COMMUNICATION METHOD, USER EQUIPMENT AND NETWORK NODE

Abstract

Provided is a communication method in a mobile communication system including a first user device, a second user device, and a base station that can communicate with the first user device and the second user device and derive a first trained model using first training data and derive a second trained model using second training data. The communication method comprises a step for either the base station or the first user device associating environmental data representing an environmental state of the first user device with the first training data.

Description

Communication Method

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

[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.

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

[0004] According to one aspect, a communication method is provided in a mobile communication system including a first user device, a second user device, and a base station capable of communicating with the first user device and the second user device, the system including: deriving a first trained model using first training data; and deriving a second trained model using second training data. The communication method includes a step in which either the base station or the first user device associates environmental data representing an environmental state of the first user device with the first training data.

[0005] 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 a first operation scenario according to the first embodiment. FIG. 8 is a diagram showing an example of the configuration of a UE and a gNB according to the first embodiment. FIG. 9 is a diagram showing an example of the configuration of a UE and a gNB according to the first embodiment. FIG. 10 is a diagram showing an example of the operation of the first operation scenario according to the first embodiment. FIG. 11 is a diagram showing an example of a second operation scenario according to the first embodiment. FIG. 12 is a diagram showing an example of the configuration of a UE and a gNB according to the first embodiment. FIG. 13 is a diagram showing an example of the configuration of a UE and a gNB according to the first embodiment. FIG. 14 is a diagram showing an example of the operation of the second operation scenario according to the first embodiment. Fig. 15 is a diagram showing a configuration example of a UE and a gNB according to the first embodiment. Fig. 16 is a diagram showing a configuration example of a UE and a gNB according to the first embodiment. Fig. 17 is a diagram showing a configuration example of a UE and a gNB according to the first embodiment. Fig. 18 is a diagram showing a configuration example of a UE and a gNB according to the first embodiment.

[0006] When attempting to apply machine learning technology to mobile communication systems, it has not yet been established how to utilize machine learning technology.

[0007] Therefore, an object of the present disclosure is to enable appropriate utilization of machine learning techniques in mobile communication systems.

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

[0017] The transmitting unit 120 performs various transmissions under the control of the control unit 130. The transmitting unit 120 includes an antenna and a transmitter. The transmitter converts a baseband signal (transmission signal) output by the control unit 130 into a radio signal and transmits it from the antenna.

[0018] The control unit 130 performs various controls and processes in the UE 100. Such processes include processes of each layer described below. The control unit 130 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used in the processes by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation / demodulation and encoding / decoding of baseband signals. The CPU executes programs stored in the memory to perform various processes.

[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, 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. The CPU executes programs stored in the memory to perform various processes.

[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 the successfully decoded DCI as DCI addressed to the UE. The DCI transmitted from gNB200 has a CRC 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 the UE's 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 300A. 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, 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.

[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. Although supervised learning will be described below, unsupervised learning and / or reinforcement learning may also be applied as machine learning.

[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 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 in which the slope and intercept are optimized, for example, "y = 5x + 3", is a trained model. Here, there are various model approaches, such as 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.

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

[0043] (Application Example of First Embodiment) In the first embodiment, an example in which machine learning technology is applied to the mobile communication system 1 will be described. Specifically, two operation scenarios will be described. That is, there is an operation scenario in which model learning and model inference are performed in the UE 100, and an operation scenario in which model learning and model inference are performed in the gNB 200.

[0044] Three operation scenarios will be described as examples of operation scenarios in which model learning and model inference are performed in the UE 100. That is, an operation scenario (first operation scenario) using channel state information (CSI) feedback (CSI feedback enhancement), an operation scenario (third operation scenario) using beam management, and an operation scenario (fourth operation scenario) using positioning accuracy enhancement.

[0045] On the other hand, in the operating scenario in which model learning and model inference are performed in gNB200, an operating scenario (second operating scenario) using CSI feedback using SRS (Sounding Reference Signal) will be described.

[0046] To avoid insufficient learning, a learner (UE100 or gNB200) may perform machine learning using a large amount of learning data. Therefore, the learner may use learning data from outside its own environment. For example, UE100-2 (learner) receives the learning data used for machine learning in UE100-1 via gNB200 or CN20 and performs machine learning using the learning data.

[0047] In this case, if a learner uses training data that does not apply to their own environment, they will perform incorrect machine learning. As a result, the trained model derived through machine learning cannot be said to be an appropriate learning model. Even if an inference result is obtained using a trained model obtained in this way, the inference result may deviate significantly from the correct answer.

[0048] For example, it is assumed that the UE 100-2 (learner) is in a stationary environment and the learning data of the UE 100-1 is learning data acquired when the UE 100-1 is moving. In this case, if the UE 100-2 adopts the learning data of the UE 100-1, the accuracy rate of the inference result inferred from the trained model may be lower than in a case where the learning data is not adopted.

[0049] Therefore, the first embodiment aims to appropriately utilize machine learning technology in the mobile communication system 1 by avoiding the use of learning data that is not suitable for the mobile communication system's own environment for machine learning.

[0050] (1) First Operation Scenario FIG. 7 is a diagram illustrating an example of a first operation scenario according to the first embodiment.

[0051] As shown in Figure 7, the mobile communication system 1 in the first operating scenario includes UE100-1 (e.g., a first user device) and UE100-2 (e.g., a second user device), and a gNB200 (e.g., a base station) capable of communicating with UE100-1 and UE100-2.

[0052] In the first operation scenario, in UE100-1 (e.g., first user device), machine learning is performed using training data (e.g., first training data) to derive a trained model (e.g., first trained model). Also, in the first operation scenario, in UE100-2 (e.g., second user device), machine learning is performed using training data (e.g., second training data) to derive a trained model (e.g., second trained model).

[0053] In addition, in the first operating scenario, UE100-2 can derive a learned model (e.g., a second learned model) using the learned data (e.g., the first learned data) used by UE100-1 when deriving the learned model (e.g., the first learned model).

[0054] In this case, in the first operating scenario, either gNB200 (e.g., a base station) or UE100-1 (e.g., a first user device) links environmental data representing the environmental conditions in UE100-1 to the learning data of UE100-1.

[0055] By such linking, the UE 100-2 that has received the environmental data of the UE 100-1 and the learning data of the UE 100-1 can determine whether or not to perform machine learning using the learning data of the UE 100-1, based on the environmental data of the UE 100-1. As a result, the UE 100-2 can avoid using learning data that is not suitable for its own environment (for example, the learning data of the UE 100-1) for machine learning, and can appropriately utilize machine learning technology in the mobile communication system 1.

[0056] (1.1) Example of functional block arrangement Figures 8 and 9 are diagrams showing an example of the configuration of UE100-1 and 100-2 and gNB200 in the first operation scenario according to the first embodiment. As shown in Figures 8 and 9, in the first operation scenario, a data collection unit A1, a model learning unit A2, and a model inference unit A3 are arranged in UE100-1 and 100-2 (e.g., control units 130-1 and 130-2). In addition, a data processing unit A4 is arranged in gNB200 (e.g., control unit 230). In other words, model learning and model inference are performed in UE100.

[0057] In the first operation scenario, machine learning technology is introduced into CSI feedback from UE100-1 and 100-2 to gNB200. The CSI transmitted (feedback) from UE100-1 and 100-2 to gNB200 is information indicating the channel state of the downlink between UE100-1 and 100-2 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 downlink scheduling and the like based on the CSI.

