Method and device for transmitting artificial intelligence model in wireless communication system

Abstract

An operation method of a source base station according to embodiments of the present disclosure comprises the steps of: transmitting an artificial intelligence model information request message to first candidate base stations or an access and mobility management function (AMF) entity for handover; receiving information about at least one artificial intelligence model from the first candidate base stations; selecting a first artificial intelligence model on the basis of the received information about the at least one artificial intelligence model; and transmitting the first artificial intelligence model to a terminal.

Description

Method and device for transmitting artificial intelligence models in wireless communication systems

[0001] The present disclosure relates to a method and device for transmitting an artificial intelligence model in a wireless communication system. Specifically, the present disclosure relates to a method and device for transmitting an artificial intelligence model in connection with a handover of a terminal in a wireless communication system.

[0002] Looking back at the evolution of wireless communication over successive generations, technologies have primarily been developed for human-facing services such as voice, multimedia, and data. With the commercialization of the 5G (5th Generation) communication system, an explosive increase in connected devices is expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction equipment, and factory equipment. Mobile devices are also expected to evolve into diverse form factors, such as augmented reality glasses, virtual reality headsets, and holographic devices. In the 6G (6th Generation) era, efforts are being made to develop improved 6G communication systems to connect hundreds of billions of devices and objects and provide diverse services. For this reason, 6G communication systems are often referred to as "beyond 5G."

[0003] The 6G communication system, expected to be realized around 2030, will have a maximum transmission speed of terabytes (i.e., 1,000 gigabits) per second (bps) and a wireless latency of 100 microseconds (μsec). In other words, compared to 5G, the transmission speed in a 6G communication system will be 50 times faster and the wireless latency will be reduced to one-tenth.

[0004] To achieve these high data rates and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz (THz) band (e.g., from 95 gigahertz (GHz) to 3 terahertz (THz)). Compared to the millimeter wave (mmWave) band introduced in 5G, the terahertz band is expected to have more severe path loss and atmospheric absorption, making it more important to develop technologies that can guarantee signal reach, or coverage. Key technologies to ensure coverage include Radio Frequency (RF) components, antennas, new waveforms that offer better coverage than Orthogonal Frequency Division Multiplexing (OFDM), beamforming, and multiple antenna transmission technologies such as massive Multiple-Input and Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing using Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, in order to improve frequency efficiency and system network, 6G communication systems are developing full duplex technology that utilizes the same frequency resources at the same time for uplink and downlink; network technology that integrates satellites and HAPS (High-Altitude Platform Stations); network structure innovation technology that supports mobile base stations and enables optimization and automation of network operation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes AI (Artificial Intelligence) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services with complexity that exceeds the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources (Mobile Edge Computing (MEC), cloud, etc.). In addition, efforts are being made to further strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase the openness of wireless communications through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe use of data, and the development of technologies for maintaining privacy.

[0006] Research and development of these 6G communication systems are expected to enable a new level of hyper-connected experience through the hyper-connectivity of 6G communication systems, which encompass not only connections between things but also connections between people and things. Specifically, 6G communication systems are expected to enable services such as truly immersive eXtended Reality (XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems through enhanced security and reliability, will be applied in diverse fields such as industry, medicine, automobiles, and home appliances.

[0007] The present disclosure may have as its primary purpose a method and device for transmitting an artificial intelligence model related to handover in a communication system such as 5G, 5G-Advanced, and 6G.

[0008] A method performed by a base station in a wireless communication system according to embodiments of the present disclosure includes the steps of transmitting an artificial intelligence model information request message to first candidate base stations for handover or an access and mobility management function (AMF) entity, receiving information about at least one artificial intelligence model from the first candidate base stations, selecting a first artificial intelligence model based on the received information about at least one artificial intelligence model, and transmitting the first artificial intelligence model to a terminal.

[0009] In one embodiment, the method according to embodiments of the present disclosure may further include the step of transmitting an RRC (radio resource control) reset message including timer information for storing an artificial intelligence model to the terminal.

[0010] In one embodiment, the method according to embodiments of the present disclosure may further include receiving at least one artificial intelligence model from the first candidate base stations based on the user plane.

[0011] In one embodiment, a method according to embodiments of the present disclosure may further include the step of transmitting a message for requesting a first artificial intelligence model to an AMF entity and the step of receiving the first artificial intelligence model from a user plane function (UPF) entity based on a control plane.

[0012] In one embodiment, the method according to embodiments of the present disclosure further comprises the step of identifying a priority of at least one artificial intelligence model based on information about at least one artificial intelligence model, wherein the first artificial intelligence model can be selected based on the priority of the at least one artificial intelligence model.

[0013] In one embodiment, the priority of at least one AI model may be identified based on the strength of the reference signal for the first candidate base stations or the type of the at least one AI model.

[0014] In one embodiment, a method according to embodiments of the present disclosure may include the steps of receiving information indicating whether a first artificial intelligence model is received from a terminal and transmitting information indicating whether the first artificial intelligence model is received by the terminal to one of the first candidate base stations.

[0015] In one embodiment, the information about at least one artificial intelligence model includes size information of the at least one artificial intelligence model, and the method according to embodiments of the present disclosure may further include a step of identifying at least one second candidate base station from the first candidate base stations based on the size information of the at least one artificial intelligence model.

[0016] In one embodiment, a method according to embodiments of the present disclosure may further include the steps of transmitting a handover request message to at least one second candidate base station and receiving a first artificial intelligence model from at least one second candidate base station.

[0017] In one embodiment, a method according to embodiments of the present disclosure further includes the step of receiving information indicating whether a first artificial intelligence model is received from a terminal and the step of transmitting information indicating whether the first artificial intelligence model is received by the terminal to one of the second candidate base stations.

[0018] The method and device according to embodiments of the present disclosure can provide an effective operation for transmitting an artificial intelligence model in connection with handover in a wireless communication system.

[0019] Specifically, embodiments of the present disclosure transmit and receive an artificial intelligence model between a terminal and a base station in relation to a handover, thereby reducing delay by applying the artificial intelligence model of the terminal immediately after the handover, effectively performing transmission of the artificial intelligence model to multiple candidate cells, and minimizing repeated transmission and reception operations of the artificial intelligence model due to repetition of handover execution and preparation.

[0020] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0021] The features and advantages of the embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0022] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0023] FIG. 2 is a drawing for explaining the structure of a terminal according to embodiments of the present disclosure.

[0024] FIG. 3 is a diagram for explaining the structure of a network entity (or base station) according to embodiments of the present disclosure.

[0025] FIG. 4 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0026] FIG. 5 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0027] FIG. 6 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0028] FIG. 7 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0029] FIG. 8 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0030] FIG. 9 illustrates the operation of a terminal and a base station for an artificial intelligence model transmission method related to conditional handover according to embodiments of the present disclosure.

[0031] FIG. 10 illustrates an operation flowchart of a source base station for a wireless link failure prediction method according to embodiments of the present disclosure.

[0032] Embodiments of the present disclosure may address the problems and / or disadvantages described above and provide the advantages described below. One aspect of the present disclosure may provide a network entity (or node) and a communication method thereof in a wireless communication system.

[0033] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0034] The various embodiments of the present disclosure described below illustrate hardware-based approaches. However, since the various embodiments of the present disclosure encompass techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude software-based approaches.

[0035] Additionally, although various embodiments of the present disclosure describe various embodiments using terminology used in certain communication standards (e.g., 3rd generation partnership project (3GPP)), this is merely an example for illustrative purposes. Various embodiments of the present disclosure can be easily modified and applied to other communication systems.

[0036] Hereinafter, various embodiments of the present disclosure will be described.

[0037] FIG. 1 illustrates a wireless communication system according to embodiments of the present disclosure.

[0038] FIG. 1 illustrates some of the nodes utilizing a wireless channel in a wireless communication system, including a base station (110), a first terminal (120), and / or a second terminal (130). Although FIG. 1 illustrates only one base station, this is merely an example. The wireless communication system of FIG. 1 may further include other base stations identical or similar to the base station (110).

[0039] The base station (110) is a network infrastructure that provides wireless access to terminals (120, 130). The base station (110) has coverage defined as a certain geographical area based on the distance at which a signal can be transmitted. In addition to the base station, the base station (110) may be referred to as an 'access point (AP)', 'evolved Node B (eNB)', 'next generation node B (gNB)', '5G node (5th generation node)', 'wireless point', 'transmission / reception point (TRP)', or other terms having equivalent technical meanings.

[0040] The first terminal (120) and the second terminal (130) are each devices used by a user and can communicate with the base station (110) via a wireless channel. At least one of the first terminal (120) or the second terminal (130) can be operated without the user's intervention. For example, at least one of the first terminal (120) or the second terminal (130) may be a device that performs machine type communication (MTC) and may not be carried by the user. Each of the first terminal (120) and the second terminal (130) may be referred to as a terminal, or other terms having equivalent technical meanings, such as 'user equipment (UE),' 'mobile station,' 'subscriber station,' 'customer premises equipment (CPE),' 'remote terminal,' 'wireless terminal,' 'electronic device,' or 'user device.'

