Terminal, base station, and communication method

Abstract

A terminal according to one aspect of the present disclosure comprises a transmission unit, a reception unit, and a control unit. The transmission unit transmits, to a movement source base station, a message including a proposal pertaining to use of an inference model. The reception unit receives, from the movement source base station in response to the proposal, a message requesting the start of handover, the message including a response pertaining to an inference model that can be used by a movement destination base station. The control unit sets, to a usable state, an inference model of the host device corresponding to a model usable by the movement destination base station.

Description

Terminal, Base Station and Communication Method

[0001] The present disclosure relates to a terminal, a base station and a communication method in a wireless communication system.

[0002] 3GPP (3rd Generation Partnership Project) (registered trademark) has standardized NR (New Radio) (also referred to as "5G"), which is a successor system to LTE (Long Term Evolution) (registered trademark), and standardization work for the next-generation system is also ongoing.

[0003] As next-generation standardization, 5G Advanced and 6G are under consideration. In 5G Advanced and 6G, utilization of a Two-sided model, which is a pair of inference models deployed in both a terminal and a base station for a specific function, is being considered.

[0004] 3GPP TS 38.331 V18.4.0, Release 18, “NR; Radio Resource Control (RRC) protocol specification”, 2024. 3GPP TR 38.423 V18.4.0, Release 18, “NG-RAN; Xn application protocol (XnAP)”, 2024. 3GPP TR 38.843 V18.0.0, Release 18, “Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR air interface”, 2023.

[0005] When considering the utilization of a Two-sided model, it is necessary to study a negotiation procedure for enabling a terminal and a base station to use inference models that match each other. For example, when performing handover, it is necessary to study what kind of negotiation procedure is used to determine the inference model to be used among the terminal, the source base station and the target base station.

[0006] One object of the present disclosure is to achieve improvement of radio link quality by using a cooperative inference model among a plurality of devices.

[0007] A terminal according to an embodiment of this disclosure includes a transmitting unit, a receiving unit, and a control unit. The transmitting unit transmits a message to a base station containing a suggestion regarding the use of an inference model. The receiving unit receives a message from the base station containing a response regarding an inference model available to the base station in response to the suggestion. The control unit sets the inference model corresponding to the inference model available to the base station to an available state in accordance with the response.

[0008] According to this disclosure, it is possible to improve the quality of the wireless section by using a coordinated inference model among multiple devices.

[0009] This figure shows an example of a terrestrial 5G network assumed in this embodiment. This is a conceptual diagram of the Two-sided Model according to this embodiment. This is a sequence diagram showing a first example of the negotiation procedure regarding the use of an inference model between a base station and a terminal according to this embodiment. This is a sequence diagram showing a second example of the negotiation procedure regarding the use of an inference model between a base station and a terminal according to this embodiment. This is a sequence diagram showing a third example of the negotiation procedure regarding the use of an inference model between a base station and a terminal according to this embodiment. This is a sequence diagram showing an example of the operation after the completion of the negotiation procedure regarding the use of an inference model according to this embodiment. This figure shows an example of the negotiation procedure regarding the use of an inference model when performing a handover according to this embodiment. This figure shows an example of a specific use case of the Two-sided model assumed in this embodiment. This figure shows an example of the functional configuration of a base station according to this embodiment. This figure shows an example of the functional configuration of a terminal according to this embodiment. This figure shows an example of the hardware configuration of a base station or terminal according to this embodiment.

[0010] Embodiments of this disclosure will be described below with reference to the drawings. Note that the embodiments described below are examples, and the embodiments to which this disclosure applies are not limited to those described below.

[0011] In the operation of the wireless communication system of the embodiment, existing technologies will be used as appropriate. However, such existing technologies include, for example, existing LTE, but are not limited to existing LTE. Furthermore, the term "LTE" as used herein has a broad meaning that includes LTE-Advanced and LTE-Advanced and later technologies (e.g., NR), unless otherwise specified.

[0012] Furthermore, in the embodiments described below, terms such as SS (Synchronization signal), PSS (Primary SS), SSS (Secondary SS), PBCH (Physical broadcast channel), PRACH (Physical random access channel), PDCCH (Physical Downlink Control Channel), PDSCH (Physical Downlink Shared Channel), PUCCH (Physical Uplink Control Channel), and PUSCH (Physical Uplink Shared Channel), which are used in existing LTE systems, will be used. This is for convenience of description, and similar signals, functions, etc., may be called by other names. Also, the above terms in NR correspond to NR-SS, NR-PSS, NR-SSS, NR-PBCH, NR-PRACH, NR-PDCCH, NR-PDSCH, NR-PUCCH, NR-PUSCH, etc. However, even if a signal is used in NR, it is not necessarily explicitly stated as "NR-".

[0013] As next-generation specifications, 5G Advanced and 6G are being considered. For 5G Advanced and 6G, the use of a two-sided model, which is a pair of inference models deployed on both the terminal and the base station, is being considered for specific functions.

[0014] When considering the use of a two-sided model, it is necessary to consider negotiation procedures to ensure that terminals and base stations can use mutually compatible inference models. For example, when performing a handover, it is necessary to consider what negotiation procedures will be used between the terminal, the source base station, and the destination base station to determine how the inference models will be used.

[0015] An example of a terrestrial 5G network assumed in this embodiment will be described with reference to Figure 1.

[0016] A terrestrial 5G network includes one or more base stations 10 and terminals 20. A base station 10 is a communication device that provides one or more cells C and communicates wirelessly with the terminals 20. The physical resources of the radio signal are defined in the time domain and the frequency domain, the time domain may be defined by the number of OFDM (Orthogonal Frequency Division Multiplexing) symbols, and the frequency domain may be defined by the number of subcarriers or resource blocks. The base station 10 transmits synchronization signals and system information to the terminals 20. Synchronization signals are, for example, NR-PSS and NR-SSS. System information is transmitted, for example, in NR-PBCH and is also called broadcast information.

