Communication device and communication method

Abstract

This communication device performs wireless communication with another communication device, and includes a processor that controls a wireless transceiver for performing the wireless communication. The processor controls the wireless transceiver so as to transmit, to the other communication device, information related to an AI / ML model to be applied to at least one process among: a first transmission process on the communication device related to a radio signal to be transmitted from the communication device to the other communication device; a first reception process on the other communication device related to a radio signal transmitted from the communication device to the other communication device; a second transmission process on the other communication device related to a radio signal to be transmitted from the other communication device to the communication device; or a second reception process on the communication device related to a radio signal transmitted from the other communication device to the communication device.

Description

Communication device and communication method

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

[0002] Wireless communication technology is being actively developed, and in recent years, there has been research into applying artificial intelligence / machine learning to wireless access networks to improve communication performance.

[0003] R1-2210997,“Discussions on AI / ML framework”,vivo,3GPP TSG-RAN WG1 Meeting #111,Toulouse,France,November 14th-18th,2022TR22.876 V19.0.0,“Study on AI / ML Model Transfer Phase 2”,3GPP Technical Specification Group Services and System Aspects, June 2023

[0004] However, simply applying artificial intelligence / machine learning technologies to wireless access networks does not necessarily result in high communication performance (e.g., improved frequency utilization efficiency, higher capacity, higher speed, lower latency, higher reliability, lower power consumption, or lower processing load).

[0005] Therefore, the present disclosure proposes a communication device and a communication method that can achieve high communication performance.

[0006] It should be noted that the above problem or object is merely one of multiple problems or objects that can be solved or achieved by multiple embodiments disclosed in this specification.

[0007] In order to solve the above problem, a communication device of one form according to the present disclosure is a communication device that performs wireless communication with another communication device, and has a processor that controls a wireless transceiver for performing the wireless communication, and the processor controls the wireless transceiver to transmit to the other communication device information regarding an AI / ML model that is applied to at least one of the following processes: a first transmission processing of the communication device regarding a wireless signal transmitted from the communication device to the other communication device, a first reception processing of the other communication device regarding a wireless signal transmitted from the communication device to the other communication device, a second transmission processing of the other communication device regarding a wireless signal transmitted from the other communication device to the communication device, or a second reception processing of the communication device regarding a wireless signal transmitted from the other communication device to the communication device.

[0008] 1 is a diagram showing an example of functionality in a use case related to the transmission and reception of CSI information. FIG. 1 is a diagram showing an example of functionality in a use case related to the transmission and reception of CSI information. FIG. 2 is a diagram showing an example of functionality in a use case related to the transmission and reception of CSI information. FIG. 3 is a diagram showing an example of functionality in a use case related to the identification of a beam ID. FIG. 4 is a diagram showing an example of functionality in a use case related to the identification of a beam ID. FIG. 5 is a diagram showing an example of functionality in a use case related to positioning. FIG. 6 is a diagram showing an example of functionality in a use case related to positioning. FIG. 7 is a diagram showing a configuration of a communication system according to the present embodiment. FIG. 8 is a diagram showing a configuration of a management device according to the present embodiment. FIG. 9 is a diagram showing a configuration of a base station according to the present embodiment. FIG. 10 is a diagram showing a configuration of a relay station according to the present embodiment. FIG. 11 is a diagram showing a configuration of a terminal device according to the present embodiment. FIG. 12 is a diagram showing an example of 5G architecture. FIG. 13 is a diagram showing a fallback process. FIG. 14 is a diagram showing an example of a basic sequence of communication processing when a transmitting device is responsible for LCM control. FIG. 1 is a diagram showing a specific sequence example of communication processing when a transmitting device is the LCM control subject; FIG. 2 is a diagram showing a basic sequence example of communication processing when a receiving device is the LCM control subject; FIG. 3 is a diagram showing a specific sequence example of communication processing when a receiving device is the LCM control subject; FIG. 4 is a diagram showing a sequence example of communication processing related to model transfer; FIG. 5 is a diagram showing an example of communication processing sequence related to model activation; FIG. 6 is a diagram showing an example of signal processing sequence using an AI / ML model; FIG. 7 is a diagram showing an example of communication processing sequence related to model monitoring; and FIG. 8 is a diagram showing an example of communication processing sequence related to model fallback.

[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the following embodiments, the same components are designated by the same reference numerals, and redundant description will be omitted.

[0010] In addition, in this specification and drawings, multiple components having substantially the same functional configuration may be distinguished by adding different alphabets or numbers to the same reference numeral. For example, multiple components having substantially the same functional configuration may be distinguished by adding different alphabets or numbers to the same reference numerals to the terminal device 40 as needed. １ , 40 ２ , and 40 ３ However, when there is no need to particularly distinguish between multiple components having substantially the same functional configuration, only the same reference numerals are used. For example, the terminal device 40 １ , 40 ２ , and 40 ３ When there is no need to particularly distinguish between them, they will be simply referred to as terminal devices 40.

[0011] One or more embodiments (including examples and modified examples) described below can be implemented independently. However, at least a portion of the embodiments described below may be implemented in appropriate combination with at least a portion of another embodiment. These embodiments may include novel features that are different from one another. Therefore, these embodiments may contribute to solving different purposes or problems and may produce different effects.

[0012] <<1. Overview>> Before describing this embodiment in detail, an overview of this embodiment will be described.

[0013] <1-1. Issues> 3GPP (registered trademark) is currently studying New Radio (NR), Beyond 5G, and 6G. NR is a radio access technology that can support various use cases, including high-speed, large-capacity (eMBB: Enhanced Mobile Broadband), multiple simultaneous connections (mMTC: Massive Machine Type Communications), and highly reliable and low-latency (URLLC: Ultra Reliable and Low Latency Communications). NR was standardized in Rel-15 as a technical framework that supports the usage scenarios, requirements, and deployment scenarios of these use cases, and technical enhancements are currently being made. Beyond 5G and 6G are the next generation mobile communication technologies after 5G. Beyond 5G and 6G are expected to further improve high-speed, large-capacity, multiple simultaneous connections, and highly reliable and low-latency.

[0014] To achieve this, technologies for improving communication performance using artificial intelligence (AI) / machine learning (ML) are being studied. For example, 3GPP is studying ways to improve frequency efficiency by applying AI / ML models to radio access networks. For example, Non-Patent Document 1 (3GPP R1-2210997) describes AI / ML model management using machine learning. Furthermore, Non-Patent Document 2 (3GPP TR22.876) describes a use case related to the application of machine learning to sidelink communication. Unlike conventional communication between a base station and a terminal device (uplink communication and / or downlink communication), sidelink communication is characterized by communication between multiple different terminal devices.

[0015] However, simply using artificial intelligence / machine learning does not necessarily result in high communication performance (e.g., improved frequency utilization efficiency, higher capacity, higher speed, lower latency, higher reliability, lower power consumption, or lower processing load).

[0016] For example, AI / ML models are expected to be used in various use cases, and the means of applying the AI / ML models may change depending on the use case. Therefore, it is necessary to change the management method of the AI / ML models for each use case depending on the situation. On the other hand, if the number of use cases to which AI / ML models are applied increases, issues such as an increase in processing load and an increase in the amount of memory required to manage the AI / ML models arise. Therefore, in communications using AI / ML models, it is necessary to efficiently manage the AI / ML models. In other words, to achieve high communication performance in communications using AI / ML, it is necessary for communication devices to properly manage the AI / ML models.

[0017] In this embodiment, the use case in which the AI / ML model is utilized is not limited to uplink communication, downlink communication, and sidelink communication. For example, the use case in which the AI / ML model is utilized may be communication using communication other than cellular communication, such as wireless LAN communication. Furthermore, the use case in which the AI / ML model is utilized may be a more specific use case using these communications (e.g., at least one of uplink communication, downlink communication, and sidelink communication).

[0018] <1-2. Solution> In this embodiment, the above-described problem is solved as follows.

[0019] Before describing the outline of the solution, functionality and management of the AI / ML model, which are important elements in this embodiment, will be described.

[0020] <1-2-1. Functionality> First, functionality will be explained.

[0021] Functionality is a concept that represents the communication requirements required for AI communication in a feature such as a use case to which an AI / ML model is applied, or a use case that utilizes an AI / ML model, or a function realized using an AI / ML model. Figures 1A to 3C each show an example of functionality.

[0022] 1A to 1C show functionality 1-A, 1-B, and 1-C in use cases (Features) related to the transmission and reception of CSI information. In the examples of FIGS. 1A to 1C, assistance information (e.g., information related to the AI / ML model) is transmitted from a transmitting device (terminal in the examples of FIGS. 1A to 1C) to a receiving device (network node in the examples of FIGS. 1A to 1C). In the examples of FIGS. 1A to 1C, the assistance information is information required for the receiving device to perform wireless communication processing, or information for assisting the receiving device in performing wireless communication processing. For example, the assistance information may be information (e.g., control information) required for the operation of the terminal device, such as downlink communication, uplink communication, sidelink communication, unlicensed communication, and handover. It is assumed that one or more communication requirements are defined for the transmission and reception of CSI information. For example, suppose three communication requirements are defined, which are defined as functionality 1-A, functionality 1-B, and functionality 1-C. In functionality 1-A, 1-B, and 1-C, both the transmitting device and the receiving device use the AI / ML model based on the communication requirements defined in each functionality, thereby enabling efficient information transmission from the transmitting device to the receiving device.

[0023] 2A to 2C show functionality 2-A, 2-B, and 2-C in a use case (Feature) related to beam ID identification. In the examples of FIGS. 2A to 2C, a receiving device (a terminal in the examples of FIGS. 2A to 2C) identifies a beam ID (e.g., the ID of a reference signal or synchronization signal) based on information / signals transmitted from a transmitting device (a network node in the examples of FIGS. 2A to 2C). It is assumed that one or more communication requirements are defined for identifying the beam ID. For example, assume that three communication requirements are defined. These are defined as functionality 2-A, functionality 2-B, and functionality 2-C. In functionality 2-A, 2-B, and 2-C, the receiving device identifies the beam ID using the information / signals received and the AI / ML model based on the communication requirements defined in each functionality.

[0024] 3A to 3C show functionality 3-A, 3-B, and 3-C in a positioning use case (Feature). In the examples of FIGS. 3A to 3C, a receiving device (a terminal in the examples of FIGS. 3A to 3C) generates positioning information based on information / signals transmitted from a transmitting device (a network node in the examples of FIGS. 3A to 3C). It is assumed that one or more communication requirements are defined when generating the positioning information. For example, assume that three communication requirements are defined. These are defined as functionality 3-A, functionality 3-B, and functionality 3-C. In functionality 3-A, 3-B, and 3-C, the receiving device generates positioning information using the received information / signals and an AI / ML model based on the communication requirements defined in each functionality.

[0025] Note that the term "functionality" used in the following description may be replaced with another term. For example, the term "functionality" used in the following description may be replaced with a term such as "use case," "feature," "function," "function index," "functional ID," "AI / ML index," "AI index," "ML index," or "model index." Of course, the term "functionality" is not limited to these terms and may be replaced with another term that represents, for example, a use case that utilizes an AI / ML model or a function that is realized using an AI / ML model.

[0026] <1-2-2. Management of AI / ML Model> Next, management of AI / ML model will be explained.

[0027] In 3GPP, management of the AI / ML model is being studied (for example, RP-221347). In this embodiment, management of the AI / ML model is sometimes referred to as LCM (Life-cycle-management).

[0028] The management of an AI / ML model (e.g., LCM) may be composed of one or more elements (processes / methods / procedures / functions) shown in the following (M1) to (M25). For example, the management of an AI / ML model (e.g., LCM) may be one of (M1) to (M25), or may be a combination of multiple elements including at least one element of (M1) to (M25).

[0029] (M1) Data collection (M2) Model training (M3) Functionality identification (M4) Model identification (M5) Model delivery (M6) Model transfer (M7) Model download (M8) Model upload (M9) Model inference (M10) Model validation (M11) Model testing (M12) Model activation (M13) Functionality activation (M14) Model deactivation (M15) Functionality deactivation (M16) Model switching (M17) Functionality switching (M18) Model fallback (M19) Model monitoring (M20) Model update (M21) Model registration (M22) Model deployment (M23) Model configuration (M24) Model selection (M25) UE capability

[0030] Note that (M1) to (M25) are merely examples. The management of the AI / ML model (e.g., LCM (or elements constituting LCM)) of this embodiment may include management (or elements) other than the above-mentioned (M1) to (M25). (M1) to (M25) will be described in detail later.

[0031] <1-2-3. Overview of Solution> Based on the above, an overview of the solution of this embodiment will be described.

[0032] A communication device of this embodiment (hereinafter referred to as a first communication device) is configured to be capable of wireless communication with another communication device (hereinafter referred to as a second communication device).

[0033] Here, the first communication device and the second communication device may be base stations or terminal devices. For example, the first communication device may be a base station and the second communication device may be a terminal device. Alternatively, the first communication device may be a terminal device and the second communication device may be a base station. Alternatively, the first communication device may be a terminal device and the second communication device may be another terminal device. Alternatively, the first communication device may be a base station and the second communication device may be another base station. Note that the first communication device and the second communication device are not limited to a base station and / or a terminal device. At least one of the first communication device and the second communication device may be a relay station, a device constituting a core network, a server device, or another control device.

[0034] At least one of the first communication device and the second communication device is configured to be able to execute one or more of the above-described or below-described functionalities. For example, at least one of the first communication device and the second communication device may be configured to be able to execute at least one of a process related to transmission or reception of assistance information, a process related to identification of a beam ID, and a process related to positioning. The processing of the functionality is realized using an AI / ML model. One or more AI / ML models are associated with one functionality.

[0035] The first communication device transmits, to the second communication device, information regarding an AI / ML model to be applied to at least one of the processes shown in (P1) to (P4) below (first transmission process, first reception process, second transmission process, and second reception process).

[0036] (P1) Transmission processing of the first communication device regarding a wireless signal transmitted from the first communication device to the second communication device (first transmission processing) (P2) Reception processing of the second communication device regarding a wireless signal transmitted from the first communication device to the second communication device (first reception processing) (P3) Transmission processing of the second communication device regarding a wireless signal transmitted from the second communication device to the first communication device (second transmission processing) (P4) Reception processing of the first communication device regarding a wireless signal transmitted from the second communication device to the first communication device (second reception processing)

[0037] Here, the above-mentioned first transmission processing and second transmission processing may refer to processing performed on a wireless signal to be transmitted. In other words, the above-mentioned first transmission processing and second transmission processing may be performed on a wireless signal before the wireless signal is transmitted. Additionally or alternatively, the above-mentioned first reception processing and second reception processing may refer to processing performed on a received wireless signal. In other words, the above-mentioned first reception processing and second reception processing may be performed on the wireless signal after the wireless signal is received.

[0038] The radio signal in the present disclosure may be a physical signal or physical channel of layer 1, or a combination thereof. For example, the physical signal of layer 1 may be at least one of the above-mentioned or below-mentioned SS (Synchronization signal), SSB (SS / PBCH Block), CSI-RS (Channel State Information-Reference Signal), SRS (Sounding Reference Signal), PT-RS (Phase-tracking reference signal), or DMRS (Demodulation reference signal). The SS may be a PSS (Primary Synchronization Signal), SSS (Secondary Synchronization Signal), SPSS (Sidelink Primary Synchronization Signal), SSSS (Sidelink Secondary Synchronization Signal), or a combination of at least two of them. The DMRS may be a PDCCH DMRS, a PDSCH DMRS, a PBCH DMRS, a PUCCH DMRS, a PUSCH DMRS, a PSCCH DMRS, or a PSSCH DMRS, or a combination of at least two of them.For example, the physical channel of Layer 1 may be the above-mentioned or below-mentioned PBCH (Physical broadcast channel), PDCCH (Physical downlink control channel), PDSCH (Physical downlink shared channel), PRACH (Physical random-access channel), PUCCH (Physical uplink control channel), PUSCH (Physical uplink shared channel), PSBCH (Physical sidelink broadcast channel), PSCCH (Physical sidelink control channel), PSSCH (Physical sidelink shared channel), or PSFCH (Physical sidelink feedback channel), or a combination of at least two of these.

[0039] Additionally or alternatively, the radio signal in the present disclosure may be a message of Layer 1, Layer 2, or Layer 3. For example, the radio signal in the present disclosure may include at least one of Downlink Control Information (DCI), Uplink Control Information (UCI), Sidelink Control Information (SCI), Medium Access Control-Control Element (MAC CE), or Radio Resource Control (RRC) message described above or below. The RRC message may be at least one of a MIB (Master Information Block), a SIB (System Information Block) (e.g., SIB1, SIB2, SIB3, SIB4, ...., SIBX (X is an integer)), an RRC Request message, an RRC Setup message, an RRC Setup Complete message, an RRC Reconfiguration message, an RRC Release message, a Security Mode Command message, a Security Mode Complete message, a Security Mode Failure message, a Counter Check message, a Counter Check Response message, a Paging message, an RRC Reestablishment Request message, and an RRC Reestablishment message.

[0040] Additionally or alternatively, at least one of the above-mentioned first transmission process, first reception process, second transmission process, or second reception process may include at least one corresponding process and / or procedure among the processes and / or procedures described in at least one of (K1) to (K6) below.

[0041] (K1) Sequence generation, scrambling, layer mapping, antenna port mapping, mapping to radio resources, precoding, modulation, cyclic shift or spreading for a radio signal or a bit string carried by the radio signal, or a combination of at least two of these.

[0042] (K2) CRC calculation, codebook segmentation, polar coding, LDPC (Low density parity check) coding, rate matching, or code block concatenation, or a combination of at least two of these, for a radio signal or a bit string carried by the radio signal.

[0043] (K3) Cell search, transmission timing adjustment, Radio Link Monitoring, Radio Link Recovery, power control for radio signals, Random Access Procedure, HARQ-ACK codebook determination, or UCI report (HARQ-ACK, SR (Scheduling Request)), or a combination of at least two of these.

[0044] (K4) Resource allocation to the time axis or frequency axis, Modulation order, TBS (Transport Block Size) determination, processing related to antenna ports quasi co-location between radio signals, CSI report, CSI feedback, CSI computation time, radio signal processing time, radio signal preparation procedure time, or uplink switching, or a combination of at least two of these.

[0045] (K5) Random Access Procedure in MAC, HARQ operation for Transport Block carried by radio signals, buffer status report, discontinuous reception (DRX), SCell (Secondary Cell) activation / deactivation, PDCP duplication activation / deactivation, Listen before talk (LBT), positioning, or Small data transmission (SDT), or a combination of at least two of these.

[0046] (K6) System information reception (acquisition) procedure, paging, RRC connection establishment procedure, Initial AS security activation procedure, RRC reconfiguration procedure, Counter check procedure, RRC connection re-establishment procedure, Radio link failure related operations, RRC connection resume, RRC connection resume, Idle mode mobility (cell selection, cell reselection), Connected mode mobility (Handover, Beam level mobility) or measurements (L1 measurement, L2 measurement, L3 measurement), or a combination of at least two of these.

[0047] As a representative example, at least one of the above-mentioned first transmission process, first reception process, second transmission process, or second reception process may be at least one of the corresponding processes and / or procedures among the processes and / or procedures described in at least one of (H1) to (H3) below.

[0048] (H1) CSI Feedback At least one of the above-described first transmission processing, first reception processing, second transmission processing, and second reception processing may be processing related to CSI feedback. Here, the CSI feedback may be, for example, at least one of a Type 1 Single-panel codebook, a Type 1 Multi-panel Codebook, a Type 2 Codebook, a Type 2 Port selection codebook, an Enhanced Type 2 Codebook, an Enhanced Type 2 Port selection codebook, and a Further enhanced Type 2 port selection codebook.

[0049] (H2) Beam management At least one of the above-mentioned first transmission process, first reception process, second transmission process, or second reception process may be a process related to beam management. Here, beam management may be an operation of receiving an SSB (Synchronization Signal Block) and transmitting a PRACH preamble using a PRACH resource corresponding to the SSB. Also, beam management may be an operation of receiving a CSI-RS and notifying a CSI report.

[0050] (H3) Positioning At least one of the above-described first transmission process, first reception process, second transmission process, and second reception process may be a process related to positioning. Here, positioning may be an operation of transmitting a PRS (Positioning Reference Signal) on the downlink and performing position estimation. Alternatively, positioning may be an operation of transmitting an SRS (Sounding Reference Signal) on the uplink and performing position estimation.

[0051] Here, the information about the AI / ML model may be information about the LCM. For example, assume that the first communication device is the controller of the LCM and the second communication device is the control target of the LCM. In this case, the first communication device may transmit at least one of the following pieces of information as the information about the AI / ML model:

[0052] (Model Transfer) The first communication device may transmit data of the AI / ML model used in at least one of the first reception process and the second transmission process to the second communication device as information about the AI / ML model. The second communication device executes the first reception process or the second transmission process using the data of the AI / ML model acquired from the first communication device.

[0053] (Model Activation) The first communication device may transmit, as information related to the AI / ML model, information instructing activation of an AI / ML model used in at least one of the first receiving process and the second transmitting process. When the second communication device receives the activation instruction information from the first communication device, the second communication device executes activation processing of the AI / ML model related to the instruction.

[0054] (Model Deactivation) The first communication device may transmit, as information related to the AI / ML model, information instructing deactivation of the AI / ML model used in at least one of the first receiving process and the second transmitting process. When the second communication device receives activation instruction information from the first communication device, the second communication device executes deactivation processing of the AI / ML model related to the instruction.

[0055] (Model Fallback) The first communication device may transmit, as information related to the AI / ML model, information for causing at least one of the first reception process and the second transmission process to fall back from processing using the AI / ML model to processing not using the AI / ML model. When the second communication device receives the fallback information from the first communication device, it falls back the processing related to the instruction from processing using the AI / ML model to processing not using the AI / ML model.

[0056] The above describes the processing of the first communication device when the LCM is model transfer, model activation, model deactivation, or model fallback. However, the LCMs controlled by the first communication device are not limited to these. The first communication device may also be the control subject for other LCMs.

[0057] In addition, the second communication device may be the control subject of the LCM, and the first communication device may be the control target of the LCM. In this case, the first communication device may transmit at least one of the following information as information about the AI / ML model:

[0058] (Terminal Capability) The first communication device may transmit its own capability information related to at least one of the first transmission process and the second reception process to the second communication device. For example, assume that an AI / ML model is linked to functionality related to at least one of the first transmission process and the second reception process. In this case, the first communication device may transmit, as capability information, information indicating which of multiple functionalities related to at least one of the first transmission process and the second reception process the first communication device supports to the second communication device. Alternatively, the first communication device may transmit, as capability information, information indicating which of multiple AI / ML models related to at least one of the first transmission process and the second reception process the first communication device supports to the second communication device. The second communication device may execute LCM based on the capability information of the first communication device.

[0059] (Model Training) The first communication device may transmit training information of an AI / ML model related to at least one of the first transmission process and the second reception process to the second communication device. For example, assume that the AI / ML model is linked to functionality related to at least one of the first transmission process and the second reception process. In this case, the first communication device may transmit, as training information, information indicating which of the multiple functionality has completed training of the AI / ML model to the second communication device. The second communication device may execute LCM based on the training information.

[0060] In the above description, the processing of the first communication device is described when the LCM is terminal capability or model training. However, the LCM that controls the first communication device is not limited to these. The first communication device may also be controlled by other LCMs.

[0061] Furthermore, although the above description is divided into two cases, namely, a case where the first communication device is the LCM control subject and the second communication device is the LCM control object, and a case where the second communication device is the LCM control subject and the first communication device is the LCM control object, the examples of information related to the AI / ML model described in each case may be implemented regardless of the two cases. That is, at least two of the examples of information related to the AI / ML model described in each case may be implemented simultaneously. In this case, even if the two cases are involved, at least two of the examples of information related to the AI / ML model described above may be implemented simultaneously.

[0062] As described above, in this embodiment, when implementing LCM, the first communication device transmits information about the AI / ML model to the second communication device. Alternatively, the first communication device transmits information about the AI / ML model to the second communication device, which is implementing LCM. The second communication device uses or manages the AI / ML model based on the information about the AI / ML model received from the first communication device. This allows the use or management of the AI / ML model to be implemented efficiently, thereby enabling the first communication device and / or the second communication device to achieve high communication performance. Note that the purpose of transmitting or receiving information about the AI / ML model is not limited to implementing LCM. In other words, transmitting or receiving information about the AI / ML model does not necessarily involve implementing LCM.

[0063] The outline of this embodiment has been described above, and the communication system 1 of this embodiment will now be described in detail.

