Method and apparatus for utilizing artificial intelligence in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. The present disclosure may provide a method performed by a user equipment in a wireless communication system, the method comprising the steps of: receiving, from a base station, a first message comprising a plurality of pieces of configuration information related to measurement for training for artificial intelligence; transmitting, to the base station, a second message for requesting first configuration information for the measurement; receiving, from the base station, a third message for providing second configuration information for the measurement; and performing the measurement for training for the artificial intelligence on the basis of the second configuration information.

Description

Method and device for utilizing artificial intelligence in a wireless communication system

[0001] The present disclosure relates to a method and device for using artificial intelligence (AI) or machine learning (ML) 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] Based on the discussion described above, the present disclosure provides a device and method for effectively providing a service by utilizing an AI / ML model in a wireless communication system.

[0008] A method performed by a terminal of a wireless communication system according to embodiments of the present disclosure includes the steps of: receiving a first message including a plurality of configuration information related to measurement for learning of artificial intelligence (Artificial Intelligence / Machine Learning, AI / ML) from a base station; transmitting a second message for requesting the first configuration information for the measurement to the base station; receiving a third message for providing the second configuration information for the measurement from the base station; and performing the measurement for learning of the artificial intelligence based on the second configuration information.

[0009] The present disclosure provides a device and method capable of effectively providing a service by utilizing an AI / ML model in a wireless communication system.

[0010] FIG. 1 is a diagram illustrating the structure of a wireless communication system according to one embodiment of the present disclosure.

[0011] FIG. 2 is a diagram for explaining a wireless connection state transition in a wireless communication system according to an embodiment of the present disclosure.

[0012] FIG. 3 is a diagram illustrating an Artificial Intelligence (AI) / Machine Learning (ML) model for predicting beam measurement values ​​for beam management according to one embodiment of the present disclosure.

[0013] FIG. 4 is a diagram illustrating a training, inference, and performance monitoring procedure for a UE-sided AI / ML model according to an embodiment of the present disclosure.

[0014] FIG. 5 is a diagram illustrating a procedure for requesting and receiving settings for collecting data required for AI / ML model learning by a terminal according to an embodiment of the present disclosure.

[0015] FIG. 6 is a diagram illustrating a procedure for requesting settings for a terminal to collect data required for AI / ML model learning according to one embodiment of the present disclosure.

[0016] FIG. 7 is a diagram illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0017] FIG. 8 is a diagram illustrating the structure of a base station according to one embodiment of the present disclosure.

[0018] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0019] In describing the embodiments, descriptions of technical details that are well known in the technical field to which the present disclosure pertains and are not directly related to the present disclosure will be omitted. This is to ensure that the gist of the present disclosure is conveyed more clearly without obscuring it by omitting unnecessary explanations.

[0020] For the same reason, some components in the attached drawings are exaggerated, omitted, or schematically depicted. Furthermore, the dimensions of each component do not entirely reflect its actual size. In each drawing, identical or corresponding components are assigned the same or different reference numbers.

[0021] The advantages and features of the present disclosure, and methods for achieving them, will become clearer with reference to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided only to ensure that the disclosure of the present disclosure is complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Like reference numerals designate like elements throughout the specification. In addition, when describing the present disclosure, if a specific description of a related function or configuration is determined to unnecessarily obscure the gist of the present disclosure, the detailed description thereof will be omitted. In addition, the terms described below are terms defined in consideration of the functions of the present disclosure, and these may vary depending on the intention or custom of the user or operator. Therefore, their definitions should be made based on the contents throughout the specification.

[0022] In the present disclosure, it will be appreciated that each block of the processing flowchart drawings and combinations of the flowchart drawings can be performed based on computer program instructions. These computer program instructions can be selectively installed in at least one processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by any one or any combination of at least one processor of the computer or other programmable data processing equipment create means for performing the functions described in the flowchart block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to implement the functions in a specific manner, so that the instructions stored in the computer-available or computer-readable memory can also produce an article of manufacture that includes instruction means for performing the functions described in the flowchart block(s). Since the computer program instructions may be installed on a computer or other programmable data processing device, a series of operational steps may be performed on the computer or other programmable data processing device to create a computer-executable process, and the instructions that cause the computer or other programmable data processing device to perform the steps for performing the functions described in the flowchart block(s) may also provide steps for performing the functions described in the flowchart block(s).

[0023] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions mentioned in the blocks may occur out of order. For example, two blocks (or functions) depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on the corresponding function.

[0024] The term '~ unit' used in the embodiments of the present disclosure means a software or hardware component such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC), and the '~ unit' performs certain roles. However, terms including '~ unit' are not limited to software or hardware. The '~ unit' may be configured to be on an addressable storage medium and may be configured to play one or more processors. Thus, as an example, the '~ unit' includes components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, the components and '~parts' may be implemented to play one or more central processing units (CPUs) within the device or secure multimedia card. Also, in an embodiment, the '~parts' may include one or more processors.

[0025] As described above, it should be noted that the blocks and combinations of flowcharts described in the present disclosure may be implemented by one or more computer programs containing instructions. One or more computer programs may be stored entirely in a single memory device, or one or more computer programs may be divided and stored in different portions across multiple memory devices.

[0026] Additionally, any / any function or operation described in the present disclosure may be processed by a single processor or a combination of processors. The single processor or the combination of processors may include circuitry that performs processing, such as an application processor (AP, e.g., a central processing unit (CPU)), a communication processor (CP, e.g., a modem), a graphics processing unit (GPU), a neural processing unit (NPU) (e.g., an artificial intelligence (AI) chip), a Wi-Fi chip, a Bluetooth® chip, a global positioning system (GPS) chip, a near-field communication (NFC) chip, a connectivity chip, a sensor controller, a touch controller, a fingerprint sensor controller, a display driver integrated circuit (IC), an audio codec (CODEC) chip, a universal serial bus (USB) controller, a camera controller, an image processing IC, a microprocessor unit (MPU), a system on a chip (SoC), an IC, or similar circuitry.

[0027] It should also be noted that the various embodiments in the claims and description of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0028] Such software may be stored on a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium stores one or more computer programs (software modules), wherein the one or more computer programs include computer-executable instructions that, when executed alone or collectively by one or more processors of an electronic device, cause the electronic device to perform a method according to the present disclosure.

[0029] The software may be stored in a temporary or non-transitory storage device, for example, in the form of a read-only memory (ROM) (whether erasable or rewritable), a random access memory (RAM), a memory chip, a device, or an integrated circuit (IC). The software may also be stored in an optically or magnetically readable medium, for example, a compact disc (CD), a digital versatile disc (DVD), a magnetic disk, or a magnetic tape. It should be understood that the storage device and the storage medium are examples of non-transitory machine-readable storage media suitable for storing a program for implementing various embodiments of the present disclosure. Accordingly, various embodiments of the present disclosure may provide a program comprising code for implementing a device or method according to any one of the claims of the present specification, and a non-transitory machine-readable storage medium storing such a program.

[0030] In the present disclosure, determining the priority between A and B may be referred to in various ways, such as selecting a higher priority according to a predetermined priority rule and performing an action corresponding to it, or omitting or dropping an action for a lower priority.

[0031] Hereinafter, 'A or B' described in the present disclosure may be understood as 'A and / or B', which may be understood to include 'A', or 'B', or 'A and B'.

[0032] Additionally, 'at least one of A, B, and C' described in the present disclosure may be understood to include 'A', or 'B', or 'C', or 'any combination of A, B, and C'.

[0033] Additionally, 'at least one of A, B, or C' described in the present disclosure may be understood to include 'A', or 'B', or 'C', or 'any combination of A, B, and C'.

[0034] Additionally, 'A / B' described in the present disclosure may be understood as 'A and / or B', which may be understood to include 'A', or 'B', or 'A and B'.

[0035] Additionally, 'A, B' described in the present disclosure may be understood as 'A and / or B', which may be understood to include 'A', or 'B', or 'A and B'.

[0036] Additionally, 'A and B' described in the present disclosure may be understood as 'A and / or B', which may be understood to include 'A', or 'B', or 'A and B'.

[0037] In addition, it can be understood that the 'case where conditions A and B are satisfied' described in the present disclosure is not necessarily limited to the case where both conditions A and B are satisfied, but may include the case where each of conditions A or B is satisfied, the case where both conditions A and B are satisfied, or the case where one or more additional conditions are satisfied together.

[0038] Additionally, throughout this specification, ordinal terms such as "first," "second," "third," and the like (and modifiers thereof) are used solely to distinguish between various instances, occurrences, configurations, messages, stages, or aspects of elements, operations, or information, as described below. Unless the context clearly requires otherwise, the use of such ordinal terms does not require that the elements, operations, or information distinguished by them be structurally, numerically, or inherently different. For example, "a first signal" and "a second signal" may represent instances of the same signal transmitted at different times, may represent signals containing the same core information albeit with some modifications, or may represent signals having different content or characteristics depending on the specific context. Similarly, "a first value" and "a second value" may represent measurements or applications of the same magnitude in different circumstances, or may represent different magnitudes. Such interpretation should be determined by the specific technical context, functions and relationships described in the relevant portions of the specification and claims.

[0039] Furthermore, although terms such as "first" and "second" described in this disclosure are used to refer to various elements such as information, objects, actions, and sequences, they are not intended to limit such elements to a specific order. These terms may be understood to be used merely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element.

[0040] Additionally, it may be understood that the terms "first~" and "second~" described in this disclosure may refer to the same or different elements. For example, if the elements are information, the first information and the second information may both be information, and in some cases, they may be the same information or different information.

[0041] In addition, the expressions "if" and "in case that" described in the present disclosure or claims may be interpreted to mean "when or upon," "in response to," or "based on," or "according to," depending on the context, and these expressions may be used interchangeably. In addition, in addition to these expressions, other expressions having substantially the same meaning may be used interchangeably, within the scope that does not impair the technical features of the present disclosure.

[0042] Additionally, the term "not perform" as used in this disclosure or claims may be understood to mean omitting or skipping a step, depending on the context. Such terms may be replaced with other terms having the same or substantially similar meaning.

[0043] Additionally, "transmitting a message including A and B" as described herein may be interpreted to include both (i) cases where A and B are transmitted in a single message, as well as (ii) cases where A and B are transmitted individually via multiple messages (e.g., transmitting a first message including A and a second message including B). This interpretation may also apply when a message including two or more items, such as A, B, and C, is transmitted together or individually.