[0017] Base station 10 transmits control signals or data to terminal 20 via DL (Downlink) and receives control signals or data from terminal 20 via UL (Uplink). Both base station 10 and terminal 20 are capable of transmitting and receiving signals using beamforming. Both base station 10 and terminal 20 are also capable of applying MIMO (Multiple Input Multiple Output) communication to DL or UL. Furthermore, both base station 10 and terminal 20 may communicate via CA (Carrier Aggregation) through SCell (Secondary Cell) and PCell (Primary Cell). In addition, terminal 20 may communicate via DC (Dual Connectivity) through the primary cell of base station 10 and the primary secondary group cell (PSCell: Primary SCG Cell) of another base station 10.

[0018] Terminal 20 is a communication device equipped with wireless communication capabilities, such as a smartphone, mobile phone, tablet, wearable device, or M2M (Machine-to-Machine) communication module. Terminal 20 receives control signals or data from base station 10 via DL and transmits control signals or data to base station 10 via UL, thereby utilizing various communication services provided by the wireless communication system. Terminal 20 may also receive various reference signals transmitted from base station 10 and perform propagation path quality measurements based on the reception results of said reference signals.

[0019] Next, a conceptual diagram of the Two-sided Model according to this embodiment will be explained with reference to Figure 2.

[0020] The base station 10 includes an AI / ML model M1. The terminal 20 includes an AI / ML model M2. AI / ML model M1 and AI / ML model M2 may each be data-driven algorithms that apply artificial intelligence (AI) and machine learning (ML) technologies to generate output based on input. The AI / ML model according to this embodiment is a model that performs inference for a certain function, and will be referred to as an inference model below.

[0021] A two-sided model is a pair of inference models in which joint inference is performed. "Joint inference" may include inference that is performed jointly by the base station 10 and the terminal 20. For example, part of the inference may be performed at the terminal 20 and the rest at the base station 10, or vice versa. In other words, part of the inference may be performed at the base station 10 and the rest at the terminal 20.

[0022] Furthermore, since AI / ML model M1 is a model that performs inference on the base station 10 side or the network side, it may also be called the network side of the Two-sided Model (NW-part of Two-sided Model). Since AI / ML model M2 is a model that performs inference on the terminal 20 side, it may also be called the terminal side of the Two-sided Model (UE-part of Two-sided Model).

[0023] AI / ML models M1 and M2 may be the same inference model or different inference models. If they are different inference models, for example, AI / ML models M1 and M2 may be consistent inference models at the base station 10 and terminal 20 in order to perform paired processes such as encoding and decoding.

[0024] Next, a first example of the negotiation procedure regarding the use of an inference model between the base station 10 and the terminal 20 will be described with reference to the sequence diagram in Figure 3.

[0025] In step SA1, the base station 10 may include a broadcast signal such as an MIB (Master Information Block) or SIB (System Information Block) indicating that it will apply the inference model, and broadcast the broadcast signal to the terminal 20. For example, if the base station 10 applies the inference model to the first function and the second function, it may include information about the first function and the second function in the broadcast signal and notify the terminal 20. For example, if there are "function #a" and "function #b" as functions to which the inference model is applied, the SIB may include information such as "applied function = #a, applied function = #b". Note that the transmission is not limited to broadcast transmission; multicast transmission to multiple terminals 20 or transmission to a single terminal 20 is also acceptable.

[0026] In step SA2, terminal 20 may decide on a proposal (aiModelOffer) regarding the use of an applicable inference model for each function owned by its own device (terminal 20 itself). Terminal 20 may send a message containing the proposal to base station 10. The message may be, for example, a UEAssistanceInformation message. As a proposal (aiModelOffer), an identifier of an applicable inference model and version information of the inference model may be associated for each function to which the inference model is applied. If terminal 20 has multiple inference models with different versions, the version information of multiple applicable inference models may be included. Terminal 20 may, for example, include information such as "aiModelOffer([Applicable function = #a, inference model identifier = A, version information = 1, version information = 2], [Applicable function = #b, inference model identifier = B, version information = 1, version information = 2, version information = 3])" in a UEAssistanceInformation message and send it to base station 10.

[0027] The inference model identifier and the inference model version information may be combined. For example, terminal 20 may determine information such as "aiModelOffer([Applicable function = #a, Inference model identifier: Version information = #a1, Inference model identifier: Version information = #a2], [Applicable function = #b, Inference model identifier: Version information = #b1, Inference model identifier: Version information = #b2, Inference model identifier: Version information = #b3])" and include the aiModelOffer in the UEAssistanceInformation message and send it to base station 10.

[0028] In step SA3, the base station 10 may select an inference model owned by its own device (the base station 10 itself) that corresponds to the inference model owned by the terminal 20. The base station 10 may own more inference models with more versions than the number of versions of the inference model owned by the terminal 20. Alternatively, the base station 10 may own the same number of inference models as the number of versions of the inference model owned by the terminal 20, or fewer versions.

[0029] The base station 10 may also assign a shortened identifier to the selected inference model. A shortened identifier is an identifier formed to uniquely identify an inference model, or a group consisting of multiple inference models, using one or several characters.

[0030] For example, let's assume that base station 10 has selected to use the inference model identifier and inference model version information "#a2" for the inference model application function "#a", and to use the inference model identifier and inference model version information "#b1" and the inference model identifier and inference model version information "#b3" for the inference model application function "#b".

[0031] In this case, the base station 10 may set the abbreviated identifier to "m1" for the inference model application function "#a", the inference model identifier, and the inference model version information "#a2". The base station 10 may also set the abbreviated identifier to "n1" for the inference model application function "#b", the inference model identifier, and the inference model version information "#b1". Similarly, the base station 10 may set the abbreviated identifier to "n3" for the inference model application function "#b", the inference model identifier, and the inference model version information "#b3". Using abbreviated identifiers allows for efficient transmission of information regarding the inference model.

[0032] In step SA4, the base station 10 may set the inference model selected in step SA3 to a ready-to-use state.

[0033] In step SA5, the base station 10 may send a message to the terminal 20 containing the information set in step SA3 as an answer (aiModelAnswer). Furthermore, in step SA4, the base station 10 may send a message to the terminal 20 containing information (aiModelStatus) indicating that the selected inference model has been set to an usable state. The message may be, for example, an RRCReconfiguration message.