[0058] The gNB 200 transmits a reference signal for the UE 100 to estimate the downlink channel state. Such a reference signal may be, for example, a CSI reference signal (CSI-RS) and / or a demodulation reference signal (DMRS). In the description of the first operation scenario, the reference signal is described as being a CSI-RS.

[0059] First, in model learning in the UE 100-1, the receiving unit 110-1 of the UE 100-1 receives the CSI-RS transmitted from the gNB 200 (hereinafter, the CSI-RS received by the UE 100-1 may be referred to as "CSI-RS #1"). The CSI generating unit 131-1 performs channel estimation using the CSI-RS #1 to generate CSI. The data collecting unit A1 inputs the CSI-RS #1 and the CSI generated by the CSI generating unit 131-1, and outputs the CSI-RS #1 and the CSI to the model learning unit A2 as learning data. The model learning unit A2 derives a learned model (for example, a first learned model) using the learning data (CSI-RS #1 and CSI).

[0060] Secondly, in the model inference in the UE 100-1, the receiving unit 110-1 of the UE 100-1 receives the CSI-RS from the gNB 200 using fewer resources than when receiving the CSI-RS #1. Such a CSI-RS may be referred to as a partial CSI-RS or a punctured CSI-RS (punctured CSI-RS) hereinafter. The model inference unit A3 uses the learned model to infer the CSI from the inference data including the partial CSI-RS as inference result data.

[0061] The model learning in the UE 100-2 is basically the same as the model learning in the UE 100-1. The CSI-RS received by the UE 100-2 may be referred to as "CSI-RS#2". The CSI generation unit 131-2 of the UE 100-2 generates CSI from the CSI-RS#2. The data collection unit A1 outputs the CSI-RS#2 and the CSI generated from the CSI-RS#2 to the model learning unit A2 as learning data. The model learning unit A2 performs machine learning using the CSI-RS#2 and the CSI as learning data, and derives a learned model (for example, a second learned model).

[0062] Furthermore, the model inference in the UE 100-2 is basically the same as the model inference in the UE 100-1. The model inference unit A3 of the UE 100-2 performs model inference from inference data including a partial CSI-RS, and outputs inference result data (CSI).

[0063] In addition, the gNB 200 may transmit partial CSI-RS by reducing the number of antenna ports for full CSI-RS that is not partial. Antenna ports are an example of resources. In addition, the gNB 200 may transmit partial CSI-RS by using resources in which time-frequency resources are reduced compared to full CSI-RS.

[0064] In this manner, the data collection unit A1, the model learning unit A2, the model inference unit A3, and the data processing unit A4 are arranged in the UEs 100-1 and 100-2 and the gNB 200.

[0065] (1.2) Acquisition of Environmental Data In the first operation scenario, the environmental data acquisition unit 140-1 of the UE 100-1 can acquire environmental data representing the environmental state of the UE 100-1. The environmental data acquisition unit 140-1 may generate environmental data for the UE 100-1 in response to acquiring learning data for the UE 100-1. The environmental data is, for example, environmental data obtained when the learning data is acquired in the UE 100-1. The environmental data acquisition unit 140-1 can transmit the environmental data for the UE 100-1 to the gNB 200 via the transmission unit 120-1.

[0066] The environmental data of UE100-1 may be acquired by gNB200. In this case, the environmental data acquisition unit 240 of gNB200 can acquire the environmental data of UE100-1 based on a received signal received from UE100-1. For example, the environmental data acquisition unit 240 may acquire the environmental data based on measurement data transmitted from UE100-1 using the functions of SON (Self-Organizing Networks) and / or MDT (Minimization of Drive Tests). SON is a technology for autonomously organizing or optimizing a network. Using the SON function, gNB200 can acquire measurement data of the radio environment from UE100-1. Furthermore, MDT is a technology that supports the collection of measurement values ​​specific to UE100-1. For example, gNB200 can acquire measurement data collected during a drive test using a radio wave measurement vehicle from UE100-1. In addition, the environmental data acquisition unit 240 of gNB200 may use the received power or reception quality of the signal received from UE100-1 as environmental data.

[0067] When environmental data is acquired by the environmental data acquisition unit 240 of the gNB 200, the UE 100-1 may transmit to the gNB 200 an environmental condition request requesting the environmental conditions desired by the UE 100-1. The environmental conditions represent conditions that the UE 100-1 desires to use as environmental data, such as environmental data in which the distance from the UE 100-1 is within a distance threshold (or greater than or equal to the distance threshold), or environmental data in which the movement speed of the UE 100-1 is within a speed threshold (or greater than or equal to the speed threshold). The UE 100-1 may transmit an environmental condition request including the request in an RRC message, a MAC Control Element (CE), or uplink control information (UCI). The environmental data acquisition unit 240 of the gNB 200 generates environmental data that matches (or satisfies) the environmental conditions based on the environmental condition request. In this way, the UE 100-1 can set environmental data that matches (or satisfies) the environmental conditions, and therefore, it is possible to set the environmental data so that the amount of environmental data does not become too large.

[0068] (1.3) Linking environmental data with learning data Then, in the first operating scenario, either UE100-1 or gNB200 can link UE100-1's environmental data to UE100-1's learning data (e.g., first learning data).

[0069] First, when the environmental data acquisition unit 140-1 of the UE 100-1 acquires environmental data, the linking may be performed in the UE 100-1. In this case, for example, the environmental data acquisition unit 140-1 acquires learning data from the data collection unit A1 and generates environmental data in response to the acquisition of the learning data. Then, the environmental data acquisition unit 140-1 links the learning data to the environmental data. The environmental data acquisition unit 140-1 transmits the learning data and the environmental data to the gNB 200 via the transmission unit 120-1.

[0070] Secondly, when the environmental data acquisition unit 140-1 of the UE 100-1 acquires environmental data, the linking may be performed in the gNB 200. In this case, for example, the environmental data acquisition unit 140-1 acquires learning data from the data collection unit A1, and generates environmental data in response to acquiring the learning data. The environmental data acquisition unit 140-1 transmits the learning data and environmental data to the gNB 200 via the transmission unit 120-1. The control unit 230 of the gNB 200 links the environmental data and the learning data.

[0071] Thirdly, when the environmental data acquisition unit 240 of the gNB 200 acquires environmental data, the linking may be performed in the gNB 200. In this case, the data collection unit A1 (control unit 130-1) of the UE 100-1 transmits the learning data used by the UE 100-1 to the gNB 200 via the transmission unit 120-1. Then, the control unit 230 of the gNB 200 inputs the learning data from the receiving unit 220, inputs the environmental data from the environmental data acquisition unit 240, and links the environmental data to the learning data.

[0072] In this way, gNB200 acquires learning data of associated UE100-1 and environmental data of UE100-1.

[0073] Then, the gNB 200 transmits the learning data of the associated UE 100-1 and the environmental data of the UE 100-1 to the UE 100-2. In the UE 100-2 that has received the learning data of the UE 100-1 and the environmental data of the UE 100-1, for example, the following processing is performed.

