Communication device and communication method

Abstract

A communication device of the present invention is capable of performing a process of a plurality of functionalities related to communication with another communication device, the communication device including a management unit that implements management of an AI / ML model used in the process on the basis of the functionalities.

Description

Technical Field

[0001] The present disclosure relates to a communication device and a communication method. Background Art

[0002] Technologies related to wireless communication have been actively developed. In recent years, research has been conducted on technologies for improving communication performance by applying artificial intelligence and machine learning technologies to radio access networks.

[0003] Reference List

[0004] Non-patent literature

[0005] Non-Patent Document 1: R1-2210997, “Discussions on AI / ML framework,” vivo, 3GPP TSG-RAN WG1 Meeting #111, Toulouse, France, November 14-18, 2022 Summary of the Invention

[0006] Technical issues

[0007] However, simply applying AI / ML techniques to radio access networks does not necessarily lead to achieving high communication performance (e.g., improved frequency utilization efficiency, greater capacity, higher speed, lower latency, higher reliability, lower power consumption, or lower processing load).

[0008] In view of this, the present disclosure proposes a communication device and a communication method capable of achieving high communication performance.

[0009] It should be noted that the aforementioned problem or goal is only one of the multiple problems or goals that can be solved or achieved by the multiple embodiments disclosed in this specification.

[0010] Solutions to Problems

[0011] In order to solve the aforementioned problem, a communication device according to one embodiment of the present disclosure is capable of performing multiple functionalities related to communication with another communication device, and the communication device includes: a management unit configured to manage the AI / ML model used in the processing based on the functionality. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a diagram illustrating an example of functionality.

[0013] Figure 2 is a diagram illustrating an example of functionality.

[0014] Figure 3 is a diagram illustrating an example of functionality.

[0015] Figure 4 is a diagram showing the configuration of a communication system according to the present embodiment.

[0016] Figure 5 is a diagram showing the configuration of the management apparatus according to the present embodiment.

[0017] Figure 6 is a diagram showing the configuration of a base station according to the present embodiment.

[0018] Figure 7 is a diagram showing the configuration of a relay station according to the present embodiment.

[0019] Figure 8 is a diagram showing the configuration of a terminal device according to the present embodiment.

[0020] Figure 9 is a diagram illustrating an example of a 5G architecture.

[0021] Figure 10 is a diagram showing a representative sequence example of the communication processing of the present embodiment.

[0022] Figure 11 1 is a diagram showing an example of a sequence in the case of performing handover.

[0023] Figure 12 1 is a diagram showing an example of a sequence in the case of performing handover.

[0024] Figure 13 is a flowchart showing a management process executed by a terminal device.

[0025] Figure 14 is a flowchart illustrating a management process performed by a base station. DETAILED DESCRIPTION

[0026] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In each of the following embodiments, identical parts are denoted by identical reference numerals, and repeated description thereof will be omitted.

[0027] In addition, in this specification and the accompanying drawings, multiple components with substantially the same functional configuration will be distinguished by appending different letters or numbers after the same reference numerals. For example, multiple configurations with substantially the same functional configuration will be distinguished when necessary, such as terminal devices 401, 402, and 403. However, when it is not particularly necessary to distinguish between multiple components with substantially the same functional configuration, they will simply be given the same reference numerals. For example, when it is not necessary to specifically distinguish between terminal devices 401, 402, and 403, they will simply be referred to as terminal device 40.

[0028] One or more embodiments described below (including implementation examples and modifications) can each be implemented independently. On the other hand, at least some of the multiple embodiments described below can be appropriately combined with at least some other embodiments. Multiple embodiments can include novel features that are different from each other. Accordingly, multiple embodiments can contribute to achieving or solving different purposes or problems and can exhibit different effects.

[0029] The present disclosure will be described in the following order of items.

[0030] 1. Overview

[0031] 1-1. Problem

[0032] 1-2. Solution

[0033] 2. Configuration of communication system

[0034] 2-1. Configuration of management device

[0035] 2-2. Base Station Configuration

[0036] 2-3. Relay Station Configuration

[0037] 2-4. Terminal device configuration

[0038] 2-5. AI / ML Model

[0039] 3. Network Architecture

[0040] 4. Operation of communication system

[0041] 4-1, LCM

[0042] 4-2. LCM Implementation

[0043] 4-3. Entity Operation

[0044] 4-4. Determine functionality

[0045] 4-5. Control LCM

[0046] 4-6. Operations during handover

[0047] 4-7. Sequence Example

[0048] 4-8. Management Processing Example

[0049] 5. Modification

[0050] 6. Conclusion

[0051] 1. Overview

[0052] Before describing the present embodiment in detail, an overview of the present embodiment will be described.

[0053] <1-1. Question>

[0054] Beyond 5G and 6G are being studied within 3GPP (registered trademark). These technologies are the next generation of 5G. They are expected to achieve further improvements in high speed and high capacity (enhanced mobile broadband (eMBB)), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC).

[0055] To achieve this, 3GPP has been researching technologies that use artificial intelligence (AI) and machine learning (ML) to improve communication performance. For example, they have been researching improving frequency efficiency by applying AI / ML models to radio access networks.

[0056] However, the mere use of AI / ML does not necessarily lead to high communication performance (e.g., improved frequency utilization efficiency, greater capacity, higher speed, lower latency, higher reliability, lower power consumption, or lower processing load).

[0057] For example, when applying AI / ML models in radio access networks, it is assumed that the AI / ML models are utilized in various use cases. Depending on the use case to be utilized, the AI / ML models can be applied in various applications. This makes it necessary to change the method of managing the AI / ML model for each use case according to the situation. On the other hand, as the number of use cases for which AI / ML models are applied increases and the various methods of managing AI / ML models are independently switched for each use case, problems will arise for terminal devices, such as an increase in the processing load for managing the AI / ML models and an increase in memory capacity. This makes it necessary to efficiently manage the AI / ML models in communications using the AI / ML models.

[0058] <1-2. Solution>

[0059] In view of these factors, this embodiment proposes the following solutions to the aforementioned problems.

[0060] Before describing an overview of the solution, the functionality and management of the AI / ML model, which is an important element in this embodiment, will be described.

[0061] <1-2-1. Functionality>

[0062] The functionality will be described first.

[0063] Functionality is a concept that represents the use cases of AI / ML models and the functions achieved using AI / ML models. Figures 1 to 3 are diagrams each showing an example of functionality.

[0064] Figure 1 The functionality A related to the sending of information is shown. Figure 1 In the example, from the sending device ( Figure 1 ) to the receiving device ( Figure 1 The auxiliary information is information required by the receiving device to perform processing related to wireless communication, or information used to assist the processing related to wireless communication performed by the receiving device. For example, the auxiliary information is information (e.g., control information) required for operations of the terminal device such as uplink data transmission, sidelink transmission, unlicensed communication, and handover. In functionality A, both the transmitting device and the receiving device use AI / ML models, allowing efficient information transmission from the transmitting device to the receiving device.

[0065] Figure 2 The functionality B related to the identification of the beam ID is shown. Figure 2 In the example of Figure 2 terminal in the example of ) based on the transmission device ( Figure 2 In functionality B, the receiving device identifies the beam ID using an AI / ML model.

[0066] Figure 3 The functionality C related to positioning is shown. Figure 3 In the example of Figure 3 terminal in the example of ) based on the transmission device ( Figure 3 In functionality C, the receiving device generates positioning information using an AI / ML model.

[0067] Functional labels appearing in the following description may be replaced with another label. For example, functionality appearing in the following description may be replaced with other labels, such as usage, function, function index, function ID, AI / ML index, AI index, ML index, or model index. Functional labels are not limited to these and may be replaced with, for example, another term representing a usage using an AI / ML model or a function implemented using an AI / ML model.

[0068] <1-2-2. AI / ML Model Management>

[0069] Next, the management of AI / ML models is described.

[0070] 3GPP has studied the management of AI / ML models (e.g., RP-221347). In this embodiment, the management of AI / ML models may be referred to as lifecycle management (LCM). LCM may be configured, for example, by one or more processes / methods / procedures selected from (M1) to (M16) below.

[0071] (M1) Data Collection

[0072] (M2) Model training

[0073] (M3) Model Identification

[0074] (M4) Model Delivery

[0075] (M5) Model Transfer

[0076] (M6) Model Download

[0077] (M7) Model upload

[0078] (M8) Model derivation

[0079] (M9) Model Verification

[0080] (M10) Model Test

[0081] (M11) Model Activation

[0082] (M12) Model Deactivation

[0083] (M13) Model Switching

[0084] (M14) Model rollback

[0085] (M15) Model Monitoring

[0086] (M16) Model Update

[0087] It should be noted that (M1) to (M16) are merely examples. LCM may include implementation examples other than the implementation examples ((M1) to (M16)) described above. (M1) to (M16) will be described in detail later.

[0088] <1-2-3. Overview of the Solution>

[0089] Based on the foregoing, an overview of the solution of the present embodiment will be described.

[0090] A communication device (e.g., a base station or terminal device) according to this embodiment is configured to perform multiple functional processes. For example, the communication device according to this embodiment is configured to perform processes related to the transmission or reception of auxiliary information, processes related to the identification of beam IDs, and processes related to positioning. These functional processes are implemented using AI / ML models. One or more AI / ML models are associated with each functional item.

[0091] The communication device according to this embodiment implements management (LCM) of the AI / ML model used in the processing of the functionality based on the functionality. For example, the communication device implements management of the AI / ML model for each use case or for each function. In this case, the communication device can implement management (LCM) of at least one of the multiple functionalities independently of management (LCM) of another functionality. In addition, the communication device can implement management (LCM) of all functionalities in association with each other. In addition, the communication device can implement management (LCM) of some of the multiple functionalities in association with each other.

[0092] In this way, in this embodiment, management of AI / ML models is implemented based on functionality. This makes it possible for the communication device to implement efficient management of AI / ML models, thereby achieving high communication performance.

[0093] The above is an overview of the present embodiment. The communication system 1 of the present embodiment will be described in detail below.

[0094] <<2. Configuration of communication system>>

[0095] First, the configuration of the communication system 1 will be described.

[0096] Figure 4This is a diagram showing an example of the configuration of a communication system 1 according to this embodiment. The communication system 1 includes a management device 10, a base station 20, a relay station 30, and a terminal device 40. By the various wireless communication devices constituting the communication system 1 operating in cooperation with each other, the communication system 1 provides users with a wireless network capable of mobile communication. The wireless network of this embodiment includes, for example, a radio access network RAN ​​and a core network CN. In this embodiment, the wireless communication device is a device having a wireless communication function, and Figure 4 In the example of , the devices correspond to the base station 20 , the relay station 30 , and the terminal device 40 .

[0097] The communication system 1 may include a plurality of management devices 10, a plurality of base stations 20, a plurality of relay stations 30, and a plurality of terminal devices 40. Figure 1 In the example of , the communication system 1 includes management devices 101 and 102 as the management device 10, and includes base stations 201, 202, and 203 as the base station 20. In addition, the communication system 1 includes relay stations 301 and 302 as the relay station 30, and includes terminal devices 401, 402, and 403 as the terminal device 40.

[0098] The terminal device 40 can be configured to connect to the network using a radio access technology (RAT) such as Long Term Evolution (LTE), New Radio (NR), 6G, Wi-Fi, or Bluetooth (registered trademark). At this time, the terminal device 40 can be configured to be able to use different radio access technologies (wireless communication methods). For example, the terminal device 40 can be configured to be able to use NR and Wi-Fi. In addition, the terminal device 40 can be configured to be able to use different cellular communication technologies (such as LTE and NR or 6G). LTE and NR are types of cellular communication technologies, and mobile communication of the terminal device is achieved by using a cellular arrangement of multiple areas covered by a base station. 6G is also a type of cellular communication technology, and mobile communication of the terminal device is achieved by using a cellular arrangement of multiple areas covered by a base station.

[0099] Hereinafter, it is assumed that "LTE" includes LTE-Advanced (LTE-A), LTE-Advanced Professional (LTE-A Pro), and Evolved Universal Terrestrial Radio Access (EUTRA). Furthermore, it is assumed that NR includes New Radio Access Technology (NRAT) and Further EUTRA (FEUTRA). It should be noted that one base station 20 can manage multiple cells. Hereinafter, a cell corresponding to LTE may be referred to as an LTE cell, and a cell corresponding to NR may be referred to as an NR cell.

[0100] NR is the next-generation (fifth-generation) radio access technology following LTE (fourth-generation communications, including LTE-Advanced and LTE-Advanced Pro). NR is a radio access technology that can support various use cases, including enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). NR was standardized by 3GPP (registered trademark) Rel-15 as a technical framework to support the use cases, requirements, deployment scenarios, and other requirements in these use cases. Furthermore, beyond 5G and 6G, it is required to simultaneously achieve high speed and large capacity, low latency / high reliability, and multiple axes with multiple simultaneous connections.

[0101] 6G is the next generation of cellular communication technology, following NR or 5GS (5G System), which is the fifth generation of mobile communication, and includes radio access technology and network technology between base stations, core networks, and data networks. 6G may include advanced technologies (extreme connectivity) in each of eMBB, mMTC, and URLLC, which are defined as primary use cases or requirements in NR, as well as new technologies in new areas such as AI (including cognitive networks and AI-native air interfaces), sensing (radar sensing, including networks acting as sensors), and terahertz communication. Regarding 6G, standard specification research in 3GPP will begin around 2025, initial specification development will be completed around 2028, and commercialization is likely to occur in 2030 or later.

[0102] The wireless network can be compatible with radio access technologies (RATs) such as Long Term Evolution (LTE), New Radio (NR), and 6G. LTE, NR, and 6G are types of cellular communication technologies, and mobile communication of terminal devices is achieved using a cellular arrangement of multiple areas covered by base stations. The radio access method used by the communication system 1 is not limited to LTE, NR, or 6G, and may be other radio access schemes such as Wideband Code Division Multiple Access (W-CDMA) and Code Division Multiple Access 2000 (cdma2000).

[0103] The base station 20 and the relay station 30 can each be a ground station or a non-ground station. The non-ground station can be a satellite station or an aircraft station. When the non-ground station is a satellite station, the wireless network can be a bent-pipe (transparent) mobile satellite communication system.

[0104] In this embodiment, a ground station (also referred to as a ground base station) refers to a base station or relay station installed on the ground. "Ground" refers not only to land but also to ground locations in a broad sense, including underground, above water, and underwater. It should be noted that in the following description, the description of "ground station" can also be referred to as "gateway."

[0105] Base stations in LTE may be referred to as evolved Node Bs (eNodeBs) or eNBs. NR base stations may be referred to as gNodeBs or gNBs. 6G base stations may be referred to as 6G Node Bs (6GNBs). In LTE, NR, and 6G, terminal devices (also referred to as mobile stations or terminals) may be referred to as user equipment (UE). A terminal device is a type of communication device and is also referred to as a mobile station or terminal.

[0106] The terminal device 40 may connect to the network using a radio access technology (wireless communication method) other than LTE, NR, 6G, Wi-Fi, or Bluetooth. For example, the terminal device 40 may connect to the network using low-power wide-area (LPWA) communication. Furthermore, the terminal device 40 may connect to the network using wireless communication using a proprietary standard.

[0107] Here, LPWA communication refers to wireless communication that enables low-power, wide-area communication. For example, LPWA wireless is Internet of Things (IoT) wireless communication that uses designated low-power radio (e.g., the 920 MHz band) or the Industrial, Scientific, and Medical (ISM) band. The LPWA communication used by the terminal device 40 may comply with an LPWA standard. Examples of LPWA standards include ELTRES, ZETA, SIGFOX, LoRaWAN, and NB-IoT. Of course, LPWA standards are not limited to these and may be other LPWA standards.

