COMMUNICATION METHOD, USER EQUIPMENT, AND ACCESS MOBILITY MANAGEMENT DEVICE

Abstract

Provided is a communication method in a mobile communication system. The communication method comprises a step in which a transmitting entity transmits, to a receiving entity, first usage condition information representing a first usage condition under which at least one of a learning model and a data set is used. Here, the learning model is either an untrained model that has not been trained or a trained model that has been trained. Further, the data set is either learning data or inference data.

Description

[Technical Field]

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

[0002] In recent years, the Third Generation Partnership Project (3GPP) (registered trademark), a standardization project for mobile communication systems, has been studying the application of artificial intelligence (AI) technology, particularly machine learning (ML) technology, to wireless communication (air interface) in mobile communication systems. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] 3GPP contribution: RP-213599, “New SI: Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface” Summary of the Invention

[0004] A communication method according to one aspect is a communication method in a mobile communication system. The communication method includes a step in which a transmitting entity transmits, to a receiving entity, first usage condition information representing first usage conditions under which at least one of a training model and a dataset is used. Here, the training model is either an untrained model that has not been trained or a trained model that has been trained. Also, the dataset is either training data or inference data.

[0005] A communication method according to one aspect is a communication method in a mobile communication system. The communication method includes a step in which a transmitting entity transmits a dataset usable by a training model to a receiving entity having the training model, without transmitting name information indicating the name of the training model. Here, the training model is either an untrained model that has not been trained or a trained model that has been trained. Also, the dataset is either training data or inference data. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a mobile communication system according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a UE (user equipment) according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating a configuration example of a gNB (base station) according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of a protocol stack according to the first embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of a protocol stack according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of functional blocks of the AI / ML technology according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an arrangement of functional blocks of the AI / ML technology according to the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of an arrangement of functional blocks of the AI / ML technology according to the first embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of an arrangement of functional blocks of the AI / ML technology according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of the configuration of a mobile communication system according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of operation according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of operation according to the second embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of operation according to the third embodiment. [Figure 14] FIG. 14 is a diagram illustrating another example of operation according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] When attempting to apply machine learning technology to mobile communication systems, it has not yet been established how to utilize machine learning technology.

[0008] The present disclosure aims to provide a communication method capable of determining whether a receiving entity can use a trained model or an untrained model, and also to provide a communication method capable of determining whether a receiving entity can use training data or inference data.

[0009] [First embodiment] The mobile communication system according to the first embodiment will be described with reference to the drawings. In the description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.

[0010] (Configuration of a 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 3GPP standard 5th Generation System (5GS). In the following description, 5GS will be used as an example, but 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 6th Generation (6G) system or later system.

[0011] The mobile communication system 1 includes a user equipment (UE) 100, a 5G radio access network (NG-RAN) 10, and a 5G core network (5GC) 20. Hereinafter, the NG-RAN 10 may be simply referred to as the RAN 10. The 5GC 20 may be simply referred to as the core network (CN) 20.

[0012] The UE 100 is a mobile wireless communication device. The UE 100 may be any device used by a user. For example, the UE 100 may be a mobile phone terminal (including a smartphone) and / or a tablet terminal, a laptop 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).

[0013] The NG-RAN 10 includes a base station (called "gNB" in the 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, etc. The term "cell" is used to indicate the smallest unit of a wireless communication area. The term "cell" is also used to indicate a function or resource that performs wireless communication with a UE 100. One cell belongs to one carrier frequency (hereinafter simply referred to as "frequency").

[0014] In addition, gNBs can also connect to the Evolved Packet Core (EPC), which is the LTE core network. LTE base stations can also connect to 5GC. LTE base stations and gNBs can also be connected via a base station-to-base station interface.

[0015] The 5GC20 includes an Access and Mobility Management Function (AMF) and a User Plane Function (UPF) 300. The AMF performs various mobility controls for the UE 100. The AMF manages the mobility of the UE 100 by communicating with the UE 100 using NAS (Non-Access Stratum) signaling. The UPF controls data forwarding. The AMF and UPF 300 are connected to the gNB 200 via an NG interface, which is an interface between a base station and a core network. The AMF and UPF 300 may be core network devices included in the CN20.

[0016] 2 is a diagram showing an example of the configuration of a UE 100 (user equipment) according to the first embodiment. The UE 100 includes a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 configure a communication unit that performs wireless communication with the gNB 200. The UE 100 is an example of a communication device.

[0017] 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.

[0018] 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.

[0019] The control unit 130 performs various controls and processes in the UE 100. Such processes include processes of each layer, which will be described later. The control unit 130 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in the processes by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation / demodulation and encoding / decoding 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.

[0020] 3 is a diagram showing an example of the configuration of a gNB200 (base station) according to the first embodiment. The gNB200 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 performs communication with the CN 20. The gNB200 is another example of a communication device.

[0021] The transmission unit 210 performs various transmissions under the control of the control unit 230. The transmission 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.

[0022] 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.

