Communication control method and network device

Abstract

One aspect provides a communication control method in a mobile communication system. The communication control method includes a step in which a network device transmits, to a user equipment, an AI / ML model that can be used under a predetermined condition and deletion restriction information indicating that the AI / ML model should not be deleted, before the predetermined condition is generated. In addition, the communication control method includes a step in which the user equipment uses the AI / ML model under the predetermined condition without deleting the AI / ML model according to the deletion restriction information. Here, the predetermined condition is either the occurrence of congestion in a data communication path for the user equipment, the transmission of an emergency call by the user equipment, or the reception of a message related to a public warning system (PWS) by the user equipment.

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] 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 network device transmits, to a user equipment before the predetermined condition occurs, an AI / ML model that can be used under a predetermined condition and deletion prohibition information indicating that the AI / ML model should not be deleted. The communication control method also includes a step in which the user equipment uses the AI / ML model under the predetermined condition without deleting the AI / ML model in accordance with the deletion prohibition information. Here, the predetermined condition is any one of congestion occurring in a data communication path of the user equipment, the user equipment transmitting an emergency call, and the user equipment receiving a message related to a public warning system (PWS).

[0005] A network device according to a second aspect is a network device in a mobile communication system, and includes a transmitter configured to transmit, to a user equipment (UE) before the occurrence of a predetermined condition, an AI / ML model that can be used under the predetermined condition and deletion prohibition information indicating that the AI / ML model should not be deleted, where the predetermined condition is one of congestion occurring in a data communication path of the UE, transmitting an emergency call from the UE, and receiving a message related to a public warning system (PWS) from the UE.

[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 the AI / ML technology according to the first embodiment. FIG. 8 is a diagram showing an example of the layout of functional blocks of the 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 the layout of functional blocks of the AI / ML technology according to the first embodiment. FIG. 11 is a diagram showing an example of the layout of functional blocks of the AI / ML technology according to the first embodiment. FIG. 12 is a diagram showing an example of the layout of functional blocks of the AI / ML technology according to the first embodiment. FIG. 13 is a diagram showing an example of operation according to the first embodiment. FIG. 14 is a diagram showing an example of a setting message according to the first embodiment. Fig. 15 is a diagram showing an example of the configuration of functional blocks of the AI / ML technology according to the first embodiment. Fig. 16 is a diagram showing an example of operation according to the first embodiment. Fig. 17 is a diagram showing another example of operation according to the first embodiment.

[0007] The present disclosure aims to prevent a user device from deleting an AI / ML model.

[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), 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 types of reception 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 can transmit 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 can receive inference result data transmitted from the transmitting entity TE. The receiving entity RE performs various processes using the inference result data. The receiving entity RE may perform machine learning to derive a trained model. In this case, the receiving entity RE transmits the derived trained model to the transmitting entity TE.

[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, 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., AI / ML layer) dedicated to 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] FIG. 9 is a diagram illustrating an example of operation in "CSI feedback improvement" according to the first embodiment.

[0063] 9, 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.

[0064] In step S102, gNB200 may send a switching notification to UE100 to start learning mode.

[0065] In step S103, the UE 100 starts the learning mode.

[0066] 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.

[0067] In step S105, UE100 transmits the generated CSI to gNB200.

[0068] 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.

[0069] 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.

[0070] In step S108, in response to receiving the switching notification, the UE 100 switches from the learning mode to the inference mode.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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".

[0075] 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:

[0076] (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.)

[0077] (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.)

[0078] (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.

[0079] (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.

[0080] 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.

[0081] Figure 10 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 10, 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 10 shows an example in which model learning and model inference are performed in UE100. Figure 10 shows an example in which the transmitting entity TE is UE100 and the receiving entity RE is gNB200.

[0082] As shown in FIG. 10, 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 of 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."

[0083] An example of the operation in "beam management" can be implemented by replacing "CSI feedback" with "optimal beam" in FIG.

[0084] 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.

[0085] 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.

[0086] 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:

[0087] (Y1) SSB (Synchronization Signal Block) received from gNB200

[0088] (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.)

[0089] (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.)

[0090] (Y4) Number of beams or beam pattern

[0091] (Y5) Beam measurement value(s)

[0092] (Y6) The movement speed of UE100 (which 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.

[0093] (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.

[0094] 11 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 FIG. 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 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, FIG. 11 shows an example in which model learning and model inference are performed in the UE 100. FIG. 11 shows an example in which the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200.

[0095] As shown in FIG. 11 , 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.

[0096] Note that the gNB 200 transmits the full PRS using a predetermined amount of first resources (for example, all antenna ports or a predetermined amount of time-frequency resources), similar to the full CSI-RS. Also, the gNB 200 transmits the partial PRS using second resources (for example, half the antenna ports in an antenna panel, or half the predetermined amount of time-frequency resources) that have a smaller amount of resources than the first resources, similar to the partial CSI-RS.

[0097] 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.