[0108] Figure 2 Each wireless communication device in the

[0014] may be considered a device in a logical sense. That is, a portion of each wireless communication device may be implemented through a virtual machine (VM), a container, or the like, and may be implemented on physically identical hardware.

[0109] In this embodiment, the concept of "wireless communication device" includes not only portable mobile devices (terminal devices) such as mobile terminals, but also devices installed in structures or mobile objects. The structures or mobile objects themselves can be considered wireless communication devices. In addition, the concept of wireless communication device includes not only terminal devices 40, but also base stations 20 and relay stations 30. Wireless communication devices are a type of processing device and information processing device. Wireless communication devices can also be referred to as transmitting devices or receiving devices.

[0110] In this embodiment, resources represent, for example, frequency, time, resource unit (including REG, CCE, CORESET), resource block, bandwidth part, component carrier, symbol, sub-symbol, time slot, mini time slot, sub-time slot, subframe, frame, PRACH opportunity, opportunity, code, multiple access physical resource, multiple access signature and subcarrier spacing (parameter set), etc.

[0111] The configuration of each wireless communication device included in the communication system 1 will be described in detail later. The configuration of each wireless communication device shown below is only an example. The configuration of each wireless communication device may be different from the following configuration.

[0112] <2-1. Configuration of Management Device>

[0113] The management device 10 is an information processing device (computer) that manages a wireless network. For example, the management device 10 manages communications of the base station 20. The management device 10 may be, for example, a device that functions as a mobility management entity (MME). The management device 10 may also function as an access and mobility management function (AMF) and / or a session management function (SMF). The MME, AMF, and SMF are control plane network functions in the core network. The management device 10 may be a device that functions as a 6G control plane network function (6G CPNF). The 6G CPNF includes one or more logical nodes.

[0114] The functions of the management device 10 are not limited to MME, AMF, SMF, or 6G CPNF. The management device 10 may be a device having a function as a network slice selection function (NSSF), an authentication server function (AUSF), a policy control function (PCF), or a unified data management (UDM). In addition, the management device 10 may be a device having a function as a home subscriber server (HSS).

[0115] It should be noted that the management device 10 may function as a gateway. For example, the management device 10 may function as a serving gateway (S-GW) or a packet data network gateway (P-GW). Furthermore, the management device 10 may function as a user plane function (UPF). In this case, the management device 10 may have multiple UPFs. The management device 10 may function as a 6G user plane network function (6G UPNF).

[0116] The core network includes multiple network functions. Each network function can be integrated into a single physical device or distributed across multiple physical devices. That is, the management device 10 can be deployed in multiple devices as a distributed arrangement. In addition, this distributed arrangement can be controlled to be implemented dynamically. The base station 20 and the management device 10 form a network and provide wireless communication services to the terminal device 40. The management device 10 is connected to the Internet, and the terminal device 40 can use various services provided via the Internet through the base station 20.

[0117] It should be noted that the management device 10 does not necessarily need to be a device that constitutes the core network. For example, assuming that the core network is a Wideband Code Division Multiple Access (W-CDMA) or Code Division Multiple Access 2000 (CDMA2000) core network, the management device 10 can be a device that acts as a radio network controller (RNC).

[0118] Figure 5 1 is a diagram showing a configuration of the management apparatus 10 according to the present embodiment. The management apparatus 10 includes a communication unit 11 , a storage unit 12 , and a control unit 13 . Figure 5 The configuration shown in FIG is a functional configuration, and the hardware configuration may be different from this. The functions of the management device 10 may be implemented in multiple physically separated configurations in a static or dynamic distribution form. The management device 10 may be composed of multiple server devices.

[0119] The communication unit 11 is a communication interface for communicating with a wireless communication device (e.g., the base station 20 or the relay station 30). The communication unit 11 may be a network interface or a device connection interface. The communication unit 11 may be a local area network (LAN) interface such as a network interface card (NIC), or a universal serial bus (USB) interface including a USB host controller, a USB port, or the like. The communication unit 11 may be a wired interface or a wireless interface. The communication unit 11 serves as a communication device for the management device 10. The communication unit 11 is controlled by the control unit 13.

[0120] The storage unit 12 is a readable / writable storage device, such as dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, or a hard disk. The storage unit 12 serves as a storage device in the management device 10. The storage unit 12 stores, for example, the connection status of the terminal device 40. The storage unit 12 stores the radio resource control (RRC) status, EPS connection management (ECM) status, or 5G system connection management (CM) status of the terminal device 40. The storage unit 12 can also serve as a unit called a "home memory" (user information database) that stores the location information of the terminal device 40.

[0121] The control unit 13 is a controller that controls the various components of the management device 10. The control unit 13 can be implemented by a processor, such as a central processing unit (CPU) or a microprocessor unit (MPU), for example. Specifically, the control unit 13 can be implemented by the processor using a random access memory (RAM) or the like as a working area to execute various programs stored in a storage device inside the management device 10. The control unit 13 can be implemented by an integrated circuit such as an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA). In addition, the control unit 13 can be implemented by a graphics processing unit (GPU). CPU, MPU, ASIC, FPGA and GPU can all be regarded as controllers. The control unit 13 may include multiple physically separated objects. For example, the control unit 13 may include multiple semiconductor chips.

[0122] <2-2. Base Station Configuration>

[0123] The base station 20 is a wireless communication device that performs wireless communication with other wireless communication devices (e.g., a relay station 30, a terminal device 40, or another base station 20). The base station 20 can perform wireless communication with the terminal device 40 via the relay station 30 or directly with the terminal device 40.

[0124] The base station 20 is a device corresponding to a radio base station (base station, node B, eNB, gNB, or 6GNB, etc.) or a radio access point. The base station 20 may be a wireless relay station. The base station 20 may be an optical link device called a remote radio head (RRH). In addition, the base station 20 may be a receiving station such as a field pickup unit (FPU). The base station 20 may be an integrated access and backhaul (IAB) donor node or an IAB relay node that provides a radio access channel and a radio backhaul channel using time division multiplexing, frequency division multiplexing, or space division multiplexing.

[0125] The radio access technology used by the base station 20 may be a cellular communication technology. The radio access technology used by the base station 20 may be a wireless LAN technology. For example, the radio access technology used by the base station 20 may be a low power wide area (LPWA) communication technology. It should be noted that the radio access technology used by the base station 20 is not limited thereto and may be other radio access technologies. The radio communication used by the base station 20 may be a radio communication using millimeter waves or a radio communication using terahertz waves (THz waves). The wireless communication used by the base station 20 may be a wireless communication using radio waves or a wireless communication using infrared or visible light (optical wireless communication). The base station 20 may be able to perform non-orthogonal multiple access (NOMA) communication with the terminal device 40. Here, NOMA communication refers to communication (sending, receiving, or both) using non-orthogonal resources. It should be noted that the base station 20 may be able to implement NOMA communication with another base station 20.

[0126] The base stations 20 may be able to communicate with each other via a base station-core network interface (e.g., an NG interface, an S1 interface, etc.). This interface may be implemented as a wired or wireless interface. In addition, the base stations may be able to communicate with each other via an inter-base station interface (e.g., an Xn interface, an X2 interface, an F1 interface, etc.). This interface may be implemented as a wired or wireless interface.

[0127] The concept of a base station (also referred to as a "base station device") includes not only a donor base station but also a relay base station (also referred to as a "relay station"). A relay base station can be any of an RF repeater, a smart repeater, and a smart surface. The concept of a base station includes not only a structure having base station functions but also the equipment installed in the structure.

[0128] Examples of the structure include buildings, such as high-rise buildings, houses, steel towers, station facilities, airport facilities, port facilities, office buildings, school buildings, hospitals, factories, commercial facilities, or stadiums. The concept of structure includes not only buildings, but also non-building structures such as tunnels, bridges, dams, fences, and iron pillars, as well as facilities such as cranes, gates, and windmills. The concept of structure includes not only land-based (narrowly defined, ground-based) structures or underground structures, but also water structures such as breakwaters or very large floating bodies, and underwater structures such as ocean observation facilities. A base station may also be referred to as an information processing device.

[0129] The base station 20 can be a donor station or a relay station. The base station 20 can be a fixed station or a mobile station. A mobile station is a wireless communication device configured to be movable (e.g., a base station). In this case, the base station 20 can be a device installed on a mobile body, or it can be the mobile body itself. For example, a relay station with mobility can be regarded as a base station 20 as a mobile station. In addition, devices such as unmanned aerial vehicles (UAVs) represented by drones or smartphones that are designed to be mobile and have base station functions (at least part of the base station functions) also correspond to the base station 20 as a mobile station.

[0130] Here, the mobile object may be a mobile terminal such as a smart phone or a mobile phone. The mobile object may be a mobile object that moves on land (ground in a narrow sense) (for example, a car, motorcycle, bus, truck, motorcycle, train, or linear electric vehicle), or a mobile object that moves underground (for example, through a tunnel) (for example, a subway). The mobile object may be a mobile object that moves on water (for example, a passenger ship, a cargo ship, or a hovercraft), or a mobile object that moves underwater (for example, a semi-submersible vessel, a submarine, or an unmanned submarine). The mobile object may be a mobile object that moves in the atmosphere (for example, an aircraft such as an airplane, an airship, or a drone).

[0131] The base station 20 can be a ground base station device (ground station) installed on the ground. The base station 20 can be a base station arranged on a structure on the ground, or it can be a base station installed in a mobile body moving on the ground. The base station 20 can be an antenna installed in a structure such as a building and a signal processing device connected to the antenna. The base station 20 can be the structure or the mobile body itself. "Ground" not only means land (ground in a narrow sense), but also means a ground position in a broad sense including underground, above water and underwater. The base station 20 is not limited to a ground base station. In the case where the communication system 1 is a satellite communication system, the base station 20 can be an aircraft station. From the perspective of a satellite station, an aircraft station located on the earth is a ground station.

[0132] The base station 20 is not limited to a ground station. The base station 20 may be a non-ground base station (non-ground station) capable of floating in the air or in space. For example, the base station 20 may be an aircraft station or a satellite station.

[0133] A satellite station is a satellite station capable of floating outside the atmosphere. A satellite station may be a device mounted on a space mobile object such as an artificial satellite, or may be the space mobile object itself. A space mobile object is a mobile object that moves outside the atmosphere. Examples of space mobile objects include artificial objects such as artificial satellites, spacecraft, space stations, or probes. A satellite serving as a satellite station may be any one of a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, or a highly elliptical orbit (HEO) satellite. A satellite station may be a device mounted on a low earth orbit satellite, a medium earth orbit satellite, a geostationary earth orbit satellite, or a highly elliptical orbit satellite.

[0134] An aircraft station is a wireless communication device capable of floating in the atmosphere, such as an aircraft. An aircraft station can be mounted on an aircraft, or it can be the aircraft itself. The term "aircraft" encompasses not only heavy aircraft such as airplanes and gliders, but also lightweight aircraft such as balloons and airships. The term "aircraft" encompasses not only heavy and lightweight aircraft, but also rotary-wing aircraft such as helicopters and autogyros. An aircraft station, or an aircraft equipped with an aircraft station, can be an unmanned aerial vehicle such as a drone.

[0135] The concept of unmanned aerial vehicles also includes unmanned aerial vehicle systems (UAS) and tethered UAS. The concept of unmanned aerial vehicles also includes lighter-than-air (LTA) unmanned aerial vehicle systems (UAS) and heavier-than-air (HTA) unmanned aerial vehicle systems (UAS). The concept of unmanned aerial vehicles also includes high-altitude unmanned aerial vehicle system (UAS) platforms (HAPs).

[0136] The coverage area of ​​base station 20 can be relatively large, such as a macrocell, or relatively small, such as a picocell. The coverage area of ​​base station 20 can also be extremely small, such as a femtocell. Base station 20 can have beamforming capabilities. In this case, base station 20 can form beams for each cell or service area.

[0137] Figure 6 2 is a diagram showing a configuration of a base station 20 according to the present embodiment. The base station 20 includes a wireless communication unit 21, a storage unit 22, and a control unit 23. Figure 6 The configuration shown in FIG. 1 is a functional configuration, and the hardware configuration may be different from this configuration. In addition, the functions of the base station 20 may be implemented in a plurality of physically separated configurations in a distributed manner.

[0138] The wireless communication unit 21 is a signal processing unit for performing wireless communication with other wireless communication devices (e.g., a relay station 30, a terminal device 40, or another base station 20). The wireless communication unit 21 is controlled by the control unit 23. The wireless communication unit 21 can support one or more radio access schemes. The wireless communication unit 21 can support at least one of NR, LTE, and 6G. In addition to NR, LTE, or 6G, the wireless communication unit 21 can support W-CDMA, cdma2000, etc. The wireless communication unit 21 can support automatic retransmission technologies such as hybrid automatic repeat request (HARQ).

[0139] The wireless communication unit 21 includes a transmit processing unit 211, a receive processing unit 212, and an antenna 213. The wireless communication unit 21 may include multiple transmit processing units 211, multiple receive processing units 212, and multiple antennas 213. If the wireless communication unit 21 supports multiple radio access schemes, each component of the wireless communication unit 21 may be configured separately for each radio access scheme. The transmit processing unit 211 and the receive processing unit 212 may be configured separately for LTE, NR, and 6G. The antenna 213 may include multiple antenna elements, such as multiple patch antennas. The wireless communication unit 21 may have a beamforming function. For example, the wireless communication unit 21 may have a polarization beamforming function using vertically polarized waves (V-polarized waves) and horizontally polarized waves (H-polarized waves) (or may have a polarization beamforming function using dual polarization in polarization directions of 45 degrees and -45 degrees from the vertical direction).

[0140] The transmission processing unit 211 implements the transmission processing of downlink control information and downlink data. The transmission processing unit 211 encodes the downlink control information and downlink data input from the control unit 23 using a coding method such as block coding, convolutional coding or turbo coding. The coding can be implemented using a polarization code or a low-density parity check (LDPC) code. The transmission processing unit 211 modulates the coded bits using a predetermined modulation scheme such as BPSK, QPSK, 16QAM, 64QAM or 256QAM. In this case, the signal points on the constellation diagram do not necessarily need to be equidistant. The constellation diagram can be a non-uniform constellation diagram (NUC). The transmission processing unit 211 multiplexes the modulation symbols and downlink reference signals of each channel and allocates the multiplexed signals on predetermined resource units. Subsequently, the transmission processing unit 211 performs various signal processing on the multiplexed signals. For example, the transmission processing unit 211 performs processes such as conversion to the frequency domain using fast Fourier transform, adding a guard interval (cyclic prefix), generating a baseband digital signal, converting to an analog signal, orthogonal modulation, up-conversion, removing unnecessary frequency components, and power amplification. The signal generated by the transmission processing unit 211 is transmitted from the antenna 213.

[0141] The receive processing unit 212 processes the uplink signal received via the antenna 213. For example, the receive processing unit 212 performs processing on the uplink signal, such as downconversion, removal of unnecessary frequency components, control of the amplification level, orthogonal demodulation, conversion to a digital signal, removal of the guard interval (cyclic prefix), and frequency domain signal extraction using a fast Fourier transform. The receive processing unit 212 then demultiplexes the signal after these processing steps into uplink channels (such as the physical uplink shared channel (PUSCH) or the physical uplink control channel (PUCCH)) and uplink reference signals. The receive processing unit 212 then demodulates the received signal using a modulation scheme such as binary phase shift keying (BPSK) or quadrature phase shift keying (QPSK) for the modulation symbols of the uplink channel. The modulation scheme used for demodulation can be 16-bit quadrature amplitude modulation (QAM), 64-QAM, or 256-QAM. In this case, the signal points on the constellation do not necessarily need to be equidistant. The constellation can be a non-uniform constellation (NUC). The reception processing unit 212 then decodes the coded bits of the demodulated uplink channel. The decoded uplink data and uplink control information are output to the control unit 23.

