNE is an OTT server device, in the operation example shown in Figure 20, UE100 (model learning entity) can be read as gNB200 and gNB200 (model management entity) can be read as OTT server device, and this can be implemented. In this case, steps S701 and S703 may be performed between the gNB200 and the OTT server device using messages that can be used between these devices.

[0218] [Other Embodiments] In the first to third embodiments described above, a trained AI / ML model has been described as the target of timing information, but this is not limited thereto. For example, the target of timing information may be an untrained AI / ML model. In this case, for example, in the operation example of FIG. 17 , steps S504 to S506 are not performed (model inference is not performed for the untrained AI / ML model), and model learning is performed in the learning mode in UE 100 (steps S507 and S508). Thereafter, the operation examples shown in FIGS. 17 and 18 are implemented. The same applies to FIGS. 18 and 19 .

[0219] Although the first to third embodiments have been described mainly in terms of supervised learning, the present invention is not limited to this. For example, unsupervised learning or reinforcement learning may be applied to the first to third embodiments.

[0220] The above-described operational flows are not limited to being implemented independently, but can also 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.

[0221] In the above-described embodiments and examples, 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.

[0222] That is, the UE 100 may be a terminal function unit (a type of communication module) for a base station to control a repeater that relays signals. Such a terminal function unit is referred to as an MT. Examples of the MT include, in addition to the IAB-MT, an NCR (Network Controlled Repeater)-MT and a RIS (Reconfigurable Intelligent Surface)-MT.

[0223] 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.

[0224] Furthermore, a program (e.g., an information processing program) that causes a computer to execute each process or function according to the above-described embodiments may be provided. Alternatively, a program (e.g., a mobile communication program) that causes the mobile communication system 1 to execute each process or function according to the above-described embodiments may be provided. The program may be recorded on a computer-readable medium. Using a computer-readable medium, the program can be installed on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or DVD-ROM. Such a recording medium may be memory included in the UE 100 and the gNB 200. Furthermore, circuits that execute each process performed by the UE 100 or the gNB 200 may be integrated, and at least a portion of the UE 100 or the gNB 200 may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0225] The functions performed by the UE 100 or the gNB 200 (network node) may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (Central Processing Units), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and 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 memory. In this specification, circuitry, unit, or means refers to hardware that is programmed to perform the described functions or hardware that executes them. 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 hardware and software used to configure the hardware and / or processor.

[0226] 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.

[0227] 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 without departing from the spirit of the invention. Furthermore, it is also possible to combine the embodiments, operation examples, or processes within a consistent range.

[0228] This application claims priority from Japanese Patent Application No. 2023-078830 (filed May 11, 2023), the entire contents of which are incorporated herein by reference.

[0229] (Supplementary Note) (Supplementary Note 1) A communication control method in a mobile communication system (e.g., mobile communication system 1), comprising the steps of: a model management entity (e.g., gNB200) transmitting timing information indicating the timing of execution of a predetermined operation to a model learning entity (e.g., UE100); and the model learning entity executing the predetermined operation at the execution timing, wherein the predetermined operation is at least one of transmitting model learning history information indicating a history of model learning performed on a first AI / ML model to the model management entity, transmitting a second AI / ML model after model learning has been performed on the first AI / ML model to the model management entity, and updating model identification information that identifies the second AI / ML model.

[0230] (Supplementary Note 2) The communication control method according to Supplementary Note 1, wherein the first AI / ML model is a trained AI / ML model.

[0231] (Supplementary Note 3) The communication control method according to Supplementary Note 1 or Supplementary Note 2, further comprising a step of turning on model change information indicating whether or not the model learning has been performed when the model learning entity has performed model learning on the first AI / ML model.

[0232] (Supplementary Note 4) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 3, wherein the model learning entity is a user device, and the model management entity is any one of a network node, a core network device, and an OTT (Over The Top) server device.

[0233] (Supplementary Note 5) A user device (e.g., UE100) having a receiver (e.g., receiver 110) that receives timing information indicating the timing of execution of a predetermined operation transmitted from a model management entity (e.g., gNB200), and a control unit (e.g., control unit 130) that executes the predetermined operation at the execution timing, wherein the predetermined operation is at least one of transmitting model learning history information indicating a history of model learning performed on a first AI / ML model to the model management entity, transmitting a second AI / ML model after model learning has been performed on the first AI / ML model to the model management entity, and updating model identification information that identifies the second AI / ML model.

[0234] 1: Mobile communication system 20: 5GC (CN) 100: UE 110: Receiving unit 120: Transmitting unit 130: Control unit 200: gNB 210: Transmitting unit 220: Receiving unit 230: Control unit A1: Data collection unit A2: Model learning unit A3: Model inference unit A4: Data processing unit TE: Transmitting entity RE: Receiving entity MLE: Model learning entity MNE: Model management entity

Claims

1. A communication control method in a mobile communication system, comprising: a model management entity transmitting timing information indicating a timing for executing a predetermined operation to a model learning entity; and the model learning entity executing the predetermined operation at the execution timing, wherein the predetermined operation is at least one of transmitting model learning history information indicating a history of model learning performed on a first AI (Artificial Intelligence) / ML (Machine Learning) model to the model management entity, transmitting a second AI / ML model after model learning has been performed on the first AI / ML model to the model management entity, and updating model identification information for identifying the second AI / ML model.

2. The communication control method according to claim 1, wherein the first AI / ML model is a trained AI / ML model.

3. The communication control method according to claim 1, further comprising: when the model learning entity performs model learning on the first AI / ML model, turning on model change information indicating whether the model learning has been performed.

4. The communication control method according to claim 1, wherein the model learning entity is a user equipment, and the model management entity is any one of a network node, a core network device, and an OTT (Over The Top) server device.

5. A user device having a receiving unit that receives timing information transmitted from a model management entity indicating the timing of execution of a specified operation, and a control unit that executes the specified operation at the execution timing, wherein the specified operation is at least one of: transmitting model learning history information indicating a history of model learning performed on a first AI / ML model to the model management entity, transmitting a second AI / ML model after model learning has been performed on the first AI / ML model to the model management entity, and updating model identification information that identifies the second AI / ML model.

Citation Information

Patent Citations

  • Method for updating machine learning model and communication device

    CN114091679A

  • Cloud server, edge server, and method of generating intelligence model using the same

    JP2023031238A

Cited By

  • Method and apparatus for acquiring model operation result

    WO2026149180A1