Method and device for performing ai / ML-based positioning in wireless communication system

Abstract

A method and device by which a base station performs AI / ML-based positioning may be provided, the method comprising the steps of: receiving, from a location management device, a measurement request including a time reporting granularity factor k, a time domain window size Nt, and the number of samples to be reported Nt'; obtaining a time domain channel response by measuring an SRS for positioning transmitted from a terminal; determining Nt' samples among Nt consecutive time domain samples on the basis of a time granularity T determined on the basis of k and a basic time unit Tc; and transmitting measurement information for the determined Nt' samples to the location management device.

Description

Method and device for performing AI / ML-based positioning in a wireless communication system

[0001] The present disclosure relates to a method and apparatus for performing AI / ML-based positioning in a wireless communication system.

[0002] The International Telecommunication Union (ITU) is conducting standardization of next-generation 5th generation (5G) and 6th generation (6G) mobile communications through the International Mobile Telecommunication (IMT)-2020 and IMT-2030 programs.

[0003] The next-generation 6th generation (6G) mobile communication system is defined as an evolutionary system that further enhances the performance of 5th generation (5G) technology, and at the same time, as a next-generation communication platform that encompasses new services and industrial applications. Based on the ultra-high transmission rates, ultra-low latency, and massive terminal connectivity achieved by 5G, 6G aims for ultra-broadband, ultra-precision, ultra-intelligence, and ultra-convergence.

[0004] To achieve this, various technologies are being discussed in 6G, including the utilization of FR3 and terahertz (THz) bands, large-scale antennas and new numerology designs, AI / ML native network optimization, global coverage based on non-terrestrial networks (NTN), dynamic channel control by intelligent reflective surfaces (RIS), and integrated sensing and communication (ISAC). In addition, technologies to enhance network energy efficiency are also being treated as an important research axis in 6G. Therefore, to achieve the goals of ultra-high speed, ultra-low latency, intelligence, global coverage, and convergence services that the next-generation 6th generation (6G) mobile communication system aims for, technical challenges related to AI-Native RAN supporting AI / ML-based network optimization, non-terrestrial networks (NTN) ensuring global connectivity, ISAC converging communication, location, and sensing, intelligent reflective surfaces (RIS) enabling dynamic channel control, and securing energy efficiency for sustainable network operation need to be resolved.

[0005] Therefore, there is an urgent need for the proposal and research of various technologies capable of meeting the technical requirements for this purpose.

[0006] The present embodiments aim to provide a method and apparatus for performing AI / ML-based positioning in a wireless communication system.

[0007] The present embodiments aim to provide a method and apparatus for optimizing high-dimensional original measurement information into low-dimensional measurement information as input data for an AI / ML model to infer the location of a terminal in a wireless communication system.

[0008] In order to solve the aforementioned problem, in one aspect, the present disclosure relates to a method for a base station to perform AI / ML-based positioning, wherein from a location management function (LMF), a timing reporting granularity factor k and a time domain window size N t , and number of samples to be reported N t A step of receiving a measurement request including ', a step of obtaining a time-domain channel response by measuring a sounding reference signal (SRS) for positioning transmitted from a terminal, N t Among n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Step of determining ' number of samples and determined N t A method can be provided that includes the step of transmitting measurement information for ' samples to a location management device.

[0009] In another aspect, the present disclosure relates to a method in which a location management function (LMF) performs AI / ML-based positioning, wherein the base station comprises a timing reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t The method includes the step of transmitting a measurement request including ' and the step of receiving measurement information from a base station as a response to the measurement request, wherein the measurement information is N obtained based on a sounding reference signal (SRS) for positioning transmitted from a terminal t Among n consecutive time domain samples, N determined according to the time grain size T determined based on k and the base time unit Tc tIt can provide a method to include information on ' samples.

[0010] In another aspect, the present disclosure relates to a base station performing AI / ML-based positioning, comprising a transmitter, a receiver, and a control unit that controls the operation of the transmitter and the receiver, wherein the control unit (1410) receives from a location management function (LMF) a timing reporting granularity factor k and a time domain window size N t , and the number of samples to be reported N t Receive a measurement request including ', measure the sounding reference signal (SRS) for positioning transmitted from the terminal to obtain a time-domain channel response, and N t Among n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Determine ' samples, and the determined N t A base station can be provided that transmits measurement information for ' 1 sample to a location management device.

[0011] According to the present disclosure, AI / ML-based positioning technology in a wireless communication system not only improves location estimation accuracy but also, by being combined with location-based network control functions such as beam management, handover, and link adaptation, provides the effect of improving overall communication stability and quality of service (QoS / QoE).

[0012] According to the present disclosure, performance degradation of an AI / ML model that may occur due to changes in the wireless environment, changes in terminal mobility, or changes in frequency bands in a wireless communication system can be detected at the network level, and positioning performance can be continuously optimized by adaptively adjusting measurement parameters, input data configuration, or AI / ML model updates in response.

[0013] According to the present disclosure, an AI / ML-based positioning technology in a wireless communication system can control the network to selectively measure and report only the information required by the network, thereby reducing unnecessary measurement signal transmission and reporting overhead and improving wireless resource usage efficiency.

[0014] According to the present disclosure, by efficiently applying AI / ML-based positioning as part of a communication procedure in a wireless communication system and controlling the reporting method and scope of time-domain channel information used for positioning at the network level, it is possible to reduce measurement information reporting overhead while simultaneously improving AI / ML-based positioning accuracy and communication efficiency in a balanced manner.

[0015] According to the present disclosure, by adopting a structure in which a location management device (LMF) determines the selection criteria for time-domain samples in a wireless communication system and a base station performs measurement and sample selection in accordance with the request, the effect of managing AI / ML model control and positioning policies in a network-centric manner without increasing the complexity of base station implementation is provided. Through this, by continuously monitoring the performance of the AI / ML model at the network level and adaptively adjusting measurement parameters, it is possible to prevent degradation of positioning performance and improve communication stability.

[0016] According to the present disclosure, the advantages of improving prediction accuracy and communication stability are provided by efficiently applying an AI / ML model as part of a communication procedure in a wireless communication system and continuously monitoring the performance of the said AI / ML model at the network level.

[0017] Furthermore, according to the present disclosure, an AI / ML native communication structure is supported in which network control and resource management are performed based on the operation results of an AI / ML model in a wireless communication system, thereby enabling the AI / ML model to be utilized as an essential network component rather than a mere auxiliary function. Based on this structure, the present disclosure effectively detects performance degradation of the AI / ML model that may occur due to changes in the wireless environment, traffic characteristics, and user mobility, and enables adaptive correction and optimization thereof, thereby stably securing the high reliability and prediction accuracy required for next-generation mobile communication systems. This provides a technical effect of improving the reliability and operability of AI / ML-based communication functions.

[0018] This disclosure satisfies the performance requirements of next-generation 6th generation (6G) mobile communication systems aiming for ultra-high speed, ultra-low latency, and large-scale connectivity, while enabling the evolution into an intelligent and autonomous network in which the network perceives its environment and optimizes its operation. This reduces unnecessary measurement, reporting, and signal exchange, and allows for more efficient management of wireless and network resources, thereby providing the effect of improving network operational efficiency and energy efficiency.

[0019] FIG. 1 is a drawing illustrating the structure of a wireless communication system to which the present embodiment can be applied.

[0020] FIG. 2 is a diagram illustrating the logical layer structure between a terminal (UE) and a base station (gNB) in a wireless communication system to which the present embodiment can be applied.

[0021] FIG. 3 is a diagram illustrating an exemplary NG-RAN structure to which the present embodiment can be applied.

[0022] FIG. 4 is a diagram illustrating the configuration of a terminal to which the present embodiment can be applied.

[0023] FIG. 5 is a diagram illustrating an AI / ML operation workflow according to one embodiment of the present disclosure.

[0024] FIG. 6 is a diagram illustrating the data collection and reporting procedure of an AI / ML model to which embodiments of the present disclosure can be applied.

[0025] FIG. 7 is a diagram illustrating the classification according to the form in which an AI / ML model to which embodiments of the present disclosure can be applied is configured.

[0026] FIG. 8 is a diagram illustrating a terminal-network collaboration level using an AI / ML model to which embodiments of the present disclosure can be applied.

[0027] FIG. 9 is a diagram illustrating the location estimation operation of a terminal according to one embodiment.

[0028] FIG. 10 is a signal diagram conveying terminal positioning-related information using AI / ML according to one embodiment.

[0029] FIG. 11 is a signal diagram conveying terminal positioning-related information using AI / ML according to another embodiment.

[0030] FIG. 12 is a diagram for explaining the operation of a base station according to one embodiment.

[0031] FIG. 13 is a diagram illustrating the operation of a position management device according to one embodiment.

[0032] FIG. 14 is a diagram illustrating the configuration of a base station according to one embodiment.

[0033] FIG. 15 is a drawing for explaining the configuration of a position management device according to one embodiment.

[0034] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0035] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0036] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0037] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0038] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0039] A wireless communication system in this specification refers to a system for providing various communication services, such as voice and data packets, using wireless resources, and may include a terminal, a base station, or a core network.

[0040] Meanwhile, the term "terminal" in this specification is a comprehensive concept meaning a device including a wireless communication module that communicates with a base station in a wireless communication system, and should be interpreted as a concept that includes not only User Equipment (UE) in WCDMA, LTE, NR, HSPA and IMT-2020 / IMT-2030 (5G, New Radio, and 6G), and wired / wireless communication sensing systems that interact with specific communication systems, but also Mobile Station (MS), User Terminal (UT), Subscriber Station (SS), wireless device, and sensing module / device in GSM. In this specification, the term "terminal" is a comprehensive concept meaning a device including a wireless communication module that communicates with a base station in a wireless communication system. It should be interpreted as a concept that includes not only User Equipment (UE) in WCDMA, LTE, NR, HSPA, and IMT-2020 / IMT-2030 (5G, New Radio, and 6G), and wired / wireless communication sensing systems that interact with specific communication systems, but also Mobile Station (MS), User Terminal (UT), Subscriber Station (SS), wireless device, sensing module / device, etc. in GSM. Furthermore, depending on the usage type, the terminal may be a user portable device such as a smartphone, and in a V2X communication system, it may refer to a device including the vehicle itself or a wireless communication module within the vehicle. Furthermore, in the case of a Machine Type Communication (MTC) system, it can be interpreted as a concept that includes not only MTC terminals, M2M terminals, URLLC terminals, and V2X terminals equipped with communication modules to perform machine type communication, but also sensor network terminals, IoT devices, wearable devices, etc.As such, “terminal” may refer to another node that transmits and receives data / signals with a specific communication node.