[0074] That is, the receiving unit 110-2 of the UE 100-2 receives the learning data of the UE 100-1 and the environmental data of the UE 100-1, and outputs the received learning data and environmental data to the data collecting unit A1. The data collecting unit A1 (or the control unit 230) determines whether or not to perform machine learning using the learning data of the UE 100-1 based on the environmental data of the UE 100-1. If, as a result of checking the environmental data, the environmental data is (significantly) different from the environment of the UE 100-2, the data collecting unit A1 may decide not to perform machine learning using the learning data of the UE 100-1. In this case, the data collecting unit A1 may discard the learning data. If the data collecting unit A1 determines not to perform machine learning using the learning data of the UE 100-1, it may decide to perform machine learning using the learning data of the UE 100-1 in order to derive another trained model (e.g., a third trained model) in the UE 100-2. In this case, the data collection unit A1 may output the learning data of the UE 100-1 to a part of the model learning unit A2 that derives other learned models.

[0075] (1.4) Environmental Data Next, a specific example of environmental data will be described. The environmental data may include at least any of the following information:

[0076] Movement speed information indicating the movement speed of the UE 100-1 For example, the UE 100-1 has a speed sensor. The environmental data acquisition unit 140-1 may be the speed sensor. The speed sensor can acquire the movement speed information of the UE 100-1.

[0077] Orientation information indicating the orientation of the UE 100-1 For example, the UE 100-1 includes an orientation sensor (for example, a gyro sensor or a geomagnetic sensor). The environmental data acquisition unit 140-1 may be the orientation sensor. The orientation sensor can acquire the orientation information of the UE 100-1.

[0078] Transmission power information indicating the transmission power of the UE 100-1 For example, the environmental data acquisition unit 140-1 of the UE 100-1 can obtain the transmission power information by acquiring, from the transmission unit 120-1, the transmission power when transmitting a transmission signal from the transmission unit 120-1.

[0079] Location information representing the location of UE100-1 For example, UE100-1 has a GNSS (Global Navigation Satellite System) receiver. The environmental data acquisition unit 140-1 may include a GNSS receiver. The GNSS receiver may acquire location information representing the location of UE100-1 based on the GNSS reception signal. The location information may be represented by latitude and longitude. The location information may also represent the distance from the gNB200. In this case, the GNSS receiver acquires the location of UE100-1, and assuming that the location of the gNB200 is known, may acquire the distance between the gNB200 and UE100-1 from the locations of UE100-1 and gNB200. Furthermore, the location information may be represented by altitude. The altitude may represent height from ground level. The altitude may represent height from sea level (i.e., above sea level). For example, the altitude may be acquired by a GNSS receiving unit, or by an altitude sensor in the UE 100-1. The altitude sensor may also be included in the environmental data acquiring unit 140-1.

[0080] Field density information representing the field density of the UE 100-1 The field density information is information representing the type of location where the UE 100-1 is located, such as whether the location where the UE 100-1 is located is urban or rural. For example, the UE 100-1 has a GNSS receiver. The GNSS receiver may be included in the environmental data acquisition unit 140-1. The GNSS receiver, for example, stores map information in advance in a memory or the like. The GNSS receiver acquires field density information representing the field density based on, for example, the acquired position of the UE 100-1 and the map information.

[0081] Line-of-sight information indicating whether the first user device is outside the line-of-sight or within the line-of-sight. The line-of-sight information is, for example, information indicating whether the propagation path of the radio signal of the UE 100-1 to the gNB 200 is within the line-of-sight (LOS: Light Of Sight) or whether the propagation path of the radio signal of the UE 100-1 to the gNB 200 is outside the line-of-sight (NLOS: Non Light Of Sight). As in the case of field density information, the GNSS receiver may acquire the line-of-sight information based on the position of the UE 100-1 and map information.

[0082] Time information For example, the UE 100-1 has a timer. The environmental data acquisition unit 140-1 may include the timer. The time information is acquired by the timer. Alternatively, the time information may be acquired by a GNSS receiving unit included in the UE 100-1. The time information may include date information.

[0083] Antenna information regarding the antenna of the UE 100-1 The antenna information may include the number of antenna ports of the antenna that the UE 100-1 has. The antenna information may also include the antenna angle of the antenna. The environmental data acquisition unit 140-1 may acquire the antenna information by reading out the antenna information stored in a memory in the UE 100-1.

[0084] Type information indicating the type of the UE 100-1 The type information is, for example, information indicating what type of UE the UE 100-1 is. The type information may include a smartphone, an Internet of Things (IoT) device, a Vehicle to Everything (V2X) target device, a UE compatible with an Integrated Access Backhaul (IAB), a model number, or a manufacturer identification number. The environmental data acquisition unit 140-1 may acquire the type information by reading the type information from a memory in the UE 100-1.

[0085] Measurement information measurable from a received signal received by the UE 100-1 The measurement information may include measurable reception quality. The reception quality may be Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), path loss, or the like. The environmental data acquisition unit 140-1 or the receiving unit 110-1 may acquire the measurement information by measuring the received signal based on the received signal received by the receiving unit 110-1.

[0086] Reliability performance indicator (KPI: Key Performance Indicator) of learning data or reliability index of learning data The KPI or reliability index is, for example, an index indicating the level of accuracy required for the learning data. The KPI or reliability index may be an index indicating a goal of the learning data. For example, the environmental data acquisition unit 140-1 may calculate the KPI or reliability index based on the above-mentioned measurement information. The KPI or reliability index may be set based on an input from a user who uses the UE 100-1.

[0087] Area information indicating the area in which UE 100-1 is located Area information is TAI (Tracking Area Identity), RA (Registration Area), PLMN (Public Land Mobile Network), PCI (Physical Cell Identity), or CGI (Cell Global Identity). TA includes one or more cells and indicates an area in which UE 100 in RRC idle state can move without updating the MME. TAI represents an identifier for identifying each TA from other TAs. RA includes one or more cells and is defined as a collection of TAs. PLMN represents the range in which a communication carrier can provide services. PCI represents a cell identifier for identifying each cell from other cells.

[0088] The region information is, for example, broadcast using broadcast information (SIB) from the gNB 200. Therefore, the receiving unit 110-1 of the UE 100-1 receives the region information, and the environmental data acquisition unit 140-1 receives the region information from the receiving unit 110-1, thereby acquiring the region information.

[0089] Frequency information used by UE 100-1 Frequency information used by UE 100-1 may be included in the environmental data. Environmental data acquisition unit 140-1 of UE 100-1 may acquire the frequency information from receiving unit 110-1 and / or transmitting unit 120-1. The frequency information may be represented by an absolute frequency radio channel number (AFRCN).

[0090] Trained model type information indicating the type of trained model derived in UE 100-1 The trained model type information includes, for example, information indicating what learning algorithm was used to derive the trained model. For example, the trained model type information includes linear regression analysis, decision tree, logistic regression, k-nearest neighbor method, support vector machine, clustering, k-means method, principal component analysis, or neural network. For example, the trained model type information is stored in the memory of UE 100-1, and therefore, the environmental data acquisition unit 140-1 can acquire the trained model type information by reading it from the memory.

[0091] Trained model configuration information representing the configuration of the trained model The trained model configuration information includes, for example, information representing the configuration of the trained model. Specifically, the trained model configuration information includes the number of stages of the neural network, the number of neurons that can be supported (the number of neurons per stage), etc. For example, the trained model configuration information is stored in the memory of the UE 100-1, and therefore, the environmental data acquisition unit 140-1 can acquire the trained model configuration information by reading it from the memory.