[0044] Additionally, 'sending a message containing A and sending a message containing B' can also be interpreted as sending a single message containing A and B.

[0045] In the specific embodiments of the present disclosure described below, terms or components included in the disclosure will be expressed in the singular or plural, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in the plural may be composed of singular elements, or components expressed in the singular may be composed of plural elements.

[0046] The drawings or flowcharts described below illustrate exemplary methods that may be implemented according to the principles of the present disclosure, and various modifications may be made to the methods depicted in the flowcharts of the present disclosure. For example, although depicted as a series of steps, various steps in each drawing or flowchart may overlap, occur in parallel, occur in different orders, or occur multiple times. In other instances, any step may be omitted or replaced with another step.

[0047] The methods and devices proposed in the embodiments of the present disclosure are not limited to each embodiment, and may be utilized as a combination of one or more embodiments, all or part of the embodiments proposed in the disclosure. Accordingly, the embodiments of the present disclosure may be applied with some modifications within a scope that does not significantly deviate from the scope of the present disclosure, as determined by a person skilled in the art.

[0048] In this case, even if any wording is mentioned in different embodiments, if the concepts correspond, they may be used interchangeably, combined, or substituted. For example, for identical or corresponding concepts, even if one embodiment uses the expression "A" and another embodiment uses the expression "B," these may be understood interchangeably, substituted, or combined.

[0049] In the following description, terms used to identify connection nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, terms referring to various identification information, etc. are examples for convenience of explanation. Therefore, the present disclosure is not limited to the terms described below, and other terms referring to objects having equivalent technical meanings may be used. In addition, the terms may be replaced with terms defined in the 3rd generation partnership project (3GPP) Technical Specifications (TS), if appropriate.

[0050] Hereinafter, the base station is an entity that performs resource allocation of a terminal, and may be at least one of a gNode B, an eNode B, a Node B, a BS (base station), a radio access unit, a base station controller, or a node on a network. In addition, the base station of the present disclosure may include a structure that is split into a central unit (CU) and a distributed unit (DU). In this structure, the CU is responsible for the upper layers of the control and user planes, and the DU is responsible for radio resource processing of the lower layers. The embodiments of the present disclosure can be equally applied to a 5G base station structure in which functions are separated into the CU and DU.

[0051] The terminal may include a UE (user equipment), MS (mobile station), cellular phone, smartphone, computer, or multimedia system capable of performing communication functions.

[0052] In the present disclosure, downlink (DL) refers to a wireless transmission path of a signal transmitted from a base station to a terminal, and uplink (UL) refers to a wireless transmission path of a signal transmitted from a terminal to a base station.

[0053] In addition, although the fifth generation mobile communication system (5G, new radio, NR) and the sixth generation mobile communication system (6G) may be described below as examples, the embodiments of the present disclosure may also be applied to other communication systems having similar technical backgrounds or channel types. For example, this may include new evolved mobile communication systems developed after 5G and 6G. In addition, the present disclosure may be applied to other communication systems (e.g., Wi-Fi systems) with some modifications within a range that does not significantly deviate from the scope of the present disclosure, as determined by a person having skilled technical knowledge.

[0054] In the following description, the terms "physical channel" and "signal" may be used interchangeably with data or control signals. For example, while PDSCH (physical downlink shared channel) refers to a physical channel through which data is transmitted, PDSCH may also be used to refer to data. That is, in the present disclosure, the expression "transmitting a physical channel" may be interpreted equivalently to the expression "transmitting data or a signal through a physical channel."

[0055] In the following description of the present disclosure, upper layer signaling may be signaling corresponding to at least one or a combination of one or more of MIB (master information block), SIB (system information block), SIB M (M=1, 2, ...), RRC (radio resource control), MAC (medium access control) CE (control element), NAS (non-access stratum) signaling, or application layer messages. The RRC signaling may also be referred to as L3 signaling (layer 3 signaling).

[0056] In addition, L1 signaling may be signaling corresponding to at least one or a combination of one or more signaling methods using a physical layer channel or signaling of PDCCH (physical downlink control channel), DCI (downlink control information), UE-specific DCI, group common DCI, common DCI, scheduling DCI (e.g., DCI used for the purpose of scheduling downlink or uplink data), non-scheduling DCI (e.g., DCI not for the purpose of scheduling downlink or uplink data), physical uplink control channel (PUCCH), or uplink control information (UCI). The L1 signaling may also be referred to as physical layer signaling.

[0057] Hereinafter, the expression that information can be configured from a base station in the present disclosure or claims may mean that a terminal receives the information from the base station through physical layer signaling or upper layer signaling, depending on the context, and such expression may be replaced with other terms having the same or substantially similar meaning.

[0058] The operating principle of the present disclosure is described in detail with reference to the attached drawings below.

[0059] Hereinafter, in the present disclosure, upper signaling refers to a signal transmission method in which a base station transmits a signal to a terminal using a downlink data channel of the physical layer, or a terminal transmits a signal to a base station using an uplink data channel of the physical layer. Upper signaling can be understood as radio resource control (RRC) signaling or a media access control (MAC) control element (CE).

[0060] For the convenience of explanation below, this disclosure uses terms and names defined in the 3rd Generation Partnership Project NR (New Radio) or 3rd Generation Partnership Project Long Term Evolution (LTE) standards. However, this disclosure is not limited by the above terms and names, and can be equally applied to systems conforming to other standards. In this disclosure, gNB may be used interchangeably with eNB for the convenience of explanation. That is, a base station described as an eNB may represent a gNB. In addition, the term terminal may represent not only a mobile phone, an MTC device, an NB-IoT device, a sensor, but also other wireless communication devices.

[0061] FIG. 1 is a diagram illustrating the structure of a wireless communication system according to one embodiment of the present disclosure.

[0062] Referring to FIG. 1, a wireless access network of a wireless communication system (New Radio, NR) according to one embodiment of the present disclosure may be composed of a base station (next generation Node B, hereinafter referred to as gNB) (110) and an AMF (105, New Radio Core Network).

[0063] According to one embodiment of the present disclosure, a user terminal (New Radio User Equipment, hereinafter referred to as NR UE or terminal) (115) can access an external network through a gNB (110) and an AMF (105).

[0064] According to one embodiment of the present disclosure, the wireless communication system may be a next-generation wireless communication system, and the base station may be a next-generation base station.

[0065] According to one embodiment, the gNB (110) in FIG. 1 may correspond to an eNB (Evolved Node B) of an LTE system. The gNB (110) is connected to an NR UE via a wireless channel and may provide a service superior to that of a conventional Node B (120). In a wireless communication system according to one embodiment of the present disclosure, since all user traffic is serviced through a shared channel, a device that collects status information such as buffer status, available transmission power status, and channel status of UEs and performs scheduling may be required, and such functions may be performed by the gNB (110). According to one embodiment, a single gNB (110) may typically control multiple cells. In order to implement ultra-high-speed data transmission, it may have a bandwidth greater than the existing maximum, and an orthogonal frequency division multiplexing (OFDM) scheme may be used as a wireless access technology, and additional beamforming technology may be incorporated. Additionally, an adaptive modulation and coding (AMC) method can be applied, which determines the modulation scheme and channel coding rate according to the channel status of the terminal.

[0066] According to one embodiment, in FIG. 1, the AMF (105) may perform functions such as mobility support, bearer setup, and QoS (quality of service) setup. The AMF (105) is a device that is responsible for various control functions as well as mobility management functions for terminals and may be connected to multiple base stations. In addition, the wireless communication system according to one embodiment of the present disclosure may also be interoperable with an LTE system, and for example, the AMF (105) may be connected to an MME (125) via a network interface.

[0067] According to one embodiment, the MME (125) may be connected to an existing base station, eNB (130). For example, in FIG. 1, a terminal supporting LTE-NR Dual Connectivity may transmit and receive data while maintaining a connection to not only the gNB (110) but also the eNB (130) (135).

[0068] FIG. 2 is a diagram for explaining a wireless connection state transition in a wireless communication system according to an embodiment of the present disclosure.

[0069] According to one embodiment of the present disclosure, a wireless communication system may have three radio access states (RRC (radio resource control) states) or RRC modes.

[0070] According to FIG. 2, the connected mode (RRC_CONNECTED, 205) may be a wireless connection state in which the terminal can transmit and receive data. Additionally, the idle mode (RRC_IDLE, 230) may correspond to a wireless connection state in which the terminal monitors whether paging is being transmitted to itself. The above two modes are wireless connection states also applicable to the LTE system, and the detailed technology may be identical to that of the LTE system. The wireless communication system according to an embodiment of the present disclosure may be a next-generation wireless communication system.

[0071] According to one embodiment of the present disclosure, a wireless communication system may define a new inactive (RRC_INACTIVE) radio connection state (215). In this radio connection state (215), UE context may be maintained between a base station and a terminal, and RAN (radio access network)-based paging may be supported. The characteristics of this new radio connection state (215) may include at least one of the following:

[0072] - Cell re-selection mobility;

[0073] - CN - NR RAN connection (both C / U-planes (control plane / user plane)) has been established for UE;

[0074] - The UE AS(Access Stratum) context is stored in at least one gNB and the UE;

[0075] - Paging is initiated by NR RAN;

[0076] - RAN-based notification area is managed by NR RAN;

[0077] - NR RAN knows the RAN-based notification area which the UE belongs to;

[0078] According to one embodiment of the present disclosure, a terminal in an INACTIVE wireless connection state (215) can use a specific procedure and transition to a connected mode (205) or a standby mode (230). The terminal can transition from the INACTIVE mode (215) to the connected mode (205) using a Resume procedure, and can transition from the connected mode (205) to the INACTIVE mode (215) using a Release procedure including suspend configuration information (210). The procedure can be performed by transmitting and receiving one or more RRC messages between the terminal and the base station, and can consist of one or more steps. In addition, according to one embodiment, the transition from the INACTIVE mode (215) to the standby mode (230) can be possible through a Release procedure after the Resume procedure (220). The transition between the connected mode (205) and the standby mode (230) can be based on LTE technology. In addition, according to FIG. 2, the transition between the modes can be performed through an establishment or release procedure (225).

