Communication control method and network device

Abstract

A communication control method according to one aspect of the present invention is used for a mobile communication system. The communication control method includes a step in which a network device transmits registration condition information indicating a registration condition of an artificial intelligence (AI) / machine learning (ML) model to a user device.

Description

Communication control method and network device

[0001] The present disclosure relates to a communication control method and a network 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) of mobile communication systems.

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

[0004] A communication control method according to a first aspect is a communication control method in a mobile communication system, the communication control method including a step of transmitting, by a network device, registration condition information indicating registration conditions of an AI / ML model to a user device.

[0005] A network device according to a second aspect is a network device in a mobile communication system, the network device having a transmission unit that transmits registration condition information indicating registration conditions of an AI / ML model to a user device.

[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 AI / ML technology according to the first embodiment. FIG. 7 is a diagram showing an example of operation in AI / ML technology according to the first embodiment. FIG. 8 is a diagram showing an example of the arrangement of functional blocks of AI / ML technology according to the first embodiment. FIG. 9 is a diagram showing an example of operation 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 a setting message according to the first embodiment. FIG. 12 is a diagram showing an example of operation according to the first embodiment. FIG. 13 is a diagram showing an example of operation according to the first embodiment.

[0007] The present disclosure aims to enable network devices to properly register AI / ML models.

[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. Furthermore, devices included in the core network CN may be referred to as core network devices.

[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 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 UPF 300 may be core network devices included in the CN 20. The core network device and the gNB 200 may be collectively referred to as a network device.

[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. Alternatively, the gNB 200 may be an example of a network node.

[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 (Data Collection) A1, a model training unit (Model Training) A2, a model inference unit (Inference) A3, a management unit (Management) A5, and a model storage unit (Model Storage) A6.

[0039] The functional block configuration example shown in FIG. 6 represents a functional framework of a general AI / ML technology. Therefore, depending on a hypothetical use case, some of the functional block configuration example (e.g., model recording unit A6, etc.) may not be included in the functional block configuration example. The functional block configuration example shown in FIG. 6 may also be distributed between the UE 100 and a network-side device. Alternatively, some functions of the functional block configuration example (e.g., model learning unit A2 or model inference unit A3, etc.) may be located in both the UE 100 and the network-side device.

[0040] The data collection unit A1 provides input data to the model learning unit A2, the model inference unit A3, and the management unit A5. The input data includes training data for the model learning unit A2, inference data for the model inference unit A3, and monitoring data for the management unit A5.

[0041] The training data is data required as input when the AI / ML model is learning. The inference data is data required as input when the AI / ML model is inferring. The monitoring data is data required as input when the AI / ML model is managing.

[0042] In addition, data collection may refer to the process of collecting data at a network node, a management entity, or a UE 100, for example, to train an AI / ML model, manage an AI / ML model, and perform inference on an AI / ML model.

[0043] The model learning unit A2 performs AI / ML model training, AI / ML model validation, and AI / ML model testing.

[0044] AI / ML model learning is the process of learning an AI / ML model from input / output relationships to obtain a trained AI / ML model to be used for inference. For example, considering y = ax + b, AI / ML model learning may be the process of optimizing a (slope) and b (intercept) by providing input (x) and output (y) (i.e., providing learning data).

[0045] Generally, machine learning includes supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data as training data. Unsupervised learning is a method that does not use correct answer data as training data. For example, unsupervised learning memorizes feature points from a large amount of training data and determines the correct answer (estimates the range). Reinforcement learning is a method that assigns a score to the output result and learns how to maximize the score. Although supervised learning will be described below, either unsupervised learning or reinforcement learning may be applied as machine learning.

[0046] The model learning unit A2 outputs a trained AI / ML model (Trained Model) obtained by AI / ML model learning to the model recording unit A6, and also outputs an updated AI / ML model (Updated Model) obtained by relearning the trained AI / ML model to the model recording unit A6.

[0047] In the following, AI / ML model learning may be referred to as "model learning" or "learning."