[0064] <<2. Configuration of Communication System>> First, the configuration of the communication system 1 will be described.

[0065] FIG. 4 is a diagram showing 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. The communication system 1 provides a wireless network enabling mobile communication to users by having the wireless communication devices constituting the communication system 1 operate in cooperation with each other. The wireless network according to this embodiment is composed of a radio access network RAN ​​and a core network CN. In this embodiment, a wireless communication device refers to a device having a wireless communication function, and in the example of FIG. 4, this corresponds to the base station 20, the relay station 30, and the terminal device 40.

[0066] The communication system 1 may include a plurality of management devices 10, base stations 20, relay stations 30, and terminal devices 40. In the example of FIG. 4, the communication system 1 includes a management device 10 １ and 10 ２ and the base station 20 is provided with １ , 20 ２ , and 20３ The communication system 1 also includes a relay station 30. １ and 30 ２ The terminal device 40 is provided with the terminal device 40 １ , 40 ２ , and 40 ３ Depending on the communication system, the relay station 30 may not be present.

[0067] The terminal device 40 may be configured to connect to a network using radio access technology (RAT) such as LTE (Long Term Evolution), NR (New Radio), 6G, Wi-Fi, or Bluetooth (registered trademark). In this case, the terminal device 40 may be configured to be able to use different radio access technologies (wireless communication methods). For example, the terminal device 40 may be configured to be able to use NR and Wi-Fi. Furthermore, the terminal device 40 may be configured to be able to use different cellular communication technologies (e.g., LTE, NR, or 6G). In the following description, the terminal device 40 may be referred to as UE (User Equipment) 40.

[0068] LTE and NR are types of cellular communication technologies that enable mobile communication for terminal devices by arranging multiple areas covered by base stations in the form of cells. 6G is also expected to be a type of cellular communication technology, and may also enable mobile communication for terminal devices by arranging multiple areas covered by base stations in the form of cells.

[0069] In the following description, "LTE" includes LTE-A (LTE-Advanced), LTE-A Pro (LTE-Advanced Pro), and EUTRA (Evolved Universal Terrestrial Radio Access). NR includes NRAT (New Radio Access Technology) and FEUTRA (Further EUTRA). NR may also include 5G-Advanced. A single base station 20 may manage multiple cells. In the following description, 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.

[0070] NR is the next generation (5th generation) radio access technology after LTE (4th generation communications including LTE-Advanced and LTE-Advanced Pro). NR is a radio access technology that can support various use cases, including eMBB (Enhanced Mobile Broadband), mMTC (Massive Machine Type Communications), and URLLC (Ultra-Reliable and Low Latency Communications). NR was standardized in 3GPP (registered trademark) Rel-15 as a technical framework that corresponds to the usage scenarios, requirements, and deployment scenarios of these use cases. Furthermore, beyond 5G and 6G, it is required to simultaneously achieve multiple axes of high speed, large capacity, low latency, high reliability, and multiple simultaneous connections.

[0071] 6G is the next generation of mobile communications technology after NR and 5GS (5G system), which are fifth-generation mobile communications. Like 5G (NR), 6G can be a cellular communications technology. 6G includes radio access technology and network technologies between base stations, core networks, and data networks. It also includes technologies for the enhancement of eMBB, mMTC, and URLLC (extreme connectivity), which were the main use cases or requirements of NR. 6G also includes new technologies in new areas. For example, 6G may include technologies related to AI (cognitive network, AI native air interface), sensing (including radar sensing and network as a sensor), and terahertz communications.

[0072] The wireless network described above or below may support at least one of radio access technologies (RATs) such as LTE (Long Term Evolution), NR (New Radio), 6G, etc. The wireless access method used by the communication system 1 is not limited to LTE, NR, or 6G, and may be other wireless access methods such as W-CDMA (Wideband Code Division Multiple Access), cdma2000 (Code Division Multiple Access 2000), etc.

[0073] Furthermore, the base station 20 and the relay station 30 may be terrestrial stations or non-terrestrial stations. In other words, the communication system of Fig. 4 may be a non-terrestrial network. The non-terrestrial stations may be satellite stations or aircraft stations. If the non-terrestrial stations are satellite stations, the wireless network may be a bent-pipe (transparent) type mobile satellite communication system.

[0074] In this embodiment, terrestrial stations and terrestrial base stations refer to base stations and relay stations installed on the ground. Here, "terrestrial" refers to terrestrial in a broad sense, including not only land but also underground, on water, and underwater. In the following description, the term "terrestrial station" may be replaced with "gateway."

[0075] Note that an LTE base station may be referred to as an eNodeB (Evolved Node B) or eNB. An NR base station may be referred to as a gNodeB or gNB. A 6G base station may be referred to as a 6G NodeB (6GNB). An LTE RAN may be referred to as an EUTRAN. An NR RAN may be referred to as an NGRAN. A 6G RAN may be referred to as a 6GRAN. In LTE, NR, and 6G, a terminal device (also referred to as a mobile station or terminal) may be referred to as a UE (User Equipment). Note that a terminal device is a type of communication device and is also referred to as a mobile station or terminal.

[0076] The terminal device 40 may be able to connect to a network using a wireless access technology (wireless communication method) other than LTE, NR, 6G, Wi-Fi, or Bluetooth. For example, the terminal device 40 may be able to connect to a network using low power wide area (LPWA) communication. The terminal device 40 may also be able to connect to a network using proprietary wireless communication.

[0077] Here, LPWA communication refers to wireless communication that enables low-power, wide-range communication. For example, LPWA wireless refers to IoT (Internet of Things) wireless communication using a specific low-power radio (e.g., the 920 MHz band) or the ISM (Industry-Science-Medical) band. The LPWA communication used by the terminal device 40 may conform to the LPWA standard. The LPWA standard may be, for example, at least one of ELTRES, ZETA, SIGFOX, LoRaWAN, LTE-M, and NB-IoT. Of course, the LPWA standard is not limited to these and may be another LPWA standard.

[0078] Each wireless communication device shown in Fig. 4 may be considered as a device in a logical sense, i.e., a part of each wireless communication device may be realized by a virtual machine (VM) or a container such as Docker, and these may be physically implemented on the same hardware.

[0079] In this embodiment, the concept of a wireless communication device includes not only portable mobile devices (terminal devices) such as mobile terminals, but also devices installed in structures or mobile bodies. The structures or mobile bodies themselves may be considered wireless communication devices. Furthermore, the concept of a wireless communication device includes not only terminal devices 40 but also base stations 20 and relay stations 30. A wireless communication device is a type of processing device or information processing device. A wireless communication device can also be referred to as a transmitting device or a receiving device.

[0080] In the present embodiment, the resource may indicate at least one of, for example, Frequency, Time, Resource Element (including REG, CCE, and CORESET), Resource Block, Bandwidth Part, Component Carrier, Symbol, Sub-Symbol, Slot, Mini-Slot, Subslot, Subframe, Frame, PRACH occasion, Occasion, Code, Multi-access physical resource, Multi-access signature, and Subcarrier Spacing (Numerology). That is, the "resource" described above or below may be interpreted as at least one of the above examples.

[0081] The following describes in detail the configuration of each wireless communication device that makes up the communication system 1. Note that the configuration of each wireless communication device shown below is merely an example. The configuration of each wireless communication device may be different from the configuration shown below.

[0082] 2-1. Configuration of the Management Device The management device 10 is an information processing device (computer) that manages a wireless network. For example, the management device 10 is an information processing device that manages communication of the base station 20.

[0083] The management device 10 may be a device constituting a core network CN. For example, the management device 10 may be a device having a function as an MME (Mobility Management Entity). The management device 10 may also be a device having a function as an AMF (Access and Mobility Management Function) and / or an SMF (Session Management Function). The MME, AMF, and SMF are control plane network function nodes in the core network CN. The management device 10 may be a device having a function as a control plane network function (6G CPNF) in 6G. The 6G CPNF may be composed of one or more logical nodes.

[0084] Of course, the functions of the management device 10 are not limited to MME, AMF, SMF, and 6G CPNF. The management device 10 may be a device having functions as a Network Slice Selection Function (NSSF), an Authentication Server Function (AUSF), a Policy Control Function (PCF), and a Unified Data Management (UDM). Furthermore, the management device 10 may be a device having functions as a Home Subscriber Server (HSS).

[0085] The management device 10 may have a gateway function. For example, the management device 10 may have a function as an S-GW (Serving Gateway) or a P-GW (Packet Data Network Gateway). The management device 10 may also have a UPF (User Plane Function) function. In this case, the management device 10 may have multiple UPFs. The management device 10 may also be a device that has a function as a 6G User Plane Network Function (6G UPNF).

[0086] The core network CN is composed of multiple network functions, and each network function may be consolidated into one physical device or distributed across multiple physical devices. In other words, the management device 10 may be distributed across multiple devices. Furthermore, this distributed distribution may be controlled so that it is executed dynamically. The base station 20 and the management device 10 form a single network, providing wireless communication services to terminal devices 40. The management device 10 is connected to the Internet, and the terminal devices 40 can use various services provided via the Internet via the base station 20.

[0087] The management device 10 does not necessarily have to be a device that constitutes the core network CN. For example, assume that the core network CN is a core network of W-CDMA (Wideband Code Division Multiple Access) or cdma2000 (Code Division Multiple Access 2000). In this case, the management device 10 may be a device that functions as an RNC (Radio Network Controller).

[0088] FIG. 5 is a diagram showing the configuration of the management device 10 according to this embodiment. The management device 10 includes a communication unit 11, a storage unit 12, and a control unit 13. The configuration shown in FIG. 5 is a functional configuration, and the hardware configuration may be different from this. Furthermore, the functions of the management device 10 may be statically or dynamically distributed and implemented in multiple physically separated configurations. The management device 10 may also be configured by multiple server devices.

[0089] The communication unit 11 is a communication interface for communicating with a wireless communication device (e.g., base station 20). The communication unit 11 may be a network interface or a device connection interface. The communication unit 11 may be a LAN (Local Area Network) interface such as a NIC (Network Interface Card), or a Universal Serial Bus (USB) interface configured by a USB host controller or a USB port. The communication unit 11 may be a wired interface or a wireless interface. The communication unit 11 is controlled by the control unit 13.

[0090] The storage unit 12 is a readable / writable storage device such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 12 stores, for example, the connection state of the terminal device 40. The storage unit 12 stores the state of the RRC (Radio Resource Control) of the terminal device 40 and the state of the ECM (EPS Connection Management) or the 5G System CM (Connection Management). The storage unit 12 may function as a home memory that stores location information of the terminal device 40.

[0091] The control unit 13 is a controller that controls each component of the management device 10. The control unit 13 may be implemented by a processor such as a central processing unit (CPU) or a microprocessing unit (MPU). For example, the control unit 13 may be implemented by a processor executing various programs stored in a storage device internal to the management device 10 using a random access memory (RAM) or the like as a work area. The control unit 13 may be implemented by an integrated circuit such as an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 13 may also be implemented by a graphics processing unit (GPU). A CPU, MPU, ASIC, FPGA, and GPU can all be considered controllers. The control unit 13 may be configured by multiple physically separated objects. For example, the control unit 13 may be configured by multiple semiconductor chips.

[0092] <2-2. Configuration of Base Station> The base station 20 is a wireless communication device that performs wireless communication with other wireless communication devices (for example, a relay station 30, a terminal device 40, or another base station 20). The base station 20 may wirelessly communicate with the terminal device 40 via the relay station 30, or may wirelessly communicate directly with the terminal device 40.

[0093] The base station 20 is a device equivalent to a radio base station (e.g., base station, Node B, eNB, gNB, or 6GNB) or a radio access point. The base station 20 may be a radio relay station. The base station 20 may be an optical device called an RRH (Remote Radio Head). The base station 20 may be a receiving station such as an FPU (Field Pickup Unit). The base station 20 may be an IAB (Integrated Access and Backhaul) donor node or an IAB relay node that provides radio access lines and radio backhaul lines using time division multiplexing, frequency division multiplexing, or space division multiplexing.

[0094] The wireless access technology used by the base station 20 may be cellular communication technology. The wireless access technology used by the base station 20 may be wireless LAN technology. The wireless access technology used by the base station 20 may be low-power wide-area (LPWA) communication technology. However, the wireless access technology used by the base station 20 is not limited to these and may be other wireless access technologies. The wireless communication used by the base station 20 may be wireless communication using millimeter waves or wireless communication using terahertz waves. The wireless communication used by the base station 20 may be wireless communication using radio waves or wireless communication using infrared or visible light (optical wireless). Furthermore, the base station 20 may be capable of NOMA (Non-Orthogonal Multiple Access) communication with the terminal device 40. Here, NOMA communication refers to communication (transmission, reception, or both) using non-orthogonal resources. Note that the base station 20 may be capable of NOMA communication with other base stations 20.

[0095] The base station 20 may be able to communicate with the core network via a base station-core network interface (e.g., NG Interface, S1 Interface, etc.). This interface may be either wired or wireless. The base station may also be able to communicate with other base stations via an inter-base station interface (e.g., Xn Interface, X2 Interface, F1 Interface, etc.). This interface may be either wired or wireless.

[0096] The concept of a base station (also called a "base station device") includes not only a donor base station but also a relay base station (also called a "relay station"). A relay base station may be any one of an RF Repeater, a Smart Repeater, and an Intelligent Surface. The concept of a base station includes not only a structure with base station functions but also equipment installed in the structure.

[0097] Examples of structures include high-rise buildings, houses, steel towers, station facilities, airport facilities, port facilities, office buildings, school buildings, hospitals, factories, commercial facilities, stadiums, and other buildings. The concept of a structure includes not only buildings, but also non-building structures such as tunnels, bridges, dams, fences, and steel pillars, as well as equipment such as cranes, gates, and wind turbines. The concept of a structure includes not only land (ground in the narrow sense) or underground structures, but also water-based structures such as piers or megafloats, and underwater structures such as ocean observation facilities. A base station can also be referred to as an information processing device.

[0098] The base station 20 may be a donor station or a relay station (relay station). The base station 20 may also be a fixed station or a mobile station. A mobile station is a wireless communication device (e.g., a base station) configured to be mobile. In this case, the base station 20 may be a device installed in a mobile body, or may be the mobile body itself. For example, a relay station with mobility can be considered as the base station 20 as a mobile station. Furthermore, devices that are inherently mobile and have base station functionality (at least part of the base station functionality), such as vehicles, UAVs (Unmanned Aerial Vehicles) represented by drones, and smartphones, also fall under the category of the base station 20 as a mobile station.

[0099] Here, the moving body may be a mobile terminal such as a smartphone or a mobile phone. The moving body may be a moving body that moves on land (ground in the narrow sense) (e.g., a vehicle such as an automobile, bicycle, bus, truck, motorcycle, train, or linear motor car), or a moving body that moves underground (e.g., in a tunnel) (e.g., a subway). The moving body may also be a moving body that moves on water (e.g., a ship such as a passenger ship, cargo ship, or hovercraft), or a moving body that moves underwater (e.g., a submersible vessel such as a submarine, submarine, or unmanned underwater vehicle). The moving body may also be a moving body that moves within the atmosphere (e.g., an aircraft such as an airplane, airship, or drone).

[0100] The base station 20 may be a terrestrial base station (ground station) installed on the ground. The base station 20 may be a base station located on a structure on the ground, or a base station installed on a mobile object moving on the ground. The base station 20 may be an antenna installed on a structure such as a building and a signal processing device connected to that antenna. The base station 20 may be the structure or the mobile object itself. "Ground" refers not only to land (ground in the narrow sense) but also to ground, on water, and underwater in a broad sense. The base station 20 is not limited to a terrestrial base station. If the communication system 1 is a satellite communication system, the base station 20 may be an aircraft station. From the perspective of a satellite station, an aircraft station located on Earth is a ground station.

[0101] The base station 20 is not limited to a ground station. The base station 20 may be a non-terrestrial base station (non-ground station) that can float in the air or space. The base station 20 may be an aircraft station or a satellite station.

[0102] A satellite station is a satellite station capable of floating outside the atmosphere. The satellite station may be a device mounted on a space vehicle such as an artificial satellite, or may be the space vehicle itself. A space vehicle is a vehicle that moves outside the atmosphere. The space vehicle may be at least one of an artificial satellite, a spacecraft, a space station, and a probe. Of course, the space vehicle may also be an artificial celestial body other than these. Note that a satellite that serves as a satellite station may be any of a low Earth orbiting (LEO) satellite, a medium Earth orbiting (MEO) satellite, a geostationary Earth orbiting (GEO) satellite, or a highly elliptical orbiting (HEO) satellite. The satellite station may be a device mounted on a low Earth orbiting (LEO), a medium Earth orbiting (MEO), a geostationary Earth orbiting (GEO), or a highly elliptical orbiting (HEO) satellite.

[0103] An aircraft station is a wireless communication device capable of floating in the atmosphere of an aircraft or the like. The aircraft station may be a device mounted on the aircraft or the like, or may be the aircraft itself. The concept of aircraft includes not only heavier-than-air vehicles such as airplanes and gliders, but also lighter-than-air vehicles such as balloons and airships. The concept of aircraft includes not only heavier-than-air vehicles or lighter-than-air vehicles, but also rotorcraft such as helicopters and autogyros. The aircraft station, or an aircraft equipped with an aircraft station, may be an unmanned aerial vehicle such as a drone.

[0104] The concept of unmanned aerial vehicles also includes unmanned aerial systems (UAS) and tethered unmanned aerial systems (UAS). The concept of unmanned aerial vehicles also includes lighter than air UAS (LTA) and heavier than air UAS (HTA). The concept of unmanned aerial vehicles also includes high altitude unmanned aerial system platforms (HAPs).

[0105] The coverage size of the base station 20 may be relatively large, such as a macrocell, or relatively small, such as a picocell. The coverage size of the base station 20 may be extremely small, such as a femtocell. The base station 20 may have a beamforming function. The base station 20 may form a cell or service area for each beam. Additionally or alternatively, in addition to beamforming, which gives directionality to a beam, the base station 20 may have a function for pinpointing a desired wave to a specific point by further considering distance information from the antenna of the base station 20. This function may be called beam focusing or point forming.

[0106] Fig. 6 is a diagram showing the configuration of a base station 20 according to this embodiment. The base station 20 includes a wireless communication unit 21, a storage unit 22, and a control unit 23. However, the configuration shown in Fig. 6 is a functional configuration, and the hardware configuration may be different. Furthermore, the functions of the base station 20 may be distributed and implemented in multiple physically separated units.

[0107] The wireless communication unit 21 is a signal processing unit for wireless communication with other wireless communication devices (e.g., at least one of the relay station 30, the terminal device 40, and another base station 20). The wireless communication unit 21 may be referred to as a wireless transceiver. The wireless communication unit 21 is controlled by the control unit 23. The wireless communication unit 21 supports one or more wireless access methods. The wireless communication unit 21 may support at least one of NR, LTE, and 6G. In addition to NR, LTE, and 6G, the wireless communication unit 21 may also support W-CDMA, cdma2000, and the like. The wireless communication unit 21 may also support automatic retransmission techniques such as HARQ (Hybrid Automatic Repeat reQuest). Some or all of the processing performed by the wireless communication unit 21 may be considered as transmission processing (the transmission processing described above or below (first transmission processing or second transmission processing)) or reception processing (the reception processing described above or below (first reception processing or second reception processing)) of this embodiment. Some or all of these processes (the transmission process or the reception process described above or below) may be executed by the control unit 23 .

[0108] The wireless communication unit 21 may refer to at least one of the transmission processing unit 211, the reception processing unit 212, and the antenna 213. The wireless communication unit 21 may include a plurality of transmission processing units 211, reception processing units 212, and antennas 213. When the wireless communication unit 21 supports a plurality of wireless access methods, each unit of the wireless communication unit 21 may be configured separately for each wireless access method. The transmission processing unit 211 and the reception processing unit 212 may be configured separately for LTE, NR, and 6G. The antenna 213 may be configured with a plurality of antenna elements, for example, a plurality of 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 vertical polarization (V polarization) and horizontal polarization (H polarization) (or a polarization beamforming function using dual polarization in polarization directions 45 degrees and -45 degrees from the vertical direction).

[0109] The transmission processing unit 211 performs transmission processing of the downlink control information and downlink data. For example, 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. Here, the encoding may be performed using polar codes or low density parity check codes (LDPC codes). The transmission processing unit 211 then modulates the coded bits using a predetermined modulation method (e.g., BPSK, QPSK, 16QAM, 64QAM, 256QAM, or a higher-order multi-level modulation method). In this case, the signal points on the constellation do not necessarily need to be equidistant. The constellation may be a non-uniform constellation (NUC). The transmission processing unit 211 then multiplexes the modulation symbols of each channel and the downlink reference signal and allocates them to predetermined resource elements. The transmission processing unit 211 then performs various signal processing on the multiplexed signal. For example, the transmission processing unit 211 performs processes such as conversion to the frequency domain by discrete Fourier transform, addition of a guard interval (cyclic prefix), generation of a baseband digital signal, conversion to an analog signal, quadrature modulation, up-conversion, removal of unnecessary frequency components, and power amplification. The signal generated by the transmission processing unit 211 is transmitted from the antenna 213. Some or all of these processes performed by the transmission processing unit 211 may be considered as the transmission process of this embodiment (the transmission process described above or below (first transmission process or second transmission process)).

[0110] The reception processing unit 212 processes the uplink signal received via the antenna 213. For example, the reception processing unit 212 performs downconversion, removal of unnecessary frequency components, control of amplification level, quadrature demodulation, conversion to a digital signal, removal of guard intervals (cyclic prefixes), extraction of frequency domain signals by discrete Fourier transform, and the like on the uplink signal. The reception processing unit 212 then separates uplink channels such as a PUSCH (Physical Uplink Shared Channel) and a PUCCH (Physical Uplink Control Channel) and an uplink reference signal from the signal that has undergone these processes. Furthermore, the reception processing unit 212 demodulates the received signal using a modulation method such as Binary Phase Shift Keying (BPSK) or Quadrature Phase Shift Keying (QPSK) for the modulation symbols of the uplink channel. The modulation method used for demodulation may be 16QAM (Quadrature Amplitude Modulation), 64QAM, or 256QAM. In this case, the signal points on the constellation do not necessarily have to be equidistant. The constellation may be a non-uniform constellation (NUC). The reception processing unit 212 then performs decoding processing on the coded bits of the demodulated uplink channel. The decoded uplink data and uplink control information are output to the control unit 23. Some or all of these processes performed by the reception processing unit 212 may be considered as the reception processing of this embodiment (the reception processing described above or below (first reception processing or second reception processing)).

[0111] The antenna 213 is an antenna device that converts electric current and radio waves into each other. The antenna 213 may be configured with a single antenna element, for example, a single patch antenna. The antenna 213 may be configured with multiple antenna elements, for example, multiple patch antennas. When the antenna 213 is configured with multiple antenna elements, the wireless communication unit 21 may have a beamforming function. The wireless communication unit 21 may be configured to generate a directional beam by controlling the directivity of a wireless signal using the multiple antenna elements. The antenna 213 may be a dual-polarized antenna. When the antenna 213 is a dual-polarized antenna, the wireless communication unit 21 may use vertical polarization (V polarization) and horizontal polarization (H polarization) (or dual polarization with polarization directions at 45 degrees and -45 degrees from the vertical direction) when transmitting a wireless signal. The wireless communication unit 21 may control the directivity of a wireless signal transmitted using vertical polarization and horizontal polarization (or dual polarization with polarization directions at 45 degrees and -45 degrees from the vertical direction). Furthermore, the wireless communication unit 21 may transmit and receive spatially multiplexed signals via multiple layers each consisting of multiple antenna elements.

[0112] The storage unit 22 is a readable / writable storage device such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 22 may store an AI / ML model used in the processing of each functionality. The AI / ML model stored in the base station 20 may be the same as or different from the AI / ML model stored in the relay station 30 or the terminal device 40 described below.

[0113] The control unit 23 is a controller that controls each unit of the base station 20. The control unit 23 may be realized by a processor such as a CPU or an MPU. For example, the control unit 23 may be realized by a processor executing various programs stored in a storage device inside the base station 20 using RAM or the like as a work area. The control unit 23 may be realized by an integrated circuit such as an ASIC or an FPGA. The control unit 23 may also be realized by a GPU. A CPU, an MPU, an ASIC, an FPGA, and a GPU can all be considered controllers. The control unit 23 may be composed of multiple physically separated objects. For example, the control unit 23 may be composed of multiple semiconductor chips.