[0092] AI identifier information indicating an individual AI identifier The AI ​​identifier information indicates, for example, the identifier of the AI ​​used in the UE 100-1. The AI ​​identifier information may also be identifier information according to the purpose or environmental conditions, such as an AI for stationary conditions, an AI for low-speed movement, an AI for high-speed movement, or an AI for a specific location. For example, since the AI ​​identifier is stored in the memory of the UE 100-1, the environmental data acquisition unit 140-1 can acquire it by reading it from the memory.

[0093] (1.5) Example of Operation of First Operation Scenario Next, a description will be given of an example of operation of the first operation scenario according to the embodiment 1. Fig. 10 is a diagram showing an example of operation of the first operation scenario.

[0094] It is assumed that, when the operation example illustrated in FIG. 10 is performed, model learning is being performed for each of the UE 100-1 and the UE 100-2.

[0095] 10 is performed, a message including instruction information instructing the linking of the learning data with the environmental data may be transmitted. For example, when the gNB200 links the environmental data to the learning data of the UE100-1, the core network device may transmit a message (e.g., a first message) including instruction information instructing the linking to the gNB200. In this case, the core network device may transmit an NG message including the instruction information to the gNB200. Furthermore, when the UE100-1 links the environmental data to the learning data of the UE100-1, the gNB200 may transmit a message (e.g., a second message) including instruction information instructing the linking to the UE100-2. In this case, the gNB200 may transmit an RRC message, a MAC CE, or a DCI including the instruction information to the UE100-1.

[0096] In step S10, the gNB 200 acquires environmental data of the UE 100-1. The gNB 200 may receive the environmental data acquired by the UE 100-1 from the UE 100-1 (step S11).

[0097] In step S12, gNB200 transmits CSI-RS#1 to UE100-1.

[0098] In step S13, UE100-1 measures CSI based on CSI-RS#1 and transmits the measurement result to gNB200 as CSI#1.

[0099] In addition, the UE 100-1 performs model learning using the CSI-RS #1 and the CSI #1 as learning data, and derives a learned model (for example, a first learned model). The UE 100-1 transmits the learning data (CSI-RS #1 and the CSI #1) of the UE 100-1 to the gNB 200. The UE 100-1 may transmit the learning data together with the CSI #1 (step S13). The UE 100-1 may transmit the learning data separately from the CSI #1.

[0100] In step S14, gNB200 transmits CSI-RS#2 to UE100-2.

[0101] In step S15, the UE 100-2 measures the CSI based on the CSI-RS #2 and transmits the measurement result as CSI #2 to the gNB 200. The UE 100-2 also performs model learning using the CSI-RS #2 and the CSI #2 as learning data, and performs a process of deriving a learned model (for example, a second learned model).

[0102] In step S16, the gNB 200 associates the learning data of the UE 100-1 with the environmental data of the UE 100-1. Then, the gNB 200 stores the associated learning data and environmental data in the memory of the gNB 200.

[0103] In addition, when the linking is performed in the UE 100-1, the UE 100-1 can acquire the learning data of the UE 100-1 when it acquires the CSI #1 (step S13). Therefore, the UE 100-1 may link the learning data of the UE 100-1 with the environmental data of the UE 100-1 when transmitting the CSI #1 (step S13) or after transmitting the CSI #1. Thereafter, the UE 100-1 transmits the linked learning data and environmental data to the gNB 200.

[0104] In step S17, gNB200 transmits the learning data of the associated UE100-1 and the environmental data of UE100-1 to UE100-2.

[0105] The gNB 200 may transmit the learning data of the associated UE 100-1 and the environmental data of the UE 100-1 to the core network device of the CN 20 (step S18). The core network device may transmit the learning data of the UE 100-1 and the environmental data of the UE 100-1 to another UE via another gNB. This is because model learning is also performed in the other UE using the learning data of the UE 100-1, as in the case of the UE 100-2.

[0106] In addition, gNB200 may confirm with UE100-1 and UE100-2 (and other UEs) the usage conditions when using UE100-1's learning data in UE100-2 (and other UEs). Alternatively, the core network device may confirm with UE100-1, UE100-2, and other UEs the usage conditions when using UE100-1's learning data in UE100-2 and other UEs. The usage conditions may be, for example, the antenna configuration of each UE, the UE type, model number, and / or manufacturer identification number. gNB200 or the core network device may determine whether UE100-1's learning data can be used in UE100-2 or other UEs based on the usage conditions acquired from each UE.

[0107] In step S19, the UE 100-2 determines whether or not to use the learning data of the UE 100-1 for machine learning, based on the environmental data of the UE 100-1. When the UE 100-2 determines to use the learning data of the UE 100-1 based on the environmental data, the UE 100-2 performs machine learning using the learning data of the UE 100-1, and derives a learned model (for example, a second learned model).

[0108] (1.6) Other Examples of the First Operation Scenario In the first operation scenario, an example has been described in which CSI-RS is used as the data included in the training data, but the present invention is not limited to this.

[0109] For example, the training data may include at least one of RSRP, RSRQ, SINR, and the output waveform of the AD converter instead of CSI-RS. The measurement targets for RSRP, RSRQ, SINR, and the output waveform of the AD converter may be CSI-RS and / or other received signals. The model training unit A2 derives a training model using, for example, RSRP and CSI as training data. Furthermore, the model inference unit A3 may input, for example, RSRP measured from a partial CSI-RS as inference data into the training model to obtain inference result data (CSI).

[0110] Alternatively, the learning data may include at least one of a bit error rate (BER) and a block error rate (BLER) instead of the CSI-RS. The BER represents the ratio of the number of erroneously received bits to the total number of transmitted bits. The BLER represents the ratio of the number of erroneously received blocks to the total number of transmitted blocks. The receivers 110-1 and 110-2 may measure the BER (or BLER) based on the CSI-RS, with the total number of transmitted bits (or the total number of transmitted blocks) known. The data collection unit A1 may include the BER (or BLER) received from the receivers 110-1 and 110-2 in the learning data and output it to the model learning unit A2.

[0111] Alternatively, the learning data may include, instead of the CSI-RS, the movement speed of the UE 100. For example, the UE 100-1 has a speed sensor, and the data collection unit A1 includes the movement speed of the UE 100-1 obtained from the speed sensor in the learning data and outputs the learning data to the model learning unit A2.

[0112] (2) Second Operation Scenario Next, the second operation scenario will be described, focusing mainly on the differences from the first operation scenario.

[0113] FIG. 11 is a diagram illustrating an example of a second operation scenario according to the first embodiment.

[0114] As described above, the second operation scenario is an example in which the gNB 200 performs machine learning and derives a learned model (for example, a first learned model and a second learned model). The second operation scenario will be described using an example of CSI feedback using SRS. In the second operation scenario, it is sufficient that reference signals for estimating the uplink channel state can be transmitted from the UEs 100-1 and 100-2, and a demodulation reference signal (DMRS) may be used instead of the SRS.

[0115] 12 and 13 are diagrams showing an example configuration of UE100-1 and 100-2 and gNB200 in the second operation scenario according to the first embodiment. As shown in FIGS. 12 and 13, in the second operation scenario, a data collection unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4 are arranged in gNB200. Therefore, model learning and model inference are performed in gNB200.