[0034] The base station 10 may include information such as "aiModelAnswer([Applicable function = #a, Inference model identifier: Version information = #a2], [Applicable function = #b, Inference model identifier: Version information = #b1, Inference model identifier: Version information = #b3], Inference model identifier: Version information = #a2 = m1, Inference model identifier: Version information = #b1 = n1, Inference model identifier: Version information = #b3 = n3, aiModelStatus(m1 = ready to use, n1 = ready to use, n3 = ready to use))" in the RRCReconfiguration message and send the RRCReconfiguration message to the terminal 20.

[0035] The base station 10 may include aiModelAnswer and aiModelStatus in a single RRCReconfiguration message and send it to the terminal 20. Alternatively, the base station 10 may include aiModelAnswer and aiModelStatus in separate messages and send them to the terminal 20.

[0036] In step SA6, terminal 20 may receive a message containing an aiModelAnswer sent from base station 10 (for example, an RRCReconfiguration message), and set its own device's inference model, which corresponds to the inference model selected by base station 10 as included in the message, to a ready-to-use state.

[0037] In step SA7, terminal 20 may send a message to base station 10 indicating that it has set its own device's inference model, which corresponds to the inference model selected by base station 10, to a ready-to-use state (aiModelStatus). The message may be, for example, an RRCReconfigurationComplete message. Terminal 20 may include information such as "aiModelStatus(m1=ready to use, n1=ready to use, n3=ready to use)" in the RRCReconfigurationComplete message and send the RRCReconfigurationComplete message to base station 10.

[0038] Steps SA4 and SA5 described above may be performed in any order. That is, after the base station 10 sends a message containing the answer regarding the selected inference model (for example, an RRCReconfiguration message) to the terminal 20, the base station 10 may set the selected inference model to a ready-to-use state.

[0039] Steps SA6 and SA7 described above may be performed in any order. That is, after the terminal 20 confirms the inference model selected by the base station 10 and sends a message including aiModelStatus to the base station 10, the terminal 20 may set the inference model of its own device corresponding to the inference model selected by the base station 10 to a ready-to-use state in its own device.

[0040] Next, a second example of the negotiation procedure regarding the use of an inference model between the base station 10 and the terminal 20 will be described with reference to the sequence diagram in Figure 4.

[0041] The second example is an example of a negotiation procedure when terminal 20 switches from an idle state (RRC_IDLE) to a connected state (RRC_CONNECTED).

[0042] Similar to the first example of the negotiation procedure, in step SA1, the base station 10 may include information indicating that an inference model is to be applied in at least one broadcast signal such as MIB and SIB, and broadcast-transmit the broadcast signal to the terminal 20.

[0043] In step SB1, similar to step SA2 in FIG. 3, the terminal 20 may determine, for each function, a proposal regarding the use of an inference model owned by the terminal itself (aiModelOffer), and transmit a message including the proposal to the base station 10. The message may be, for example, an RRCSetupRequest message.

[0044] In step SB2, similar to step SA3 in FIG. 3, the base station 10 may select an inference model. Furthermore, the base station 10 may assign a shortened identifier to the selected inference model.

[0045] In step SB3, similar to step SA4 in FIG. 3, the base station 10 may set the selected inference model to a ready-to-use state.

[0046] In step SB4, the base station 10 may transmit a message including the information set in step SB2 as a reply (aiModelAnswer) to the terminal 20. Furthermore, the base station 10 may transmit, to the terminal 20, a message including information (aiModelStatus) indicating that the inference model selected in step SB3 has been set to a ready-to-use state. The message may be, for example, an RRCSetup message.

[0047] In step SB5, the terminal 20 receives a message including the aiModelAnswer transmitted from the base station 10 in step SB4 (e.g., an RRCSetup message), and may set the inference model of the terminal itself corresponding to the inference model selected by the base station 10 included in the message to a ready-to-use state.

[0048] In step SB6, the terminal 20 may transmit, to the base station, a message including information (aiModelStatus) indicating that the terminal 20 has set its own inference model corresponding to the inference model selected by the base station 10 to a ready-to-use state. The message may be, for example, an RRCSetupComplete message.

[0049] This allows a negotiation procedure regarding the use of an inference model in a two-sided model to be executed even in the RRC protocol for transitioning to a connected state.

[0050] Next, a third example of a negotiation procedure regarding the use of an inference model between the base station 10 and the terminal 20 will be described with reference to the sequence diagram of FIG. 5.

[0051] The third example differs from the second example shown in FIG. 4 in the timing at which aiModelOffer is transmitted.

[0052] Similar to the first example of the negotiation procedure, in step SA1, the base station 10 may include information indicating that an inference model is to be applied in at least one of broadcast signals such as MIB and SIB, and broadcast the broadcast signal to the terminal 20.

[0053] In step SC1, the terminal 20 may transmit an RRCSetupRequest message to the base station 10.

[0054] In step SC2, the base station 10 may transmit an RRCSetup message, which is a response to the RRCSetupRequest message, to the terminal 20.

[0055] In step SC3, similar to step SA2, the terminal 20 may determine a proposal (aiModelOffer) regarding the use of the inference model owned by the terminal 20, and transmit a message including the proposal to the base station 10. The message may be, for example, an RRCSetupComplete message.

[0056] In step SC4, similar to step SA3 in FIG. 3, the base station 10 may select an inference model. Furthermore, the base station 10 may assign a shortened identifier to the selected inference model.

[0057] In step SC5, similar to step SA4 in Figure 3, the base station 10 may set the selected inference model to a ready-to-use state.

[0058] In step SC6, the base station 10 may send a message to the terminal 20 containing the information set in step SB2 as an answer (aiModelAnswer). Furthermore, the base station 10 may send a message to the terminal 20 containing information (aiModelStatus) indicating that the inference model selected in step SC5 has been set to an available state. The message may be, for example, an RRCReconfiguration message.

[0059] In step SC7, terminal 20 may receive a message containing the aiModelAnswer transmitted from base station 10 in step SB4 (for example, an RRCReconfiguration message), and set its own device's inference model, which corresponds to the inference model selected by base station 10 and is included in the message, to a ready to use state.