[0114] The control unit 23 includes at least one block from among an acquisition unit 231, a management unit 232, a determination unit 233, and a transmission unit 234. Each block (acquisition unit 231 to transmission unit 234) constituting the control unit 23 is a functional block that indicates the function of the control unit 23. These functional blocks may be software blocks or hardware blocks. For example, each of the above-described functional blocks may be a software module realized by software (including a microprogram), or may be a circuit block on a semiconductor chip (die). Of course, each functional block may be a processor or an integrated circuit. The control unit 23 may be configured with functional units different from the above-described functional blocks. The method of configuring the functional blocks is arbitrary. The operation of each functional block of the control unit 23 may be the same as the operation of each functional block of the relay station 30 or the terminal device 40.

[0115] In some embodiments, the base station 20 may be configured as a collection of multiple physical or logical devices. As an example, the base station 20 of this embodiment may be divided into multiple devices such as a baseband unit (BBU) and a radio unit (RU). The base station 20 may be interpreted as a collection of these multiple devices. Furthermore, the base station may be either a BBU or an RU, or both. The BBU and the RU may be connected by a predetermined interface such as an enhanced Common Public Radio Interface (eCPRI).

[0116] The RU may be referred to as an RRU (Remote Radio Unit) or an RD (Radio DoT). The RU may correspond to a gNB-DU (gNB Distributed Unit) described later. The BBU may correspond to a gNB-CU (gNB Central Unit) described later. The RU may be a device integrally formed with an antenna. The antenna of the base station 20, for example, an antenna integrally formed with the RU, may employ an Advanced Antenna System and support MIMO such as FD-MIMO or beamforming. The antenna of the base station 20 may include, for example, 64 transmitting antenna ports and 64 receiving antenna ports.

[0117] The antenna mounted on the RU may be an antenna panel consisting of one or more antenna elements, and the RU may be equipped with one or more antenna panels. The RU may be equipped with two types of antenna panels, a horizontally polarized antenna panel and a vertically polarized antenna panel. The RU may be equipped with two types of antenna panels, a right-handed circularly polarized antenna panel and a left-handed circularly polarized antenna panel, or an antenna panel with a polarization direction at 45 degrees from the vertical direction and an antenna panel with a polarization direction at -45 degrees from the vertical direction. Multiple antennas with these multiple polarization directions may be mounted on a single antenna panel. The RU may form and control an independent beam for each antenna panel.

[0118] A plurality of base stations 20 may be connected to each other. One or more base stations 20 may be included in a radio access network (RAN). In this case, the base station 20 may be simply referred to as a RAN, a RAN node, an AN (Access Network), an AN node, or the like. The RAN in LTE may be called an Enhanced Universal Terrestrial RAN (EUTRAN). The RAN in NR may be called an NGRAN. Furthermore, the RAN in 6G may be called a 6GRAN. The RAN in W-CDMA (UMTS) may be called a UTRAN.

[0119] An LTE base station 20 may be referred to as an eNodeB (Evolved Node B) or eNB. In this case, the EUTRAN includes one or more eNodeBs (eNBs). An NR base station 20 may be referred to as a gNodeB or gNB. In this case, the NGRAN includes one or more gNBs. A 6G base station may 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 a core network (EPC) in an LTE communication system (EPS). The NGRAN may include an ng-eNB connected to a core network 5GC in a 5G communication system (5GS).

[0120] When the base station 20 is an eNB, gNB, 6GNB, or the like, the base station 20 may be referred to as a 3GPP access. When the base station 20 is a wireless access point, the base station 20 may be referred to as a non-3GPP access. The base station 20 may be a radio device called an RRH (Remote Radio Head). When the base station 20 is a gNB, the 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.

[0121] Here, the gNB-CU hosts multiple upper layers (e.g., RRC (Radio Resource Control), SDAP (Service Data Adaptation Protocol), PDCP (Packet Data Convergence Protocol)) of the access stratum for communication with the UE. On the other hand, the gNB-DU hosts multiple lower layers (e.g., RLC (Radio Link Control), MAC (Medium Access Control), PHY (Physical layer)) of the access stratum. That is, among the messages / information described below, RRC signaling (semi-static notification) is generated by the gNB-CU, while MAC The CE and DCI (dynamic notification) may be generated by the gNB-DU. Alternatively, some configurations of the RRC configuration (semi-static notification), such as IE:cellGroupConfig, may be generated by the gNB-DU, and the remaining configurations may be generated by the gNB-CU. These configurations may be transmitted and received over the F1 interface described below.

[0122] The base station 20 may be configured to be able to communicate with other base stations. When multiple base stations 20 are eNBs or a combination of eNBs and en-gNBs, these base stations 20 may be connected to each other via an X2 interface. When multiple base stations 20 are gNBs or a combination of gn-eNBs and gNBs, these base stations 20 may be connected to each other via an Xn interface. When multiple base stations 20 are a combination of gNB-CUs and gNB-DUs, these base stations 20 may be connected to each other via the F1 interface described above. Messages / information (e.g., RRC signaling, MAC Control Element (CE), or Downlink Control Information (DCI)) described below may be transmitted between multiple base stations 20 via these inter-base station interfaces (e.g., X2 interface, Xn interface, or F1 interface).

[0123] A cell provided by the base station 20 may be referred to as a serving cell. The concept of a serving cell includes a PCell (Primary Cell) and an SCell (Secondary Cell). When dual connectivity is provided to the terminal device 40, the PCell and zero or more SCells provided by a Master Node (MN) may be referred to as a Master Cell Group. The dual connectivity may be at least one of EUTRA-EUTRA Dual Connectivity, EUTRA-NR Dual Connectivity (ENDC), EUTRA-NR Dual Connectivity with 5GC, NR-EUTRA Dual Connectivity (NEDC), NR-NR Dual Connectivity, NR-6G Dual Connectivity, and 6G-NR Dual Connectivity. Of course, dual connectivity is not limited to these.

[0124] The serving cell may include a PSCell (Primary Secondary Cell or Primary SCG Cell). When dual connectivity is provided to the terminal device 40, the PSCell provided by a Secondary Node (SN) and zero or more SCells may be referred to as a Secondary Cell Group (SCG). Unless special configuration (e.g., PUCCH on SCell) is performed, the Physical Uplink Control Channel (PUCCH) is transmitted by the PCell and PSCell but not by the SCell. Radio link failure is detected by the PCell and PSCell but not (does not need to be detected by) the SCell. As such, the PCell and PSCell play special roles among serving cells and are therefore also referred to as Special Cells (SpCells).

[0125] One cell may be associated with one downlink component carrier and one uplink component carrier. The system bandwidth corresponding to one cell may be divided into multiple BWPs (Bandwidth Parts). In this case, one or multiple BWPs may be configured in the terminal device 40, and one BWP may be used by the terminal device 40 as an active BWP. Radio resources available to the terminal device 40, such as a frequency band, numerology (subcarrier spacing), or slot format (Slot configuration), may differ for each cell, each component carrier, or each BWP.

[0126] <2-3. Configuration of Relay Station> The relay station 30 is a wireless communication device that serves 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 can also be called a relay base station. Note that the relay station 30 may also be a device called a repeater (e.g., RF Repeater, Smart Repeater, Intelligent Surface). The relay station 30 is a wireless communication device that performs wireless communication with other wireless communication devices (e.g., base station 20, other relay stations 30, or terminal device 40).

[0127] The relay station 30 may be capable of 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 wireless communication with other relay stations 30 and the base station 20. The relay station 30 may be a terrestrial station device or a non-terrestrial station device. The relay station 30, together with the base station 20, constitutes a radio access network RAN.

[0128] The relay station 30 may be a fixed device, a mobile device, or a floating device. The size of the coverage of the relay station 30 is not limited to a specific size. The cell covered by the relay station 30 may be a macrocell, a microcell, or a small cell.

[0129] As long as the relay station 30 fulfills the relay function, it may be a device mounted on another device. For example, the relay station 30 may be mounted on a terminal device such as a smartphone, a moving object such as an automobile, a train, a balloon, an airplane, or a drone, or a home appliance such as a television, a game console, an air conditioner, a refrigerator, or a lighting fixture.

[0130] The configuration of the relay station 30 may be the same as the configuration of the base station 20 described above. Like the base station 20 described above, the relay station 30 may be a device installed in a mobile body, or may be the mobile body itself. As described above, the mobile body may be a mobile terminal such as a smartphone or a mobile phone. The mobile body may be a mobile body that moves on land (terrestrial in the narrow sense) or may be a mobile body that moves underground. The mobile body may be a mobile body that moves on water or may be a mobile body that moves underwater. The mobile body may be a mobile body that moves within the atmosphere or may be a mobile body that moves outside the atmosphere. The relay station 30 may be a terrestrial station device or a non-terrestrial station device. The relay station 30 may be an aircraft station, a satellite station, or the like.

[0131] The size of the coverage of the relay station 30 may be as large as a macrocell or as small as a picocell, similar to the base station 20. The size of the coverage of the relay station 30 may be extremely small, such as a femtocell. The relay station 30 may have a beamforming function. The relay station 30 may form a cell or service area for each beam.

[0132] Fig. 7 is a diagram showing the configuration of a relay station 30 according to this embodiment. The relay station 30 includes a wireless communication unit 31, a storage unit 32, and a control unit 33. However, the configuration shown in Fig. 7 is a functional configuration, and the hardware configuration may be different from this. Furthermore, the functions of the relay station 30 may be distributed and implemented in multiple physically separated units.

[0133] The wireless communication unit 31 is a signal processing unit for wireless communication with other wireless communication devices (e.g., at least one of the base station 20, the terminal device 40, and another relay station 30). The wireless communication unit 31 may be referred to as a wireless transceiver. The wireless communication unit 31 supports one or more wireless access methods. The wireless communication unit 31 may support at least one of NR, LTE, and 6G. In addition to NR, LTE, and 6G, the wireless communication unit 31 may also support W-CDMA and cdma3000. Some or all of the processing performed by the wireless communication unit 31 may be considered as transmission processing (the transmission processing described above or below (first transmission processing or second transmission processing)) or reception processing (the reception processing described above or below (first reception processing or second reception processing)) of this embodiment. Some or all of these processes (the transmission processing or reception processing described above or below) may be performed by the control unit 33.

[0134] The wireless communication unit 31 may refer to at least one of the transmission processing unit 311, the reception processing unit 312, and the antenna 313. The wireless communication unit 31 may include multiple transmission processing units 311, multiple reception processing units 312, and multiple antennas 313. When the wireless communication unit 31 supports multiple wireless access methods, each unit of the wireless communication unit 31 may be configured separately for each wireless access method. The transmission processing unit 311 and the reception processing unit 312 may be configured separately for LTE, NR, and 6G. The configurations of the transmission processing unit 311, the reception processing unit 312, and the antenna 313 may be similar to the configurations of the transmission processing unit 211, the reception processing unit 212, and the antenna 213 of the base station 20 described above. The wireless communication unit 31 may have a beamforming function, similar to the wireless communication unit 21 of the base station 20. Some or all of the processing performed by the transmission processing unit 311 may be considered as the transmission processing of this embodiment (the transmission processing described above or below (first transmission processing or second transmission processing)). Furthermore, all or part of the processing executed by the reception processing unit 312 may be considered as the reception processing of this embodiment (the reception processing described above or below (first reception processing or second reception processing)).

[0135] The storage unit 32 is a readable / writable storage device such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 32 functions as a storage means of the relay station 30. The configuration and function of the storage unit 32 may be similar to the configuration and function of the storage unit 22 of the base station 20 described above. The storage unit 32 may store an AI / ML model used in the processing of each functionality. The AI / ML model stored in the relay station 30 may be similar to or different from the AI / ML model stored in the base station 20 described above or a terminal device 40 described later.

[0136] The control unit 33 is a controller that controls each unit of the relay station 30. The control unit 33 may be realized by a processor such as a CPU or an MPU. Specifically, the control unit 33 may be realized by a processor executing various programs stored in a storage device inside the relay station 30 using RAM or the like as a work area. The control unit 33 may be realized by an integrated circuit such as an ASIC or an FPGA. The CPU, MPU, ASIC, and FPGA can all be considered controllers. The control unit 33 may also be realized by a GPU. The CPU, MPU, ASIC, FPGA, and GPU can all be considered controllers. The control unit 33 may be composed of multiple physically separated objects. For example, the control unit 33 may be composed of multiple semiconductor chips. The configuration and functions of the control unit 33 may be similar to those of the control unit 23 of the base station 20 described above.

[0137] The control unit 33 includes at least one block from among an acquisition unit 331, a management unit 332, a determination unit 333, and a transmission unit 334. Each block (acquisition unit 331 to transmission unit 334) constituting the control unit 33 is a functional block that indicates the function of the control unit 33. These functional blocks may be software blocks or hardware blocks. For example, each of the above-described functional blocks may be a software module realized by software (including a microprogram), or may be a circuit block on a semiconductor chip (die). Of course, each functional block may be a processor or an integrated circuit. The control unit 33 may be configured by functional units different from the above-described functional blocks. The configuration method of the functional blocks is arbitrary. The operation of each functional block of the control unit 33 may be the same as the operation of each functional block of the base station 20 or the terminal device 40.

[0138] The relay station 30 may be an IAB relay node. The relay station 30 operates as an IAB-MT (Mobile Termination) for an IAB donor node that provides backhaul, and operates as an IAB-DU (Distributed Unit) for a terminal device 40 that provides access. The IAB donor node may be, for example, a base station 20, and operates as an IAB-CU (Central Unit).

[0139] <2-4. Configuration of Terminal Device> The terminal device 40 is a wireless communication device that performs wireless communication with other wireless communication devices (for example, a base station 20, a relay station 30, or another terminal device 40). The terminal device 40 can be referred to as UE (User Equipment) 40.

[0140] The terminal device 40 may be any type of information processing device (computer). For example, the terminal device 40 may be a mobile terminal such as a mobile phone, a smart device (smartphone or tablet), a PDA (Personal Digital Assistant), or a notebook PC. The terminal device 40 may also be a communication module that is connected to an information processing device (e.g., an imaging device without wireless communication capabilities) and provides the information processing device with wireless communication capabilities. The terminal device 40 may also be an imaging device with wireless communication capabilities (e.g., a camcorder).

[0141] The terminal device 40 may be a motorcycle or a mobile broadcasting vehicle equipped with a communication device such as a Field Pickup Unit (FPU). The terminal device 40 may be a Machine to Machine (M2M) device or an Internet of Things (IoT) device. The terminal device 40 may be a wearable device such as a smartwatch.

[0142] Furthermore, the terminal device 40 may be an XR (Extended Reality) device such as an AR (Augmented Reality) device, a VR (Virtual Reality) device, or an MR (Mixed Reality) device. In this case, the XR device may be a glasses-type device such as AR glasses or MR glasses, or a head-mounted device such as a VR head-mounted display. When the terminal device 40 is an XR device, the terminal device 40 may be a standalone device consisting only of a part worn by a user (e.g., a glasses part). Furthermore, the terminal device 40 may be a terminal-linked device consisting of a part worn by a user (e.g., a glasses part) and a terminal part (e.g., a smart device) linked to the part worn by a user.

[0143] The terminal device 40 may be capable of NOMA communication with the base station 20. The terminal device 40 may be able to use an automatic repeat transmission technique such as HARQ when communicating with the base station 20. The terminal device 40 may be capable of sidelink communication with another terminal device 40. The terminal device 40 may be able to use an automatic repeat transmission technique such as HARQ when performing sidelink communication. The terminal device 40 may be capable of NOMA communication when performing sidelink communication with another terminal device 40. The terminal device 40 may be capable of LPWA communication with other wireless communication devices 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 used by the terminal device 40, including sidelink communication, may be wireless communication using radio waves or wireless communication using infrared or visible light (i.e., optical wireless).

[0144] The terminal device 40 may be a mobile wireless communication device, i.e., a mobile device. The terminal device 40 may be a wireless communication device installed in a mobile device, or may be the mobile device itself. The terminal device 40 may be a vehicle that moves on a road, such as an automobile, bus, truck, or motorcycle, or a train that runs on a track, or may be a wireless communication device mounted on the vehicle. The mobile device may be a mobile terminal, or a mobile device that moves on land (in the narrow sense of the word), underground, on water, or underwater. The mobile device may also be a mobile device that moves within the atmosphere, such as an airplane, airship, balloon, or helicopter, or a mobile device that moves outside the atmosphere, such as an artificial satellite. The mobile device may also be a UAV (Unmanned Aerial Vehicle) such as a drone. The terminal device 40 may also be a wireless communication device mounted on the mobile device.

[0145] The terminal device 40 may be capable of simultaneously connecting to and communicating with a plurality of base stations 20 or a plurality of cells. When one base station 20 supports a communication area through a plurality of cells (e.g., pCell or sCell), the plurality of cells can be bundled together to enable communication between the base station 20 and the terminal device 40 by using carrier aggregation (CA) technology, dual connectivity (DC) technology, multi-connectivity (MC) technology, or the like. Alternatively, communication between the terminal device 40 and the plurality of base stations 20 can also be performed via cells of different base stations 20 by coordinated multi-point transmission and reception (CoMP) technology.

[0146] The terminal device 40 may be a relay terminal that relays communications to a remote terminal.

[0147] Fig. 8 is a diagram showing the configuration of a terminal device 40 according to this embodiment. The terminal device 40 includes a wireless communication unit 41, a storage unit 42, and a control unit 33. However, the configuration shown in Fig. 8 is a functional configuration, and the hardware configuration may be different from this. Furthermore, the functions of the terminal device 40 may be distributed and implemented in multiple physically separated components.

[0148] The wireless communication unit 41 is a signal processing unit for wireless communication with other wireless communication devices (e.g., at least one of the base station 20, the relay station 30, and the other terminal device 40). The wireless communication unit 41 may be referred to as a wireless transceiver. The wireless communication unit 41 is controlled by the control unit 43. The wireless communication unit 41 supports one or more wireless access methods. The wireless communication unit 41 may support at least one of NR, LTE, and 6G. In addition to NR, LTE, and 6G, the wireless communication unit 41 may also support W-CDMA, cdma2000, and the like. The wireless communication unit 41 may also support automatic retransmission techniques such as HARQ (Hybrid Automatic Repeat reQuest). Some or all of the processing performed by the wireless communication unit 41 may be considered as transmission processing (the transmission processing described above or below (first transmission processing or second transmission processing)) or reception processing (the reception processing described above or below (first reception processing or second reception processing)). Some or all of these processes (the transmission process or the reception process described above or below) may be executed by the control unit 43 .

[0149] The wireless communication unit 41 may refer to at least one of the transmission processing unit 411, the reception processing unit 412, and the antenna 413. The wireless communication unit 41 may include multiple transmission processing units 411, multiple reception processing units 412, and multiple antennas 413. If the wireless communication unit 41 supports multiple wireless access methods, each unit of the wireless communication unit 41 may be configured individually for each wireless access method. The transmission processing unit 411 and the reception processing unit 412 may be configured individually for LTE, NR, and 6G. The antenna 413 may be configured with multiple antenna elements, for example, 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 vertical polarization (V polarization) and horizontal polarization (H polarization) (or a polarization beamforming function using dual polarization in polarization directions 45 degrees and -45 degrees from the vertical direction). Furthermore, the antenna 413 does not necessarily have to be a part of the terminal device 40 or the wireless communication unit 41. For example, the antenna 413 may not be included in the wireless communication unit 41, but may be installed in the terminal device 40 as an external antenna. Some or all of the processing performed by the transmission processing unit 411 may be considered to be the transmission processing of this embodiment (the transmission processing described above or below (first transmission processing or second transmission processing)). Furthermore, some or all of the processing performed by the reception processing unit 412 may be considered to be the reception processing of this embodiment (the reception processing described above or below (first reception processing or second reception processing)).

[0150] The storage unit 42 is a readable / writable storage device such as a DRAM, an SRAM, a flash memory, or a hard disk. The storage unit 42 functions as a storage means of the terminal device 40. The storage unit 42 may store an AI / ML model used in the processing of each functionality. The AI / ML model stored in the terminal device 40 may be the same as or different from the AI / ML model stored in the base station 20 or the relay station 30 described above.

[0151] The control unit 43 is a controller that controls each unit of the terminal device 40. The control unit 43 may be realized by a processor such as a CPU or an MPU. For example, the control unit 43 may be realized by a processor executing various programs stored in a storage device inside the terminal device 40 using RAM or the like as a work area. The control unit 43 may be realized by an integrated circuit such as an ASIC or an FPGA. The control unit 43 may be realized by a GPU. A CPU, an MPU, an ASIC, an FPGA, and a GPU can all be considered controllers. The control unit 43 may be composed of multiple physically separated objects. For example, the control unit 43 may be composed of multiple semiconductor chips.

[0152] The control unit 43 includes at least one block from among an acquisition unit 431, a management unit 432, a determination unit 433, and a transmission unit 434. Each block (acquisition unit 431 to transmission unit 434) constituting the control unit 43 is a functional block that indicates the function of the control unit 43. These functional blocks may be software blocks or hardware blocks. For example, each of the above-described functional blocks may be a software module realized by software (including a microprogram), or may be a circuit block on a semiconductor chip (die). Of course, each functional block may be a processor or an integrated circuit. The control unit 43 may be configured by functional units different from the above-described functional blocks. The configuration method of the functional blocks is arbitrary. The operation of each functional block of the control unit 43 may be the same as the operation of each functional block of the base station 20 or relay station 30.

[0153] <2-5. AI / ML Model> At least one of 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 may store an AI / ML model. Furthermore, at least one of the base station 20, the relay station 30, and the terminal device 40 may execute various processes using the AI / ML model. For example, at least one of the base station 20, the relay station 30, and the terminal device 40 may generate information such as assistance information and transmission data using the AI / ML model. In the following description, the AI / ML model may be referred to as a learning model or simply as a model.

[0154] The learning model is, for example, a neural network model. A neural network model is composed of layers called an input layer, an intermediate layer (or hidden layer), and an output layer, each of which includes a plurality of nodes, and each node is connected via an edge. 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 a neural network model, learning the learning model means, for example, setting the number of intermediate layers (or hidden layers), the number of nodes in each layer, or the weight of each edge.

[0155] Here, the neural network model may be a model based on deep learning. In this case, the neural network model may be a model in a form called a deep neural network (DNN). Furthermore, the neural network model may be a model in a form called a convolution 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 types of models.

[0156] In a CNN, the hidden layer is composed of layers called a convolution layer and a pooling layer. The convolution layer performs filtering using convolution operations to extract data called a feature map. The pooling layer compresses the information of the feature map output from the convolution layer and performs downsampling. CNNs are used, for example, for image recognition applications, where information about each pixel in an image, also known as a pixel, is input to the input layer, and information about the recognized image can be obtained as the output layer.

[0157] The RNN has a network structure in which values ​​of a hidden layer are recursively input to the hidden layer, and is used to process, for example, short-term time-series data.

[0158] In LSTM, the influence of distant past outputs can be retained by introducing parameters called memory cells that retain the state of the hidden layer outputs of the RNN. In other words, LSTM processes time series data over a longer period than RNN.

[0159] Furthermore, the learning model is not limited to a neural network model. For example, the learning model may be a model based on reinforcement learning. In reinforcement learning, behaviors (settings) that maximize value are learned through trial and error. Alternatively, the learning model may be a logistic regression model.

[0160] The learning model may be composed of a plurality of models. For example, the learning model may be composed of a plurality of neural network models. More specifically, the learning model may be composed of a plurality of neural network models selected from, for example, CNN, RNN, and LSTM. When the learning model is composed of a plurality of neural network models, these plurality of neural network models may be in a subordinate relationship or in a parallel relationship.

[0161] The learning model can also be referred to as an AI (Artificial Intelligence) model, an ML (Machine Learning) model, or a trained model. In the following description, the learning model may be simply referred to as a model. Hereinafter, the learning model will be described using the learning model M shown in FIG. 1A as an example, but the learning model of this embodiment is not limited to the learning model M shown below.

[0162] The learning model M is a learning model composed of a first model and a second model. The first model and the second model are each sub-models 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 first half of the learning model M and is stored in the transmitting device. Note that the sub-models can also be considered a type of learning model. The learning model of this embodiment will be described in detail below. In the following description, the learning model will be described using the generation of assistance information as an example, but the functions of the learning model are not limited to the generation of assistance information.

[0163] The learning model M is, for example, a learning model (trained model) that is trained using the assistance information T as input data and the assistance information R as correct labels (teacher data). As described above, the assistance information is information required for the receiving device to perform processing related to wireless communication, or information for assisting the receiving device in processing related to wireless communication. For example, the assistance information is information (e.g., control information) required for operations such as uplink data transmission, sidelink transmission, unlicensed communication, and handover of the terminal device 40. Note that the assistance information R is information related to the assistance information T. The assistance information R may be information with content different from that of the assistance information T, or may be information with content identical to that of the assistance information T.