[0041] The base station (110), the first terminal (120), and the second terminal (130) can transmit and / or receive wireless signals in the millimeter wave (mmWave) band (e.g., 28 GHz, 30 GHz, 38 GHz, 60 GHz). At this time, in order to improve channel gain, the base station (110), the first terminal (120), and / or the second terminal (130) can perform beamforming.

[0042] Beamforming may include transmit beamforming and / or receive beamforming. That is, the base station (110), the first terminal (120), and / or the second terminal (130) may impart directionality to the transmit signal or the receive signal. To impart directionality to the receive signal, the base station (110) and / or the terminals (120, 130) may select serving beams (112, 113, 121, 131) through a beam search or beam management procedure. After the serving beams (112, 113, 121, 131) are selected, subsequent communication may be performed through resources that are in a quasi-co-located (QCL) relationship with the resources that transmitted the serving beams (112, 113, 121, 131).

[0043] The base station (110), the first terminal (120), and the second terminal (130) of the present disclosure may each be a transmitting apparatus, a transmitting node, a receiving apparatus, and / or a receiving node. For example, the base station (110) may transmit an RF (radio frequency) signal to the first terminal (120). The base station (110) may receive the RF signal from the first terminal (120). As another example, the first terminal (120) may transmit an RF signal to the base station (110) or the second terminal (130). The first terminal (120) may receive the RF signal from the base station (110) or the second terminal (130).

[0044] Figure 2 is a drawing for explaining the structure of a terminal according to embodiments.

[0045] Referring to FIG. 2, a terminal (200) according to embodiments may include a transceiver (transmitting and receiving unit) (210), a memory (220), and / or a processor (230). In the present disclosure, the terminal (200) is described as including the transceiver (210), the memory (220), and / or the processor (230), but this is merely an example. For example, the terminal (200) may further include other components in addition to the transceiver (210), the memory (220), and the processor (230).

[0046] According to embodiments, the transceiver (210), memory (220), and processor (230) may be implemented or formed as separate chips. However, this is merely an example, and the transceiver (210), memory (220), and / or processor (230) may be implemented or formed as a single chip.

[0047] According to embodiments, the transceiver (210) may include at least one transmitter and / or at least one receiver. For example, the transceiver (210) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (210) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0048] The configurations of the transceiver (210) described in the present disclosure are merely examples, and the configuration of the transceiver (210) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (210) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0049] According to embodiments, the transceiver (210) may transmit or receive a signal to the processor (230). For example, the transceiver (210) may transmit or deliver an RF signal received via a wireless communication channel to the processor (230). The transceiver (210) may receive or deliver an RF signal from the processor (230).

[0050] According to embodiments, the transceiver (210) may be referred to as a UE transmitter or a UE receiver.

[0051] According to embodiments, the transceiver (210) may transmit a signal to a base station (e.g., base station (110) of FIG. 1) or a network entity (e.g., access and mobility management function (AMF) entity) or receive a signal from the base station or the network entity. In embodiments, the transmitted or received signal may include a control signal and data.

[0052] According to embodiments, the memory (220) may include or store programs and data necessary for the operations of the terminal (200). For example, the memory (220) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration of the terminal (200) (e.g., a processor (230) or a transceiver (210)). The memory (220) may store control information or data including a signal acquired by the terminal (200). In embodiments, the memory (220) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0053] According to embodiments, the processor (230) may include one processor or multiple processors. For example, the processor (230) may include a communication processor. For example, the processor (230) may include a communication processor and / or an application processor.

[0054] According to embodiments, the processor (230) may control a series of processes performed by the terminal (200). For example, the transceiver (210) may receive a data signal including control information transmitted by a base station or network entity. The processor (230) may process the received control signal and data signal.

[0055] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of the terminal (200). For example, the term "processor" may be replaced with a controller or a computing circuit.

[0056] The terminal (200) of the present disclosure may correspond to the first terminal (120) and / or the second terminal (130) of FIG. 1.

[0057] FIG. 3 is a drawing for explaining the structure of a network entity (or base station) according to embodiments.

[0058] Referring to FIG. 3, a network entity (300) according to embodiments may include a transceiver (transmitter / receiver) (310), a memory (320), and / or a processor (330). Although the network entity (300) is described in the present disclosure as including the transceiver (310), the memory (320), and / or the processor (330), this is merely an example. For example, the network entity (300) may further include other components in addition to the transceiver (310), the memory (320), and the processor (330). The network entity (300) may represent network functions included in a base station or other core network.

[0059] According to embodiments, the transceiver (310), memory (320), and processor (330) may be implemented or formed as separate chips, respectively. However, this is merely an example, and the transceiver (310), memory (320), and / or processor (330) may be implemented or formed as a single chip.

[0060] According to embodiments, the transceiver (310) may include at least one transmitter and / or at least one receiver. For example, the transceiver (310) may include an RF transmitter for amplifying and up-converting the frequency of a transmitted signal. The transceiver (310) may include an RF receiver for down-converting the frequency of a received signal and amplifying low-noise.

[0061] The configurations of the transceiver (310) described in the present disclosure are merely examples, and the configuration of the transceiver (310) is not limited to an RF transmitter and an RF receiver. For example, the transceiver (310) may further include a coupler to ensure isolation between the RF transmitter and the RF receiver.

[0062] According to embodiments, the transceiver (310) may transmit or receive a signal to the processor (330). For example, the transceiver (310) may transmit or deliver an RF signal received via a wireless communication channel to the processor (330). The transceiver (310) may receive or deliver an RF signal from the processor (230).

[0063] According to embodiments, the transceiver (310) may be referred to as a network entity transmitter or a network entity receiver.

[0064] According to embodiments, the transceiver (310) may transmit a signal to the terminal (200) or receive a signal from the terminal (200). In embodiments, the transmitted or received signal may include a control signal and data.

[0065] According to embodiments, the memory (320) may include programs and data necessary for the operations of the network entity (300). For example, the memory (320) may be a non-transitory memory, and a program stored in the non-transitory memory may be organically combined with a hardware configuration (e.g., a processor (330) or a transceiver (310)) of the network entity (300). The memory (320) may store control information or data including a signal acquired by the network entity (300). In embodiments, the memory (320) may include a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, a DVD, and / or a storage medium.

[0066] According to embodiments, the processor (330) may include one processor or multiple processors. For example, the processor (330) may include a communication processor. For example, the processor (330) may include a communication processor and / or an application processor.

[0067] According to embodiments, the processor (330) may control a series of processes performed by the network entity (300). For example, the transceiver (310) may receive a data signal including control information transmitted by the network entity. The processor (330) may process the received control signal and data signal.

[0068] The term "processor" in the present disclosure may be replaced with various terms referring to a configuration that executes or performs operations of a network entity (300). For example, the term "processor" may be replaced with a controller or a computing unit.

[0069] The network entity (300) of the present disclosure may correspond to the base station (110) of FIG. 1.

[0070] The devices described in FIGS. 2 and 3 may correspond to devices of a transmitter or receiver. A terminal or network entity according to embodiments of the present disclosure may be a transmitter if it is a transmitter, and may be a receiver if it is a receiver.

[0071] Hereinafter, the transmitter and receiver may each refer to the terminals or network entities described in FIGS. 1 to 3 above. When describing downlink signals, the network entity will be the transmitter and the terminal will be the receiver, and when describing uplink signals, the terminal will be the transmitter and the network entity will be the receiver.

[0072] FIG. 4 illustrates the operations of a terminal and a base station for an artificial intelligence model transmission method according to embodiments of the present disclosure. The terminal and base station for performing the operations described in FIG. 4 may correspond to the terminal of FIG. 2 and the network entity of FIG. 3 , respectively.

[0073] Referring to FIG. 4, transmission and reception operations of a terminal (UE) (410), a source base station (412) for a serving cell, a candidate base station (414), and network entities are illustrated in relation to a conditional handover (CHO) of the terminal (410). Specifically, the embodiment of FIG. 4 may represent an embodiment in which, in a preparation procedure for a conditional handover, the terminal (410) receives artificial intelligence / machine learning model (AI / ML model) information about candidate base stations (414) based on a user plane (UP).

[0074] In operation 432, the terminal (410) may receive an RRC reconfiguration message from the source base station (412). The RRC reconfiguration message may include configuration information related to the operation of the terminal (410). Specifically, the configuration information may include timer information regarding a period during which the terminal (410) stores an AI model. Accordingly, the terminal (410) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (410) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (410) hands over to a specific cell and then hands over to the previous cell again within a short period of time, it does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, by storing the artificial intelligence model until the timer expires, the conditional handover preparation procedure is repeated, so that unnecessary procedures in which the artificial intelligence model previously received by the terminal (410) in the conditional handover preparation procedure is deleted and retransmitted in the repeated procedure can be minimized.

[0075] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, Table 1 below shows the timer when the Index value is 0. The AI ​​model storage time may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0076] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal during the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 below is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0077] Table 1 below can show the types of timer information.

[0078]

[0079] Table 2 below can show the specific AI model storage time for timer information.

[0080]

[0081] As shown in Table 1 and Table 2, the type of timer information and the storage time of the artificial intelligence model can be indicated by the index value.