[0098] 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 9.

[0099] 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.

[0100] 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.

[0101] 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:

[0102] (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.)

[0103] (Z2) LOS (Line of Sight) or NLOS (Non Line of Sight)

[0104] (Z3) Measurement timing, accuracy, likelihood

[0105] (Z4) RF Fingerprint (Cell ID and reception quality in the cell of the cell ID)

[0106] (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

[0107] (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)

[0108] (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). The capability information may include any of the information or data from (Z1) to (Z7), separating the learning data and the 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), separating the learning data and the inference data.

[0109] (1.4) Other Arrangement Examples Next, other arrangement examples will be described.

[0110] Fig. 12 is a diagram showing another example of the arrangement of "CSI feedback improvement" according to the first embodiment. Fig. 12 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. 12 shows an example in which model learning and model inference are performed in the gNB200. Fig. 12 shows an example in which the transmitting entity TE is the gNB200 and the receiving entity RE is the UE100.

[0111] 12 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.

[0112] (1.5) Model transfer example

[0113] 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.

[0114] (1.5.1) First operation pattern related to model forwarding Figure 13 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 13, 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 13, 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.

[0115] 13, in step S201, 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 is to be executed).

[0116] In step S202, 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.

[0117] 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.

[0118] Alternatively, the information element indicating the execution capability of the machine 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 or an information element indicating the time required to execute the inference process (or the response time).

[0119] Alternatively, the information element indicating the execution capability of 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 or an information element indicating the processing capacity of the learning process.

[0120] In step S203, gNB200 determines the model to be configured (or deployed) in UE100 based on the information elements included in the message received in step S202.

[0121] In step S204, gNB200 transmits a message including the model determined in step S203 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 S204 will be described in the following second operation pattern.

[0122] (1.5.2) Second operation pattern related to model transfer FIG. 14 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.

[0123] In the example of FIG. 14, 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.

[0124] 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.

[0125] 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.

[0126] (1.6) Example of Functional Block Configuration Functional blocks for AI for wireless communication have been described using Fig. 6. Currently, 3GPP is considering the block diagram shown in Fig. 15 for functional blocks for AI for wireless communication.

[0127] Fig. 15 is a diagram illustrating an example of the configuration of functional blocks according to the first embodiment. Compared to the functional block diagram illustrated in Fig. 6, the functional block diagram illustrated in Fig. 15 further includes a model management unit A5 and a model recording unit A6.

[0128] The model management unit A5 manages the AI / ML model. For example, the model management unit A5 requests the model training unit A2 to retrain the trained model or requests the model recording unit A6 to transfer the model. As shown in FIG. 15 , an AI / ML model that has been trained through retraining may be referred to as an updated model. Furthermore, for example, the model management unit A5 instructs (or requests) the model inference unit A3 to select a model, (de)activate a model, switch a model, and / or fallback. The model management unit A5 may evaluate the performance of the trained model using the monitoring data acquired from the data collection unit A1 and the monitoring output acquired from the model inference unit A3, and may request retraining or instruct model switching based on the evaluation results.

[0129] The model recording unit A6 functions as a reference point in the functional blocks. Therefore, the model recording unit A6 does not necessarily have to record the trained model or the updated model on a recording medium.

[0130] The arrangement of the functional blocks shown in FIG. 15 in each use case is currently under consideration in 3GPP.

[0131] Hereinafter, an AI / ML model to be trained may be referred to as a "training model," and a trained AI / ML model may be referred to as a "trained model." Furthermore, data for inference may be referred to as inference data, and data for training may be referred to as training data. Furthermore, when there is no need to distinguish between an AI / ML model undergoing model training and a trained AI / ML model, they may be simply referred to as an AI / ML model. As described above, an AI / ML model is a data-driven algorithm that can obtain a series of outputs from a series of inputs, for example, by using AI / ML technology.

[0132] (Communication Control Method According to First Embodiment) Next, a communication control method according to the first embodiment will be described.

[0133] 3GPP is currently discussing the transfer (or delivery) of AI / ML models. In particular, an agreement has been reached on reactive model transfer (or delivery) (hereinafter, sometimes referred to as "reactive model transfer"). Reactive model transfer is a method of downloading an AI / ML model when the need arises due to a change in scenario, setting, or location. For example, when UE 100 performs a handover to a target cell (i.e., a change in location) and the AI / ML model cannot be used in the target cell, UE 100 receives a new AI / ML model from the target cell. Such a case is expected to correspond to reactive model transfer.

[0134] In addition to reactive model transfer, 3GPP is also discussing proactive model transfer (or delivery) (hereinafter, sometimes referred to as "proactive model transfer"). Proactive model transfer is, for example, a technique in which an AI / ML model is downloaded in advance, and model switching is performed when a change occurs in the scenario, setting, or location. For example, UE 100 downloads an AI / ML model from a serving cell in advance, and after handover to a target cell, switches to the downloaded AI / ML model (from the AI / ML model that has been used until now). With proactive model transfer, for example, UE 100 does not need to wait for the AI / ML model to be downloaded after changing its location, and can immediately use the (previously downloaded) AI / ML model.