[0164] When the base station 20 or the terminal device 40 inputs first information (e.g., assistance information T) to a first model of the learning model M, the first model outputs second information (e.g., compressed information / feature information of the assistance information T). Also, when the base station 20 or the terminal device 40 inputs the second information to a second model of the learning model M, the second model outputs third information (e.g., assistance information R).

[0165] In this case, the learning model M may include an input layer that inputs first information (e.g., assistance information T), an output layer that outputs third information (e.g., assistance information R), a first element that belongs to any layer between the input layer and the output layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and may be a learning model that causes a computer to function so that, for the information input to the input layer, each element belonging to each layer other than the output layer is used as the first element, and by performing a calculation based on the first element and the weight of the first element (i.e., the connection coefficient), the third information is output from the output layer in accordance with the first information input to the input layer.

[0166] Here, it is assumed that the learning model M is realized by a neural network having one or more intermediate layers, such as a DNN. In this case, the first element included in the learning model corresponds to any node in the input layer or the intermediate layer. The second element corresponds to a node in the next stage, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient, which is a weight taken into account for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

[0167] Also, assume that the learning model M is realized as 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 input data (xi) such as x1 or x2. 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 corresponds to one of the nodes in the input layer, and the second element can be regarded as a node in the output layer.

[0168] The base station 20 or the terminal device 40 calculates the information to be output using a model having any structure, such as a neural network or a regression model. Specifically, the coefficients of the learning model M are set so that third information (e.g., assistance information R) is output when first information (e.g., assistance information T) is input. For example, the base station 20 or the terminal device 40 sets the coefficients based on the similarity between the third information and a value obtained by inputting the first information into the learning model. The base station 20 or the terminal device 40 generates second information from the first information using a submodel (first model) of such learning model M. Alternatively, the base station 20 or the terminal device 40 generates third information from the second information using a submodel (second model) of such learning model M.

[0169] In the above example, a model that outputs third information when first information is input is shown 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.

[0170] Furthermore, when the base station 20 or the terminal device 40 performs learning or generates output information using GAN (Generative Adversarial Networks), the learning model may be a model that constitutes part of the GAN.

[0171] The learning device that learns the learning model M may be the base station 20, the relay station 30, or the terminal device 40. The learning device may also 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, assume that the server device learns the learning model M. In this case, the server device learns the learning model M and stores the learned learning model M in a memory unit. More specifically, the server device sets the connection coefficients of the learning model M so that, when first information (e.g., assistance information T) is input to the learning model M, the learning model outputs third information (e.g., assistance information R).

[0172] For example, an information processing device (e.g., management device 10, base station 20, relay station 30, terminal device 40, or server device) inputs first information to a node in the input layer of learning model M, and propagates the data through each intermediate layer to the output layer of learning model M, thereby causing learning model M to output third information. The information processing device then corrects the connection coefficients of learning model M based on the difference between the value actually output by learning model M and the value designated as the correct label (teaching data). At this time, the information processing device may correct the connection coefficients using a technique such as backpropagation. At this time, the server device may correct the connection coefficients based on the cosine similarity between a vector indicating the input value and a vector indicating the value actually output by the learning model.

[0173] Any learning algorithm may be used for the learning. For example, the information processing device may perform learning of the learning model using a learning algorithm such as a neural network, a support vector machine, clustering, reinforcement learning, a random forest, or a decision tree.

[0174] Although the method for generating the learning model M has been described above, the above embodiment can also be applied to learning models other than the learning model M.

[0175] Furthermore, the learning algorithm used in this embodiment may be one that is learned by a single information processing device (for example, the management device 10, the base station 20, the relay station 30, the terminal device 40, or the server device) alone, or one that is learned by multiple information processing devices (for example, multiple devices selected from the management device 10, the base station 20, the relay station 30, the terminal device 40, and the server device) working together. An example of a learning algorithm in which multiple information processing devices work together to learn is federated learning.

[0176] <<3. Network Architecture>> The configuration of the communication system 1 has been described above. Next, a network architecture that can be applied to the communication system 1 of this embodiment will be described. Here, the architecture of a fifth-generation mobile communication system (5G) will be described as an example of the core network CN of the communication system 1.

[0177] 9 is a diagram illustrating an example of a 5G architecture. The 5G core network CN is also called 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 a UE (User Equipment) 40 via an (R)AN 530.

[0178] The terminal device 40 shown in Fig. 8 is an example of a UE 40. The base station 20 shown in Fig. 6 or the relay station 30 shown in Fig. 7 is an example of a RAN / AN 530. The management device 10 shown in Fig. 5 is an example of a device having the functions of, for example, an AF 549 or an AMF 541.

[0179] The (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. The (R)AN 530 includes a base station called a gNB or ng-eNB.

[0180] The core network CN mainly performs connection permission and session management when the UE 40 connects to the network. The core network CN can be configured to include a user plane function group 520 and a control plane function group 540.

[0181] The user plane function group 520 includes a UPF (User Plane Function) 521 and a DN (Data Network) 522. The UPF 521 has a user plane processing function. The UPF 521 includes a routing / transfer function for data handled in the user plane. The DN 522 has a function to provide connection to an operator's own service, such as an MNO (Mobile Network Operator), a function to provide Internet connection, or a function to provide connection to a third-party service. In this way, the user plane function group 520 plays the role of a gateway that serves as the boundary between the core network CN and the Internet.

[0182] The control plane function group 540 includes an AMF (Access Management Function) 541, an SMF (Session Management Function) 542, an AUSF (Authentication Server Function) 543, an NSSF (Network Slice Selection Function) 544, an NEF (Network Exposure Function) 545, an NRF (Network Repository Function) 546, a PCF (Policy Control Function) 547, an UDM (Unified Data Management) 548, and an AF (Application Function) 549.

[0183] 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, IP allocation and management for the UE 40, etc. The AUSF 543 has an authentication function. The NSSF 544 has a function related to network slice selection. The NEF 545 has a function of providing network function capabilities and events to third parties, the AF 549, and edge computing functions.

[0184] The NRF 546 has the function of discovering network capabilities and maintaining network capability profiles. The PCF 547 has the function of policy control. The UDM 548 has the function of generating 3GPP AKA authentication information and processing user identities. The AF 549 has the function of interacting with the core network to provide services.

[0185] For example, the control plane function group 540 acquires information from the UDM 548 in which subscriber information of the UE 40 is stored, and determines whether or not the UE 40 may connect to the network. For this determination, the control plane function group 540 uses the contract information of the UE 40 and an encryption key contained in the information acquired from the UDM 548. The control plane function group 540 also generates encryption keys, etc.

[0186] That is, the control plane function group 540 determines whether or not the UE 40 can connect to the network depending on whether or not information about the UE 40 linked to a subscriber number called an IMSI (International Mobile Subscriber Identity) is stored in the UDM 548. The IMSI is stored in a SIM (Subscriber Identity Module) card in the UE 40, for example.

[0187] The core network CN may have an LCM-related network function. The LCM-related network function is a network function that provides an LCM-related control function. For example, the LCM-related network function has a function of controlling at least one of the above-mentioned (M1) to (M25), or providing information required for executing at least one of the above-mentioned (M1) to (M25).

[0188] The LCM-related network function may be included in an existing network function. For example, the LCM-related network function may be included in an MTLF (Model Training Logical Function) 551. The management device 10 shown in FIG. 5 is an example of a device having the functionality of the MTLF 551.

[0189] The LCM-related network function may also 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 also be included in a server connected to the base station 20 ((R)AN 530) (e.g., an MEC server 553). The management device 10 shown in FIG. 5 is an example of the MEC server 552 or the MEC server 553.

[0190] Furthermore, 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 functions 540. The management device 10 shown in FIG. 5 is an example of a device having the functionality of the LCM-related network function 554.

[0191] In addition, there may be one or more LCM-related network functions in the core network CN.

[0192] <<4. LCM>> Having explained the network architecture above, we will now explain LCM (Life-cycle-management) in detail.

[0193] As described above, LCM refers to the management of the AI / ML model. LCM may be executed by a management unit of a communication device. For example, LCM may be executed by at least one of the management unit 232 of the base station 20, the management unit 332 of the relay station 30, and the management unit 432 of the terminal device 40. Of course, LCM may be executed by the management device 10 or a server device on the Internet.

[0194] In the following description, the AI / ML model may be referred to as a learning model or simply as a model.

[0195] The LCM may be composed of one or more of the elements (processes / methods / procedures / functions) shown below in (M1) to (M25). For example, the LCM may be one of (M1) to (M25), or may be a combination of multiple elements selected from (M1) to (M25). Note that (M1) to (M25) shown below are merely examples. The LCM of this embodiment (or the elements constituting the LCM) may include elements other than (M1) to (M25). Each of (M1) to (M25) will be described below.

[0196] (M1) Data collection Data collection is the process by which a network node (e.g., base station 20), a management entity (e.g., management device 10), or a UE (User Equipment) (e.g., terminal device 40) collects data for the purpose of training an AI / ML model, data analysis, and inference.

[0197] (M2) Model training Model training is a process of data-driven training by learning the input-output relationship of an AI / ML model and obtaining the trained AI / ML model for inference.

[0198] (M3) Functionality Identification Functionality identification is the process / method of identifying functions or requirements to which AI / ML is applied.

[0199] (M4) Model Identification Model identification is a process / method of identifying an AI / ML model for common understanding between the network (eg, base station 20, management device 10) and the UE (eg, terminal device 40).

[0200] (M5) Model Delivery Model delivery is a general term that refers to the delivery of an AI / ML model from one entity (e.g., a communication device described above or below) to another entity (e.g., a communication device described above or below) in any manner.

[0201] (M6) Model transfer Model transfer is the process of transferring an AI / ML model over the air interface, either parameters of a model structure known at the receiving end (e.g., receiving device) or a new model with parameters. Transfer may involve the transfer of a full model or a partial model.

[0202] (M7) Model Download Model download is a process of transferring a model from the network (eg, the base station 20, the management device 10) to the UE (eg, the terminal device 40).

[0203] (M8) Model Upload Model upload is a process of transferring a model from a UE (eg, terminal device 40) to a network (eg, base station 20, management device 10).

[0204] (M9) Model inference Model inference is the process of using a trained AI / ML model to generate a set of outputs based on a set of inputs (e.g., receiving information from other communication devices).

[0205] (M10) Model validation Model validation is a sub-process of training that evaluates the quality of an AI / ML model using a dataset different from the dataset used for model training.

[0206] (M11) Model testing: Model testing is a sub-process of training in which the performance of the final AI / ML model is evaluated using a dataset that is different from the dataset used for training and validating the model. Unlike AI / ML model validation, model testing does not anticipate subsequent adjustments to the model.

[0207] (M12) Model Activation Model activation is the process of validating an AI / ML model for a particular function.

[0208] (M13) Functionality Activation Functionality activation is the process of enabling the AI / ML functionality of a particular feature.

[0209] (M14) Model deactivation Model deactivation is the process of deactivating an AI / ML model for a particular function.

[0210] (M15) Functionality Deactivation Functionality deactivation is the process of disabling the AI / ML functionality of a particular feature.

[0211] (M16) Model switching Model switching is the process of deactivating the currently active AI / ML model and activating another AI / ML model for a particular function.

[0212] (M17) Functionality Switching Functionality switching is the process of deactivating a currently active AI / ML model and activating another AI / ML model for a particular function.

[0213] (M18) Model Fallback Model fallback is a process of deactivating an AI / ML model and switching to processing that does not use the AI / ML model.

[0214] (M19) Model monitoring Model monitoring is a procedure for monitoring the inference performance of an AI / ML model.

[0215] (M20) Model Update Model update is the process of updating the model parameters and / or model structure of a model.

[0216] (M21) Model Registration Model registration is the process of registering the model parameters and / or model structure of a model.

[0217] (M22) Model deployment Model deployment is a general term that refers to the deployment of an AI / ML model from one entity (e.g., a communication device described above or below) to another entity (e.g., a communication device described above or below) in any manner.

[0218] (M23) Model configuration Model configuration is the process of setting the model parameters and / or model structure of a model.

[0219] (M24) Model Selection Model selection is the process of selecting and activating an AI / ML model from multiple AI / ML models that are currently selectable.

[0220] (M25) UE capability The UE capability is a process in which the capability of a terminal device (eg, the terminal device 40) is notified from the terminal device (eg, the terminal device 40) to another communication device (eg, the base station 20).

[0221] In the following explanation, managing an AI / ML model based on functionality (e.g., managing an AI / ML model for each use case and / or function) may be referred to as functionality-based LCM.

[0222] FIG. 10 is a diagram for explaining the LCM. More specifically, FIG. 10 is a diagram showing the relationships between the LCM (or elements constituting the LCM). The LCM may be implemented as shown in the diagram of FIG. 10. Note that the diagram shown in FIG. 10 may be implemented by any one of the base station 20, a transmitting device (e.g., terminal device 40), and a receiving device (e.g., terminal device 40), or a combination of at least two of them. In other words, any one of the base station 20, a transmitting device (e.g., terminal device 40), and a receiving device (e.g., terminal device 40) may perform at least some of the operations defined in the above-mentioned LCM and the diagram of FIG. 10. The diagram shown in FIG. 10 is merely an example. The relationships between the LCM (or elements constituting the LCM) are not limited to those shown in FIG. 10.

[0223] Data collection provides training data for model training, monitoring data for model management / performance monitoring, and inference data for model inference.

[0224] Model training stores the trained / updated model in model storage.

[0225] Model management / performance monitoring controls model training (e.g., controls model maintenance and / or updates) and model inference (e.g., performs at least one of model activation, model deactivation, model selection, model switching, and model fallback).

[0226] Model storage distributes or transfers trained / updated models for model inference.

[0227] Model inference notifies model management / performance monitoring of the output from the inference.

[0228] <<4. Operation of the Communication System>> Based on the above, the operation of the communication system 1 related to LCM (Life-cycle-management) will be described. Note that the term "LCM" that appears in the following description can be replaced with "AI / ML model management."

[0229] A communication device (hereinafter referred to as a first communication device) included in the communication system 1 is configured to be capable of wireless communication with another communication device (hereinafter referred to as a second communication device).

[0230] Here, the first communication device and the second communication device may be a base station 20, a relay station 30, or a terminal device 40. For example, the first communication device may be a base station 20 and the second communication device may be a terminal device 40. Alternatively, the first communication device may be a terminal device 40 and the second communication device may be a base station 20. Alternatively, the first communication device may be a terminal device 40 and the second communication device may be another terminal device 40. Alternatively, the first communication device may be a base station 20 and the second communication device may be another base station 20. Note that the first communication device and the second communication device are not limited to the base station 20 and / or the terminal device 40. At least one of the first communication device and the second communication device may be a relay station 30 or a management device 10. Of course, at least one of the first communication device and the second communication device may be a server device connected to the Internet or another communication device.

[0231] The wireless communication between the first communication device and the second communication device may be cellular communication. For example, the wireless communication between the first communication device and the second communication device may be uplink communication in which the terminal device 40 is a transmitting device and the base station 20 is a receiving device, downlink communication in which the base station 20 is a transmitting device and the terminal device 40 is a receiving device, or sidelink communication in which the terminal device 40 is a transmitting device and another terminal device 40 is a receiving device.

[0232] In this embodiment, the first communication device transmits, to the second communication device, information regarding an AI / ML model to be applied to at least one of the processes shown in (P1) to (P4) below (first transmission process, first reception process, second transmission process, and second reception process).

[0233] (P1) Transmission processing of the first communication device regarding a wireless signal transmitted from the first communication device to the second communication device (first transmission processing) (P2) Reception processing of the second communication device regarding a wireless signal transmitted from the first communication device to the second communication device (first reception processing) (P3) Transmission processing of the second communication device regarding a wireless signal transmitted from the second communication device to the first communication device (second transmission processing) (P4) Reception processing of the first communication device regarding a wireless signal transmitted from the second communication device to the first communication device (second reception processing)

[0234] The transmission of information related to the AI / ML model may be performed by a transmitting unit of the communication device. The transmission of information related to the AI / ML model may be performed by a control unit of the communication device controlling the transmitting unit. For example, the transmission of information related to the AI / ML model may be performed by at least one of the transmitting unit 234 of the base station 20, the transmitting unit 334 of the relay station 30, and the transmitting unit 434 of the terminal device 40. Of course, the transmission of information related to the AI / ML model may be performed by the management device 10 or a server device on the Internet.

[0235] The second communication device acquires information about the AI / ML model from the first communication device. Then, the second communication device uses or manages the AI / ML model based on the information about the AI / ML model. For example, assume that the first communication device is the controller of the LCM and the second communication device is the control target of the LCM. In this case, the second communication device may execute processing related to signal processing (first reception processing or second transmission processing) of the second communication device based on the information about the AI / ML model. Also assume that the second communication device is the controller of the LCM and the first communication device is the control target of the LCM. In this case, the second communication device may execute LCM related to signal processing (first transmission processing or second reception processing) of the first communication device based on the information about the AI / ML model.

[0236] The acquisition of information related to the AI / ML model may be performed by an acquisition unit of the communication device. The acquisition of information related to the AI / ML model may be performed by a control unit of the communication device controlling the acquisition unit. For example, the acquisition of information related to the AI / ML model may be performed by at least one of the acquisition unit 231 of the base station 20, the acquisition unit 331 of the relay station 30, and the acquisition unit 431 of the terminal device 40. Of course, the acquisition of information related to the AI / ML model may be performed by the management device 10 or a server device on the Internet.

[0237] In the above and below explanations, a communication device that performs a transmission process (first transmission process / second transmission process) may be referred to as a transmitting device, and a communication device that performs a reception process (first reception process / second reception process) may be referred to as a receiving device.

[0238] Here, the information about the AI / ML model may be information about the LCM (information about the management of the AI / ML model). Hereinafter, the operation of the communication system 1 will be described assuming that the information about the AI / ML model is information about the LCM (information about the management of the AI / ML model).

[0239] <4-1. Controlling Body of AI / ML Model Management> First, the controlling body of LCM (AI / ML model management) will be explained.

[0240] The control entity of the LCM may be the first communication device or the second communication device. In this case, the control entity of the LCM may be the communication device that serves as the transmitting device of the first communication device and the second communication device, or the communication device that serves as the receiving device of the first communication device and the second communication device. Furthermore, the control entity of the LCM may be both the first communication device and the second communication device.

[0241] The control entity of the LCM may be a communication device (hereinafter referred to as a communication control device) that controls at least one of the transmitting device and the receiving device. For example, in the case of sidelink communication in which a terminal device 40 is a transmitting device and another terminal device 40 is a receiving device, the control entity of the LCM may be a base station 20 that controls the sidelink communication. Note that the communication between the transmitting device and the receiving device is not limited to sidelink communication. The communication between the transmitting device and the receiving device may be uplink communication or downlink communication. Furthermore, the communication control device that controls the LCM is not limited to the base station 20. For example, the communication control device may be a management device 10, a relay station 30, or a server device on the Internet. The communication control device may also be a terminal device 40. For example, the communication control device may be a primary terminal (master terminal) in which at least one of the transmitting device and the receiving device is a secondary terminal (slave terminal) (for example, a primary terminal device 40 (master terminal device 40) that controls sidelink communication between secondary terminals (slave terminals)).

[0242] <4-1-1. Specific examples of LCM control entities> Wireless communication to which the AI / ML model is applied (wireless communication between a first communication device and a second communication device (or processing related thereto)) may be uplink communication (or processing related thereto) in which the terminal device 40 is a transmitting device and the base station 20 is a receiving device, or may be downlink communication (or processing related thereto) in which the base station 20 is a transmitting device and the terminal device 40 is a receiving device. The control entity of LCM in uplink / downlink communication may be any of the following (A1-1) to (A1-3).

[0243] (A1-1) Base station 20 (A1-2) Terminal device 40 (A1-3) Both base station 20 and terminal device 40

[0244] In addition, when both the base station 20 and the terminal device 40 are the control entities (case (A1-3) above), the base station 20 and the terminal device 40 may control the LCM in cooperation with each other, or the base station 20 and the terminal device 40 may each control the LCM independently. In addition, the control entity of the LCM is not limited to the base station 20 and / or the terminal device 40. The control entity of the LCM in uplink / downlink communication may be a communication control device (for example, the management device 10 or a server device on the Internet) that controls the base station 20 and / or the terminal device 40.

[0245] Furthermore, the wireless communication between the first communication device and the second communication device may be sidelink communication in which the terminal device 40 is a sidelink data transmitter and another terminal device 40 is a sidelink data receiver. In this case, the control entity of the LCM may be any of the following (A2-1) to (A2-3).

[0246] (A2-1) A communication control device that controls at least one of a transmitting device and a receiving device. (A2-2) A terminal device 40 that serves as a transmitting device. (A2-3) A terminal device 40 that serves as a receiving device. (A2-4) Both the terminal device 40 that serves as a transmitting device and the terminal device 40 that serves as a receiving device.

[0247] Here, the communication control device of (A2-1) may be a base station 20 that controls sidelink communication between a transmitting device and a receiving device, or may be a primary terminal (master terminal) that treats at least one of the transmitting device and the receiving device as a secondary terminal (slave terminal). Furthermore, when both the terminal device 40 that serves as the transmitting device and the terminal device 40 that serves as the receiving device are the control subjects (as in the case of (A2-4) above), the terminal device 40 that serves as the transmitting device and the terminal device 40 that serves as the receiving device may control the LCM in cooperation with each other, or the terminal device 40 that serves as the transmitting device and the terminal device 40 that serves as the receiving device may each control the LCM independently.

[0248] The LCM diagram shown in Fig. 10 may be implemented by either or both of the first and second communication devices. In other words, either the first and second communication devices may implement at least some of the elements (processes / methods / procedures / functions) shown in (M1) to (M25) above and the operations defined in the diagram shown in Fig. 10.

[0249] <4-1-2. Determining the Control Body of the LCM> The communication system 1 may determine (determine) the control body of the LCM.

[0250] The determination of the LCM control entity may be performed by at least one of the first communication device and the second communication device. For example, the communication device serving as a transmitter out of the first communication device and the second communication device may determine the LCM control entity, or the communication device serving as a receiving device may determine the LCM control entity. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the base station 20 may determine the LCM control entity, or the terminal device 40 may determine the LCM control entity. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), the terminal device 40 serving as a transmitter may determine the LCM control entity, or the terminal device 40 serving as a receiving device may determine the LCM control entity.

[0251] Furthermore, both the first communication device and the second communication device may determine the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), both the base station 20 and the terminal device 40 may determine the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), both the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device may determine the control entity of the LCM.

[0252] Furthermore, a third device different from the transmitting device and the receiving device may determine the control entity of the LCM. For example, a communication control device that controls at least one of the transmitting device and the receiving device may determine the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), a device constituting the core network (e.g., the management device 10) may determine the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), another device within the network coverage (the base station 20 or the primary terminal device 40 (master terminal device 40)) may determine the control entity of the LCM.

[0253] Hereinafter, the device that determines (discriminates) the control entity of the LCM may be referred to as the determining device. As described above, the determining device may be either the first communication device or the second communication device, or may be both. Furthermore, the determining device may be a communication device other than the first communication device and the second communication device.

[0254] If the determining device is the base station 20, the determination of the control entity of the LCM may be performed by the determining unit 233 of the base station 20. If the determining device is the relay station 30, the determination of the control entity of the LCM may be performed by the determining unit 333 of the relay station 30. If the determining device is the terminal device 40, the determination of the control entity of the LCM may be performed by the determining unit 433 of the terminal device 40. Of course, the determining device is not limited to the base station 20, the relay station 30, or the terminal device 40. The determining device may be the management device 10 or a server device on the Internet.

[0255] The determination device may determine (discriminate) the control entity of the LCM based on at least one of the following determination methods (B1) to (B5): The means for determining the control entity of the LCM will be described below.

[0256] (B1) Determination Based on Specifications The determination device may determine the control entity of the LCM based on specifications (e.g., rules shared in advance between communication devices). The specifications here may be technical standards defined by 3GPP (registered trademark). If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the determination device may determine one or both of the base station 20 and the terminal device 40 as the control entities of the LCM based on the specifications. Furthermore, if the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), the determination device may determine one or both of the terminal device 40 serving as a transmitting device and a receiving device as the control entities of the LCM based on the specifications.

[0257] (B2) Determination Based on Configuration Information The determining device may determine the control entity of the LCM based on configuration information stored in advance (for example, information pre-configured in a storage unit of a communication device). Here, the information pre-configured in the determining device may be information stored in a storage unit of the determining device when the determining device is shipped from a factory. Note that the pre-configured LCMs do not necessarily have to be all LCMs. The pre-configured LCMs may be only some of the LCMs (for example, some of the above-mentioned (M1) to (M25)).