[0023] The control unit 230 performs various controls and processes in the gNB 200. Such processes include processes for each layer, which will be described later. The control unit 230 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in the processes by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation / demodulation and encoding / decoding of baseband signals, etc. 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.

[0024] The backhaul communication unit 250 is connected to neighboring 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. Note that the gNB 200 may be configured (i.e., functionally divided) with a central unit (CU) and a distributed unit (DU), and both units may be connected via an F1 interface, which is a fronthaul interface.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] In NR, the UE 100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). The gNB 200 configures the UE 100 with a bandwidth portion (BWP) consisting of consecutive physical resource blocks (PRBs). The UE 100 transmits and receives data and control signals in the active BWP. For example, up to four BWPs may be configured for the UE 100. Each BWP may have a different subcarrier spacing. The BWPs may overlap in frequency. When multiple BWPs are configured for the UE 100, the gNB 200 can specify which BWP to apply by controlling the downlink. This allows the gNB 200 to dynamically adjust the UE bandwidth according to the amount of data traffic of the UE 100, etc., thereby reducing UE power consumption.

[0029] For example, the gNB 200 can configure up to three control resource sets (CORESETs) for each of up to four BWPs on the serving cell. A CORESET is a radio resource for control information to be received by the UE 100. Up to 12 or more CORESETs may be configured for the UE 100 on the serving cell. Each CORESET may have an index of 0 to 11 or more. A CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive Orthogonal Frequency Division Multiplexing (OFDM) symbols in the time domain.

[0030] 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 UE100 and the MAC layer of gNB200 via transport channels. The MAC layer of gNB200 includes a scheduler, which determines the uplink and downlink transport format (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to UE100.

[0031] The RLC layer transmits data to the RLC layer on the receiving side 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 logical channels.

[0032] The PDCP layer performs header compression / decompression, encryption / decryption, etc.

[0033] The SDAP layer maps IP flows, which are the units for Quality of Service (QoS) control by the core network, to radio bearers, which are the units for QoS control by the access stratum (AS). Note that if the RAN is connected to the EPC, SDAP is not necessary.

[0034] 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).

[0035] The protocol stack of the radio interface of the control plane has a radio resource control (RRC) layer and a non-access stratum (NAS) instead of the SDAP layer shown in FIG.

[0036] 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.

[0037] 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. The layer below the NAS is called an AS (Access Stratum).

[0038] (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.

[0039] 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.

[0040] The data collection unit A1 collects input data, specifically, learning data and inference data. The data collection unit A1 outputs the learning data to the model learning unit A2. The data collection unit A1 also outputs the inference data to the model inference unit A3. The data collection unit A1 may acquire data in the device on which the data collection unit A1 is provided as input data. The data collection unit A1 may also acquire data in another device as input data.

[0041] The model learning unit A2 performs model learning. Specifically, the model learning unit A2 optimizes the 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 divided into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data for training data. Unsupervised learning is a method that does not use correct answer data for training data. For example, unsupervised learning memorizes feature points from a large amount of training data and determines the correct answer (range estimation). Reinforcement learning is a method that assigns a score to the output result and learns how to maximize the score. Although supervised learning is explained below, either unsupervised learning or reinforcement learning can be applied to machine learning.

[0042] 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 inference result data to the data processing unit A4. For example, In the case of 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. There are various model approaches, 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.

[0043] The data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0044] (Deployment 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, an example of the arrangement of the functional blocks will be described along with a specific use case.

[0045] For example, there are three use cases where AI / ML technology is applied:

[0046] (1) "CSI (Channel State Information) Feedback Enhancement"

[0047] (2) "Beam management"

[0048] (3) “Positioning accuracy enhancement” Below, we will explain examples of functional block placement for each use case.

[0049] (1. Example of functional block layout for "CSI feedback improvement") "Improved CSI feedback" represents a use case in which, for example, machine learning technology is applied to the CSI fed back from UE 100 to gNB 200.

[0050] Fig. 7 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. 7, 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. In "CSI feedback improvement," for example, the following processing is performed.

[0051] That is, the UE 100 estimates channel state information (CSI) based on a CSI reference signal (CSI-RS) received from the gNB 200. The CSI generation unit 131 generates (or estimates) CSI based on the CSI-RS. The data collection unit A1 collects the CSI-RS and the CSI. The model training unit A2 creates a trained model using the CSI-RS and the CSI as training data. The model inference unit A3 inputs the (e.g., punctured) CSI-RS and CSI as inference data into the trained model, and obtains CSI as an inference result. The UE 100 transmits (or feeds back) the inference result (CSI) to the gNB 200 as inference result data. The UE 100 can generate a trained model with a predetermined accuracy or higher by repeating model training. It is expected that the inference result using the trained model generated in this way will also have a predetermined accuracy or higher.

[0052] The CSI includes at least one of a Channel Quality Indicator (CQI), a Precoding Matrix Indicator (PMI), and a Rank Indicator (RI). The CSI is used for downlink scheduling in the gNB 200.