[0048] The model inference unit A3 performs AI / ML model inference. Specifically, the model inference unit A3 applies the inference data provided by the data collection unit A1 to the trained AI / ML model (or updated AI / ML model) to obtain inference output data. For example, in the equation y = ax + b, x corresponds to the inference data and y corresponds to the inference output data. Note that "y = ax + b" is an AI / ML model. A model with optimized slope and intercept, for example, "y = 5x + 3," is a trained AI / ML model. There are various model approaches, including linear regression analysis, neural networks, and decision tree analysis. The above "y = ax + b" can also be considered a type of linear regression analysis.

[0049] The model inference unit A3 outputs inference output data to the management unit A5. The model inference unit A3 also receives management instructions from the management unit A5. For example, the management instructions include selection of an AI / ML model, activation (deactivation) of an AI / ML model, switching of an AI / ML model, and fallback (performing inference without using an AI / ML model). The model inference unit A3 performs model inference in accordance with the management instructions.

[0050] Note that AI / ML model inference is, for example, a process of obtaining a set of outputs from a set of inputs using a trained AI / ML model (or an updated AI / ML model). Alternatively, model inference may be a process of obtaining inference output data from inference data using a trained AI / ML model (or an updated AI / ML model). Hereinafter, AI / ML model inference may be referred to as "model inference" or "inference."

[0051] In the following, an AI / ML model that is currently being trained (or updated) may be referred to as a training AI / ML model (or an updating AI / ML model). In the following, when there is no need to distinguish between a training (or updating) AI / ML model and a trained (or updated) AI / ML model, they may be simply referred to as an "AI / ML model."

[0052] The management unit A5 supervises operations on the AI / ML model (selection, activation, deactivation, switching, fallback, etc.). The management unit A5 also supervises monitoring of the AI / ML model. The management unit A5 can also perform operations to ensure appropriate inference operations based on monitoring data and inference output data. To this end, the management unit A5 outputs a model transfer and / or model delivery request (Model Transfer / Delivery Request) to the model recording unit A6, and causes the trained (or updated) AI / ML model recorded in the model recording unit A6 to be output to the model inference unit A3. The management unit A5 also outputs management instructions to the model inference unit A3 and supervises operations on the AI / ML model. Furthermore, the management unit A5 can output performance feedback and a re-learning request to the model learning unit A2, causing the model learning unit A2 to re-learn the AI / ML model (i.e., update the learned AI / ML model).

[0053] FIG. 7 is a diagram illustrating an example of operation in the AI / ML technique according to the first embodiment.

[0054] In Fig. 7, the transmitting entity TE is an entity capable of performing model inference and transmitting inference output data to the receiving entity RE. Meanwhile, the receiving entity RE is an entity capable of receiving inference output data from the transmitting entity TE. Model training may be performed in the transmitting entity TE. The model training may also be performed in the receiving entity RE. If the model training is performed in the receiving entity RE, the trained AI / ML model may be transmitted from the receiving entity RE to the transmitting entity TE.

[0055] Note that an entity may be, for example, a device, a functional block included in a device, or a hardware block included in a device.

[0056] 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.

[0057] As shown in Fig. 7 , in step S1, the transmitting entity TE transmits control data related to AI / ML technology to the 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 downlink signaling may be broadcast signaling. The control data may be a control message in a control layer (e.g., an AI / ML layer) dedicated to artificial intelligence or machine learning. Alternatively, the control data may be a NAS message in the NAS layer. The control data may include a performance feedback request and / or a re-learning request transmitted from the management unit A5 to the model learning unit A2. Alternatively, the control data may include a model transfer request and / or a model delivery request sent from the management unit A5 to the model recording unit A6, or a management instruction sent from the management unit A5 to the model inference unit A3.

[0058] (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.

[0059] For example, there are three use cases in which AI / ML technology is applied:

[0060] (X1.1) "CSI (Channel State Information) Feedback Enhancement"

[0061] (X1.2) "Beam management"

[0062] (X1.3) “Positioning accuracy enhancement”

[0063] (X1.1) Example of functional block arrangement in "CSI feedback improvement" "CSI feedback improvement" represents a use case in which AI / ML technology is applied to CSI fed back from UE100 to gNB200, for example. 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.