[0079] FIG. 3 is a diagram illustrating an AI / ML model for predicting beam measurement values ​​for beam management according to one embodiment of the present disclosure.

[0080] In one embodiment of the present disclosure, beam management may be one use case that can utilize the AI / ML model. For example, a base station may utilize the AI / ML model for beam management for downlink (DL) transmission beams. In one embodiment of the present disclosure, positioning accuracy enhancements may be one use case that can utilize the AI / ML model. In one embodiment of the present disclosure, channel state information (CSI) feedback enhancement may be one use case that can utilize the AI / ML model.

[0081] In one embodiment of the present disclosure, the beam management use case may include sub-use cases called spatial prediction and temporal prediction.

[0082] In one embodiment of the present disclosure, a set of beams used as input to an AI / ML model for a beam management use case may be referred to as SET B. In one embodiment of the present disclosure, a set of beams derived as output to an AI / ML model for a beam management use case may be referred to as SET A.

[0083] In one embodiment of the present disclosure, in spatial prediction (305) for beam management, the input of the AI / ML model is at a specific point in time (e.g., t K ) in one or more beams (e.g. B i ) for measurements (e.g., RSRP, RSRQ and / or SINR) (e.g., Meas(B i ,t K )) (315) may be. In one embodiment of the present disclosure, the measurement value for the beam may be at least one of the following.

[0084] - RSRP, RSRQ and / or SINR measured at Layer 1

[0085] - RSRP, RSRQ and / or SINR measured / obtained at Layer 3

[0086] - Filtered values ​​of RSRP, RSRQ, and / or SINR measured at Layer 1 (e.g., weighted average values ​​using measurements over a given period of time)

[0087] - A filtered value of RSRP, RSRQ, and / or SINR measured / obtained at Layer 3 (e.g., a (weighted) average value using the measured values ​​over a given period of time)

[0088] In one embodiment of the present disclosure, when performing spatial prediction (305) for beam management, the following information may be considered / used as input to the AI / ML model.

[0089] - SET B related information (e.g., beam-specific ID)

[0090] - Measurement point information

[0091] - L1-RSRP measurement information based on a set of beams used as input to the AI / ML model (L1-RSRP measurement based on Set B)

[0092] - L1-RSRP measurement information and assistance information based on the set of beams used as input to the AI / ML model (L1-RSRP measurement based on Set B and assistance information)

[0093] - Channel Impulse Response (CIR) based on Set B, a set of beams used as input to the AI / ML model

[0094] - L1-RSRP measurement information based on Set B and the corresponding DL Tx and / or Rx beam ID.

[0095] In one embodiment of the present disclosure, in spatial prediction (305) for beam management, the output of the AI / ML model is at a specific point in time (e.g., t K ) in one or more beams (e.g. B i ) for predicted values ​​(e.g., RSRP, RSRQ and / or SINR) (e.g., P_Meas(B i ,t K )) (320) may be.

[0096] In one embodiment of the present disclosure, the predicted value for the beam may be one of the following:

[0097] - RSRP, RSRQ and / or SINR expected to be measured at Layer 1

[0098] - RSRP, RSRQ and / or SINR expected to be measured / obtained at Layer 3

[0099] - Predicted (or filtered) values ​​of the filtered RSRP, RSRQ and / or SINR measured (or predicted to be measured) at Layer 1 (e.g., a (weighted) average using measured / predicted values ​​over a given period of time)

[0100] - Predicted value (or filtered value) of the filtered RSRP, RSRQ and / or SINR measured / obtained (or predicted to be measured / obtained) at Layer 3 (e.g., a (weighted) average value using measured / predicted values ​​over a given period of time)

[0101] In one embodiment of the present disclosure, when performing spatial prediction (305) for beam management, at least one of the following information may be considered / used as an output of the AI / ML model.

[0102] SET A related information (e.g., beam-specific ID)

[0103] One beam that is predicted to have the highest (best) measurement value (e.g., Top-1 beam)

[0104] N (≥1) beams (e.g., Top-N beams) whose measurements are predicted to be the highest (best)

[0105] The probability that each beam in SET A is a Top-1 or Top-N beam

[0106] In one embodiment of the present disclosure, when temporal prediction (310) for beam management, the input of the AI / ML model is one or more (past) points in time (e.g., t i ) in one beam (e.g. B K ), measurements for (e.g., RSRP and / or RSRQ and / or SINR) (e.g., Meas(B K ,t i ))(325) may be. In one embodiment of the present disclosure, the measurement value for the beam may be at least one of the following.

[0107] - RSRP, RSRQ and / or SINR measured at Layer 1

[0108] - RSRP, RSRQ and / or SINR measured / obtained at Layer 3

[0109] - Filtered values ​​of RSRP, RSRQ and / or SINR measured at Layer 1 (e.g., weighted average values ​​using measurements over a given period of time)

[0110] - A filtered value of RSRP and / or RSRQ and / or SINR measured / obtained at Layer 3 (e.g., a weighted average value using the measured values ​​over a given period of time)

[0111] In one embodiment of the present disclosure, when performing temporal prediction (310) for beam management, at least one of the following information may be considered / used as input to the AI / ML model.

[0112] - SET B related information (e.g., beam-specific ID)

[0113] - Measurement point information

[0114] - L1-RSRP measurement information based on the set of beams used as input to the AI / ML model (L1-RSRP measurement based on Set B)

[0115] - L1-RSRP measurement information and assistance information based on the set of beams used as input to the AI / ML model (L1-RSRP measurement based on Set B and assistance information)

[0116] - Channel Impulse Response (CIR) based on Set B, a set of beams used as input to the AI / ML model

[0117] - L1-RSRP measurement information based on Set B and the corresponding DL Tx and / or Rx beam ID.

[0118] In one embodiment of the present disclosure, in temporal prediction (310) for beam management, the output of the AI / ML model is one or more (future) points in time (e.g., t i ) in one beam (e.g. B K ) for predicted values ​​(e.g., RSRP and / or RSRQ and / or SINR) (e.g., P_Meas(B K ,t i ))(330) may be.

[0119] In one embodiment of the present disclosure, the predicted value for the beam may be at least one of the following:

[0120] - RSRP, RSRQ and / or SINR expected to be measured at Layer 1

[0121] - RSRP, RSRQ and / or SINR expected to be measured / obtained at Layer 3

[0122] - Predicted (or filtered) values ​​of the filtered RSRP, RSRQ and / or SINR measured (or predicted to be measured) at Layer 1 (e.g., a (weighted) average using measured / predicted values ​​over a given period of time)

[0123] - Predicted value (or filtered value) of the filtered RSRP, RSRQ and / or SINR measured / obtained (or predicted to be measured / obtained) at Layer 3 (e.g., a (weighted) average value using measured / predicted values ​​over a given period of time)

[0124] In one embodiment of the present disclosure, when performing temporal prediction (310) for beam management, at least one of the following information may be considered / used as an output of the AI / ML model.

[0125] SET A related information (e.g., beam-specific ID)

[0126] Forecast timing information

[0127] The point in time when the measurement value is predicted to be highest (best)

[0128] N (≥1) time points at which the measurement value is predicted to be highest (best)

[0129] In one embodiment of the present disclosure, the AI / ML model for beam management may be an AI / ML model that simultaneously performs the aforementioned spatial prediction and temporal prediction. In this case, the input of the AI / ML model may be measurement values ​​at one or more time points for each beam, for one or more beams. For the input information, reference may be made to the aforementioned content. Furthermore, the output of the AI / ML model may include prediction values ​​at one or more time points for each beam, for one or more beams. For the output information, reference may be made to the aforementioned content.

[0130] In one embodiment of the present disclosure, a terminal may operate an AI / ML model to derive predicted values ​​and related information. The AI / ML model operated by the terminal may be referred to as a UE-sided AI / ML model. The terminal may transmit the derived information and related information to a base station. For example, the base station may utilize the received information to manage downlink transmission beams, improve position accuracy, and / or enhance CSI feedback.

[0131] In one embodiment of the present disclosure, a NW or network (e.g., a base station or LMF (e.g., a location management function)) may drive an AI / ML model to derive predictions and related information. An AI / ML model driven by a NW may be referred to as a NW-sided AI / ML model.

[0132] FIG. 4 is a diagram illustrating a training, inference, and / or performance monitoring procedure for a UE-sided AI / ML model according to an embodiment of the present disclosure.

[0133] In step 405, the terminal (e.g., 401) may report AI / ML-related support capability information of the terminal to a base station (gNB) or a network (NW) (e.g., 402). The report may be transmitted via a UE Capability Information message. Before the terminal makes the report, the base station may transmit a UE Capability Enquiry message to the terminal to request the terminal's support capability report or to request transmission of the report. The AI / ML-related support capability information may include at least one of the following information.

[0134] - Whether the terminal supports AI / ML model-related operations

[0135] - Whether the terminal supports UE-sided AI / ML model-related operations (by use case or sub-use case)

[0136] - Information about use cases, sub-use cases, and / or functionality that the terminal supports for UE-sided AI / ML model-related operations.

[0137] - Information related to network settings (to be described later) supported by the terminal and / or network setting ID (to be described later)

[0138] - Information related to network implementation (to be described later) supported by the terminal and / or network implementation ID (to be described later)

[0139] - Information related to network settings and implementation supported by the terminal (to be described later) and / or network settings / implementation ID (to be described later)

[0140] In step 410, the base station may provide the terminal with “AI / ML related settings” (e.g., via an RRC Reconfiguration message or a UE information Request message, via Layer 1 signaling, via MAC CE, or via Layer 1 and / or RRC CSI reporting settings). The AI / ML related settings may include at least one of the following information.

[0141] - Information 1. AI / ML related setting ID

[0142] > The terminal can receive multiple AI / ML related settings from the base station, and an AI / ML related setting ID can be indicated for each AI / ML related setting to distinguish each AI / ML related setting.

[0143] - Information 2. Information related to use cases, sub-use cases, and / or functionality utilizing AI / ML

[0144] - Information 3. Information related to network settings and / or network implementation.

[0145] > Network configuration-related information may refer to configuration information provided by the network to the terminal. Network configuration-related information may include at least one of the information in the subparagraphs.