[0041] In this specification, the term "base station" is a comprehensive concept referring to a network device that performs wireless communication with a terminal in a wireless communication system. It should be interpreted to include eNBs (evolved Node Bs) in 3GPP LTE systems, gNBs (gNode Bs) in NR (New Radio) systems, and next-generation base stations in IMT-2020 / IMT-2030 (5G and 6G) ​​systems, as well as Node Bs in WCDMA systems, BTSs (Base Transceiver Stations) in GSM systems, APs (Access Points) in Wi-Fi systems, and RSUs (Road Side Units) in V2X communication systems. Furthermore, base stations can be implemented in various forms, including not only a centralized architecture but also distributed Small Cell units, Repeaters, Relay Nodes, Satellite Gateways, and Intelligent Reflective Surface (RIS) controllers, and all such variations should be interpreted as being included in the term "base station" in this specification. As such, "base station" may refer to another communication node that transmits and receives data / signals with another node in a specific communication system. In this specification, the term "Cell" should be interpreted as a comprehensive concept referring to a logical / physical area in a wireless communication system where a terminal receives wireless services from a base station. In LTE systems, the coverage provided by the base station (eNB) may include not only physical cells, but also multiple cell concepts (e.g., SCell, PCell, BWP-based virtual cell, etc.) based on frequency resources, beams, slot structures, etc., in 5G NR systems. Furthermore, as beam-based communication structures are emphasized along with FR2 / FR3 and terahertz (THz) band expansion, beam-based coverage may be included as the basic unit of a cell.Furthermore, in a Non-Terrestrial Network (NTN) environment, as the beam footprint of an orbiting satellite changes over time, there is a characteristic where the boundaries of cells are not fixed but change dynamically, and this can be defined and included as a cell. Additionally, it may include cell expansion based on Intelligent Reflective Surfaces (RIS), dynamic cell structures considering Integrated Sensing and Communication (ISAC), and cells based on virtualized network slices. This may include a structure in which a terminal connects to multiple cells simultaneously or selectively according to physical / logical resource units. Therefore, the present specification should be interpreted as a concept that includes not only base station-based coverage but also beam-unit logical cells, NTN-based dynamic cells, and new types of cells formed based on RIS or virtualization.

[0042]

[0043] The present disclosure describes an NR system as an example, but it will be obvious that the present disclosure can be applied to and used in the relevant functions of a 6G mobile communication network, and that the limitations of the present disclosure are not restricted by the said NR system. This specifies that while NR (New Radio) is used as a specific embodiment, the technical concept of the present disclosure can be modified or expanded and applied to future systems such as 6G and the newly defined Beyond_G, and is characterized by not being limited to a specific system (NR). Accordingly, the technical scope of the invention is not limited to an NR system and is characterized by being implementable in various wireless systems including 6G.

[0044] The 6G communication to which the present disclosure applies is a next-generation wireless communication technology following 5G, and standardization is currently underway with the goal of commercialization around 2030. Beyond simple speed improvements, 6G aims for artificial intelligence, hyper-spatial scalability, and reality-digital convergence, and is being prepared as a core infrastructure for the future digital society. This 6G communication aims to support the next-generation digital society by organically combining core technologies such as THz communication capable of ultra-broadband transmission, AI-Native networks integrating AI / ML across all network layers, RIS (Reconfigurable Intelligent Surface) technology that actively reflects / manipulates radio waves, NTN (Non-Terrestrial Network) providing 3D coverage such as satellites, Joint Communication & Sensing (JCAS) integrating communication and sensing functions, ultra-precise location estimation, and Quantum Key Distribution (QKD) for security.

[0045] The structure of these 6G communication networks is being discussed based on the following directions and characteristics. First, as an End-to-End Intelligent Autonomous Network (AI-Native Architecture) structure, AI / ML is fundamentally embedded across all network layers to perform data-driven policy optimization, autonomous network operation, anomaly detection, and Quality of Service (QoS / QoE) assurance; it is expected that AI functions will operate in a distributed manner across the RAN, Core, and service management. Second, by adopting a 3D scalability architecture, it supports a Non-Terrestrial Network (NTN) that integrates the terrestrial network (RAN), satellite, and High Altitude Platform (HAPS); to this end, an integrated cell structure and IAB-based backhaul / fronthaul design are planned to be supported. Third, the Service-Based Architecture (SBA) introduced in 5G will be advanced to strengthen the modularization of Network Functions (NF), and flexible API-based service creation will be enabled through NEF, NWDAF, PCF, etc. Fourth, through a distributed intelligence structure, we plan to move away from a centralized architecture and perform real-time AI-based decisions at edge nodes such as RAN, MEC, and UE, thereby supporting local decision-making in smart transportation, factories, and medical sites. Fifth, by introducing a structure that integrates communication and sensing (Joint Communication & Sensing), we will enable the RAN to perform environmental sensing functions beyond simple communication capabilities; to this end, structures for processing sensing features and asynchronous data collection will also be designed. Finally, through a digital twin-based virtualization structure, we will replicate the physical network state in real time and enable predictive autonomous operation and network simulation, thereby supporting the intelligence and efficiency of the entire network.The next-generation wireless system to which this disclosure applies includes support for both frequency bands below 6 GHz (FR1, Frequency Range 1) and frequency bands above 6 GHz (FR2, Frequency Range 2), and specifically defines support for FR3 (Frequency Range 3) between FR1 and FR2, and proposes various support technologies related to end-to-end interoperability and data connectivity for the FR3 band (7.125-24.25 GHz).

[0046] For example, NR has defined various operation scenarios by adding considerations for satellites, automobiles, and new verticals, and in terms of service, it supports eMBB (Enhanced Mobile Broadband) scenarios, mMTC (Massive Machine Communication) scenarios that require low data rates and asynchronous connections while having high terminal density and being deployed over a wide range, and URLLC (Ultra Reliability and Low Latency) scenarios that require high responsiveness and reliability and can support high-speed mobility.

[0047] To satisfy these scenarios, NR introduces a wireless communication system equipped with new waveform and frame structure technologies, low latency technologies, mmWave support technologies, and forward compatibility technologies. In particular, NR systems present various technical changes in terms of flexibility to provide forward compatibility.

[0048] Although the following description focuses on NR, it can also be applied to next-generation wireless communication systems (e.g., 6G, etc.) as described above. Additionally, while the aforementioned terms may be used as different terms in next-generation wireless communication systems, the device providing the same function may be the device described in this specification.

[0049] FIG. 1 is a drawing illustrating the structure of a wireless communication system to which the present embodiment can be applied.

[0050] Referring to FIG. 1, a wireless communication system may be composed of a core network unit (120), a base station (110), and terminals (100, 101). In addition, the wireless communication system may include additional nodes such as a Radio Unit (RU). From the perspective of terminal expansion, the wireless communication system may further include vehicles (102, 103), aerial mobile bodies (104), etc. From the perspective of base station expansion (110), the wireless communication system may further include satellites (111), etc.

[0051] The base station (110) can provide user plane and control plane protocol termination to the terminal (100). For example, the base station (110) may be named gNB (next generation-Node B) and / or eNB (evolved-Node B), and may be referred to by other terms in next-generation wireless communication systems. For example, the terminal (100) may be fixed or mobile and may be referred to by other terms such as MS (Mobile Station), UT (User Terminal), SS (Subscriber Station), MT (Mobile Terminal), or Wireless Device. For example, the base station (110) may be a fixed station communicating with the terminal (100) and may be referred to by other terms such as BTS (Base Transceiver System) or Access Point.

[0052] Base stations (110) can be connected to each other via protocol interfaces. For example, base stations (110) can be connected to each other via Xn interfaces. Additionally, base stations (110) can be connected to core network entities (120) via protocol interfaces. For example, base stations (110) can be connected to core network entities (120) via NG interfaces. More specifically, base stations (110) can be connected to an access and mobility management function (AMF) (120) via an NG-C interface and to a user plane function (UPF) (120) via an NG-U interface. The AMF is responsible for control planes such as terminal access and mobility control functions, and the UPF is responsible for control functions for user data.

[0053] The satellite (111) can provide communication services to a terminal through a ground antenna or gateway as a core network entity. The satellite (111) may provide communication services while orbiting the Earth or may provide communication services while fixed in orbit on the Earth. The satellite (111) may be configured to transparently transmit messages provided by a ground gateway or base station (110). Alternatively, the satellite (111) may be equipped with some or all of the functions of a base station (110) to perform the function of a base station for the core network entity (120) and the terminal.

[0054] Meanwhile, the terminal (100) can perform direct communication with other terminals (101) without passing through the base station (110) through terminal-to-terminal communication technology. For example, direct communication between terminals can be described as D2D or V2X technology, but is not limited to such terms. For example, vehicles (102, 103) can use terminal-to-terminal communication technology as vehicle-to-vehicle communication technology, and communication can also be performed between the vehicle (103) and the terminal (100). Of course, communication can also be performed between the vehicle (102) and the base station (110). Similarly, a communication link can be established between the aerial mobile body (104) and the base station (110) to perform communication, and communication can also be performed between the aerial mobile body (104) and the vehicle (102, 103) or the terminal (100, 101).

[0055] In NR, CP-OFDM waveforms using a cyclic prefix are used for downlink transmission, while CP-OFDM or DFT-s-OFDM are used for uplink transmission. OFDM technology is easy to combine with MIMO (Multiple Input Multiple Output) and has the advantage of enabling the use of low-complexity receivers along with high frequency efficiency. For next-generation wireless communication systems, various waveforms and modulation technologies may be applied.

[0056] FIG. 2 is a diagram illustrating the logical layer structure between a terminal (UE) and a base station (gNB) in a wireless communication system to which the present embodiment can be applied.

[0057] Referring to FIG. 2, data transmission between a terminal and a base station in a wireless communication system is performed through a multilayer protocol structure. Generally, NR and NG-RAN structures are configured to include at least one of a Service Data Adaptation Protocol (SDAP), a Packet Data Collection Protocol (PDCP), Radio Link Control (RLC), Media Access Control (MAC), and a Physical Layer (PHY).

[0058] In the User Plane, the SDAP layer maps QoS flows defined in the 5G core (5GC) to the Data Radio Bearer (DRB), and the PDCP layer performs encryption, integrity protection, header compression, packet reordering, and deduplication functions. The RLC layer provides splitting and combining, retransmission, and reordering functions, while the MAC layer handles radio resource scheduling, multiplexing, and HARQ. The PHY layer performs modulation, encoding, channel estimation, and beamforming.

[0059] In the control plane, the RRC layer is responsible for wireless bearer setup, measurement and handover procedures, and security parameter exchange, and works in conjunction with the upper layer, NAS, to perform terminal authentication and session management.

[0060] The functions and operations of each layer described above are exemplary, and the functions of a specific layer may be separated and performed by other layers. For instance, the splitting and combining functions of the RLC layer may be performed by PDCP, and the retransmission and reordering functions may be absorbed into similar functions in the MAC or PHY layers, thereby eliminating the RLC layer.