[0142] Antenna 213 is an antenna device that implements the mutual conversion between electric current and radio waves. Antenna 213 may include an antenna element, such as a patch antenna. In addition, antenna 213 may include multiple antenna elements (e.g., multiple patch antennas). When antenna 213 includes multiple antenna elements, wireless communication unit 21 may have a beamforming function. Wireless communication unit 21 may use multiple antenna elements to control the directionality of radio signals to generate a directional beam. Antenna 213 may be a dual-polarization antenna. When antenna 213 is a dual-polarization antenna, wireless communication unit 21 may use vertically polarized waves (V-polarized waves) and horizontally polarized waves (H-polarized waves) (or dual-polarized waves with polarization directions of 45 degrees and -45 degrees to the vertical direction) in radio signal transmission. Wireless communication unit 21 may control the directionality of radio signals transmitted using vertically polarized waves and horizontally polarized waves (or dual-polarized waves with polarization directions of 45 degrees and -45 degrees to the vertical direction). In addition, wireless communication unit 21 may transmit and receive spatially multiplexed signals through multiple layers including multiple antenna elements.

[0143] Storage unit 22 is a readable / writable storage device, such as DRAM, SRAM, flash memory, or a hard disk. Storage unit 22 serves as a storage device in base station 20. Storage unit 22 can store AI / ML models used in each functional process. The AI / ML models stored in base station 20 may be similar to or different from the AI / ML models stored in relay station 30 or terminal device 40, described later.

[0144] The control unit 23 is a controller that controls various parts of the base station 20. The control unit 23 controls the wireless communication unit to implement wireless communication with another wireless communication device (such as a relay station 30, a terminal device 40 or another base station 20). The control unit 23 can be implemented by a processor such as a CPU or an MPU. Specifically, the control unit 23 can be implemented by the processor using RAM or the like as a working area to execute various programs stored in a storage device inside the base station 20. The control unit 23 can be implemented by an integrated circuit such as an ASIC or an FPGA. The control unit 23 can be implemented by a GPU. CPU, MPU, ASIC, FPGA and GPU can all be regarded as controllers. The control unit 23 may include multiple physically separate objects. For example, the control unit 23 may include multiple semiconductor chips.

[0145] The control unit 23 includes an acquisition unit 231, a management unit 232, a discrimination unit 233, a decision unit 234, a sending unit 235 and a receiving unit 236. The various blocks (acquisition unit 231 to receiving unit 236) that constitute the control unit 23 are functional blocks that respectively indicate the various functions of the control unit 23. These functional blocks can be software blocks or hardware blocks. For example, each functional block described above can be a software module implemented by software (including microprograms), or can be a circuit block on a semiconductor chip (die). It goes without saying that each functional block can be formed as a processor or an integrated circuit. It should be noted that the control unit 23 can be configured in a functional unit different from the functional blocks described above. Any method can be used to configure the functional blocks.

[0146] In some embodiments, the base station 20 may be configured as a collection of multiple physical or logical devices. For example, the base station 20 in this embodiment may be classified into multiple devices such as a baseband unit (BBU) and a radio unit (RU). The base station 20 may be understood as a collection of multiple devices. In addition, the base station may be either or both of the BBU and the RU. The BBU and the RU may be connected to each other via a predetermined interface, such as an enhanced common public radio interface (eCPRI).

[0147] The RU can be referred to as a remote radio unit (RRU) or radio DoT (RD). The RU can support the gNB distributed unit (gNB-DU) described below. The BBU can support the gNB central unit (gNB-CU) described below. The RU can be a device integrated with an antenna. The antenna of the base station 20 (e.g., an antenna integrated with the RU) can adopt an advanced antenna system and support MIMO (e.g., FD-MIMO) or beamforming. For example, the antenna of the base station 20 can include 64 transmit antenna ports and 64 receive antenna ports.

[0148] The antenna mounted on the RU can be an antenna panel including one or more antenna elements, and the RU can include one or more antenna panels. The RU can be equipped with two types of antenna panels: a horizontally polarized antenna panel and a vertically polarized antenna panel. The RU can be equipped with two types of antenna panels, namely a right-hand circularly polarized antenna panel and a left-hand circularly polarized antenna panel, or an antenna panel with a polarization direction of 45 degrees to the vertical direction and an antenna panel with a polarization direction of -45 degrees to the vertical direction. Multiple antennas with multiple polarization directions can be mounted on a single antenna panel. The RU can form and control independent beams for each antenna panel.

[0149] A plurality of base stations 20 may be connected to one another. One or more base stations 20 may be included in a radio access network (RAN). That is, a base station 20 may be simply referred to as a RAN, a RAN node, an access network (AN), an AN node, etc. The RAN in LTE is sometimes referred to as an Enhanced Universal Terrestrial RAN (EUTRAN). The RAN in NR may be referred to as an NGRAN. Furthermore, the RAN in 6G may be referred to as a 6G RAN. The RAN in W-CDMA (UMTS) may be referred to as an UTRAN.

[0150] The base station 20 in LTE can be referred to as an evolved Node B (eNodeB) or eNB. That is, the EUTRAN includes one or more eNodeBs (eNBs). The NR base station 20 can be referred to as a gNodeB or gNB. In this case, the NGRAN includes one or more gNBs. The 6G base station can be referred to as a 6GNodeB, 6gNodeB, 6GNB, or 6gNB. In this case, the 6GRAN includes one or more 6GNBs. The EUTRAN may include a gNB (en-gNB) connected to the core network (EPC) in the LTE communication system (EPS). The NGRAN may include an ng-eNB connected to the core network 5GC in the 5G communication system (5GS).

[0151] When base station 20 is an eNB, gNB, 6GNB, etc., base station 20 may be referred to as 3GPP access. When base station 20 is a radio access point, base station 20 may be referred to as non-3GPP access. Base station 20 may be an optical link device referred to as a remote radio head (RRH). Furthermore, when base station 20 is a gNB, base station 20 may be a combination of the gNB-CU and gNB-DU described above, or may be either a gNB-CU or a gNB-DU.

[0152] To communicate with the UE, the gNB-CU hosts multiple upper layers in the access stratum (e.g., Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP)). Meanwhile, the gNB-DU hosts multiple lower layers in the access stratum (e.g., Radio Link Control (RLC), Medium Access Control (MAC), and Physical Layer (PHY)). Specifically, among the messages / information described below, RRC signaling (quasi-static notification) may be generated by the gNB-CU, while MAC CE and DCI (dynamic notification) may be generated by the gNB-DU. Alternatively, for example, in RRC configuration (quasi-static notification), some configurations, such as IE:cellGroupConfig, may be generated by the gNB-DU, while the remaining configurations may be generated by the gNB-CU. These configurations may be sent and received via the F1 interface, described below.

[0153] The base station 20 can be configured to communicate with another base station. When multiple base stations 20 are eNBs or a combination of eNBs and en-gNBs, these base stations 20 can be connected through the X2 interface. When multiple base stations 20 are gNBs or a combination of gn-eNBs and gNBs, these base stations 20 can be connected through the Xn interface. When multiple base stations 20 are a combination of gNB-CUs and gNB-DUs, these base stations 20 can be interconnected through the F1 interface described above. Messages / information (such as RRC signaling, MAC control element (MAC CE), downlink control information (DCI), etc.) to be described later can be sent between multiple base stations 20, for example, through interfaces such as the X2 interface, the Xn interface, and the F1 interface.

[0154] The cell provided by the base station 20 may be referred to as a serving cell. The concept of a serving cell includes a primary cell (PCell) and a secondary cell (SCell). When dual connectivity is provided for a terminal device 40, the PCell and zero or one or more SCells provided by a leading node (MN) may be referred to as a leading cell group. Examples of dual connectivity include EUTRA-EUTRA dual connectivity, EUTRA-NR dual connectivity (ENDC), EUTRA-NR dual connectivity with 5GC, NR-EUTRA dual connectivity (NEDC), and NR-NR dual connectivity. Examples of dual connectivity also include NR-6G dual connectivity and 6G-NR dual connectivity.

[0155] The serving cell may include a primary secondary cell or a primary SCG cell (PSCell). In the case of providing dual connectivity for the terminal device 40, the PSCell and zero or one or more SCells provided by the secondary node (SN) may be referred to as a secondary cell group (SCG). Unless specially configured (e.g., PUCCH on the SCell), the physical uplink control channel (PUCCH) is sent through the PCell and PSCell, but not through the SCell. Radio link failures are also detected through the PCell and PSCell, but not through the SCell (does not need to be detected). In this way, since the PCell and PSCell have special roles in the serving cell, these cells are also referred to as special cells (SpCell).

[0156] A cell can be associated with one downlink component carrier and one uplink component carrier. The system bandwidth corresponding to a cell can be divided into multiple bandwidth parts (BWPs). In this case, one or more BWPs can be configured for the terminal device 40, and one BWP can be used for the terminal device 40 as the active BWP. The radio resources (e.g., frequency bandwidth, parameter set (subcarrier spacing), and time slot format (time slot configuration)) that can be used by the terminal device 40 can be different for each cell, each component carrier, or each BWP.

[0157] <2-3. Relay Station Configuration>

[0158] The relay station 30 is a wireless communication device that acts as a repeater for the base station 20. The relay station 30 is a type of base station. The relay station 30 is a type of information processing device. The relay station 30 may also be referred to as a relay base station. For example, the relay station 30 may be a device known as a repeater (e.g., an RF repeater, a smart repeater, or a smart surface). The relay station 30 is a wireless communication device that wirelessly communicates with other wireless communication devices (e.g., the base station 20, another base station 30, or a terminal device 40).

[0159] The relay station 30 may be capable of performing NOMA communication with the terminal device 40. The relay station 30 relays communication between the base station 20 and the terminal device 40. The relay station 30 may be capable of performing wireless communication with another relay station 30 and the base station 20. The relay station 30 may be a ground station device or a non-ground station device. The relay station 30 and the base station 20 together constitute a radio access network RAN.

[0160] The relay station 30 may be a fixed device, a mobile device, or a floating device. The size of the coverage area of ​​the relay station 30 is not limited to a specific size. The cell covered by the relay station 30 may be a macro cell, a micro cell, or a small cell.

[0161] The relay station 30 can be installed on any type of device as long as it satisfies the relay function. The relay station 30 can be installed on a terminal device such as a smartphone, a car, a train, or a rickshaw, a balloon, an airplane, or a drone, or a household appliance such as a television, a game console, an air conditioner, a refrigerator, or a lighting fixture.

[0162] The configuration of the relay station 30 can be similar to the configuration of the base station 20 described above. Similar to the base station 20 described above, the relay station 30 can be a device installed on a mobile body, or it can be the mobile body itself. Here, as described above, the mobile body can be a mobile terminal such as a smart phone or a cellular phone. The mobile body can be a mobile body that moves on land (on the ground in a narrow sense), or it can be a mobile body that moves underground. The mobile body can be a mobile body that moves on water, or it can be a mobile body that moves underwater. The mobile body can be a mobile body that moves within the atmosphere, or it can be a mobile body that moves outside the atmosphere. The relay station 30 can be a ground station device or a non-ground station device. The relay station 30 can be an aircraft station or a satellite station.

[0163] Similar to base station 20, relay station 30 can have a large coverage area, such as a macrocell, or a small coverage area, such as a picocell. Relay station 30 can also have an extremely small coverage area, such as a femtocell. Relay station 30 can have a beamforming function. Relay station 30 can form beams for each cell or service area.

[0164] Figure 7 3 is a diagram showing a configuration of the relay station 30 according to the present embodiment. The relay station 30 includes a wireless communication unit 31 , a storage unit 32 , and a control unit 33 . Figure 7 The configuration shown in FIG is a functional configuration, and the hardware configuration may be different from this configuration. In addition, the functions of the relay station 30 may be implemented in a plurality of physically separated configurations in a distributed manner.

[0165] The wireless communication unit 31 is a signal processing unit for performing wireless communication with other wireless communication devices (e.g., the base station 20, the terminal device 40, or another relay station 30). The wireless communication unit 31 can support one or more radio access schemes. The wireless communication unit 31 can support at least one of NR, LTE, and 6G. In addition to NR, LTE, and 6G, the wireless communication unit 31 can also support W-CDMA, cdma3000, and the like.

[0166] The wireless communication unit 31 includes a transmit processing unit 311, a receive processing unit 312, and an antenna 313. The wireless communication unit 31 may include multiple transmit processing units 311, multiple receive processing units 312, and multiple antennas 313. If the wireless communication unit 31 supports multiple radio access schemes, each component of the wireless communication unit 31 may be configured separately for each radio access scheme. The transmit processing unit 311 and receive processing unit 312 may be configured separately for LTE, NR, and 6G. The configurations of the transmit processing unit 311, receive processing unit 312, and antenna 313 may be similar to the configurations of the transmit processing unit 211, receive processing unit 212, and antenna 213 of the base station 20, respectively, described above. Similar to the wireless communication unit 21 of the base station 20, the wireless communication unit 31 may have a beamforming function.

[0167] Storage unit 32 is a readable / writable storage device, such as DRAM, SRAM, flash memory, or a hard disk. Storage unit 32 serves as a storage device in relay station 30. The configuration and function of storage unit 32 can be similar to the configuration and function of storage unit 22 of base station 20 described above. Storage unit 32 can store AI / ML models used in each functional processing. The AI / ML models stored in relay station 30 can be similar to or different from the AI / ML models stored in base station 20 described above or in terminal device 40 described below.

[0168] The control unit 33 is a controller that controls various parts of the relay station 30. The control unit 33 can be implemented by a processor such as a CPU or an MPU. For example, the control unit 33 is implemented by the processor using RAM or the like as a work area to execute various programs stored in a storage device inside the relay station 30. The control unit 33 can be implemented by an integrated circuit such as an ASIC or an FPGA. A CPU, an MPU, an ASIC, and an FPGA can all be considered controllers. The control unit 33 can be implemented by a GPU. A CPU, an MPU, an ASIC, an FPGA, and a GPU can all be considered controllers. The control unit 33 can include multiple physically separate objects. For example, the control unit 33 can include multiple semiconductor chips. The configuration and functions of the control unit 33 can be similar to the configuration and functions of the control unit 23 of the base station 20 described above.

[0169] The control unit 33 includes an acquisition unit 331, a management unit 332, a discrimination unit 333, a decision unit 334, a sending unit 335 and a receiving unit 336. The various blocks (acquisition unit 331 to receiving unit 336) that constitute the control unit 33 are functional blocks that respectively indicate the various functions of the control unit 33. These functional blocks can be software blocks or hardware blocks. For example, each functional block described above can be a software module implemented by software (including microprograms), or can be a circuit block on a semiconductor chip (die). Of course, each functional block can be formed as a processor or an integrated circuit. It should be noted that the control unit 33 can be configured in a functional unit different from the functional blocks described above. Any method can be used to configure the functional blocks.

[0170] It should be noted that the relay station 30 may be an IAB relay node. The relay station 30 operates as an IAB mobile termination (IAB-MT) for an IAB donor node for providing backhaul, and operates as an IAB distributed unit (IAB-DU) for providing access to a terminal device 40. The IAB donor node may be, for example, the base station 20, and operates as an IAB central unit (IAB-CU).