[0116] As shown in FIG. 12, the gNB 200 generates CSI from the SRS #1 transmitted from the UE 100-1. Therefore, the gNB 200 further includes a CSI generation unit 231. The CSI is used, for example, for uplink scheduling of the UE 100-1. The model learning unit A2 performs machine learning using the SRS #1 and the generated CSI as learning data (e.g., first learning data) for the UE 100-1, and derives a learned model. Then, the model inference unit A3 inputs the partial SRS transmitted from the UE 100-1 as inference data into the derived learned model, and obtains inference result data (CSI).

[0117] On the other hand, as shown in FIG. 13, in the gNB 200, the CSI generation unit 231 generates CSI from the SRS #2 transmitted from the UE 100-2. The model learning unit A2 performs machine learning using the SRS #2 and the generated CSI as learning data (e.g., second learning data) of the UE 100-2, and derives a learning model (e.g., a second learned model). Then, in the model inference unit A3, the partial SRS transmitted from the UE 100-2 is input as inference data into the derived learned model, and inference result data (CSI) is obtained.

[0118] In the mobile communication system 1 arranged in this manner, in the second operation scenario, acquisition of environmental data may be performed in the gNB 200, as in the first operation scenario. The acquisition of the environmental data may be performed in the UE 100-1. That is, an environmental data acquisition unit 240 may be provided in the gNB 200. An environmental data acquisition unit 140-1 may be provided in the UE 100-1. When the environmental data acquisition unit 140-1 of the UE 100-1 acquires the environmental data, it transmits the acquired environmental data to the gNB 200 via the control unit 130-1 and the transmission unit 120-1.

[0119] Then, in the second operation scenario, the gNB200 links the environmental data of the UE100-1 to the learning data of the UE100-1. This linking may be performed by the data collection unit A1 (or the control unit 230). This linking may be performed by the environmental data acquisition unit 240. When this linking is performed by the environmental data acquisition unit 240, the data collection unit A1 outputs the learning data of the UE100-1 to the environmental data acquisition unit 240. Then, the environmental data acquisition unit 240 links the learning data with the environmental data and outputs it to the data collection unit A1 (or the control unit).

[0120] In the second operation scenario, when gNB200 is performing machine learning using the learning data of UE100-2, it can determine whether or not to perform the machine learning using the learning data of UE100-1 based on the environmental data of UE100-1. In gNB200, for example, the following processing is performed.

[0121] That is, the data collection unit A1 acquires environmental data of the UE 100-1 from the environmental data acquisition unit 240. Alternatively, the data collection unit A1 acquires environmental data transmitted from the UE 100-1 via the receiving unit 220. Then, the data collection unit A1 (or the control unit 230) determines, based on the environmental data of the UE 100-1, whether or not to perform machine learning using the learning data of the UE 100-1 to derive a trained model using the learning data of the UE 100-2. As with the first operation scenario, when the data collection unit A1 determines, based on the environmental data, not to perform the machine learning using the learning data of the UE 100-1, the data collection unit A1 may discard the learning data of the UE 100-1. Furthermore, even when the data collection unit A1 has determined not to perform the machine learning using the learning data of the UE 100-1, the data collection unit A1 may determine to perform machine learning using the learning data of the UE 100-1 in order to derive another trained model (e.g., a third trained model) using the learning data of the UE 100-2. In this case, the data collection unit A1 may output the training data of the UE 100-1 to a part of the model training unit A2 that derives another trained model.

[0122] In this way, even in the second operation scenario, the learning data of UE100-1 is linked to the environmental data of UE100-1. As a result, for example, when gNB200 is performing machine learning using the learning data of UE100-2, it is possible to determine whether or not to use the learning data of UE100-1 for the machine learning based on the environmental data of UE100-1. As a result, gNB200 can avoid using learning data that is not suitable for the environment of UE100-2 for machine learning, and it is possible to appropriately utilize machine learning technology in the mobile communication system 1.

[0123] (2.1) Example of Operation of Second Operation Scenario Next, a description will be given of an example of operation of the second operation scenario according to the first embodiment. Fig. 14 is a diagram showing an example of operation of the second operation scenario.

[0124] It should be noted that when the operation example shown in Figure 14 is being performed, model learning to derive a learning model is being performed in gNB200.

[0125] As in the case of the first operation scenario, before the operation example shown in Figure 14 is performed, a message including instruction information instructing gNB200 to link the learning data with environmental data may be sent from the core network device.

[0126] In step S30, the gNB200 acquires environmental data of the UE100-1. The gNB200 may acquire the environmental data by receiving the environmental data from the UE100-1 (step S31). The gNB200 may acquire the environmental data by generating environmental data of the UE100-1 based on a received signal received from the UE100-1. In this case, the gNB200 may acquire the environmental data by using the functions of SON and / or MDT, as in the first operation scenario.

[0127] In step S32, UE 100-1 transmits SRS #1 to gNB 200. In gNB 200, CSI #1 is generated from SRS #1, and model learning is performed from the learning data (SRS #1 and CSI #1) of UE 100-1.

[0128] In step S33, the gNB 200 associates the learning data of the UE 100-1 with the environmental data of the UE 100-1. The gNB 200 stores the associated learning data and environmental data in memory.

[0129] In step S34, the gNB 200 may transmit the learning data of the associated UE 100-1 and the environmental data of the UE 100-1 to the core network device. The core network device may transmit the learning data of the UE 100-1 and the environmental data of the UE 100-1 to another UE via another gNB.

[0130] In step S35, UE 100-2 transmits SRS #2 to gNB 200. In gNB 200, CSI #2 is generated from SRS #2, and machine learning is performed based on the learning data (SRS #1 and CSI #2) of UE 100-2 to derive a learned model (e.g., a second learned model).

[0131] In step S36, based on the environmental data of UE100-1, it is determined whether or not to use the learning data of UE100-1 for machine learning to derive a trained model (e.g., a second trained model) using the learning data of UE100-2. When it is determined to use the learning data of UE100-1, gNB200 performs machine learning using the learning data of UE100-1 and derives a trained model using the learning data of UE100-2.

[0132] (2.2) Other Examples of the Second Operation Scenario In the second operation scenario, an example using SRS was described as being included in the learning data, but this is not limited to this. The learning data may include, for example, at least one of RSRP, RSRQ, SINR, the output waveform of the AD converter, BER, BLER, and the movement speed of UE100-1 and 100-2, as in the first operation scenario. RSRP, RSRQ, SINR, the output waveform of the AD converter, BER, and BLER may be measured by the receiving unit 220 of the gNB200 based on the SRS. In addition, the gNB200 may receive from the UE100-1 and 100-2 the movement speed measured by the speed sensor of the UE100-1 and 100-2.

[0133] (3) Third Operation Scenario Next, the third operation scenario will be explained. The third operation scenario will also be explained, focusing on the differences from the first operation scenario.

[0134] The third operation scenario is a case in which machine learning is performed in the UE 100-1 and the UE 100-2 to derive a learned model, similar to the first operation scenario. However, in the third operation scenario, beam management is used.

[0135] 15 and 16 are diagrams showing example configurations of UEs 100-1 and 100-2 and gNB 200 in a third operation scenario according to the first embodiment. As shown in FIGS. 15 and 16, in the third operation scenario, CSI-RS and the optimal beam among the beams transmitted from gNB 200 are used as learning data.