[0146] >> Information 3-1. Measurement-related setting information for cells or beams required for training AI / ML models by the terminal or the server (e.g., terminal OTT (over-the-top)) (e.g., 403) connected to the terminal (e.g., beam-related information used as input, beam-related information to be inferred / derived as output, measurement cell information, measurement beam information, measurement beam ID, SET A / B-related information, measurement cycle, measurement resource settings for SET A / B)

[0147] >> Information 3-2. Input and / or output related information and related setting information required when the terminal performs inference using an AI / ML model (e.g., learning completed) (e.g., value / information to be used as input by the terminal, measurement beam information for obtaining measurement values ​​to be used as input by the terminal, measurement beam ID, measurement resource setting, measurement cycle, SET B related information, value / information to be derived as output by the terminal, prediction cycle of predicted values ​​to be derived as output by the terminal, SET A related information, prediction beam ID, time interval to be predicted)

[0148] >> Information 3-3. Network Configuration ID. Each network configuration-related piece of information can be identified / indicated by a single ID (e.g., a network configuration ID). A terminal can receive multiple pieces of network configuration-related information from a base station, and a network configuration ID can be assigned to each piece of network configuration-related information to distinguish it.

[0149] > Network implementation related information may refer to network implementation information other than the network settings that the network sets for the terminal, and may be referred to as NW-side additional conditions. For example, it may include a downlink spatial domain transmission filter, QCL (Quasi colocation) information, TCI (Transmission configuration indication) information, the input and output order of the model, downlink transmission beam information (direction, number), downlink transmission beam operation related settings, beam codebook, antenna operation related settings, transmission power information, terminal distribution information, antenna height information, cell or base station installation environment information (e.g., indoor, outdoor, urban, rural, road), etc. > In one embodiment of the present disclosure, each network implementation related information may be distinguished / indicated by one ID (e.g., network implementation ID). The terminal may receive a plurality of network implementation related information from the base station, and a network implementation ID may be indicated for each network implementation related information in order to distinguish each network implementation related information.

[0150] > In one embodiment of the present disclosure, each network configuration and implementation-related information may be distinguished / indicated by a single ID (e.g., a network configuration / implementation ID). The terminal may receive multiple network configuration / implementation-related information from the base station, and a network configuration / implementation ID may be indicated for each network configuration / implementation-related information to distinguish each network configuration / implementation-related information.

[0151] - Information 4. PLMN information and / or Area information

[0152] > Some or all of the AI / ML related settings received by the terminal may indicate a valid PLMN or Area. In one embodiment of the present disclosure, some or all of the AI / ML related settings received by the terminal may be values ​​used within specific PLMN(s) and / or area(s). That is, when the terminal stays within (or moves within) the specific PLMN(s) and / or area(s), the existing configuration information may be maintained / used, and when the terminal moves out of the specific PLMN(s) and / or area(s) and into a new PLMN(s) and / or area(s), the existing configuration may be released or deleted. When the terminal moves out of the specific PLMN(s) and / or area(s) and into a new PLMN(s) and / or area(s), the corresponding configuration may be updated (by requesting new configurations from the base station or by the base station providing new configurations).

[0153] In step 410, the base station (402) may request the terminal (401) to transmit applicability-related information (e.g., via an RRC Reconfiguration message or a UE information Request message, or via Layer 1 signaling, or via MAC CE, or via Layer 1 and / or RRC CSI reporting settings) (by transmitting AI / ML-related settings). The applicability-related information transmitted by the terminal to the base station may be at least one of the following.

[0154] - Indicates that the terminal can perform inference using the AI / ML model (for the received AI / ML-related settings), monitoring (performance monitoring) the AI / ML model, and / or LCM (Life cycle management) for the AI / ML model (e.g., applicability).

[0155] - Indicates that the terminal cannot perform inference using the AI / ML model (for the received AI / ML-related settings), monitoring (performance monitoring) the AI / ML model, and / or LCM (Life cycle management) for the AI / ML model (e.g., Inapplicability).

[0156] - Indicate one or more use cases, sub-use cases, functionality and / or IDs (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, network implementation ID) (e.g., applicable information) that enable the terminal to perform inference using the AI / ML model (for the received AI / ML-related settings), monitor the AI / ML model (performance monitoring), and / or perform LCM (Life cycle management) for the AI / ML model (e.g., applicable information)

[0157] - Indicate one or more use cases, sub-use cases, functionality and / or IDs (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, network implementation ID) (e.g., inapplicable information) that the terminal cannot perform (e.g., inapplicable) inference using the AI / ML model (for the received AI / ML-related settings), monitoring (performance monitoring) the AI / ML model, or LCM (Life cycle management) for the AI / ML model.

[0158] At step 415, the terminal may determine applicability-related information (after receiving AI / ML-related settings). The terminal may report / instruct the base station of the determined applicability-related information (e.g., step 440).

[0159] In one embodiment of the present disclosure, in step 440, if the terminal can perform inference using an AI / ML model (for the received AI / ML-related settings), monitoring (performance monitoring) of the AI / ML model, and LCM (Life cycle management) for the AI / ML model, the terminal can indicate applicability or applicable information (e.g., applicable use case, sub-use case, functionality, and / or ID (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, network implementation ID)).

[0160] In one embodiment of the present disclosure, in step 440, if the terminal cannot perform inference using the AI / ML model (for the received AI / ML-related settings), monitoring (performance monitoring) of the AI / ML model, and / or LCM (Life cycle management) for the AI / ML model, the terminal may indicate inapplicability or inapplicable information (e.g., inapplicable use case, sub-use case, functionality, and / or ID (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, network implementation ID)).

[0161] In one embodiment of the present disclosure, after receiving AI / ML-related settings (e.g., step 410), the terminal may, in response, indicate (in)applicability to the base station or transmit (in)applicable information. Such an operation may be referred to as reactive (in)applicability reporting.

[0162] In one embodiment of the present disclosure, the terminal may periodically perform an applicability check (e.g., step 415) and, whenever the (in)applicability and / or (in)applicable information changes, may indicate the changed (in)applicability to the base station or transmit (in)applicable information. Such an operation may be referred to as proactive (in)applicability reporting.

[0163] In one embodiment of the present disclosure, the terminal may use a UE Assistance information message, an RRC Reconfiguration complete message, a UE information response message, a new RRC message, Layer 1 signaling, or MAC CE to indicate (in)applicability to the base station or to transmit (in)applicable information.

[0164] In one embodiment of the present disclosure, when the terminal indicates inapplicability and / or inapplicable information, it may indicate a basis or reason for the judgment / decision (e.g., a reason for inapplicability). For example, the basis or reason for the judgment / decision may be at least one of the following:

[0165] - The terminal may indicate that there is no AI / ML model available for inference (for the received AI / ML-related settings).

[0166] - The terminal may indicate that there is no trained AI / ML model (for the received AI / ML-related settings).

[0167] - The terminal can indicate that learning is in progress for the AI / ML model (for the received AI / ML-related settings).

[0168] - The terminal may indicate (with respect to received AI / ML-related settings) that the terminal is in a state that is not suitable for using (e.g., for inference) the AI / ML model (although a trained AI / ML model exists). For example, the terminal may indicate that the terminal is moving at a high speed, that the terminal's battery is low, that the terminal's computing power is low, or that the terminal is entering a room. The terminal may indicate that the internal or external temperature is high.

[0169] - The terminal can indicate (with respect to received AI / ML-related settings) that the terminal state at the time the AI / ML model was trained (even though there is a trained AI / ML model) is different from the current state. For example, it can indicate that the terminal's movement speed is different, that the terminal's surrounding environment has changed (e.g., moving from outdoors to indoors), or that the terminal's internal or external temperature has changed.

[0170] - The terminal indicates that the accuracy or reliability of the AI / ML model's inference (as a result of performance monitoring) is low (for the received AI / ML-related settings).

[0171] In step 420, if the terminal determines / determines inapplicability and / or inapplicable information in step 415 (e.g., there is no AI / ML model available for inference), the terminal may request transmission of an AI / ML model suitable (e.g., available for inference for the received AI / ML-related settings) to a server (e.g., terminal OTT (over-the-top)) that trains and stores an AI / ML model connected to the terminal before reporting this to the base station (e.g., 440). The terminal OTT is a server managed by a terminal vendor and / or a terminal chip vendor and / or a network vendor and / or a network operator, and may train / store AI / ML models for other terminals as well as the terminal in question, and thus may request transmission of the AI / ML model. In response to the request, the terminal may transmit the AI / ML-related configuration information received in 410 and the (internal) environment / condition / status information of the terminal together. The terminal OTT (403) that receives this can determine whether it has an appropriate AI / ML model (e.g., one that can be used for inference for the received AI / ML-related settings).

[0172] In step 430, if the terminal OTT determines that it has a suitable AI / ML model in step 420, the model can be transmitted to the terminal.

[0173] In step 435, if the terminal OTT determines that it does not have a suitable AI / ML model in step 420, the AI / ML model may not be transmitted to the terminal. Alternatively, the terminal OTT may indicate that it does not have a suitable AI / ML model by setting / including a specific indicator (e.g., indicator A).

[0174] In step 435, if the terminal OTT determines that it does not have a suitable AI / ML model in step 420, it can request / instruct the terminal to learn a suitable AI / ML model for the AI / ML-related settings received by the terminal by setting / including a specific indicator (e.g., indicator B).

[0175] In one embodiment of the present disclosure, if the terminal OTT determines in step 420 that it does not possess a suitable AI / ML model, it may request / instruct the base station or network to learn a suitable AI / ML model for the AI / ML-related settings by setting / including a specific indicator (e.g., indicator B). The base station or network receiving this may then perform step 460.

[0176] In step 440, the terminal may report inapplicability and / or inapplicable information to the base station. At this time, the terminal may request the base station to train the AI / ML model (if it receives a request for training of the AI / ML model from the terminal OTT or an indicator B) or request configuration information for training (e.g., by setting / including a specific indicator (e.g., indicator C) in step 445)). In order to indicate AI / ML-related settings for the request, the terminal may indicate some of the AI / ML-related settings (e.g., use case, sub-use case, functionality, and / or ID (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, network implementation ID)) to the base station.

[0177] In step 450, the terminal may delete or disable the AI / ML-related (inference) settings received in step 410 after performing the operation in step 440 and may not perform the related operation. This may be because the terminal is unable to perform inference.

[0178] At step 455, the base station can accept a request to learn the AI / ML model of the terminal.