[0053] 7, the training data is "CSI-RS" and "CSI," and the inference data is also "CSI-RS" and "CSI." Hereinafter, the training data and / or the inference data may be referred to as a "dataset."

[0054] In "improving CSI feedback," in addition to "CSI-RS" and "CSI," at least one of the following data or information may be used as data used in the dataset.

[0055] (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.)

[0056] (X2) Bit Error Rate (BER) or Block Error Rate (BLER) (The BER (or BLER) may be measured based on the CSI-RS, with the total number of transmitted bits (or the total number of transmitted blocks) known.)

[0057] (X3) The moving speed of the UE 100 (which may be measured by a speed sensor in the UE 100).

[0058] (2. Example of functional block layout in "Beam Management") "Beam management" refers to a use case in which, for example, machine learning technology is used to manage which beam is the optimal one among those transmitted from gNB200.

[0059] Figure 8 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 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. In "beam management", for example, the following processing is performed.

[0060] That is, the optimal beam determination unit 132 of UE100 determines the optimal beam based on the CSI-RS. The optimal beam determination unit 132 may determine the optimal beam based on the reception quality of the CSI-RS, etc. The data collection unit A1 collects the CSI-RS and the optimal beam (information indicating the optimal beam). The model learning unit A2 creates a trained model using the CSI-RS and the optimal beam as training data. The model inference unit A3 inputs the CSI-RS and the optimal beam as inference data into the trained model, and obtains the optimal beam as the inference result. The UE100 transmits the inference result (optimal beam) to the gNB200 as inference result data.

[0061] 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.

[0062] (Y1) SSB (Synchronization Signal Block) received from gNB200

[0063] (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 the gNB 200.)

[0064] (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.)

[0065] (Y4) Number of beams or beam pattern

[0066] (Y5) Beam measurement value(s)

[0067] (Y6) Moving speed of UE 100 (may be measured by a speed sensor in UE 100)

[0068] (3. Example of functional block layout for "improving position accuracy") "Improved location accuracy" represents a use case in which, for example, the accuracy of location information measured by UE 100 is improved by using machine learning technology.

[0069] Fig. 9 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. 9, 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. In "improving location accuracy", for example, the following processing is performed.

[0070] That is, the location information generation unit 133 of the UE 100 generates location data of the UE 100 based on a positioning reference signal (PRS) received from the gNB 200. The location information generation unit 133 may receive a GNSS signal received by a Global Navigation Satellite System (GNSS) receiver 150, and generate location data of the UE 100 based on the GNSS signal. The data collection unit A1 collects the PRS (or the GNSS signal) and the location data. The model learning unit A2 creates a trained model using the PRS (or the GNSS signal) and the location data as training data. The model inference unit A3 inputs the PRS (or the GNSS signal) and the location data as inference data into the trained model, and obtains the location data as an inference result. The UE 100 transmits the inference result (location data) to the gNB 200 as inference result data.

[0071] In "improving position accuracy," in addition to "PRS," "GNSS signal," and "position data," at least one of the following data or information may be used in the data set:

[0072] (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 the gNB 200.)

[0073] (Z2) LOS (Line of Sight) or NLOS (Non Line of Sight)

[0074] (Z3) Measurement timing, accuracy, likelihood

[0075] (Z4) RF fingerprint (cell ID and reception quality in the cell of that cell ID)

[0076] (Z5) Angle of Arrival (AOA), reception level for each antenna, reception phase for each antenna, and observed time difference of arrival for each antenna (OTDOA)

[0077] (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)

[0078] (Z7) Moving speed of UE 100 (The moving speed may be measured by GNSS receiver 150. The moving speed may be measured by a speed sensor in UE 100.)

[0079] Although examples of the arrangement of each functional block used in AI / ML technology have been described above, the arrangement examples are not limited to those shown in FIGS. 7 to 9. For example, the data collection unit A1, the model learning unit A2, and the model inference unit A3 may be arranged on the gNB 200 side, and the data processing unit A4 may be arranged on the UE 100 side. For example, in "CSI feedback improvement," the gNB 200 estimates CSI based on an SRS (Sounding Reference Signal) transmitted from the UE 100. Then, the model learning unit A2 in the gNB 200 derives a trained model based on the SRS and CSI. Furthermore, the model inference unit A3 in the gNB 200 inputs the SRS and CSI into the trained model to obtain inference result data (CSI). The gNB 200 transmits (feeds back) the CSI to the UE 100.

[0080] (Communication method according to the first embodiment) Next, a communication method according to the first embodiment will be described.

[0081] Fig. 10 is a diagram illustrating an example of the configuration of a mobile communication system 1 according to the first embodiment. As shown in Fig. 10, the mobile communication system 1 includes a transmitting entity TE and a receiving entity RE.

[0082] The transmitting entity TE may be the UE 100. In this case, the receiving entity RE may be a network device (e.g., the gNB 200 or the AMF 300).

[0083] The transmitting entity TE may also be a network device, in which case the receiving entity RE may be the UE 100.

[0084] 10, there may be a plurality of receiving entities RE, and a transmitting entity TE may transmit to a plurality of receiving entities RE.