[0136] The gNB 200 uses beamforming technology that uses multiple antenna ports (or multiple antenna elements) to compensate for propagation loss in the transmission frequency band. Using beamforming technology, the gNB 200 can form beams that impart directionality to the transmission signal and increase or decrease the signal power in a specific direction. The gNB 200 can then transmit CSI-RS for each beam formed in a different direction. The UE 100 can select the optimal beam by measuring RSRP and the like from each CSI-RS. As shown in FIGS. 15 and 16, the UEs 100-1 and 100-2 further include optimal beam determination units 132-1 and 132-2 to select the optimal beam.

[0137] The optimal beam determination unit 132-1 of the UE 100-1 determines an optimal beam based on the reception quality of each CSI-RS received from the receiving unit 110-1. Hereinafter, one or more CSI-RSs received by the UE 100-1 may also be referred to as "CSI-RS#1". The optimal beam determination unit 132-1 performs, for example, the following process.

[0138] That is, the optimal beam determination unit 132-1 receives the reception quality (or measurement value) of each CSI-RS #1 from the receiving unit 110. The optimal beam determination unit 132-1 also receives resource information used to receive each CSI-RS #1 from the receiving unit 110. The optimal beam determination unit 132-1 acquires a CSI-RS resource indicator (CRI) from the resource information. The CRI is used to identify each CSI-RS. The CRI is also linked to each beam. Then, the optimal beam determination unit 132-1 determines, for example, the CRI of the CSI-RS with the best reception quality as the optimal beam. The optimal beam determination unit 132-1 outputs the determined CRI as the optimal beam.

[0139] Note that as long as each beam can be identified by identifying each CSI-RS, an index other than CRI may be used.

[0140] The data collection unit A1 outputs the CSI-RS #1 and the optimal beam to the model learning unit A2 as learning data (for example, first learning data) of the UE 100-1. The model learning unit A2 performs machine learning using the CSI-RS #1 and the optimal beam to derive a learned model (for example, a first learned model).

[0141] Similarly to the first operation scenario, the data collection unit A1 outputs the partial CSI-RS as inference data to the model inference unit A3. The model inference unit A3 inputs the partial CSI-RS to the trained model and outputs the optimal beam as inference result data.

[0142] The optimal beam determination unit 132-2 of the UE 100-2 determines the optimal beam based on the reception quality of each CSI-RS received from the receiving unit 110-2. One or more CSI-RSs received by the UE 100-2 may also be referred to as "CSI-RS#2". The optimal beam determination unit 132-2 may determine the optimal beam by performing the same processing as the optimal beam determination unit 132-1 of the UE 100-1.

[0143] In the UE 100-2, the model learning unit A2 performs machine learning using the CSI-RS #2 and the optimal beam as learning data (for example, second learning data) of the UE 100-2, and derives a learned model (for example, a second learned model). Further, the model inference unit A3 of the UE 100-2 uses the learned model to output inference result data (optimal beam) for a partial CSI-RS.

[0144] Even in the third operation scenario, either the UE 100-1 or the gNB 200 can link the environmental data to the learning data of the UE 100-1 (for example, the first learning data). By such linking, the UE 100-2 that receives the UE 100-1 environmental data and the learning data of the UE 100-1 can determine whether or not to perform machine learning using the learning data of the UE 100-1 based on the environmental data. As a result, the UE 100-2 can avoid using learning data that is not suitable for its own environment (for example, the learning data of the UE 100-1) for machine learning, making it possible to appropriately utilize machine learning technology in the mobile communication system 1.

[0145] (3.1) Operation example of the third operation scenario In the third operation scenario, as in the first operation scenario, trained models are derived in the UE 100-1 and the UE 100-2. In the third operation scenario, compared to the first operation scenario, only the target training data is different, and basically, the same processing as in the operation example of the first operation scenario ( FIG. 10 ) is performed.

[0146] (3.2) Other Examples of the Third Operation Scenario In the third operation scenario, an example has been described in which CSI-RS is used as the data included in the training data, but the present invention is not limited to this.

[0147] For example, the learning data may include a synchronization signal block (SSB) instead of the CSI-RS. In the gNB 200, the SSB is transmitted at different timings for each beam using beamforming technology, and the UE 100-1 can determine the optimal beam by measuring each of the received SSBs. For example, the UE 100-1 performs the following processing. That is, the receiving unit 110-1 of the UE 100-1 outputs the SSB index included in the SSB along with the measurement results of each SSB to the optimal beam determination unit 132-1. The optimal beam determination unit 132-1 identifies the SSB index of the SSB with the best reception quality based on the measurement results of each SSB. Since each SSB index is linked to each beam, the optimal beam determination unit 132-1 can identify (or determine) the optimal beam by identifying the SSB index of the SSB with the best reception power (or reception quality).

[0148] Alternatively, instead of CSI-RS, the training data may include at least one of RSRP, RSRP, SINR, and the output waveform of the AD converter, as in the first operation scenario. The measurement targets of RSRP, RSRP, SINR, and the output waveform of the AD converter may be CSI-RS and / or SSB.

[0149] Alternatively, the training data may include at least one of the BER and the BLER instead of the CSI-RS, as in the first operating scenario.

[0150] Alternatively, the learning data may include at least one of the number of beams and the beam pattern instead of the CSI-RS. The number of beams and the beam pattern are included in, for example, DCI or broadcast information, and the UEs 100-1 and 100-2 can acquire the number of beams and the beam pattern by receiving the DCI or broadcast information transmitted from the gNB 200.

[0151] Alternatively, when multiple beams exist, the training data may include, instead of CSI-RS, at least one of RSRP, RSRP, SINR, and the output waveform of an AD converter for the number of beams.

[0152] Alternatively, the learning data may include the movement speed of the UE 100 instead of the CSI-RS, as in the first operation scenario.

[0153] Furthermore, in the third operation scenario, the optimal beam was described as being included in the learning data. For example, the optimal beam may be determined by taking into consideration the time at which the beam is measured and the time at which the beam is selected. That is, the time at which the UEs 100-1 and 100-2 acquire the measurement values ​​of the beam (or a set of beams) is set to T1, and the time at which the UEs 100-1 and 100-2 select the optimal beam is set to T2. Then, the UEs 100-1 and 100-2 may determine the beam selected at time T2 as the optimal beam based on the measurement values ​​at time T1.

[0154] (4) Fourth Operation Scenario Next, the fourth operation scenario will be described. The fourth operation scenario will also be described, focusing on the differences from the first operation scenario.

[0155] In the fourth operation scenario, similarly to the first operation scenario, the learned models are derived in the UE 100-1 and the UE 100-2. In the fourth operation scenario, positioning accuracy enhancement is used.

[0156] 17 and 18 are diagrams showing example configurations of UEs 100-1 and 100-2 and a gNB 200 in a fourth operation scenario according to the first embodiment. In the example shown in FIGS. 17 and 17, a positioning reference signal (PRS) and location data are used as learning data. The UEs 100-1 and 100-2 further include location information generation units 133-1 and 133-2. For example, the location information generation unit 133-1 generates location information from the PRS by the following process.

[0157] That is, the receiving unit 110-1 of the UE 100-1 receives a PRS transmitted from the gNB 200 (hereinafter, the PRS received by the UE 100-1 may be referred to as "PRS #1"). The receiving unit 110-1 outputs the PRS #1 to the location information generating unit 133-1. The location information generating unit 133-1 generates location information of the UE 100-1 based on the PRS #1. The location information generating unit 133-1 generates location information of the UE 100-1 using, for example, DL-TDOA (Downlink Time Difference Of Arrival) as a positioning method. In this case, the location information generating unit 133-1 measures the arrival time difference (DL RSTD (Reference Signal Time Difference)) for the PRS and calculates the distance to the cell (or gNB) from the arrival time difference. Then, the location information generation unit 133-1 generates location information of the UE 100-1 based on the distances to at least three cells (or gNBs). The location information generation unit 133-1 outputs the generated location information to the data collection unit A1 as location data.