[0060] In step SC8, terminal 20 may send a message to base station 10 indicating that it has set its own device's inference model, which corresponds to the inference model selected by base station 10, to a ready to use state (aiModelStatus). The message may be, for example, an RRCReconfigurationComplete message.

[0061] This allows the negotiation procedure regarding the use of the inference model in the two-sided model to be executed even when the aiModelOffer is sent at a different timing than in the case of Figure 4 in the RRC protocol for transitioning to the connected state.

[0062] Next, an example of the operation after the completion of the negotiation procedure regarding the use of the inference model will be explained with reference to Figure 6.

[0063] When using an inference model, the base station 10 may send a message to the terminal 20 notifying it that it is actually using (activating) the inference model for the function. This message may be a DCI (Downlink Control Information) or a MAC CE (Media Access Control Control Element) in a lower layer such as the MAC layer.

[0064] On the other hand, if the use of the inference model is to be stopped, the base station 10 may send a message to the terminal 20 notifying it that the use of the inference model has been stopped (deactivate). The message may be in DCI or MAC CE, or a message in the RRC protocol, or any protocol and layer message.

[0065] (Handover) In this disclosure, an example of a negotiation procedure regarding the use of an inference model between the base station 10 and the terminal 20 when performing a handover will be described with reference to the sequence diagram in Figure 7.

[0066] Here, we assume that terminal 20 is in contact with source base station (Source gNB) 10-1, and that target base station (Target gNB) 10-2 has been specified as the handover destination.

[0067] In step SD1, the source base station 10-1 may include the proposal for using the inference model (aiModelOffer) received from the terminal 20 in a message requesting a handover and send it to the destination base station 10-2. The message may be, for example, a Handover Request message. If the source base station 10-1 is using a two-sided model before the handover is performed, it may store the aiModelOffer already received during negotiations between the terminal 20 and the source base station 10-1. The source base station 10-1 may include the stored aiModelOffer in a Handover Request message and send it to the destination base station 10-2.

[0068] On the other hand, if the source base station 10-1 is not using the two-sided model with the terminal 20 before the handover is performed, the aiModelOffer received from the terminal 20 may be included in the Handover Request message and sent to the destination base station 10-2.

[0069] In step SD2, the destination base station 10-2 may store the aiModelOffer.

[0070] In step SD3, the destination base station 10-2 may select an inference model that is available to its device in response to aiModelOffer. The destination base station 10-2 may also assign a shortened identifier to the selected inference model.

[0071] In step SD4, the destination base station 10-2 may set the selected inference model to a ready-to-use state.

[0072] In step SD5, the destination base station 10-2 may send a message to the source base station 10-1 that includes the information set in step SD3 as an answer (aiModelAnswer). Furthermore, the destination base station 10-2 may send a message to the source base station 10-1 that includes information (aiModelStatus) indicating that the inference model selected in step SD3 has been set to an available state. The message may be, for example, a Handover Request Acknowledge message, which is a message that is a response to a handover request. Both aiModelAnswer and aiModelStatus may be sent in the Handover Request Acknowledge message, or one may be sent in the Handover Request Acknowledge message and the other in a separate message.

[0073] In step SD6, the mobile base station 10-1 may send a message to the terminal 20 that includes a request to initiate a handover (Handover Command) including aiModelAnswer and aiModelStatus. The message may be, for example, an RRCReconfiguration message.

[0074] In step SD7, terminal 20 may set its own device's inference model, which corresponds to a model available to the destination base station 10-2, to a ready-to-use state.

[0075] In step SD8, terminal 20 may send a message to the destination base station 10-2, which is the handover destination, that includes a Handover Confirmation message, which includes information (aiModelStatus) indicating that the destination base station 10-2 has set its own device's inference model to a usable state corresponding to a model available to the destination base station 10-2. The message may be, for example, an RRCReconfigurationComplete message.

[0076] Note that steps SD4 and SD5 described above may be performed in any order. That is, after the destination base station 10-2 sends a message containing the answer regarding the selected inference model (for example, a Handover Request Acknowledge message) to the source base station 10-1, the destination base station 10-2 may set the selected inference model to a ready-to-use state.

[0077] Steps SD7 and SD8 described above may be performed in any order. That is, after the terminal 20 confirms the inference model selected at the destination base station 10-2 and sends a message including aiModelStatus to the destination base station 10-2, the terminal 20 may set the inference model of its own device corresponding to the inference model selected at the destination base station 10-2 to a ready-to-use state.

[0078] (Use Case) Next, an example of a use case for the two-sided model assumed in this embodiment will be described with reference to Figure 8.

[0079] Figure 8 shows an example of using a two-sided model for CSI (Channel State Information) compression. Such a CSI compression method may also be called AI-based CSI feedback and may be implemented, for example, using an autoencoder.

[0080] Figure 8 shows an example of CSI feedback using an encoder / decoder. Terminal 20 includes an encoder, which is an inference model, and base station 10 includes a decoder, which is an inference model. Terminal 20 inputs a CSI to the encoder and transmits information (CSI feedback information) that includes encoded bits output. Base station 10 inputs the bits of the received CSI feedback information to the corresponding decoder and obtains the output CSI.

[0081] The input CSI may include, for example, information on channel coefficients (elements of the channel matrix) or information on precoding coefficients (elements of the precoding matrix). In other words, the CSI may correspond to information on channel information in the spatial-frequency domain. Note that the input may also include information other than CSI.

[0082] The CSI output from the decoder may be a reconstructed CSI corresponding to the input to the encoder, or it may be a different CSI from the input to the encoder (for example, if the input information is channel coefficient information, it may be precoding coefficient information).

[0083] Furthermore, the encoder / decoder may include pre-processing of the input and post-processing of the output. The encoded bits are more compressed than the input information before encoding, and CSI feedback is expected to reduce communication overhead.

[0084] Alternatively, terminal 20 may use an inference model in channel coding processing to compress and encode the information bits. On the other hand, base station 10 can decode the compressed information bits transmitted from terminal 20 using an inference model.