[0258] (B3) Determination Based on Control Information The determination device may determine the controller of the LCM based on control information (control information including information about the controller of the LCM) received from another communication device. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the base station 20 may determine the controller of the LCM based on control information received from the terminal device 40, or the terminal device 40 may determine the controller of the LCM based on control information received from the base station 20. Furthermore, if the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), one or both of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device may determine the controller of the LCM based on control information notified between the terminal devices 40. The control information here may be at least one of an RRC message, a MAC CE, and a DCI.

[0259] (B4) Determination Based on Priority A priority may be set to determine which of the AI / ML models of the first communication device and the second communication device should be used with priority. The determination device may then determine, from the first communication device and the second communication device, the communication device having the AI / ML model with the higher priority as the control entity of the LCM. The determination of the control entity of model transfer will be described as an example.

[0260] For example, suppose a rule is established that an AI / ML model of a communication device that has an already trained AI / ML model is preferentially used. In this case, the determination device may determine, from the first communication device and the second communication device, the communication device that has the trained AI / ML model as the control subject of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the communication device that has the trained AI / ML model from the base station 20 or the terminal device 40 may be determined to be the control subject of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), the terminal device 40 that has the trained AI / ML model from the terminal device 40 that serves as the transmitting device or the terminal device 40 that serves as the receiving device may be determined to be the control subject of the LCM. The communication device determined as the controlling entity of the LCM (the communication device that possesses the trained AI / ML model) may transfer the trained AI / ML model to a communication device that does not possess the model.

[0261] For example, suppose a rule is established that prioritizes the use of an AI / ML model of a communication device that possesses a trained AI / ML model of an AI / ML model (or functionality) supported by both a first communication device and a second communication device. In this case, the determination device may determine the AI / ML model (or functionality) supported by both the first communication device and the second communication device based on the capability information of the first communication device and the second communication device. Then, the determination device may determine, from the first communication device and the second communication device, the communication device that possesses the trained AI / ML model of the determined AI / ML model (or functionality) as the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the communication device (or the base station 20 or the terminal device 40) that possesses the trained AI / ML model may be determined as the control entity of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device, the terminal device 40 that possesses the trained AI / ML model may be determined as the control entity of the LCM. The communication device determined as the control entity of the LCM (the communication device that possesses the trained AI / ML model) may transfer the trained AI / ML model to a communication device that does not possess the model.

[0262] (B5) Determination Method Based on Model Type The determination device may determine the control entity of the LCM based on the type of AI / ML model applied to wireless communication. The type of AI / ML model may include at least one of a one-sided model and a two-sided model.

[0263] The one-sided model is a case where the AI / ML model is applied to either the first communication device or the second communication device. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), in the one-sided model, the AI / ML model is applied to either the base station 20 or the terminal device 40. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), in the one-sided model, the AI / ML model is applied to either the terminal device 40 that serves as a transmitting device or the terminal device 40 that serves as a receiving device. The one-sided model can be rephrased as a one-sided AI / ML model.

[0264] In the case of a one-sided model, the communication device that has the AI / ML model out of the first communication device and the second communication device may be the control subject of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), the communication device that has the AI / ML model out of the base station 20 and the terminal device 40 may be the control subject of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), the communication device that has the AI / ML model out of the terminal device 40 that is the transmitting device and the terminal device 40 that is the receiving device may be the control subject of the LCM.

[0265] The two-sided model is a case where the AI / ML model is applied to both the first communication device and the second communication device. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), in the two-sided model, the AI / ML model is applied to both the base station 20 and the terminal device 40. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), in the two-sided model, the AI / ML model is applied to both the terminal device 40 that serves as the transmitting device and the terminal device 40 that serves as the receiving device. The two-sided model can be rephrased as a two-sided AI / ML model.

[0266] In the case of a two-side model, of the first communication device and the second communication device, the communication device that has the AI / ML model may be the control subject of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), either the base station 20 or the terminal device 40 may be the control subject of the LCM, or both the base station 20 and the terminal device 40 may be the control subjects of the LCM. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), either the terminal device 40 serving as a transmitting device or the terminal device 40 serving as a receiving device may be the control subject of the LCM, or both the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device may be the control subjects of the LCM.

[0267] <4-1-3. When one of the communication devices becomes the control subject of the LCM> First, the operation of the control subject of the LCM when either the first communication device or the second communication device becomes the control subject of the LCM will be described.

[0268] The LCM control entity performs control related to the application of the AI / ML model (hereinafter also referred to as LCM control). For example, either the first communication device or the second communication device becomes the LCM control entity and performs LCM control of the other communication device (hereinafter also referred to as the controlled device). For example, if the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), one of the base station 20 and the terminal device 40 becomes the LCM control entity and performs LCM control of the other communication device. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device becomes the LCM control entity and performs LCM control of the other communication device.

[0269] Specifically, the control entity of the LCM may execute at least one of the processes shown in (C1) to (C10) below.

[0270] (C1) Model Transfer When LCM control is model transfer, the control entity of the LCM transmits data of the AI / ML model used in the transmission process or the reception process as information about the AI / ML model to a communication device to be controlled (e.g., at least one of a first communication device and a second communication device). For example, assume that the control entity of the LCM is the first communication device. In this case, the first communication device transmits data of the AI / ML model used in at least one of the above-mentioned first reception process and the above-mentioned second transmission process to the second communication device. The communication device to be controlled (e.g., the second communication device) uses the received data of the AI / ML model to execute at least one of the first reception process and the second transmission process.

[0271] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and that the LCM is controlled by the base station 20. In this case, the base station 20 transmits the AI / ML model data held by the base station 20 to the terminal device 40 before or during transmission of downlink data, or before receiving uplink data. The terminal device 40 uses the received AI / ML model data directly or after fine tuning it, for receiving downlink data or transmitting uplink data.

[0272] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and that the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits the AI / ML model data held by the terminal device 40 to the base station 20 before receiving downlink data or before or during transmission of uplink data. The base station 20 uses the received AI / ML model data directly or after fine tuning it for transmitting downlink data or receiving uplink data.

[0273] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as a transmitting device. In this case, the terminal device 40 serving as a transmitting device transmits data of the AI / ML model held by the terminal device 40 serving as a transmitting device to the terminal device 40 serving as a receiving device before or during transmission of sidelink data. The terminal device 40 serving as a receiving device uses the received data of the AI / ML model, either directly or after fine tuning, to receive the sidelink data.

[0274] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device transmits data of the AI / ML model held by the terminal device 40 serving as a transmitting device to the terminal device 40 serving as a receiving device before or during transmission of sidelink data. The terminal device 40 serving as a receiving device uses the received data of the AI / ML model, either directly or after fine tuning, to receive sidelink data.

[0275] The AI / ML model data transmitted by the communication device that controls the LCM does not necessarily have to be data that the communication device being controlled can directly use for its own processing. For example, suppose the control device of the LCM is a first communication device. In this case, the first communication device may transmit AI / ML model data used in the processing performed by the first communication device (at least one of the first transmission processing and the second reception processing described above) rather than AI / ML model data directly used in the processing performed by the second communication device (at least one of the first reception processing and the second transmission processing described above). In this case, the second communication device may generate an AI / ML model to be used by itself based on the AI / ML model data received from the first communication device.

[0276] (C2) Data Collection When the LCM control is data collection, the control entity of the LCM transmits control information instructing execution of data collection as information related to the AI / ML model to a communication device to be controlled (e.g., at least one of the first communication device and the second communication device). For example, the control entity of the LCM transmits control information instructing the communication device to be controlled to collect data for model inference and / or model training. The communication device to be controlled executes data collection based on the control information.

[0277] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing the execution of data collection to the terminal device 40. The terminal device 40 executes data collection based on the received control information.

[0278] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information instructing the base station 20 to execute data collection. The base station 20 executes data collection based on the received control information.

[0279] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a transmitting device. In this case, the terminal device 40 serving as a transmitting device transmits control information instructing the terminal device 40 serving as a receiving device to execute data collection. The terminal device 40 serving as a receiving device executes data collection based on the received control information.

[0280] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device transmits control information instructing the execution of data collection to the terminal device 40 serving as a transmitting device. The terminal device 40 serving as a transmitting device executes data collection based on the received control information.

[0281] (C3) Functionality Identification When LCM control is functionality identification, the LCM control entity notifies the communication device to be controlled (e.g., at least one of the first communication device and the second communication device) of information on the functionality to which the AI / ML model is applied, as information on the AI / ML model. Here, the information on the functionality to which the AI / ML model is applied may be the ID of the functionality (including a list of IDs). The communication device to be controlled determines whether to apply the AI / ML model to the functionality based on the information on the functionality to which the AI / ML model is applied.

[0282] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 notifies the terminal device 40 of information related to the functionality to which the AI / ML model is applied. Based on the received information, the terminal device 40 determines whether to apply the AI / ML model to the functionality related to the notification.

[0283] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 notifies the base station 20 of information related to the functionality to which the AI / ML model is applied. Based on the received information, the base station 20 determines whether to apply the AI / ML model to the functionality related to the notification.

[0284] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a transmitting device. In this case, the terminal device 40 serving as a transmitting device notifies the terminal device 40 serving as a receiving device of information related to functionality to which the AI / ML model is applied. Based on the received information, the terminal device 40 serving as a receiving device determines whether to apply the AI / ML model to the functionality related to the notification.

[0285] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device notifies the terminal device 40 serving as a transmitting device of information regarding functionality to which the AI / ML model is applied. The terminal device 40 serving as a transmitting device determines, based on the received information, whether to apply the AI / ML model to the functionality related to the notification.

[0286] As described above, the communication device to be controlled determines whether to apply an AI / ML model to the functionality related to the notification. In this case, the communication device to be controlled may always apply the AI / ML model to the functionality related to the notification. Alternatively, the communication device to be controlled may apply the AI / ML model to the functionality related to the notification when a predetermined condition is satisfied. For example, the communication device to be controlled may determine whether to apply the AI / ML model by combining a functionality identification operation and a model activation operation. For example, the communication device to be controlled may apply the AI / ML model to the functionality when an AI / ML model applicable to the functionality related to the notification is activated by the control entity of the LCM.

[0287] (C4) Model Identification When LCM control is model identification, the LCM control entity notifies the communication device to be controlled (e.g., at least one of the first communication device and the second communication device) of information on the AI / ML model applied by the communication device to be controlled. Here, the information on the AI / ML model applied by the communication device to be controlled may be the ID (including a list of IDs) of the AI / ML model. Based on the received information, the communication device to be controlled determines whether to apply the AI / ML model to the process it executes (e.g., transmission process and / or reception process).

[0288] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 notifies the terminal device 40 of information related to the AI / ML model applied by the terminal device 40. Based on the received information, the terminal device 40 determines whether to apply the AI / ML model to the processing that it itself executes.

[0289] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 notifies the base station 20 of information related to the AI / ML model applied by the base station 20. Based on the received information, the base station 20 determines whether to apply the AI / ML model to the processing that it itself executes.

[0290] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device notifies the terminal device 40 serving as the receiving device of information regarding the AI / ML model applied by the terminal device 40 serving as the receiving device. The terminal device 40 serving as the receiving device determines whether to apply the AI / ML model to the processing it itself executes based on the received information.

[0291] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device notifies the terminal device 40 serving as a transmitting device of information regarding the AI / ML model applied by the terminal device 40 serving as a transmitting device. The terminal device 40 serving as a transmitting device determines whether to apply the AI / ML model to the processing it itself executes based on the received information.

[0292] As described above, when a communication device to be controlled receives a notification from the control entity of the LCM, the communication device determines whether to apply the AI / ML model to the process that the communication device itself executes. At this time, the communication device to be controlled may always apply the AI / ML model related to the notification to the process that the communication device itself executes. Furthermore, after receiving a notification from the control entity of the LCM, the communication device to be controlled may apply the AI / ML model related to the notification if a predetermined condition is satisfied. For example, the communication device to be controlled may determine whether to apply the AI / ML model by combining a model identification operation and a model activation operation. For example, when the AI / ML model related to the notification is activated by the control entity of the LCM, the communication device to be controlled may apply the AI / ML model to the process that the communication device itself executes.

[0293] (C5) Model Activation When the LCM control is model activation, the LCM control entity transmits control information, which is information about the AI / ML model, instructing activation of the AI / ML model used in the transmission process or the reception process to the communication device to be controlled (e.g., at least one of the first communication device and the second communication device). For example, assume that the LCM control entity is the first communication device. In this case, the first communication device transmits control information instructing activation of the AI / ML model used in at least one of the above-mentioned first reception process and the above-mentioned second transmission process to the second communication device. The communication device to be controlled (e.g., the second communication device) activates the AI / ML model related to the instruction based on the received control information.

[0294] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing activation of the AI / ML model to the terminal device 40. The terminal device 40 activates the AI / ML model related to the instruction based on the received control information.

[0295] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information instructing activation of the AI / ML model to the base station 20. Based on the received control information, the base station 20 activates the AI / ML model related to the instruction.

[0296] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing activation of the AI / ML model to the terminal device 40 serving as the receiving device. The terminal device 40 serving as the receiving device activates the AI / ML model related to the instruction based on the received control information.

[0297] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device transmits control information instructing activation of the AI / ML model to the terminal device 40 serving as a transmitting device. The terminal device 40 serving as a transmitting device activates the AI / ML model related to the instruction based on the received control information.

[0298] The control information instructing activation of the AI / ML model may include information (e.g., a timer value) that allows the communication device to be controlled to specify the timing of activation of the AI / ML model. For example, when the communication device to be controlled receives a timer value, it may start a timer for the timer value. Then, the communication device to be controlled may activate the AI / ML model at the timing specified from the information (e.g., when the timer expires). The information for specifying the timing of activation of the AI / ML model may be information indicating a period (window, duration, or period) until activation of the AI / ML model, or information indicating a cycle (periodicity or cycle) for activating the AI / ML model.

[0299] Additionally or alternatively, the control information instructing activation of the AI / ML model may include information (e.g., a timer value) for the communication device to be controlled to specify a period during which activation of the AI / ML model is valid. For example, when the communication device to be controlled receives a timer value, it may start a timer for the timer value. Then, when the valid period specified from the information expires (e.g., when the timer expires), the communication device to be controlled may deactivate the AI / ML model. Note that the information for specifying the period during which activation of the AI / ML model is valid may be indicated by a window, duration, or period, or may be information indicating the periodicity (or cycle) of the period during which activation of the AI / ML model is valid. Furthermore, the deactivation here may be a fallback of the AI / ML model, as described below.

[0300] (C6) Model Deactivation When the LCM control is model deactivation, the LCM controller transmits control information instructing the deactivation of the AI / ML model used in the transmission process or the reception process to a communication device to be controlled (e.g., a first communication device or at least one of a second communication device) as information related to the AI / ML model. For example, assume that the LCM controller is the first communication device. In this case, the first communication device transmits control information instructing the deactivation of the AI / ML model used in at least one of the first reception process and the second transmission process to a second communication device. The communication device to be controlled (e.g., a second communication device) deactivates the AI / ML model related to the instruction based on the received control information.

[0301] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing deactivation of the AI / ML model to the terminal device 40. Based on the received control information, the terminal device 40 executes deactivation of the AI / ML model related to the instruction.

[0302] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information instructing the deactivation of the AI / ML model to the base station 20. Based on the received control information, the base station 20 deactivates the AI / ML model related to the instruction.

[0303] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing deactivation of the AI / ML model to the terminal device 40 serving as the receiving device. The terminal device 40 serving as the receiving device deactivates the AI / ML model related to the instruction based on the received control information.

[0304] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the receiving device. In this case, the terminal device 40 serving as the receiving device transmits control information instructing deactivation of the AI / ML model to the terminal device 40 serving as the transmitting device. The terminal device 40 serving as the transmitting device deactivates the AI / ML model related to the instruction based on the received control information.

[0305] Note that the control information instructing deactivation of the AI / ML model may include information (e.g., a timer value) that allows a communication device to be controlled to specify the timing of deactivation of the AI / ML model. For example, when the communication device to be controlled receives a timer value, it may start a timer for the timer value. Then, the communication device to be controlled may deactivate the AI / ML model at the timing specified from the information (e.g., when the timer expires). The information for specifying the timing of deactivation of the AI / ML model may be information indicating a period (window, duration, or period) until deactivation of the AI / ML model, or information indicating a cycle (periodicity or cycle) for deactivating the AI / ML model. Furthermore, the deactivation here may be a fallback of the AI / ML model, which will be described later.

[0306] (C7) Model switching When the LCM control is model switching, the LCM control entity transmits control information instructing switching of the AI / ML model used for transmission processing or reception processing to a communication device to be controlled (e.g., at least one of the first communication device and the second communication device), as information on the AI / ML model. The communication device to be controlled switches the AI / ML model currently in use to another AI / ML model based on the received control information.

[0307] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and that the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing the terminal device 40 to switch the AI / ML model. Based on the received control information, the terminal device 40 switches the AI / ML model currently in use to another AI / ML model.

[0308] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and that the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information instructing the base station 20 to switch the AI / ML model. Based on the received control information, the base station 20 switches the AI / ML model currently in use to another AI / ML model.

[0309] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing switching of the AI / ML model to the terminal device 40 serving as the receiving device. Based on the received control information, the terminal device 40 serving as the receiving device switches the currently used AI / ML model to another AI / ML model.

[0310] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the receiving device. In this case, the terminal device 40 serving as the receiving device transmits control information instructing switching of the AI / ML model to the terminal device 40 serving as the transmitting device. Based on the received control information, the terminal device 40 serving as the transmitting device switches the currently used AI / ML model to another AI / ML model.

[0311] It should be noted that the model switching operation may be realized by a combination of a model activation operation and a model deactivation operation.

[0312] Furthermore, the communication device to be controlled may be configured to execute a model switching operation if another activated AI / ML model exists when the control information for model switching is received. Furthermore, the communication device to be controlled may not execute a model switching operation if another activated AI / ML model does not exist when the control information for model switching is received. If the communication device to be controlled does not execute a model switching operation, it may notify the control entity of the LCM that the model switching operation has not been executed.

[0313] Additionally or alternatively, the control information instructing switching of the AI / ML model used in the transmission process or the reception process may include information indicating the timing of switching the AI / ML model (e.g., subframe, radio frame, SFN, slot, symbol). The information indicating the timing of switching the AI / ML model may include information indicating a period from reception of the control information to the timing of switching the AI / ML model. For example, if the timing of receiving the control information is n (e.g., nth subframe, nth radio frame, nth SFN, nth slot, nth symbol, where n is an integer), the timing of switching the AI / ML model may be represented by n+k (e.g., n+kth subframe, n+kth radio frame, n+kth SFN, n+kth slot, n+kth symbol, where n and k are integers). The period from reception of the control information to the timing of switching the AI / ML model may be represented by k.

[0314] (C8) Model Fallback When LCM control is model fallback, the control entity of the LCM transmits control information, which is information about the AI / ML model, instructing the fallback of the AI / ML model used in the transmission process or the reception process to a communication device to be controlled (e.g., a first communication device or a second communication device). For example, assume that the control entity of the LCM is the first communication device. In this case, the first communication device transmits control information to the second communication device to cause at least one of the above-mentioned first reception process and the above-mentioned second transmission process to fall back from a process using the AI / ML model to a process not using the AI / ML model. Based on the received control information, the communication device to be controlled (e.g., the second communication device) falls back from the AI / ML model-applied process to a process not using the AI / ML model. For example, the second communication device falls back at least one of the first receiving process and the second transmitting process from a process using the AI / ML model to a process not using the AI / ML model.

[0315] In the following description, processing that does not use an AI / ML model may be referred to as conventional processing or conventional signal processing. Alternatively, processing that does not use an AI / ML model may be referred to as non-AI / ML-based processing. Note that processing that does not use an AI / ML model is not necessarily limited to existing signal processing. The terms "conventional processing" or "conventional signal processing" that appear in the following description may be replaced with "processing that does not use an AI / ML model."

[0316] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing a fallback of the AI / ML model to the terminal device 40. Based on the received control information, the terminal device 40 executes a fallback of the AI / ML model application processing to conventional processing.

[0317] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information instructing a fallback of the AI / ML model to the base station 20. Based on the received control information, the base station 20 executes a fallback of the AI / ML model application processing to conventional processing.

[0318] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing a fallback of the AI / ML model to the terminal device 40 serving as the receiving device. Based on the received control information, the terminal device 40 serving as the receiving device performs a fallback to conventional processing of the AI / ML model application processing.

[0319] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the receiving device. In this case, the terminal device 40 serving as the receiving device transmits control information instructing a fallback of the AI / ML model to the terminal device 40 serving as the transmitting device. Based on the received control information, the terminal device 40 serving as the transmitting device performs a fallback to conventional processing of the AI / ML model application processing.

[0320] The control entity of the LCM may instruct fallback of only some of the processes to which the AI / ML model is applied (e.g., processing of functionality). For example, assume that the second communication device has multiple functionalities related to at least one of the above-mentioned first receiving process and the above-mentioned second transmitting process. The first communication device may transmit, as control information (information related to the AI / ML model), information to the second communication device for causing the processing of some of the multiple functionalities to fallback from processing using the AI / ML model to processing not using the AI / ML model. The control entity of the LCM may instruct fallback of all of the processes.

[0321] When a communication device to be controlled receives control information from the control entity of the LCM, it may perform fallback only for some of the processes to which the AI / ML model is applied (e.g., functionality processing), or it may perform fallback for all processes.

[0322] Note that the control information instructing the fallback of the AI / ML model may include information (e.g., a timer value) that allows the communication device to be controlled to specify the timing of the fallback of the AI / ML model. For example, when the communication device to be controlled receives a timer value, the communication device to be controlled may start a timer for the timer value. Then, the communication device to be controlled may execute the fallback of the AI / ML model at the timing specified from the information (e.g., when the timer expires).

[0323] Furthermore, the fallback of the AI / ML model may be a process of executing fallback to a default AI / ML model. For example, a terminal device that has received a fallback notification of the AI / ML model may change the AI / ML model used in the transmission process or the reception process from the currently applied AI / ML model to a preset default AI / ML model.

[0324] Additionally or alternatively, the control information instructing the fallback of the AI / ML model used in the transmission process or the reception process may include information (e.g., subframe, radio frame, SFN, slot, symbol) indicating the timing of performing the fallback of the AI / ML model. The information indicating the timing of performing the fallback of the AI / ML model may include information indicating the period from the reception of the control information to the timing of performing the fallback of the AI / ML model. For example, if the reception of the control information is n (e.g., nth subframe, nth radio frame, nth SFN, nth slot, nth symbol, where n is an integer), the timing of performing the fallback of the AI / ML model may be represented by n+k (e.g., n+kth subframe, n+kth radio frame, n+kth SFN, n+kth slot, n+kth symbol, where n and k are integers). The period from the reception of the control information to the timing of performing the fallback of the AI / ML model may be represented by k.

[0325] (C9) Model monitoring When the LCM control is model monitoring, the control entity of the LCM transmits control information instructing the execution of monitoring of the AI / ML model as information about the AI / ML model to a communication device to be controlled (for example, at least one of the first communication device and the second communication device). Upon receiving the control information, the communication device to be controlled executes the monitoring operation of the AI / ML model.

[0326] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information instructing the execution of monitoring of the AI / ML model to the terminal device 40. Upon receiving the control information, the terminal device 40 executes the monitoring operation of the AI / ML model.

[0327] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information to the base station 20 instructing the execution of monitoring of the AI / ML model. Upon receiving the control information, the base station 20 executes the monitoring operation of the AI / ML model.

[0328] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing the execution of monitoring of the AI / ML model to the terminal device 40 serving as the receiving device. Upon receiving the control information, the terminal device 40 serving as the receiving device executes the monitoring operation of the AI / ML model.

[0329] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by a terminal device 40 serving as a receiving device. In this case, the terminal device 40 serving as a receiving device transmits control information instructing the execution of monitoring of the AI / ML model to the terminal device 40 serving as a transmitting device. Upon receiving the control information, the terminal device 40 serving as a transmitting device executes monitoring operations of the AI / ML model.

[0330] Note that a communication device to be controlled may perform performance measurement of the currently applied AI / ML model as a monitoring operation of the AI / ML model. The performance measurement of the AI / ML model may be performed for a predetermined period or a predetermined cycle. That is, the control information instructing monitoring of the AI / ML model described above may be information indicating a period (window, duration, or period) during which the performance measurement of the AI / ML model is performed, or information indicating a cycle (periodicity or cycle) during which the performance measurement of the AI / ML model is performed. Furthermore, the control information instructing monitoring of the AI / ML model may be a combination of these.