[0085] For example, consider the following case: The transmitting entity TE derives (or creates) a trained model and transmits the derived trained model to the receiving entity RE. In this case, the transmitting entity TE may also transmit inference data used in the trained model to the receiving entity RE. Furthermore, the transmitting entity TE transmits an untrained trained model (hereinafter, may be referred to as an "untrained model") to the receiving entity RE. In this case, the transmitting entity TE may also transmit training data used in the untrained model to the receiving entity RE.

[0086] However, the receiving entity RE may not know whether it can use the trained model received from the transmitting entity TE. For example, a memory capacity required to use the trained model is required, and the receiving entity RE may not know the amount of memory capacity. In addition, the receiving entity RE may not know whether it can use the inference data received from the transmitting entity TE. Furthermore, the receiving entity RE may not know whether it can use both the untrained model and the training data.

[0087] As a result, the receiving entity may not be able to use the received trained model, and the trained model sent by the sending entity may be wasted. Similarly, the inference data, untrained models, and training data may be wasted.

[0088] Therefore, the first embodiment aims to enable the receiving entity RE to determine whether a trained model or an untrained model can be used. Also, the first embodiment aims to enable the receiving entity RE to determine whether training data or inference data can be used.

[0089] Therefore, in the first embodiment, a transmitting entity (e.g., a transmitting entity TE) transmits to a receiving entity (e.g., a receiving entity RE) first use condition information representing first use conditions when model data representing at least one of a training model and a dataset is used. Here, the training model is either an untrained model that has not been trained or a trained model that has been trained. Also, the dataset is either training data or inference data.

[0090] As a result, for example, the receiving entity RE can determine, based on the first usage condition information, whether it is possible to perform learning or inference using the learning model received from the sending entity TE, and the receiving entity RE can determine, based on the first usage condition information, whether it is possible to perform learning or inference using the data set received from the sending entity TE.

[0091] As described above, the "trained model" may be an "untrained model." The "trained model" may be a "trained model." The "trained model" is either an "untrained model" or a "trained model." Furthermore, the "dataset" may be "trained data." The "dataset" may be "inference data." The "dataset" is either "trained data" or "inference data."

[0092] As described above, at least one of the “learning model” and the “data set” may be referred to as “model data.” The “model data” may include at least one of the “learning model” and the “data set.”

[0093] (Operation example according to the first embodiment) Next, an example of operation according to the first embodiment will be described.

[0094] FIG. 11 is a diagram illustrating an example of operation according to the first embodiment.

[0095] As shown in FIG. 11, in step S10, the transmitting entity TE decides to transmit model data.

[0096] In step S11, the transmitting entity TE broadcasts the model data and the use condition information (for example, the first use condition information). The transmitting entity TE may transmit the model data and the use condition information to the receiving entity RE. The use condition information represents the use condition (for example, the first use condition) when the receiving entity RE uses the model data.

[0097] First, the usage conditions may represent the types of data sets (data sets included in the model data) transmitted from the transmitting entity TE to the receiving entity RE, e.g., for the use case of "Enhanced CSI Feedback", the types are "CSI", "RSRP", and "CSI".

[0098] Second, the usage conditions may represent the location or affiliation where the model data is used, such as location information, place name, cell name, cell ID, Tracking Area Identity (TAI), Registration Area (RA) identity, and PLMN (Public Land Mobile Network Number).

[0099] Third, the usage conditions may represent required resources. The required resources may be represented by memory capacity. The required resources may be represented by the size of the model data. The required resources may be represented by a computer performance index (e.g., FLOPS (Floating-point Operations Per Second)) (or CPU power) required when executing the model data.

[0100] Fourth, the conditions of use may be, for example: [Table 1]

[0101] The transmitting entity TE may transmit the use condition information and the model data (simultaneously), or may transmit the use condition information and then transmit the model data.

[0102] Firstly, the transmitting entity TE may transmit the use condition information using an information element containing the use condition information.

[0103] When the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200, the transmitting entity TE may transmit using an RRC message including the information element, or may transmit using a MAC CE including the information element. Similarly, when the transmitting entity TE is the gNB 200 and the receiving entity RE is the UE 100, the transmitting entity TE may transmit using an RRC message or a MAC CE.

[0104] Furthermore, when the transmitting entity TE is the UE 100 and the receiving entity RE is the AMF 300, the transmitting entity TE may transmit the information element by using a NAS message including the information element. Similarly, when the transmitting entity TE is the AMF 300 and the receiving entity RE is the UE 100, the transmitting entity TE may transmit the information element by using a NAS message.

[0105] Furthermore, when the transmitting entity TE is the UE 100 and the receiving entity RE is an OTT (Over The Top) server, the transmitting entity TE may transmit packet data including the data set using packet data of the TCP / IP protocol. When the transmitting entity TE is an OTT server and the receiving entity RE is the UE 100, the data set may also be transmitted using packet data of the TCP / IP protocol. Note that an OTT server is a server that distributes media content such as video and / or audio distributed over the Internet.