[0135] In the first embodiment, attention is focused on proactive model transfer. For example, even when an AI / ML model is transferred to UE 100 by proactive model transfer, UE 100 may delete the AI / ML model due to memory capacity limitations. After that, for example, when UE 100 switches connection from a serving cell to a target cell by handover and receives the AI / ML model from the target cell, the proactive model transfer itself by the serving cell may become useless.

[0136] Therefore, the first embodiment aims to prevent the UE 100 from deleting the AI / ML model.

[0137] Therefore, in the first embodiment, when the network device transmits the AI / ML model to the UE 100 by proactive model transfer, the network device transmits to the UE 100 deletion-prohibited information indicating that the AI / ML model cannot be deleted.

[0138] Specifically, first, the network device transmits to the user equipment (e.g., UE 100) an AI / ML model that can be used under a predetermined condition and deletion prohibition information indicating that the AI / ML model must not be deleted before the predetermined condition occurs. Second, the user equipment uses the AI / ML model under the predetermined condition without deleting the AI / ML model in accordance with the deletion prohibition information. Here, the predetermined condition may be any one of congestion occurring on a communication path between the user equipment and the network device, the user equipment transmitting an emergency call, and the user equipment receiving a message related to a public warning system (PWS).

[0139] In this way, in the first embodiment, the network device transmits the AI / ML model and the non-deletion information to UE100 before congestion occurs, so that UE100 can properly receive the AI / ML model and can prevent the AI / ML model from being deleted in accordance with the non-deletion information.

[0140] In the first embodiment, a case where congestion occurs will be described as an example of the predetermined condition. In the second embodiment, a case where the UE 100 transmits an emergency call and a case where the UE 100 receives a message related to a public warning system (PWS) will be described as the predetermined condition.

[0141] (Operation Example According to First Embodiment) Fig. 16 is a diagram illustrating an operation example according to First Embodiment. In the operation example shown in Fig. 16, a case where congestion occurs at a fireworks venue will be described as an example.

[0142] Here, there is a tracking area (TA) including the fireworks venue, and there is an AMF that manages the tracking area. In Figure 16, the AMF (second AMF) is shown as an example of a second network device. Meanwhile, there is also a tracking area adjacent to the tracking area (TA) including the fireworks venue, and there is also an AMF that manages the tracking area. In Figure 16, the AMF (first AMF) is shown as an example of a first network device. That is, Figure 16 shows an example in which the fireworks venue is located in a TA managed by the second network device, and the TA adjacent to the TA is managed by the first network device.

[0143] In step S20, the UE 100 executes a registration procedure with the first network device. The UE 100 registers with the network under the first network device through the registration procedure.

[0144] In step S21, the first network device detects that the UE 100 is moving to a predetermined TA (e.g., a TA having a fireworks venue). For example, if the first network device is an AMF, a control unit of the AMF may perform this detection based on an identifier of the last visited TA, "last visited TAI," received from the UE 100 during the registration procedure. Specifically, if the identifier is other than a TAI (Tracking Area Identifier) ​​managed by the second network device, the control unit may detect that the UE 100 is moving to (or heading toward) a TA managed by the second network device, i.e., a TA of the fireworks venue.

[0145] In step S22, when the first network device detects that the UE 100 is moving to a predetermined TA, the first network device transmits an instruction to use the learned AI / ML model to the UE 100. For example, when the first network device is an AMF, a transmitting unit of the AMF transmits a NAS message including the instruction to use the AI / ML model to the UE 100.

[0146] First, in the case of a UE-side model, the first network device checks whether the UE 100 holds the AI / ML model that is the target of the usage instruction. The UE-side model is, for example, a model in which inference is performed in the UE 100 using a trained AI / ML model. On the other hand, a model in which inference is performed in a network device using a trained AI / ML model may be referred to as a network-side model. For example, the transmission unit 120 of the UE 100 may transmit a NAS message including identification information (or model ID) of the trained AI / ML model that it holds to the first network device (AMF) during the registration procedure. The control unit of the first network device checks whether the UE 100 holds the trained AI / ML model that is the target of the usage instruction based on the identification information.

[0147] In the first network device, when it is confirmed that the UE 100 does not hold the trained AI / ML model that is the subject of the usage instruction, in step S23, the first network device transmits the trained AI / ML model to the UE 100 (i.e., performs "model transfer"). For example, the transmitting unit of the AMF 300 transmits a NAS message including the trained AI / ML model to the UE 100.

[0148] In this way, in the first embodiment, "model transfer" of the trained AI / ML model is performed before congestion occurs. This "model transfer" can be said to correspond to the above-mentioned "proactive model transfer."