[0331] (C10) Model Update When the LCM control is a model update, the control entity of the LCM transmits control information instructing the execution of an AI / ML model update as information related to the AI / ML model to a communication device to be controlled (e.g., at least one of the first communication device and the second communication device). When the communication device to be controlled receives the control information, it executes an update operation of the AI / ML model. For example, when the communication device to be controlled receives the control information, it executes retraining of the AI / ML model currently in use.

[0332] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and that the LCM is controlled by the base station 20. In this case, the base station 20 transmits control information to the terminal device 40 to instruct the execution of an update of the AI / ML model. Upon receiving the control information, the terminal device 40 executes the update operation of the AI / ML model.

[0333] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 transmits control information to the base station 20 instructing the base station 20 to update the AI / ML model. Upon receiving the control information, the base station 20 executes the update operation of the AI / ML model.

[0334] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the transmitting device. In this case, the terminal device 40 serving as the transmitting device transmits control information instructing the execution of an update of the AI / ML model to the terminal device 40 serving as the receiving device. Upon receiving the control information, the terminal device 40 serving as the receiving device executes the update operation of the AI / ML model.

[0335] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by the terminal device 40 serving as the receiving device. In this case, the terminal device 40 serving as the receiving device transmits control information instructing the execution of an update of the AI / ML model to the terminal device 40 serving as the transmitting device. Upon receiving the control information, the terminal device 40 serving as the transmitting device executes the update operation of the AI / ML model.

[0336] Note that a communication device to be controlled cannot use an AI / ML model during an update operation of the AI / ML model. Therefore, when a communication device to be controlled executes an update operation of the AI / ML model, the communication device to be controlled may fall back to a conventional process that does not apply the AI / ML model for the currently executing process. Alternatively, when a communication device to be controlled executes an update operation of the AI / ML model, the communication device to be controlled may switch the AI / ML model involved in the update operation to another AI / ML model.

[0337] <4-1-4. Cases in which both communication devices are the control subjects of the LCM> As described above, both the first communication device and the second communication device may be the control subjects of the LCM. For example, when the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), both the base station 20 and the terminal device 40 may be the control subjects of the LCM. When the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), both the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device may be the control subjects of the LCM.

[0338] When both the first communication device and the second communication device are to be the control subjects of the LCM, the communication devices may coordinate in advance to determine which of the first communication device and the second communication device will be the control subject. For example, either the first communication device or the second communication device may transmit information about the control subject to the other communication device as information about the AI / ML model. If the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), either the base station 20 or the terminal device 40 may transmit information about the control subject to the other communication device. Furthermore, if the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), either the terminal device 40 serving as a transmitter or the terminal device 40 serving as a receiver may transmit information about the control subject to the other communication device.

[0339] When both the first communication device and the second communication device are to be the control subjects of the LCM, it may be determined for each LCM (for example, for each of (M1) to (M25)) which communication device will be the control subject. The means for determining which communication device will be the control subject for each LCM may be either Determination Means 1 or Determination Means 2 described below.

[0340] (Determination means 1) The determination device determines the control entity of the LCM based on static information. For example, the first communication device and the second communication device may determine the control entity of the LCM based on specifications (e.g., rules shared in advance between the communication devices).

[0341] (Determination means 2) The determination device determines which LCM control entity will be controlled based on semi-static information. For example, one of the first and second communication devices may determine in advance which of the multiple LCMs it will control and which will be controlled by the other communication device. Then, the one communication device may notify the other communication device which of the multiple LCMs the other communication device will control.

[0342] The determining device may be either the first communication device or the second communication device, or may be both of them. Alternatively, the determining device may be a communication device other than the first communication device and the second communication device.

[0343] When both the first communication device and the second communication device are the control subjects of the LCM, some of the control included in the LCM may be executed by both the first communication device and the second communication device. For example, both the first communication device and the second communication device may execute model training. In this case, both the first communication device and the second communication device may execute training of an AI / ML model and use the trained model.

[0344] <4-1-5. Others> LCM control (including the LCMs described above or below) may be executed by the management device 10. For example, LCM control may be executed by a network function (LCM-related network function) included in the core network. The LCM-related network function is a network function that provides the functionality of LCM-related control. The LCM-related network function has functions such as providing information required for the controls or functions such as (M1) to (M25) described above.

[0345] FIG. 9 shows an example of a network configuration including an LCM-related network function. The LCM-related network function may be included in a server (e.g., MEC server 552) connected to the UPF 521. The LCM-related network function may also be included in a server (e.g., MEC server 553) connected to the base station 20 ((R)AN 530). The LCM-related network function may also be defined as one of the network functions. This network function (LCM-related network function 554 shown in FIG. 9) may then be included in the core network as a new network function. The LCM-related network function may also be included in an existing network function. For example, the functionality of the LCM-related network function may be included in the MTLF 551 shown in FIG. 9. The LCM-related network function may exist in one or more locations.

[0346] Alternatively, the LCM control may be performed by the management device 10, the base station 20, the relay station 30, the terminal device 40, or another communication device (for example, a server device on the Internet). Each of these communication devices can be the LCM control entity.

[0347] <4-2. Control Means of AI / ML Model Management> The control body of LCM has been explained above, and next, the control means of LCM (AI / ML model management) will be explained.

[0348] <4-2-1. Wireless Communication Using AI / ML Model> When wireless communication using an AI / ML model (hereinafter also referred to as AI communication) is performed, the LCM control entity performs control related to the application of the AI / ML model (hereinafter referred to as LCM control). The LCM control may be functionality-based LCM or model ID-based LCM. The LCM control entity may apply only either functionality-based LCM or model ID-based LCM, or may apply both in combination.

[0349] (D1) Functionality-Based LCM Functionality-based LCM refers to the management of an AI / ML model based on functionality. For example, functionality-based LCM refers to the management of an AI / ML model based on use cases and / or functions.

[0350] For example, suppose that functionality indicates communication requirements required for AI communication in a use case and / or function to which the AI / ML model is applied. In this case, the control entity of the LCM notifies the communication device to be controlled of information indicating which functionality's AI communication is to be activated. For example, the control entity of the LCM decides which functionality's AI communication is to be activated and notifies the communication device to be controlled of the ID of the functionality related to the decision (hereinafter referred to as the functionality ID).

[0351] (Transmission of Capability Information) At this time, the terminal device to be controlled may transmit capability information to the communication device that controls the LCM as information related to the AI / ML model. For example, assume that the second communication device controls the LCM and the first communication device is the control target of the LCM. At this time, the first communication device may transmit, as capability information, information indicating which of multiple functionalities related to at least one of the first transmission process and the second reception process the first communication device supports to the second communication device. Here, the capability information may be the IDs (functionality IDs) of the supported functionalities or a list of functionality IDs.

[0352] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the terminal device 40 to be controlled transmits capability information indicating which functionality it supports to the base station 20.

[0353] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 that serves as the transmitting device and the terminal device 40 that serves as the receiving device. In this case, the terminal device 40 to be controlled transmits capability information indicating which functionality it corresponds to to the terminal device 40 that controls the LCM.

[0354] (Transmission of Training Completion Information) Furthermore, a terminal device to be controlled may transmit training completion information as information about the AI / ML model to a communication device that controls the LCM. For example, assume that a second communication device controls the LCM and a first communication device is controlled by the LCM. Furthermore, assume that the AI / ML model is linked to functionality related to at least one of the first transmission process and the second reception process. In this case, the first communication device may transmit, as training completion information, information indicating which of the multiple functionality related to at least one of the first transmission process and the second reception process has completed training of the AI / ML model (whether model inference is possible) to the second communication device. Here, the training completion information may be the ID (functionality ID) of the functionality for which training of the AI / ML model has completed, or a list of functionality IDs.

[0355] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the terminal device 40 to be controlled transmits training completion information to the base station 20, indicating which AI / ML model of which functionality has completed training.

[0356] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. In this case, the terminal device 40 to be controlled transmits training completion information indicating which functionality's AI / ML model has completed training to the terminal device 40 serving as the LCM's controlling device.

[0357] (Activation) The control entity of the LCM determines which functionality's AI communication to activate based on information received from the controlled entity. For example, assume that the second communication device is the control entity of the LCM and the first communication device is the controlled entity of the LCM. The second communication device determines which functionality's AI communication to activate based on information received from the first communication device (e.g., capability information and / or training completion information).

[0358] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 determines which functionality of AI communication to activate based on information (e.g., capability information and / or training completion information) received from the terminal device 40 to be controlled. The base station 20 then notifies the terminal device 40 of information indicating the determination result (e.g., functionality ID).

[0359] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. The terminal device 40 serving as the LCM controller determines which functionality of AI communication to activate based on information received from the terminal device 40 to be controlled (e.g., capability information and / or training completion information). The terminal device 40 serving as the LCM controller then notifies the terminal device 40 to be controlled of information indicating the determination result (e.g., functionality ID).

[0360] In the case of functionality-based LCM, the communication device that controls the LCM can execute LCM control without receiving the AI / ML model list held by the communication device to be controlled. In other words, the communication device to be controlled determines which AI / ML model to use based on information notified by the communication device that controls the LCM.

[0361] (D2) Model ID-Based LCM Model ID-based LCM indicates that management of an AI / ML model is performed based on an AI / ML model.

[0362] For example, assume that logical IDs are assigned to AI / ML models that can be supported by a communication device (at least one of a first communication device and a second communication device) that performs AI communication. In this case, the control entity of the LCM notifies the communication device to be controlled of information indicating which AI / ML model's AI communication is to be activated. For example, the control entity of the LCM decides which AI / ML model to activate and notifies the communication device to be controlled of the ID of the AI / ML model related to the decision (hereinafter referred to as model ID). Note that the model ID is not limited to a logical ID. The control entity of the LCM may notify the communication device to be controlled of a physical ID individually linked to the AI / ML model instead of a logical ID.

[0363] (Transmission of Capability Information) A terminal device to be controlled may transmit capability information, as information regarding the AI / ML model, to a communication device that controls the LCM. For example, assume that a second communication device controls the LCM and a first communication device is controlled by the LCM. In this case, the first communication device may transmit, as capability information, information indicating which of multiple AI / ML models related to at least one of the first transmission process and the second reception process the first communication device supports to the second communication device. Here, the capability information may be the ID (model ID) of the compatible AI / ML model or a list of model IDs.

[0364] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the terminal device 40 to be controlled transmits capability information indicating which AI / ML model it supports to the base station 20.

[0365] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. In this case, the terminal device 40 to be controlled transmits capability information indicating which AI / ML model it supports to the terminal device 40 serving as the LCM controlling device.

[0366] (Transmission of Training Completion Information) Furthermore, a terminal device to be controlled may transmit training completion information to a communication device that controls the LCM as information related to the AI / ML model. For example, assume that a second communication device controls the LCM and a first communication device is controlled by the LCM. In this case, the first communication device may transmit, as training completion information, information indicating which AI / ML models, among multiple AI / ML models related to at least one of the first transmission process and the second reception process, have completed training (whether model inference is possible) to the second communication device. Here, the training completion information may be the ID (model ID) of the AI / ML model for which training has been completed, or a list of model IDs.

[0367] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the terminal device 40 to be controlled transmits training completion information indicating which AI / ML model has completed training to the base station 20.

[0368] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. In this case, the terminal device 40 to be controlled transmits training completion information indicating which AI / ML model has completed training to the terminal device 40 serving as the LCM controlling device.

[0369] (Activation) The controlling entity of the LCM determines which AI / ML model to activate based on information received from the controlled entity. For example, assume that the second communication device is the controlling entity of the LCM and the first communication device is the controlled entity of the LCM. The second communication device determines which AI / ML model to activate based on information received from the first communication device (e.g., capability information and / or training completion information).

[0370] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 determines which AI / ML model to activate based on information (e.g., capability information and / or training completion information) received from the terminal device 40 to be controlled. The base station 20 then notifies the terminal device 40 of information indicating the determination result (e.g., a model ID).

[0371] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. The terminal device 40 serving as the LCM controller determines which AI / ML model to activate based on information received from the terminal device 40 to be controlled (e.g., capability information and / or training completion information). The terminal device 40 serving as the LCM controller then notifies the terminal device 40 to be controlled of information indicating the determination result (e.g., a model ID).

[0372] <4-2-2. Means for Transmitting Information Related to AI / ML Model> The communication device may transmit information related to the AI / ML model (for example, control information for controlling LCM) as follows.

[0373] (E1) Unicast: The control entity of the LCM may control one control target. In this case, the control entity of the LCM may transmit information about the AI / ML model (e.g., control information for controlling the LCM) to the one control target.

[0374] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 may transmit information (control information) related to the AI / ML model to one terminal device 40.

[0375] Furthermore, it is assumed that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 may transmit information (control information) related to the AI / ML model to one base station 20.

[0376] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the LCM is controlled by one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. The terminal device 40 serving as the LCM control device may transmit information (control information) related to the AI / ML model to one of the terminal devices 40.

[0377] Alternatively, a communication control device that controls at least one of the first communication device and the second communication device may transmit information (control information) related to the AI / ML model to one of the first communication device and the second communication device. For example, a communication control device that controls at least one of the communication device that serves as a transmitter and the communication device that serves as a receiver may transmit information (control information) related to the AI / ML model to one of the transmitter and the receiver.

[0378] (E2) Group Sharing: The control entity of the LCM may control a plurality of specific control targets. In this case, the control entity of the LCM may transmit information about the AI / ML model (e.g., control information for controlling the LCM) to the plurality of specific control targets.

[0379] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the base station 20. In this case, the base station 20 may transmit information (control information) related to the AI / ML model to a specific number of terminal devices 40.

[0380] Furthermore, it is assumed that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto), and the LCM is controlled by the terminal device 40. In this case, the terminal device 40 may transmit information (control information) related to the AI / ML model to a specific plurality of base stations 20.

[0381] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto), and the control entity of the LCM is one of the terminal device 40 serving as the transmitting device and the terminal device 40 serving as the receiving device. The terminal device 40 serving as the control entity of the LCM may transmit information (control information) related to the AI / ML model to specific terminal devices 40.

[0382] Alternatively, a communication control device that controls at least one of the first communication device and the second communication device may transmit information (control information) related to the AI / ML model to both the first communication device and the second communication device. For example, a communication control device that controls at least one of the communication device that serves as a transmitter and the communication device that serves as a receiver may transmit information (control information) related to the AI / ML model to both the transmitter and the receiver.

[0383] (E3) Broadcast The control entity of the LCM may control multiple unspecified control objects. In this case, the control entity of the LCM may transmit information about the AI / ML model (e.g., control information for controlling the LCM) to multiple unspecified control objects. For example, the base station 20 may transmit information about the AI / ML model (control information) to multiple unspecified terminal devices 40, or the terminal device 40 may transmit information about the AI / ML model (control information) to multiple unspecified base stations 20. The terminal device 40 may transmit information about the AI / ML model (control information) to multiple unspecified terminal devices 40. The communication control device may transmit information about the AI / ML model (control information) to multiple unspecified communication devices including at least one of a first communication device and a second communication device.

[0384] (E4) Others In the above (E1) to (E3), the communication device that controls the LCM transmitted information about the AI / ML model. However, a communication device to be controlled may also transmit information about the AI / ML model. In this case, the communication device to be controlled may transmit information about the AI / ML model to one communication device. Furthermore, the communication device to be controlled may transmit information about the AI / ML model to multiple communication devices. In this case, the communication device to be controlled may transmit information about the AI / ML model to specific multiple communication devices, or may transmit information about the AI / ML model to unspecified multiple communication devices.

[0385] <4-2-3. Information Sharing Regarding LCM Control> When performing wireless communication using an AI / ML model, the first communication device and the second communication device need to have a common understanding of which AI / ML model or functionality LCM is to be implemented for.

[0386] Below, several examples of information sharing related to LCM control are described. Note that the examples shown in (F1) to (F4) below may be implemented independently. Alternatively, at least some of the examples shown in (F1) to (F4) below may be implemented in combination with other parts. Furthermore, at least some of the information transmitted from the first communication device to the second communication device (or information transmitted from the second communication device to the first communication device) in the examples shown in (F1) to (F4) below may be information related to the AI / ML model described above or below, or may be included in information related to the AI / ML model described above or below.

[0387] In the following description, it is assumed that a first communication device transmits information to a second communication device, but the second communication device may also transmit information to the first communication device. In this case, the first communication device and the second communication device may be a base station 20 and a terminal device 40, or a terminal device 40 and another terminal device 40. Furthermore, a third communication device (e.g., a communication control device) different from the first communication device and the second communication device may transmit information to the first communication device and / or the second communication device. In this case, the third communication device may be a management device 10 or a primary terminal device 40 (master terminal device 40).

[0388] In the following description, the term "first communication device" can be replaced with "second communication device" or "third communication device." Furthermore, the term "second communication device" can be replaced with "first communication device" or "first communication device and / or second communication device."

[0389] (F1) Information Sharing Using Model ID The first communication device notifies the second communication device of the ID (model ID) of the AI / ML model. For example, the base station 20 notifies the terminal device 40 of the model ID. Alternatively, one of the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device notifies the other terminal device 40 of the model ID. The second communication device determines the AI / ML model to use based on the notified model ID.

[0390] The first communication device may notify, as the model ID, an ID linked to the AI / ML model, or a logically assigned ID. The first communication device may notify information about the model ID as semi-static information such as system information or RRC signaling. Alternatively, the first communication device may notify information about the model ID as dynamic information such as MAC Control Element (CE), Downlink Control Information (DCI), Uplink Control Information (UCI), or Sidelink Control Information (SCI).

[0391] The second communication device may activate the AI / ML model identified by the notified model ID, or may retain the notified information (e.g., model ID information) as information about the usable AI / ML model until receiving an activation notification for the AI / ML model identified by the notified model ID.

[0392] Information notified from the first communication device to the second communication device may be, for example, the following notification information (e.g., RRC IEs (Information Elements)). The following notification information (e.g., ModelIDConfig) may further include at least a portion of information relating to the AI / ML model described above or below. Additionally or alternatively, at least a portion of the following notification information may be included in the information relating to the AI / ML model described above or below. The first communication device may notify the second communication device of at least a portion of the notification information shown below.

[0393] ModelIDConfig::= SEQUENCE { modelId CHOICE { modelID1 SEQUENCE { modelId, numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, …}, modelID2 SEQUENCE { modelId, numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, …}, …}}

[0394] Here, modelId indicates a physical or logical identifier assigned to the AI / ML model. numberOfInputNode indicates the number of input nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfOutputNode indicates the number of output nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfLayer indicates the number of layers in the AI / ML model network structure that constitutes the AI / ML model. informationOfWeight indicates the weights assigned between each node in the AI / ML model network structure that constitutes the AI / ML model.

[0395] (F2) Information Sharing Using Functionality ID The first communication device notifies the second communication device of a functionality ID. For example, the base station 20 notifies the terminal device 40 of the functionality ID. Alternatively, one of the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device notifies the other terminal device 40 of its functionality ID. The second communication device determines the AI / ML model to use based on the notified functionality ID.

[0396] The first communication device may notify, as the functionality ID, an ID linked to a functionality model, or a logically assigned ID. The first communication device may notify information about the functionality ID as semi-static information such as system information or RRC signaling. Alternatively, the first communication device may notify information about the functionality ID as dynamic information such as MAC Control Element (CE), Downlink Control Information (DCI), Uplink Control Information (UCI), or Sidelink Control Information (SCI).

[0397] The second communication device determines functionality to which the AI / ML model is to be applied based on the notified functionality ID. The second communication device may activate the AI / ML model identified by the determined functionality. Note that the second communication device may retain determination information (e.g., model ID information) as information on usable AI / ML models until it receives an activation notification for the determined AI / ML model. Alternatively, the second communication device may retain notification information (e.g., functionality ID information) until it receives an activation notification for the functionality identified by the notified functionality ID.

[0398] Information notified from the first communication device to the second communication device may be, for example, the following notification information (e.g., RRC IEs (Information Elements)). The following notification information (e.g., FunctionalityConfig) may further include at least a portion of information relating to the AI / ML model described above or below. Additionally or alternatively, at least a portion of the following notification information may be included in the information relating to the AI / ML model described above or below. The first communication device may notify the second communication device of at least a portion of the notification information shown below.

[0399] FunctionalityConfig::= SEQUENCE { Functionality CHOICE { functionality1 SEQUENCE { functionalityId, feature, requirementList, capableModelList, …}, functionality2 SEQUENCE { functionalityId, feature, requirementList, capableModelList, …},}}

[0400] Here, functionalityId indicates the physical or logical identifier assigned to the functionality, feature indicates the feature that the functionality is included in, requirementList indicates the required values ​​required for the functionality, and capableModelList indicates information on AI / ML models that can be applied to the functionality.

[0401] (F3) Information Sharing by Model Config The first communication device notifies the second communication device of RRC signaling defined for each AI / ML model. For example, the base station 20 notifies the terminal device 40 of the RRC signaling defined for each AI / ML model. Alternatively, one of the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device notifies the other terminal device 40 of the RRC signaling defined for each AI / ML model. At this time, the first communication device may perform notification using a different message, a different information field, or a different information element for each AI / ML model.

[0402] The second communication device determines the notified AI / ML model based on RRC signaling defined for each AI / ML model. The second communication device may determine the notified AI / ML model based on which message, which information field, or which information element it has received. Note that the second communication device may retain determination information (e.g., model ID information) as information on the usable AI / ML model until it receives an activation notification for the determined AI / ML model.

[0403] Information notified from the first communication device to the second communication device may be, for example, the following notification information (e.g., RRC IEs (Information Elements)). The following notification information (e.g., ModelConfigA, ModelConfigB) may further include at least a portion of information related to the AI / ML model described above or below. Additionally or instead, at least a portion of the following notification information may be included in information related to the AI / ML model described above or below. The first communication device may notify the second communication device of at least a portion of the notification information shown below. In this case, if ModelConfigA is notified, the second communication device may determine that the AI / ML model related to the notification is the AI / ML model of ModelConfigA. Furthermore, if ModelConfigB is notified, the second communication device may determine that the AI / ML model related to the notification is the AI / ML model of ModelConfigB.

[0404] ModelConfigA::= SEQUENCE { numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, …} ModelConfigB::= SEQUENCE { numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, …}

[0405] Here, modelId indicates a physical or logical identifier assigned to the AI / ML model. numberOfInputNode indicates the number of input nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfOutputNode indicates the number of output nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfLayer indicates the number of layers in the AI / ML model network structure that constitutes the AI / ML model. informationOfWeight indicates the weights assigned between each node in the AI / ML model network structure that constitutes the AI / ML model.

[0406] (F4) Information Sharing by Functionality Config The first communication device notifies the second communication device of RRC signaling defined for each functionality ID. For example, the base station 20 notifies the terminal device 40 of the RRC signaling defined for each functionality ID. Alternatively, one of the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device notifies the other terminal device 40 of the RRC signaling defined for each functionality ID. At this time, the first communication device may perform notification using a different message, a different information field, or a different information element for each functionality ID.

[0407] The second communication device determines functionality to which the AI / ML model is applied based on the notified functionality ID. The second communication device may determine the notified functionality (or AI / ML model) based on which message, which information field, or which information element it has received. The second communication device may activate the AI / ML model identified by the determined functionality. Note that the second communication device may retain determination information (e.g., model ID information) as information on usable AI / ML models until it receives an activation notification for the determined AI / ML model. Alternatively, the second communication device may retain determination information (e.g., functionality ID information) until it receives an activation notification for the determined functionality.

[0408] Information notified from the first communication device to the second communication device may be, for example, the following notification information (e.g., RRC IEs (Information Elements)). The following notification information (e.g., FunctionalityConfigA, FunctionalityConfigB) may further include at least a portion of information related to the AI / ML model described above or below. Additionally or instead, at least a portion of the following notification information may be included in information related to the AI / ML model described above or below. The first communication device may notify the second communication device of at least a portion of the notification information shown below. In this case, when FunctionalityConfigA is notified, the second communication device may determine that the functionality (or the AI / ML model) related to the notification is the functionality of FunctionalityConfigA (or the AI / ML model of FunctionalityConfigA). Furthermore, when FunctionalityConfigB is notified, the second communication device may determine that the functionality (or the AI / ML model) related to the notification is the functionality of FunctionalityConfigB (or the AI / ML model of FunctionalityConfigB).