[0106] Second, the transmitting entity TE may transmit the usage condition information using a predetermined bit sequence to which the presence or absence of usage condition information is mapped. For example, assume that the first bit of the predetermined bit sequence represents "CSI-RS", the second bit represents "RSRP", the third bit represents "RSRQ", and the fourth bit represents "SINR". In such a case, the transmitting entity TE can transmit the usage condition information indicating that "CSI-RS", "RSRP", and "RSRQ" are to be used as the data set by transmitting the predetermined bit sequence "1110".

[0107] In step S12, the receiving entity RE checks the received use condition information to determine whether the model data can be used. The receiving entity RE may compare the use condition information with its own computing capabilities, etc., to determine whether the use conditions indicated in the use condition information are met. If the receiving entity RE determines that the use conditions are met, i.e., that the model data can be used, it uses the model data as is. On the other hand, if the receiving entity RE determines that the use conditions are not met, i.e., that the model data cannot be used, it does not use the model data. In the latter case, the receiving entity RE may discard the model data. The receiving entity RE may transmit information indicating that the model data cannot be used to the transmitting entity TE. In this case, the receiving entity RE may transmit the information to the transmitting entity TE by transmitting an RRC message or MAC-CE including information indicating that the model data cannot be used. Furthermore, if the receiving entity RE transmits the information indicating that the model data cannot be used to the transmitting entity TE, the receiving entity RE may transmit the conditions under which the model data can be used to the transmitting entity TE. The receiving entity RE may transmit the condition after receiving the model data, or may transmit the condition before receiving the model data, or may also transmit the condition using an RRC message or MAC CE.

[0108] (Another operation example according to the first embodiment) In the first embodiment, an example in which the transmitting entity TE transmits use condition information to the receiving entity RE has been described, but the present invention is not limited to this. For example, the receiving entity RE may transmit usable use condition information to the transmitting entity TE. The receiving entity RE may transmit the use condition information by using an RRC message or a MAC CE. In response to receiving the use condition information, the transmitting entity TE may transmit model data that satisfies the use conditions included in the use condition information to the receiving entity RE (step S11).

[0109] [Second embodiment] Next, a second embodiment will be described, focusing on the differences from the first embodiment.

[0110] In the first embodiment, an example in which the transmitting entity TE transmits a training model has been described. Also, in the first embodiment, a case in which the model name is included in the transmission condition has been described.

[0111] For example, assume the following case: the receiving entity RE has multiple learning models, and the sending entity TE sends multiple learning model names to the receiving entity RE to specify all of the multiple learning models that the receiving entity RE has.

[0112] However, when multiple learning model names are transmitted, the amount of transmitted data becomes larger than when no learning model names are transmitted.

[0113] Therefore, in the second embodiment, an example will be described in which the transmitting entity TE transmits a dataset instead of transmitting the name of a learning model. Specifically, the transmitting entity (e.g., the transmitting entity TE) transmits a dataset usable for the learning model to a receiving entity (e.g., the receiving entity RE) having the learning model without transmitting name information indicating the name of the learning model.

[0114] As described above, in the second embodiment, since the learning model name is not transmitted, it is possible to reduce the amount of transmitted data compared to when the learning model name is transmitted. Moreover, if the receiving entity RE can use the received dataset, it can use the dataset as is for the learning model, and if the received dataset cannot be used, it can avoid using the dataset. Therefore, the receiving entity RE can also process the received dataset appropriately.

[0115] (Example of operation according to the second embodiment) Fig. 12 is a diagram illustrating an example of operation according to the second embodiment. Note that before the operation illustrated in Fig. 12 starts, the receiving entity RE has one or more learning models.

[0116] As shown in Fig. 12, in step S20, the transmitting entity TE decides to transmit a data set to the receiving entity RE, the data set being usable by a learning model of the receiving entity RE.

[0117] In step S21, the transmitting entity TE broadcasts a data set, which may be sent to the receiving entity RE.

[0118] First, when the transmitting entity TE is the UE 100 and the receiving entity RE is the gNB 200, the transmitting entity TE may transmit the data set using an RRC message (or MAC CE) including the data set. When the transmitting entity TE is the gNB 200 and the receiving entity RE is the UE 100, the data set may also be transmitted using an RRC message (or MAC CE).

[0119] Secondly, when the transmitting entity TE is the UE 100 and the receiving entity RE is the AMF 300, the transmitting entity TE may transmit the data set using a NAS message including the data set. When the transmitting entity TE is the AMF 300 and the receiving entity RE is the UE 100, the data set may also be transmitted using a NAS message.

[0120] Third, when the transmitting entity TE is the UE 100 and the receiving entity RE is an OTT server, the transmitting entity TE may transmit packet data including the data set using packet data of the TCP / IP protocol. When the transmitting entity TE is an OTT server and the receiving entity RE is the UE 100, the data set may also be transmitted using packet data of the TCP / IP protocol.

[0121] It should be noted that the sending entity TE may send a training model together with the data set to the receiving entity RE, which may either be used for the training model or may not be used for the training model (or may be used in a training model already present in the receiving entity RE).