[0179] In step 460, the base station may provide AI / ML-related settings to the terminal. The AI / ML-related settings may include configuration information for the terminal or the terminal OTT to train an AI / ML model. For example, measurement settings for SET A as well as SET B may be included. This is because the information may be necessary for the terminal or the terminal OTT to train an AI / ML model that derives a specific output (e.g., a measurement value for SET A) from a specific input (e.g., a measurement value for SET B). For a detailed description of the AI / ML-related settings, refer to the description of step 410 described above.

[0180] In step 465, the terminal may perform measurements required for AI / ML model learning (e.g., measurements for SET A / B) based on AI / ML related settings received from the base station (e.g., settings received in 460).

[0181] In step 470, the terminal may transmit to the base station (e.g., via a Measurement report message, a UE Assistance Information message, a UE Information Response message, a new RRC message, via Layer 1 signaling, via MAC CE, or via an RRC Reconfiguration complete message) the result of the measurement (required for AI / ML model learning) performed based on the AI / ML-related settings received from the base station (e.g., the settings received in step 460). The terminal may transmit the aforementioned AI / ML-related setting ID and / or network setting ID and / or network implementation ID and / or network setting / implementation ID together with the measurement result to indicate which AI / ML-related setting the measurement result is based on. In addition, the terminal may transmit information necessary for the terminal OTT to learn the AI / ML model. The information that the terminal transmits to the terminal OTT in step 470 may be referred to as “data necessary for AI / ML model learning.”

[0182] In step 475, the base station can transmit data required for AI / ML model learning received from the terminal to the terminal OTT (via CN (Core network) and / or OAM (Operation and management)).

[0183] In one embodiment of the present disclosure, at step 470, the terminal can directly transmit data required for AI / ML model training to the terminal OTT (e.g., via WIFI without going through a 3GPP network).

[0184] In one embodiment of the present disclosure, at step 470, the terminal AS (e.g., the terminal RRC layer, the physical layer) may transmit data required for AI / ML model training to a higher layer (e.g., the terminal application layer). Upon receiving this, the higher layer (e.g., the terminal application layer) may transmit the measurement results to the terminal OTT via the user plane (e.g., via a base station and / or CN).

[0185] In one embodiment of the present disclosure, at step 470, the terminal AS (e.g., terminal RRC layer, physical layer) can transmit data required for AI / ML model training to a higher layer (e.g., terminal NAS layer). The higher layer (e.g., terminal NAS layer) that receives this can transmit the measurement result to the CN (e.g., AMF, SMF) using the control plane (e.g., via NAS signaling). The CN (e.g., AMF, SMF) that receives this can transmit the corresponding measurement result to the terminal OTT (e.g., via OAM).

[0186] In one embodiment of the present disclosure, the network may, at step 460, instruct the terminal OTT in a manner (e.g., one of the manners for transmitting data required for AI / ML model training to the terminal OTT listed in the multiple embodiments described above) to transmit data required for AI / ML model training to the terminal OTT.

[0187] In one embodiment of the present disclosure, in step 470, the terminal may transmit information about SET A, measurement results, and information about SET B and / or measurement results together within the same message. The terminal may transmit information about SET A, measurement results, and information about SET B and / or measurement results separately / distinctly within the same message. This may be because the terminal OTT must understand information about SET A, measurement results, and information about SET B and / or measurement results separately / distinctly in order to properly train the AI / ML model.

[0188] In one embodiment of the present disclosure, in step 470, the terminal may transmit information about SET A, measurement results, and information about SET B and / or measurement results without separating / distinguishing them (within the same message). Instead, the base station receiving this may separate / distinguish the information about SET A, measurement results, and information about SET B and / or measurement results. This is because the base station may separate / distinguish the information even if it receives information that is not separated / distinguished since it provided SET A / B-related settings in step 470. In step 475, the base station may separate / distinguish the information about SET A, measurement results, and information about SET B and / or measurement results and transmit them to the terminal OTT.

[0189] In step 485, the terminal OTT can perform model training using the data required for AI / ML model training received.

[0190] At step 490, the terminal OTT may complete model learning, performance verification, and / or validation, and then transmit the completed model to the base station (e.g., via CN or OAM).

[0191] At step 495, the base station can transmit the received AI / ML model to the terminal.

[0192] In one embodiment of the present disclosure, at step 490, the terminal OTT can directly transmit the AI / ML model to the terminal (e.g., via WIFI without going through a 3GPP network).

[0193] In one embodiment of the present disclosure, the terminal OTT can transmit a model to a terminal upper layer (e.g., a terminal application layer) through a user plane, and the terminal upper layer that receives the model can directly run the model or pass it on to the terminal AS layer (e.g., so that the terminal AS layer can run it).

[0194] In one embodiment of the present disclosure, a terminal OTT transmits a model to a CN (e.g., AMF, SMF) (e.g., via OAM), and the CN, upon receiving the model, can use the control plane to forward the model to a terminal upper layer (e.g., terminal NAS layer) (e.g., via NAS signaling). The terminal upper layer that receives the model can directly operate the model or forward it to the terminal AS layer (e.g., so that the terminal AS layer can operate it).

[0195] At step 4100, the terminal may now have the trained model and be ready to run the model.

[0196] In step 4105, the terminal may notify the base station that the model has been trained or is in possession of the same. Alternatively, the terminal may indicate applicability or transmit applicable information to the base station as applicability-related information. The reason the terminal notifies the base station of this is because the base station (or network operator) may not be aware that the terminal possesses the model or that training has been completed. For example, the procedures from steps 470 to 495 may be transmitted without going through a 3GPP network (e.g., using a Wi-Fi network). Alternatively, even if the procedures from steps 470 to 495 are transmitted through a 3GPP network, the AI / ML model training and the trained model-related information included in the procedures may be transparent to the base station (or network operator).

[0197] In step 4110, after receiving the information described in step 4105, the base station may release some or all (e.g., measurement settings) of the AI / ML-related settings set for the terminal in step 460. This may be because, for example, the terminal no longer needs to perform measurements for model learning. To this end, the base station may indicate the AI / ML-related settings ID, network configuration ID, network implementation ID, and / or network configuration / implementation ID to indicate the settings to be released.

[0198] In one embodiment of the present disclosure, the terminal may release some or all (e.g., measurement settings) of the AI / ML related settings (received in step 460) by itself after completing the transmission at 4105.

[0199] In step 4115, the base station may provide AI / ML-related settings to the terminal to instruct the terminal to perform inference using the AI / ML model (e.g., via an RRC Reconfiguration message or a UE information Request message, or via Layer 1 signaling, or via MAC CE, or via Layer 1 and / or RRC CSI reporting settings). The AI / ML-related settings may refer to the description described above (e.g., step 410).

[0200] At 4120, the terminal can indicate applicability or transmit applicable information to the base station (e.g., via a Measurement report message, a UE Assistance Information message, a UE Information Response message, a new RRC message, Layer 1 signaling, a MAC CE, or an RRC Reconfiguration complete message).

[0201] In step 4130, the base station can instruct activation of inference using the AI / ML model of the terminal after checking the applicability or applicable information of the terminal (e.g., via an RRC Reconfiguration message, a UE information Request message, via Layer 1 signaling, or via MAC CE).

[0202] At step 4135, the terminal that has received an activation instruction from the base station can start inference using the AI / ML model.

[0203] In one embodiment of the present disclosure, the terminal may initiate inference using the AI / ML model on its own (e.g., without explicit activation instructions from the base station) after indicating applicability to the base station or transmitting applicable information in step 4120 or 4105.

[0204] In one embodiment of the present disclosure, if the base station sets / includes a specific indicator (e.g., indicator D) (e.g., in step 4115), the terminal can start inference using the AI / ML model by itself after indicating applicability to the base station or transmitting applicable information (e.g., without an explicit activation instruction from the base station). Conversely, if the base station does not set or omits the specific indicator (e.g., indicator D) (e.g., in step 4115), the terminal cannot start inference using the AI / ML model by itself after indicating applicability to the base station or transmitting applicable information, and can start inference using the AI / ML model only when it receives an explicit activation instruction (step 4130) from the base station (step 4135).

[0205] In one embodiment of the present disclosure, step 4130 may be performed after step 4105 (steps 4110, 4115, and 4120 may be omitted).

[0206] In one embodiment of the present disclosure, at step 4130 (instead of step 4115), the base station may provide AI / ML-related settings to the terminal to instruct the terminal to perform inference using the AI / ML model, which may also mean an activation instruction for the base station. This may be a possible embodiment if the terminal reports applicability or applicable information to the base station at step 4120.

[0207] In one embodiment of the present disclosure, the base station may use both steps 4115 and 4130 to transmit AI / ML-related settings to the terminal. For example, in step 4115, the base station may transmit only (some or minimal) setting information (e.g., AI / ML-related setting ID, network setting ID, network implementation ID, and / or network setting / implementation ID) for the terminal to determine applicability or applicable information among the AI / ML-related settings, and may provide the remaining (detailed) AI / ML-related setting information (e.g., information required for the terminal to perform inference, resource location information to be measured by the terminal for inference) to the terminal in step 4130 after step 4120 (after receiving applicability or applicable information from the terminal).

[0208] In step 4140, the terminal may transmit the predicted value, predicted information, and / or output information inferred using AI / ML to the base station (e.g., via a Measurement report message, a UE Assistance Information message, a UE Information Response message, a new RRC message, via Layer 1 signaling, via MAC CE, or via an RRC Reconfiguration complete message). At this time, the terminal may transmit the aforementioned AI / ML-related configuration ID, network configuration ID, network implementation ID, and / or network configuration / implementation ID together with the measurement result to indicate which AI / ML-related configuration the measurement result is based on. At this time, the terminal may also transmit information used as input or measurement value information.

[0209] In step 4145, the base station may provide monitoring settings to the terminal (e.g., via an RRC Reconfiguration message, a UE information Request message, Layer 1 signaling, or MAC CE) for performance verification or monitoring of the terminal's AI / ML model. The monitoring settings may include at least one of the following pieces of information:

[0210] - AI / ML related setting ID, network setting ID, network implementation ID and / or network setting / implementation ID related to the monitoring setting in question

[0211] - (e.g., in case of spatial prediction) the cycle at which the terminal must actually perform measurements (for performance monitoring) for the beam that is the prediction target (model output)

[0212] For example, a terminal can perform spatial prediction and perform actual measurements for the predicted beam (e.g., for beams that do not require actual measurements in most cases) at each interval. This allows the terminal to compare and analyze the actually measured values ​​for the beam with the predicted values.