[0064] 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.

[0065] 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).

[0066] 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.

[0067] 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).

[0068] 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.

[0069] 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.

[0070] 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.

[0071] FIG. 9 is a diagram illustrating an example of operation in "CSI feedback improvement" according to the first embodiment.

[0072] 9, in step S10, 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.

[0073] In step S11, gNB200 may send a switching notification to UE100 to start learning mode.

[0074] In step S12, the UE 100 starts a learning mode.

[0075] In step S13, 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 uses the full CSI-RS and the CSI as learning data to create a learned AI / ML model.

[0076] In step S14, UE100 transmits the generated CSI to gNB200.

[0077] Thereafter, in step S15, 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.

[0078] In step S16, in response to receiving the completion notification, gNB200 sends a switching notification to UE100 to switch UE100 from learning mode to inference mode.

[0079] In step S17, in response to receiving the switching notification, the UE 100 switches from the learning mode to the inference mode.

[0080] In step S18, 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.

[0081] In step S19, 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.

[0082] In addition, in step S20, if UE100 determines that model learning is necessary, it may send a notification indicating that model learning is necessary to gNB200 as control data.

[0083] In the example shown in Fig. 9, an example has been described in which 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".

[0084] 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:

[0085] (Y1) 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 or other received signals received from gNB200).

[0086] (Y2) 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.)

[0087] (Y3) 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 (Y1) to (Y3). 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 (Y1) to (Y3). 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.

[0088] An example of the arrangement of functional blocks in (X1.1) "CSI feedback" has been described above. The above-mentioned arrangement example is just one example, and in 3GPP, the arrangement example of functional blocks is still in the process of being studied. Similarly, (X1.2) "Beam management" and (X1.3) "Position accuracy improvement" are also still in the process of being studied.

[0089] (X1.4) Example of Model Transfer Next, we will explain the transfer of an AI / ML model (Model Transfer). Note that the terms "transfer of an AI / ML model" and "delivery of an AI / ML model" have the same meaning.

[0090] (X1.4.1) First operation pattern related to model forwarding Figure 10 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 10, the receiving entity RE will be described as mainly being the UE 100, but the receiving entity RE may be the gNB 200 or the AMF 300. Also, in the example shown in Figure 10, the transmitting entity TE will be described as being the gNB 200, but the transmitting entity TE may be the UE 100 or the AMF 300.

[0091] 10, in step S25, the gNB 200 transmits a capability inquiry message to the UE 100 to request transmission of a message including an information element (IE) indicating the execution capability for the learning process. The UE 100 receives the capability inquiry message. However, the gNB 200 may transmit the capability inquiry message when it executes the learning process (when it determines that it will execute the learning process).

[0092] In step S26, the UE 100 transmits to the gNB 200 a message including an information element indicating execution capabilities for the learning process (in another respect, the execution environment for the learning process). 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 is defined for performing or controlling the learning process (AI / ML process), the message may be a message of the new layer.

[0093] The information element indicating the execution capability related to the learning process may be an information element indicating the capability of a processor for executing the learning process and / or an information element indicating the capability of a memory for executing the 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.

[0094] Alternatively, the information element indicating the execution capability of the learning process may be an information element indicating the execution capability of the inference process (model inference). Specifically, the information element indicating the execution capability of the inference process 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 process.

[0095] Alternatively, the information element indicating the execution capability related to the 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.

[0096] In step S27, gNB200 determines the model to be configured (or deployed) in UE100 based on the information elements contained in the message received in step S26.

[0097] In step S28, gNB200 transmits a message including the model determined in step S27 to UE100. UE100 receives the message and performs a learning process (i.e., a model learning process and / or a model inference process) using the model included in the message. A specific example of step S28 will be described in the following second operation pattern.

[0098] (X1.4.2) Second Operation Pattern Related to Model Transfer FIG. 11 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.