[0122] In step S22, the receiving entity RE checks whether the received data set is usable. If the received data set is usable, the receiving entity RE uses the data set for the training model. If the received data set is not usable, the receiving entity RE does not use the data set for the training model. In the latter case, the receiving entity RE may discard the data set. In this case, the receiving entity RE may transmit information indicating that the data set has been discarded to the transmitting entity TE. The information may be transmitted using an RRC message, a MAC CE, or a NAS message. The receiving entity RE may also transmit a reason for the discard (e.g., the target data is not usable) to the transmitting entity TE. Furthermore, the receiving entity RE may transmit information indicating a suitable data set (e.g., identification information of a suitable data set) to the transmitting entity TE. The receiving entity RE may transmit the information indicating the discard, together with the reason for the discard and information indicating a suitable data set, to the transmitting entity TE. The information indicating the discard reason and the suitable data set may also be transmitted using an RRC message, a MAC CE, or a NAS message.

[0123] (Another operation example according to the second embodiment) In step S21, the transmitting entity TE may transmit the type of use case in which the data set is used together with the data set. For example, if the data set is "CSI-RS", there are two cases in which "CSI-RS" is used for "CSI feedback enhancement" and "beam management". By transmitting the use case type, the transmitting entity TE can notify the receiving entity RE of the use case in which the data set is used.

[0124] [Third embodiment] Next, a third embodiment will be described, focusing on the differences from the first embodiment.

[0125] For example, assume the following case. That is, the UE 100 derives a trained model. The trained model is a model derived in an "urban" environment. In such a case, it is desirable that the UE 100 connects to a cell in an "urban" environment, not a cell in a "rural" environment, and performs inference on the trained model.

[0126] Therefore, the third embodiment aims to enable the UE 100 to appropriately connect to a cell in which a learning model is available.

[0127] Therefore, in the third embodiment, first, the user equipment (e.g., UE100) transmits second use condition information representing second use conditions when using the learning model to the base station (e.g., gNB200) based on the first use condition information (e.g., use condition information received from the transmitting entity TE). Second, the user equipment connects to a cell that satisfies the second use condition.

[0128] This allows the UE 100 to connect to an appropriate cell that satisfies the use condition (or the second use condition) when executing the learning model, for example.

[0129] (Operation example according to the third embodiment) Next, an operation example according to the third embodiment will be described.

[0130] Fig. 13 is a diagram illustrating an example of operation according to the third embodiment. In the example of operation illustrated in Fig. 13, the UE 100 will be described as already having a learning model.

[0131] 13, in step S30, the transmitting entity TE transmits, to the UE 100, use condition information (or first use condition information) of the learning model that the UE 100 has. The use condition information may be transmitted by an RRC message, a MAC CE, or a NAS message.

[0132] In step S31, the UE 100 transitions to an RRC idle state or an RRC inactive state.

[0133] In step S32, UE 100 executes a cell reselection procedure. For example, UE 100 selects a cell that matches the learning model, and executes the cell reselection procedure by setting the frequency priority for the cell to the highest priority. Alternatively, UE 100 may select a tracking area that matches the learning model, and executes the cell reselection procedure by setting the frequency priority for a cell in the tracking area to the highest priority. Note that the cell ID of the cell and the tracking area code (TAC) of the tracking area are broadcast by gNB 200 using system information. UE 100 camps on the cell reselected by the cell reselection procedure.

[0134] In step S33, when UE100 transitions to the RRC connected state, it transmits to gNB200 usage condition information (or second usage condition information) representing the usage conditions (or second usage conditions) of the learning model. The first usage conditions may be the usage conditions of the learning model requested by the transmitting entity TE. The second usage conditions may be the usage conditions of the learning model requested by UE100. The first usage conditions and the second usage conditions may be different or the same. For example, the first usage conditions may be "rural" and the second usage conditions may be "urban", etc.

[0135] First, the UE 100 may transmit the second use condition information in a random access procedure for the cell reselected (or camped-on cell) in step S32. In this case, the UE 100 may transmit the second use condition information by including it in MSG3 (for example, an RRC setup request (RRCSetupRequest) message or an RRC resume request (RRCResumeRequest) message).

[0136] Second, the UE 100 may transmit the second use condition information after entering the RRC connected state. In this case, the UE 100 may include the second use condition information in a UE Assistance Information message and transmit it to the gNB 200. Alternatively, the UE 100 may include the second use condition information in a UE Capability Information message and transmit it to the gNB 200. Alternatively, the UE 100 may transmit an NAS message including the second use condition information to the AMF 300. Alternatively, the UE 100 may transmit a measurement report including the second use condition information to the gNB 200, triggered by confirming that the first use condition and the second use condition are different. The gNB 200 may transmit an RRC Reconfiguration message including a conditional Reconfiguration indicating that the measurement report will be transmitted in response to the confirmation, to the UE 100, thereby causing the UE 100 to transmit the measurement report.