[0171] <2-4. Terminal Device Configuration>

[0172] The terminal device 40 is a wireless communication device that implements wireless communication with another wireless communication device (such as a base station 20, a relay station 30, or another terminal device 40). The terminal device 40 can be implemented using any form of information processing device (computer). For example, the terminal device 40 can be a mobile terminal such as a mobile phone, a smart device (smartphone or tablet device), a personal digital assistant (PDA), or a laptop PC. The terminal device 40 can be an imaging device with a communication function (such as a camcorder). The terminal device 40 can be a motorcycle, a mobile relay vehicle, etc. equipped with a communication device such as a field pickup unit (FPU). The terminal device 40 can be a machine-to-machine (M2M) device or an Internet of Things (IoT) device. The terminal device 40 can be a wearable device such as a smart watch.

[0173] The terminal device 40 may be an xR device, such as an augmented reality (AR) device, a virtual reality (VR) device, or a mixed reality (MR) device. In this case, the xR device may be a glasses-type device such as AR glasses or MR glasses, or may be a head-mounted device such as a VR head-mounted display. In the case where the terminal device 40 is an xR device, the terminal device 40 may be an independent device that only includes a user-worn part (e.g., a glasses part). In addition, the terminal device 40 may be a terminal-linked device that includes a user-worn part (e.g., a glasses part) and a terminal part (e.g., a smart device) linked to the user-worn part.

[0174] The terminal device 40 may be able to implement NOMA communication with the base station 20. The terminal device 40 may be able to use automatic retransmission technologies such as HARQ when communicating with the base station 20. The terminal device 40 may be able to perform sidelink communication with another terminal device 40. The terminal device 40 may be able to use automatic retransmission technologies such as HARQ when implementing sidelink communication. The terminal device 40 may be able to implement NOMA communication when implementing a sidelink with another terminal device 40. The terminal device 40 may be able to implement LPWA communication with another wireless communication device (such as the base station 20). The wireless communication used by the terminal device 40 may be wireless communication using millimeter waves. The wireless communication (including sidelink communication) used by the terminal device 40 may be wireless communication using radio waves or wireless communication using infrared or visible light (i.e., optical wireless communication).

[0175] The terminal device 40 can be a movable wireless communication device, that is, a mobile device. In addition, the terminal device 40 can be a wireless communication device installed on a mobile body, or can be the mobile body itself. The terminal device 40 can be a vehicle moving on the road, such as a car, a bus, a truck or a motorcycle, or can be a wireless communication device installed on a vehicle. The mobile body can be a mobile terminal, or can be a mobile body moving on land (on the ground in a narrow sense), underground, on water or underwater. The mobile body can be a mobile body moving within the atmosphere, such as an aircraft, an airship, a balloon or a helicopter, or can be a mobile body moving outside the atmosphere, such as an artificial satellite. The mobile body can be an unmanned aerial vehicle (UAV) such as a drone. The terminal device 40 can be a wireless communication device installed on a mobile body.

[0176] The terminal device 40 may be able to simultaneously connect to multiple base stations 20 or multiple cells to implement communications. For example, when a base station 20 supports a communication area through multiple cells (e.g., pCells and sCells), it is possible to use carrier aggregation (CA), dual connectivity (DC), or multi-connectivity (MC) technology to bundle the multiple cells together and communicate between the base station 20 and the terminal device 40. Alternatively, the terminal device 40 and multiple base stations 20 may communicate with each other via the cells of different base stations 20 using coordinated multipoint transmission and reception (CoMP).

[0177] The terminal device 40 may be a relay terminal that relays communications to a remote terminal.

[0178] Figure 8 4 is a diagram showing a configuration of a terminal device 40 according to the present embodiment. The terminal device 40 includes a wireless communication unit 41 , a storage unit 42 , and a control unit 43 . Figure 8 The configuration shown in is a functional configuration, and the hardware configuration may be different from this configuration. In addition, the functions of the terminal device 40 may be implemented in a plurality of physically separate configurations in a distributed manner.

[0179] The wireless communication unit 41 is a signal processing unit for performing wireless communication with other wireless communication devices (e.g., the base station 20, the relay station 30, and another terminal device 40). The wireless communication unit 41 is controlled by the control unit 43. The wireless communication unit 41 can support one or more radio access schemes. The wireless communication unit 41 can support at least one of NR, LTE, and 6G. In addition to NR, LTE, and 6G, the wireless communication unit 41 can support W-CDMA, cdma2000, etc. The wireless communication unit 41 can support automatic retransmission technologies such as hybrid automatic repeat request (HARQ).

[0180] The wireless communication unit 41 includes a transmit processing unit 411, a receive processing unit 412, and an antenna 413. The wireless communication unit 41 may include multiple transmit processing units 411, multiple receive processing units 412, and multiple antennas 413. If the wireless communication unit 41 supports multiple radio access schemes, each component of the wireless communication unit 41 may be configured separately for each radio access scheme. The transmit processing unit 411 and the receive processing unit 412 may be configured separately for LTE, NR, and 6G. The antenna 413 may include multiple antenna elements, such as multiple patch antennas. The wireless communication unit 41 may have a beamforming function. For example, the wireless communication unit 41 may have a polarization beamforming function using vertically polarized waves (V-polarized waves) and horizontally polarized waves (H-polarized waves) (or may have a polarization beamforming function using dual polarization in polarization directions of 45 degrees and -45 degrees from the vertical direction).

[0181] Storage unit 42 is a readable / writable storage device, such as DRAM, SRAM, flash memory, or a hard disk. Storage unit 42 serves as a storage device in terminal device 40. Storage unit 42 can store AI / ML models used in each functional process. The AI / ML models stored in terminal device 40 can be similar to or different from the AI / ML models stored in base station 20 or relay station 30 described above.

[0182] The control unit 43 is a controller that controls various parts of the terminal device 40. The control unit 43 controls the wireless communication unit to implement wireless communication with another wireless communication device (such as the base station 20, the relay station 30 or another terminal device 40). The control unit 43 can be implemented by a processor such as a CPU or an MPU. For example, the control unit 23 is implemented by the processor using RAM or the like as a working area to execute various programs stored in a storage device inside the terminal device 40. The control unit 43 can be implemented by an integrated circuit such as an ASIC or an FPGA. The CPU, MPU, ASIC and FPGA can all be regarded as controllers. The control unit 43 can be implemented by a GPU. The CPU, MPU, ASIC, FPGA and GPU can all be regarded as controllers. The control unit 43 can include multiple physically separate objects. For example, the control unit 43 can include multiple semiconductor chips.

[0183] The control unit 43 includes an acquisition unit 431, a management unit 432, a discrimination unit 433, a decision unit 434, a sending unit 435 and a receiving unit 436. The various blocks (acquisition unit 431 to receiving unit 436) that constitute the control unit 43 are functional blocks that respectively indicate the various functions of the control unit 43. These functional blocks can be software blocks or hardware blocks. For example, each functional block described above can be a software module implemented by software (including microprograms), or can be a circuit block on a semiconductor chip (die). Of course, each functional block can be formed as a processor or an integrated circuit. It should be noted that the control unit 43 can be configured in a functional unit different from the functional blocks described above. Any method can be used to configure the functional blocks.

[0184] <2-5. AI / ML Model>

[0185] As previously described, the storage unit 22 of the base station 20, the storage unit 32 of the relay station 30, and the storage unit 42 of the terminal device 40 each store an AI / ML model. Furthermore, as previously described, the base station 20, the relay station 30, and the terminal device 40 each generate various information using the AI / ML model. In the following description, the AI / ML model may be referred to as a learning model or simply a model.

[0186] The learning model is, for example, a neural network model. The neural network model includes an input layer, an intermediate layer (or hidden layer) and an output layer, each of which includes multiple nodes, and the nodes are connected to each other by edges. Each layer has a function called an activation function, and each edge is weighted. The learning model has one or more intermediate layers (or hidden layers). When the learning model is implemented as a neural network model, the learning of the learning model includes, for example, setting the number of intermediate layers (or hidden layers), the number of nodes in each layer, the weight of each edge, etc.

[0187] Here, the neural network model may be a model trained by deep learning. In this case, the neural network model may be a model in the form of a deep neural network (DNN). For example, the neural network model may be a model in the form of a convolutional neural network (CNN), a recurrent neural network (RNN), or a long short-term memory (LSTM). Of course, the neural network model is not limited to these forms of models.

[0188] In CNN, the hidden layers include layers called convolutional layers and pooling layers. The convolutional layer applies filtering through convolution operations to extract data called feature maps. The pooling layer compresses the information of the feature maps output from the convolutional layer to achieve downsampling. CNN is used for image recognition, for example, and information about each picture element (also called a pixel of an image) is input to the input layer, making it possible to obtain information related to the image recognized as the output layer.

[0189] RNN has a network structure in which a value of a hidden layer is recursively input to the hidden layer, and processes, for example, short-term time series data.

[0190] In LSTM, by introducing parameters called memory cells that maintain the state of the intermediate layers into the output of the intermediate layers of the RNN, the influence of the output in the distant past can be retained. In other words, LSTM can process time series data with longer term duration than RNN.

[0191] Of course, the learning model is not limited to a neural network model. For example, the learning model can be a model based on reinforcement learning. In reinforcement learning, the model is trained through trial and error to take actions (settings) that maximize the value. Alternatively, the learning model can be a logistic regression model.

[0192] It should be noted that the learning model may include multiple models. For example, the learning model may include multiple neural network models. More specifically, the learning model may include multiple neural network models selected from CNN, RNN, and LSTM. When the learning model includes multiple neural network models, the multiple neural network models may be in a dependent relationship or a parallel relationship.

[0193] It should be noted that a learning model may also be referred to as an artificial intelligence (AI) model, a machine learning (ML) model, or a trained model. In the following description, a learning model may be simply referred to as a model. Figure 1 The learning model M shown in FIG is used as an example to describe the learning model.

[0194] The learning model M is a learning model that includes a first model and a second model. The first model and the second model are each submodels of the learning model M. The first model is the first half of the learning model M and is stored in the transmitting device. The second model is the second half of the learning model M and is stored in the receiving device. It should be noted that a submodel can also be considered a type of learning model. The learning model of this embodiment will be described in detail later.

[0195] The learning model M is, for example, a learning model (trained model) that has been trained using auxiliary information T as input data and auxiliary information R as reference fact labels (teaching data). As described above, auxiliary information is information required for a receiving device to perform processing related to wireless communication, or information used to assist in processing related to wireless communication performed by the receiving device. For example, auxiliary information is information (e.g., control information) required for operations of the terminal device 40, such as uplink data transmission, sidelink transmission, unlicensed communication, and handover. The auxiliary information R is information related to the auxiliary information T. The auxiliary information R may be information that is partially different from the auxiliary information T, or may be information that indicates the same information as the auxiliary information T.

[0196] When the base station 20 or the terminal device 40 inputs first information (e.g., auxiliary information T) into the first model of the learning model M, the first model outputs second information (e.g., compressed information / feature information of the auxiliary information T). Furthermore, when the base station 20 or the terminal device 40 inputs second information into the second model of the learning model M, the second model outputs third information (e.g., auxiliary information R).

[0197] In this case, the learning model M may be a learning model including: an input layer that inputs first information (e.g., auxiliary information T); an output layer that outputs third information (e.g., auxiliary information R); a first element belonging to any layer from the input layer to the output layer other than the output layer; and a second element having a value calculated based on the first element and the weight of the first element. The learning model M may be a learning model that enables a computer to implement the following function: by using each element belonging to each layer other than the input layer as a first element, performing an operation based on the first element and the weight of the first element (i.e., a connection coefficient) on the information input to the input layer, and outputting third information from the output layer based on the first information input to the input layer.

[0198] Here, it is assumed that the learning model M is implemented by a neural network with one or more intermediate layers, such as a DNN. In this case, the first element included in the learning model corresponds to, for example, any node in the input layer or an intermediate layer. In addition, the second element corresponds to a node at the next level, that is, a node to which a value is sent from the node corresponding to the first element. In addition, the weight of the first element corresponds to a connection coefficient, which is the weight considered for the value sent from the node corresponding to the first element to the node corresponding to the second element.

[0199] Furthermore, it is assumed that the machine learning model M is implemented by a regression model expressed as "y=a1*x1+a2*x2+···+ai*xi". In this case, the first element included in the learning model M corresponds to the input data (xi), such as x1, x2, etc. In addition, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can be regarded as any node included in the input layer, and the second element can be regarded as a node included in the output layer.

[0200] The base station 20 or the terminal device 40 calculates the information to be output using a model having any type of structure (such as a neural network and a regression model). Specifically, the learning model M has coefficients set to output third information (such as auxiliary information R) in response to the input of first information (such as auxiliary information T). For example, the base station 20 or the terminal device 40 sets the coefficients based on the similarity between the third information and the value obtained by inputting the first information into the learning model. The base station 20 or the terminal device 40 uses such a sub-model (first model) of the learning model M to generate the second information from the first information. Alternatively, the base station 20 or the terminal device 40 uses such a sub-model (second model) of the learning model M to generate the second information from the third information.

[0201] The foregoing example describes a model that outputs third information when first information is input as an example of the learning model M. However, the learning model M according to the embodiment may be a model generated based on results obtained by repeatedly inputting and outputting data to the learning model.

[0202] Furthermore, in the case where the base station 20 or the terminal device 40 performs learning or generates output information using a generative adversarial network (GAN), the learning model may be a model constituting a part of the GAN.

[0203] It should be noted that the training device for training the learning model M can be a base station 20, a relay station 30, or a terminal device 40. The training device can be another information processing device (e.g., the management device 10 or a server device connected to the management device 10 via a network). For example, it is assumed that the server device trains the learning model M. In this case, the server device trains the learning model M and stores the trained learning model M in a storage unit. More specifically, the server device sets the connection coefficient of the learning model M so that the learning model outputs third information (e.g., auxiliary information R) when the first information (e.g., auxiliary information T) is input to the learning model M.

[0204] For example, an information processing device (e.g., management device 10, base station 20, relay station 30, terminal device 40, or server device) inputs the first information into a node of an input layer included in the learning model M, allowing the data to propagate through each intermediate layer to the output layer of the learning model M, thereby causing the learning model M to output third information. Subsequently, the information processing device corrects the connection coefficient of the learning model M based on the difference between the value actually output by the learning model M and the value defined as the reference fact label (teaching data). At this time, the information processing device can correct the connection coefficient using a method such as backpropagation. At this time, the server device can correct the connection coefficient based on the cosine similarity between the vector indicating the input value and the vector indicating the value actually output by the learning model.

[0205] The learning may use any learning algorithm. For example, the information processing device may use a learning algorithm such as a neural network, a support vector machine, clustering, reinforcement learning, a random forest, or a decision tree to train a learning model.

[0206] Although the method of generating the learning model M is described above, the above implementation example is also applicable to learning models other than the learning model M.

[0207] In addition, the learning algorithm used in this embodiment can be used for training implemented individually by a single information processing device (e.g., the management device 10, the base station 20, the relay station 30, the terminal device 40, or the server device), or can be used for collaborative training implemented by multiple information processing devices (e.g., multiple devices selected from the management device 10, the base station 20, the relay station 30, the terminal device 40, and the server device). Here, an example of a learning algorithm for collaborative training implemented by multiple information processing devices is federated learning.

[0208] <<3. Network Architecture>>

[0209] The configuration of the communication system 1 has been described above. Next, the network architecture of the communication system 1 applicable to this embodiment will be described. Here, the architecture of the fifth generation mobile communication system (5G) will be described as an example of the core network CN of the communication system 1.

[0210] Figure 9 5G core network CN is also referred to as 5G core (5GC) / next generation core (NGC). Hereinafter, the 5G core network CN is also referred to as 5GC / NGC. The core network CN is connected to the user equipment (UE) 40 via the (R)AN 530.