[0061] The embodiments in this specification may be applied to the aforementioned logical layer structure and may also be applied to various logical layer structures that are modified in the future.

[0062] FIG. 3 is a diagram illustrating an exemplary NG-RAN structure to which the present embodiment can be applied.

[0063] Referring to FIG. 3, in the NG-RAN structure, base station (110) functions can be separated into a central unit (CU) and a distributed unit (DU). The CU is responsible for the control plane (RRC / PDCP-C) and the user plane (SDAP / PDCP-U), while the DU is responsible for the RLC / MAC / PHY layer. The interface between the CU and the DU is defined as F1-C and F1-U, and within the CU, an E1 interface is defined between the control plane and the user plane. This allows for support of both distributed and centralized architectures.

[0064] Additionally, the connection between base stations is performed by the CU through the Xn interface, and the base station (110) is connected to the core network entity (120) through the NG interface. Meanwhile, in a 6th generation (6G) wireless communication system, the above logic layer structure can be extended for AI / ML-based network optimization, FR3 and THz band expansion, non-terrestrial network (NTN) support, RIS (Reconfigurable Intelligent Surfaces)-based dynamic channel control, and ISAC (Integrated Sensing and Communication)-based integrated service provision. For example, the RRC and MAC layers may include new control signals for low-power mode and energy efficiency, and the SDAP / PDCP layer may simultaneously perform QoS processing and sensing quality assurance. Additionally, in an NTN environment, RLC / MAC procedures may be added to assist time / frequency synchronization, and new RRC information elements for RIS control may be defined.

[0065] As described above, the communication system to which this disclosure applies inherits the 5G-Advanced infrastructure for interoperability with 6G or next-generation communication systems, but may evolve in a form where each layer of the newly defined next-generation communication system interacts to expand or converges. Alternatively, the communication system to which this disclosure applies may include a separate Radio Access Network (RAN) and Core Network structure distinct from the 4G and 5G wireless communication structures. This disclosure is not limited to the network architecture of the existing generation and may be applied based on a next-generation network structure in which AI / ML native-based functions are essentially integrated into communication procedures and network control. Accordingly, each embodiment described in this disclosure is not limited to a specific generation of mobile communication systems and is characterized by being adaptively applicable not only to currently commercialized 4G and 5G mobile communication systems but also to 6G mobile communication systems that are currently under discussion and standardization or are scheduled for the future.

[0066] For example, the present disclosure may apply to AI-Native RAN interconnection operations. The AI-Native RAN may be configured to extend beyond the control layer within the Radio Access Network (RAN) to the Radio Resource Control (RRC), the orchestration of the Central Unit (CU) and the Distributed Unit (DU), and further to the Policy Control Function (PCF) of the core network. In this case, AI / ML models and policies may be arranged hierarchically according to the control target and time sensitivity; for example, real-time control centered on the MAC / PHY layer may be performed in the DU, and near-real-time control related to RRM, handover, and measurement policies may be performed in the CU-CP. Additionally, policy control related to slice control and QoS governance on a minute to hourly basis may be performed in the core network and PCF.

[0067] Higher-level policies can be propagated throughout the network from the PCF via the AMF and SMF paths, and these policies can be converted into model-derived parameters that are reflected in procedures such as measurement, handover, DRX, and cell reselection through the extension of RRC Information Elements (IEs), and then transmitted to terminals and base stations. Through this, terminals and base stations can adaptively adjust their behavior based on network policies and the inference results of AI / ML models.

[0068] In addition, in the present disclosure, network metrics generated at various layers can be systematically collected and utilized for AI / ML learning and inference. For example, retransmission and packet drop delay information can be collected at the PDCP layer, and buffer occupancy status and retransmission-related metrics can be collected at the RLC layer. At the MAC / PHY layer, beam quality information based on CQI, CSI, BLER, HARQ, PHR, SRS, and CSI-RS can be utilized, and at the RRC, NGAP, and XnAP layers, metrics related to measurement events, handover failures, delays, and jitter can be collected.

[0069] As another example, the frequency band used in the communication system to which the present disclosure applies may be extended beyond the existing FR1 and FR2 to the FR3 band. The FR3 band may consist of an ultra-high frequency band approaching or including terahertz (THz), in which case the complexity of beam configuration and wireless resource management may increase significantly. In particular, in a THz environment, link stability may fluctuate very rapidly due to high path loss, increased sensitivity to shielding, and amplification of the Doppler effect.

[0070] In such an environment, beam tracking operations performed at the MAC / PHY layer and policy control performed at the RRC and SDAP layers need to be closely coupled. For example, the AI ​​according to the present disclosure can predictively preempt future valid beams by utilizing various features related to the terminal's operating state, mobility, and surrounding environment, thereby effectively mitigating control overhead by reducing the size of the beam sweeping period or the set of synchronized signal blocks (SSB).

[0071] In addition, radio resource decisions, such as the selection of slot or mini-slot structures, density settings for DMRS and CSI-RS, and whether to use auxiliary carriers, can be performed in conjunction with the QoS mapping policy of the SDAP layer. This allows for controlling latency-sensitive traffic and bandwidth-intensive traffic to be subject to different beam and carrier strategies, and consequently, enables the provision of stable communication performance that meets service requirements even in ultra-high frequency FR3 environments.

[0072] Furthermore, in this disclosure, slot or mini-slot-based transmission structures may be applied differentially depending on the service type. In particular, since Ultra-Reliable and Ultra-Low Latency Communication (URLLC), Extended Reality (XR) services, and traffic involving sensing and communication have different time sensitivities and transmission characteristics, a policy distinction regarding wireless resource allocation units is required. First, in the case of URLLC traffic, since short latency requirements and high reliability are simultaneously required, a mini-slot-based transmission structure may be applied preferentially in this disclosure. Mini-slots enable immediate transmission not restricted by slot boundaries, thereby supporting fast scheduling and HARQ operations even in situations requiring rapid changes in link quality or retransmission. Accordingly, the AI ​​can dynamically select mini-slot-based transmission for URLLC traffic by considering beam quality changes, Doppler characteristics, packet arrival intervals, etc., and reinforce link reliability by increasing DMRS and CSI-RS densities as needed. Meanwhile, XR traffic requires high bandwidth and continuous data transmission, but it has characteristics that allow for a certain level of latency tolerance. Accordingly, the present disclosure applies a slot-based transmission structure as the basis for XR traffic, but may partially parallel mini-slot transmission in sections where frame loss or degradation of user perceived quality is predicted. For example, AI can simultaneously secure spectrum efficiency and user perceived quality by combining slot-based high-capacity transmission and mini-slot-based complementary transmission based on user viewpoint movement, display frame requirements, and beam stability prediction results. Furthermore, in the case of traffic involving the linkage of sensing and communication, resource management is required considering the periodicity and accuracy requirements of the sensing signal, as well as the possibility of interference with communication traffic.In this disclosure, regular resource allocation in slot units is applied to sensing-related traffic to ensure sensing accuracy, while rapid beam switching or retransmission can be performed through mini-slot-based transmission when abrupt changes in the communication link are predicted based on the sensing results. This allows for improved adaptability to dynamic environmental changes while minimizing mutual interference between the sensing signal and the communication signal.

[0073] In this way, the present disclosure does not apply a fixed slot or mini-slot structure according to the characteristics of URLLC, XR, and sensing-linked traffic, but rather adaptively selects it based on AI / ML-based prediction and policy control, thereby efficiently supporting various service requirements within a single wireless interface structure.

[0074] As another example, in a dual network environment where non-terrestrial (NTN) and terrestrial networks coexist, simple connection procedures alone are insufficient to support stable communication and mobility due to the presence of satellite orbit characteristics, visibility variations, Doppler shifts, and path delay fluctuations. Accordingly, it is necessary to complement the measurement and handover procedures at the Radio Resource Control (RRC) layer by linking them with timing alignment and frequency synchronization mechanisms on the Distribution Unit (DU) side.

[0075] For example, by predicting and correcting timing advances and frequency offsets in advance based on satellite orbit information, ephemeris information, and terminal mobility models, it is possible to respond to rapid time and frequency fluctuations of the NTN link. In addition, by utilizing visibility prediction information between the terrestrial network and the NTN or between different NTNs, hand-over preparation or conditional handover can be performed before actual link quality degradation, thereby minimizing service interruption and improving mobility performance.

[0076] As another example, from an energy efficiency perspective, green RAN improves energy efficiency by maintaining traffic and SLAs while implementing DU sleep / wake, MIMO chain off, and DRX optimization. For instance, hierarchical coverage strategies can be employed, such as turning off small cells / auxiliary carriers and maintaining wide-area cell anchors during nighttime or low-load periods. To achieve this, RRC low-power profiles by service class, power state transition commands / telemetry (KPM) from CU to DU, and OAM collection of energy KPIs (cell power, RF chain uptime, cooling alarms) can be defined. To address increased handover failures or delays caused by excessive power saving, relevant policies and procedures regarding minimum resources and maximum wake-up delays per SLA can also be established.

[0077] As another example, the present disclosure may apply an Integrated Sensing and Communication (ISAC) coupled operation. In this case, physical layer (PHY) signals, such as a Position Reference Signal (PRS) or a Reference Signal (RS), may be utilized for sensing purposes as well as for communication purposes, and sensing performance may be treated as a key element of network quality management. For example, sensing-related performance indicators, such as sensing accuracy, sensing latency, and sensing information update cycle, may be considered as part of the Quality of Service (QoS) of communication.

[0078] Specifically, in the present disclosure, auxiliary indicators such as sensing-accuracy, sensing-latency, and sensing-update-rate may be included in the SDAP layer and 5QI scheme, and these sensing-related indicators may be reflected together in the objective function for policy optimization. Through this, the network can perform resource management and policy decisions to satisfy both sensing performance and communication performance simultaneously, rather than allocating resources based solely on communication performance.

[0079] Furthermore, at the RRC layer, the configuration of sensing-related PHY signals can be adaptively controlled according to service characteristics. For example, in cases requiring high sensing accuracy and reliability, such as industrial position estimation or sensing services, the RRC can adjust the pattern, density, and transmit power of the PRS or CSI-RS to meet the requirements of the service. This allows for improved sensing quality while minimizing unnecessary signal overhead.

[0080] Through such an ISAC linkage structure, the present disclosure goes beyond conventional structures where sensing and communication operate as separate functions, enabling more precise and intelligent network control by integrating sensing performance into network policy and QoS management.

[0081] FIG. 4 is a diagram illustrating the configuration of a terminal to which the present embodiment can be applied.