[0137] In step S34, the gNB 200 controls the connection destination of the UE 100 in accordance with the second use condition. For example, when the gNB 200 confirms that the UE 100 is connected to a cell that satisfies the second use condition, the series of processes ends. In this case, the UE 100 connects to the cell reselected by the cell reselection procedure, since the cell satisfies the second use condition.

[0138] On the other hand, when the gNB 200 confirms that the UE 100 is not connected to a cell that satisfies the second use condition, the gNB 200 may perform a process to connect the UE 100 to the cell that satisfies the second use condition. Specifically, in step S35, the gNB 200 may issue a handover instruction to the UE 100 to the cell. In this case, in response to receiving the measurement report in step S33, the gNB 200 may transmit an RRCReconfiguration message including a handover command to the cell to the UE 100. In response to receiving the message, the UE 100 performs a connection process to the cell that satisfies the second use condition, thereby being able to connect to the cell.

[0139] (Another operation example 1 according to the third embodiment) In the third embodiment, an example has been described in which the UE 100 performs a cell reselection procedure to connect to a cell that applies to the learning model (or a cell that satisfies the second use condition), but this is not limiting. For example, the UE 100 may perform a cell selection procedure to connect to a cell that matches the learning model.

[0140] In this case, in step S31 of FIG. 13, the power-on state is entered instead of the RRC idle state or the RRC inactive state.

[0141] Also, in step S32, a cell selection procedure is performed instead of the cell reselection procedure. In the cell selection procedure, the UE 100 may select a cell that matches the learning model, and may perform the cell selection procedure by setting the frequency priority for the selected cell to the highest priority.

[0142] (Another operation example 2 according to the third embodiment) In the third embodiment, an example has been described in which UE100 performs a cell reselection procedure to connect to a cell that applies to the learning model (or a cell that satisfies the second usage condition), but this is not limited to this. For example, UE100 may perform a slice-specific cell reselection procedure to connect to a cell that conforms to the learning model. Note that the slice-specific cell reselection procedure is, for example, a procedure that enables reselection to a cell that supports a desired network slice.

[0143] FIG. 14 is a diagram illustrating another operation example 2 according to the third embodiment.

[0144] 14, in step S40, the AMF 300 transmits slice information including the first usage condition to the UE 100. The slice information may include the priority of one or more slices. The slice information may be an NSAG (Network Slice Access Stratum Group) message.

[0145] In step S42, the UE 100 executes a slice-specific cell reselection procedure using the slice information. The UE 100 may execute the procedure by giving the highest priority to the frequency supporting the cell so that the cell conforming to the learning model can be selected preferentially. In this case, the UE 100 can connect to the cell by executing a random access procedure for the cell on which it is camped.

[0146] In addition, when establishing a PDU session with the network, UE100 may request the network to connect to a network slice that matches its own learning model. Specifically, UE100 may send a PDU Session Establishment Request message including a connection request to the network slice to AMF300. The network (e.g., AMF300) may send to UE100 a message (e.g., a PDU Session Establishment Accept message) that permits UE100 to connect to a cell that supports the network slice. This enables UE100 to perform model learning or inference using a network slice that matches its own learning model.

[0147] [Other embodiments] 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.

[0148] In the above-described embodiment and example, 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.

[0149] Also, the term "network node" primarily refers to a base station, but may also refer to a device in the core network or part of a base station (CU, DU, or RU).

[0150] A program may be provided that causes a computer to execute each process performed by UE100 or gNB200. The program may be recorded on a computer-readable medium. The computer-readable medium can be used to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory 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 UE100 or gNB200 may be integrated, and at least a part of UE100 or gNB200 may be configured as a semiconductor integrated circuit (chip set, SoC: System on a chip).

[0151] Although the first to third embodiments have been described above mainly in terms of supervised learning, the present invention is not limited to this. For example, the first to third embodiments may be applied to unsupervised learning or reinforcement learning.

[0152] Also, a program (information processing program) that causes a computer to execute each process or function according to the above-described embodiment may be provided. Alternatively, a program (e.g., a mobile communication program) that causes the mobile communication system 1 to execute each process or function according to the above-described embodiment may be provided. The program may be recorded on a computer-readable medium. Using the computer-readable medium, it is possible to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-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. Such a recording medium may be a memory included in the UE 100 and the gNB 200.

[0153] 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.

[0154] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes can be made without departing from the spirit of the invention. Furthermore, it is also possible to combine the embodiments, operation examples, or processes within a consistent range.

[0155] This application claims priority from Japanese Patent Application No. 2022-175869 (filed November 1, 2022), the entire contents of which are incorporated herein by reference.

[0156] (Addendum) (Appendix 1) A communication method in a mobile communication system, comprising: a transmitting entity transmitting, to a receiving entity, first use condition information representing first use conditions under which model data representing at least one of a learning model and a dataset is used; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. Communication method.

[0157] (Appendix 2) The step of transmitting includes a step of the transmitting entity transmitting the first usage condition information and the model data. The communication method described in Appendix 1.