[0211] It should be noted that Figure 8 The terminal device 40 shown in FIG. 4 is an example of the UE 40 . Figure 6 The base station 20 shown in Figure 7 The relay station 30 shown in FIG is an example of the RAN / AN 530. In addition, Figure 5 The management device 10 shown in FIG. 5 is an example of a device having the function of AF 549 or AMF 541, for example.

[0212] (R)AN 530 has a function of enabling connection to a radio access network (RAN) and connection to an access network (AN) other than the RAN. (R)AN 530 includes a base station called a gNB or ng-eNB.

[0213] The core network CN mainly implements connection admission and session management when the UE 40 is connected to the network. The core network CN may include a user plane function group 520 and a control plane function group 540.

[0214] User plane function group 520 includes user plane function (UPF) 521 and data network (DN) 522. UPF 521 performs user plane processing. UPF 521 performs routing / transmission functions for data handled in the user plane. DN 522, including mobile network operator (MNO), provides services for the operator itself, provides Internet connectivity, or provides connections for third-party services. In this way, user plane function group 520 plays the role of a gateway serving as the boundary between the core network (CN) and the Internet.

[0215] The control plane function group 540 includes an access management function (AMF) 541, a session management function (SMF) 542, an authentication server function (AUSF) 543, a network slice selection function (NSSF) 544, a network exposure function (NEF) 545, a network repository function (NRF) 546, a policy control function (PCF) 547, a unified data management (UDM) 548 and an application function (AF) 549.

[0216] The AMF 541 has functions such as registration processing, connection management, and mobility management for the UE 40. The SMF 542 has functions such as session management and IP allocation and management for the UE 40. The AUSF 543 has an authentication function. The NSSF 544 has functions related to the selection of network slices. The NEF 545 has a function of providing network function capabilities and events to third parties, the AF 549, or edge computing functions.

[0217] The NRF 546 has the function of discovering network functions and maintaining network function profiles. The PCF 547 has the function of policy control. The UDM 548 has the function of generating 3GPP AKA authentication information and user ID processing. The AF 549 has the function of interacting with the core network to provide services.

[0218] For example, the control plane function group 540 obtains information from the UDM 548 that stores the subscriber information of the UE 40 and determines whether the UE 40 is permitted to connect to the network. In this determination, the control plane function group 540 uses the contract information and encryption key of the UE 40 included in the information obtained from the UDM 548. In addition, the control plane function group 540 performs processes such as the generation of encryption keys.

[0219] That is, the control plane function group 540 determines whether to permit network connection based on, for example, whether the UDM 548 stores information of the UE 40 associated with a subscriber number called an International Mobile Subscriber Identity (IMSI). It should be noted that the IMSI is stored in, for example, a Subscriber Identity Module (SIM) card in the UE 40.

[0220] The core network (CN) may include LCM-related network functions. These functions provide LCM-related control. For example, LCM-related network functions control data collection, model training, model identification, model delivery, model transmission, model download, model upload, model derivation, model verification, model testing, model activation, model deactivation, model switching, model fallback, model monitoring, model update, model registration, model deployment, model configuration, or model selection, as well as provide information required for the aforementioned functions.

[0221] The LCM-related network functions may be included in existing network functions. For example, the LCM-related network functions may be included in the model training logic function (MTLF) 551 . Figure 5 The management device 10 shown in FIG. 5 is an example of a device having the function of the MTLF 551 .

[0222] The LCM-related network function may be included in a server constituting the core network CN. For example, the LCM-related network function may be included in a server connected to the UPF 521 (e.g., a mobile edge computing (MEC) server 552). The LCM-related network function may be included in a server connected to the base station 20 ((R)AN 530) (e.g., an MEC server 553). Figure 5 The management device 10 shown in is an example of the MEC server 552 or the MEC server 553.

[0223] The LCM-related network function may be included in the core network CN as a new network function. For example, the LCM-related network function 554 may be included in the core network CN as one of the control plane function groups 540. Figure 5 The management device 10 shown in FIG. 5 is an example of a device having the function of the LCM-related network function 554 .

[0224] The LCM-related network function may exist in the core network CN as one function or multiple functions.

[0225] <<4. Operation of Communication System>>

[0226] The network architecture has been described above. Next, the operation of the communication system 1 having such a configuration will be described.

[0227] <4-1, LCM>

[0228] First, we will describe lifecycle management (LCM). As described above, LCM represents the management of AI / ML models. In the following description, AI / ML models may be referred to as learning models, or simply models.

[0229] The LCM may be configured, for example, by one or more processes / methods / procedures selected from (M1) to (M20) below. It should be noted that (M1) to (M20) below are merely examples. The LCM may include implementation examples other than (M1) to (M20) below. (M1) to (M20) will be described separately below.

[0230] (M1) Data Collection

[0231] Data collection is the process by which a network node, management entity, or user equipment (UE) collects data for the purpose of training, data analysis, and inference of AI / ML models.

[0232] (M2) Model training

[0233] Model training is a process of implementing data-driven training by learning the input / output relationship of the AI / ML model and obtaining the trained AI / ML model for inference.

[0234] (M3) Model Identification

[0235] Model identification is the process / method of identifying AI / ML models for the common understanding of the network and UE.

[0236] (M4) Model Delivery

[0237] Model delivery is a general term that refers to the delivery of an AI / ML model from one entity to another in an optionally selected method.

[0238] (M5) Model Transfer

[0239] Model transmission is the process of transmitting the parameters of a model structure known to the receiving side or a new model with parameters of an AI / ML model over an air interface. The transmission may include the transmission of a complete model or a partial model.

[0240] (M6) Model Download

[0241] Model download is the process of transferring the model from the network to the UE.

[0242] (M7) Model upload

[0243] Model upload is the process of transferring the model from the UE to the network.

[0244] (M8) Model derivation

[0245] Model inference is the process of using a trained AI / ML model to generate a series of outputs based on a series of inputs.

[0246] (M9) Model Verification

[0247] Model validation is a sub-process of training that evaluates the quality of an AI / ML model using a dataset different from the one used for model training.

[0248] (M10) Model Test

[0249] Model testing is a sub-process of training that uses a different dataset than that used for model training or validation to evaluate the performance of the final AI / ML model. Unlike AI / ML model validation, model testing does not assume subsequent model tuning.

[0250] (M11) Model Activation

[0251] Model activation is the process of activating an AI / ML model for specific functions.

[0252] (M12) Model Deactivation

[0253] Model deactivation is the process of deactivating an AI / ML model for a specific function.

[0254] (M13) Model Switching

[0255] Model switching is the process of deactivating a currently active AI / ML model and activating another AI / ML model for a specific function.

[0256] (M14) Model rollback

[0257] Model fallback is a process of deactivating an AI / ML model and switching to normal processing that does not use the AI / ML model.

[0258] (M15) Model Monitoring

[0259] Model monitoring is the process of monitoring the inference performance of AI / ML models.

[0260] (M16) Model Update

[0261] Model updating is the process of updating the model parameters and / or model structure of a model.

[0262] (M17) Model Registration

[0263] Model registration is a process of registering model parameters and / or model structure of a model.

[0264] (M18) Model Deployment

[0265] Model deployment is a general term that refers to the deployment of an AI / ML model from one entity to another in an optionally selected method.

[0266] (M19) Model Configuration

[0267] Model configuration is the process of configuring model parameters and / or model structure of a model.

[0268] (M20) Model Selection

[0269] Model selection is the process of selecting and activating an AI / ML model from among multiple currently selectable AI / ML models.

[0270] In the following description, management of AI / ML models implemented based on functionality (e.g., management of AI / ML models implemented for each use case and / or function) will in some cases be labeled as functionality-based LCM.

[0271] <4-2. Implementation of LCM>

[0272] Next, the implementation of LCM will be described.

[0273] The communication device of this embodiment (e.g., the management device 10, the base station 20, the relay station 30, or the terminal device 40) is configured to be able to perform a plurality of functional processes. For example, the communication device according to this embodiment is configured to be able to perform processes related to the transmission or reception of auxiliary information ( Figure 1 ), processing related to identification of beam ID ( Figure 2 The functional B shown in FIG is processed), as well as the positioning-related processing. The functional processing is implemented using an AI / ML model.

[0274] An AI / ML model can be associated with a functionality. In this case, the communication device can uniquely determine the AI / ML model when the functionality to be processed has been defined.

[0275] Multiple AI / ML models can be associated with a functionality. In this case, when the functionality to be processed has been defined, the communication device can determine the AI / ML model to be used from the multiple AI / ML models associated with the functionality.

[0276] When a communication device has multiple functionalities, the communication device can implement management (LCM) of AI / ML models used in the processing of the functionalities based on the functionalities. For example, the communication device can implement LCM for each use case or for each function. In this case, the communication device can implement the LCM of at least one of the multiple functionalities independently of the LCMs of other functionalities (implementation example 1). In addition, the communication device can implement the LCMs of all functionalities in association with each other (implementation example 2). In addition, the communication device can implement the LCMs of some of the multiple functionalities in association with each other (implementation example 3).

[0277] In the following description of implementation examples, it is assumed that the communication device has a total of three functionalities. These three functionalities are assumed to be functionalities A, B, and C. A communication device may, of course, have fewer than three functionalities, or more than three functionalities. Each of implementation examples 1 to 3 will be described in detail below.

[0278] <4-2-1. Implementation Example 1>

[0279] The communication device can implement the LCM of at least one of the multiple functionalities independently of the LCMs of other functionalities. For example, the communication device can control the LCM of functionality A independently of the LCMs of functionality B and functionality C. Of course, the communication device can independently control the LCMs of all functionalities.

[0280] For example, the communication device may implement data collection so that data collection is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement data collection so that data collection is performed in functionality B and functionality C, but not in functionality A.

[0281] For example, the communication device may implement model training so that model training is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model training so that model training is performed in functionality B and functionality C, but not in functionality A.

[0282] For example, the communication device may implement model recognition so that model recognition is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model recognition so that model recognition is performed in functionality B and functionality C, but not in functionality A.

[0283] For example, the communication device may implement model delivery so that model delivery is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model delivery so that model delivery is implemented in functionality B and functionality C, but not in functionality A.

[0284] For example, the communication device may implement model transmission so that the model transmission is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model transmission so that the model transmission is implemented in functionality B and functionality C, but not in functionality A.

[0285] For example, the communication device may implement model downloading, thereby implementing model downloading in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model downloading, thereby implementing model downloading in functionality B and functionality C, but not in functionality A.

[0286] For example, the communication device may implement model upload, thereby implementing model upload in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model upload, thereby implementing model upload in functionality B and functionality C, but not in functionality A.

[0287] For example, the communication device may implement model deduction so that the model deduction is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model deduction so that the model deduction is performed in functionality B and functionality C, but not in functionality A.

[0288] For example, the communication device may implement Model Verification so that Model Verification is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement Model Verification so that Model Verification is performed in functionality B and functionality C, but not in functionality A.

[0289] For example, the communication device may implement model testing such that the model test is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model testing such that the model test is performed in functionality B and functionality C, but not in functionality A.

[0290] For example, the communication device may implement model activation so that model activation is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model activation so that model activation is performed in functionality B and functionality C, but not in functionality A.

[0291] For example, the communication device may implement model deactivation such that model deactivation is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model deactivation such that model deactivation is implemented in functionality B and functionality C, but not in functionality A.

[0292] For example, the communication device may implement model switching so that model switching is performed in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model switching so that model switching is performed in functionality B and functionality C, but not in functionality A.

[0293] For example, the communication device may implement model fallback such that the model fallback is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model fallback such that the model fallback is implemented in functionality B and functionality C, but not in functionality A.

[0294] For example, the communication device may implement model monitoring such that model monitoring is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model monitoring such that model monitoring is implemented in functionality B and functionality C, but not in functionality A.

[0295] For example, the communication device may implement a model update so that the model update is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement a model update so that the model update is implemented in functionality B and functionality C, but not in functionality A.

[0296] For example, the communication device may implement model registration so that model registration is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model registration so that model registration is implemented in functionality B and functionality C, but not in functionality A.

[0297] For example, the communication device may implement model deployment so that the model deployment is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model deployment so that the model deployment is implemented in functionality B and functionality C, but not in functionality A.

[0298] For example, the communication device may implement a model configuration such that the model configuration is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement a model configuration such that the model configuration is implemented in functionality B and functionality C, but not in functionality A.

[0299] For example, the communication device may implement model selection so that model selection is implemented in functionality A, but not in functionality B and functionality C. Conversely, the communication device may implement model selection so that model selection is implemented in functionality B and functionality C, but not in functionality A.

[0300] According to implementation example 1, the communication device independently controls the LCMs of some or all functionalities, thereby making it possible to switch the control according to the characteristics of the functionality.

[0301] <4-2-2. Implementation Example 2>

[0302] The communication device can implement LCMs of all functionalities in association with each other. For example, the communication device can control the LCM of functionality A in association with the LCMs of functionality B and functionality C.

[0303] For example, when implementing data collection in functionality A, the communication device similarly implements data collection in functionality B and functionality C.

[0304] For example, when implementing model training in functionality A, the communication device similarly implements model training in functionality B and functionality C.

[0305] For example, when implementing model recognition in functionality A, the communication device similarly implements model recognition in functionality B and functionality C.

[0306] For example, when implementing model delivery in functionality A, the communication device similarly implements model delivery in functionality B and functionality C.

[0307] For example, when implementing model transmission in functionality A, the communication device similarly implements model transmission in functionality B and functionality C.

[0308] For example, when implementing model downloading in functionality A, the communication device similarly implements model downloading in functionality B and functionality C.

[0309] For example, when implementing model upload in functionality A, the communication device similarly implements model upload in functionality B and functionality C.

[0310] For example, when implementing model derivation in functionality A, the communication device similarly implements model derivation in functionality B and functionality C.

[0311] For example, when implementing model verification in functionality A, the communication device similarly implements model verification in functionality B and functionality C.

[0312] For example, when implementing the model test in functionality A, the communication device similarly implements the model tests in functionality B and functionality C.

[0313] For example, when implementing model activation in functionality A, the communication device similarly implements model activation in functionality B and functionality C.

[0314] For example, when implementing model disabling in functionality A, the communication device similarly implements model disabling in functionality B and functionality C.

[0315] For example, when implementing model switching in functionality A, the communication device similarly implements model switching in functionality B and functionality C.

[0316] For example, when implementing model fallback in functionality A, the communication device similarly implements model fallback in functionality B and functionality C.

[0317] For example, when implementing model monitoring in functionality A, the communication device similarly implements model monitoring in functionality B and functionality C.

[0318] For example, when implementing a model update in functionality A, the communication device similarly implements model updates in functionality B and functionality C.

[0319] For example, when implementing model registration in functionality A, the communication device similarly implements model registration in functionality B and functionality C.

[0320] For example, when implementing the model deployment in functionality A, the communication device similarly implements the model deployment in functionality B and functionality C.

[0321] For example, when implementing the model configuration in functionality A, the communication device similarly implements the model configurations in functionality B and functionality C.

[0322] For example, when implementing model selection in functionality A, the communication device similarly implements model selection in functionality B and functionality C.

[0323] According to implementation example 2, by uniformly controlling LCMs of all functionalities by the communication device, it is possible to reduce the amount of dynamic control information required for controlling the LCMs compared to the case of independent control.

[0324] <4-2-3. Implementation Example 3>

[0325] The communication device can implement LCMs for some of the multiple functionalities in association with each other. For example, the communication device can control the LCM for functionality A in association with the LCM for functionality B. In this case, the communication device can control the LCM for functionality C independently of the LCM for functionality A and the LCM for functionality B.