[0085] Alternatively, terminal 20 may use an inference model in the modulation processing of the encoded signal to generate a modulated signal. On the other hand, base station 10 can demodulate the modulated signal transmitted from terminal 20 using the inference model.

[0086] In this way, by including mutually compatible inference models in the base station 10 and the terminal 20, more efficient signal compression and decoding processes can be achieved.

[0087] Furthermore, a two-sided model may be used for beam management, not limited to CSI compression. For example, the spatial domain downlink beam for beamset A may be predicted based on the measurement results for beamset B. Alternatively, the temporary downlink beam for beamset A may be predicted based on the measurement history of beamset B.

[0088] Furthermore, a two-sided model may be used to improve positioning accuracy. For example, positioning may be achieved directly using an AI / ML model. Alternatively, fingerprinting based on channel observations may be used as input to an inference model, and the terminal position may be output from the inference model. Or, AI / ML-assisted positioning may be achieved by outputting enhanced existing measurements and new measurements from the inference model.

[0089] For example, in estimating the terminal location, some of the inference may be performed using an inference model included in the base station 10, and the remaining inference may be performed using an inference model included in the terminal 20.

[0090] Furthermore, the information elements included in the above-mentioned message, such as "aiModelOffer," "aiModelAnswer," "ready to use," "aiModelStatus," "Handover Command," and "Handover Confirm," are merely listed to distinguish the corresponding information elements within the specification. They may be any name, and may be included in other information.

[0091] Furthermore, in the above-described embodiment, it is assumed that the identification of the inference model for common understanding between the base station 10 (or network) and the terminal 20 is determined by wireless communication (over-the-air signaling), but the invention is not limited to this, and the identifier of the inference model may be shared without wireless communication.

[0092] According to the embodiments described above, it is possible to improve the quality of the wireless section by using a coordinated inference model among multiple devices, such as the base station 10 and the terminal 20.

[0093] (Functional Configuration) Next, an example of the functional configuration of the base station 10 and terminal 20 that perform the processes and operations described above will be explained. The base station 10 and terminal 20 include functions to implement the embodiments described above. However, the base station 10 and terminal 20 may each be equipped with only some of the functions in the embodiments.

[0094] Figure 9 shows an example of the functional configuration of a base station 10 according to the embodiment. The base station 10 has a transmitting unit 110, a receiving unit 120, a setting unit 130, and a control unit 140. The functional configuration shown in Figure 9 is merely an example. The names of the functional categories and functional units can be anything as long as they can perform the operations according to the embodiment.

[0095] The transmitting unit 110 includes the function of generating a signal to be transmitted to the terminal 20 and transmitting the signal wirelessly. The transmitting unit 110 also transmits inter-network node messages to other network nodes.

[0096] The receiving unit 120 includes the function of receiving various signals transmitted from the terminal 20 and obtaining information from higher layers, for example, from the received signals. The transmitting unit 110 has the function of transmitting NR-PSS, NR-SSS, NR-PBCH, DL / UL control signals, etc. to the terminal 20. The receiving unit 120 also receives inter-network node messages from other network nodes.

[0097] The setting unit 130 stores pre-configured setting information and various setting information to be transmitted to the terminal 20. The content of the setting information includes, for example, the communication information described in this embodiment.

[0098] As described in the embodiment, the control unit 140 performs control related to signal transmission and reception and control related to the use of the inference model. The signal transmission function unit of the control unit 140 may be included in the transmission unit 110, and the signal reception function unit of the control unit 140 may be included in the reception unit 120.

[0099] Figure 10 is a diagram showing an example of the functional configuration of a terminal according to the embodiment. As shown in Figure 10, the terminal 20 has a transmitting unit 210, a receiving unit 220, a setting unit 230, and a control unit 240. The functional configuration shown in Figure 10 is merely an example. The names of the functional categories and functional units can be anything as long as they can perform the operations according to the embodiment.

[0100] The transmitting unit 210 creates a transmission signal from the transmission data and transmits the transmission signal wirelessly. Furthermore, for example, when performing D2D communication, the transmitting unit 210 may transmit PSCCH (Physical Sidelink Control Channel), PSSCH (Physical Sidelink Shared Channel), PSDCH (Physical Sidelink Discovery Channel), PSBCH (Physical Sidelink Broadcast Channel), etc., to other terminals 20.

[0101] The receiving unit 220 wirelessly receives various signals and acquires signals from higher layers based on the received physical layer signals. The receiving unit 220 also has the function of receiving NR-PSS, NR-SSS, NR-PBCH, DL / UL / SL control signals, etc. transmitted from the base station 10. When performing D2D communication, the receiving unit 120 may also receive PSCCH, PSSCH, PSDCH, or PSBCH, etc. from other terminals 20.

[0102] The setting unit 230 stores various setting information received from the base station 10 by the receiving unit 220 in its memory and reads it from the memory as needed. The setting unit 230 also stores pre-set setting information. The content of the setting information is, for example, the communication information described in this embodiment.

[0103] The control unit 240 controls the entire terminal 20, including control related to signal transmission and reception. Alternatively, the signal transmission function in the control unit 240 may be included in the transmission unit 210, and the signal reception function in the control unit 240 may be included in the reception unit 220.

[0104] Terminal 20 may report the following capabilities to base station 10: the capabilities of each operation described above, the capabilities of each option of an operation, or the capabilities of a combination of options, or the capabilities of each alternative in an operation, or the capabilities of a combination of alternatives.

[0105] Terminal 20 can report the above capabilities for each frequency. For example, the above capabilities may be reported for each terminal 20, each FR (Frequency Range) 1, FR2, FR2-1, FR2-2, each SCS (Subcarrier Spacing), each band or bandwidth, each BC (Band Combination), each FS (Feature Set), or each FSPC (Feature Set Per Component-carrier).

[0106] Terminal 20 can report the above capabilities for each cell. For example, the above capabilities may be reported for each terminal 20, each cell, or for each TDD (Time Division Duplex) and FDD (Frequency Division Duplex).