[0149] In the first embodiment, when the first network device transmits the learned AI / ML model to the UE 100, it transmits to the UE 100 deletion prohibition information indicating that the learned AI / ML model must not be deleted. The deletion prohibition information may be transmitted together with an instruction to use the AI / ML model (step S22). The deletion prohibition information may be transmitted together with the AI / ML model (step S23). The deletion prohibition information may be transmitted after the AI / ML model has been transferred. For example, the transmitting unit of the AMF 300 may transmit a NAS message including the deletion prohibition information to the UE 100. The UE 100 receives the deletion prohibition information. The receiving unit 110 of the UE 100 may receive the NAS message including the deletion prohibition information.

[0150] Note that, when UE 100 receives the deletion-impossible information, it may transmit to the network device information indicating that the learned AI / ML model cannot be deleted (i.e., must be deleted) because UE 100's own memory capacity is limited. Alternatively, after receiving the deletion-impossible information, when it becomes necessary to delete the learned AI / ML model, UE 100 may transmit to the network device request information requesting deletion of the learned AI / ML model. Meanwhile, the network device may transmit to UE 100, together with the deletion-impossible information, deletion conditions (e.g., insufficient memory capacity) for deleting the learned AI / ML model. Alternatively, when transferring the trained AI / ML model, the network device may transmit to UE 100 a priority number relating to the deletion impossibility. For example, the priority number indicates that the higher the priority number, the more priority is given to the impossibility of deletion of the trained AI / ML model, and the lower the priority number, the more the trained AI / ML model may be deleted (or vice versa). The priority number may be transmitted together with the transfer of the trained AI / ML model. The priority number may be transmitted as part of the non-deletable information.

[0151] The deletion prohibition information may be expressed as flag information indicating that the trained AI / ML model must not be deleted. Alternatively, the deletion prohibition information may include information indicating that the trained AI / ML model must not be deleted until a specified deadline. This is because congestion may occur before the specified deadline, and the trained AI / ML model is not to be deleted until the specified deadline. Alternatively, the deletion prohibition information may include the specified deadline. Including the specified deadline in the deletion prohibition information may indicate that the trained AI / ML model must not be deleted until the specified deadline. Alternatively, the deletion prohibition information may include a reason why the trained AI / ML model must not be deleted. For example, the reason may be that congestion may occur at a fireworks venue. Alternatively, the deletion prohibition information may include identification information (e.g., a model ID) of the trained AI / ML model that cannot be deleted. For example, the transmission unit of the AMF 300 may transmit a NAS message including the deletion prohibition information to the UE 100. The UE 100 receives the deletion prohibition information. For example, the receiver 110 of the UE 100 receives the deletion prohibition information. Upon receiving the deletion prohibition information, the UE 100 (controller 130 thereof) retains the target trained AI / ML model in a memory or the like without deleting it. If the deletion prohibition information includes a specified deadline, the UE 100 retains the target trained AI / ML model until the specified deadline arrives. If the deletion prohibition information includes identification information of the target trained AI / ML model, the UE 100 retains the trained AI / ML model. Alternatively, the deletion prohibition information may include location information indicating a location where the trained AI / ML model is not prohibited from being deleted. For example, some network devices do not use machine learning technology using an AI / ML model. By notifying the UE 100 of such network devices, the UE 100 can avoid connecting to the network device and avoid a situation in which the trained AI / ML model is not transferred from the network device. The location information may be represented, for example, by a TAID. The location information may be represented by a cell ID. The location information may be represented by GNSS location information.The designation of the location information may indicate that the trained AI / ML model is not prohibited from being deleted when the user moves to the location. The designation may indicate that the trained AI / ML model is not prohibited from being deleted when the user moves away from the location.

[0152] Second, in the case of a network-side model, the first network device instructs the network device to collect inference data and transmit it to the network device (Data Collection) as an instruction to use the trained AI / ML model (step S22).

[0153] In addition, in the network-side model, UE 100 may hold the target trained AI / ML model. In this case, the first network device may instruct UE 100 to transfer the trained AI / ML model along with an instruction to use the trained AI / ML model (step S22). Then, the first network device may transmit to UE 100 deletion-prohibition information for the instructed trained AI / ML model. The transmission unit of the network device transmits a message including a transfer instruction and deletion-prohibition information for the trained AI / ML model to UE 100. In response to reception of the message by the reception unit 110 of UE 100, the control unit 130 of UE 100 does not delete the instructed trained AI / ML model, and the transmission unit 120 of UE 100 transmits (a message including) the trained AI / ML model to the network device. In this case, "model transfer" of the trained model is performed before congestion occurs. This "model transfer" can also be considered to be "proactive model transfer." Both the message sent from the network device and the message sent from the UE 100 may be a NAS message.

[0154] In step S24, the UE 100 continues to move, and when the UE 100 moves to a TA managed by the second network device, the UE 100 performs a registration procedure with the second network device (AMF). The UE 100 is registered in a network of the AMF that has a predetermined TA (for example, a TA having a fireworks venue) under its control.