[0326] For example, when performing data collection in functionality A, the communication device similarly performs data collection in functionality B. On the other hand, the communication device does not need to perform data collection for functionality C.

[0327] For example, when performing model training in functionality A, the communication device similarly performs model training in functionality B. On the other hand, the communication device does not need to perform model training for functionality C.

[0328] For example, when performing model recognition in functionality A, the communication device similarly performs model recognition in functionality B. On the other hand, the communication device does not need to perform model recognition for functionality C.

[0329] For example, when implementing model delivery in functionality A, the communication device similarly implements model delivery in functionality B. On the other hand, the communication device does not need to implement model delivery for functionality C.

[0330] For example, when implementing model transmission in functionality A, the communication device similarly implements model transmission in functionality B. On the other hand, the communication device does not need to implement model transmission for functionality C.

[0331] For example, when implementing model download in functionality A, the communication device similarly implements model download in functionality B. On the other hand, the communication device does not need to implement model download for functionality C.

[0332] For example, when implementing model upload in functionality A, the communication device similarly implements model upload in functionality B. On the other hand, the communication device does not need to implement model upload for functionality C.

[0333] For example, when performing model derivation in functionality A, the communication device similarly performs model derivation in functionality B. On the other hand, the communication device does not need to perform model derivation for functionality C.

[0334] For example, when performing model verification in functionality A, the communication device similarly performs model verification in functionality B. On the other hand, the communication device does not need to perform model verification for functionality C.

[0335] For example, when performing a model test in functionality A, the communication device similarly performs a model test in functionality B. On the other hand, the communication device does not need to perform a model test for functionality C.

[0336] For example, when implementing model activation in functionality A, the communication device similarly implements model activation in functionality B. On the other hand, the communication device does not need to implement model activation for functionality C.

[0337] For example, when implementing model disabling in functionality A, the communication device similarly implements model disabling in functionality B. On the other hand, the communication device does not need to implement model disabling for functionality C.

[0338] For example, when implementing model switching in functionality A, the communication device similarly implements the model in functionality B. On the other hand, the communication device does not need to implement model switching for functionality C.

[0339] For example, when implementing model fallback in functionality A, the communication device similarly implements model fallback in functionality B. On the other hand, the communication device does not need to implement model fallback for functionality C.

[0340] For example, when implementing model monitoring in functionality A, the communication device similarly implements model monitoring in functionality B. On the other hand, the communication device does not need to implement model monitoring for functionality C.

[0341] For example, when implementing a model update in functionality A, the communication device similarly implements a model update in functionality B. On the other hand, the communication device does not need to implement a model update for functionality C.

[0342] For example, when implementing model registration in functionality A, the communication device similarly implements model registration in functionality B. On the other hand, the communication device does not need to implement model registration for functionality C.

[0343] For example, when implementing the model deployment in functionality A, the communication device similarly implements the model deployment in functionality B. On the other hand, the communication device does not need to implement the model deployment for functionality C.

[0344] For example, when implementing the model configuration in functionality A, the communication device similarly implements the model configuration in functionality B. On the other hand, the communication device does not need to implement the model configuration for functionality C.

[0345] For example, when implementing model selection in functionality A, the communication device similarly implements model selection in functionality B. On the other hand, the communication device does not need to implement model selection for functionality C.

[0346] According to Implementation Example 3, by controlling some functional LCMs in association with each other by the communication device, it is possible to reduce the amount of dynamic control information required for controlling the LCMs compared to the case of controlling all functional LCMs.

[0347] <4-2-4. Other Implementation Examples>

[0348] The multiple management functions included in the LCM can be divided into management functions that can be associated and management functions that are difficult to associate and need to be independently controlled. Therefore, the communication device can switch the LCM implementation method for each management function included in the LCM. The management function can be one of (M1) data collection to (M20) model selection.

[0349] For example, assume that each LCM of a plurality of functionalities included in a communication device includes a plurality of management functions, including a first management function (e.g., model activation). In this case, the communication device may implement the first management function included in the LCM of at least one of the plurality of functionalities in association with the first management function included in the LCM of another functionality. In this case, the communication device may implement the first management function in association with all functionalities.

[0350] Furthermore, assuming that each LCM of a plurality of functionalities included in a communication device includes a plurality of management functions, including a second management function (e.g., model transfer). In this case, the communication device can implement the second management function included in the LCM of at least one of the plurality of functionalities independently of the second management function included in the LCM of another or more functionalities. In this case, the communication device can independently implement the second management function for each functionality.

[0351] According to this implementation example, it is possible to implement LCM more efficiently. For example, it can be assumed that when processing using AI / ML models is implemented in multiple functionalities, the communication device activates the AI / ML models of the multiple functionalities at the same timing. In this case, the communication device controls model activation in association with all functionalities, making it possible to activate the AI / ML models of all functionalities through a single activation control. On the other hand, for example, it is assumed that model transmission as a type of LCM is implemented for each functionality when necessary. In this case, the communication device independently controls the transmission of the model for each functionality, thereby achieving flexible model transmission.

[0352] <4-3. Entity Operation>

[0353] Next, the operation of each entity related to the implementation of the functionality-based LCM will be described.

[0354] <4-3-1. Base Station Operation>

[0355] First, the operation of the base station 20 will be described.

[0356] The base station 20 may make decisions regarding the association of LCMs between functionalities.

[0357] For example, the base station 20 can decide which functionality to independently control when implementing functionality-based LCM. In addition, the base station 20 can decide which functionality to associate with which functionality in control when implementing functionality-based LCM.

[0358] The plurality of functionalities included in the base station 20 may be functionalities related to communication with the terminal device 40. In addition, the base station 20 may transmit a decision related to LCM association to the terminal device 40. For example, when implementing functionality-based LCM, the base station 20 may notify the terminal device 40 of information related to functionality-based LCMs to be controlled independently, and information related to functionality-based LCMs to be controlled in association with each other.

[0359] The plurality of functionalities included in the base station 20 may be functionalities related to communication with the terminal device 40. When implementing control related to association based on LCMs of the functionalities, the base station 20 may request the terminal device 40 to transmit information required for control related to association based on LCMs of the functionalities on the base station 20 side. It is assumed that the information required for control related to the association includes, for example, implementation results and measurement results of the LCMs on the terminal device 40 side.

[0360] The plurality of functionalities included in the base station 20 may be functionalities related to communication with the terminal device 40. When implementing control related to association based on LCMs of the functionalities, the base station 20 may obtain information required for control related to association based on LCMs of the functionalities on the base station 20 side from the terminal device 40. For example, it is assumed that the information required for control related to the association includes implementation results and measurement results of LCMs on the terminal device 40 side. The base station 20 may make a decision related to association based on LCMs of the functionalities based on the information from another communication device.

[0361] <4-3-2. Operation of Terminal Device>

[0362] Next, the operation of the terminal device 40 will be described.

[0363] The terminal device 40 may make decisions regarding the association of LCMs between functionalities.

[0364] For example, when implementing LCM based on functionality, the terminal device 40 can decide which functionality to control independently based on pre-acquired information. In addition, when implementing LCM based on functionality, the terminal device 40 can decide which functionality to control in association with each other based on pre-acquired information.

[0365] The plurality of functionalities included in the terminal device 40 may be functionalities related to communication with the base station 20. When implementing the functionality-based LCM, the terminal device 40 may obtain information related to the functionality-based LCM to be controlled independently, and information related to the functionality-based LCM to be controlled in association with each other from the base station 20. The terminal device 40 may then make decisions related to management association based on the information from the base station 20.

[0366] The plurality of functionalities included in the terminal device 40 may be functionalities related to communication with the base station 20. When implementing control related to association based on LCMs of the functionalities, the terminal device 40 may receive a request from the base station 20 for transmission of information required for control related to association based on LCMs of the functionalities on the base station 20 side. For example, it is assumed that the information required for control related to the association includes implementation results and measurement results of the LCMs on the terminal device 40 side.

[0367] The plurality of functionalities included in the terminal device 40 may be functionalities related to communication with the base station 20. When implementing control related to association based on LCMs of the functionalities, the terminal device 40 may notify the base station 20 of information required for control related to association based on LCMs of the functionalities on the base station 20 side, such as implementation results and measurement results of LCMs on the terminal device 40 side. It is assumed that the information required for control related to the association includes, for example, implementation results and measurement results of LCMs on the terminal device 40 side.

[0368] <4-3-3. Others>

[0369] Next, the operation of the core network CN related to the implementation of the functionality-based LCM will be described.

[0370] As described above, the core network CN may have LCM-related network functions. LCM-related network functions are network functions that provide LCM-related control functions. For example, LCM-related network functions may be included in Figure 9 The LCM related network functions may be included in a server (e.g., a server connected to the UPF 521) Figure 9 LCM related network functions may be included in a server (e.g., MEC server 552) connected to the base station 20 ((R)AN 530). Figure 9 In addition, the LCM-related network function 554 can be included in the core network CN as one of the control plane function groups 540.

[0371] Communication devices (e.g., base station 20, relay station 30, and terminal device 40) directly or indirectly connected to the core network CN can obtain information required for implementation of functionality-based LCM from the core network CN (e.g., management device 10). Subsequently, the communication devices can implement functionality-based LCM based on the information obtained from the core network CN.

[0372] <4-4. Discrimination Function>

[0373] The multiple functionalities included in a communication device may be functionalities related to communication between the communication devices. When implementing functionality-based LCM, the multiple communication devices (e.g., terminal device 40 and base station 20) implementing communication need to have a common understanding of which functional LCM to implement. The functionality determination method will be described later.

[0374] <4-4-1. Identification Method 1>

[0375] One of the two communicating devices may notify the other communication device of identification information (functionality ID) for identifying functionality. The other communication device may determine the functionality of the LCM implementation target based on the identification information. For example, base station 20 may notify terminal device 40 of the functional ID. Terminal device 40 may then determine the functionality based on the functional ID.

[0376] <4-4-2, Identification Method 2>

[0377] One communication device may notify the other communication device of identification information (AI / ML model ID) for identifying an AI / ML model. Functionality is associated with one or more AI / ML models. The other communication device may determine functionality based on the notified AI / ML model ID.

[0378] For example, the base station 20 pre-provides information on the association between the AI / ML model ID and functionality to the terminal device 40. For example, the base station 20 notifies the terminal device 40 of the AI / ML model ID information as LCM-related control information. The terminal device 40 determines the functionality based on the received AI / ML model ID information and the pre-acquired information on the association between the AI / ML model ID and functionality.

[0379] <4-4-3, Judgment Method 3>

[0380] The communication device can identify functionality based on the functional configuration. For example, the base station 20 notifies the terminal device 40 of RRC signaling defined for each functionality. In this case, the base station 20 notifies the terminal device 40 of information related to the LCM using a different message, information field, or information element for each functionality. The terminal device 40 identifies the functionality based on the received message, information field, or information element.

[0381] <4-4-4, Discrimination Method 4>

[0382] The communication device can determine functionality based on the type of AI / ML model to be applied. Assumable AI / ML models include the following (A1) to (A4).

[0383] (A1) UE-side (AI / ML) model

[0384] The UE-side (AI / ML) model is an AI / ML model whose derivation is completely implemented in the UE.

[0385] (A2) Network-side (AI / ML) model

[0386] The network-side (AI / ML) model is an AI / ML model that is completely implemented and derived in the network.

[0387] (A3) One-Sided (AI / ML) Model

[0388] The one-side (AI / ML) model is either the UE-side (AI / ML) model or the network-side (AI / ML) model.

[0389] (A4) Two-Sided (AI / ML) Model

[0390] The two-sided (AI / ML) model is a paired AI / ML model that performs derivation jointly. The joint derivation includes AI / ML derivation and is performed jointly by the UE and the network. That is, the initial part of the derivation is initially performed by the UE, and then the rest is performed by the base station.

[0391] <4-4-5, Judgment Method 5>

[0392] To distinguish functionality, a functional radio network temporary identifier (functional RANTI) can be established. The base station 20 assigns functional RANTI information to control information. The terminal device 40 determines the functionality based on the functional RANTI assigned to the control information. This makes it possible for the terminal device 40 to determine which functionality the received control information relates to. The functional RANTI can be used, for example, in scrambling of cyclic redundancy checks (CRCs), information assigned to downlink control information (DCI), radio resource control signaling (RRC), and the like.

[0393] <4-4-5, Judgment Method 5>

[0394] The communication device can determine functionality based on input information to the AI / ML model and output information from the AI / ML model. In this case, the input information and / or output information may be, for example, one or more of the following information (B1) to (B15). Of course, the input information and / or output information is not limited to the following information.

[0395] (B1) Channel Quality Information (CQI)

[0396] (B2) Precoding Matrix Indicator (PMI)

[0397] (B3) CSI-RS Resource Indicator (CRI)

[0398] (B4) SS / PBCH Resource Block Indicator (SSBRI)

[0399] (B5) Layer Indicator (LI)

[0400] (B6) Rank Indicator (RI)

[0401] (B7) Layer 1 reference signal received power (L1-RSRP)

[0402] (B8) Interference level with other cells

[0403] (B9) Position estimation information of terminal device 40

[0404] (B10) Location information of base station 20

[0405] (B11) Channel Matrix

[0406] (B12) Eigenvector

[0407] (B13) Beam ID

[0408] (B14) Timing error information

[0409] (B15) Line of sight (LOS) / Lost line of sight (NLOS) information

[0410] The communication device can determine functionality based on input information and / or output information. For example, when an AI / ML model is applied to the transmission of PMI, the communication device determines that the functionality being processed is functionality A. Furthermore, when an AI / ML model is applied to the determination of beam IDs, the communication device determines that the functionality being processed is functionality B. In this way, the communication device can determine functionality based on input information to the AI / ML model and / or output information from the AI / ML model. The determination examples shown here are merely examples. The determination process is not limited to this.

[0411] <4-4-6, Discrimination Method 6>

[0412] A communication device can determine functionality based on the compatibility status of the communication device (eg, base station 20 ) and capability information of another communication device (eg, terminal device 40 ).

[0413] For example, a plurality of functionalities included in a communication device (e.g., base station 20) may be functionalities related to communication with another communication device (e.g., terminal device 40). The communication device may obtain capability information of the other communication device (e.g., UE capabilities of terminal device 40) from the other communication device. The communication device (e.g., base station 20) may determine, based on the obtained capability information, the functionality applicable to the other communication device (e.g., terminal device 40). The communication device may notify the other communication device of the functionality to which the AI / ML model is applied.

[0414] The information notified from a communication device (e.g., base station 20) to another communication device (e.g., terminal device 40) may include, for example, functional information (e.g., functional ID) to which the AI / ML model is applied. Furthermore, when LCM is implemented in association with another functionality, the information notified from a communication device (e.g., base station 20) to another communication device (e.g., terminal device 40) may include, for example, related information between the functionalities.

[0415] <4-5. Control LCM>

[0416] In the functional LCM, it is possible to introduce event-triggered control or periodic control.

[0417] <4-5-1. Example of event-triggered control>

[0418] The communication device can implement LCM at the timing of the occurrence of a predetermined event. In addition, the communication device can implement LCM at the timing of receiving a notification issued at the timing of the occurrence of a predetermined event from another communication device. The timing of the occurrence of the predetermined event that can be assumed includes the following (C1) to (C14). It should be noted that the timing described below is only for example. The timing of the occurrence of the predetermined event is not limited to the following timing.

[0419] (C1) Timing of AI / ML model training completion

[0420] (C2) Timing of AI / ML model training start

[0421] (C3) Timing of AI / ML model expiration (timer expiration, etc.)