[0107] Throughout the above operations, whether or not they apply, which operations apply, or which options or alternatives are used may be determined, for example, by at least one of the following (a) through (g): (a) set by higher-layer parameters; (b) determined by relevant higher-layer parameters; (c) notified by MAC-CE (Media Access Control Control Element) or DCI (Downlink Control Information); (d) determined based on terminal 20 capabilities; (e) described in the operations described above; (f) determined based on the conditions described in the operations described above; (g) determined by the settings of higher-layer parameters / MAC-CE / DCI and reported terminal 20 capabilities.

[0108] Throughout the entire process, multiple options and alternatives can be combined into a single option or alternative.

[0109] As described in the above embodiments, the transmitting unit 210 may transmit a message to the source base station 10-1 that includes a suggestion regarding the use of an inference model. The receiving unit 220 may receive a message from the source base station 10-1 requesting the activation of a handover, which includes a response from the destination base station 10-2 regarding an inference model available to the suggestion. The control unit 240 may set the inference model of the terminal 20 that corresponds to an available model at the destination base station 10-2 to an available state.

[0110] The transmitting unit 210 may send a message to the destination base station 10-2 confirming the activation of the handover, which includes information about the inference model of the terminal 20 that has been set to a usable state.

[0111] The receiving unit 120 may receive a first message from the source base station 10-1 requesting a handover, which includes a suggestion regarding the use of an inference model. The transmitting unit 110 may send a second message to the source base station 10-1, which is a response to the handover request, which includes a response from the destination base station 10-2 regarding the inference models available to it. The control unit 140 may set the inference models available to the destination base station 10-2 to an available state.

[0112] The second message may further include information indicating the inference model available for use at the destination base station 10-2.

[0113] The receiving unit 120 may receive a first message from the terminal 20 that includes a suggestion regarding the use of an inference model. The transmitting unit 110 may send a second message to the destination base station 10-2 requesting a handover, which includes the suggestion. The receiving unit 120 may receive a third message from the destination base station 10-2 that is a response to the handover request, which includes a response from the destination base station 10-2 regarding an inference model available to the destination base station 10-2 in response to the suggestion. The transmitting unit 110 may send a fourth message to the terminal 20 requesting the activation of the handover, which includes the response.

[0114] (Hardware Configuration) The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are accessed directly or indirectly (for example, using wired or wireless connections) and these multiple devices are accessed. A functional block may be realized by combining the one or multiple devices with software.

[0115] For example, the base station 10, terminal 20, etc. in one embodiment of the present disclosure may function as a computer that processes the wireless communication method of the present disclosure. Figure 11 is a diagram showing an example of the hardware configuration of the base station 10 and terminal 20 according to one embodiment of the present disclosure. The above-described base station 10 and terminal 20 may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0116] In the following explanation, the term "device" can be read as a circuit, device, unit, module, chip, etc. The hardware configuration of the base station 10 and terminal 20 may include one or more of the devices shown in the figure, or it may be configured without some of the devices.

[0117] Each function in the base station 10 and terminal 20 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

[0118] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may consist of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the control unit 140, control unit 240, etc., described above may be implemented by the processor 1001.

[0119] Furthermore, the processor 1001 reads programs (program code), software modules, or data from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the control unit 140 of the base station 10 may be implemented by a control program stored in the memory 1002 and operated by the processor 1001, and other functional blocks may be implemented similarly. Also, for example, the control unit 240 of the terminal 20 may be implemented by a control program stored in the memory 1002 and operated by the processor 1001, and other functional blocks may be implemented similarly. The above-described processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from the network via a telecommunications line.

[0120] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM) (registered trademark), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for implementing a communication method according to one embodiment of this disclosure.

[0121] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital multipurpose disk, a Blu-ray® disk), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of the memory 1002 and the storage 1003.

[0122] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may include a high-frequency switch, duplexer, filter, frequency synthesizer, etc. For example, the transmitting / receiving antenna, amplifier section, transmitting / receiving section, transmission path interface, etc., may be implemented by the communication device 1004. The transmitting / receiving section may be implemented in a physically or logically separated manner, consisting of a transmitting section and a receiving section.

[0123] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0124] Furthermore, each device, such as the processor 1001 and the memory 1002, is accessed by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0125] Furthermore, the base station 10 and terminal 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0126] (Supplement to Embodiments) Although one embodiment of the present disclosure has been described above, the disclosed invention is not limited to such an embodiment, and those skilled in the art will understand various modifications, alterations, alternatives, substitutions, etc. Where specific numerical examples are used in the explanation to facilitate understanding of the present disclosure, unless otherwise specified, those numerical values ​​are merely examples and any appropriate values ​​may be used. Where items are separated in the above explanation, the separation of items is not essential, and matters described in two or more items may be used in combination as necessary, and matters described in one item may be applied to matters described in another item (as long as they do not contradict each other). The boundaries of functional units or processing units in the functional block diagram do not necessarily correspond to the boundaries of physical parts. The operation of multiple functional units may be physically performed by one part, or the operation of one functional unit may be physically performed by multiple parts. The processing procedures described in the embodiments may be rearranged as long as they do not contradict each other. For the convenience of explaining the processing, the base station 10 and terminal 20 have been described using functional block diagrams, but such devices may be realized in hardware, software, or a combination thereof. The software operated by the processor of the base station 10 according to the embodiment and the software operated by the processor of the terminal 20 according to the embodiment may be stored in any suitable storage medium such as random access memory (RAM), flash memory, read-only memory (ROM), EPROM, EEPROM, register, hard disk (HDD), removable disk, CD-ROM, database, server, or other appropriate storage medium.

[0127] Each aspect / embodiment described in this disclosure is LTE (Long Term Evolution), LTE-A (LTE-Advanced), IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 5G-A (5G-Advanced), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (where x is, for example, an integer or decimal)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), Open RAN (Open Radio Access Network), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE IEEE 802.11x (where x is any string such as b, a, g, n, ac, ax, be, bn, etc., and x=n is also referred to as Wi-Fi 4, x=ac as Wi-Fi 5, x=ax as Wi-Fi 6 or Wi-Fi 6E, x=be as Wi-Fi 7, x=bn as Wi-Fi 8, etc. Note that Wi-Fi is a registered trademark.), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems may be applied to at least one of these and next-generation systems that are extended, modified, created, or defined based on them. Multiple systems may also be applied in combination.