[0155] In step S25, the second network device detects that the communication volume in the data communication path of the UE 100 is equal to or greater than a threshold. The data communication path may be a communication path between the UE 100 and a UPF (e.g., a UPF that processes data transmitted from the UE 100 at the fireworks venue). That is, the control unit of the second network device detects that congestion is occurring in the data communication path. A situation in which congestion is occurring at the fireworks venue.

[0156] In step S26, the second network device transmits an instruction to use the learned AI / ML model to the UE 100. For example, a transmitting unit of the second network device transmits a NAS message including the instruction to use the learned AI / ML model to the UE 100. The UE 100 receives the instruction to use the learned AI / ML model. The instruction to use the learned AI / ML model may be transmitted before congestion occurs (step S25).

[0157] In the case of the UE-side model, in step S27, the UE 100 performs inference using the trained AI / ML model received in step S23 in accordance with the usage instruction. In the case of the network-side model, instead of step S27, the UE 100 collects inference data for the trained AI / ML model used in the second network device and transmits the collected inference data to the second network device. The inference data may also be transmitted by a NAS message.

[0158] (Another Operation Example 1 According to First Embodiment) In the first embodiment, an example in which the network device is an AMF has been mainly described, but the network device is not limited to an AMF. The network device may be a gNB 200.

[0159] First, in Figure 16, the first network device may be the "first cell" and the second network device may be the "second cell." The first cell and the second cell may be managed by the same gNB, or different gNBs may manage each cell.

[0160] Second, instead of the registration procedure (steps S20 and S24), a handover procedure may be performed. The handover procedure in step S20 is a procedure for UE 100 to execute handover from another cell to the first cell. Also, the handover procedure in step S24 is a procedure for UE 100 to execute handover from the first cell to the second cell. In this case, the first cell issues a handover instruction to UE 100 by using an RRC message (e.g., an RRC Reconfiguration message), and the RRC message may include deletion impossible information and be transmitted to UE 100.

[0161] Third, in the first embodiment, the NAS message may be replaced with an RRC message. The instruction to use the learned AI / ML model in steps S22 and S26 may be included in an RRC message and transmitted. The transfer of the AI / ML model in step S23 may also be included in an RRC message (or the above-mentioned configuration message) and transmitted. The deletion non-permission information may also be included in an RRC message and transmitted. The RRC message may be transmitted between the transmitter 120 of the UE 100 and the receiver 220 of the gNB 200, or between the transmitter 210 of the gNB 200 and the receiver 110 of the UE 100. The processing in the first network device (step S21) and the processing in the second network device (step S25) may be performed by a control unit of the gNB 200.

[0162] In the first embodiment, the predetermined condition is described using the occurrence of congestion as an example, but the predetermined condition is not limited to this. For example, the completion of the handover described above may be the predetermined condition. Specifically, for example, in the first embodiment, instead of the operation related to congestion (step S25), the predetermined condition may be that a handover completion message (e.g., an RRC reconfiguration complete (RRCReconfigurationComplete) message) has been transmitted from the second cell. The handover completion message may include a usage instruction.

[0163] (Another operation example 2 according to the first embodiment) In another operation example 1 according to the first embodiment, the "first cell" may be the first gNB, and the "second cell" may be the second gNB. In this case, it is an example of the case where the network device is a gNB.

[0164] (Another Operation Example 3 According to the First Embodiment) In the first embodiment, an example has been described in which a trained AI / ML model is transmitted to UE 100 by proactive model transfer. For example, the transfer of the trained AI / ML model may be performed by reactive model transfer. For example, the first network device does not transfer the trained AI / ML model (step S23), and the second network device transfers the trained AI / ML model from step S25 onwards. In this case, the target of the non-deletable information is the trained AI / ML model transferred by the second network device. Reactive model transfer may be performed, for example, under certain conditions other than congestion.

[0165] (Another Operation Example 4 According to the First Embodiment) In the above-described Other Operation Example 3, an example was described in which the predetermined condition includes handover. For example, instead of the occurrence of congestion, the predetermined condition may be that the UE 100 has entered a specific TA. In this case, in FIG. 16, the operation related to congestion (step S25) is not performed. Instead of step S25, the following processing may be performed. That is, the UE 100 performs a tracking area update (TAU) from TA #1 to TA #2 and performs a registration procedure (step S24) with a second network device (e.g., AMF #2) that manages TA #2, and receives an SIB broadcast from the gNB 200 in TA #2. The SIB includes identification information of TA #2. When the UE 100 confirms that it is located in TA #2 based on the SIB, it performs inference using the AI / ML model (for TA #2) (step S27) without receiving the use instruction in step S26. Alternatively, instead of receiving the SIB, the UE 100 performs step S24 and then receives a use instruction from the second network device (step S26), which enables the UE 100 to perform inference using the AI / ML model (for TA #2) in the same way as when the UE 100 receives the SIB (step S27).