[0099] In the example of FIG. 11, 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.

[0100] 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.

[0101] 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.

[0102] (Model Identification According to First Embodiment) Next, model identification according to the first embodiment will be described.

[0103] Currently, 3GPP is discussing model identification of AI / ML models. For example, in the framework shown in FIG. 6 , model identification may be performed during model training. Specifically, model identification may be performed in UE 100 (or a network device) when it is determined to which AI / ML model training data corresponds. Alternatively, model identification may be performed during model inference. Specifically, model identification may be performed in UE 100 (or a network device) when it is determined to which AI / ML model inference data corresponds. Alternatively, model identification may be performed during management. Specifically, model identification may be performed in UE 100 (or a network device) when it is determined to which AI / ML model training data corresponds.

[0104] In 3GPP, model identification is classified into two types, Type A and Type B. Type A is, for example, a type in which model identification is performed without using signaling between the UE 100 and the network device. On the other hand, Type B is, for example, a type in which model identification is performed via signaling.

[0105] In addition, 3GPP classifies Type B model identification into the following three options.

[0106] (Option 1) Model identification accompanying data collection settings and / or instructions

[0107] (Option 2) Model identification accompanying dataset transmission

[0108] (Option 3) Model Identification in Model Transfer from Network to UE 100 In the first embodiment, the description will be focused on (Option 2). Note that there are also the following options 4 and 5, but they have not yet been agreed upon in 3GPP.

[0109] (Option 4) Model identification via reference model

[0110] (Option 5) Model Identification via Model Monitoring

[0111] (Communication Control Method According to First Embodiment) In the first embodiment, model identification via model monitoring (Option 5) will be described. Here, a specific use case of Option 5 will be described.

[0112] Fig. 12 is a diagram illustrating an example of an operation of a use case according to the first embodiment. The example of operation shown in Fig. 12 is based on the 3GPP contribution "R1-2401435."

[0113] In the following, a device or entity included in the core network (5GC20) in the mobile communication system 1 may be referred to as a "core network device." Also, in the following, in the mobile communication system 1, the gNB200 and the core network device may be referred to as a "network device." The network device may be an LPP (LTE Positioning Protocol) server or an OAM (Operations, Administration and Maintenance) server. Furthermore, the network device and the UE100 may be referred to as a "node." The node may be the UE100 or a core network device.

[0114] As shown in FIG. 12, in step S30, the gNB 200 holds a codebook #1 and a codebook #2. The codebook represents, for example, candidates for precoding matrices that the UE 100 uses for uplink transmission. The gNB 200 indicates a precoding matrix using DCI (Downlink Control Information), and the UE 100 selects a precoding matrix from the codebook. The UE 100 can transmit a beam in a specific direction using the selected precoding matrix. Note that the UE 100 does not hold the codebook #1 or the codebook #2.

[0115] In step S31, the control unit 130 of the UE 100 generates four trained AI / ML models. For example, the control unit 130 generates each trained AI / ML model based on a virtual beam shape from the gNB 200. Here, it is assumed that, of the four trained AI / ML models, trained AI / ML model #1 happens to work well with codebook #1, and trained AI / ML model #2 happens to work well with codebook #2. The network device is unaware of the existence of the four trained AI / ML models. The model numbers "trained AI / ML model #1" to "trained AI / ML model #4" are used to identify the trained AI / ML models within the UE 100.

[0116] In step S32, the control unit 130 of the UE 100 evaluates the performance of the four trained AI / ML models. This performance evaluation corresponds to model management (A5) in the functional framework shown in FIG. 7. The control unit 130 may perform this performance evaluation by performing model inference on the four trained AI / ML models. At this time, it is assumed that the gNB 200 is operating under certain additional conditions (e.g., using codebook #1). For example, the transmitter 210 of the gNB 200 transmits a beam using codebook #1. In other words, this performance evaluation is performed under the additional conditions in the gNB 200. However, the UE 100 is unaware of these additional conditions. Here, it is assumed that under these additional conditions, the UE 100 evaluates that the AI / ML model #4 has the best performance.