[0422] (C4) Timing of when the validity of the AI / ML model is judged invalid

[0423] (C5) When the AI / ML model is determined to need updating

[0424] (C6) Timing of training data expiration (timer expiration, etc.)

[0425] (C7) Timing of AI / ML model downloads

[0426] (C8) Timing of AI / ML model uploads

[0427] (C9) Timing of AI / ML model transmission

[0428] (C10) Timing of AI / ML model derivation

[0429] (C11) Timing of AI / ML model activation

[0430] (C12) Timing of AI / ML model deactivation

[0431] (C13) Timing of AI / ML model switching

[0432] (C14) Timing of AI / ML model fallback being implemented to switch to normal processing without using AI / ML model

[0433] <4-5-2. Example of periodic control>

[0434] The communication device may implement LCM at a predetermined time (e.g., a set time slot, symbol, etc.). Furthermore, the communication device may implement LCM upon receiving a notification from another communication device that the notification was implemented at a predetermined time (e.g., a set time slot, symbol, etc.).

[0435] <4-5-3. Others>

[0436] The base station 20 may notify the terminal device 40 of control information related to the LCM for each functionality. The base station 20 may control the control information notification on an event-triggered basis or on a periodic basis.

[0437] The base station 20 may request the terminal device 40 to notify the control information related to the LCM for each functionality. Upon receiving the request, the terminal device 40 may notify the base station 20 of the control information related to the LCM. The base station 20 may control the request for control information notification on an event-triggered basis or on a periodic basis. Furthermore, the terminal device 40 may control the control information notification on an event-triggered basis or on a periodic basis.

[0438] The base station 20 may implement settings related to the implementation of measurements required by LCM on the terminal device 40 for each functionality. The base station 20 may control the settings related to the implementation of measurements on an event-triggered basis or on a periodic basis. In addition, the terminal device 40 may control the implementation of measurements on an event-triggered basis or on a periodic basis.

[0439] In the case where the aforementioned control (eg, event-triggered or periodic control) is set to any one of the plurality of functionalities, the control device may apply similar settings to another associated functionality.

[0440] When the aforementioned control (e.g., event-triggered or periodic control) is set to multiple functionalities among multiple functionalities, the communication device can apply similar settings to another related functionality. In this case, the communication device can set the most recently set information among the multiple settings as the effective setting.

[0441] For example, assume that functionality A and functionality B are associated with each other. First, when setting control 1 to functionality A, the communication device also sets control 1 to functionality B. Subsequently, when setting control 2 to functionality B, the communication device overwrites the control setting of functionality A with control 2.

[0442] When different controls are set for multiple functionalities simultaneously, a communication device (e.g., terminal device 40) may notify another communication device (e.g., base station 20) of the inappropriate setting by returning a NACK or the like. Alternatively, the communication device may allow any setting based on a predetermined priority. Alternatively, the implementation of the communication device (e.g., base station 20 and / or terminal device 40) may stipulate that different controls will not be set for multiple functionalities simultaneously.

[0443] <4-6. Operations during handover>

[0444] Regarding handover, when the terminal device 40 undergoes handover to another base station 20, the base station 20 (source base station 20) may notify another target base station 20 (target base station 20) of information related to functionality-based LCM. After receiving the information from the source base station 20, the target base station 20 may implement functionality-based LCM based on the received information.

[0445] For example, a communication device may limit or determine a handover destination based on capability information related to the AI / ML model of the base station 20 or terminal device 40 and / or information related to the functionality-based LCM. This is an exemplary scenario in which the terminal device 40 performs a handover. In this case, if the target base station 20 cannot use the trained AI / ML model, the terminal device 40 and the target base station 20 need to retrain the AI / ML model. In this case, new training processing is required in the terminal device 40 and the base station 20, which increases the processing load on the terminal device 40 and the base station 20. To address this situation, when the terminal device 40 performs a handover, the handover is performed at the target base station 20 where the trained AI / ML model can be reused. When performing this operation, the base station 20 or the terminal device 40 may determine whether the base station 20 can use the target candidate for the trained AI / ML model based on the functionality-based LCM. The terminal device 40 may then perform a handover with the base station 20 that has been determined to be capable of using the trained AI / ML model as the target.

[0446] <4-7. Sequence Example>

[0447] Based on the foregoing, a sequence example of the communication process of this embodiment will be described. In the following description, a communication process implemented between the base station 20 and the terminal device 40 will be described. It should be noted that the following assumes that the terminal device 40 has three functionalities A, B, and C.

[0448] <4-7-1. Representative sequence examples>

[0449] Representative sequence examples will be described first. Figure 10 This is a diagram showing a representative sequence example of the communication processing of this embodiment. Figure 10 The communication process according to the present embodiment is described.

[0450] The terminal device 40 receives the synchronization signal transmitted from the base station 20 and performs downlink synchronization. Subsequently, the terminal device 40 receives the system information transmitted from the base station 20 and receives information required for cellular connection (step S101). Here, the system information may include an explicit notification related to LCM.

[0451] The terminal device 40 performs a random access procedure to connect to the base station 20 (step S102). Through this procedure, the terminal device 40 performs uplink synchronization to complete the connection to the base station 20.

[0452] The terminal device 40 notifies the base station 20 of capability information about the terminal device 40 (step S103). The terminal device 40 may include capability information related to the implementation method of LCM in the capability information.

[0453] The base station 20 notifies the terminal device 40 of the quasi-static control information (step S104). This may be referred to as RRC signaling. The base station 20 notifies the terminal device 40 of the information related to the LCM (step S105). Here, it is assumed that the terminal device 40 receives information related to the LCM for each functionality. The base station 20 may include the information related to the LCM in the quasi-static control information.

[0454] The terminal device 40 implements association of functionality based on the information related to LCM (step S106). The following description will assume that LCM is implemented with functionality A and functionality B associated with each other, while LCM is implemented independently in functionality C.

[0455] The base station 20 notifies the terminal device 40 of the activation of the AI / ML model for functionality A (step S107). The terminal device 40 activates the AI / ML model for functionality A (Model A) (step S108). Similarly, the AI / ML model for functionality B (Model B) associated with functionality A is activated (step S109).

[0456] Next, the base station 20 notifies the terminal device 40 of the switching of the AI / ML model for functionality C (step S110). The terminal device 40 switches the AI / ML model for functionality C (model C) to another AI / ML model (step S111). It should be noted that LCM is implemented independently in functionality C. Accordingly, the terminal device 40 does not implement LCM related to the switching of the AI / ML model for functionality A and functionality B.

[0457] <4-7-2. Example of sequence during handover>

[0458] Next, a sequence example in the case where handover is performed will be described. Figure 11 and 12 This is an example of a sequence in which a handover is performed. Figure 11 and 12 The communication process according to the present embodiment is described.

[0459] The terminal device 40 receives the synchronization signal transmitted from the base station 201 and performs downlink synchronization. Subsequently, the terminal device 40 receives the system information transmitted from the base station 201 and receives the information required for the cellular connection ( Figure 11 Here, the system information may include an explicit notification related to the LCM.

[0460] Next, the terminal device 40 implements a random access procedure to achieve connection with the base station 201 (step S202). Through this procedure, the terminal device 40 implements uplink synchronization to complete the connection to the base station 201.

[0461] The terminal device 40 notifies the base station 201 of capability information about the terminal device 40 (step S203). The terminal device 40 may include capability information related to the implementation method of LCM in the capability information.

[0462] The base station 201 notifies the terminal device 40 of the quasi-static control information (step S204). This may be referred to as RRC signaling. The base station 201 notifies the terminal device 40 of the information related to the LCM (step S205). Here, it is assumed that the terminal device 40 receives information related to the LCM for each functionality. The base station 201 may include the information related to the LCM in the quasi-static control information.

[0463] The terminal device 40 implements association of functionality based on the information related to LCM (step S206). The following description will assume that LCM is implemented with functionality A and functionality B associated with each other, while LCM is implemented independently in functionality C.

[0464] The base station 201 notifies the terminal device 40 of the activation of the AI / ML model for functionality A (step S207). The terminal device 40 activates the AI / ML model for functionality A (Model A) (step S208). Similarly, the AI / ML model for functionality B (Model B) associated with functionality A is activated (step S209).

[0465] Next, the base station 201 notifies the terminal device 40 of the switching of the AI / ML model for functionality C (step S210). The terminal device 40 switches the AI / ML model for functionality C (model C) to another AI / ML model (step S211). It should be noted that LCM is implemented independently in functionality C. Accordingly, the terminal device 40 does not implement LCM related to the switching of the AI / ML model for functionality A and functionality B.

[0466] The base station 201 (source cell) and the terminal device 40 perform measurement procedures related to the connected cell (step S212).

[0467] Based on the results of the measurement procedure, base station 201 makes a handover determination (step S213). Base station 201 determines that a handover is necessary and implements the handover procedure. At this point, base station 201 notifies the target base station 20 (base station 202 in this example sequence) of a handover request (step S214).

[0468] Now, refer to Figure 12 After receiving the handover request, the base station 202 serving as the target cell may perform processing such as handover permission determination (step S215), and notify the source cell of the handover request confirmation (step S216).

[0469] At this time, base station 201 may notify base station 202 of information related to LCM (eg, functional LCM association information, etc.) (step S217). After receiving the information related to LCM, base station 202 may return an acknowledgement to base station 201 (step S218).

[0470] The base station 201 performs RRC reconfiguration on the terminal device 40 (step S219) and notifies the terminal device 40 of information related to the handover. The information related to the handover may include information related to the LCM. For example, the information related to the handover may include association information based on the functional LCM.

[0471] Then, the terminal device 40 detaches from the base station 201 (step S220). Then, the terminal device 40 implements a random access procedure (step S221) to connect to the base station 202. Through this procedure, the terminal device 40 implements uplink synchronization to complete the connection to the base station 202.

[0472] The terminal device 40 may notify the base station 202 of capability information about the terminal device 40 (step S221). The terminal device 40 may include capability information related to the implementation of LCM in the capability information. The capability information of the terminal device 40 may be shared between the base station 201 and the base station 202.

[0473] The base station 202 notifies the terminal device 40 of the semi-static control information (step S223). This may be referred to as RRC signaling. The base station 202 may include information related to the LCM in the semi-static control information in the notification.

[0474] The terminal device 40 can implement association of functionality based on information related to LCM. The following description will assume that LCM is implemented in association with each other in functionality A and functionality B, while LCM is implemented independently in functionality C, and there is no change from the setting before handover.

[0475] The base station 201 notifies the terminal device 40 of the deactivation of the AI / ML model for functionality B (step S224). The terminal device 40 deactivates the AI / ML model (Model A) for functionality B (step S225). Similarly, the AI / ML model (Model A) for functionality A associated with functionality B in the LCM process is deactivated (step S226).

[0476] Next, the base station 201 notifies the terminal device 40 of the fallback of the AI / ML model for functionality C (step S227). The terminal device 40 deactivates processing using the AI / ML model (model C) for functionality C and implements fallback to normal processing (step S228). It should be noted that LCM is implemented independently in functionality C. Accordingly, the terminal device 40 does not implement LCM related to the fallback of the AI / ML model for functionality A or functionality B.

[0477] <4-8. Management Processing Example>

[0478] The communication processing performed between the terminal device 40 and the base station 20 has been described above using a sequence diagram. Next, an example of processing related to LCM on each of the terminal device 40 side and the base station 20 side in the communication processing will be described with reference to a flowchart. It should be noted that the following assumes that the terminal device 40 has three functionalities A, B, and C.

[0479] <4-8-1. Processing Example on the Terminal Device Side>

[0480] First, a processing example on the terminal device 40 side will be described. Figure 1340 is a flowchart showing a management process performed by the terminal device 40. The management process is a process related to LCM. The management process is performed by, for example, the control unit 43 of the terminal device 40. Figure 13 The management process performed by the terminal device 40 is described.

[0481] First, the acquisition unit 431 of the terminal device 40 receives information related to the LCM from the base station 20 (step S301). Here, it is assumed that the terminal device 40 receives information related to the LCM for each functionality.

[0482] Subsequently, the decision unit 434 of the terminal device 40 makes a decision related to the association of the LCM based on the information related to the LCM. Subsequently, the decision unit 434 implements the association of the functionality (step S302). The following description will assume that the LCM is implemented in the case where functionality A and functionality B are associated with each other, while the LCM is implemented independently in functionality C.

[0483] Subsequently, the acquisition unit 431 of the terminal device 40 receives LCM control information related to functionality A from the base station 20 (step S303). For example, the acquisition unit 431 receives control information related to activation of the AI / ML model of functionality A from the base station 20. At this time, the determination unit 433 of the terminal device 40 can determine which of the multiple functionalities is the application target of the LCM indicated by the control information.

[0484] Subsequently, the management unit 432 of the terminal device 40 implements LCM related to functionality A based on the control information received from the base station 20 (step S304). For example, the management unit 432 activates the AI / ML model of functionality A.

[0485] Then, the determination unit 433 of the terminal device 40 selects one of the other functionalities (step S305). For example, the determination unit 433 selects functionality B or functionality C. Then, the determination unit 433 determines whether the selected functionality is associated with functionality A (step S306).

[0486] If the functionality is associated (step S306: Yes), the management unit 432 of the terminal device 40 also implements an LCM similar to the LCM implemented in step S304 for the selected functionality (step S307). For example, let's assume that functionality B was selected in step S305, and the LCM implemented in step S304 was the activation of an AI / ML model. In this case, the management unit 432 activates the AI / ML model for functionality B similarly to functionality A.

[0487] Conversely, if the functionality is not associated (step S306: No), the control unit 43 of the terminal device 40 proceeds to step S308 without implementing the LCM. For example, let's assume that the functionality is functionality C selected in step S305, and the LCM implemented in step S304 is the activation of the AI / ML model. In this processing example, since the LCM is independently implemented for functionality C, the control unit 43 proceeds to step S308 without activating the AI / ML model for functionality C.

[0488] Subsequently, the determination unit 433 of the terminal device 40 determines whether the determination in step S306 has been performed for all functionalities (step S308). If there is any functionality that has not yet been determined (step S308: No), the control unit 43 of the terminal device 40 returns the process to step S305. If the determination is completed for all functionalities (step S308: Yes), the control unit 43 completes the management process.

[0489] <4-8-2. Example of processing on the base station side>

[0490] Next, a processing example on the base station 20 side will be described. Figure 14 2 is a flowchart showing the management process performed by the base station 20. The management process is a process related to LCM. The management process is performed by, for example, the control unit 23 of the base station 20. Figure 14 The management processing performed by the base station 20 is described.

[0491] First, the decision unit 234 of the base station 20 makes a decision on the association of LCMs. The transmission unit 235 of the base station 20 transmits information related to LCMs to the terminal device 40 (step S401). Here, it is assumed that the base station 20 transmits information related to LCMs for each functionality.

[0492] Subsequently, the control unit 23 of the base station 20 sets the association of multiple functionalities included in the terminal device 40 (step S402). The following description will assume that in the terminal device 40, LCM is implemented with functionalities A and B associated with each other, while LCM is implemented independently for functionalities C.

[0493] Subsequently, the transmitting unit 235 of the base station 20 transmits LCM control information related to functionality A to the terminal device 40 (step S403). For example, the transmitting unit 235 transmits control information related to activation of the AI / ML model of functionality A to the terminal device 40. If the base station 20 has functionality corresponding to functionality A of the terminal device 40, the management unit 232 of the base station 20 can implement LCM for the functionality corresponding to functionality A.