[0082] In operation 434, the terminal (410) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (412) to the terminal (410) via an RRC reset message in operation 432.

[0083] In operation 436, the terminal (410) may transmit a measurement report to the source base station (412). In relation to conditional handover, the terminal (410) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (412).

[0084] In operation 438, the source base station (412) may determine a conditional handover based on a measurement report received from the terminal (410). While determining the conditional handover, the source base station (412) may determine a candidate cell (or candidate base station) to which the terminal (410) can hand over.

[0085] In operation 440, the source base station (412) can transmit a handover request message to candidate base stations (414) to which the terminal (410) can handover, and can receive an ACK message indicating that the handover request message has been received from the candidate base stations (414).

[0086] In operation 442, the source base station (412) may transmit an AI model information request message to the candidate base stations (414). The AI ​​information request message transmitted from the source base station (412) to the candidate base stations (414) may be a message requesting information about an AI model that must be transmitted through a user plane. That is, the source base station (412) may request the candidate base stations (414) for information about an AI model that cannot be transmitted through a control plane (CP) between the candidate base stations and the source base station due to reasons such as the size of the AI ​​model and must be transmitted through the user plane.

[0087] In operation 444, the source base station (412) may transmit a handover command to the terminal (410). Here, the transmission of the handover command may be performed based on the source base station (412) receiving an ACK message from the candidate base stations (414). Accordingly, the order of operation 444 may be positioned after operation 440. However, the order of operation 444 may be changed with other operations, such as operations 442 to 448.

[0088] In operation 446, the source base station (412) receives artificial intelligence model information for each candidate base station from candidate base stations (414). Specifically, the artificial intelligence model information may include information on an artificial intelligence model that should be transmitted through the user plane among the artificial intelligence models for each candidate base station (414).

[0089] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Accordingly, if the identifier of the AI ​​model for the source base station (412) and the identifier of the AI ​​model for the candidate base station (414) are the same, the terminal (410) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (414), thereby preventing unnecessary transmission and reception operations.

[0090] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0091] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (410) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (410) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The candidate base station (414) sets priority information for the AI ​​model, and the information may be included in the AI ​​model information and transmitted to the source base station (412). The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0092] In one embodiment, an AI model may have a base model commonly used in multiple cells, and when a base model exists, the transmission priority of an AI model related to a case in which the base model is applied may be set low. That is, an AI model related to a case in which the base model is used may be transmitted to a terminal (410) after the handover is completed. In operation 448, the source base station (412) may select an AI model based on the AI ​​model information received in operation 442. At this time, the selection may be selecting an AI model to which an access and mobility management function (AMF) entity (416) is to be requested to transmit.

[0093] In one embodiment, the source base station (412) can set the transmission priority of the AI ​​models for each candidate base station (414) based on the AI ​​model information, and select the AI ​​model to request from the AMF entity (416) based on the set priority. That is, the source base station (412) can set the transmission priority for a plurality of AI models for a plurality of candidate base stations (414), and select the AI ​​model based on the set priority.

[0094] In one embodiment, the source base station (412) may select artificial intelligence models by considering the strength of signals (e.g., RSRP, RSRQ, etc.) for candidate base stations (or candidate cells) included in a measurement report received from the terminal (410) by operation 436. For example, the priority of the artificial intelligence model for a candidate base station with a low signal strength may be set lower than the priority of the artificial intelligence model for a candidate base station with a high signal strength, and the source base station (412) may preferentially select the artificial intelligence model for the candidate base station with a high signal strength.

[0095] In operation 450, the source base station (412) may request the AMF entity (416) to transmit the selected artificial intelligence model.

[0096] In one embodiment, for an AI model that is commonly used in multiple candidate base stations (414), if the source base station (412) selects to transmit the AI ​​model to the terminal (410), the source base station (412) may request the AMF entity (416) to prevent duplicate transmission requests for the AI ​​models. For example, if AI models 1, 2, and 3 are used for candidate base station 1 with a high priority, and AI models 1, 4, and 5 are used for candidate base station 2 with a low priority, and the source base station requests the AMF entity to transmit AI model 1, the source base station may request the AMF entity to transmit AI model 1 in the transmission request for the AI ​​model for candidate base station 1, and may not request the transmission of AI model 1 in the transmission request for the AI ​​model for candidate base station 2. In other words, duplicate transmission of AI model 1 may be prevented.

[0097] In one embodiment, the source base station (412) may sequentially request AI models for each candidate base station from the AMF entity (416) for each AI model.

[0098] In one embodiment, the source base station (412) may request the AMF entity (416) to select AI models based on priorities among the AI ​​models for all candidate base stations.

[0099] In one embodiment, the source base station (412) may sequentially request the AMF entity (416) for the AI ​​models for each candidate base station. For example, if the AI ​​models for candidate base station 1 are A, B, and C, and the AI ​​models for candidate base station 2 are D and E, the source base station may sequentially request the AMF entity to transmit AI models A, B, and C for candidate base station 1, and to transmit AI models D and E for candidate base station 2.

[0100] In operation 452, the AMF entity (416) that received the request for transmitting the artificial intelligence model transmits and receives the artificial intelligence model according to a network procedure previously agreed upon with other network entities, such as the Session management function (SMF) entity (418), the User plane function (UPF) entity (420), or the Network data analytics function (NWDAF) entity (422), and as a result, the UPF entity (420) can receive the artificial intelligence model requested by the source base station (412) from the NWDAF entity (422).

[0101] In operation 454, the UPF entity (420) can transmit an artificial intelligence model to the source base station (412) based on a user plane, and the source base station (412) can transmit the artificial intelligence model to the terminal (410) based on a user plane. That is, the artificial intelligence models can be transmitted by transmitting user data through a PDU session.

[0102] In operation 456, the terminal (410) may transmit an ACK message to the source base station (412) to inform it of the received artificial intelligence model. Based on the received ACK message, the source base station (412) may identify the artificial intelligence model received by the terminal (410) among the artificial intelligence models transmitted by the source base station (412) to the terminal (410) in operation 454.

[0103] In operation 458, the source base station (412) may transmit information about the artificial intelligence model possessed by the terminal (410) to the candidate base station (414). The information about the artificial intelligence model possessed by the terminal (410) may be based on the ACK message received by the source base station (412) in operation 456.

[0104] In one embodiment, operation 458 may represent an operation in which the source base station (412) transmits information about an artificial intelligence model held by the terminal (410) to the determined target base station after the source base station (412) determines the target base station for conditional handover of the terminal (410). That is, the source base station (412) may transmit the information to a single determined target base station (or target cell) rather than to multiple candidate base stations.

[0105] In one embodiment, operation 458 may represent an operation in which a source base station (412) transmits information about an artificial intelligence model it possesses to a target base station after uplink synchronization through a random access channel (RACH) procedure.

[0106] In one embodiment, actions 454, 456, and 458 may be repeated actions per artificial intelligence model.

[0107] Action 460 may represent a conditional handover execution procedure.

[0108] In describing embodiments of the present disclosure, a source base station may correspond to a serving cell, a candidate base station may correspond to a candidate cell, and a target base station may correspond to a target cell. According to embodiments of the present disclosure, when a terminal prepares to handover from a serving cell to a target cell, the terminal may receive an artificial intelligence model associated with the candidate cell in advance through the user plane or the control plane.

[0109] In one embodiment, the source base station may correspond to a serving cell, and the candidate base station may correspond to the candidate cell. Additionally, the target base station may correspond to the target cell.

[0110] FIG. 5 illustrates the operations of a terminal and a base station for a wireless link failure prediction method according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 5 may represent an embodiment in which a terminal (510) receives artificial intelligence / machine learning model (AI / ML model) information about candidate base stations (514) based on a control plane (CP).

[0111] The terminal and base station performing the operations described in FIG. 5 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0112] In operation 532, the terminal (510) may receive an RRC reconfiguration message from the source base station (512). The RRC reconfiguration message may include configuration information related to the operation of the terminal (510). Specifically, the configuration information may include timer information regarding a period during which the terminal (510) stores an AI model. Accordingly, the terminal (510) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (510) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (510) hands over to a specific cell and then hands over to the previous cell again within a short period of time, it does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, since the terminal (510) stores the artificial intelligence model until the timer expires, when the conditional handover preparation procedure is repeated, the unnecessary procedure of deleting the artificial intelligence model previously received by the terminal (510) in the conditional handover preparation procedure and receiving it again in the repeated procedure can be minimized.

[0113] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, the timer is indicated when the Index value is 0 in Table 1 described above. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0114] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal in the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 described above is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0115] In operation 534, the terminal (510) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (512) to the terminal (510) via an RRC reset message in operation 532.

[0116] In operation 536, the terminal (510) may transmit a measurement report to the source base station (512). In relation to conditional handover, the terminal (510) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (512).

[0117] In operation 538, the source base station (512) may determine a conditional handover based on a measurement report received from the terminal (510). While determining the conditional handover, the source base station (512) may determine a candidate cell (or candidate base station) to which the terminal (510) can hand over.