[0166] (Another Operation Example 5 According to First Embodiment) In the first embodiment, an example of an AMF has been described as an example of the first network device and the second network device. Also, in Another Operation Example 1 according to the first embodiment, a cell (or a gNB) has been described as an example of the first network device and the second network device. The first network device and the second network device may be collectively called a single OTT server. In this case, for example, the following processing is performed between the OTT server and the UE 100.

[0167] That is, UE 100 transmits location information acquired by GNSS receiver 150 to the OTT server, for example, at regular time intervals. The OTT server detects that UE 100 is approaching a fireworks venue based on the location information. At this time, the OTT server transmits non-deletion information and the trained AI / ML model to UE 100. The OTT server also transmits location information of the fireworks venue to UE 100.

[0168] UE 100 detects that it has arrived at the fireworks venue based on the location information acquired by GNSS receiver 150 and the location information of the fireworks venue acquired from the OTT server. At this time, UE 100 performs inference using the trained AI / ML model (used at the fireworks venue) received from the OTT server.

[0169] (Another Operation Example 6 According to the First Embodiment) An example of a network device may be an LMF. The LMF is an example of a core network device. In this case, for example, the following operation is performed.

[0170] That is, UE 100 acquires location information via LMF. LMF detects that UE 100 is approaching a fireworks venue from the location information of UE 100. At this time, LMF transmits the learned AI / ML model and non-removal information to UE 100. Furthermore, LMF transmits location information of the fireworks venue to UE 100.

[0171] The UE 100 may acquire its own location information from the LMF at regular intervals. The UE detects that it has moved to the fireworks venue based on the location information acquired from the LMF and the location information of the fireworks venue received from the LMF. At this time, the UE 100 performs inference using the trained AI / ML model (used at the fireworks venue) received from the LMF. In this way, the network device used in the first embodiment may be a core network device such as an LMF.

[0172] [Second Embodiment] Next, a second embodiment will be described. In the first embodiment, congestion was used as an example of the predetermined condition. In the second embodiment, examples of the predetermined condition include a case where the UE 100 transmits (or makes) an emergency call and a case where the UE 100 receives a message related to a public warning system (PWS).

[0173] In the second embodiment, an example will be described in which a trained AI / ML model used in cases of high urgency compared to other systems, such as emergency calls and PWS, is transferred from a network device to a UE 100 before a high-urgency situation occurs (i.e., proactive model transfer). Then, in the second embodiment, an example will be described in which, similar to the first embodiment, when proactive model transfer of a trained AI / ML model is performed, non-deletion information is transferred from a network device to a UE 100.

[0174] In the second embodiment, an Earthquake and Tsunami Warning System (ETWS) or a Commercial Mobile Alert System (CMAS) will be described as an example of a message related to a PWS. However, the present invention is not limited to this, and messages related to other PWSs may also be used. The ETWS is a system that delivers highly urgent information, such as tsunamis and earthquakes, to the UE 100. The CMAS is a system that delivers a wide range of information, such as a presidential message or product advertisements, to the UE 100.

[0175] (Operation example according to the second embodiment) Figure 17 is a diagram showing an operation example according to the second embodiment. The network device may be an AMF, a gNB 200, or another core network device. In addition, the network device may be an OTT (Over The Top) server.

[0176] In step S30, the network device transmits an instruction to use the trained AI / ML model to the UE 100. The instruction to use represents an instruction to use the trained AI / ML model on the condition that a predetermined condition occurs in the UE 100.

[0177] First, the predetermined condition may be that the UE 100 has transmitted (or originated) an emergency call. An emergency call is when the UE 100 notifies the police, hospital, fire department, or other national emergency organizations. For example, when the control unit 130 of the UE 100 detects that the UE 100 has transmitted (or originated) a call to a telephone number addressed to such an organization, the occurrence of the predetermined condition is detected.

[0178] Second, the predetermined condition may be that the UE 100 has received either a message related to ETWS or a message related to CMAS. Specifically, the predetermined condition may be determined to have occurred when the receiver 110 of the UE 100 has received broadcast information (e.g., SIB6 and / or SIB7) indicating a message related to ETWS. Alternatively, the predetermined condition may be determined to have occurred when the receiver 110 of the UE 100 has received broadcast information (e.g., SIB8) indicating a message related to CMAS.

[0179] Third, the predetermined condition may be that the UE 100 has detected the occurrence of congestion. For example, the control unit 130 of the UE 100 may detect that congestion has occurred when the transmission unit 120 of the UE 100 has repeated retransmission a predetermined number of times or more within a predetermined time period.

[0180] If the network device is a gNB, the transmitter 210 of the gNB 200 may transmit an RRC message including the use instruction to the UE 100. Also, if the network device is an AMF, the transmitter of the AMF 300 may transmit a NAS message including the use instruction. Furthermore, if the network device is an OTT server, the transmitter of the OTT server may transmit a message of a predetermined protocol including the use instruction. The UE 100 receives the use instruction. For example, the receiver 110 of the UE 100 receives a message including the use instruction.