[0117] In step S33, the transmitter 120 of the UE 100 transmits to the gNB 200 information indicating that the UE 100 holds a trained AI / ML model that operates reasonably well (under specific conditions unknown to the UE 100). Information indicating that a specific trained AI / ML model is held may be referred to as "model holding information" hereinafter. The receiver 220 of the gNB 200 receives the model holding information.

[0118] In step S34, the control unit 230 of the gNB 200 assigns a model ID in response to receiving the model holding information.

[0119] In step S35, the transmitter 210 of the gNB 200 transmits the model ID to the UE 100.

[0120] In step S36, the control unit 230 of the gNB 200 associates the model ID with the additional condition (e.g., codebook #1) and registers it in the memory. By this registration, for example, when the additional condition is used thereafter, the control unit 230 of the gNB 200 can set the memory ID for the UE 100.

[0121] In step S37, the transmitter 210 of the gNB 200 instructs the UE 100 to perform an LCM operation including the model ID. The LCM operation may be an inference instruction for the learned AI / ML model indicated by the model ID.

[0122] The use cases described above have the following problems:

[0123] First, when multiple UEs 100 simultaneously transmit model holding information, the gNB 200 may not be able to properly perform the registration process (step S36). This is because the gNB 200 may experience delays in the registration process if the number of received model holding information exceeds a certain level.

[0124] Second, if the performance of the trained AI / ML model generated by UE100 is the same as the performance of the trained AI / ML model generated by another UE, the generation of the trained AI / ML model (or model inference) by the UE100 may be redundant. In the use case shown in FIG. 12, if a trained AI / ML model with the same performance as the trained AI / ML model #4 generated by UE100 has already been generated by another UE, the generation of trained AI / ML model #4 by UE100 may be wasted. In this case, in the use case shown in FIG. 12, the gNB200 receives model retention information (step S33), and registers the model ID of the trained AI / ML model with the same performance (step S36), and the registration process itself may also be wasted.

[0125] Therefore, the first embodiment aims to appropriately register an AI / ML model in a network device.

[0126] Therefore, in the first embodiment, a network device (e.g., gNB200) transmits registration condition information indicating the registration conditions of the AI / ML model to a user device (e.g., UE100).

[0127] In the above example, even if trained AI / ML model #1 has the highest performance, UE 100 does not transmit model retention information if the trained AI / ML model does not satisfy the registration conditions indicated in the registration condition information. On the other hand, UE 100 transmits model retention information if trained AI / ML model #1 has the highest performance and satisfies the registration conditions. Therefore, the network device registers trained AI / ML models that satisfy the registration conditions and does not register trained AI / ML models that do not satisfy the registration conditions, making it possible to properly register trained AI / ML models.

[0128] In addition, since the model retention information sent from UE100 is also sent when the registration conditions are met, it is also possible to limit the number of model retention information sent to a certain number or less, and registration on the network device side can also be performed appropriately.

[0129] Furthermore, for example, the network device may include the performance of an already registered trained AI / ML model in the registration condition information, so that even if the UE 100 generates a trained AI / ML model with the same performance, the UE 100 will not transmit model retention information if the trained AI / ML model has already been registered. This allows the network device to properly register the trained AI / ML model without wasting the registration process.

[0130] In the following, when there is no need to distinguish between a trained AI / ML model and an AI / ML model currently being trained, they may be referred to as "AI / ML model."

[0131] (Example of Operation According to First Embodiment) Next, an example of operation according to the first embodiment will be described.

[0132] FIG. 13 is a diagram illustrating an example of operation according to the first embodiment.

[0133] Steps S40 to S42 shown in Fig. 13 are the same as steps S30 to S32 shown in Fig. 12. Also, when performance evaluation is performed in UE 100, it is performed under additional conditions in the network device, which is the same as the use case of Fig. 12, and the UE 100 is unaware of these additional conditions, which is the same as the use case of Fig. 12. Furthermore, the model numbers of the four AI / ML models generated by UE 100 are also used inside UE 100, and the network device is unaware of these model numbers, which is the same as the use case of Fig. 12.