[0409] FunctionalityConfigA::= SEQUENCE { feature, requirementList, capableModelList, …} FunctionalityConfigB::= SEQUENCE { feature, requirementList, capableModelList, …}

[0410] Here, feature indicates the feature that contains the functionality, requirementList indicates the required values ​​required for the functionality, and capableModelList indicates information on AI / ML models that can be used by the functionality.

[0411] <4-2-4. Execution Timing of LCM> Event-trigger-based control or periodic-based control may be introduced into the control of LCM (AI / ML model management).

[0412] In the following description, it is assumed that the first communication device executes LCM control, but the second communication device may execute LCM control. In this case, the first communication device may be the base station 20 or the terminal device 40. Furthermore, the LCM control may be executed by a third communication device (e.g., a communication control device) different from the first and second communication devices. In this case, the third communication device may be the management device 10 or the primary terminal device 40 (master terminal device 40).

[0413] In the following description, the term "first communication device" can be replaced with "second communication device" or "third communication device." Furthermore, the term "second communication device" or "third communication device" can be replaced with "first communication device" or "first communication device and / or second communication device."

[0414] (G1) Example of Event-Trigger-Based Control The first communication device may perform LCM control when a predetermined event occurs. For example, the first communication device may transmit information about the AI / ML model to another communication device (e.g., a second communication device and / or a third communication device) when the predetermined event occurs. Alternatively, the first communication device may perform one or more of the above-described (M1) to (M25) when the predetermined event occurs. Note that the timing when the predetermined event occurs may be when the first communication device receives a predetermined notification from another communication device. For example, the timing when the predetermined event occurs may be when the first communication device receives a predetermined notification transmitted by the other communication device when the predetermined event occurs.

[0415] The timing at which the predetermined event occurs may be at least one of the timings shown below. Note that the timings shown below are merely examples. The timing at which the predetermined event occurs is not limited to the following. Furthermore, information indicating which of the following timings or events the first communication device should apply may be provided to the first communication device from another communication device (a second communication device and / or a third communication device).

[0416] ・When AI / ML model training is completed ・When AI / ML model training starts ・When the expiration date of the AI / ML model has passed (Timer Expire, etc.) ・When it is determined that the validity of the AI / ML model is invalid ・When it is determined that the AI / ML model needs to be updated ・When the expiration date of the learning data has passed (Timer Expire, etc.) ・When an AI / ML model is downloaded ・When an AI / ML model is uploaded ・When an AI / ML model is transferred ・When an AI / ML model inference is performed ・When an AI / ML model is activated ・When an AI / ML model is deactivated ・When the AI / ML model is switched ・When the AI / ML model is fallen back to and switched to conventional processing that does not use the AI / ML model

[0417] (G2) Example of Period-Based Control The first communication device may perform LCM control when a predetermined time is reached. For example, the first communication device may transmit information about the AI / ML model to another communication device (e.g., the second communication device and / or the third communication device) when the predetermined time is reached. Additionally, the first communication device may perform one or more of the above-described steps (M1) to (M25) when the predetermined time is reached.

[0418] The timing at which the predetermined time is reached may be a regular time interval (e.g., at least one of the number of symbols, the number of slots, the number of subframes, and absolute time), or may be a set time timing (e.g., at least one of the symbol index, the slot index, the subframe index, and absolute time).

[0419] (G3) Notification Information In the event-trigger-based control and / or the periodic-based control, information notified from the first communication device to another communication device (e.g., the second communication device and / or the third communication device) may be, for example, the following notification information (e.g., RRC IEs (Information Elements)). The following notification information (e.g., LCMConfig) may further include at least a portion of information relating to the AI / ML model described above or below. Additionally or alternatively, at least a portion of the following notification information may be included in the information relating to the AI / ML model described above or below. The first communication device may notify the other communication device of at least a portion of the notification information shown below.

[0420] LCMConfig::= SEQUENCE { modelTrainingConfig SEQUENCE { onlineTrainingEnable, trainingEventTrigger, trainingPeridoicTimer, … }, modelIdentificationConfig SEQUENCE { identificationModelList, identificationEventTrigger, identificationPeriodicTimer, … }, functionalityIdentificationConfig SEQUENCE { identificationFunctionalityList, identificationEventTrigger, identificationPeriodicTimer, … }, modelTransferConfig SEQUENCE { modelId, numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, … }, modelInferenceConfig SEQUENCE { modelId, numberOfInputNode, numberOfOutputNode, numberOfLayer, informationOfWeight, … }, modelActivationConfig SEQUENCE { modelId, functionalityId, feature, requirementList, capableModelList, modelValidationTimer … },functionalityActivationConfig SEQUENCE { functionalityId, feature, requirementList, capableModelList, functionalityValidationTimer … }, modelDeactivationConfig SEQUENCE { modelId, functionalityId, feature, requirementList, capableModelList, modelValidationTimer … }, functionalityDeactivationConfig SEQUENCE { functionalityId, feature, requirementList, capableModelList, functionalityValidationTimer … }, modelSwitchingConfig SEQUENCE { modelId, functionalityId, feature, requirementList, capableModelList, modelValidationTimer … }, functionalitySwitchingConfig SEQUENCE { functionalityId, feature, requirementList, capableModelList, functionalityValidationTimer … }, modelFallbackConfig SEQUENCE { modelId, functionalityId, feature,requirementList, capableModelList, modelValidationTimer, fallbackConventionalConfiguration …}, modelMonitoringConfig SEQUENCE { modelId, functionalityId, feature, requirementList, capableModelList, monitoringEventTrigger, monitoringPeriodicTimer, …}, modelUpdateConfig SEQUENCE { modelId, functionalityId, feature, requirementList, capableModelList, updateEventTrigger, updatePeriodicTimer, …}, …},

[0421] Here, onlineTrainingEnable indicates whether online training is enabled or disabled. Here, online training may refer to a means of performing model training using training data acquired in real time. trainingEventTrigger indicates information about an event trigger that starts model training. trainingPeridoicTimer indicates information about a periodic timer that performs model training.

[0422] Furthermore, identificationModelList indicates information notifying a list of model IDs used in model identification. IdentificationFunctionalityList indicates information notifying a list of model IDs used in model identification. IdentificationEventTrigger indicates information related to an event trigger that starts model identification. IdentificationPeriodicTimer indicates information related to a periodic timer that performs model identification.

[0423] Furthermore, modelId indicates a physical or logical identifier assigned to the AI / ML model. numberOfInputNode indicates the number of input nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfOutputNode indicates the number of output nodes in the AI / ML model network structure that constitutes the AI / ML model. numberOfLayer indicates the number of layers in the AI / ML model network structure that constitutes the AI / ML model. informationOfWeight indicates the weights assigned between each node in the AI / ML model network structure that constitutes the AI / ML model.

[0424] Furthermore, functionalityId indicates the physical or logical identifier assigned to the functionality. feature indicates the feature that the functionality is included in. requirementList indicates information on the required values ​​required for the functionality. capableModelList indicates information on the AI / ML models that can be applied to the functionality. modelValidationTimer indicates information on the timer that indicates the period during which the AI / ML model can be used, or the period until it becomes unusable. functionalityValidationTimer indicates information on the timer that indicates the period until the functionality information is updated.

[0425] Furthermore, fallbackConventionalConfiguration indicates semi-static information about signal processing after fallback when falling back to conventional signal processing. monitoringEventTrigger indicates information about the event trigger that starts model monitoring. monitoringPeriodicTimer indicates information about the periodic timer that performs model monitoring. updateEventTrigger indicates information about the event trigger that starts model update. updatePeriodicTimer indicates information about the periodic timer that performs model update.

[0426] <4-3. Fallback to Conventional Signal Processing> Next, fallback to conventional processing that does not use an AI / ML model will be described.

[0427] 11 is a diagram for explaining fallback processing. For example, a signal processing method (transmission signal processing method and / or reception signal processing method) that uses an AI / ML model is defined as a first signal processing method, and a signal processing method (transmission signal processing method and / or reception signal processing method) that does not use an AI / ML model is defined as a second signal processing method. In the example of FIG. 11, AI / ML-based encoder processing is transmission signal processing using the first signal processing method, and AI / ML-based decoder processing is reception signal processing using the first signal processing method. Also, in the example of FIG. 11, conventional signal processing is transmission signal processing / reception signal processing using the second signal processing method. Note that conventional signal processing may also be referred to as non-AI / ML-based encoder processing or non-AI / ML-based decoder processing.

[0428] When a predetermined condition is satisfied, the communication device (first communication device and / or second communication device) may execute a process of switching the signal processing method from a first signal processing method using an AI / ML model to a second signal processing method not using the AI / ML model (hereinafter also referred to as a fallback process). Here, the first communication device may be a transmitting device and the second communication device may be a receiving device, or the first communication device may be a receiving device and the second communication device may be a transmitting device.

[0429] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto). In this case, the base station 20 and the terminal device 40 may execute fallback processing when a predetermined condition is satisfied. Also, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto). In this case, the terminal device 40 serving as a transmitting device and the terminal device 40 serving as a receiving device may execute fallback processing when a predetermined condition is satisfied.

[0430] Here, the conventional signal processing (signal processing using the second signal processing method) may be at least one of the signal processing shown in (H1) to (H3) below. Note that the signal processing shown below is an example. The conventional signal processing is not limited to the following.

[0431] (H1) CSI Feedback The conventional signal processing may be conventional CSI feedback processing in CSI feedback. Here, the conventional CSI feedback may be, for example, at least one of a Type 1 Single-panel codebook, a Type 1 Multi-panel Codebook, a Type 2 Codebook, a Type 2 Port selection codebook, an Enhanced Type 2 Codebook, an Enhanced Type 2 Port selection codebook, and a Further enhanced Type 2 Port selection codebook.

[0432] (H2) Beam management The conventional signal processing may be conventional beam management processing in beam management. Here, the conventional beam management may be an operation of receiving an SSB (Synchronization Signal Block) and transmitting a PRACH preamble using a PRACH resource corresponding to the SSB. In addition, the conventional beam management may be an operation of receiving a CSI-RS and notifying a CSI report.

[0433] (H3) Positioning The conventional signal processing may be conventional positioning processing in positioning. Here, the conventional positioning may be an operation of transmitting a PRS (Positioning Reference Signal) in a downlink and performing position estimation. Also, the conventional positioning may be an operation of transmitting an SRS (Sounding Reference Signal) in an uplink and performing position estimation.

[0434] As described above, the communication device (the first communication device and / or the second communication device) may execute the fallback process when a predetermined condition is satisfied. In this case, the communication device may execute the fallback process when a predetermined event occurs, when a predetermined trigger is activated, or when a predetermined time has elapsed.

[0435] More specifically, the communication device may perform a fallback process in at least one of the following cases (I1) to (I4).

[0436] (I1) When a fallback notification is received: A communication device may execute a fallback process when it receives a fallback notification from another communication device instructing it to switch to conventional signal processing. For example, one of a first communication device and a second communication device may execute the fallback process when it receives a fallback notification from the other communication device. The first communication device and / or the second communication device may execute the fallback process when it receives a fallback notification from a third communication device (a communication control device that controls the first communication device and / or the second communication device).

[0437] (I2) When Communication Quality Deteriorates: When communication quality deteriorates, the communication device may execute a fallback process. For example, when communication quality deteriorates and an initial access procedure is required, the communication device may execute the fallback process.

[0438] (I3) When the Performance of the AI / ML Model No Longer Satisfies the Requirements The communication device may execute a fallback process when the performance of the AI / ML model no longer satisfies the requirements. For example, the communication device may execute the fallback process when it determines, as a result of model monitoring, that the performance of the AI / ML model no longer satisfies the requirements of the applied functionality.

[0439] (I4) When the Validity Period of the AI / ML Model Has Expired The communication device may perform a fallback process when the validity period of the AI / ML model has expired. For example, the communication device may perform the fallback process when the validation timer of the AI / ML model has expired and the AI / ML model needs to be retrained or reacquired.

[0440] <4-4. Changing the LCM Control Subject> If the communication device that controls the LCM is mobile, there is a possibility that the communication device that controls the LCM will move outside the communication area. Therefore, it is necessary to execute LCM control taking into consideration the possibility that the control subject will change. Therefore, the communication device (first communication device and / or second communication device) may execute LCM control as follows.

[0441] For example, a validity period may be set for the LCM control. Then, the communication device starts counting a timer when the LCM control entity executes the LCM control. Here, the communication device counting the timer may be the LCM control entity or the controlled object. The communication device determines that the AI / ML model-related information (setting information and / or control information) is valid information (usable information) until the timer reaches zero. When the timer reaches zero, the communication device determines that the AI / ML model-related information is invalid.

[0442] A communication device may also transfer an already activated AI / ML model to another communication device so that the other communication device can use the same AI / ML model.

[0443] For example, assume that the wireless communication (or processing related thereto) to which the AI / ML model is applied is uplink / downlink communication (or processing related thereto). １ The AI / ML model used in communication with the terminal device 40 is ２ This allows the base station 20 １ Even if the terminal device 40 moves out of the communication area of ​​the base station 20,２ However, communication with the terminal device 40 can be carried out smoothly.

[0444] Furthermore, it is assumed that the wireless communication (or processing related thereto) to which the AI / ML model is applied is sidelink communication (or processing related thereto). In this case, the terminal device 40 ２ terminal device 40 １ The AI / ML model used in the communication with the terminal device 40 ３ This allows the terminal device 40 ２ If the terminal device 40 is outside the communication area １ Even if the terminal device 40 moves, ３ However, the terminal device 40 １ and communication can be carried out.

[0445] <4-5. Example of Input / Output Information of AI / ML Model> The communication device (first communication device and / or second communication device) may perform signal processing based on input information to the AI / ML model and / or output information from the AI / ML model. Furthermore, the information processing device may train the AI / ML model based on the input information and / or output information shown below. Here, the information processing device may be either or both of the first communication device and the second communication device. Furthermore, the information processing device may be a device other than the first communication device and the second communication device.

[0446] Here, the input information and / or output information may include, for example, at least one of the pieces of information shown in (J1) to (J15) below. Of course, the input information and / or output information is not limited to the information below.

[0447] (J1) CQI (Channel Quality Information) (J2) PMI (Precoding Matrix Indicator) (J3) CRI (CSI-RS Resource Indicator) (J4) SSBRI (SS / PBCH Resource Block Indicator) (J5) LI (Layer Indicator) (J6) RI (Rank Indicator) (J7) L1-RSRP (Layer 1 Reference Signal Received Power) (J8) Amount of interference from other cells (J9) Location estimation information of terminal device 40 (J10) Location information of base station 20 (J11) Channel Matrix (J12) Eigenvector (J13) Beam ID (J14) Timing error information (J15) LOS (Line Of Sight) / NLOS (Non Line Of Sight) information

[0448] <4-6. Coexistence with communication devices that do not support AI communication> Next, coexistence between communication devices that support AI communication and communication devices that do not support AI communication will be described. As described above, AI communication is wireless communication that uses an AI / ML model.

[0449] In the following description, wireless communication that does not use the AI / ML model (wireless communication that is not AI communication) may be referred to as conventional communication or conventional wireless communication. Note that wireless communication that does not use the AI / ML model (wireless communication that is not AI communication) is not necessarily limited to existing wireless communication. The terms "conventional communication" or "conventional wireless communication" that appear in the following description can be replaced with "wireless communication that does not use the AI / ML model" or "wireless communication that is not AI communication."

[0450] Note that the wireless communication mentioned in the following description may be uplink communication in which the terminal device 40 is a transmitting device and the base station 20 is a receiving device, or may be downlink communication in which the base station 20 is a transmitting device and the terminal device 40 is a receiving device. Also, the wireless communication mentioned in the following description may be sidelink communication in which the terminal device 40 is a transmitting device of sidelink data and another terminal device 40 is a receiving device of sidelink data.

[0451] To perform AI communication, both the transmitting device and the receiving device must support AI communication. In this case, it is necessary to consider the coexistence of communication devices that support AI communication and communication devices that do not support AI communication.

[0452] On the other hand, if one of the communication devices, the transmitting device or the receiving device, is an AI communication-compatible communication device and the other communication device is a communication device capable of performing conventional wireless communication that does not use the AI / ML model, it is not necessarily necessary to consider the coexistence of an AI communication-compatible communication device and an AI communication-incompatible communication device.

[0453] Here, in a process related to an AI / ML model of an AI communication-compatible communication device, information provided by a communication device that does not support AI communication may be required. For example, in at least one of the processes described above in (M1) to (M25), such as model training or model inference, information provided by a communication device that does not support AI communication may be required. Therefore, even if an AI communication-compatible communication device is capable of performing conventional wireless communication, it may be necessary to consider the coexistence of an AI communication-compatible communication device and a communication device that does not support AI communication.

[0454] In addition, if one of the communication devices, the transmitting device or the receiving device, is an AI communication-compatible communication device and the other communication device is a communication device that is incapable of performing conventional wireless communication that does not use the AI / ML model, it is still necessary to consider the coexistence of an AI communication-compatible communication device and an AI communication-incompatible communication device.

[0455] When it is necessary to consider the coexistence of communication devices that support AI communication and communication devices that do not support AI communication, the operation of the communication devices will be as follows: Below, the operation of the communication devices will be explained for each of broadcast communication, groupcast communication, and unicast communication.

[0456] (L1) Broadcast communication For example, when a transmitting device performs signal processing using an AI / ML model and transmits data, there may be cases where a communication device that supports AI communication can receive the data, but a communication device that does not support AI communication cannot receive the data.

[0457] (L2) Groupcast Communication In the case of groupcast communication, the communication device determines whether the communication device (first communication device and / or second communication device) performing wireless communication belongs to an AI communication-compatible group or an AI communication-incompatible group. Here, the communication device making the determination may be the first communication device, may be the second communication device, or may be a third communication device different from the first communication device and the second communication device (for example, a communication control device that controls the first communication device and / or the second communication device).

[0458] Then, the communication device determines whether the signal processing of the first communication device and / or the signal processing of the second communication device should be signal processing using the AI / ML model or signal processing without using the AI / ML model, based on the determination result. The first communication device and / or the second communication device executes signal processing using the AI / ML model or signal processing without using the AI / ML model, based on the determination result.

[0459] (L3) Unicast Communication In the case of unicast communication, the communication device determines whether the communication device (first communication device and / or second communication device) performing wireless communication is capable of AI communication. Here, the communication device performing the determination may be the first communication device, the second communication device, or a third communication device different from the first communication device and the second communication device (for example, a communication control device that controls the first communication device and / or the second communication device).

[0460] At this time, the communication device performing wireless communication may transmit capability information including information indicating whether or not the communication device performing the determination is capable of supporting AI communication, and the communication device performing the determination may determine whether or not the first communication device and / or the second communication device is capable of supporting AI communication based on the capability information.

[0461] Then, the communication device determines whether the signal processing of the first communication device and / or the signal processing of the second communication device should be signal processing using the AI / ML model or signal processing without using the AI / ML model, based on the determination result. The first communication device and / or the second communication device executes signal processing using the AI / ML model or signal processing without using the AI / ML model, based on the determination result.

[0462] One of the first and second communication devices may notify the other communication device of control information regarding whether to communicate using AI communication or conventional communication. The control information may include capability information including information indicating whether the other communication device is compatible with AI communication. Then, based on the received control information, the other communication device performs signal processing using an AI / ML model or signal processing without using an AI / ML model.

[0463] <<5. Sequence Example>> Based on the above, a sequence example of communication processing according to this embodiment will be described.

[0464] The following describes an example sequence of wireless communication between a transmitting device and a receiving device. Note that the wireless communication shown in the following sequence example may be uplink communication in which the terminal device 40 is a transmitting device and the base station 20 is a receiving device, or may be downlink communication in which the base station 20 is a transmitting device and the terminal device 40 is a receiving device. Furthermore, the wireless communication shown in the following sequence example may be sidelink communication in which the terminal device 40 is a transmitting device of sidelink data and another terminal device 40 is a receiving device of sidelink data.

[0465] The communication process of this embodiment is not limited to the communication process shown in the following sequence example, but can also be implemented in other sequences.

[0466] <5-1. When the Transmitting Device is the Control Subject of the LCM> First, an example of a sequence when the transmitting device is the control subject of the LCM and the receiving device is the controlled device will be described. In this example of a sequence, the operation of the transmitting device and the receiving device in a two-sided model will be described. The two-sided model is a case where both the transmitting device and the receiving device use the AI / ML model.

[0467] <5-1-1. Basic Sequence Example> First, a basic sequence example will be described. FIG. 12A is a diagram showing a basic sequence example of communication processing when the transmitting device is the LCM control subject. Note that, for convenience of explanation, the following describes the details of each step from steps S11 to S15, but not all steps are essential components for identifying the invention. For example, the invention may be identified by step S11 and its details (e.g., details regarding information related to the AI / ML model). In other words, steps S12 to S15 may be optional. Below, the communication processing related to this sequence example will be described with reference to FIG. 12A.

[0468] The transmitting device transmits information about the AI / ML model (information about the AI / ML model described above or below) to the receiving device (control target) (step S11). At this time, the transmitting device may transmit data of a trained AI / ML model (a learned AI / ML model) as the information about the AI / ML model, may transmit an activation notification of the AI / ML model, or may transmit feedback information (information for model monitoring). In addition, the transmitting device may transmit information about the LCM described above as the information about the AI / ML model.

[0469] The receiving device receives information about the AI / ML model (information about the AI / ML model described above or below). Then, the receiving device executes processing based on the information about the AI / ML model (step S12). For example, if the receiving device receives data about a trained AI / ML model as information about the AI / ML model, the receiving device sets the received AI / ML model (or an AI / ML model generated based on the received AI / ML model data) as the AI / ML model related to the reception processing. Furthermore, if the receiving device receives an activation notification for the AI / ML model as information about the AI / ML model, the receiving device executes activation of the AI / ML model related to the notification. If the receiving device receives feedback information as information about the AI / ML model, the receiving device executes model monitoring based on the received feedback information.

[0470] The transmitting device generates transmission data by executing transmission signal processing (step S13). Here, the transmitting device may generate the transmission data by executing transmission signal processing using an AI / ML model (first transmission processing). Note that the transmitting device may execute transmission signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the transmitting device may execute transmission signal processing using the AI / ML model when the transmitting device uses the AI / ML model in a use case of a one-sided model.

[0471] The transmitting device transmits the generated transmission data to the receiving device (step S14).

[0472] The receiving device decodes the received data by performing received signal processing (first receiving processing) (step S15). Here, the receiving device may decode the received data by performing received signal processing using the activated AI / ML model. Note that the receiving device may perform received signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the receiving device may perform received signal processing using the AI / ML model when the receiving device uses the AI / ML model in a use case of a one-sided model.

[0473] <5-1-2. Specific sequence example> Next, a specific sequence example will be described. Fig. 12B is a diagram showing a specific sequence example of communication processing when the transmitting device is the LCM control subject. Below, the communication processing related to this sequence example will be described with reference to Fig. 12B.

[0474] The transmission device performs training of the AI / ML model (step S101), thereby obtaining a trained AI / ML model (a learned AI / ML model).

[0475] The transmitting device transfers the trained AI / ML model to the receiving device (step S102). The transmitting device may notify the receiving device of the AI / ML model as semi-static information such as RRC signaling.

[0476] The receiving device notifies the transmitting device of whether the received AI / ML model has been successfully received (ACK / NACK) (step S103).

[0477] The transmitting device notifies the receiving device of the activation of the AI / ML model (step S104). Here, the transmitting device may notify, for example, the ID (model ID) of the AI / ML model to be activated and / or the ID (functionality ID) of the functionality to be activated. The transmitting device may notify the model ID and / or the functionality ID as semi-static information such as RRC signaling, or as dynamic information such as MAC CE, DCI, UCI, or SCI.

[0478] The receiving device performs activation of the AI / ML model based on the activation notification (step S105).

[0479] The transmitting device generates transmission data by performing transmission signal processing (step S106). Here, the transmitting device may generate the transmission data by performing transmission signal processing using an AI / ML model. Note that the transmitting device may perform transmission signal processing using the AI / ML model in a use case that requires a two-sided model. Alternatively, the transmitting device may perform transmission signal processing using the AI / ML model when the transmitting device uses the AI / ML model in a use case of a one-sided model.

[0480] The transmitting device transmits the generated transmission data to the receiving device (step S107).

[0481] The receiving device decodes the received data by performing received signal processing (step S108). Here, the receiving device may decode the received data by performing received signal processing using the activated AI / ML model. Note that the receiving device may perform received signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the receiving device may perform received signal processing using the AI / ML model when the receiving device uses the AI / ML model in a use case of a one-sided model.

[0482] The receiving device may feed back information for model monitoring to the transmitting device (step S109). For example, the receiving device may feed back decoded received data to the transmitting device.