[0181] In step S31, the network device transmits the trained AI / ML model to the UE 100. The trained AI / ML model is a trained AI / ML model that can be used under predetermined conditions. Alternatively, the trained AI / ML model may be a trained AI / ML model used by the UE 100 in an emergency. The trained AI / ML model is transmitted before a predetermined condition occurs, which corresponds to "proactive model transfer." For example, a transmitting unit of the network device transmits a message including the trained AI / ML model to the UE 100. Depending on the type of the network device, the message may be an RRC message (or a configuration message), a NAS message, or a message of a predetermined protocol. The UE 100 receives the trained AI / ML model. For example, the receiving unit 110 of the UE 100 receives the message including the trained model.

[0182] In the second embodiment, as in the first embodiment, the network device transmits deletion-prohibition information for the trained AI / ML model. The deletion-prohibition information may be transmitted together with an instruction to use the trained AI / ML model (step S30). The deletion-prohibition information may be transmitted together with the trained AI / ML model (step S31). The deletion-prohibition information may be transmitted after the trained AI / ML model is transmitted. A transmitting unit of the network device may transmit a message including the deletion-prohibition information. The message may be an RRC message depending on the type of network device. The message may be a NAS message. The message may be a message according to a predetermined protocol. The content of the deletion-prohibition information may be the same as in the first embodiment. When the UE 100 (control unit 130 thereof) receives the deletion-prohibition information, the UE 100 will use the trained AI / ML model when a predetermined condition occurs, without deleting the trained AI / ML model.

[0183] Note that step S31 represents an example in the case of a UE-side model. In the case of a network-side model, if the network device does not hold a trained model to be used in an emergency, the UE 100 may transmit a trained AI / ML model to the network device instead of step S31. In this case, for example, the use instruction in step S30 includes identification information (or model ID) of the trained model to be used in an emergency. The UE 100 may transmit the trained model corresponding to the identification information to the network device. In this case, the use instruction and the trained model are also transmitted in an RRC message (or a configuration message), a NAS message, or a message according to a predetermined protocol, depending on the type of network device.

[0184] In step S32, UE 100 detects that a predetermined condition has occurred. For example, the occurrence of the predetermined condition is detected in the following cases. That is, the occurrence of the predetermined condition is detected when control unit 130 of UE 100 detects that a call to a telephone number addressed to an emergency service has been transmitted. Alternatively, the occurrence of the predetermined condition is detected when receiving unit 110 of UE 100 receives SIB6 and / or SIB7. Alternatively, the occurrence of the predetermined condition is detected when receiving unit 110 of UE 100 receives SIB8. Alternatively, control unit 130 of UE 100 may detect that a predetermined condition has occurred by determining that congestion has occurred when transmitting unit 120 of UE 100 has repeated retransmission a predetermined number of times or more within a predetermined time.

[0185] In the case of the UE-side model, in step S33, the UE 100 performs inference using the trained AI / ML model received in step S31. In the case of the network-side model, instead of step S33, the UE 100 collects inference data used in the network device and transmits the collected inference data to the network device. The inference data may also be transmitted using any of an RRC message (or control data), a NAS message, and a message of a predetermined protocol, depending on the type of the network device.

[0186] In addition, the network device may be triggered by detecting that a predetermined condition has occurred to transmit to UE100 an instruction to use the learned AI / ML model transmitted in step S31. For example, the transmitting unit of the network device may transmit a message including the instruction to use to UE100 in response to the receiving unit of the network device receiving an emergency call. Alternatively, the transmitting unit 210 of gNB200 may transmit an RRC message including the instruction to use to UE100 simultaneously with the broadcast of SIB6 and / or SIB7. Alternatively, the transmitting unit 210 of gNB200 may transmit an RRC message including the instruction to use to UE100 simultaneously with the broadcast of SIB8. UE100 (the receiving unit 110 thereof) receives the message. UE100 may execute step S33 in response to receiving the instruction to use.

[0187] (Another Operation Example 1 According to the Second Embodiment) In the second embodiment, the network device has been described on the assumption that the UE 100 does not hold the learned AI / ML model used in an emergency. For example, when the network device confirms that the UE 100 does not hold the AI / ML model, the network device may transmit the AI / ML model to the UE 100. For example, the following processing may be performed. That is, the transmission unit of the network device transmits a confirmation message to the UE 100 indicating whether the AI / ML model is held. The confirmation message may include identification information of the AI / ML model. In response to receiving the confirmation message, the transmission unit 120 of the UE 100 transmits a response message to the network device including a confirmation result indicating whether the AI / ML model is held. In response to the confirmation result, the transmission unit of the network device transmits the learned AI / ML model used in an emergency to the UE 100. The confirmation message and the response message may be any of an RRC message, a NAS message, and a message of a predetermined protocol, depending on the type of the network device.