[0082] Referring to FIG. 4, the terminal (100) may be composed of various elements, components, units, and / or modules. For example, the terminal (100) may include a communication unit (300), a processor (310), and a memory (320). The communication unit (300) may include a communication circuit and transceiver(s). For example, the communication circuit may include circuit configurations such as a signal oscillator for transmitting or receiving a signal through an antenna. For example, the transceiver(s) may be composed of one or more and may include one or more antennas. The processor (310) is electrically connected to the communication unit (300) and the memory (320) and controls the overall operation of the terminal (100). For example, the processor (310) may control the electrical / mechanical operation of the terminal based on a program / code / command / information stored in the memory (320). Additionally, the processor (310) can transmit information stored in memory (320) to an external (e.g., another communication device or base station) via a wireless / wired interface through the communication unit (300), or store information received from an external (e.g., another communication device or base station) via a wireless / wired interface through the communication unit (300) in memory (320).

[0083] Additionally, the processor (310) can perform AI / ML-related data processing by loading program code into memory (320). Alternatively, the processor (310) may perform data analysis and processing operations using signals and / or data received through the communication unit (300).

[0084] As described above, the present disclosure enables the support of a standard performance monitoring structure required for an AI / ML-based wireless communication system at the terminal level. Accordingly, the terminal (100) can determine the performance status of an AI / ML model based on various measurement indicators and operation results of the PHY / MAC / RRC layer collected through the communication unit (300), and can store the determination result in memory (320) or report it to the network. Such performance monitoring results can be utilized for adjusting model parameters, changing inference policies, triggering retraining, or controlling the activation or deactivation of AI / ML functions. In particular, as the AI / ML model is involved in network core control loops such as wireless resource control, beam management, handover, and measurement settings, the inference accuracy of the model, stability degradation, and performance deterioration due to environmental changes can be monitored in real-time or near-real-time, and the relevant information can be transmitted and received.

[0085] In addition, the present disclosure is consistent with the flow of AI / ML-based positioning technology, and the terminal (100) can evaluate the inference accuracy, stability, and performance degradation of an AI / ML-based positioning model due to environmental changes by comprehensively considering the measurement results in the time, frequency, and spatial domains obtained through a positioning reference signal (PRS), a sounding reference signal (SRS), and related control procedures, as well as the results of performing network control operations such as beam management, handover, and measurement settings. The results of such judgment may be stored in the memory (320) of the terminal or reported to a location management device (LMF) or a base station.

[0086] In addition, the performance monitoring results according to the present disclosure can be used to adjust AI / ML model parameters, change inference policies, set retraining triggers, or control the activation or deactivation of AI / ML-based positioning functions, thereby enabling the network to continuously maintain and improve positioning performance.

[0087] In addition to this, the terminal (100) may include various additional elements. For example, the additional elements may be configured in various ways depending on the type of terminal. For example, the additional elements may include at least one of a power unit / battery, an input / output unit (I / O unit), a driving unit, and a computing unit. Although not limited thereto, the terminal (100) may be implemented in the form of a drone, robot, vehicle, XR device, portable device, home appliance, IoT device, digital broadcasting terminal, hologram device, public safety device, MTC device, medical device, fintech device (or financial device), security device, climate / environment device, AI server / device, sensor device, network node, etc. Depending on the use—e.g., service—the terminal (100) may be movable or used in a fixed location.

[0088] Meanwhile, various elements, components, units / parts, and / or modules within the terminal (100) may be entirely interconnected via a wired interface, or at least some of them may be wirelessly connected via a communication unit (300). For example, within the terminal (100), the processor (310) and the communication unit (300) may be wired, and the processor (310) and the memory (320) and / or additional elements may be wirelessly connected via the communication unit (300). Additionally, each element, component, unit / part, and / or module within the terminal (100) may include one or more additional elements. For example, the processor (310) may be composed of a set of a communication control processor, an application processor, an Electronic Control Unit (ECU), a graphics processing processor, a memory control processor, etc. As another example, memory (320) may be composed of RAM (Random Access Memory), DRAM (Dynamic RAM), ROM (Read Only Memory), flash memory, volatile memory, non-volatile memory and / or a combination thereof.

[0089] Wireless communication systems are in the process of adopting artificial intelligence technology to provide more effective and faster communication services. For example, advancements in AI / ML (Artificial intelligence / machine learning) technology are leading to the intelligentization and sophistication of node(s) and terminal(s) constituting wireless communication networks.

[0090] In particular, due to the intelligence of networks and base stations, it is expected that various network / base station decision parameter values ​​can be rapidly optimized, derived, and applied according to various environmental parameters. Environmental parameters may include at least one of the distribution / location of base stations, the distribution / location / material of buildings / furniture, the location / movement direction / speed of terminals, and climate information. However, the parameters described above are merely examples, and the environmental parameters may include other environmental parameters related to the network / base station decision parameters in addition to the parameters listed. Network / base station decision parameter values ​​may include at least one of the transmit / receive power of each base station, transmit power of each terminal, precoder / beam of the base station / terminal, time / frequency resource allocation for each terminal, and duplex method of each base station. However, the parameters described above are merely examples, and the network / base station decision parameter values ​​may include other parameters determined by the network / base station in addition to the parameters listed.

[0091] In a narrow sense, AI / ML can easily be referred to as artificial intelligence based on deep learning, but conceptually, it can be distinguished as follows.

[0092] - Artificial Intelligence: This refers to all automation where machines can take over tasks that humans would otherwise have to perform.

[0093] - Machine Learning: Machines learn patterns for decision-making from data on their own, without explicitly programming rules.

[0094] - Deep Learning: A model based on artificial neural networks that enables machines to perform everything from feature extraction to judgment from unstructured data in a single step. The algorithm relies on multi-layered networks composed of interconnected nodes for feature extraction and transformation, inspired by biological nervous systems, or neural networks. Common deep learning network architectures include Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), and Convolutional Neural Networks (CNN).

[0095] As mentioned above, artificial intelligence (AI) is the broadest concept of AI / ML, and deep learning is the narrowest concept of AI / ML. Machine learning (ML) can be interpreted as a concept that is narrower than artificial intelligence but broader than deep learning.

[0096] In this specification, AI / ML or artificial intelligence is a comprehensive concept that includes the aforementioned deep learning and does not limit specific models or specific learning / inference methods.

[0097] FIG. 5 is a diagram illustrating an AI / ML operation workflow according to one embodiment of the present disclosure.

[0098] Referring to Fig. 5, the AI / ML operations workflow highlights the key stages of the ML model lifecycle. The ML model lifecycle includes Training (510), Testing (520), Emulation (530), Deployment (540), and Inference (550).

[0099] ML Model Training (510): Includes initial training and retraining of an ML model (or family of models). It also includes validation to evaluate the performance of the model when performed on training and validation data. If the validation results fall short of expectations (e.g., variance exceeds the acceptable range), the model may be retrained. During the training phase, validation of the model's generalization performance, stability, and operability can be performed, and the results of such performance validation can be used as defined threshold values ​​in the subsequent operation phase.

[0100] ML Model Testing (Testing, 520): A validated ML model is tested to evaluate the performance of the ML model trained on test data. If the test results meet expectations, the next step can be performed. If the test results do not meet expectations, the model can be retrained. This can be defined as the concept of pre-deployment validation of AI / ML capabilities and can also function as a standard safeguard to prevent the deployment of models that may compromise network stability.

[0101] AI / ML Inference Emulation: Before applying to a target network or system, the model is run in an emulation environment to evaluate inference performance. If the emulation results fall short of expectations (e.g., failure to meet target inference performance, negative impact on the performance of existing features), the model must be retrained. AI / ML inference emulation is optional and can be omitted from the ML model lifecycle.

[0102] ML Model Deployment: Includes a model loading procedure that makes the trained model available for use in the target AI / ML inference function. Deployment may not be necessary in cases where the training function and the inference function are co-located in the same location, etc. The model deployment may include a model identifier, version information, scope, activation conditions, etc., and the present disclosure may manage such deployment metadata in conjunction with the performance monitoring and inference steps.

[0103] AI / ML Inference: The AI / ML inference function performs inference using a trained model. It may also trigger retraining or model updates based on performance monitoring and evaluation. Here, run-time performance monitoring or closed-loop monitoring of the AI / ML model is considered an essential function for detecting model degradation over time or due to environmental changes and for taking appropriate countermeasures; control over the aforementioned time and environment can be variably configured considering the service, stability, and reliability.

[0104] Depending on the system implementation method and the configuration of AI / ML functions, both the AI / ML inference emulation step and the ML model deployment step may be omitted. Meanwhile, since model performance may degrade over time or due to changes in the wireless environment or traffic characteristics, retraining and model update procedures based on model performance feedback may be performed periodically or on an event basis. As such, when AI / ML models are applied in a communication system, training, storage, deployment, inference, performance monitoring, and retraining can be adaptively applied and operated, taking into account the reliability, stability, and operability of the AI / ML-based network.

[0105] Furthermore, AI / ML inference may further include a configuration that performs location estimation or location-related decision-making using a trained AI / ML model. Considering network-centric, for example, location management device (LMF)-led operation in an AI / ML-assisted positioning structure, the AI / ML inference function may be deployed at a base station or an LMF. In this case, the terminal supports the inference process by providing a positioning reference signal (PRS), a sounding reference signal (SRS), and measurement results from the PHY / MAC / RRC layer. Additionally, the LMF manages measurement requests, reporting parameters, and AI / ML model operation policies, controls physical layer measurements and signal structures through the L1 layer, and controls LPP / LPPa-based measurement reporting and control procedures through the L2 layer. Meanwhile, in AI / ML-based positioning, model performance may degrade over time due to changes in the wireless environment, terminal mobility, multiple TRP configurations, or frequency band changes; therefore, run-time performance monitoring or closed-loop monitoring functions may be essential. Such performance monitoring can be performed based on the error between inference results and actual measurement results, location estimation reliability indicators, or positioning failure events, and the results can be utilized as inputs to trigger retraining or model updates. Depending on the system implementation method, the inference emulation phase or the pre-model deployment phase may be omitted; however, if model performance degradation is detected, periodic or event-based retraining and model updates may be performed. Through this, the training, deployment, inference, and performance management of the AI / ML model can be operated adaptively, taking into account network reliability, communication stability, and service continuity.

[0106] FIG. 6 is a diagram illustrating a data collection and reporting procedure for an AI / ML model to which embodiments of the present disclosure can be applied.

[0107] Referring to FIG. 6, 610 and 620 can each be nodes in a communication system. For example, 610 can be a base station and 620 can be a terminal. Conversely, 610 can be a terminal and 620 can be a base station. In addition, 610 can be a first base station and 620 can be a second base station. That is, a data request procedure between base stations can be performed. Similarly, 610 can be a first terminal and 620 can be a second terminal.