[0213] - (e.g., in case of temporal prediction) the cycle at which the terminal must actually perform measurements (for performance monitoring) for the point in time when the prediction target (model output) is reached

[0214] For example, a terminal can perform temporal prediction, performing actual measurements at each predicted time point (e.g., at points where actual measurements are not required in most cases). This allows the terminal to compare and analyze the predicted values ​​with the values ​​actually measured at that point in time.

[0215] - The period at which the terminal reports to the base station (for performance monitoring) the values ​​actually measured for the beam and / or time point that are the prediction target (model output).

[0216] > For example, at each of the above periods, the terminal can perform a monitoring report (e.g., 4150).

[0217] - An indicator that activates actual measurements at the terminal for the beam and / or time point that is the prediction target (model output) (measurement activation indicator for monitoring)

[0218] > The terminal receiving this can perform actual measurements for the beam and / or time point that becomes the prediction target (model output).

[0219] - An indicator that disables the terminal's actual measurements for the beam and / or time point that is the prediction target (model output) (measurement disable indicator for monitoring)

[0220] > The terminal receiving this can stop the actual measurement in progress for the beam and / or time point that is the prediction target (model output).

[0221] - Condition or event-related setting information (e.g., threshold) that triggers actual measurement of the terminal for the beam and / or time point that becomes the prediction target (model output).

[0222] > For example, if the terminal detects mobility (e.g., if a change in a cell or beam measurement value is greater than a threshold included in the configuration information), the terminal may perform actual measurements of the terminal for the beam and / or time point that is the prediction target (model output). Conversely, if the terminal does not detect mobility (e.g., if a change in a cell or beam measurement value is less than a threshold included in the configuration information), the terminal may stop actual measurements of the terminal for the beam and / or time point that is the prediction target (model output).

[0223] > For example, if the measurement value of the cell or beam being measured is less than the threshold included in the configuration information, the terminal may perform actual measurement of the beam and / or time point that becomes the prediction target (model output). Conversely, if the measurement value of the cell or beam being measured is greater than the threshold included in the configuration information, the terminal may stop actual measurement of the beam and / or time point that becomes the prediction target (model output).

[0224] In step 4150, the terminal may perform a monitoring report. The terminal may perform the monitoring report based on the monitoring configuration information (step 4145).

[0225] In one embodiment of the present disclosure, the terminal can report to the base station both the actually measured value and the predicted value at the beam and / or time point that becomes the prediction target (model output).

[0226] In one embodiment of the present disclosure, the terminal may report to the base station a value generated using the actually measured value and the predicted value at the beam and / or time point that becomes the prediction target (model output). For example, the value may be at least one of the following:

[0227] - Difference between actual measured value and predicted value

[0228] - The probability that the difference between the actual measured value and the predicted value is less than or greater than a certain threshold (e.g., set at 4145).

[0229] - Request to disable AI / ML model inference settings set on the terminal (for example, if the terminal determines that the performance of the AI / ML model is poor due to a large error in comparison between actual measured values ​​and predicted values)

[0230] - Request to update the AI / ML model inference settings set for the terminal (for example, if the terminal determines that the performance of the AI / ML model is poor due to a large error in comparison between the actual measured value and the predicted value)

[0231] In one embodiment of the present disclosure, the terminal may perform a monitoring report only if the difference between the actual measured value and the predicted value is greater than a certain threshold value (e.g., set in 4145).

[0232] At step 4155, the base station can decide on management of the AI / ML model based on the monitoring report received from the terminal.

[0233] In step 4160, the base station can instruct the terminal to make a management decision. For example, if the AI / ML performance is determined to be good, the base station can maintain the inference settings using the AI / ML model configured for the terminal. For example, if the AI / ML performance is determined to be poor, the base station can instruct the terminal to disable or disable the inference settings using the AI / ML model, update the inference settings using the AI / ML model, or switch to a different AI / ML model.

[0234] FIG. 5 is a diagram illustrating a procedure for requesting and receiving settings for collecting data required for training an Artificial Intelligence (AI) / Machine Learning (ML) model by a terminal according to an embodiment of the present disclosure.

[0235] In step 515, the base station (gNB) (510) may transmit a UE Capability Enquiry message requesting UE capability information to the terminal (505).

[0236] In step 520, the terminal (505) may transmit a UE Capability Information message including terminal capability information to the base station (510). The terminal capability information may include information A.

[0237] In one embodiment, the information A may mean an indicator or information related thereto indicating whether the terminal (505) supports or supports a request for data collection (required for UE-side and / or NW-side AI / ML model training) (e.g., a request for starting or stopping data collection, or configuration information indicating an intention to perform (or start) data collection, configuration information indicating an intention to stop data collection, or a request for a candidate configuration (e.g., 525) (list) that can be used for data collection that the base station (510) can provide).

[0238] For example, if the terminal (505) supports the request, it may set or include the information A (in the UE Capability Enquiry message) as 'true'. For example, if the terminal (505) does not support the request, it may set or omit the information A (in the UE Capability Enquiry message). In one embodiment of the present disclosure, the request may mean a request made by the terminal (505) through UE Assistance Information transmission.

[0239] In step 525, the base station (510) may provide the terminal (505) with one or more candidate settings (settings for the terminal to collect data required for model learning) that it can provide or supports.

[0240] Optionally, prior to step 525, in step 522, if the base station (510) has received terminal capability information for the information A, it may determine to provide the candidate setting to the terminal (505). On the other hand, if the base station (510) has not received terminal capability information for the information A, it may determine not to provide the candidate setting to the terminal (505).

[0241] The base station (510) may provide the candidate configuration to the terminal (505) via an RRC Reconfiguration message or an RRC Resume message. The candidate configuration may be included in OtherConfig and / or CSI-MeasConfig and / or CSI-ReportConfig configurations. In one embodiment of the present disclosure, the candidate configuration may be included in OtherConfig. In one embodiment of the present disclosure, the candidate configuration may be indicated as CSI-ReportConfigId in OtherConfig, and detailed configurations may be included in the indicated CSI-ReportConfig (e.g., CSI-ReportConfig included in csi-ReportConfigToAddModList included in CSI-MeasConfig). In one embodiment of the present disclosure, the candidate configuration may be included as CSI-ReportConfig in OtherConfig.

[0242] If the above candidate setting is indicated by CSI-ReportConfig or CSI-ReportConfigId, a setting indicating that CSI reporting is not required for the corresponding CSI-ReportConfig may be included in the CSI-ReportConfig. For example, reportQuantity may be set to none or none-BM-r19.

[0243] The above candidate setting may include at least one piece of information from the information in Table 1 below.

[0244]

[0245] In one embodiment of the present disclosure, the candidate setting may include only one associated ID for Set A and Set B. For example, if Set B is a subset of or identical to Set A, the candidate setting may include only one associated ID for Set A and Set B. In one embodiment of the present disclosure, the terminal (505) may not perform measurement and data collection for the candidate setting and may perform measurement and data collection when an actual data collection setting (e.g., step 535) is received later.

[0246] In one embodiment of the present disclosure, when the terminal receives the candidate settings from the base station, it may consider that transmission of a request for data collection (for model learning) is permitted.

[0247] In one embodiment of the present disclosure, the description of step 525 may be cross-referenced with the description of step 410 of FIG. 4.

[0248] In step 530, the terminal (505) may transmit a request regarding data collection (e.g., a request (or preference) for starting or stopping data collection, or configuration information indicating (or preferring) to perform (or start) data collection, configuration information indicating to stop data collection, or a request for candidate configurations (e.g., step 525) (list) that can be used for data collection that the base station (510) can provide) to the base station (510). The terminal (505) may transmit information related to the request to the base station (510) via a UE Assistance Information message.

[0249] In one embodiment of the present disclosure, the description of step 530 may be cross-referenced with the description of steps 440 and 445 of FIG. 4.

[0250] In one embodiment of the present disclosure, if the base station (510) provides the candidate settings in step 525, the terminal (505) may transmit the request. In one embodiment of the present disclosure, if the base station (510) does not provide the candidate settings, the terminal (505) may not transmit the request. In one embodiment of the present disclosure, the terminal (505) may select (preferred) some or all (one or more) settings for which it wants to perform / start measurements for data collection among the one or more candidate settings provided by the base station (510) and instruct the base station (510) to select the same (e.g., instruct candidate setting related information or instruct an ID associated with the candidate setting).

[0251] The ASN.1 (Abstract Syntax Notation One) structure of the above request can be expressed as shown in Table 2 below.

[0252]

[0253] The terminal's actions in response to the above request can be expressed as shown in Table 3 below.

[0254]

[0255] In step 535, the base station (510) may provide the terminal (505) with settings (measurement / collection settings or actual measurement / collection settings) required for data collection. The settings may be provided, for example, via an RRC Reconfiguration or RRC Resume message. The base station (510) may provide the terminal (505) with some or all of the (preferred) settings indicated by the terminal (505) provided in step 530. The actual measurement settings may be provided to the terminal (505) as settings within CSI-MeasConfig (within CSI-ReportConfig) rather than within OtherConfig. The description of step 535 may be cross-referenced with the description of step 460 of FIG. 4 .

[0256] In step 540, the terminal (505) may perform measurements (based on the data collection settings provided by the base station (510) in step 535) and collect data necessary for model learning. The description of step 540 may be cross-referenced with the description of step 465 of FIG. 4.

[0257] In step 545, the terminal (505) can transmit the collected data to the base station (510).

[0258] In step 555, the base station (510) may (process / process) data or a message including data received from the terminal (505) and transmit it to the CN or OAM (550).

[0259] In step 565, the CN or OAM (550) may process / handle data or a message containing data received from the base station (510) and transmit it to a learning object (e.g., UE server or NW server) (560).

[0260] The descriptions of steps 545, 555, and 565 above may be cross-referenced with the descriptions of steps 470 and 475 of FIG. 4.

[0261] In step 570, the learning object (560) may perform model learning using the received data. The description of step 570 may be cross-referenced with the description of step 485 of FIG. 4.

[0262] In one embodiment of the present disclosure, the data transmission process can be performed transparently to the base station (510) and / or CN and / or OAM (550) (e.g., without processing / managing their data or messages).