[0188] In the first and second embodiments, the predetermined condition is described as any one of congestion occurring on a communication path between the user equipment and the network device, the user equipment transmitting an emergency call, and the user equipment receiving a message related to a public warning system (PWS). The predetermined condition may be, for example, handing over to a specific cell or entering a specific TA (or performing a registration procedure with a specific TA).

[0189] In the first and second embodiments, the UE-side model has been mainly described. The first and second embodiments can also be applied to a double-side model. A double-side model is, for example, a model in which inference using a trained AI / ML model is performed in both the UE 100 and the network device. Examples of double-side models include the following:

[0190] That is, using the learned AI / ML model in the UE 100, the punctured CSI-RS is used as inference data, and the (punctured) CSI is inferred (or output) as inference result data. The UE 100 transmits the CSI to the network device. The network device uses the (punctured) CSI as inference data, and infers the CSI obtained using all the CSI-RS (i.e., unpunctured CSI) as inference result data.

[0191] Even in the case of a double-sided model, the first network device transfers the trained AI / ML model (step S23), as in the first embodiment. In this case, the network device transmits the trained AI / ML model used in UE 100, of the double-sided models, to UE 100 as the transfer target. In this way, even in the case of a double-sided model, the same implementation as in the first embodiment ( FIG. 16 ) is possible. In the second embodiment, as in the case of a double-sided model, the trained AI / ML model used in UE 100, of the double-sided models, is the transfer target in the transfer of the trained AI / ML model in step S31.

[0192] Furthermore, in the first and second embodiments, an example in which deletion prohibition information is used has been described. For example, instead of deletion prohibition information, the network device may transmit to the UE 100 deletion permission information indicating that the learned AI / ML model may be deleted. The deletion permission information may include the model ID (or the model ID in list format) of the learned AI / ML model to be deleted. Alternatively, the deletion permission information may include a priority (for each trained AI / ML model to be deleted). In this case, the higher the priority, the more it may be indicated that deletion is permitted, and the lower the priority, the more it may be indicated that deletion is not permitted (or vice versa).

[0193] In the first and second embodiments 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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. 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 a DVD-ROM. Furthermore, circuits that execute each process performed by the UE 100, the gNB 200, or the network device may be integrated, and at least a portion of the UE 100, the gNB 200, or the network device may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0199] The functions performed by the UE 100, the gNB 200, or the network device 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 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.

[0200] 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.

[0201] 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.

[0202] This application claims priority from Japanese Patent Application No. 2023-168503 (filed September 28, 2023), the entire contents of which are incorporated herein by reference.

[0203] (Supplementary Note) (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 an AI / ML model that can be used under a predetermined condition and deletion prohibition information indicating that the AI / ML model must not be deleted before the predetermined condition occurs; and a step in which the user device uses the AI / ML model under the predetermined condition without deleting the AI / ML model in accordance with the deletion prohibition information, wherein the predetermined condition is any one of congestion occurring in a data communication path of the user device, the user device transmitting an emergency call, and the user device receiving a message related to a public warning system (PWS).

[0204] (Supplementary Note 2) The communication control method according to Supplementary Note 1, wherein the non-deletion information includes at least one of the fact that the AI / ML model must not be deleted until a specified deadline, the specified deadline, and a reason why the AI / ML model must not be deleted.

[0205] (Supplementary Note 3) A network device in a mobile communication system, comprising: a transmitter that transmits, to a user device before the predetermined condition occurs, an AI / ML model that can be used under a predetermined condition and non-deletion information indicating that the AI / ML model must not be deleted, wherein the predetermined condition is one of congestion occurring in a data communication path of the user device, the user device transmitting an emergency call, and the user device receiving a message related to a public warning system (PWS).

[0206] 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 300: AMF

Claims

1. A communication control method in a mobile communication system, comprising: a network device transmitting, to a user device before the predetermined condition occurs, an AI (Artificial Intelligence) / ML (Machine Learning) model that can be used under a predetermined condition and deletion prohibition information indicating that the AI / ML model should not be deleted; and the user device using the AI / ML model under the predetermined condition without deleting the AI / ML model in accordance with the deletion prohibition information, wherein the predetermined condition is any one of congestion occurring in a data communication path of the user device, the user device transmitting an emergency call, and the user device receiving a message related to a public warning system (PWS).

2. The communication control method according to claim 1, wherein the non-deletion information includes at least one of the following: that the AI / ML model must not be deleted until a specified deadline, the specified deadline, and the reason why the AI / ML model must not be deleted.

3. A network device in a mobile communication system, comprising: a transmission unit that transmits to a user device before the specified condition occurs an AI / ML model that can be used under a specified condition and non-deletion information indicating that the AI / ML model should not be deleted, wherein the specified condition is any one of congestion occurring in a data communication path of the user device, the user device transmitting an emergency call, and the user device receiving a message related to a public warning system (PWS).