[0108] The exchange of Data Collection Request, Data Collection Failure, and Data Collection Update messages between the first node (610) and the second node (620) is described as an example. The first node (610) can send a message requesting data collection to the second node (620) for training, inference, management, and updating of an artificial intelligence model (S601). The message requesting data collection may vary depending on the subject of each node. For example, the message requesting data collection may be transmitted through the Xn interface, NG interface, or Uu interface. The message requesting data collection may be an upper-layer message or a lower-layer message. S601 is a procedure in which the first node (610) requests specific operational data, performance indicators, or measurement data from the second node (620). At this time, the data may be used for integration with the Self-Organizing Network (SON), Network Data Analytics Function (NWDAF), or OAM. Through this, it is possible to link with OAM / MDT (Minimization of Drive Test) data collection or E2E performance analysis.

[0109] The second node (620) determines whether the requested data can be collected. For example, if the 620 does not possess the requested data or if collection is difficult, the second node (620) sends a data collection failure message to the first node (610) (S602). For example, the data collection failure (S502) procedure may return a failure response when the requested data does not exist or when the node cannot provide it due to a lack of authority or resources. This corresponds to an error handling procedure and can be transmitted as a failure cause IE (Information Element) specified in the standardization. For example, it may include unsupported parameter, resource not available, etc. As described above, the data collection failure message may also be configured with various interfaces and message formats depending on the subject of each node. The data collection failure message may include information on the cause of the data collection failure. Alternatively, information reported through updates may include predicted resource status information, terminal performance feedback information, measured terminal path, energy cost, etc.

[0110] If the second node (620) succeeds in collecting the requested data, it may send a data collection update message to the first node (610) (S603). For example, the data collection update (S503) procedure may subsequently send an update message to the first node (610) when the situation improves or when some data becomes available. This includes sending via asynchronous reporting or periodic / conditional update methods. Examples may include RAN performance counters, QoE measurements, QoS Flow utilization, location / traffic patterns, etc. The data collection update message may include data information collected regarding the requested data. In the case of previously transmitted data, it may be included in the data collection update message by indicating an update.

[0111] Through this process, data collection and transmission between each node can be performed.

[0112] As explained above, the artificial intelligence model can be configured in the terminal and / or base station.

[0113] In particular, a data collection framework centered on linkage with NWDAF (Network Data Analytics Function), SON (Self-Organizing Network), OAM (Operation, Administration and Maintenance), and MDT (Minimization of Drive Test) is being discussed as a function to systematically collect operational data, performance indicators, and measurement results generated from RAN, Core, and terminals for use in AI / ML learning and inference. Accordingly, the data collection request, failure reporting, and data collection update procedures between the first node (610) and the second node (620) described in FIG. 6 can directly correspond to the analysis and management functions defined in 3GPP standards. For example, the procedure in which the first node requests data collection from the second node as the entity operating the network analysis or AI / ML model aligns with the standard mechanism for NWDAF or RAN intelligence functions to collect input data from terminals or base stations. At this time, the data subject to collection can be expanded to include RAN performance counters, QoS Flow statistics, QoE measurement results, location and mobility information, traffic patterns, and energy consumption indicators, which can be utilized for training, inference, and performance monitoring of AI / ML models. Additionally, the failure cause information included in data collection failure messages can be used for evaluating the reliability of input data, analyzing the causes of model performance degradation, or selecting alternative data sources in terms of AI / ML model operation.In addition, the data collection update procedure can be performed using asynchronous reporting, periodic reporting, or event-triggered reporting methods. For example, data collection updates can be triggered when a specific threshold is exceeded, performance degradation is detected, or environmental changes occur, allowing AI / ML models to update inference results or policy decisions by reflecting the latest network status.

[0114] FIG. 7 is a diagram illustrating a classification according to the configuration of an AI / ML model to which embodiments of the present disclosure can be applied. FIG. 7 performs wireless resource management and beam management optimization using an artificial intelligence / machine learning (AI / ML) model.

[0115] First, (a) in the case of a network-sided AI / ML model, an AI / ML model located at a base station (710) performs resource optimization operations such as scheduling, beam selection, and interference management based on channel state information, measurements, performance indicators, etc. collected from a terminal (700).

[0116] Next, (b) in the case of a terminal-side AI / ML model (UE-sided AI / ML Model), the AI / ML model located at the terminal (700) performs beam prediction, performance estimation, and movement pattern analysis on its own and reports the results to the base station (710), thereby improving the accuracy of network control.

[0117] Finally, (c) in the case of a two-sided AI / ML model, the base station (710) and the terminal (700) each perform AI / ML inference, and the utilization of network resources is maximized by mutually exchanging inference results, performance indicators, and confidence level information.

[0118] Accordingly, the present embodiments perform wireless resource optimization operations in a network-only, terminal-only, or network-terminal collaborative structure depending on the deployment location of the AI / ML model, thereby providing the effect of enabling the implementation of ultra-high-speed, ultra-low-latency, and intelligent services for next-generation wireless communication systems.

[0119] Referring again to FIG. 6, the artificial intelligence model may be configured in only one of the terminal (700) or the base station (710). This can be described as a one-side AI / ML model. Alternatively, the artificial intelligence model may be configured in both the terminal (700) and the base station (710). This can be described as a two-side AI / ML model.

[0120] In the form of a one-side AI / ML model, an artificial intelligence model is configured at a base station (710), and a terminal (700) transmits information necessary for model input to the base station (710) via a wireless interface. The base station (710) can generate inference results by providing the received information as input to the model. Through this, the base station (710) can directly utilize the model to perform beam management, terminal mobility management, etc. This is called a NW-side AI / ML model.

[0121] In another form of the one-side AI / ML model, an artificial intelligence model is configured in the terminal (700), and the base station (710) transmits information necessary for model input to the terminal (700) through a wireless interface. For example, a reference signal can be transmitted through the base station (710) beam, or a reference signal for channel measurement can be transmitted. In this case, the base station (710) can transmit the signal that was previously transmitted. The terminal (700) can generate an inference result by providing the received information as input to the model. The terminal (700) transmits the generated inference result to the base station (710). Through this, the terminal (700) performs inference using the model and transmits the inference result to the base station (710) to assist with beam management of the base station (710), mobility management of the terminal, etc. This is called a UE-side AI / ML model.

[0122] In the case of a two-sided AI / ML model, a model may be configured at the terminal (700) and the base station (710), respectively. In this case, the terminal (700) and the base station (710) can input mutually received data into the model to derive an inference result. The terminal (700) can transmit the inference result to the base station (710). The base station (710) can control the operation of the terminal using the inference result received from the terminal (700) and the inference result of the base station (710). The models configured at the terminal (700) and the base station (710) may each be configured with different purposes or functions.

[0123] As such, AI / ML capabilities vary depending on specific use cases and sub-use cases, and may focus on the interaction between the network and the terminal.

[0124] FIG. 8 is a diagram illustrating a terminal-network collaboration level using an AI / ML model to which embodiments of the present disclosure can be applied.

[0125] Referring to FIG. 8, the collaboration levels between the base station (810) and the terminal (800) can be defined as follows.

[0126] 1. Level X (or Collaboration Level 0) is characterized by a method in which the terminal (800) and the base station (810) each independently operate AI / ML models, and the network-side (NW-side) AI model and the terminal-side (UE-side) AI model perform only self-optimization without standardized signaling. For example, the base station (810) uses its own beam management model, and the terminal (800) uses its own power optimization model. That is, the base station (810) and the terminal (800) each independently operate their own AI / ML models, and both sides operate through AI / ML logic implemented within their own or the device without standardized signaling or model sharing. For example, beam management, scheduling, and power control of the base station can be performed using their own AI models, and operations such as power consumption optimization based on the terminal's movement pattern, antenna selection, and local beam prediction can be performed independently. In this Level X, unpredictable operations may occur between them due to the opacity of the AI ​​operations.

[0127] 2. Level Y (Collaboration Level 1) allows the terminal (UE, 800) and the base station (810) to perform the step of exchanging signals with each other to assist in the inference and operation of an AI model. Specifically, the terminal (800) reports the inference results or performance indicators (e.g., Top-K beam prediction accuracy, confidence level, etc.) of the AI / ML model it has performed itself to the base station (810). After receiving the reported information, the base station (810) performs network optimization decisions, such as resource management, beam management, and scheduling, based on this information. In particular, as part of the AI / ML model performance monitoring and auxiliary signaling procedures, signaling definitions such as RRC information elements (RRC IE) or MAC control elements (MAC CE) are required. Therefore, compared to the case where the terminal (800) and the base station (810) operate the AI ​​model independently according to the present disclosure, this provides a technical advantage of being able to efficiently manage signaling overhead while improving mutual collaboration performance. The present disclosure includes the ability for a terminal to report “inference output” or “auxiliary information (e.g., Top-K candidate beams, confidence / probability, etc.)” to be utilized for network beam management / resource determination, and may also include the ability to apply UE-side inference in a collaborative form that combines it with network procedures. Additionally, for the operation of AI / ML functions, the network may instruct the UE regarding the activation / deactivation, fallback, switching, etc., of AI / ML functions through RRC, MAC-CE, and DCI signaling, and in this case, the concept of lifecycle management (LCM) may be considered.

[0128] 3. Level Z (Collaboration Level 2) allows the base station (810) and the terminal (UE, 800) to directly exchange the AI ​​model itself or learned parameters. Specifically, the base station (810) can download the AI ​​model learned on the network side to the terminal (800) to enhance the inference function at the terminal, while conversely, the terminal (800) can upload parameters learned independently or model update information to the base station (810) to enhance the central management function of the network. To this end, procedures for distributing and updating the AI ​​model can be performed, and include defining dedicated signaling procedures for model transmission, security / integrity guarantees, and transmission efficiency optimization techniques. For example, RRC protocol extensions, new MAC CE definitions, or interoperability structures with NWDAF / AF can be considered. Accordingly, according to the present disclosure, the base station (810) and the terminal (800) raise the level of cooperation to the highest level (full collaboration), providing the advantage that the network and the terminal can perform resource management and service optimization based on the same AI model. This can be applied adaptively while simultaneously considering issues such as increased signaling overhead and standardization complexity. The base station (810) and the terminal (800) can deliver / transfer an AI / ML model (or model parameters) via RRC signaling, which may include the transmission of a model identifier (model ID) and metadata (version / coverage / validity period, etc.). Here, the exchange of models / parameters can be applied adaptively according to the service / situation by considering not only transmission overhead but also integrity and security (e.g., prevention of model tampering, secure download / update) and storage / cache policies (e.g., whether the UE can store the model). That is, Level Z can be applied adaptively by considering standardization complexity.