[0134] In step S43, the transmission unit of the network device transmits the registration condition information to the UE 100. The registration condition information is information indicating the registration conditions of the AI / ML model.

[0135] First, the registration condition information may include at least any of the following information: The information is included in the registration condition information as a registration condition.

[0136] (B1) Information about performance: Performance may be expressed by an evaluation index such as a key performance indicator (KPI). Specifically, it may be expressed by inference accuracy (%), normalized mean square error (NMSE), or the like.

[0137] (B2) Development history or learning (training) history

[0138] (B3) Signaling information or technical conditions used in the AI / ML model (e.g., Codebook #1 or Codebook #2)

[0139] (B4) Geographical conditions and / or temporal conditions: Geographical conditions may be expressed by latitude, longitude, and altitude, or may be expressed by PCI (Physical Cell ID), RA (Registration Area)-ID, PLMN (Public Land Mobile Network)-ID, etc. Temporal conditions may be expressed by date and time.

[0140] (B5) AI / ML model size

[0141] (B6) Computing power required to execute the AI / ML model: This may be expressed, for example, in CPU clock frequency or MIPS (Million Instructions Per Second).

[0142] (B7) Model format (open format, proprietary format, or type of standard library)

[0143] (B8) Registration deadline (e.g., registration is possible until March 31, 2024)

[0144] (B9) Designation of reference model (the AI / ML model indicated by the model ID becomes the reference model)

[0145] Second, the registration condition information may include registered list information indicating AI / ML models currently registered by the network device. By preventing the UE 100 from transmitting model retention information for AI / ML models indicated in the registered list information, the network device can prevent duplicate registration of AI / ML models. The registered list information may include a registered model ID. Alternatively, the registered list information may include an address of storage in which the AI / ML model is stored. Alternatively, the registered list information may include at least one of the information (B1) to (B9) described above. The registered list information may be list information of AI / ML models for which transmission of model retention information is not permitted.

[0146] The receiving unit 110 of the UE 100 receives the registration condition information. The control unit 130 of the UE 100 determines, based on the registration condition information, to transmit the model retention information when it holds (or has generated) an AI / ML model that satisfies the registration conditions indicated in the registration condition information. On the other hand, the control unit 130 determines not to transmit the model retention information when the held AI / ML model does not satisfy the registration conditions. The following description will be given assuming that it has decided to transmit the model retention information.

[0147] In addition, since the UE 100 determines whether or not it holds an AI / ML model that satisfies the registration conditions and individually identifies the AI / ML model, it may be considered that model identification is performed at this stage. The identification of the AI / ML model that is performed when determining whether or not the AI / ML model satisfies the registration conditions may be the model identification according to the first embodiment.

[0148] In step S44, the transmission unit 120 of the UE 100 transmits the model holding information.

[0149] In step S45, the control unit of the network device assigns a model ID in response to receiving the model storage information.

[0150] In step S46, the transmission unit of the network device transmits the model ID to the UE 100. At that time, the transmission unit of the network device may transmit registration possibility information to the UE 100.

[0151] First, the registration information may include any of information indicating that registration has been made, information indicating that registration has not been made, and information indicating that registration has been suspended. If the registration information includes information indicating that registration has not been made, the reason for not registering may also be included. Furthermore, if the registration information includes information indicating that registration has been suspended, the reason for suspension of registration may also be included.

[0152] Second, if the network device receives the model retention information (step S44) but does not perform registration, re-registration condition information may be included in the registration availability information. The re-registration condition information is, for example, information indicating the conditions for re-registering the model ID and additional conditions (step S47) in the network device. The re-registration condition information may be represented by any of the information (B1) to (B9) described above. The re-registration condition information may also include a re-registration deadline (for example, re-registration is permitted until March 31, 2024).