[0263] In step 575, if the terminal (505) wants to stop data collection and / or measurements for data collection (if it prefers to stop), it can transmit a request to the base station (510) to stop data collection. The request can be transmitted, for example, via a UE Assistance Information message. For example, the terminal (505) can transmit the stop request to the base station (510) after receiving information indicating that model learning has been completed from the learning object (560). For example, the terminal (505) can transmit the stop request to the base station (510) when it detects a lack of energy / battery.

[0264] In step 580, the base station (510) may instruct the terminal (505) to release data collection and / or measurement settings. The release instruction may be transmitted, for example, via an RRC Reconfiguration or RRC Resume message. In one embodiment of the present disclosure, the terminal (505) that receives the release instruction may stop measurement and / or data collection for model learning.

[0265] FIG. 6 is a diagram illustrating a procedure for requesting settings for a terminal to collect data required for training an Artificial Intelligence (AI) / Machine Learning (ML) model, according to one embodiment of the present disclosure.

[0266] At step 615, the UE may send an RRC Setup Request message to the gNB-DU (distributed unit) (for initial connection).

[0267] At step 620, the gNB-DU may transmit an RRC Setup Request message and, if the UE is authorized, the lower layer settings of the UE to the gNB-CU (centralized unit) in an INITIAL UL RRC MESSAGE TRANSFER message. The INITIAL UL RRC MESSAGE TRANSFER message may include the C-RNTI allocated by the gNB-DU.

[0268] In step 630, the gNB-CU may allocate a gNB-CU UE F1AP ID to the UE and generate an RRC Setup message targeting the UE. The RRC message or RRC Setup message may be encapsulated in a DL RRC MESSAGE TRANSFER message and transmitted to the gNB-DU.

[0269] At step 635, the gNB-DU may send an RRC Setup message to the UE.

[0270] At step 640, the UE may send an RRC SETUP COMPLETE message to the gNB-DU.

[0271] At step 645, the gNB-DU may encapsulate the RRC message or the RRC SETUP COMPLETE message into a UL RRC MESSAGE TRANSFER message and transmit it to the gNB-CU.

[0272] At step 650, the gNB-CU may send an INITIAL UE MESSAGE message to the AMF.

[0273] In step 660, the AMF may transmit an INITIAL CONTEXT SETUP REQUEST message to the gNB-CU. The INITIAL CONTEXT SETUP REQUEST message may include terminal capability information or a message including terminal capability information. For example, at least one of the capability information described above in step 520 may be included in the INITIAL CONTEXT SETUP REQUEST message. For example, it may include whether the terminal supports a request for data collection (required for UE-side and / or NW-side AI / ML model training).

[0274] At step 665, the gNB-CU may transmit a UE CONTEXT SETUP REQUEST message to the gNB-DU to set up a UE context. This message may encapsulate a SecurityModeCommand message. The gNB-CU may request the gNB-DU (via the UE CONTEXT SETUP REQUEST message) for information (e.g., information A) necessary to set candidate configurations for data learning (within OtherConfig) to the UE. For example, the gNB-CU may indicate the request to the gNB-DU by setting one indicator (e.g., indicator E) in the UE CONTEXT SETUP REQUEST message to “true.” For example, the gNB-CU may transmit the request to the gNB-DU including the (maximum) number of candidate configurations for data learning that it requests / requires. In this case, the gNB-DU may provide the corresponding number (or less) of candidate configurations to the gNB-CU. For example, a gNB-CU may request part or all of a candidate set for data learning (including that information) by indicating to the gNB-DU the associated ID (for Set A and / or Set B) and / or CSI resource (e.g., CSI-ResourceId) and / or (serving) cell ID or index.

[0275] In one embodiment of the present disclosure, the request may be included in a message (e.g., UE CONTEXT SETUP REQUEST, UE CONTEXT RELEASE COMMAND, UE CONTEXT MODIFICATION REQUEST, UE CONTEXT MODIFICATION CONFIRM, UE CONTEXT MODIFICATION REFUSE, DL RRC MESSAGE TRANSFER, CU-DU RADIO INFORMATION TRANSFER) transmitted by the gNB-CU to the gNB-DU.

[0276] At step 670, the gNB-DU may send a SecurityModeCommand message to the UE.

[0277] At step 675, the gNB-DU may determine / generate candidate configuration information (e.g., information A) regarding data learning (within OtherConfig). The gNB-DU may determine / generate information A based on a request (e.g., 665) provided by the gNB-CU.

[0278] In step 680, the gNB-DU may transmit a UE CONTEXT SETUP RESPONSE message to the gNB-CU. The gNB-DU may include information A in the message. In one embodiment of the present disclosure, information A may be included in a message (e.g., UE CONTEXT SETUP RESPONSE, UE CONTEXT SETUP FAILURE, UE CONTEXT RELEASE REQUEST, UE CONTEXT RELEASE COMPLETE, UE CONTEXT MODIFICATION RESPONSE, UE CONTEXT MODIFICATION FAILURE, UE CONTEXT MODIFICATION REQUIRED, INITIAL UL RRC MESSAGE TRANSFER, UL RRC MESSAGE TRANSFER, RRC DELIVERY REPORT, DU-CU RADIO INFORMATION TRANSFER) that the gNB-DU transmits to the gNB-CU. Information A may include at least one of the information in Table 1.

[0279] In step 685, the gNB-CU may determine / generate candidate configuration information (e.g., information A') for data learning based on information provided by the gNB-DU (e.g., information A). For example, the gNB-CU may determine / generate information A' by selecting some of the configurations provided by the gNB-DU. For example, the gNB-CU may determine / generate information A' by selecting, modifying, or processing some of the configuration information provided by the gNB-DU.

[0280] At step 690, the UE may respond with a Security Mode Complete message.

[0281] At step 695, the gNB-DU may encapsulate the Security Mode Complete message in a UL RRC MESSAGE TRANSFER message and transmit it to the gNB-CU.

[0282] In step 6100, the gNB-CU may generate an RRC Reconfiguration message, encapsulate it in a DL RRC MESSAGE TRANSFER message, and transmit it to the gNB-DU. The gNB-CU may include candidate configuration information regarding data learning by including information A or information A' (in OtherConfig) in the RRC Reconfiguration message (697). In one embodiment of the present disclosure, the information A or information A' may be included in a message that the gNB-CU transmits to the gNB-DU (e.g., UE CONTEXT SETUP REQUEST, UE CONTEXT RELEASE COMMAND, UE CONTEXT MODIFICATION REQUEST, UE CONTEXT MODIFICATION CONFIRM, UE CONTEXT MODIFICATION REFUSE, DL RRC MESSAGE TRANSFER, CU-DU RADIO INFORMATION TRANSFER).

[0283] In step 6105, the gNB-DU may transmit an RRC Reconfiguration message to the UE. The RRC Reconfiguration message may include information A or information A', or candidate configuration information regarding data learning. The description of step 6105 may be cross-referenced with the description of step 525.

[0284] At step 6110, the terminal may transmit an RRC Reconfiguration Complete message to the gNB-DU.

[0285] At step 6115, the gNB-DU may encapsulate the RRC Reconfiguration Complete message into a UL RRC MESSAGE TRANSFER message and transmit it to the gNB-CU.

[0286] At step 6120, the gNB-CU may send an INITIAL CONTEXT SETUP RESPONSE message to the AMF.

[0287] In step 6125, the terminal may transmit to the base station information including some or all of the candidate settings (including information A or information A') related to data learning (data collection or measurement desired or preferred by the terminal). The terminal may indicate this via a UE Assistance Information message. The description of step 6125 may be cross-referenced with the description of step 535.

[0288] At step 6130, the gNB-DU may transmit a UL RRC MESSAGE TRANSFER message (including the UE's indication / preference setting or including the UE Assistance Information message) to the gNB-CU.

[0289] At step 6135, the gNB-CU may send a UE CONTEXT MODIFICATION REQUEST message to the gNB-DU (including the UE's instructions / preferences or including the UE Assistance Information message).

[0290] At step 6140, the gNB-DU may send a UE CONTEXT MODIFICATION RESPONSE message to the gNB-CU.

[0291] FIG. 7 is a diagram illustrating the internal structure of a terminal according to one embodiment of the present disclosure.

[0292] Fig. 7 may represent a structure for a terminal described in Figs. 1 to 6.

[0293] Referring to FIG. 7, the terminal may include an RF (Radio Frequency) processing unit (710), a baseband processing unit (720), a storage unit (730), and a control unit (740).

[0294] The RF processing unit (710) may perform functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. For example, the RF processing unit (710) may up-convert a baseband signal provided from the baseband processing unit (720) into an RF band signal and transmit the same through an antenna, and may down-convert an RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (710) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital to analog convertor (DAC), an analog to digital convertor (ADC), etc. In FIG. 5, only one antenna is illustrated, but the terminal may be equipped with multiple antennas. In addition, the RF processing unit (710) may include multiple RF chains. In addition, the RF processing unit (710) may perform beamforming. For the above beamforming, the RF processing unit (710) can adjust the phase and size of each signal transmitted and received through multiple antennas or antenna elements. In addition, the RF processing unit can perform MIMO (multi-input multi-output) and can receive multiple layers when performing MIMO operation.

[0295] The baseband processing unit (720) may perform a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the baseband processing unit (720) may generate complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (720) may restore a reception bit stream by demodulating and decoding a baseband signal provided from the RF processing unit (710). For example, in the case of following the orthogonal frequency division multiplexing (OFDM) method, when transmitting data, the baseband processing unit (720) may generate complex symbols by encoding and modulating a transmission bit stream, and may map the complex symbols to subcarriers, and then configure OFDM symbols through an inverse fast Fourier transform (IFFT) operation and a cyclic prefix (CP) insertion. In addition, when receiving data, the baseband processing unit (720) can divide the baseband signal provided from the RF processing unit (710) into OFDM symbol units, restore signals mapped to subcarriers through FFT (fast Fourier transform) operation, and then restore the received bit string through demodulation and decoding.