[0129] More specifically, Collaboration Level 0 involves the terminal operating through its own AI / ML model or performing only RRC / RRM procedures without AI functions, and includes operations where the base station does not separately configure or intervene with the AI ​​model for the terminal. In other words, it is characterized by the absence of AI / ML-related interaction between the base station and the terminal. Meanwhile, Collaboration Level 1 is characterized by the fact that while the model itself is not transmitted, configuration / signaling information to support AI / ML functions is exchanged between the base station and the terminal. For example, the terminal receives configuration information (e.g., reference signal configuration, evaluation conditions, reporting cycle, etc.) for using the AI / ML model from the base station. Considering this, the terminal reports only the results of AI inference or measurement results, while the model itself exists independently within the terminal. That is, the terminal can report the results of local AI model execution used for CSI enhancement, beam management, mobility enhancement, etc., to the base station. In addition, Collaboration Level 2 enables the base station to transmit the AI / ML model itself or some parameter / configuration information to the terminal, and the terminal to perform AI functions based on the model (e.g., inference module, weight, etc.) received from the base station, or to feed back the model results learned by the terminal to the base station, or to support bidirectional model updates. This can be referred to as collaborative inference and federated learning-like operations. To this end, the terminal and the base station can transmit and receive model-related signaling, such as the configuration, parameters, and training cycle of the AI ​​model. The technology described herein may be applied to at least one of the three collaboration levels mentioned above.

[0130] Meanwhile, when a model is configured on a terminal, various methods may be applied to deliver the model to the terminal.

[0131] For example, the model can be trained on a terminal, a base station, or a separate device. The trained model can be stored on a server via model transfer / delivery. The model stored on the server can be delivered to the terminal as needed and configured on the terminal.

[0132] As another example, the model may be trained on a terminal or a separate device. The trained model is transmitted to a base station through a model delivery procedure and stored at the base station. The base station can then transmit the model to the terminal as needed for configuration on the terminal.

[0133] As another example, a model can be trained at a base station. The trained model is stored at the base station. The base station storing the model may be the same as or different from the base station that performed the training. The base station storing the model can then transmit the model to a terminal as needed to configure the model on the terminal.

[0134] Meanwhile, AI / ML models can be applied to various usage scenarios.

[0135] For example, it can be used for the purpose of saving network energy. For instance, to balance performance and energy savings, it is necessary to optimize cell activation or deactivation decisions based on predicted traffic loads by utilizing AI / ML technology. To this end, internal base station information such as current and predicted resource status, UE path prediction, currently predicted UE traffic, and predicted resource status of adjacent RAN nodes can be used as inputs to the model. Additionally, terminal-related information such as UE location data, UE measurement reports, and cell-level and beam-level UE measurement reports can be used as inputs. Furthermore, neighbor network information such as currently predicted energy efficiency, currently predicted resource status, and current energy status can be used as inputs. The model's output can infer energy saving strategies (recommended cell activation / deactivation), handover strategies, recommended candidate cells to take over traffic, predicted energy efficiency, and predicted energy status information. Feedback considers the resource status of adjacent RAN nodes, energy efficiency, UE performance affected by energy saving measures, and system KPIs.

[0136] As another example, AI / ML technology may be used for load balancing purposes. For instance, this functionality can be applied to enhance the quality of user experience and improve system capacity by improving load balancing performance through AI / ML model-based solutions and predicted loads, based on various metrics, feedback collected from UEs and network nodes, and historical data. To this end, the model's inputs may include base station information such as UE mobility path predictions, currently predicted energy efficiency, and currently predicted resource status, as well as terminal information such as UE location data, UE movement history data, and cell-level and beam-level UE measurement reports. Additionally, neighbor network information may include terminal performance measurement data from adjacent cells to which traffic has been offloaded. The model's outputs may infer target cell selection for load balancing, predicted local resource status information, a resource status model of predicted adjacent RAN nodes, and predicted UE information selected for handover to the target RAN node. Feedback information may include UE performance data of the target NG RAN, updates to the target NG RAN's resource status information, and system KPIs.

[0137] As another example, AI / ML technology may be used from a mobility perspective. For instance, based on AI / ML, functions such as (1) reducing the probability of unintended mobility events (early / late handover, incorrect cell handover), (2) predicting UE location mobility performance, and (3) optimizing traffic steering can be performed. To this end, the input to the model may include base station information such as UE mobility path prediction, currently predicted energy efficiency, and currently predicted resource status, as well as terminal measurement information such as UE location information, UE movement history information, and wireless measurements of adjacent cells to the UE service cell. Additionally, neighbor base station information may include UE history information, the location of the handovered UE, QoS parameter performance information, and information on past UE handovers that were successful or failed in the currently predicted resource status. The output of the model may include UE path prediction, conditional handover-related prediction, UE traffic prediction, and the validity period of the model output.

[0138] In addition, AI / ML capabilities can be used to analyze metrics related to network and UE performance to perform optimal resource management and mobility decisions for network slicing, thereby ensuring the Quality of Service (QoS) of each slice and improving network efficiency. Alternatively, AI / ML capabilities can provide network performance improvements and maintain consistency in the UE experience by proactively detecting and responding to Coverage and Capacity Optimization issues.

[0139] In addition to these scenarios and usability, the operations described in this specification can be applied to various past, present, and future scenarios.

[0140] Below, we will explain several representative scenarios and their applications.

[0141] AI / ML models can be used to enhance CSI feedback. Based on channel state feedback information, CSI feedback enables base stations to accurately identify the user's wireless channel status, allowing for optimal wireless resource allocation and transmission. However, a disadvantage exists in that the feedback load required for accurate channel state information feedback increases significantly as the number of antennas and subbands increases. To address this, technology for delivering accurate channel state information at an appropriate feedback load is required.

[0142] CSI feedback is a critical procedure for adaptive communication technologies such as adaptive modulation, coding, and beamforming. Base stations utilize CSI feedback received from terminals to determine detailed downlink transmission methods, thereby improving overall network efficiency and system performance. However, periodically transmitting CSI feedback can cause system overhead and waste wireless resources, and pose a problem where it becomes difficult to manage as the number of users increases.

[0143] By utilizing AI / ML models to further enhance CSI feedback, it may be possible to provide benefits such as reduced overhead and improved accuracy.

[0144] FIG. 9 is a diagram illustrating the location estimation operation of a terminal according to one embodiment.

[0145] Referring to Fig. 9, the location estimation of a terminal can be classified into the OTDOA (Observed Time-Difference of Arrival) method and the UTDOA (Uplink Time-Difference of Arrival) method.

[0146] 901 represents the OTDOA method, and 905 represents the UTDOA method.

[0147] In the case of 901, it is assumed that at least three transmission nodes (910) are in tight time synchronization with each other, and the location of the target terminal (900) can be determined by measuring the time difference of downlink signals transmitted from each site based on such time synchronization. Here, the downlink signal may be a PRS (Positioning Reference Signal).

[0148] For example, the terminal (900) can receive PRS and generate and report RSTD (Reference Signal Time Difference) measurements. The location server (920) defines the signaling provided to the terminal regarding the resource settings for PRS transmission. A single positioning frequency layer constitutes one or more sets of PRS resources. A set of PRS resources includes PRS transmission resources transmitted from the same site. Of course, one or more sets of PRS transmission resources can be set at a single site. Each PRS resource usually corresponds to one beam from a single site. Therefore, setting the terminal to measure location positioning on a specific PRS resource within a set of PRS resources means that the location server (920) obtains information about the positioning quality of a specific beam at a certain site.

[0149] A PRS is transmitted using a single PRS resource, and the terminal receives the PRS from the base station TRP to measure the RSTD value. PRS sequence information can be allocated in the form of a staggered comb. Different frequency offsets may be applied to the PRS based on the OFDM symbol index within a single resource block. The comb factor can consist of 2, 4, 6, or 12 subcarriers, meaning that a PRS is allocated for a comb for every 2 to 12 subcarriers. In the time domain, 2, 4, 6, or 12 OFDM symbols constitute a single PRS resource.

[0150] In the case of 905, at least three transmission nodes (960) receive the uplink signal transmitted by the target terminal (950) and measure the time difference of the received uplink signals to determine the location of the target terminal (950). Here, the uplink signal may be an SRS.

[0151] This method can be applied to the uplink, and in addition to this traditional method, Angle-or-Arrival (AoA), Roundtrip Time (RTT), Cell Identity, and Received Power can be used as input values ​​for the positioning algorithm to obtain improved positioning quality.

[0152] Each transmission node (960) can estimate the location of the terminal by transmitting information about the uplink signal received from the terminal to the positioning server (970). The transmitted information may include not only RSTD but also various information such as the aforementioned AoA, RTT, cell identification information, RSRP, etc.

[0153] As described, PRS-based OTDOA and SRS-based UTDOA positioning procedures can be utilized as standard input data generation procedures for AI / ML inference in an AI / ML-assisted positioning structure. This can be applied to enhance the inference accuracy of position estimation algorithms by using multidimensional measurement indicators such as PRS / SRS measurement results and derived indicators like RSTD, AoA, RTT, Multi-RTT / Rx-Tx time difference, cell identification information (information corresponding to cell / frequency identification such as PCI, GCI, ARFCN (and PRS resource ID, etc.)), and received power as input when performing AI / ML-based positioning. Therefore, positioning performance can be improved in multipath environments, beamforming environments, or NLOS conditions while maintaining the OTDOA / UTDOA positioning framework.

[0154] Here, the DL RSTD (PRS-based) is a value generated by the UE by measuring the difference in arrival times of PRS received from multiple TRPs / TPs (Transmission / Reception Points), and includes a value that estimates the location by utilizing the time difference of the PRS signals received by the UE. DL-PRS-RSRP / DL-PRS-RSRPP is related to the received power (RSRP) measured by the UE after receiving DL-PRS from multiple TRPs, and in Multi-RTT positioning, the UE measures DL-PRS-RSRP and includes a value that verifies the RTT value and multipath characteristics based on it. UL-SRS-RSRP (Uplink Sounding Reference Signal RSRP) is a value containing the uplink reference signal transmitted by the UE and received by multiple TRPs, and is utilized for positioning performance related to UL-TDOA or Multi-RTT positioning. UE Rx-Tx time difference (Multi-RTT) is a method that derives the round-trip time (RTT) by combining the UE's Rx-Tx time difference measurement and TRP measurement. When the UE measures the Rx-Tx difference between DL-PRS and UL-SRS signals, the network can utilize the time difference between multiple TRPs to calculate a more accurate location even in dynamic environments. UL-AoA (A-AoA / Z-AoA) measures the direction in which the SRS transmitted by the UE reaches multiple TRPs, and can improve location estimation performance by utilizing angle of arrival information (A-AoA) and elevation angle (Z-AoA). Here, AoA information can be used as important spatial information when a positioning server (e.g., LMF) combines it with other measurements to estimate the location. In the positioning procedure, the UE or TRP may report cell / frequency information to which it belongs, including Physical Cell ID (PCI), Global Cell ID (GCI), Absolute Radio Frequency Channel Number (ARFCN), etc.

[0155] In addition, for AI / ML-based inference, as an example, a location management device (LMF) can operate measurement requests, reporting parameters, and AI / ML models, and terminals and transmission nodes generate and report the PRS / SRS measurement results, and the LMF can synthesize the information to perform location estimation or adjust the inference policy through the AI / ML model.