[0158] In addition, the location information generation unit 133-1 may use a positioning method capable of locating the position of the UE 100-1 using a received signal, and may acquire the location information of the UE 100-1 using DL-AoD (Downlink Angle-of-Departure) or Multi-RTT (Multi-RTT (Roundtrip Time)) in addition to DL-TDOA. DL-AoD is a positioning method in which the angle of departure (AoD) of PRS #1 is calculated from the received power of PRS #1, and the location information of the UE 100-1 is acquired from the intersection position of three directions. Multi-RTT is a positioning method in which, in each cell, the round trip time (round trip time) is measured from the time difference between transmission and reception, and the distance (at least three distances) is calculated from the round trip time to locate the position of the UE 100-1.

[0159] The location information generation unit 133-2 of the UE 100-2 is similar to the location information generation unit 133-1 of the UE 100-1, except that the PRS received by the UE 100-2 (hereinafter, may be referred to as "PRS#2") is PRS#2.

[0160] The data collection unit A1 of the UE 100-1 outputs the PRS #1 and the location data of the UE 100-1 as learning data to the model learning unit A2. The model learning unit A2 performs model learning using the PRS #1 and the location data of the UE 100-1, and derives a learned model (for example, a first learned model).

[0161] In addition, the data collection unit A1 of the UE 100-1 receives the partial PRS received by the receiver 110-1 from the gNB 200, and outputs the partial PRS as inference data to the model inference unit A3. The model inference unit A3 uses the learned model to output an inference result (location data) for the partial PRS.

[0162] UE100-2 is similar to UE100-1, except that the PRS received from gNB200 is PRS#2.

[0163] In the fourth operation scenario, either the gNB 200 or the UE 100-1 links the environmental data of the UE 100-1 to the learning data of the UE 100-1. The UE 100-2, which receives the environmental data of the UE 100-1 and the learning data of the UE 100-1, can determine whether to perform machine learning using the learning data of the UE 100-1 based on the environmental data. This allows the UE 100-2 to avoid using learning data that is not suitable for its own environment (for example, the learning data of the UE 100-1) for machine learning, making it possible to appropriately utilize machine learning technology in the mobile communication system 1.

[0164] (4.1) Operation example of the fourth operation scenario In the fourth operation scenario, as in the first operation scenario, trained models are derived in the UE 100-1 and the UE 100-2. In the fourth operation scenario, compared to the first operation scenario, only the target training data is different, and basically, the same processing as in the operation example of the first operation scenario ( FIG. 10 ) is performed.

[0165] (4.2) Other Examples of the Fourth Operation Scenario In the fourth operation scenario, an example has been described in which PRS is used as data included in the learning data, but the present invention is not limited to this.

[0166] For example, the learning data may include positioning data from the GNSS receiver 150-1 instead of the PRS. In this case, as shown in FIGS. 17 and 18 , the UE 100-1 may further include the GNSS receiver 150-1, and the UE 100-2 may further include the GNSS receiver 150-2. Alternatively, the position information generation unit 133-1 may include the GNSS receiver 150-1, and the position information generation unit 133-2 may include the GNSS receiver 150-2. The GNSS receiver 150-1 outputs positioning information based on the GNSS reception signal as positioning data to the position information generation unit 133-1 and the data collection unit A1. The position information generation unit 133-1 generates position information for the UE 100-1 based on the positioning data. The position information may be information represented by a route and latitude. The position information may also be information representing height from the ground. The location information generating unit 133-1 outputs the generated location information as location data to the data collecting unit A1. The data collecting unit A1 of the UE 100-1 outputs the positioning data and the location data of the UE 100-1 as learning data to the model learning unit A2. In this case, the data collecting unit A1 of the UE 100-1 outputs, for example, partial positioning data as inference data to the model inference unit A3.

[0167] Alternatively, the training data may include any one of RSRP, RSRP, SINR, and the output waveform of the AD converter instead of the PRS, as in the first operation scenario. The measurement targets of RSRP, RSRP, SINR, and the output waveform of the AD converter may be PRS and / or other received signals.

[0168] Alternatively, the learning data may include an LOS or NLOS instead of the PRS. For example, the location information generation unit 133-1 stores map information in an internal memory, and generates an LOS or NLOS based on the location information of the UE 100-1 and the map information. The location information generation unit 133-1 outputs the generated LOS or NLOS to the data collection unit A1. The data collection unit A1 outputs the LOS or NLOS and the location information of the UE 100-1 to the model learning unit A2 as learning data.

[0169] Alternatively, the learning data may include, instead of the PRS, the measurement timing or the likelihood to be applied to the measurement value (or the likelihood function to be applied to the measurement value). The measurement timing may be the reception timing of the PRS. The measurement timing may be the timing when the location information generation unit 133-1 generates the location information of the UE 100-1. For example, the measurement value is RSSI, and the likelihood to be applied to the measurement value represents the likelihood (or probability) of the distance calculated from the RSSI. For example, the location information generation unit 133-1 receives the RSSI from the receiving unit 110-1, calculates the distance to the gNB 200 from the RSSI, and calculates the likelihood (or likelihood function) from the probability distribution.

[0170] Alternatively, the training data may include an RF fingerprint instead of the PRS. The RF fingerprint is, for example, a cell ID and the reception quality of a cell having the cell ID. The RF fingerprint is, for example, acquired by receiving units 110-1 and 110-2 and output to data collection unit A1.

[0171] Alternatively, the learning data may include, instead of the PRS, at least one of the angle of arrival (AoA) of the received signal, the reception level for each antenna, the reception phase for each antenna, and the observed time difference of arrival (OTDOA) for each antenna. The AoA of the received signal, the reception level for each antenna, the reception phase for each antenna, and the OTDOA for each antenna are acquired by, for example, the receiving units 110-1 and 110-2, and output to the data collecting unit A1.

[0172] Alternatively, the learning data may include, instead of the PRS, reception information of a beacon used in a wireless LAN (Local Area Network) such as Wi-Fi (registered trademark) or in short-range wireless communication such as Bluetooth (registered trademark). The reception information of the beacon may be, for example, the reception quality of the beacon (RSRP, RSRQ, etc.).

[0173] Alternatively, the learning data may include the movement speed of the UE 100 instead of the PRS, similar to the first operation scenario.

[0174] [Other Embodiments] In the first embodiment described above, supervised learning has been mainly described, but the present invention is not limited to this. For example, the first embodiment may be applied to unsupervised learning or reinforcement learning.

[0175] Furthermore, 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 a 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 memory included in the UE 100 and the gNB 200.

[0176] As used in this disclosure, the terms "based on" and "depending on" 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 "based only on" and "at least in part on." Furthermore, "obtain" may mean obtaining information from stored information, obtaining information from information received from another node, or obtaining information by generating the information. The terms "include," "comprise," and variations thereof do not mean including only the listed items, but may also mean including only the listed items or including additional items in addition to the listed items. Furthermore, as used in this disclosure, the term "or" is not intended to mean an exclusive or. Furthermore, any reference to an element using a designation 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, 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, when articles are added by translation, such as a, an, and the in English, these articles are intended to include the plural unless the context clearly indicates otherwise.