[0118] In operation 540, the source base station (512) can transmit a handover request message to candidate base stations (514) to which the terminal (510) can handover, and can receive an ACK message indicating that the handover request message has been received from the candidate base stations (514).

[0119] In operation 542, the source base station (512) may transmit an AI model information request message to the candidate base stations (514). The AI ​​information request message transmitted from the source base station (512) to the candidate base stations (514) may be a message requesting information about an AI model that must be transmitted through a control plane. That is, the source base station (512) may request the candidate base stations (514) for information about an AI model that can be transmitted between the candidate base stations and the source base station through a control plane (CP) due to reasons such as the size of the AI ​​model.

[0120] In one embodiment, the source base station (512) requests information on artificial intelligence models for candidate base stations (514), and each of the candidate base stations (514) can distinguish between artificial intelligence models that should be transmitted through the user plane and artificial intelligence models that should be transmitted through the control plane. In addition, the candidate base stations (514) can transmit the artificial intelligence models that can be transmitted through the control plane to the source base station (512).

[0121] In operation 544, the source base station (512) may transmit a handover command to the terminal (510). Here, the transmission of the handover command may be performed based on the source base station (512) receiving an ACK message from the candidate base stations (514). Accordingly, the order of operation 544 may be positioned after operation 540. However, the order of operation 544 may be changed with other operations, such as operations 542 to 548.

[0122] In operation 546, the source base station (512) can receive an artificial intelligence model for each candidate base station from the candidate base stations (514) through the control plane.

[0123] In operation 548, the source base station (512) receives artificial intelligence model information for each candidate base station from the candidate base stations (514). Specifically, the artificial intelligence model information may include information about an artificial intelligence model that must be transmitted through the control plane among the artificial intelligence models for each candidate base station (514) and / or information about an artificial intelligence model that the source base station (512) received through the control plane in operation 546.

[0124] In one embodiment, operations 546 and 548 may be performed concurrently.

[0125] In one embodiment, the AI ​​model information of the 548 operation may include AI model information about candidate base stations that can be transmitted based on the user plane or the control plane.

[0126] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Therefore, if the identifier of the AI ​​model for the source base station (512) and the identifier of the AI ​​model for the candidate base station (414) are the same, the terminal (510) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (514), thereby preventing unnecessary transmission and reception operations.

[0127] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0128] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (510) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (510) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The candidate base station (514) may set priority information for the AI ​​model and transmit it to the source base station (512) as AI model information. The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0129] In one embodiment, the AI ​​model may have a base model commonly used in multiple cells, and if the base model exists, the transmission priority of the AI ​​model related to the case where the base model is used may be set low. In other words, the AI ​​model related to the case where the base model is applied may be transmitted to the terminal (510) after the handover is completed.

[0130] In operation 550, the source base station (512) may select an artificial intelligence model based on the artificial intelligence model information received in operation 548. At this time, the artificial intelligence model selection includes selecting an artificial intelligence model to be transmitted to the terminal (510) via the control plane.

[0131] In one embodiment, the source base station (512) can set the transmission priority of the AI ​​models for each candidate base station (514) based on the AI ​​model information, and select the AI ​​model to be transmitted to the terminal (510) based on the set priority. That is, the source base station (512) can set the transmission priority for a plurality of AI models for a plurality of candidate base stations (514), and select the AI ​​model based on the set priority.

[0132] In one embodiment, the source base station (512) may select artificial intelligence models by considering the strength of signals (e.g., RSRP, RSRQ, etc.) for candidate base stations (or candidate cells) included in a measurement report received from the terminal (510) by operation 536. For example, the priority of the artificial intelligence model for a candidate base station with a low signal strength may be set lower than the priority of the artificial intelligence model for a candidate base station with a high signal strength, and the source base station (512) may preferentially select the artificial intelligence model for the candidate base station with a high signal strength.

[0133] In one embodiment, in operation 548, the source base station (512) receives artificial intelligence model information, and in operation 550, the source base station (512) selects an artificial intelligence model based on the received artificial intelligence model information, and then requests a candidate base station to transmit the selected artificial intelligence model (not shown), and may receive the selected artificial intelligence model from the candidate base station. That is, after operation 550, operation 546 may be performed after requesting the candidate base station to transmit the selected artificial intelligence model.

[0134] In operation 552, the source base station (512) can transmit the selected artificial intelligence model to the terminal (510) through the control plane.

[0135] In one embodiment, the source base station (512) may sequentially transmit the artificial intelligence models for each candidate base station to the terminal (510) for each artificial intelligence model.

[0136] In one embodiment, the source base station (512) may transmit to the terminal (510) the selected artificial intelligence models based on the priority among the artificial intelligence models for all candidate base stations.

[0137] In operation 554, the terminal (510) may transmit an ACK message to the source base station (512) to inform it of the received artificial intelligence model. Based on the received ACK message, the source base station (512) may identify the artificial intelligence model received by the terminal (510) among the artificial intelligence models transmitted by the source base station (512) to the terminal (510) in operation 552.

[0138] In operation 556, the source base station (512) may transmit information about the artificial intelligence model possessed by the terminal (510) to the candidate base station (414). The information about the artificial intelligence model possessed by the terminal (510) may be based on the ACK message received by the source base station (512) in operation 554.

[0139] In one embodiment, operation 556 may represent an operation in which the source base station (512) transmits information about an artificial intelligence model held by the terminal (510) to the determined target base station after the source base station (512) determines the target base station for conditional handover of the terminal (510). That is, the source base station (512) may transmit the information to a single determined target base station (or target cell) rather than to multiple candidate base stations.

[0140] In one embodiment, operation 556 may represent an operation in which a source base station (512) transmits information about an artificial intelligence model it possesses to a target base station after uplink synchronization through a random access channel (RACH) procedure.

[0141] In one embodiment, operations 552, 554, and 556 may be repeated operations per artificial intelligence model.

[0142] FIG. 6 illustrates the operations of a terminal and a base station for a method of transmitting an AI model related to a conditional handover according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 6 may represent an embodiment in which a terminal (610) receives AI model information about candidate base stations (614) based on a control plane (CP). Unlike the embodiment of FIG. 5, the embodiment of FIG. 6 allows a source base station (612) to request AI model information from an AMF entity (616).

[0143] The terminal and base station performing the operations described in FIG. 6 may correspond to the terminal and network entity of FIG. 2 and FIG. 3, respectively.

[0144] In operation 632, the terminal (610) may receive an RRC reconfiguration message from the source base station (612). The RRC reconfiguration message may include configuration information related to the operation of the terminal (610). Specifically, the configuration information may include timer information regarding a period during which the terminal (610) stores an AI model. Accordingly, the terminal (610) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (610) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (610) hands over to a specific cell and then hands over to the previous cell again within a short period of time, it does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, since the terminal (610) stores the artificial intelligence model until the timer expires, when the conditional handover preparation procedure is repeated, the unnecessary procedure of deleting the artificial intelligence model previously received by the terminal (610) in the conditional handover preparation procedure and receiving it again in the repeated procedure can be minimized.

[0145] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, the timer is indicated when the Index value is 0 in Table 1 described above. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0146] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal in the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 described above is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0147] In operation 634, the terminal (610) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (612) to the terminal (610) via an RRC reset message in operation 632.

[0148] In operation 636, the terminal (610) may transmit a measurement report to the source base station (612). In relation to conditional handover, the terminal (610) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (612).

[0149] In operation 638, the source base station (612) may determine a conditional handover based on a measurement report received from the terminal (610). While determining the conditional handover, the source base station (612) may determine a candidate cell (or candidate base station) to which the terminal (610) can hand over.

[0150] In operation 640, the source base station (612) can transmit a handover request message to candidate base stations (614) to which the terminal (610) can handover, and can receive an ACK message indicating that the handover request message has been received from the candidate base stations (614).

[0151] In operation 642, the source base station (612) may transmit an AI model information request message to the AMF entity (616). The AI ​​information request message transmitted from the source base station (612) to the AMF entity (616) may be a message requesting information about an AI model that must be transmitted through the control plane. That is, the source base station (612) may request the AMF entity (616) for information about an AI model that can be transmitted through the control plane (CP) between the candidate base station and the source base station due to reasons such as the size of the AI ​​model.

[0152] In one embodiment, the source base station (612) requests information on artificial intelligence models for candidate base stations (614) from the AMF entity (616), and the AMF entity (616) can distinguish between artificial intelligence models that should be transmitted through the user plane and artificial intelligence models that should be transmitted through the control plane among the artificial intelligence models. In addition, the AMF entity (616) can request the candidate base stations (614) to transmit artificial intelligence models that can be transmitted through the control plane to the source base station (612).

[0153] In operation 644, the source base station (612) may transmit a handover command to the terminal (610). Here, the transmission of the handover command may be performed based on the source base station (612) receiving an ACK message from the candidate base stations (614). Accordingly, the order of operation 644 may be positioned after operation 640. However, the order of operation 644 may be changed with other operations, such as operations 642 to 648.

[0154] In operation 646, the AMF entity (616) may request the candidate base stations (614) to transmit an AI model that is transmittable via the control plane to the source base station (612).

[0155] In one embodiment, for an artificial intelligence model that can be transmitted through the user plane, the AMF entity (616) can collaborate with other network entities, such as operation 452 of FIG. 4.