[0153] Third, if the network device receives the model retention information (step S44) but does not register the model, model transmission request information may be included in the registration permission information. The model transmission request information is, for example, information that requests (or requires) UE 100 to transmit an AI / ML model. The model transmission request information enables the network device to acquire the AI / ML model and transmit (or deploy) the AI / ML model to another UE. The model transmission request information may include information indicating the transmission destination (destination) of the AI / ML model. The transmission destination may be the network device itself. The transmission destination may also be another network device. The transmission destination may be specified by an HTTP address. The model transmission request information may include a transmission deadline for the AI / ML model.

[0154] The registration permission information may include a model ID. In this case, it may indicate that registration of the model ID is permitted. On the other hand, if the registration permission information does not include a model ID, it may (implicitly) indicate that registration of the AI / ML model was not performed.

[0155] In step S47, the control unit of the network device associates the model ID with the additional condition and registers them in memory. By registering the model ID, it may be considered that the AI / ML model has been registered in the network device.

[0156] Step S48 is the same as step S37 in FIG.

[0157] (Another operation example according to the first embodiment) Control data ( FIG. 7 ) may be used for transmission between the UE 100 and the network device. For the transmission, a new message according to a protocol newly defined for AI / ML (AI / ML protocol) may be used.

[0158] [Other Embodiments] In the first embodiment described above, supervised learning has been mainly described, but the present invention is not limited to this. For example, unsupervised learning or reinforcement learning may be applied to the first embodiment.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] A program may be provided that causes a computer to execute each process performed by the UE 100, the gNB 200, or the network device 400. 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 and / or a DVD-ROM. Furthermore, circuits that execute each process performed by the UE 100, the gNB 200, or the network device 400 may be integrated, and at least a portion of the UE 100, the gNB 200, or the network device 400 may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0164] 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.

[0165] The functions performed by the UE 100 or base station 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), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and / or other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes a program stored in a memory.

[0166] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0167] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or processor.

[0168] Although one embodiment has been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes can be made within the scope of the gist. Furthermore, the embodiments, operation examples, and processes can be appropriately combined within the scope of not being inconsistent.

[0169] This application claims priority from Japanese Patent Application No. 2024-061017 (filed April 4, 2024), the entire contents of which are incorporated herein by reference.

[0170] (Addendum) The above can be summarized as follows.

[0171] (Supplementary Note 1) A communication control method in a mobile communication system, comprising: a step in which a network device transmits, to a user device, registration condition information indicating a registration condition of an AI / ML model.

[0172] (Supplementary Note 2) The communication control method according to Supplementary Note 1, wherein the registration condition information includes registered list information indicating AI / ML models registered by the network device.

[0173] (Supplementary Note 3) The communication control method according to Supplementary Note 1 or Supplementary Note 2, further comprising the step of receiving, from the user device, model retention information indicating that the network device has the AI / ML model that satisfies the registration condition.

[0174] (Supplementary Note 4) The communication control method according to any one of Supplementary Note 1 to Supplementary Note 3, further comprising a step in which the network device, in response to receiving the model retention information, transmits registration permission information indicating whether or not to permit registration of the AI / ML model to the user device.

[0175] (Supplementary Note 5) A network device in a mobile communication system, comprising: a transmitter that transmits registration condition information indicating a registration condition of an AI / ML model to a user device.

[0176] 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 250: Backhaul communication unit 400: Network device

Claims

1. A communication control method in a mobile communication system, comprising: a network device transmitting, to a user device, registration condition information indicating registration conditions for an AI (Artificial Intelligence) / ML (Machine Learning) model.

2. The communication control method according to claim 1, wherein the registration condition information includes registered list information indicating AI / ML models registered by the network device.

3. The communication control method according to claim 1, further comprising receiving, from the user device, model retention information indicating that the network device has the AI / ML model that satisfies the registration conditions.

4. The communication control method according to claim 3, further comprising the network device transmitting registration permission information indicating whether or not to permit registration of the AI / ML model to the user device in response to receiving the model retention information.

5. A network device in a mobile communication system, comprising: a transmitting unit that transmits registration condition information indicating the registration conditions of an AI / ML model to a user device.

Images