[0483] The transmitting device performs model monitoring based on the received feedback information (step S110). Then, the transmitting device determines whether the characteristics of the AI / ML model satisfy the requirements based on the results of the model monitoring (step S111). For example, the transmitting device may determine whether the characteristics of the AI / ML model satisfy the requirements based on requirement information set in the notified functionality.

[0484] If the transmitting device determines that the characteristics of the AI / ML model do not satisfy the requirements, the transmitting device notifies the receiving device of a fallback to conventional signal processing (step S112).

[0485] When the receiving device receives the fallback notification, the receiving device stops the signal processing using the AI / ML model and then falls back to the conventional signal processing that does not use the AI / ML model (step S113).

[0486] The transmitting device trains the AI / ML model (step S114), and then transfers the trained AI / ML model to the receiving device (step S115).

[0487] The receiving device notifies the transmitting device of whether the received AI / ML model has been successfully received (ACK / NACK) (step S116).

[0488] The transmitting device notifies the receiving device of the activation of the AI / ML model (step S117). Here, the transmitting device may notify, for example, the ID of the AI / ML model to be activated and / or the ID of the functionality to be activated.

[0489] The receiving device activates the AI / ML model based on the activation notification (step S118).

[0490] <5-2. When the Receiving Device is the Control Subject of the LCM> Next, an example of a sequence when the receiving device is the control subject of the LCM and the transmitting device is the controlled object will be described. In this example of a sequence, the operation of the transmitting device and the receiving device in a two-sided model will be described. The two-sided model is a case where both the transmitting device and the receiving device use the AI / ML model.

[0491] <5-2-1. Basic Sequence Example> First, a basic sequence example will be described. FIG. 13A is a diagram showing a basic sequence example of communication processing when the receiving device is the LCM control subject. Note that, for convenience of explanation, the details of each step from steps S21 to S25 will be described below, but not all steps are essential components for identifying the invention. For example, the invention may be identified by step S21 and its details (e.g., details regarding information related to the AI / ML model). In other words, steps S22 to S25 may be optional. Below, the communication processing related to this sequence example will be described with reference to FIG. 13A.

[0492] The receiving device transmits information about the AI / ML model (information about the AI / ML model described above or below) to the transmitting device (control target) (step S21). At this time, the receiving device may transmit data of a trained AI / ML model (a learned AI / ML model) as the information about the AI / ML model, may transmit an activation notification of the AI / ML model, or may transmit feedback information (information for model monitoring). In addition, the receiving device may transmit information about the LCM described above as the information about the AI / ML model.

[0493] The transmitting device receives information about the AI / ML model (information about the AI / ML model described above or below). Then, the transmitting device executes processing based on the information about the AI / ML model (step S22). For example, if the transmitting device receives data about a trained AI / ML model as information about the AI / ML model, the transmitting device sets the received AI / ML model (or an AI / ML model generated based on the received AI / ML model data) as the AI / ML model related to the transmission processing. Furthermore, if the transmitting device receives an activation notification for the AI / ML model as information about the AI / ML model, the transmitting device executes activation of the AI / ML model related to the notification. If the transmitting device receives feedback information as information about the AI / ML model, the transmitting device executes model monitoring based on the received feedback information.

[0494] The transmitting device generates transmission data by executing transmission signal processing (step S23). Here, the transmitting device may generate transmission data by executing transmission signal processing using an AI / ML model (second transmission processing). Note that the transmitting device may execute transmission signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the transmitting device may execute transmission signal processing using the AI / ML model when the transmitting device uses the AI / ML model in a use case of a one-sided model.

[0495] The transmitting device transmits the generated transmission data to the receiving device (step S24).

[0496] The receiving device decodes the received data by performing received signal processing (step S25). Here, the receiving device may decode the received data by performing received signal processing (second receiving processing) using the activated AI / ML model. Note that the receiving device may perform received signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the receiving device may perform received signal processing using the AI / ML model when the receiving device uses the AI / ML model in a use case of a one-sided model.

[0497] <5-2-2. Specific sequence example> Next, a specific sequence example will be described. Fig. 13B is a diagram showing a specific sequence example of communication processing when the receiving device is the LCM control subject. Below, the communication processing related to this sequence example will be described with reference to Fig. 13B.

[0498] The receiving device performs training of the AI / ML model (step S201), thereby obtaining a trained AI / ML model (a learned AI / ML model).

[0499] The receiving device transfers the trained AI / ML model to the transmitting device (step S202). The receiving device may notify the AI / ML model as semi-static information such as RRC signaling.

[0500] The transmitting device notifies the receiving device of whether the received AI / ML model has been successfully received (ACK / NACK) (step S203).

[0501] The receiving device notifies the transmitting device of the activation of the AI / ML model (step S204). Here, the receiving device may notify, for example, the ID (model ID) of the AI / ML model to be activated and / or the ID (functionality ID) of the functionality to be activated. The receiving device may notify the model ID and / or the functionality ID as semi-static information such as RRC signaling, or as dynamic information such as MAC CE, DCI, UCI, or SCI.

[0502] Based on the activation notification, the transmitting device executes activation of the AI / ML model (step S205).

[0503] The transmitting device generates transmission data by performing transmission signal processing (step S206). Here, the transmitting device may generate the transmission data by performing transmission signal processing using an AI / ML model. Note that the transmitting device may perform transmission signal processing using the AI / ML model in a use case that requires a two-sided model. Alternatively, the transmitting device may perform transmission signal processing using the AI / ML model when the transmitting device uses the AI / ML model in a use case of a one-sided model.

[0504] The transmitting device transmits the generated transmission data to the receiving device (step S207).

[0505] The receiving device decodes the received data by performing received signal processing (step S208). Here, the receiving device may decode the received data by performing received signal processing using the activated AI / ML model. Note that the receiving device may perform received signal processing using the AI / ML model in a use case requiring a two-sided model. Alternatively, the receiving device may perform received signal processing using the AI / ML model when the receiving device uses the AI / ML model in a use case of a one-sided model.

[0506] The receiving device performs model monitoring based on the decoded received data (step S209). Then, the transmitting device determines whether the characteristics of the AI / ML model satisfy the requirements based on the results of the model monitoring (step S210). For example, the transmitting device may determine whether the characteristics of the AI / ML model satisfy the requirements based on requirement information set in the notified functionality.

[0507] If the receiving device determines that the characteristics of the AI / ML model do not satisfy the requirements, the receiving device notifies the receiving device of fallback to conventional signal processing (step S211).

[0508] When the receiving device receives the fallback notification, it stops signal processing using the AI / ML model, and the transmitting device falls back to conventional signal processing that does not use the AI / ML model (step S212).

[0509] The receiving device trains the AI / ML model (step S213), and then transfers the trained AI / ML model to the transmitting device (step S214).

[0510] The transmitting device notifies the receiving device of whether the received AI / ML model has been successfully received (ACK / NACK) (step S215).

[0511] The receiving device notifies the transmitting device of the activation of the AI / ML model (step S216). Here, the receiving device may notify, for example, the ID of the AI / ML model to be activated and / or the ID of the functionality to be activated.

[0512] The receiving device activates the AI / ML model based on the activation notification (step S217).

[0513] <5-3. Other Sequence Examples> The above sequence examples show communication processing examples including multiple LCM controls. However, even some of the above sequence examples can be communication processing of this embodiment. Below, other sequence examples of communication processing of this embodiment will be described.

[0514] (N1) Model Transfer Figure 14 is a diagram showing an example of a communication processing sequence related to model transfer. The communication device that controls the LCM trains an AI / ML model (step S301). Then, the communication device that controls the LCM transfers the trained AI / ML model to the communication device that is to be controlled (step S302). The communication device that is to be controlled processes received signals using the received AI / ML model (step S303).

[0515] (N2) Model Activation Figure 15 shows an example of a communication processing sequence for model activation. The communication device that controls the LCM notifies the communication device that is to be controlled of the activation of the AI / ML model (step S401). The communication device that is to be controlled activates the AI / ML model based on the activation notification (step S402).

[0516] (N3) Signal Processing Using AI / ML Model Figure 16 is a diagram showing an example sequence of signal processing using the AI / ML model. The communication device that controls the LCM generates transmission data by performing transmission signal processing using the AI / ML model (step S501). The communication device that controls the LCM transmits the generated transmission data to the communication device that is to be controlled (step S502). The communication device that is to be controlled decodes the received data by performing reception signal processing using the AI / ML model (step S503).

[0517] (N4) Model Monitoring Fig. 17 is a diagram showing an example of a communication processing sequence related to model monitoring. The communication device to be controlled decodes received data by executing received signal processing (step S601). The communication device to be controlled transmits the decoded received data as feedback information to the communication device that will control the LCM (step S602). The communication device that will control the LCM executes model monitoring based on the received feedback information (step S603).

[0518] (N5) Model Fallback FIG. 18 illustrates an example of a communication processing sequence related to model fallback. The communication device that controls the LCM determines whether the characteristics of the AI / ML model satisfy the requirements based on the results of model monitoring (step S701). If the characteristics of the AI / ML model do not satisfy the requirements, the communication device that controls the LCM notifies the communication device to be controlled of a fallback to conventional signal processing (step S702). Upon receiving the fallback notification, the communication device to be controlled stops signal processing using the AI / ML model and falls back received signal processing to conventional signal processing that does not use the AI / ML model (step S703). The communication device to be controlled performs training of the AI / ML model (step S704).

[0519] <<6. Modifications>> The above-described embodiment is merely an example, and various modifications and applications are possible.

[0520] In the above-described embodiment, the technology of the present disclosure has been described using examples of wireless communication between a base station 20 and a terminal device 40, or wireless communication between a terminal device 40 and another terminal device 40. However, the scope of application of the present embodiment is not limited to this. For example, the technology of the present disclosure can also be applied to wireless communication between multiple communication devices selected from a management device 10, a base station 20, a relay station 30, and a terminal device 40. The technology of the present disclosure can also be applied to wireless communication between management devices 10, between base stations 20, between relay stations 30, or between terminal devices 40. The technology of the present disclosure can also be applied to processing performed independently by the management device 10, the base station 20, the relay station 30, and the terminal device 40 using an AI / ML model.

[0521] The functions of the blocks (acquisition unit 231 to transmission unit 234) included in the control unit 23 of the base station 20 may be similar to the functions of the blocks (acquisition unit 431 to transmission unit 434) included in the control unit 43 of the terminal device 40. The functions of the blocks (acquisition unit 331 to transmission unit 334) included in the control unit 33 of the relay station 30 may be similar to the functions of the blocks included in the control unit 23 of the base station 20, or similar to the functions of the blocks included in the control unit 23 of the terminal device 40. The functions of the blocks included in the control unit 43 of the terminal device 40 may be similar to the functions of the blocks included in the control unit 23 of the base station 20. The functions of the control unit 13 of the management device 10 may be similar to the functions of the control unit 23 of the base station 20, or similar to the functions of the control unit 33 of the relay station 30, or similar to the functions of the control unit 43 of the terminal device 40.

[0522] The management device 10, the base station 20, the relay station 30, or the control device that controls the terminal device 40 in this embodiment may be realized by a dedicated computer system or a general-purpose computer system.

[0523] For example, a communication program for executing the above-described operations is stored on a computer-readable recording medium such as an optical disk, a semiconductor memory, a magnetic tape, or a flexible disk and distributed. Then, for example, the program is installed on a computer and the above-described processing is executed to configure a control device. In this case, the control device may be a device (e.g., a personal computer) external to the management device 10, the base station 20, the relay station 30, or the terminal device 40. Alternatively, the control device may be a device (e.g., a control unit 13, a control unit 23, a control unit 33, or a control unit 43) internal to the management device 10, the base station 20, the relay station 30, or the terminal device 40.

[0524] The communication program may also be stored in a disk device provided in a server on a network such as the Internet, and may be downloaded to a computer. The above-described functions may also be realized by cooperation between an operating system (OS) and application software. In this case, the components other than the OS may be stored on a medium and distributed, or may be stored on a server and downloaded to a computer.

[0525] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0526] Furthermore, the components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of the devices can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Note that this distribution or integration configuration may also be performed dynamically.

[0527] The above-described embodiments can be combined as appropriate within the scope of the processing content without causing inconsistency. The order of the steps shown in the flowcharts and sequence diagrams of the above-described embodiments can be changed as appropriate.

[0528] Furthermore, for example, the present embodiment can also be implemented as any configuration that constitutes an apparatus or system, such as a processor as a system LSI (Large Scale Integration), a module using multiple processors, a unit using multiple modules, a set in which other functions are added to a unit, or the like (i.e., a configuration of a part of an apparatus).

[0529] The system LSI may also be referred to as an SOC (System on Chip). In other words, each of the above-described or later-described devices (e.g., the management device 10, the base station 20, the relay station 30, and the terminal device 40) may be interpreted as a processor (e.g., a CPU) as a system LSI (e.g., SoC), or a module that uses or constitutes the processor. Additionally or alternatively, the present embodiment may be implemented by any configuration that constitutes a device or system, such as a modem chip (baseband chip) or an RF (Radio Frequency) unit, or a combination thereof. The RF unit includes at least one of an RF circuit or an RF front-end. In other words, each of the above-described or later-described devices may be interpreted as a modem chip (baseband chip) or an RF unit, or a combination thereof. Additionally or alternatively, each of the above-described or later-described devices may be interpreted as a module that uses or constitutes a modem chip or an RF unit.

[0530] The modem chip performs signal processing for communications within a device (including the devices described above or below). The modem chip may have at least the function of a modulator or demodulator. The RF unit may have the function of at least one of an RF transceiver (RF upconverter, RF downconverter), a power amplifier, and a low-noise amplifier. The RF transceiver converts between baseband signals and RF frequencies. The power amplifier amplifies signals for transmission from an antenna. The low-noise amplifier amplifies weak signals received from the antenna. Additionally or alternatively, the RF unit (particularly, the RF front-end) may include at least one of the above-mentioned power amplifier, low-noise amplifier, envelope tracker, filter, duplexer, multiplexer, antenna switch, and antenna tuner.

[0531] The combination of the modem chip and the RF unit may be referred to as a modem-RF system. At least a portion of the modem chip, the RF unit, or a combination thereof may be included in a system LSI (e.g., SoC). For example, at least a portion of the MAC layer processing / PHY layer processing performed by at least a portion of the modem chip, the RF unit, or a combination thereof may be realized by the system LSI. The MAC layer processing or PHY layer processing here may be at least a portion of the processing performed by the devices (e.g., the management device 10, the base station 20, the relay station 30, and the terminal device 40) in the above-described or below-described embodiments.

[0532] In this embodiment, a system refers to a collection of multiple components (devices, modules (components), etc.), regardless of whether all of the components are in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device in which multiple modules are housed in a single housing, are both systems.

[0533] Furthermore, for example, this embodiment can have a cloud computing configuration in which one function is shared and processed jointly by a plurality of devices via a network.

[0534] <<7. Conclusion>> As described above, the first communication device (e.g., the base station 20 or the terminal device 40) of this embodiment is configured to be able to wirelessly communicate with the second communication device (e.g., the base station 20 or the terminal device 40). Furthermore, at least one of the first communication device and the second communication device is able to execute processing related to wireless communication using an AI / ML model.

[0535] The first communication device transmits information about the AI / ML model to the second communication device when performing LCM (AI / ML model management), or the first communication device transmits information about the AI / ML model to the second communication device for performing LCM.

[0536] For example, a first communication device transmits to a second communication device information regarding an AI / ML model to be applied to at least one of the following processes: (P1) a first transmission process of the communication device regarding a radio signal transmitted from the first communication device to a second communication device; (P2) a first reception process of the other communication device regarding a radio signal transmitted from the first communication device to the other communication device; (P3) a second transmission process of the other communication device regarding a radio signal transmitted from the other communication device to the first communication device; and (P4) a second reception process of the first communication device regarding a radio signal transmitted from the other communication device to the first communication device.

[0537] The second communication device uses or manages the AI / ML model based on information about the AI / ML model received from the first communication device. For example, assume that the first communication device is the controlling entity of the LCM and the second communication device is the controlled object of the LCM. In this case, the second communication device may execute processing related to signal processing (first reception processing or second transmission processing) of the second communication device based on the information about the AI / ML model. Also, assume that the second communication device is the controlling entity of the LCM and the first communication device is the controlled object of the LCM. In this case, the second communication device may execute LCM related to signal processing (first transmission processing or second reception processing) of the first communication device based on the information about the AI / ML model.

[0538] This allows the use or management of the AI / ML model to be carried out efficiently, allowing the first communication device and / or the second communication device to achieve high communication performance.

[0539] Although the embodiments of the present disclosure have been described above, the technical scope of the present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the gist of the present disclosure. Furthermore, components of different embodiments and modifications may be combined as appropriate.

[0540] Furthermore, the effects of each embodiment described in this specification are merely examples and are not intended to be limiting, and other effects may also be obtained.

[0541] Note that the present technology may also be configured as follows: (1) A communication device that performs wireless communication with another communication device, comprising: a processor that controls a wireless transceiver for performing the wireless communication, wherein the processor controls the wireless transceiver to transmit, to the other communication device, information on an AI / ML model that is applied to at least one of: a first transmission process of the communication device regarding a wireless signal transmitted from the communication device to the other communication device; a first reception process of the other communication device regarding a wireless signal transmitted from the communication device to the other communication device; a second transmission process of the other communication device regarding a wireless signal transmitted from the other communication device to the communication device; or a second reception process of the communication device regarding a wireless signal transmitted from the other communication device to the communication device. (2) The communication device according to (1), wherein the processor is configured to determine a control entity for management of the AI / ML model based on setting information stored in advance in the communication device or control information received from the other communication device, and the determined control entity is one or both of the communication device and the other communication device. (3) The communication device according to (2), wherein the management of the AI / ML models includes at least two of data collection, model training, functionality identification, model identification, model distribution, model testing, model activation, functionality activation, model deactivation, functionality deactivation, model switching, functionality switching, model fallback, model monitoring, model update, model deployment, model design, model selection, or terminal capability, and when the processor determines both the communication device and the other communication device as the control entities, it determines the control entity for each of the management of the at least two AI / ML models.(4) The communication device according to any one of (1) to (3), wherein the information related to the AI / ML model includes at least one of: data on the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing activation of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing deactivation of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing switching of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; or information for fallback from at least one of the first reception processing to which the AI / ML model is applied or the second transmission processing to which the AI / ML model is applied to a processing that does not use the AI / ML model. (5) The communication device according to (4), wherein the information instructing activation of the AI / ML model includes at least one of: information for the other communication device to specify the timing of the activation, or information for the other communication device to specify a period during which the activation is valid. (6) The communication device according to (4) or (5), wherein the information instructing deactivation of the AI / ML model includes information for the other communication device to specify the timing of the deactivation. (7)...

Claims

1. A communication device that performs wireless communication with another communication device, the communication device having a processor that controls a wireless transceiver for performing the wireless communication, the processor controlling the wireless transceiver to transmit to the other communication device information regarding an AI / ML model that is applied to at least one of the following processes: a first transmission process of the communication device for a wireless signal transmitted from the communication device to the other communication device; a first reception process of the other communication device for a wireless signal transmitted from the communication device to the other communication device; a second transmission process of the other communication device for a wireless signal transmitted from the other communication device to the communication device; or a second reception process of the communication device for a wireless signal transmitted from the other communication device to the communication device.

2. The communication device according to claim 1, wherein the processor is configured to determine a control entity for management of the AI / ML model based on setting information pre-stored in the communication device or control information received from the other communication device, and the determined control entity is one or both of the communication device and the other communication device.

3. The communication device of claim 2, wherein the management of the AI / ML models includes at least two of: data collection, model training, functionality identification, model identification, model delivery, model testing, model activation, functionality activation, model deactivation, functionality deactivation, model switching, functionality switching, model fallback, model monitoring, model update, model deployment, model design, model selection, or terminal capability, and when the processor determines both the communication device and the other communication device as the control entities, it determines the control entity for each of the management of the at least two AI / ML models.

4. The communications device of claim 1, wherein the information regarding the AI / ML model includes at least one of the following: data on the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing activation of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing deactivation of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; information instructing switching of the AI / ML model applied to at least one of the first reception processing or the second transmission processing; or information for falling back from at least one of the first reception processing to which the AI / ML model is applied or the second transmission processing to which the AI / ML model is applied to a processing that does not use the AI / ML model.

5. The communication device of claim 4, wherein the information instructing activation of the AI / ML model includes at least one of the following: information for the other communication device to identify the timing of the activation, or information for the other communication device to identify the period during which the activation is valid.

6. The communication device according to claim 4, wherein the information instructing the deactivation of the AI / ML model includes information for the other communication device to specify the timing of the deactivation.

7. The communication device of claim 4, wherein the information instructing the AI / ML model switching includes information indicating a timing for switching the AI / ML model, and the information indicating the timing for switching the AI / ML model indicates a period from receiving the information indicating the timing for switching the AI / ML model to the timing for switching the AI / ML model.

8. The communication device of claim 4, wherein the information for causing the other communication device to perform fallback includes information indicating timing of fallback of an AI / ML model, and the information indicating the timing of fallback indicates a period from receiving the information indicating the timing of fallback to the timing of performing the fallback.

9. The communication device according to claim 8, wherein the other communication device has a plurality of functionalities relating to at least one of the first receiving process and the second transmitting process, and the information for causing the fallback is information for causing the processing of some of the plurality of functionalities to fall back from processing using the AI / ML model to processing not using the AI / ML model.

10. The information on the AI / ML model includes at least one of: ModelIDConfig, which is setting information on an identifier of the AI / ML model; or FunctionalityConfig, which is setting information on a functionality to which the AI / ML model is applied; the ModelIDConfig includes at least one of: ModelId, which indicates an identifier of the AI / ML model; numberOfInputNode, which indicates the number of input nodes in an AI / ML model network structure constituting the AI / ML model; numberOfOutputNode, which indicates the number of output nodes in an AI / ML model network structure constituting the AI / ML model; numberOfLayer, which indicates the number of layers in an AI / ML model network structure constituting the AI / ML model; or informationOfWeight, which indicates a weight allocated between each node in an AI / ML model network structure constituting the AI / ML model; and the FunctionalityConfig includes: functionalityId, which indicates an identifier of the functionality; feature, which indicates a feature in which the functionality is included; The communication device according to claim 8 , further comprising at least one of: a requirementList indicating required values ​​required for the functionality; or a capableModelList indicating information on AI / ML models applicable to the functionality.

11. The communication device of claim 8, wherein the processor controls the wireless transceiver to transmit information for causing the fallback in at least one of the following cases: when communication quality deteriorates; when the performance of the AI / ML model no longer satisfies specified requirements; or when the validity period of the AI / ML model has expired.

12. The communication device according to claim 1, wherein the processor controls the wireless transceiver to transmit, to the other communication device, information indicating which functionality the communication device supports among a plurality of functionalities related to at least one of the first transmission process and the second reception process.

13. The communication device of claim 1, wherein the AI / ML model is linked to functionality relating to at least one of the first transmission process and the second reception process, and the processor controls the wireless transceiver to transmit to the other communication device, as information relating to the AI / ML model, information indicating which of the multiple functionality's AI / ML models has completed training.

14. The communication device according to claim 1, wherein the processor controls the wireless transceiver to transmit, to the other communication device, information indicating which AI / ML model, among a plurality of AI / ML models relating to at least one of the first transmission process and the second reception process, the communication device supports.

15. The communication device according to claim 1, wherein the AI / ML model is associated with identification information, and the processor transmits to the other communication device, as information regarding the AI / ML model, information indicating which of a plurality of AI / ML models has completed training.

16. The communication device of claim 1, wherein the processor controls the wireless transceiver to transmit information about the AI / ML model to a plurality of the other communication devices.

17. The communication device according to claim 1, wherein the processor controls the wireless transceiver to transmit information about the AI / ML model to the other communication device when a predetermined event occurs or when a predetermined time is reached.

18. The communication device according to claim 1, wherein the communication device is one of a base station and a terminal device, and the other communication device is the other of the base station and the terminal device.

19. The communication device according to claim 1, wherein the communication device is a terminal device, and the other communication device is another terminal device.

20. A communication method, in which a communication device that wirelessly communicates with another communication device transmits to the other communication device information regarding an AI / ML model applied to at least one of the following processes: a first transmission process of the communication device regarding a radio signal transmitted from the communication device to the other communication device; a first reception process of the other communication device regarding a radio signal transmitted from the communication device to the other communication device; a second transmission process of the other communication device regarding a radio signal transmitted from the other communication device to the communication device; or a second reception process of the communication device regarding a radio signal transmitted from the other communication device to the communication device.

Images