[0156] FIG. 10 is a signal diagram conveying terminal positioning-related information using AI / ML according to one embodiment.

[0157] Referring to FIG. 10, a terminal (1000) can receive at least one reference signal for positioning based on an AI / ML (artificial intelligence / machine learning) model (S1010). The terminal (1000) can measure the received at least one reference signal.

[0158] The terminal (1000) can obtain LoS-related information based on measurements of a reference signal and an AI / ML model (S1020). The terminal (1000) can transmit a signal containing LoS-related information to a base station (1010) (S1030).

[0159] For example, LoS-related information may include information regarding the reliability of a determination by an AI / ML model regarding whether each reference signal is provided via LoS or via NLoS (non-line of sight). The reliability information may include the LoS probability calculated by the AI / ML model. LoS-related information may be provided individually for each of the at least one reference signal. LoS-related information may be provided individually for each arrival path of each reference signal. LoS-related information may be provided for reference signals where the LoS probability is above a threshold. Based on the LoS-related information, the reference signal settings to be used for positioning may be determined. Based on the LoS-related information, at least one of the reference signal transmission power and the reference signal muting pattern may be determined. The reference signal transmission power and the reference signal muting pattern may be determined for each TRP (transmission reception point).

[0160] FIG. 11 is a signal diagram conveying terminal positioning-related information using AI / ML according to another embodiment.

[0161] Referring to FIG. 11, the base station / TRP (1110) may transmit and / or receive at least one reference signal for positioning to the terminal (1100) (S1110). For example, the base station / TRP (1110) may transmit at least one DL reference signal for positioning to the terminal (1100) and receive a measurement result therefrom from the terminal. Alternatively, the base station / TRP (1110) may receive at least one UL reference signal for positioning from the terminal (1100) and measure it.

[0162] The base station / TRP (1110) can obtain LoS-related information based on measurements of a reference signal and an AI / ML model (S1120) and transmit a signal containing this information to a positioning server (1120) (S1130).

[0163]

[0164] With the evolution of 5G NR (New Radio) systems, positioning methods applying artificial intelligence (AI) and machine learning (ML) technologies are being discussed to dramatically improve the location accuracy of terminals. In particular, various scenarios (e.g., AI / ML-based positioning) have been introduced that utilize AI / ML models to analyze the characteristics of wireless channels and estimate the location of terminals.

[0165] In such AI / ML-based positioning, detailed channel data, such as Channel State Information (CSI) or Channel Impulse Response (CIR) measured by base stations or terminals, is required as input data for AI / ML models to achieve accurate location estimation. However, transmitting all sample-based channel response samples in the time domain to network nodes (e.g., LMFs) can cause massive data overhead, thereby degrading system efficiency.

[0166] Accordingly, a method of compressing high-dimensional channel data into low-dimensional core information for reporting may be considered. However, in order to reduce the amount of data while maintaining positioning performance by selecting and reporting only a subset of samples from the entire time domain, it is necessary to first establish specific parameters to determine the criteria for sample selection and the precision with which time information is reported.

[0167] Accordingly, the present disclosure proposes a procedure in which a base station receives a measurement request containing these parameters from a positioning server (LMF), measures an uplink signal in a manner optimized for AI / ML positioning, and reports the result.

[0168]

[0169] FIG. 12 is a diagram for explaining the operation of a base station according to one embodiment.

[0170] Referring to FIG. 12, the base station obtains from the location management function (LMF) a timing reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t A measurement request including ' can be received (S1210).

[0171] A measurement request may be a message instructing a base station to measure the terminal's uplink signal, e.g., SRS, and report the result for AI / ML-based positioning. In one example, the measurement request may be received via the NR Positioning Protocol A (NRRPPa) protocol.

[0172] The parameters included in the measurement request can be configured to determine the specific method of measurement and reporting to be performed by the base station. Specifically, the time domain window size N t may refer to the total interval size of continuous time-domain samples that the base station must acquire. For example, the number of time-domain samples may consist of 32, 64, 128, etc. Additionally, the number of samples to be reported N t ' is the whole N t It may refer to the number of valid samples that must actually be selected and reported out of the samples. Depending on the example, the number of valid samples may consist of 8, 16, 24, etc.

[0173] Additionally, the time reporting particle size factor k may refer to a parameter that determines the time resolution used when reporting timing information of a measured sample. According to one example, k may be set to a value of one of a plurality of integers including at least 3, 4, and 5. For example, k may be selected within a range including 3, 4, and 5, e.g., from 0 to 5, taking into account the balance between measurement precision and reporting overhead.

[0174] According to one example, the base station can determine whether it can support a combination of parameters included in a received measurement request. If the base station receives a combination of parameters (N) requested from a location management device t , N t If measurement according to ', k) cannot be supported, the base station may, instead of performing the measurement and reporting the result, transmit a message to the location management device indicating that measurement information in response to the measurement request cannot be provided, such as "Measurement Failure." This is intended to respond to situations such as the base station's capability, current load conditions, or when the requested parameter combination is invalid.

[0175] Referring again to FIG. 12, the base station can obtain a time domain channel response by measuring a sounding reference signal (SRS) for positioning transmitted from a terminal (S1220).

[0176] According to one example, a terminal may transmit an SRS for positioning to a base station in a periodic, semi-persistent, or aperioditic manner, depending on the configuration of the base station or the location management device. Here, the SRS for positioning may be configured through an Information Element (IE) of the SRS-Config of the Radio Resource Control (RRC) layer. The SRS-Config may be configured to include one or more SRS-PosResource and SRS-PosResourceSet for the transmission of uplink reference signals for positioning purposes, thereby defining the terminal's SRS transmission resources, temporal operation mode, and related parameters. The SRS-PosResourceSet may include a resourceType, which may be set to one of aperiodic, semi-persistent, or periodic to define the operational characteristics in the time domain of the SRS transmitted by the terminal. Accordingly, the terminal can transmit SRS for positioning in a periodic, semi-persistent, or non-periodic manner depending on the network configuration. According to one example, aperiodic SRS transmission may be triggered by an aperiodicSRS-ResourceTrigger, which may be provided through control information of the lower layer (L1), for example, downlink control information (DCI). On the other hand, periodic or semi-persistent SRS transmission may have its transmission period and time offset set by parameters of the periodicityAndOffset series included in SRS-PosResource or SRS-PosResourceSet.

[0177] Accordingly, the terminal can transmit SRS periodically, semi-continuously, or aperiodicly based on the SRS resource / resource set and resourceMapping (symbol location / repetition) and periodicityAndOffset or aperiodicSRS-ResourceTrigger (DCI trigger / slot offset) configuration set by SRS-Config, and the base station can obtain uplink radio channel characteristics between the terminal and the base station by estimating the uplink channel response from the received SRS.

[0178] The base station can estimate the uplink radio channel characteristics between the terminal and the base station using the received SRS.

[0179] Specifically, the base station can obtain a time-domain channel response by first calculating a frequency-domain channel response based on the received SRS signal and converting it to the time-domain through signal processing processes such as the Fast Inverse Fourier Transform (IFFT). This time-domain channel response may be in the form of a Channel Impulse Response (CIR) or Power Delay Profile (PDP), which represents the signal power or amplitude according to time delay.

[0180] In this case, the base station has a time domain window size N t Based on the information, the entire observation interval in the time domain can be set. That is, the base station is not in an infinite time domain, but N t A channel response consisting of consecutive time domain samples can be acquired or extracted. Here, each sample may be a data point distinguished according to the basic time unit Tc of the NR system or a set time granularity. The N thus acquired t N consecutive samples are valid in the subsequent step.t It can serve as pool data for selecting ' 1' samples.

[0181] Referring again to Fig. 12, the base station is N t Among n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Can determine the number of samples (S1230).

[0182] According to one example, the time particle size T is T = 2 k * A value determined by Tc, which may represent the temporal resolution for reporting timing information of selected samples. Tc is the subcarrier spacing (SCS) and FFT magnitude of the NR system (hereinafter referred to as Nf or N FFT It can be constructed based on (as written). That is, Tc can mean the minimum time unit determined by Tc = 1 / (Δf * Nf).

[0183] The base station is the total N t Among the time-domain samples, N contains the most significant information for AI / ML-based positioning. t A process of selecting ' samples can be performed. According to one example, this selection process can be performed based on power or amplitude. Specifically, the base station can perform the above N t Measure the signal strength of each of the n consecutive samples, and the number (N) set in order of having the strongest power among them t A sample size of ') can be selected and determined as a valid sample.

[0184] For example, the total window size (N t ) is 128 and the number of samples to be reported (N tWhen ') is set to 8, the base station can extract the top 8 samples with the highest power values ​​out of 128 samples. Through this, the base station can efficiently compress and extract information on the most dominant paths among the multipath characteristics of the wireless channel.

[0185] Referring again to Fig. 12, the base station is a determined N t Measurement information for ' 1 sample can be transmitted to a location management device (S1240).

[0186] Measurement information can be transmitted by being included in an NRPPa (NR Positioning Protocol A) message, which is the interface protocol between the base station and the LMF, for example, in a Measurement Report. The measurement information is the previously selected N t It may include amplitude or power information and timing information for each of the samples.

[0187] For example, the timing information of each sample may be reported as a relative value to a specific reference time, rather than as an absolute time value. In this case, the reporting resolution of the timing information follows a previously set timing granularity T. For instance, the timing information may be expressed by quantization into integer multiples of T.

[0188] The location management device can infer the location of the terminal by utilizing measurement information received from the base station as input data for an AI / ML positioning model.

[0189] Thus, according to the present disclosure, a base station has a whole-time domain channel response (N t Instead of transmitting all samples (N), valid samples (N) that contribute significantly to AI / ML model performance tBy selecting only ' ) and reporting with optimized temporal resolution (T according to k value), high-precision positioning performance can be secured while drastically reducing transmission data overhead.

[0190] According to this, a method and apparatus can be provided for optimizing high-dimensional original measurement information into low-dimensional measurement information as input data for an AI / ML model to infer the location of a terminal in a wireless communication system.

[0191]

[0192] FIG. 13 is a diagram illustrating the operation of a position management device according to one embodiment.

[0193] Referring to FIG. 13, the location management function (LMF) is a base station, with a timing reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t A measurement request including ' can be transmitted (S1310).

[0194] A measurement request may be a message instructing a base station to measure the terminal's uplink signal, e.g., SRS, and report the result for AI / ML-based positioning. In one example, the measurement request may be transmitted via the NR Positioning Protocol A (NRRPPa) protocol.

[0195] The parameters included in the measurement request can be configured to determine the specific method of measurement and reporting to be performed by the base station. Specifically, the time domain window size N t may refer to the total interval size of continuous time-domain samples that the base station must acquire. For example, the number of time-domain samples may consist of 32, 64, 128, etc. Additionally, the number of samples to be reported N t ' is the whole Nt It may refer to the number of valid samples that must actually be selected and reported out of the samples. Depending on the example, the number of valid samples may consist of 8, 16, 24, etc.