[0156] In operation 648, the source base station (612) can receive an artificial intelligence model for each candidate base station from the candidate base stations (614) through the control plane.

[0157] Additionally, in operation 650, the source base station (612) may receive artificial intelligence model information for each candidate base station from the candidate base stations (614). Specifically, the artificial intelligence model information may include information about an artificial intelligence model that must be transmitted through the control plane among the artificial intelligence models for each candidate base station (614) and / or information about an artificial intelligence model that the source base station (612) received through the control plane in operation 648.

[0158] In one embodiment, operations 648 and 650 may be performed concurrently.

[0159] In one embodiment, the artificial intelligence model information of the 650 operations may include artificial intelligence model information about candidate base stations that can be transmitted based on the user plane or the control plane.

[0160] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Accordingly, if the identifier of the AI ​​model for the source base station (612) and the identifier of the AI ​​model for the candidate base station (614) are the same, the terminal (610) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (614), thereby preventing unnecessary transmission and reception operations.

[0161] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0162] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (610) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (610) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The candidate base station (614) may set priority information for the AI ​​model and transmit it to the source base station (612) as AI model information. The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0163] In one embodiment, the AI ​​model may have a base model commonly used in multiple cells, and if the base model exists, the transmission priority of the AI ​​model related to the case where the base model is used may be set low. In other words, the AI ​​model related to the case where the base model is applied may be transmitted to the terminal (610) after the handover is completed.

[0164] In operation 652, the source base station (612) may select an artificial intelligence model based on the artificial intelligence model information received in operation 650. At this time, the artificial intelligence model selection includes selecting an artificial intelligence model to be transmitted to the terminal (610) via the control plane.

[0165] In one embodiment, the AI ​​model selection may include selecting an AI model to be transmitted via the user plane. (See FIG. 4 ) In this case, as in operation 450 of FIG. 4 , the source base station (612) may transmit a request for the selected AI model to the AMF entity (616). The requested AI model may then be transmitted from the UPF entity to the terminal via the source base station via the user plane.

[0166] In one embodiment, the source base station (612) can set the transmission priority of the AI ​​models for each candidate base station (614) based on the AI ​​model information, and select the AI ​​model to be transmitted to the terminal (610) based on the set priority. That is, the source base station (612) can set the transmission priority for a plurality of AI models for a plurality of candidate base stations (614), and select the AI ​​model based on the set priority.

[0167] In one embodiment, the source base station (612) may select artificial intelligence models by considering the strength of signals (e.g., RSRP, RSRQ, etc.) for candidate base stations (or candidate cells) included in a measurement report received from the terminal (610) by operation 636. For example, the priority of the artificial intelligence model for a candidate base station with a low signal strength may be set lower than the priority of the artificial intelligence model for a candidate base station with a high signal strength, and the source base station (612) may preferentially select the artificial intelligence model for the candidate base station with a high signal strength.

[0168] In one embodiment, in operation 650, the source base station (612) receives artificial intelligence model information, and in operation 652, the source base station (612) selects an artificial intelligence model based on the received artificial intelligence model information, and then requests a candidate base station to transmit the selected artificial intelligence model (not shown), and may receive the selected artificial intelligence model from the candidate base station. That is, after operation 652, operation 648 may be performed after requesting the candidate base station to transmit the selected artificial intelligence model.

[0169] In operation 654, the source base station (612) can transmit the selected artificial intelligence model to the terminal (610) through the control plane.

[0170] In one embodiment, the source base station (612) may sequentially transmit the artificial intelligence models for each candidate base station to the terminal (610) for each artificial intelligence model.

[0171] In one embodiment, the source base station (612) may transmit to the terminal (610) the AI ​​models selected based on the priority among the AI ​​models for all candidate base stations.

[0172] In operation 656, the terminal (610) may transmit an ACK message to the source base station (612) to inform it of the received artificial intelligence model. Based on the received ACK message, the source base station (612) may identify the artificial intelligence model received by the terminal (610) among the artificial intelligence models transmitted by the source base station (612) to the terminal (610) in operation 654.

[0173] In operation 658, the source base station (612) may transmit information about the artificial intelligence model possessed by the terminal (610) to the candidate base station (614). The information about the artificial intelligence model possessed by the terminal (610) may be based on the ACK message received by the source base station (612) in operation 656.

[0174] In one embodiment, operation 658 may represent an operation in which the source base station (612) transmits information about an artificial intelligence model held by the terminal (610) to the determined target base station after the source base station (612) determines the target base station for conditional handover of the terminal (610). That is, the source base station (612) may transmit the information to a single determined target base station (or target cell) rather than to multiple candidate base stations.

[0175] In one embodiment, operation 658 may represent an operation in which a source base station (612) transmits information about an artificial intelligence model it possesses to a target base station after uplink synchronization through a random access channel (RACH) procedure.

[0176] In one embodiment, actions 654, 656, and 658 may be repeated actions per artificial intelligence model.

[0177] FIG. 7 illustrates operations of a terminal and a base station for a method of transmitting an AI model related to a conditional handover according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 7 may represent an embodiment in which a terminal (710) receives AI model information about candidate base stations (714) based on a control plane (CP). Unlike the embodiment of FIG. 6, the embodiment of FIG. 7 may perform an operation of selecting an AI model before a source base station (712) requests AI model information from an AMF entity (716).

[0178] The terminal and base station performing the operations described in Fig. 7 may correspond to the terminal and network entity of Figs. 2 and 3, respectively.

[0179] In operation 732, the terminal (710) may receive an RRC reconfiguration message from the source base station (712). The RRC reconfiguration message may include configuration information related to the operation of the terminal (710). Specifically, the configuration information may include timer information regarding a period during which the terminal (710) stores an AI model. Accordingly, the terminal (710) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (710) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (710) hands over to a specific cell and then hands over to the previous cell again within a short period of time, it does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, since the terminal (710) stores the artificial intelligence model until the timer expires, when the conditional handover preparation procedure is repeated, the unnecessary procedure of deleting the artificial intelligence model previously received by the terminal (710) in the conditional handover preparation procedure and receiving it again in the repeated procedure can be minimized.

[0180] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, the timer is indicated when the Index value is 0 in Table 1 described above. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0181] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal in the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 described above is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0182] In operation 734, the terminal (710) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (712) to the terminal (710) via an RRC reset message in operation 732.

[0183] In operation 736, the terminal (710) may transmit a measurement report to the source base station (712). In relation to conditional handover, the terminal (710) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (712).

[0184] In operation 738, the source base station (712) may determine a conditional handover based on a measurement report received from the terminal (710). While determining the conditional handover, the source base station (712) may determine a candidate cell (or candidate base station) to which the terminal (710) can hand over.

[0185] In operation 740, the source base station (712) can transmit a handover request message to candidate base stations (714) to which the terminal (710) can handover, and can receive an ACK message indicating that the handover request message has been received from the candidate base stations (714).

[0186] In operation 742, the source base station (712) may receive artificial intelligence model information for each candidate base station from the candidate base stations (714). Specifically, the artificial intelligence model information may include information on an artificial intelligence model that must be transmitted through the user plane among the artificial intelligence models for each candidate base station (714) and / or information on an artificial intelligence model that the source base station (712) may transmit through the control plane.

[0187] In one embodiment, the source base station (712) can receive information about artificial intelligence models from candidate base stations (714) and distinguish between artificial intelligence models that should be transmitted through the user plane and artificial intelligence models that should be transmitted through the control plane. Then, the source base station (712) can request the candidate base stations (714) or the AMF entity (716) to transmit an artificial intelligence model that can be transmitted through the control plane to the source base station (712). In addition, the source base station (712) can request the AMF entity (716) to transmit an artificial intelligence model that can be transmitted through the user plane.

[0188] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Accordingly, if the identifier of the AI ​​model for the source base station (712) and the identifier of the AI ​​model for the candidate base station (714) are the same, the terminal (710) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (714), thereby preventing unnecessary transmission and reception operations.

[0189] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0190] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (710) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (710) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The candidate base station (714) may set priority information for the AI ​​model and transmit it to the source base station (712) as AI model information. The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0191] In one embodiment, the AI ​​model may have a base model commonly used in multiple cells, and if the base model exists, the transmission priority of the AI ​​model related to the case where the base model is used may be set low. In other words, the AI ​​model related to the case where the base model is applied may be transmitted to the terminal (710) after the handover is completed.

[0192] In operation 744, the source base station (712) may select an artificial intelligence model based on the artificial intelligence model information received in operation 742. At this time, the artificial intelligence model selection includes selecting an artificial intelligence model to be transmitted to the terminal (710) via the control plane.

[0193] In one embodiment, the AI ​​model selection may include selecting an AI model to be transmitted via the user plane. (See FIG. 4 ) In this case, as in operation 450 of FIG. 4 , the source base station (712) may transmit a request for the selected AI model to the AMF entity (716). The requested AI model may then be transmitted from the UPF entity to the terminal via the source base station via the user plane.