[0296] The baseband processing unit (720) and the RF processing unit (710) can transmit and receive signals as described above. Accordingly, the baseband processing unit (720) and the RF processing unit (710) may be referred to as a transmitter, a receiver, a transceiver, or a communication unit. Furthermore, at least one of the baseband processing unit (720) and the RF processing unit (710) may include a plurality of communication modules to support a plurality of different wireless access technologies. In addition, at least one of the baseband processing unit (720) and the RF processing unit (710) may include different communication modules to process signals of different frequency bands. For example, the different wireless access technologies may include a wireless LAN (e.g., IEEE 802.11), a cellular network (e.g., LTE), etc. Additionally, the different frequency bands may include a super high frequency (SHF) (e.g., 2.NRHz, NRhz) band and a millimeter wave (mm wave) (e.g., 60GHz) band.

[0297] The storage unit (730) can store data such as basic programs, application programs, and setting information for the operation of the terminal. In particular, the storage unit (730) can store information related to a second access node that performs wireless communication using wireless access technology. In addition, the storage unit (730) can provide the stored data at the request of the control unit (740).

[0298] The control unit (740) can control the overall operations of the terminal. For example, the control unit (740) can transmit and receive signals through the baseband processing unit (720) and the RF processing unit (710). In addition, the control unit (740) can record and read data in the storage unit (730). For this purpose, the control unit (740) can include at least one processor. For example, the control unit (740) can include a communication processor (CP) that performs control for communication and an application processor (AP) that controls upper layers such as application programs, and can include a multi-connection processing unit (742) as illustrated in the drawing.

[0299] FIG. 8 is a diagram illustrating the structure of a base station according to one embodiment of the present disclosure.

[0300] FIG. 8 may represent a structure for a base station described in FIGS. 1 to 6.

[0301] Referring to FIG. 8, according to an example of the present disclosure, a base station may be configured to include an RF processing unit (810), a baseband processing unit (820), a backhaul communication unit (830), a storage unit (840), and a control unit (850).

[0302] The RF processing unit (810) may perform functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (810) may up-convert a baseband signal provided from the baseband processing unit (820) into an RF band signal and transmit the same through an antenna, and may down-convert an RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (810) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc. In the drawing, only one antenna is illustrated, but the base station may have multiple antennas. In addition, the RF processing unit (810) may include multiple RF chains. In addition, the RF processing unit (810) may perform beamforming. For the beamforming, the RF processing unit (810) may adjust the phase and magnitude of each of the signals transmitted and received through multiple antennas or antenna elements. The above RF processing unit can perform a downlink MIMO operation by transmitting one or more layers.

[0303] The baseband processing unit (820) may perform a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the wireless access technology. For example, when transmitting data, the baseband processing unit (820) may generate complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the baseband processing unit (820) may restore a reception bit stream by demodulating and decoding a baseband signal provided from the RF processing unit (810). For example, in the case of OFDM, when transmitting data, the baseband processing unit (820) may generate complex symbols by encoding and modulating a transmission bit stream, and may map the complex symbols to subcarriers, and then configure OFDM symbols through IFFT operation and CP insertion. In addition, when receiving data, the baseband processing unit (820) can divide the baseband signal provided from the RF processing unit (810) into OFDM symbol units, restore signals mapped to subcarriers through FFT operation, and then restore the received bit string through demodulation and decoding. The baseband processing unit (820) and the RF processing unit (810) can transmit and receive signals as described above. Accordingly, the baseband processing unit (820) and the RF processing unit (810) may be referred to as a transmitter, a receiver, a transceiver, a communication unit, or a wireless communication unit.

[0304] The backhaul communication unit (830) may provide an interface for communicating with other nodes within the network. That is, the backhaul communication unit (830) may convert a bit string transmitted from the main base station to another node, such as an auxiliary base station or a core network, into a physical signal, and may convert a physical signal received from the other node into a bit string.

[0305] The storage unit (840) can store data such as basic programs, application programs, and configuration information for the operation of the main base station. In particular, the storage unit (840) can store information on bearers assigned to connected terminals, measurement results reported from connected terminals, and the like. In addition, the storage unit (840) can store information that serves as a judgment criterion for whether to provide or terminate multiple connections to a terminal. In addition, the storage unit (840) can provide stored data at the request of the control unit (850).

[0306] The control unit (850) can control the overall operations of the base station. For example, the control unit (850) can transmit and receive signals through the baseband processing unit (820) and the RF processing unit (810) or through the backhaul communication unit (830). In addition, the control unit (850) can record and read data in the storage unit (840). To this end, the control unit (850) can include at least one processor and, as illustrated in the drawing, a multi-connection processing unit (852).

[0307] The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0308] When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to the embodiments described in the claims or specification of the present disclosure.

[0309] These programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic disc storage device, compact disc ROM (CD-ROM), digital versatile discs (DVDs) or other forms of optical storage device, magnetic cassette. Or, they may be stored in a memory configured as a combination of some or all of these. In addition, each configuration memory may be included in multiple numbers.

[0310] Additionally, the program may be stored in an attachable storage device that is accessible via a communication network such as the Internet, an intranet, a local area network (LAN), a wide local area network (WLAN), a storage area network (SAN), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device performing an embodiment of the present disclosure.

[0311] In this disclosure, the term "computer program product" or "computer-readable medium" is used to collectively refer to media such as memory, a hard disk installed in a hard disk drive, and signals. These "computer program products" or "computer-readable mediums" are components provided in a method for reporting terminal capabilities in a wireless communication system according to the present disclosure.

[0312] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.

[0313] According to one embodiment, the method according to various embodiments disclosed in the present document 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 machine-readable storage medium (e.g., 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 (e.g., a downloadable app) may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0314] In the specific embodiments of the present disclosure described above, components included in the invention are expressed in the singular or plural form, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in the plural form may be composed of singular elements, or components expressed in the singular form may be composed of plural elements.

[0315] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims set forth below, but also by equivalents thereof.

Claims

1. In a method performed by a terminal of a wireless communication system, A step of receiving a first message including a plurality of configuration information related to measurements for learning artificial intelligence (AI / ML) from a base station; A step of transmitting a second message to the base station for requesting first setting information for the measurement; A step of receiving a third message from the base station for providing second setting information for the measurement; and A method comprising a step of performing the measurement for learning of the artificial intelligence based on the second setting information.

2. In paragraph 1, A method wherein the first setting information includes at least one of the plurality of setting information.

3. In paragraph 1, The above second setting information is, A first measurement resource setting associated with the output of the artificial intelligence model, a second measurement resource setting associated with the input of the artificial intelligence model, and a first identifier associated with the network, A method wherein the first measurement resource setting and the second measurement resource setting are related to channel state information (CSI) setting.

4. In paragraph 1, One of the above plurality of setting information is: A third measurement resource setting associated with the output of the artificial intelligence model, a fourth measurement resource setting associated with the input of the artificial intelligence model, and a second identifier associated with the network, The above third measurement resource setting and the above fourth measurement resource setting are related to the CSI setting, A method wherein the second message comprises a UE Assistance Information (UAI) message.

5. In a method performed by a base station of a wireless communication system, A step of transmitting a first message including a plurality of setting information related to measurements for learning artificial intelligence (AI / ML) to a terminal; A step of receiving a second message for requesting first setting information for the measurement from the terminal; and A method comprising the step of transmitting a third message to the terminal for providing second setting information for the measurement.

6. In paragraph 5, A method wherein the first setting information includes at least one of the plurality of setting information.

7. In paragraph 5, The above second setting information is, A first measurement resource setting associated with the output of the artificial intelligence model, a second measurement resource setting associated with the input of the artificial intelligence model, and a first identifier associated with the network, A method wherein the first measurement resource setting and the second measurement resource setting are related to channel state information (CSI) setting.

8. In paragraph 5, One of the above plurality of setting information is: A third measurement resource setting associated with the output of the artificial intelligence model, a fourth measurement resource setting associated with the input of the artificial intelligence model, and a second identifier associated with the network, The above third measurement resource setting and the above fourth measurement resource setting are related to the CSI setting, A method wherein the second message comprises a UE Assistance Information (UAI) message.

9. For UE (user equipment): At least one transceiver; At least one processor communicatively coupled to said at least one transceiver; and At least one memory communicatively coupled to said at least one processor and storing instructions, The above instructions are executed individually or in any combination by the at least one processor so that the UE: Receive a first message from a base station including a plurality of configuration information for measurements for learning artificial intelligence (AI / ML), Transmitting a second message to the base station to request first setting information for the measurement, Receive a third message from the base station for providing second setting information for the measurement, and A UE that performs the measurement for learning of the artificial intelligence based on the second setting information.

10. In paragraph 9, The UE, wherein the first setting information includes at least one of the plurality of setting information.

11. In paragraph 9, The above second setting information is, A first measurement resource setting associated with the output of the artificial intelligence model, a second measurement resource setting associated with the input of the artificial intelligence model, and a first identifier associated with the network, The above first measurement resource setting and the above second measurement resource setting are related to channel state information (CSI) setting, UE.

12. In paragraph 9, One of the above plurality of setting information is: A third measurement resource setting associated with the output of the artificial intelligence model, a fourth measurement resource setting associated with the input of the artificial intelligence model, and a second identifier associated with the network, The above third measurement resource setting and the above fourth measurement resource setting are related to the CSI setting, The second message includes a UE Assistance Information (UAI) message.

13. At the base station: At least one transceiver; At least one processor communicatively coupled to said at least one transceiver; and At least one memory communicatively coupled to said at least one processor and storing instructions, The above instructions are executed individually or in any combination by the at least one processor so that the base station: Transmitting a first message to the terminal, which includes a plurality of configuration information related to measurements for learning artificial intelligence (AI / ML), Receive a second message from the terminal to request first setting information for the measurement, and A base station that transmits a third message to the terminal to provide second setting information for the measurement.

14. In paragraph 13, The first setting information includes at least one of the plurality of setting information, The above second setting information is, A first measurement resource setting associated with the output of the artificial intelligence model, a second measurement resource setting associated with the input of the artificial intelligence model, and a first identifier associated with the network, The above first measurement resource setting and the above second measurement resource setting are related to channel state information (CSI) setting, the base station.

15. In paragraph 13, One of the above plurality of setting information is: A third measurement resource setting associated with the output of the artificial intelligence model, a fourth measurement resource setting associated with the input of the artificial intelligence model, and a second identifier associated with the network, The above third measurement resource setting and the above fourth measurement resource setting are related to the CSI setting, The second message includes a UE Assistance Information (UAI) message, wherein the base station.

Images