[0177] 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.

[0178] This application claims priority from Japanese Patent Application No. 2022-115293 (filed July 20, 2022), the entire contents of which are incorporated herein by reference.

[0179] (Supplementary Note) (Supplementary Note 1) A communication method in a mobile communication system having a first user device, a second user device, and a base station capable of communicating with the first user device and the second user device, and capable of deriving a first trained model using first training data and deriving a second trained model using second training data, the communication method comprising a step in which either the base station or the first user device links environmental data representing an environmental state of the first user device to the first training data.

[0180] (Supplementary Note 2) The communication method according to Supplementary Note 1, further comprising the step of the first user device deriving the first trained model and the second user device deriving the second trained model.

[0181] (Supplementary Note 3) The communication method according to Supplementary Note 1 or Supplementary Note 2, wherein the linking step includes a step of, when the first user device links the environmental data to the first training data, the first user device transmitting the linked environmental data and the first training data to the base station.

[0182] (Supplementary Note 4) The communication method according to any one of Supplementary Notes 1 to 3, wherein the associating step includes a step of, when the base station associates the environmental data with the first training data, transmitting the first training data to the base station by the first user device.

[0183] (Supplementary Note 5) The communication method according to any one of Supplementary Notes 1 to 4, further comprising: the base station transmitting the first training data and the environmental data to the second user device; and the second user device determining, based on the environmental data, whether to perform machine learning using the first training data.

[0184] (Supplementary Note 6) The communication method according to any one of Supplementary Notes 1 to 5, wherein the determining step includes a step of determining to perform machine learning using the first training data to derive a third trained model when the second user device determines not to perform machine learning using the first training data.

[0185] (Supplementary Note 7) The communication method according to any one of Supplementary Notes 1 to 6, wherein the linking step includes: a step in which the first user device generates the environmental data in response to acquisition of the first training data; and a step in which the first user device transmits the environmental data to the base station.

[0186] (Supplementary Note 8) The communication method according to any one of Supplementary Notes 1 to 7, wherein the linking step includes: a step in which the first user device transmits to the base station an environmental condition request requesting environmental conditions desired by the first user device; and a step in which the base station generates the environmental data based on the environmental condition request.

[0187] (Supplementary Note 9) The communication method according to any one of Supplementary Notes 1 to 8, further comprising the step of the base station deriving the first trained model and the second trained model.

[0188] (Supplementary Note 10) The communication method according to any one of Supplementary Notes 1 to 9, wherein the linking step includes a step in which the base station links the first training data to the environmental data, and further includes a step in which the base station determines, based on the environmental data, whether to perform machine learning using the first training data to derive the second trained model.

[0189] (Supplementary Note 11) The communication method according to any one of Supplementary Notes 1 to 10, wherein the determining step includes a step of determining, when the base station determines not to perform machine learning using the first training data to derive the second trained model, to perform machine learning using the first training data to derive a third trained model.

[0190] (Supplementary Note 12) The communication method according to any one of Supplementary Notes 1 to 11, further comprising a step in which the base station or core network device confirms with the first user device and the second user device usage conditions when the first training data is used in the second user device.

[0191] (Supplementary Note 13) The communication method according to any one of Supplementary Notes 1 to 12, further comprising the steps of: when the base station associates the environmental data with the first training data, a core network device transmitting to the base station a first message including instruction information instructing the base station to associate the environmental data with the first training data; and when the first user equipment associates the environmental data with the first training data, the base station transmitting to the first user equipment a second message including the instruction information instructing the base station to associate the environmental data with the first training data.

[0192] 1: Mobile communication system 100 (100-1, 100-1): UE 110 (110-1, 110-2): Receiving unit 120 (120-1, 120-2): Transmitting unit 130 (130-1, 130-2): Control unit 131-1, 131-2: CSI generating unit 132-1, 132-2: Optimal beam determining unit 133-1, 133-2: Position information generating unit 140-1: Environmental data acquiring unit 150-1, 150-2: GNSS receiver 200: gNB 210: Transmitting unit 220: Receiving unit 230: Control unit 231: CSI generating unit 240: Environmental data acquiring unit A1: Data collecting unit A2: Model learning unit A3: Model inference unit A4: Data processing unit

Claims

1. A communication method in a mobile communication system including a first user device, a second user device, and a network node capable of communicating with the first user device and the second user device, the communication method comprising: deriving a first trained model using first training data; and deriving a second trained model using second training data, the communication method comprising: and wherein either the network node or the first user device associates environmental data representative of an environmental state of the first user device with the first learning data. Communication methods.

2. The first user device derives the first trained model, and the second user device derives the second trained model. The communication method according to claim 1.

3. The linking includes, when the first user device links the environmental data to the first learning data, transmitting the linked environmental data and the first learning data to the network node by the first user device. The communication method according to claim 2.

4. and wherein the binding includes the first user equipment transmitting the first training data to the network node if the network node binds the environmental data to the first training data. The communication method according to claim 2.

5. the network node transmitting the first training data and the environmental data to the second user equipment; The second user device further comprises determining whether to perform machine learning using the first learning data based on the environmental data. The communication method according to claim 3 or 4.

6. The determining includes, when the second user device determines not to perform machine learning using the first training data, determining to perform machine learning using the first training data to derive a third trained model. The communication method according to claim 5.

7. The linking includes: The first user device generates the environmental data in response to acquiring the first learning data; and transmitting, by the first user equipment, the environmental data to the network node. The communication method according to claim 4.

8. The linking includes: sending, by the first user equipment, to the network node, an environmental condition request requesting environmental conditions desired by the first user equipment; generating the environmental data based on the environmental condition request. The communication method according to claim 1 .

9. The network node further comprises deriving the first trained model and the second trained model. The communication method according to claim 1.

10. The linking step includes the network node linking the first learning data to the environmental data; The network node further comprises determining, based on the environmental data, whether to perform machine learning using the first training data to derive the second trained model. The communication method according to claim 9.

11. The determining includes, when the network node determines not to perform machine learning using the first training data to derive the second trained model, determining to perform machine learning using the first training data to derive a third trained model. The communication method according to claim 10.

12. The network node or core network device further includes confirming with the first user device and the second user device the usage conditions when the first learning data is used in the second user device. The communication method according to claim 2.

13. When the network node associates the environmental data with the first learning data, a core network device transmits a first message to the network node, the first message including instruction information instructing the network node to associate the environmental data with the first learning data; and when the first user device associates the environmental data with the first learning data, the core network device transmits a second message to the first user device, the second message including the instruction information instructing the network node to associate the environmental data with the first learning data. The communication method according to claim 1.

14. A user device in a mobile communication system having a user device and another user device, and a network node capable of communicating with the user device and the other user device, the user device being capable of deriving a first trained model using first training data and deriving a second trained model using second training data, a control unit that associates environmental data representing an environmental state of the user device with the first learning data; User equipment.

15. A mobile communication system comprising: a user device and another user device; and a network node capable of communicating with the user device and the other user device, the network node being capable of deriving a first trained model using first training data and deriving a second trained model using second training data, a control unit that associates environmental data representing an environmental state of the user device with the first learning data; Network node.