[0194] In one embodiment, the source base station (712) can set the transmission priority of the AI ​​models for each candidate base station (714) based on the AI ​​model information, and select the AI ​​model to be transmitted to the terminal (710) based on the set priority. That is, the source base station (712) can set the transmission priority for a plurality of AI models for a plurality of candidate base stations (714), and select the AI ​​model based on the set priority.

[0195] In one embodiment, the source base station (712) may select artificial intelligence models by considering the strength of signals (e.g., RSRP, RSRQ, etc.) for candidate base stations (or candidate cells) included in a measurement report received from the terminal (710) by operation 736. For example, the priority of the artificial intelligence model for a candidate base station with a low signal strength may be set lower than the priority of the artificial intelligence model for a candidate base station with a high signal strength, and the source base station (712) may preferentially select the artificial intelligence model for the candidate base station with a high signal strength.

[0196] In operation 746, the source base station (712) may transmit an AI model transmission request message to the AMF entity (716). The AI ​​transmission request message transmitted from the source base station (712) to the AMF entity (716) may be a message requesting transmission of an AI model that must be transmitted via a control plane. That is, the source base station (712) may request the AMF entity (716) to transmit an AI model that can be transmitted via a control plane (CP) between the candidate base station and the source base station due to reasons such as the size of the AI ​​model.

[0197] In operation 748, the source base station (712) may transmit a handover command to the terminal (710). Here, the transmission of the handover command may be performed based on the source base station (712) receiving an ACK message from the candidate base stations (714). Accordingly, the order of operation 748 may be positioned after operation 740. However, the order of operation 748 may be changed with other operations, such as operations 742 to 752.

[0198] In operation 750, the AMF entity (716) may request the candidate base stations (714) to transmit an AI model that is transmittable via the control plane to the source base station (712).

[0199] In one embodiment, for an artificial intelligence model that can be transmitted through the user plane, the AMF entity (716) can collaborate with other network entities, such as operation 452 of FIG. 4.

[0200] In operation 752, the source base station (712) can receive an artificial intelligence model for each candidate base station from the candidate base stations (714) through the control plane.

[0201] In operation 754, the source base station (712) can transmit the selected artificial intelligence model (see operation 744) or the received artificial intelligence model (see operation 752) to the terminal (710) via the control plane.

[0202] In one embodiment, the source base station (712) may sequentially transmit the artificial intelligence models for each candidate base station to the terminal (710) for each artificial intelligence model.

[0203] In one embodiment, the source base station (712) may transmit to the terminal (710) the AI ​​models selected based on the priority among the AI ​​models for all candidate base stations.

[0204] In operation 756, the terminal (710) may transmit an ACK message to the source base station (712) to inform it of the received artificial intelligence model. Based on the received ACK message, the source base station (712) may identify the artificial intelligence model received by the terminal (710) among the artificial intelligence models transmitted by the source base station (712) to the terminal (710) in operation 754.

[0205] In operation 758, the source base station (712) may transmit information about the artificial intelligence model possessed by the terminal (710) to the candidate base station (714). The information about the artificial intelligence model possessed by the terminal (710) may be based on the ACK message received by the source base station (712) in operation 756.

[0206] In one embodiment, operation 758 may represent an operation in which the source base station (712) transmits information about an artificial intelligence model held by the terminal (710) to the determined target base station after the source base station (712) determines the target base station for conditional handover of the terminal (710). That is, the source base station (712) may transmit the information to a single determined target base station (or target cell) rather than to multiple candidate base stations.

[0207] In one embodiment, operation 758 may represent an operation in which a source base station (712) transmits information about an artificial intelligence model it possesses to a target base station after uplink synchronization through a random access channel (RACH) procedure.

[0208] In one embodiment, actions 754, 756, and 758 may be repeated actions per artificial intelligence model.

[0209] In the embodiment of FIG. 7, a source base station (712) can receive artificial intelligence model information from candidate base stations (714), select an artificial intelligence model based on the received artificial intelligence model information, and transmit an artificial intelligence model transmission request message for the selected artificial intelligence model to an AMF entity (716) or candidate base stations (714). Accordingly, the source base station (712) can receive only the selected artificial intelligence model, thereby simplifying the transmission and reception procedure.

[0210] FIG. 8 illustrates the operations of a terminal and a base station for a method of transmitting an AI model related to conditional handover according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 8 may represent an embodiment in which a source base station (812) receives information about an AI model from a neighboring base station (814), and then performs a decision on candidate base stations based on the received information, thereby optimizing the number of candidate base stations.

[0211] In operation 832, the terminal (810) may receive an RRC reconfiguration message from the source base station (812). The RRC reconfiguration message may include configuration information related to the operation of the terminal (810). Specifically, the configuration information may include timer information regarding a period during which the terminal (810) stores an AI model. Accordingly, the terminal (810) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (810) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (810) hands over to a specific cell and then hands over to the previous cell again within a short period of time, the terminal does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, by storing the artificial intelligence model by the terminal (810) until the timer expires, when the conditional handover preparation procedure is repeated, the unnecessary procedure of deleting the artificial intelligence model received by the terminal (810) in the previous conditional handover preparation procedure and receiving it again in the repeated procedure can be minimized.

[0212] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, the timer is indicated when the Index value is 0 in Table 1 described above. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0213] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal in the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 described above is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0214] In operation 834, the terminal (810) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (812) to the terminal (810) via an RRC reset message in operation 832.

[0215] In operation 836, the terminal (810) may transmit a measurement report to the source base station (812). In relation to conditional handover, the terminal (810) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (812).

[0216] In operation 838, the source base station (812) may transmit an AI model information request message to neighboring base stations (814) (or neighboring cells). The AI ​​information request message transmitted from the source base station (812) to the neighboring base stations (814) may be a message requesting information about an AI model that must be transmitted through a user plane and information about an AI model that can be transmitted through a control plane. That is, the source base station (812) may request information about AI models that must be transmitted through a control plane (CP) between a candidate base station and the source base station or must be transmitted through a user plane from the neighboring base stations (814) due to reasons such as the size of the AI ​​model.

[0217] In operation 840, the source base station (812) may receive artificial intelligence model information for each neighboring base station from neighboring base stations (814). Specifically, the artificial intelligence model information may include information on an artificial intelligence model that must be transmitted through the user plane and information on an artificial intelligence model that must be transmitted through the control plane among the artificial intelligence models for each neighboring base station (814).

[0218] In one embodiment, whether an AI model should be transmitted to the user plane or through the control plane can be determined by the source base station (812). That is, even if the AI ​​model information does not include a transmission method (a transmission method through the user plane or a transmission method through the control plane) for each AI model, the source base station (812) can determine a transmission method for each AI model based on the AI ​​model information. In addition, the source base station (812) can perform operations according to the above-described embodiments according to the transmission method determined for each AI model.

[0219] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Accordingly, if the identifier of the AI ​​model for the source base station (812) and the identifier of the AI ​​model for the candidate base station (814) are the same, the terminal (810) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (814), thereby preventing unnecessary transmission and reception operations.

[0220] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0221] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (810) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (810) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The candidate base station (814) may set priority information for the AI ​​model and transmit it to the source base station (812) as AI model information. The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0222] In one embodiment, an AI model may have a base model commonly used in multiple cells, and if a base model exists, the transmission priority of the AI ​​model related to the case where the base model is applied may be set low. In other words, the AI ​​model related to the case where the base model is used may be transmitted to the terminal (810) after the handover is completed.

[0223] In operation 842, the source base station (812) may determine a conditional handover based on a measurement report received from the terminal (810). While determining the conditional handover, the source base station (812) may determine a candidate cell (or candidate base station) to which the terminal (810) can hand over.

[0224] In one embodiment, the source base station (812) may determine a candidate base station for conditional handover based on the AI ​​model information received in operation 840. For example, if the number of AI models for the first neighboring base station is large or the capacity is large, the source base station (812) may not determine the first neighboring base station as a candidate base station. In addition, if some of the AI ​​models for the second neighboring base station are identical to some of the AI ​​models currently held by the terminal, or if the number of AI models for the second neighboring base station is small or the capacity is small, the source base station (812) may determine the second neighboring base station as a candidate base station. That is, the source base station (812) may or may not determine the neighboring base station as a candidate base station for conditional handover by considering the amount of data processing that must be used to transmit the AI ​​model of the neighboring base station to the terminal (810), the time consumed, etc.

[0225] Action 844 may indicate that other procedures for conditional handover are performed. For example, action 844 may include an action in which the source base station (812) transmits a handover request message to the determined candidate base station (814) and receives an ACK message from the candidate base station (814).

[0226] FIG. 9 illustrates the operations of a terminal and a base station for a method for transmitting an AI model related to a conditional handover according to embodiments of the present disclosure. Specifically, the embodiment of FIG. 9 may represent an embodiment that combines the candidate base station determination operation according to the embodiment of FIG. 8 and the AI ​​model transmission operation via the control plane according to the embodiment of FIG. 5. Embodiments of the present disclosure may include embodiments that combine embodiments represented by different drawings.