[0128] In this disclosure, terms such as "Base Station (BS)", "Radio Base Station", "Fixed Station", "NodeB", "eNodeB (eNB)", "gNodeB (gNB)", "Access Point (AP)", "Transmission Point (TP)", "Reception Point (RP)", "Transmission / Reception Point (TRP)", "Radio Unit (RU)", "Remote Unit (RU)", "Control Unit (CU)", "Distributed Unit (DU)", "Remote Radio Head (RRH)", "Node", "Gateway", "Ground Base Station", "Stratospheric Base Station", "Unmanned Aerial Vehicle", "High Altitude Platform Station (HAPS)", and "Airborne Platform" may be used interchangeably. Each cell contained within a base station may also be referred to by terms such as macrocell, small cell, femtocell, picocell, serving cell, or supercell. Each cell may also be called a "sector," "cell group," "carrier," "component carrier," "cluster," "bandwidth part (BWP)," or "carrier bandwidth."

[0129] In this disclosure, the transmission of information by a base station to a terminal may be interpreted as the base station instructing the terminal to perform control or operation based on the information.

[0130] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0131] A terminal may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, router (e.g., home router, mobile router, etc.), TCU (Telematics Control Unit), or several other appropriate terms.

[0132] A base station and a terminal may each consist of one or more devices. Devices constituting at least a part of each base station and terminal may be called transmitting devices, receiving devices, communication devices, etc. Devices constituting at least a part of each base station and terminal may be, for example, vehicles, transport vehicles, automobiles, motorcycles, bicycles, connected cars, excavators, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, handcarts, rickshaws, ships and other watercraft, airplanes, rockets, unmanned aerial vehicles, stratospheric base stations (e.g., High Altitude Platform Stations (HAPS)), artificial satellites (e.g., Low Earth Orbit (LEO) satellites, Middle Earth Orbit (MEO) satellites, Geostationary Earth Orbit (GEO) satellites), drones (registered trademark), multicopters, quadcopters, balloons, smart meters, sensors, and other IoT (Internet of Things) devices, or include, but are not limited to, objects or devices mounted on such objects. Furthermore, the object in question may be a moving object (hereinafter referred to as a "moving object"; this does not exclude the possibility of the moving object being in a stationary state) or a fixedly positioned object (hereinafter referred to as a "non-moving object").

[0133] Furthermore, the term "base station" in this disclosure may be interpreted as "terminal." For example, the various aspects / embodiments of this disclosure may be applied to configurations in which communication between a base station and a terminal is replaced with communication between multiple terminals (which may be called, for example, D2D (Device-to-Device), V2X (Vehicle-to-Everything), etc.) or communication over a non-terrestrial network (NTN). In this case, the terminal 20 may have at least some of the functions of the base station 10 described above. Also, terms such as "uplink" and "downlink" may be interpreted as terms corresponding to terminal-to-terminal communication (for example, "sidelink") or terms corresponding to NTN (for example, "feeder link"). For example, uplink channel or downlink channel may be interpreted as sidelink channel.

[0134] Furthermore, this disclosure is also applicable when at least some of the equipment constituting the base station and terminal operates outside of the ground (for example, in the atmosphere or in outer space).

[0135] Furthermore, the term "terminal" in this disclosure may be interpreted as "base station." In this case, the base station 10 may be configured to have the same functions as the terminal 20 described above.

[0136] Furthermore, notification of information is not limited to the embodiments described herein and may be carried out by other means. For example, notification of information may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling), broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or combinations thereof. RRC signaling may also be referred to as an RRC message or an Information Element within such RRC message. The RRC message may be a message used for, for example, controlling an RRC connection (e.g., setup, reconfiguration, establishment, reestablishment, release, or resume), mobility, measurement report, or notification of terminal capability, or it may be an information element within the message. Furthermore, the notification of information may be explicit or implicit. An explicit notification of information is the notification of the information itself, while an implicit notification of information may be the notification of information other than the information in question, or the notification of the information in question may be deemed to have been notified due to the fulfillment of certain conditions. In addition, the notification of information may include not only notifications between the same layer of different devices (e.g., between lower layers or upper layers of base station 10 and terminal 20), but also notifications between different layers within the same or different devices (e.g., notifications between lower and upper layers within base station 10 or terminal 20). Furthermore, the notification of information from one device to another may be carried out via one or more devices.

[0137] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they are consistent. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0138] The specific operations described in this disclosure as being performed by a base station may, in some cases, be performed by its upper node, or by a part of it (e.g., CU, RU, or DU). It is clear that various operations performed for communication with terminals in a RAN or CN may be performed by at least a part of the base station and other network nodes other than the base station. Although the above example illustrates the case where there is one other network node other than the base station, there may also be a combination of multiple other network nodes. Network nodes are, for example, nodes located in various core networks such as EPC and 5GC, but are not limited to these.

[0139] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0140] Radio resources can be defined by a combination of units of resources in one or more domains, such as the time domain, frequency domain, spatial domain, code domain, and power domain.

[0141] For example, resources in the time domain may be defined by one or more time units. Such one or more time units include, but are not limited to, at least one of the following: radio frame, subframe, slot, symbol, and transmission time interval (TTI). Furthermore, such time units may be fixed-length time units that do not depend on numerology, variable-length time units that depend on numerology, or both. Examples of fixed-length time units include, but are not limited to, subframes consisting of one or more slots, and radio frames containing multiple subframes. Examples of variable-length time units include, but are not limited to, symbols and slots containing a fixed number of symbols. Note that a certain time unit may be divided into shorter time units. Examples of shorter time units include, but are not limited to, mini-slots consisting of fewer symbols than the number of symbols that make up a slot. The time units described above may include, for example, time units used as units for scheduling, link adaptation, and the like.

[0142] Numerology refers to parameters that define the physical layer structure, and may be parameters based on at least one of the following: subcarrier spacing (SCS), symbol length, cyclic prefix length, and sampling time.