[0158] (Appendix 3) The step of transmitting includes a step of the transmitting entity transmitting the model data after transmitting the first usage condition information. 1. A communication method according to claim 1 or 2.

[0159] (Appendix 4) The step of transmitting includes a step of the sending entity transmitting the first use condition information to the receiving entity using an information element including the first use condition information. 4. A communication method according to any one of claims 1 to 3.

[0160] (Appendix 5) The transmitting step includes a step in which the transmitting entity transmits the first usage condition information to the receiving entity using a predetermined bit string to which the presence or absence of the first usage condition information is mapped. 5. A communication method according to any one of claims 1 to 4.

[0161] (Appendix 6) the receiving entity is a user equipment, The user device transmits, to a network node, second use condition information representing second use conditions when using the learning model based on the first use condition information; and the user equipment further comprises connecting to a cell that satisfies the second condition of use. A communication method according to any one of Supplementary Note 1 to Supplementary Note 5.

[0162] (Appendix 7) The method further comprises the step of: performing a process by the network node to connect the user equipment to the cell that satisfies the second condition of use; The step of connecting includes the step of the user equipment connecting to the cell according to the process. 7. A communication method according to any one of Supplementary Note 1 to Supplementary Note 6.

[0163] (Appendix 8) The sending entity is an access mobility management device, and the receiving entity is a user equipment; the transmitting step includes a step of the access mobility management device transmitting slice priority information indicating a priority for each slice to the user device; The slice priority information includes the first use condition information. 8. A communication method according to any one of Supplementary Note 1 to Supplementary Note 7.

[0164] (Appendix 9) A communication method in a mobile communication system, comprising: a sending entity sending a dataset usable by the learning model to a receiving entity having the learning model without sending name information indicating the name of the learning model; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. Communication method. [Explanation of symbols]

[0165] 1: Mobile communication system 20:5GC(CN) 100:UE 110: Receiving unit 120: Transmitter 130: Control unit 131:CSI generation unit 132: Optimal beam determination unit 133: Location information generation unit 150: GNSS receiver 200:gNB 210: Transmitter 220: Receiving unit 230: Control unit A1: Data collection section A2: Model learning section A3: Model inference part A4: Data processing section TE: Sending Entity RE: Receiving entity

Claims

1. A communication method in a mobile communication system, comprising: a transmitting entity transmitting, to a receiving entity, first use condition information representing first use conditions under which model data representing at least one of a learning model and a dataset is used; The receiving entity is a user equipment, and the user equipment transmits second use condition information representing second use conditions when using the learning model to a network node based on the first use condition information; The user equipment connects to a cell that satisfies the second condition of use; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. Communication method.

2. The transmitting step includes the transmitting entity transmitting the first usage condition information and the model data. The communication method according to claim 1.

3. The transmitting step includes the transmitting entity transmitting the model data after transmitting the first usage condition information. The communication method according to claim 1.

4. The transmitting step includes the transmitting entity transmitting the first usage condition information to the receiving entity using an information element including the first usage condition information. The communication method according to claim 1.

5. The transmitting step includes transmitting the first usage condition information to the receiving entity by using a predetermined bit string to which the presence or absence of the first usage condition information is mapped. The communication method according to claim 1.

6. The network node further performs a process of connecting the user equipment to the cell that satisfies the second condition of use, The connecting includes the user equipment connecting to the cell according to the process. The communication method according to claim 1.

7. A communication method in a mobile communication system, comprising: a transmitting entity transmitting, to a receiving entity, first use condition information representing a first use condition under which model data representing at least one of a learning model and a dataset is used; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, the dataset is either training data or inference data, the sending entity is an access mobility management device and the receiving entity is a user equipment; The transmitting step includes the access mobility management device transmitting slice priority information indicating a priority for each slice to the user device; The slice priority information includes the first use condition information. Communication method.

8. A communication method in a mobile communication system, comprising: A sending entity transmits a dataset usable by the learning model to a receiving entity having the learning model without transmitting name information indicating the name of the learning model; the receiving entity determining whether the received dataset is usable without identifying the learning model; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. Communication method.

9. A user equipment in a mobile communication system, a receiving unit that receives, from the access mobility management device, first use condition information that indicates a first use condition when model data that indicates at least one of a learning model and a data set is used; a transmitting unit that transmits second use condition information representing second use conditions when using the learning model to a network node based on the first use condition information; a control unit that connects to a cell that satisfies the second use condition, The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. User equipment.

10. A user equipment in a mobile communication system, a receiving unit having a learning model and receiving a data set usable in the learning model from an access mobility management device, instead of name information indicating the name of the learning model; A control unit that determines whether the received dataset is usable without specifying the learning model, The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. User equipment.

11. An access mobility management device in a mobile communication system, comprising: a transmitter that transmits, to a user device, first use condition information that represents a first use condition when model data that represents at least one of a learning model and a data set is used, and slice priority information that includes the first use condition information and represents a priority for each slice; The learning model is either an unlearned model that has not been learned or a learned model that has been learned, The data set is either training data or inference data. Access mobility management device.

Images