[0227] Referring to FIG. 9, in operation 932, the terminal (910) may receive an RRC reconfiguration message from the source base station (912). The RRC reconfiguration message may include configuration information related to the operation of the terminal (910). Specifically, the configuration information may include timer information regarding a period during which the terminal (910) stores an AI model. Accordingly, the terminal (910) may receive an AI model and store the received AI model until the timer expires. When the timer expires, the terminal (910) may delete AI models for other base stations previously received from the memory, except for the AI ​​model for the current serving base station. By storing the AI ​​model until the timer expires, when the terminal (910) hands over to a specific cell and then hands over to the previous cell again within a short period of time, it does not need to receive the AI ​​model for the previous cell again, thereby minimizing unnecessary transmission and reception operations. In addition, by storing the artificial intelligence model by the terminal (910) until the timer expires, when the conditional handover preparation procedure is repeated, the unnecessary procedure of deleting the artificial intelligence model received by the terminal (910) in the previous conditional handover preparation procedure and receiving it again in the repeated procedure can be minimized.

[0228] In one embodiment, the timer information for storing an AI model may include timer information for the terminal to store the AI ​​model for the source base station prior to the handover for a certain period of time after the handover is completed. That is, the timer is indicated when the Index value is 0 in Table 1 described above. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0229] In one embodiment, the timer information for storing the AI ​​model may include timer information for the terminal to store the AI ​​models for candidate base stations received by the terminal in the conditional handover preparation procedure for a certain period of time after the handover preparation procedure ends. That is, the timer for the case where the Index value is 1 in Table 1 described above is shown. The storage time of the AI ​​model may include 10 ms, 20 ms, 40 ms, etc., and the timer information may be indicated as a bitmap.

[0230] In operation 934, the terminal (910) may identify a conditional handover preparation event. Information about the event triggering the conditional handover preparation may be transmitted from the source base station (912) to the terminal (910) via an RRC reset message in operation 932.

[0231] In operation 936, the terminal (910) may transmit a measurement report to the source base station (912). In relation to conditional handover, the terminal (910) may measure the signal strength for a neighboring cell (or neighboring base station) and transmit a measurement report including the measured values ​​to the source base station (912).

[0232] In operation 938, the source base station (912) may transmit an AI model information request message to neighboring base stations (916) (or neighboring cells). The AI ​​information request message transmitted from the source base station (912) to the neighboring base stations (916) may be a message requesting information about an AI model that must be transmitted through a user plane and / or information about an AI model that can be transmitted through a control plane. That is, the source base station (912) may request information about AI models that must be transmitted through a control plane (CP) between a candidate base station and the source base station or must be transmitted through a user plane from the neighboring base stations (916) due to reasons such as the size of the AI ​​model.

[0233] In operation 940, the source base station (912) may receive artificial intelligence model information for each neighboring base station from neighboring base stations (914). Specifically, the artificial intelligence model information may include information on an artificial intelligence model that must be transmitted through the user plane and information on an artificial intelligence model that must be transmitted through the control plane among the artificial intelligence models for each neighboring base station (916).

[0234] In one embodiment, whether an AI model should be transmitted to the user plane or the control plane can be determined by the source base station (912). That is, even if the AI ​​model information does not include a transmission method (a transmission method via the user plane or a transmission method via the control plane) for each AI model, the source base station (912) can determine a transmission method for each AI model based on the AI ​​model information. In addition, the source base station (912) can perform operations according to the above-described embodiments according to the transmission method determined for each AI model.

[0235] In one embodiment, the AI ​​model information may include at least one of the AI ​​model size, the AI ​​model identifier, and the AI ​​model priority information. The same AI model identifier (ID) may indicate the same AI model. Therefore, if the identifier of the AI ​​model for the source base station (912) and the identifier of the AI ​​model for the candidate base station (914) are the same, the terminal (910) already possesses the corresponding AI model and therefore does not need to receive the AI ​​model for the candidate base station (914), thereby preventing unnecessary transmission and reception operations.

[0236] In one embodiment, if the AI ​​models transmitted from a higher node, such as a server entity, to a specific cell (or base station) are identical, information about the corresponding AI models may be expressed as a group identifier. That is, AI models corresponding to a specific group may be indicated via a group identifier.

[0237] In one embodiment, the priority information of the AI ​​model may indicate the transmission priority of the AI ​​model. For example, a high priority may be set for an AI model that is required to be transmitted to the terminal (910) before the handover completion time, and a low priority may be set for an AI model that may be transmitted to the terminal (910) after the handover completion time. Specifically, a high priority may be set for an AI model related to cases such as beamforming, positioning, channel state indicator (CSI) feedback, etc. (Layer 1 related), and a low priority may be set for an AI model related to cases such as handover, scheduling, etc. (Layer 2 or 3 related). The neighboring base station (916) may set priority information for the AI ​​model and transmit it to the source base station (912) as AI model information. The priorities for the AI ​​models are not limited to the examples described above, and the priorities among various AI models utilized in various cases may be set in various ways depending on specific embodiments.

[0238] In one embodiment, an AI model may have a base model commonly used in multiple cells, and when a base model exists, the transmission priority of an AI model related to a case where the base model is applied may be set low. In other words, an AI model related to a case where the base model is used may be transmitted to the terminal (910) after the handover is completed.

[0239] In one embodiment, the neighboring base station (916) may be a first candidate base station. That is, the source base station (912) may request artificial intelligence model information from the first candidate base station and receive artificial intelligence model information from the first candidate base station.

[0240] In operation 942, the source base station (912) may determine a conditional handover based on a measurement report received from the terminal (910). While determining the conditional handover, the source base station (912) may determine a candidate cell (or candidate base station) (914) to which the terminal (910) can handover among neighboring base stations (916).

[0241] In one embodiment, the source base station (912) may determine a second candidate base station (914) to which the terminal can handover among the first candidate base stations (916) while determining a conditional handover.

[0242] In one embodiment, the source base station (912) may determine a candidate base station for conditional handover based on the AI ​​model information received in operation 940. For example, if the number of AI models for the first neighboring base station is large or the capacity is large, the source base station (912) may not determine the first neighboring base station as a candidate base station. In addition, if some of the AI ​​models for the second neighboring base station are identical to some of the AI ​​models currently held by the terminal, or if the number of AI models for the second neighboring base station is small or the capacity is small, the source base station (912) may determine the second neighboring base station as a candidate base station. That is, the source base station (912) may or may not determine the neighboring base station as a candidate base station for conditional handover by considering the amount of data processing that must be used to transmit the AI ​​model of the neighboring base station to the terminal (910), the time consumed, etc.

[0243] In operation 944, the source base station (912) may transmit a handover request message to candidate base stations (914) to which the terminal (910) may hand over, and may receive an ACK message indicating that the handover request message has been received from the candidate base stations (914). At this time, the candidate base stations (914) may indicate the candidate base stations determined by the source base station (912) in operation 942.

[0244] In operation 946, the source base station (912) may transmit a handover command to the terminal (910). Here, the transmission of the handover command may be performed based on the source base station (912) receiving an ACK message from the candidate base stations (914). Accordingly, the order of operation 946 may be positioned after operation 944. However, the order of operation 946 may be changed with other operations, such as operations 948 to 950.

[0245] In operation 948, the source base station (912) can receive an artificial intelligence model for each candidate base station from the candidate base stations (914) through the control plane.

[0246] In operation 950, the source base station (912) may select an artificial intelligence model based on the artificial intelligence model information received in operation 940. At this time, the artificial intelligence model selection includes selecting an artificial intelligence model to be transmitted to the terminal (910) via the control plane.

[0247] In one embodiment, the source base station (912) can set the transmission priority of the AI ​​models for each candidate base station (914) based on the AI ​​model information, and select the AI ​​model to be transmitted to the terminal (910) based on the set priority. That is, the source base station (912) can set the transmission priority for a plurality of AI models for a plurality of candidate base stations (914), and select the AI ​​model based on the set priority.

[0248] In one embodiment, the source base station (912) may select artificial intelligence models by considering the strength of signals (e.g., RSRP, RSRQ, etc.) for candidate base stations (or candidate cells) included in a measurement report received from the terminal (910) by operation 936. For example, the priority of the artificial intelligence model for a candidate base station with a low signal strength may be set lower than the priority of the artificial intelligence model for a candidate base station with a high signal strength, and the source base station (912) may preferentially select the artificial intelligence model for the candidate base station with a high signal strength.

[0249] In operation 952, the source base station (912) can transmit the selected artificial intelligence model to the terminal (910) through the control plane.

[0250] In one embodiment, the source base station (912) may sequentially transmit the artificial intelligence models for each candidate base station to the terminal (910) for each artificial intelligence model.

[0251] In one embodiment, the source base station (912) may transmit to the terminal (910) the AI ​​models selected based on the priority among the AI ​​models for all candidate base stations.

[0252] In operation 954, the terminal (910) may transmit an ACK message to the source base station (912) to inform it of the received artificial intelligence model. Based on the received ACK message, the source base station (912) may identify the artificial intelligence model received by the terminal (910) among the artificial intelligence models transmitted by the source base station (912) to the terminal (910) in operation 952.

[0253] In operation 956, the source base station (912) may transmit information about the artificial intelligence model possessed by the terminal (910) to the candidate base station (914). The information about the artificial intelligence model possessed by the terminal (910) may be based on the ACK message received by the source base station (912) in operation 954.