[0143] Resources in the frequency domain may be defined, for example, by one or more frequency units. Such one or more frequency units may include, for example, at least one of the following: a subcarrier, a resource block (RB), a bandwidth part (BWP), or a carrier bandwidth, but the names of the frequency units are not limited to these. Furthermore, the number of subcarriers included in a frequency unit may be a fixed number regardless of the neurology, or it may be a variable number that changes according to the neurology. For example, an RB may consist of a predetermined number of consecutive subcarriers in the frequency domain, and the number of subcarriers included in the RB may be the same regardless of the neurology, for example, 12, but is not limited to this. Similarly, a BWP may consist of, for example, one or more consecutive RBs within a certain carrier bandwidth, but is not limited to this. For terminal 20, one or more BWPs may be set within one carrier, and at least one of the BWPs may be activated.

[0144] Furthermore, resources in both the time domain and the frequency domain may be defined, for example, by one or more time / frequency units composed of time units and frequency units. Such time / frequency units are, but are not limited to, resource elements (REs) consisting of one symbol and one subcarrier, resource element groups (REGs) consisting of a predetermined number of REs, and control resource sets (CORESETs) consisting of a predetermined number of symbols and a predetermined number of RBs.

[0145] Furthermore, resources in the spatial domain may be defined by, for example, one or more spatial resources. Such spatial resources may be, but are not limited to, beams, MIMO (Multiple Input Multiple Output) layers, antenna ports, etc.

[0146] Furthermore, resources in the code domain may be defined by, for example, one or more code resources. Such code resources may be, but are not limited to, cyclic shifts (CS) or orthogonal spread codes (OCC).

[0147] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0148] In the above-described configuration of each device, the term "part" may be replaced with "means," "circuit," "device," etc.

[0149] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning. For example, at least one of a channel and a symbol may be a signal (signaling). A signal may also be a message.

[0150] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0151] Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during execution.

[0152] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are for illustrative purposes only and are not intended to be restrictive in any way. (Note) The following is added with respect to one embodiment of the present disclosure: [Note 1] A terminal comprising: a transmitting unit that transmits a message (Handover Request) including a proposal for the use of an inference model (aiModelOffer) to a source base station; (Step SD1) a receiving unit that receives a message (Handover Command) from the source base station requesting the activation of a handover, including a response (aiModelAnswer) regarding an inference model available to the destination base station in response to the proposal (aiModelOffer); (Step SD6) a control unit that sets the inference model of its own device corresponding to a model available to the destination base station to a usable state; and (Step SD7). [Note 2] The terminal described in Note 1, wherein the transmitting unit transmits a message (Handover Confirm, RRCReconfigurationComplete) to the destination base station, which includes information (aiModelStatus) regarding the inference model of the device set to a usable state, confirming the activation of the handover. (Step SD8) [Note 3] A base station comprising: a receiving unit that receives a first message (Handover Request) requesting a handover, which includes an offer (aiModelOffer) regarding the use of an inference model, from the source base station (Step SD1); and a transmitting unit that transmits a second message (Handover Request Acknowledge) to the source base station, which is a response to the handover request, which includes an answer (aiModelAnswer) regarding an inference model that the device can use in response to the offer (aiModelOffer), (Step SD5).[Note 4] A base station comprising: a receiving unit that receives a first message (aiModelOffer) from a terminal that includes a proposal regarding the use of an inference model; and a transmitting unit that transmits a second message (Handover Request) requesting a handover, including the proposal, (Step SD1) The receiving unit receives a third message (Handover Request Acknowledge) from the base station, which is a response to the handover request, including an answer (aiModelAnswer) regarding an inference model available to the base station in response to the proposal, (Step SD5) The transmitting unit transmits a fourth message (RRCReconfiguration) requesting the activation of the handover, including the answer, to the terminal, (Step SD6) [Note 5] A communication method performed by a terminal, comprising: sending a message to the source base station including a proposal regarding the use of an inference model; receiving a message from the source base station requesting the activation of a handover, which includes a response from the destination base station regarding an inference model that can be used in response to the proposal; and setting the inference model of the terminal's device corresponding to an available model to be used.

[0153] 10 Base station 10-1 Source base station 10-2 Destination base station 110 Transmitting unit 120 Receiving unit 130 Setting unit 140 Control unit 20 Terminal 210 Transmitting unit 220 Receiving unit 230 Setting unit 240 Control unit 1001 Processor 1002 Memory 1003 Storage 1004 Communication device 1005 Input device 1006 Output device 1007 Bus

Claims

1. A terminal comprising: a transmitting unit that transmits a message to a source base station containing a proposal regarding the use of an inference model; a receiving unit that receives a message from the source base station requesting the activation of a handover, which includes a response from the destination base station regarding an inference model available to the proposal; and a control unit that sets the inference model of its own device, corresponding to a model available to the destination base station, to a usable state.

2. The terminal according to claim 1, wherein the transmitting unit transmits a message to the destination base station confirming the activation of the handover, which includes information regarding the inference model of the device set to a usable state.

3. A base station comprising: a receiving unit that receives a first message requesting a handover from a mobile base station, which includes a proposal regarding the use of an inference model; and a transmitting unit that transmits a second message to the mobile base station, which is a response to the handover request, which includes a response regarding an inference model available to the device in response to the proposal.

4. A base station comprising: a receiving unit that receives a first message from a terminal containing a proposal regarding the use of an inference model; and a transmitting unit that transmits a second message requesting a handover, containing the proposal, wherein the receiving unit receives a third message from the base station that is a response to the handover request, containing a response from the base station regarding an inference model available to the base station in response to the proposal; and the transmitting unit transmits a fourth message requesting the activation of the handover, containing the response, to the terminal.

5. A communication method performed by a terminal, comprising: sending a message to a source base station including a proposal regarding the use of an inference model; receiving a message from the source base station requesting the activation of a handover, which includes a response from the destination base station regarding an available inference model to the proposal; and setting the inference model of the terminal's device to an available state, corresponding to a model available to the destination base station.

Images