[0494] Subsequently, the determination unit 233 of the base station 20 determines that the implementation of the LCM related to functionality A has been completed in the terminal device 40 (step S404). For example, when a response indicating successful reception of control information is received from the terminal device 40, the determination unit 233 determines that activation of the AI / ML model of functionality A in the terminal device 40 has been completed.

[0495] Then, the determination unit 233 of the base station 20 selects one of the other functionalities (step S405). For example, the determination unit 233 selects functionality B or functionality C. Then, the determination unit 233 determines whether the selected functionality is associated with functionality A (step S406).

[0496] When the functionality is associated (step S406: yes), the determination unit 233 of the base station 20 also determines that an LCM similar to the LCM determined to be completed in step S404 is implemented in the terminal device 40 for the selected functionality (step S407). For example, it can be assumed here that the functionality is B selected in step S405, and the LCM determined to be completed in step S404 is the activation of the AI / ML model. In this case, the determination unit 233 also determines that the activation of the AI / ML model for functionality B in the terminal device 40 is completed. It should be noted that in the case where the base station 20 has a functionality corresponding to functionality B of the terminal device 40, the management unit 232 of the base station 20 can implement the LCM for the functionality corresponding to functionality B.

[0497] On the other hand, if the functionality is not associated (step S406: No), the control unit 23 of the base station 20 proceeds to the process of step S408 without confirming that the LCM is complete. For example, assume that the functionality C selected in step S405 and the LCM determined to be completed in step S404 is the activation of the AI / ML model. In this processing example, since the LCM is independently implemented for functionality C, the control unit 23 proceeds to the process of step S408 without confirming that the activation of the AI / ML model for functionality C is complete.

[0498] Subsequently, the determination unit 233 of the base station 20 determines whether the determination in step S406 has been performed for all functionalities (step S408). If there is any functionality that has not yet been determined (step S408: No), the control unit 23 of the base station 20 returns the process to step S405. If the determination is completed for all functionalities (step S408: Yes), the control unit 23 completes the management process.

[0499] 5. Modification

[0500] The embodiments described above are by way of example, and various modifications and applications are possible.

[0501] In the embodiment described above, the technology of the present disclosure is described by taking the communication processing between the base station 20 and the terminal device 40 as an example. However, the scope of application of the present embodiment is not limited to this. For example, the technology of the present disclosure is also applicable to communication between multiple communication devices selected from the management device 10, the base station 20, the relay station 30, and the terminal device 40. In addition, the technology of the present disclosure is also applicable to communication between management devices 10, between base stations 20, between relay stations 30, or between terminal devices 40. In addition, the technology of the present disclosure is also applicable to processing implemented by the management device 10, the base station 20, the relay station 30, and the terminal device 40 independently using AI / ML models.

[0502] The functions of the respective blocks (acquisition unit 231 to reception unit 236) included in the control unit 23 of the base station 20 may be respectively similar to the functions of the respective blocks (acquisition unit 431 to reception unit 436) included in the control unit 43 of the terminal device 40. In addition, the function of each block (acquisition unit 331 to reception unit 336) included in the control unit 33 of the relay station 30 may be similar to the function of each block included in the control unit 23 of the base station 20, or may be similar to the function of each block included in the control unit 23 of the terminal device 40. In addition, the function of each block included in the control unit 43 of the terminal device 40 may be similar to the function of each block included in the control unit 23 of the base station 20. In addition, the function of the control unit 13 of the management device 10 may be similar to the function of the control unit 23 of the base station 20, may be similar to the function of the control unit 33 of the relay station 30, or may be similar to the function of the control unit 43 of the terminal device 40.

[0503] The control device for controlling the management device 10, the base station 20, the relay station 30, and the terminal device 40 of this embodiment can be implemented by a dedicated computer system or a general-purpose computer system.

[0504] For example, a communication program for performing the operations described above is stored in a computer-readable recording medium such as an optical disc, a semiconductor memory, a magnetic tape, or a flexible disk and distributed. For example, the program is installed on a computer and the above processing is performed to realize the configuration of the control device. In this case, the control device can be a device external to the management device 10, the base station 20, the relay station 30, or the terminal device 40 (e.g., a personal computer). In addition, the control device can be an internal device of the management device 10, the base station 20, the relay station 30, or the terminal device 40 (e.g., the control unit 13, the control unit 23, the control unit 33, or the control unit 43).

[0505] In addition, the communication program can be stored in a disk device included in a server on a network such as the Internet, so that it can be downloaded to the computer. In addition, the functions described above can be implemented using an operating system (OS) and application software in collaboration. In this case, the parts other than the OS can be stored in a medium for distribution, or the parts other than the OS can be stored in a server so that they can be downloaded to the computer.

[0506] In addition, among the various processes described in the preceding embodiments, all or part of the processes described as being automatically implemented can be implemented manually, or the processes described as being manually implemented can be automatically implemented by known methods. In addition, unless otherwise specified, the processing procedures, specific names, and information including various data and parameters shown in the preceding documents or accompanying drawings can be flexibly changed. For example, the various information shown in each accompanying drawing is not limited to the information shown.

[0507] Furthermore, each component of each device is provided as a functional and conceptual illustration and therefore does not necessarily need to be physically configured as shown. That is, the specific form of distribution / integration of each device is not limited to that shown in the drawings; all or part of it can be functionally or physically distributed or integrated into arbitrarily determined units based on various loads and usage conditions. This distributed or integrated configuration can be implemented dynamically.

[0508] Furthermore, the embodiments described above may be appropriately combined within the scope of implementation without inconsistency. Furthermore, the order of the steps shown in the flowcharts or sequence diagrams of the embodiments described above may be appropriately changed.

[0509] In addition, for example, the present embodiment can be implemented as any configuration constituting a device or system, such as a processor as a system large-scale integration (LSI), a module using multiple processors, a unit using multiple modules, and a set obtained by further adding other functions to the unit, etc. (that is, a configuration of a part of the device).

[0510] In this embodiment, a system refers to a collection of multiple components (devices, modules (components), etc.), and whether all components are housed in the same housing is not a major issue. Therefore, multiple devices housed in separate housings and connected via a network, and a single device housing multiple modules in a single housing, are both systems.

[0511] Furthermore, for example, the present embodiment may adopt a cloud computing configuration, in which a function is collaboratively shared and processed by multiple devices or apparatuses over a network.

[0512] 6. Conclusion

[0513] As described above, the communication device (e.g., base station 20 or terminal device 40) according to this embodiment implements LCM of the AI / ML model based on functionality. For example, the communication device implements LCM of the AI / ML model for each use case or for each function. For example, the communication device implements LCM of at least one of the multiple functionalities independently of LCM of other functionalities. Alternatively, the communication device implements LCM of all functionalities in association with each other. Alternatively, the communication device implements management (LCM) of some of the multiple functionalities in association with each other.

[0514] In this way, in this embodiment, management of AI / ML models is implemented based on functionality. This makes it possible for the communication device to implement efficient management of AI / ML models, thereby achieving high communication performance.

[0515] The embodiments of the present disclosure have been described above. However, the technical scope of the present disclosure is not limited to the embodiments described above, and various modifications can be made without departing from the scope of the present disclosure. In addition, it is possible to appropriately combine components of different embodiments and modifications.

[0516] The effects described in the respective embodiments in this specification are merely examples, and thus there may be other effects not limited to the exemplified effects.

[0517] It should be noted that the present technology can also have the following configurations.

[0518] (1) A communication device capable of performing a plurality of functional processes related to communication with another communication device, the communication device comprising:

[0519] A management unit is configured to implement management of an AI / ML model used in the processing based on the functionality.

[0520] (2) The communication device according to (1), wherein

[0521] Management of at least one of the plurality of functionalities is performed independently of management of the other functionalities.

[0522] (3) The communication device according to (1), wherein

[0523] The management of all multiple functionalities is performed in relation to one another.

[0524] (4) The communication device according to (1), wherein

[0525] Management of some of the multiple functionalities is performed in relation to each other.

[0526] (5) The communication device according to any one of (1) to (4), wherein

[0527] The management includes multiple management functions, including a first management function, and

[0528] A first management function included in the management of at least one of the plurality of functionalities is implemented in association with a first management function included in the management of the other functionalities.

[0529] (6) The communication device according to any one of (1) to (5), wherein

[0530] The management includes a plurality of management functions, including a second management function, and

[0531] A second management function included in the management of at least one of the plurality of functionalities is implemented independently of a second management function included in the management of another one or more functionalities.

[0532] (7) The communication device according to any one of (1) to (6), comprising

[0533] A decision making unit is configured to make decisions related to the management association between the plurality of functionalities.

[0534] (8) The communication device according to (7), wherein

[0535] The decision unit makes a decision related to the managed association based on information from the other communication device.

[0536] (9) The communication device according to (7) or (8), comprising

[0537] The sending unit is configured to send the decision made by the decision unit to another communication device.

[0538] (10) The communication device according to any one of (1) to (6), wherein

[0539] The plurality of functionalities are functionalities related to communication with another communication device, the other communication device being capable of making decisions related to the management of associations between the plurality of functionalities, and

[0540] The communication device includes a receiving unit configured to receive, from another communication device, a decision made by the other communication device.

[0541] (11) The communication device according to (7) or (8), wherein

[0542] The communication device is a base station or a terminal device, and

[0543] The communication device includes an acquisition unit configured to acquire information required for implementing management from a core network.

[0544] (12) The communication device according to any one of (1) to (11), wherein

[0545] The communication device comprises:

[0546] an acquiring unit configured to acquire management-related information; and

[0547] The determination unit is configured to determine the functionality to which the management indicated by the information related to management is applied.

[0548] (13) The communication device according to (12), wherein

[0549] The information related to management includes identification information of an AI / ML model notified from another communication device, and

[0550] Based on the identification information of the AI / ML model, the determination unit determines functionality to which the management indicated by the information related to management is applied.

[0551] (14) The communication device according to (12), wherein

[0552] The information related to management is notified from another communication device through a different message, a different information field, or a different information element for each functionality, and

[0553] The discrimination unit discriminates, based on the message, information field, or information element, functionality to which the management indicated by the information related to management is applied.

[0554] (15) The communication device according to any one of (1) to (11), wherein

[0555] The communication device comprises:

[0556] an acquiring unit configured to acquire capability information of another communication device; and

[0557] A determination unit is configured to determine functionality applicable to the other communication device based on the capability information.

[0558] (16) The communication device according to any one of (1) to (15), wherein

[0559] The management unit performs management at the timing when a predetermined event occurs or at a predetermined time.

[0560] (17) The communication device according to any one of (1) to (15), wherein

[0561] The management unit performs management at a timing of receiving a notification from the other communication device, the notification being performed at a timing of occurrence of a predetermined event or at a predetermined time.

[0562] (18) The communication device according to any one of (1) to (17), wherein

[0563] The communication device is a base station that communicates with a terminal device, and

[0564] The communication device includes a notification unit configured to notify another base station of information related to management when a terminal device performs handover to the another base station.

[0565] (19) The communication device according to any one of (1) to (17), wherein

[0566] The communication device is a base station that communicates with a terminal device, and

[0567] When the terminal device performs handover from another base station to the communication device, the management unit performs management based on management-related information acquired from the another base station.

[0568] (20) A communication method performed by a communication device capable of performing a plurality of functional processes related to communication with another communication device, the communication method comprising:

[0569] Management of the AI / ML models used in the processing is implemented based on functionality.

[0570] Reference Signs List

[0571] 1. Communication System

[0572] 10 - Management Device

[0573] 20——Base Station

[0574] 30——Relay Station

[0575] 40——Terminal device

[0576] 11 - Communication unit

[0577] 21, 31, 41 - wireless communication units

[0578] 12, 22, 32, 42 - storage units

[0579] 13, 23, 33, 43 - control units

[0580] 211, 311, 411—Sending Processing Unit

[0581] 212, 312, 412 - receiving processing unit

[0582] 213, 313, 413 - Antenna

[0583] 231, 331, 431 - Acquisition Unit

[0584] 232, 332, 432 - Management Unit

[0585] 233, 333, 433——Discrimination unit

[0586] 234, 334, 434 - Decision-making Unit

[0587] 235, 335, 435——Sending unit

[0588] 236, 336, 436——Receiving unit

[0589] 520——User plane function group

[0590] 540——Control Plane Function Group

[0591] 551——MTLF

[0592] 552, 553—MEC servers

[0593] 554——LCM-related network functions

[0594] RAN – Radio Access Network

[0595] CN - Core Network

Claims

1. A communication device capable of performing a plurality of functional processes related to communication with another communication device, the communication device comprising: A management unit is configured to implement management of an AI / ML model used in the processing based on the functionality.

2. The communication device according to claim 1, wherein Management of at least one of the plurality of functionalities is performed independently of management of the other functionalities.

3. The communication device according to claim 1, wherein The management of all multiple functionalities is performed in relation to one another. The communication device according to claim 1 , wherein Management of some of the multiple functionalities is performed in relation to each other. The communication device according to claim 1 , wherein The management includes multiple management functions, including a first management function, and A first management function included in the management of at least one of the plurality of functionalities is implemented in association with a first management function included in the management of the other functionalities. The communication device according to claim 1 , wherein The management includes a plurality of management functions, including a second management function, and A second management function included in the management of at least one of the plurality of functionalities is implemented independently of a second management function included in the management of another one or more functionalities.

7. The communication device according to claim 1, comprising A decision making unit is configured to make a decision related to the management association between the plurality of functionalities.

8. The communication device according to claim 7, wherein The decision unit makes a decision related to the managed association based on the information from the other communication device.

9. The communication device according to claim 7, comprising The sending unit is configured to send the decision made by the decision unit to the other communication device.

10. The communication device according to claim 1, wherein The plurality of functionalities are functionalities related to communication with the other communication device, the other communication device being capable of making decisions related to the management association between the plurality of functionalities, and The communication device includes a receiving unit configured to receive a decision made by the other communication device from the other communication device.

11. The communication device according to claim 7, wherein The communication device is a base station or a terminal device, and The communication device includes an acquisition unit configured to acquire information required for implementing management from a core network.

12. The communication device according to claim 1, wherein the communication device comprises: an acquisition unit configured to acquire management-related information; as well as The determination unit is configured to determine the functionality to which the management indicated by the information related to management is applied.

13. The communication device according to claim 12, wherein The information related to management includes identification information of the AI / ML model notified from the other communication device, and Based on the identification information of the AI / ML model, the determination unit determines functionality to which the management indicated by the information related to management is applied.

14. The communication device according to claim 12, wherein The information related to management is notified from the other communication device through a different message, a different information field, or a different information element for each functionality, and The discrimination unit discriminates, based on the message, information field, or information element, functionality to which the management indicated by the information related to management is applied.

15. The communication device according to claim 1, wherein the communication device comprises: an acquiring unit, configured to acquire capability information of the other communication device; as well as A determination unit is configured to determine functionality applicable to the other communication device based on the capability information.

16. The communication device according to claim 1, wherein The management unit performs management at the timing when a predetermined event occurs or at a predetermined time.

17. The communication device according to claim 1, wherein The management unit performs management at a timing of receiving a notification from the other communication device, the notification being performed at a timing of occurrence of a predetermined event or at a predetermined time.

18. The communication device according to claim 1, wherein The communication device is a base station that communicates with a terminal device, and The communication device includes a notification unit configured to notify another base station of information related to management when a terminal device performs handover to the another base station.

19. The communication device according to claim 1, wherein The communication device is a base station that communicates with a terminal device, and When the terminal device performs handover from another base station to the communication device, the management unit performs management based on management-related information acquired from the another base station.

20. A communication method performed by a communication device, the communication device being capable of performing a plurality of functional processes related to communication with another communication device, the communication method comprising: Management of the AI / ML models used in the processing is implemented based on the functionality.

Images