[0254] In one embodiment, operation 956 may represent an operation in which the source base station (912) transmits information about an artificial intelligence model held by the terminal (910) to the determined target base station after the source base station (912) determines the target base station for conditional handover of the terminal (910). That is, the source base station (912) may transmit the information to a single determined target base station (or target cell) rather than to multiple candidate base stations.

[0255] In one embodiment, operation 956 may represent an operation in which a source base station (512) transmits information about an artificial intelligence model it possesses to a target base station after uplink synchronization through a random access channel (RACH) procedure.

[0256] In one embodiment, operations 952, 954, and 956 may be repeated operations per artificial intelligence model.

[0257] In one embodiment, the neighboring base station of FIG. 9 may be referred to as a first candidate base station, and the candidate base station of FIG. 9 may be referred to as a second candidate base station.

[0258] In one embodiment, the source base station (912) can determine the second candidate base stations (914) from the first candidate base stations (916) based on the artificial intelligence model information for the first candidate base stations (916). That is, when the conditional handover is determined and the first candidate base stations (916) have already been determined, the source base station (912) can determine the second candidate base stations (914) from among the first candidate base stations (916) based on the artificial intelligence model information, and thereafter, the conditional handover procedure and the artificial intelligence model transfer procedure can be performed for the second candidate base stations.

[0259] FIG. 10 illustrates an operation flowchart of a source base station according to embodiments of the present disclosure.

[0260] The source station performing the operation described in FIG. 10 may correspond to the network entity of FIG. 3.

[0261] Referring to FIG. 10, operation 1010 represents an operation in which a source base station transmits an AI model information request message. The source base station may request AI model information about candidate base stations from candidate base stations or AMF entities.

[0262] Action 1020 represents an action in which the source base station receives AI model information based on a request according to action 1010. The source base station can receive AI model information for each candidate base station from the candidate base stations for conditional handover.

[0263] Action 1030 represents an action in which the source base station selects a first AI model based on the AI ​​model information obtained from Action 1020. At this time, the first AI model may be selected based on the priority set for each AI model and / or the signal strength for the candidate base station.

[0264] Action 1040 may represent an action in which the source base station transmits the artificial intelligence model selected according to action 1030 to the terminal.

[0265] In one embodiment, the source base station may receive an AI model from the UPF entity via the user plane prior to operation 1040. At this time, the source base station may transmit an AI model transmission request message to the AMF entity, and receive the AI ​​model from the UPF entity based on the AI ​​model transmission request message.

[0266] In one embodiment, the source base station may receive the AI ​​model from the candidate base station via the control plane prior to operation 1040.

[0267] In one embodiment, the source base station may transmit a radio resource control (RRC) reset message including timer information for storing an artificial intelligence model to the terminal prior to operation 1010.

[0268] In one embodiment, the source base station performs an operation to identify an AI model priority based on information about the AI ​​model, and operation 1030 may be performed based on the identified priority. The AI ​​model priority may be identified based on the type of AI model (the AI ​​model to which the AI ​​model is applied).

[0269] In one embodiment, the source base station can receive information indicating whether or not the artificial intelligence model is received from the terminal, and can transmit information indicating whether or not the artificial intelligence model is received by the terminal to the candidate base station.

[0270] In one embodiment, the source base station may identify at least one of the previous candidate base stations (first candidate base stations) based on the size information of the AI ​​model included in the AI ​​model information and determine the base stations as new candidate base stations (second candidate base stations). Then, the source base station may transmit a handover request message to the new candidate base station and receive the AI ​​model from the new candidate base station. The new candidate base station may be any of the previous candidate base stations. In addition, the source base station may transmit information indicating whether the AI ​​model of the terminal has been received, received from the terminal, to one of the new candidate base stations (the target base station).

[0271] As a communication method according to embodiments of the present disclosure, a method performed by a base station in a wireless communication system may be composed of operations of the base station corresponding to operations of the terminal described above.

[0272] While the operations of the communication method according to the embodiments of the present disclosure have been described separately for each embodiment, the operations included in each embodiment can be combined with operations of other embodiments to form a new embodiment. Accordingly, it can be understood that embodiments in which the embodiments of the present disclosure are combined are also described by the present disclosure.

[0273] The various embodiments of the present disclosure and the terminology used therein are not intended to limit the technical features described in the present disclosure to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more items, unless the relevant context clearly indicates otherwise. In the present disclosure, each of the phrases "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among the phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0274] The term "module" as used herein may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally formed component or a minimum unit or part of a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0275] Various embodiments of the present disclosure may be implemented as software (e.g., a program (140)) including one or more commands stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a device (e.g., a processor (e.g., processor (120) of an electronic device (101)) can call at least one command from among one or more commands stored from a storage medium and execute it. This enables the device to operate to perform at least one function according to the called at least one command. The one or more commands may include code generated by a compiler or code executable by an interpreter. A storage medium readable by the device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (e.g., EM wave), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0276] According to one embodiment, the method according to various embodiments disclosed in the present disclosure may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0277] According to various embodiments, each component (e.g., a module or a program) of the described components may include one or more entities. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. A method performed by a base station in a wireless communication system, A step of transmitting an artificial intelligence model information request message to the first candidate base stations for handover or an access and mobility management function (AMF) entity; A step of receiving information about at least one artificial intelligence model from the first candidate base stations; A step of selecting a first artificial intelligence model based on information about at least one received artificial intelligence model; and comprising a step of transmitting the first artificial intelligence model to the terminal; method.

2. In claim 1, Further comprising a step of transmitting an RRC (radio resource control) reset message including timer information for storing an artificial intelligence model to the terminal. method.

3. In claim 1, Further comprising the step of receiving at least one artificial intelligence model based on a control plane from the first candidate base stations. method.

4. In claim 1, a step of transmitting a message to the AMF entity requesting the first artificial intelligence model; and Further comprising a step of receiving the first artificial intelligence model based on a user plane from a UPF (user plane function) entity. method.

5. In claim 1, Further comprising a step of identifying a priority of the at least one artificial intelligence model based on information about the at least one artificial intelligence model, The first artificial intelligence model is selected based on a priority for at least one artificial intelligence model. method.

6. In claim 5, The priority of the at least one artificial intelligence model is identified based on the strength of the reference signal for the first candidate base stations or the type of the at least one artificial intelligence model. method.

7. In claim 1, A step of receiving information indicating whether the first artificial intelligence model is received from the terminal; and A step of transmitting information indicating whether the terminal receives the first artificial intelligence model to any one of the first candidate base stations, method.

8. In claim 1, The information about the at least one artificial intelligence model includes size information of the at least one artificial intelligence model, The above method, A step of identifying at least one second candidate base station from the first candidate base stations based on size information of at least one artificial intelligence model; A step of transmitting a handover request message to at least one second candidate base station; A step of receiving a first artificial intelligence model from at least one second candidate base station; A step of receiving information indicating whether the first artificial intelligence model is received from the terminal; and Further comprising a step of transmitting information indicating whether the terminal has received the first artificial intelligence model to one of the second candidate base stations. method.

9. As a source base station of a wireless communication system, Transmitter and receiver; and Including a processor connected to the above transceiver, The above processor: Transmit an artificial intelligence model information request message to the first candidate base stations for handover or AMF (access and mobility management function) entities, Receive information about at least one artificial intelligence model from the first candidate base stations, Selecting a first artificial intelligence model based on information about at least one artificial intelligence model received, Set to transmit the first artificial intelligence model to the terminal, Source base station.

10. In claim 9, The above processor, It is set to transmit an RRC (radio resource control) reset message including timer information for storing an artificial intelligence model to the terminal. Source base station.

11. In claim 9, The above processor, Set to receive at least one artificial intelligence model based on a control plane from the first candidate base stations, Source base station.

12. In claim 9, The above processor, Sending a message to the AMF entity to request the first artificial intelligence model, Set to receive the first artificial intelligence model based on the user plane from the UPF (user plane function) entity, Source base station.

13. In claim 9, The above processor, is set to identify a priority of the at least one artificial intelligence model based on information about the at least one artificial intelligence model; The first artificial intelligence model is selected based on a priority for at least one artificial intelligence model, The priority of the at least one artificial intelligence model is identified based on the strength of the reference signal for the first candidate base stations or the type of the at least one artificial intelligence model. Source base station.

14. In claim 9, The above processor, Receive information indicating whether the first artificial intelligence model is received from the terminal, It is set to transmit information indicating whether the terminal receives the first artificial intelligence model to any one of the first candidate base stations. Source base station.

15. In claim 19, The information about the at least one artificial intelligence model includes size information of the at least one artificial intelligence model, The above processor, Identifying at least one second candidate base station from the first candidate base stations based on the size information of the at least one artificial intelligence model, Transmitting a handover request message to at least one second candidate base station, Receive a first artificial intelligence model from at least one second candidate base station, Receive information indicating whether the first artificial intelligence model is received from the terminal, It is set to transmit information indicating whether the first artificial intelligence model of the terminal is received to one of the second candidate base stations. Source base station.

Images