[0196] Additionally, the time reporting particle size factor k may refer to a parameter that determines the time resolution used when reporting timing information of a measured sample. According to one example, k may be set to a value of one of a plurality of integers including at least 3, 4, and 5. For example, k may be selected within a range including 3, 4, and 5, e.g., from 0 to 5, taking into account the balance between measurement precision and reporting overhead.

[0197] According to one example, the base station can determine whether it can support a combination of parameters included in a received measurement request. If the base station receives a combination of parameters (N) requested from a location management device t , N t If measurement according to ', k) cannot be supported, the location management device may receive a message from the base station, such as "Measurement Failure," indicating that measurement information in response to the measurement request cannot be provided, instead of receiving the measurement result. This is intended to respond to situations such as the base station's capability, current load conditions, or when the requested combination of parameters is invalid.

[0198] Referring again to FIG. 13, the location management device can receive measurement information in response to a measurement request from a base station (S1320).

[0199] According to one example, the terminal may transmit an SRS for positioning to the base station periodically, semi-persistently, or aperiodisically, depending on the settings of the base station or the location management device. The base station may use the received SRS to estimate the uplink radio channel characteristics between the terminal and the base station.

[0200] Specifically, the base station can obtain a time-domain channel response by first calculating a frequency-domain channel response based on the received SRS signal and converting it to the time-domain through signal processing processes such as the Fast Inverse Fourier Transform (IFFT). This time-domain channel response may be in the form of a Channel Impulse Response (CIR) or Power Delay Profile (PDP), which represents the signal power or amplitude according to time delay.

[0201] In this case, the base station has a time domain window size N t Based on the information, the entire observation interval in the time domain can be set. That is, the base station is not in an infinite time domain, but N t A channel response consisting of consecutive time domain samples can be acquired or extracted. Here, each sample may be a data point distinguished according to the basic time unit Tc of the NR system or a set time granularity. The N thus acquired t N consecutive samples are valid in the subsequent step. t It can serve as pool data for selecting ' 1' samples.

[0202] The base station is N tAmong n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Can determine ' 1 sample

[0203] According to one example, the time particle size T is T = 2 k A value determined by * Tc, which may represent the time resolution for reporting timing information of selected samples. Tc can be constructed based on the subcarrier spacing (SCS) and FFT size (Nf) of the NR system. That is, Tc may represent the minimum time unit determined by Tc = 1 / (Δf * Nf).

[0204] The base station is the total N t Among the time-domain samples, N contains the most significant information for AI / ML-based positioning. t A process of selecting ' samples can be performed. According to one example, this selection process can be performed based on power or amplitude. Specifically, the base station can perform the above N t Measure the signal strength of each of the n consecutive samples, and the number (N) set in order of having the strongest power among them t A sample size of ') can be selected and determined as a valid sample.

[0205] For example, the total window size (N t ) is 128 and the number of samples to be reported (N t When ') is set to 8, the base station can extract the top 8 samples with the highest power values ​​out of 128 samples. Through this, the base station can efficiently compress and extract information on the most dominant paths among the multipath characteristics of the wireless channel.

[0206] The location management device is determined N tMeasurement information for ' samples can be received from the base station. The measurement information can be received by including it in an NRPPa (NR Positioning Protocol A) message, which is the interface protocol between the base station and the LMF, for example, in a Measurement Report. The measurement information is the previously selected N t It may include amplitude or power information and timing information for each of the samples.

[0207] For example, the timing information of each sample may be reported as a relative value to a specific reference time, rather than as an absolute time value. In this case, the reporting resolution of the timing information follows a previously set timing granularity T. For instance, the timing information may be expressed by quantization into integer multiples of T.

[0208] The location management device can infer the location of the terminal by utilizing measurement information received from the base station as input data for an AI / ML positioning model.

[0209] Thus, according to the present disclosure, a base station has a whole-time domain channel response (N t Instead of transmitting all samples (N), valid samples (N) that contribute significantly to AI / ML model performance t By selecting only ' ) and reporting with optimized temporal resolution (T according to k value), high-precision positioning performance can be secured while drastically reducing transmission data overhead.

[0210] According to this, a method and apparatus can be provided for optimizing high-dimensional original measurement information into low-dimensional measurement information as input data for an AI / ML model to infer the location of a terminal in a wireless communication system.

[0211] In an example according to the present disclosure, time-domain channel measurements and reporting related to AI / ML-based positioning may select or use in parallel a path-based method that expresses the time-domain channel information in units of individual propagation paths and a sample-based method that expresses the channel response estimated in the time domain in units of samples. In particular, regarding the sample-based measurement method, a structure in which the channel response estimated in the time domain consists of a plurality of time-domain samples and only some of the samples are selected and reported is repeatedly proposed. The measurement result is N of the time-domain channel response t It consists of samples, and the timing information for each sample is T = 2 k * Defined as Tc, the time domain channel information can be modified, expanded, or reduced into a form suitable for AI / ML input. Additionally, the time domain measurement parameters are sent to the base station via LMF with a time domain window size (N t ), number of samples subject to reporting (N t It is characterized by performing measurement and reporting by considering measurement request signaling including '), and a time reporting particle size factor (k). The above information can be transmitted via an LMF-base station interface (e.g., NRPPa). In addition, N t is a parameter that defines the entire interval of the channel response to be observed by the base station in the time domain, and includes a value corresponding to the observation window that determines "how wide a time or delay interval to observe," and N t' is a parameter that defines the number of samples actually reported within the aforementioned observation interval and is directly linked to the amount of information reported and the input dimensions of the AI / ML model. Finally, k is a parameter that determines the temporal resolution at which the timing information of each sample is expressed, serving to control the trade-off between the precision of timing reporting and reporting overhead. Here, regarding the value of k, a continuous range can be selectively supported as a specific set (e.g., {3,4}, {4}, {2,3,4,5}, etc.), which can be adjusted considering base station implementation complexity and interoperability. Additionally, information related to the number of supported sets for the value of k or the composition of such sets can be signaled through procedures such as capability indication. Furthermore, for the selection or coexistence of sample-based and path-based measurements, N is provided along with meta-information identifying the measurement type. t , N t A parameter set such as ', k can be optionally passed.

[0212] Hereinafter, each embodiment related to the method of performing AI / ML-based positioning will be described in detail with reference to the relevant drawings.

[0213] Table 1 is a diagram illustrating a combination of parameters of a path-based measurement determined based on a preset FFT size, SCS, and Sampling Interval (Tc) according to one embodiment.

[0214] Referring to Table 1, the present disclosure may pre-set an FFT size, SCS, and Sampling Interval (Tc) to determine a combination of parameters for a path-based measurement for AI / ML positioning. When the FFT size is 4096, the SCS and Tc values ​​may be set, and accordingly, a combination of parameters for a path-based measurement may be determined.

[0215]

[0216] Referring to Table 2, when the FFT size is 2048, the SCS and Tc values ​​can be set, and accordingly, the parameter combination of the path-based measurement can be determined.

[0217]

[0218] Currently, CIR, PDP, and DP are used as channel-related metrics in AI / ML, and each metric is derived in the time domain.

[0219] To evaluate positioning-based AI / ML through multipath measurement, given a set of parameters (N' TRP, N t , N t ', N port In relation to ), it has the following characteristics.

[0220] - CIR has the largest measurement size and consists of a measurement list in which information regarding (a) delay, (b) power, and (c) phase is included for each measurement value.

[0221] - PDP has a smaller measurement size than CIR. Here, PDP consists of a measurement list in which information on (a) delay and (b) power is included for each measurement value.

[0222] - DP has the smallest measurement size and consists of a measurement log containing (a) information related to delay for each measurement value.

[0223] Regarding the input and output of the model, the following can be proposed.

[0224] When evaluating AI / ML-based position measurements, if the time-domain channel impulse response (CIR) or power delay profile (PDP) is used as a model input in the evaluation, the input dimension is N TRP * N port * N t It can be determined as. Here, N TRP is the number of TRPs (transmission / reception points), N port is the number of transmit / receive antenna port pairs, N t represents the number of consecutive time domain samples.

[0225] If N t ' (N t ' < N t ) samples with strong power are selected as model inputs, and the remaining (N t - N t If the time domain sample is set to 0, N t In addition to N t The value can be determined. Also, N t It can be assumed that time information for the sample must be provided as input to the model.

[0226] When evaluating AI / ML-based localization, if time-domain samples are used as model input and subsampling is applied, N t The selection of the measurement value is determined based on the strongest power unless otherwise specified. If subsampling is applied, N t Measurements do not necessarily have to be continuous in time.

[0227] - The training dataset and the test dataset use the same measure selection method (e.g., strongest power) unless explicitly stated otherwise.

[0228] - N tOther methodologies for selecting measurements may also be evaluated.

[0229] When using channel-related measurements such as CIR / PDP / DP in AI / ML positioning, among the time-domain measurements, N t A method for defining ' and k samples can be proposed. First, the channel resource information is as shown in Equation 1.

[0230] [Mathematical Formula 1]

[0231] T = 2 k * Tc

[0232] Here, k is the time reporting granularity factor, and T is the time granularity. Tc represents the basic time unit, and Tc can be defined as in Equation 2.

[0233] [Mathematical Formula 2]

[0234] Tc = 1 / (Δf * Nf)

[0235] Here, Δf is the subcarrier spacing and Nf is the FFT size.

[0236] Next, the number of channel estimates in the time domain can be defined as Equation 3.

[0237] [Mathematical Formula 3]

[0238] N t = 2 k

[0239] Here, N t represents the number of samples in a continuous time domain, and N is the number of samples with the highest amplitude among them. t It is said that. Since the FFT size in 5G is 4096, once the size of the SCS is determined, the values ​​of Tc and T are calculated, and k and N t Can suggest a value.

[0240] N t = 256, N tPositioning performance can be verified by fixing ' = {8, 16, 32, 64, 128, 256}. Accordingly, FFT=4096, N t It is based on 256, and thus k can be defined as 8.

[0241] For I / ML positioning, CIR can be processed before inputting into the neural network.

[0242] This disclosure proposes a combination of parameters for compressing or using high-dimensional sample-based measurements into low-dimensional path-based measurements for AI / ML positioning, based on the FFT size and PRS comb type for each subcarrier space. The LMF (location management function) comprises a time granularity factor k and a window size N for compressing sample-based measurements taken via NRPPa. t , # reported values ​​N t ' can be passed to gNB.

[0243] For example, when FR1 and FFT size is 4096, N t k and N for ga to be set to 32 t ' can be configured as shown in Table 3. In this case, T is calculated according to the SCS. As the value of k increases, the resolution for channel measurements increases, but since the associated overhead also increases, k = {3, 4, 5} is used.

[0244]

[0245] As another example, when FR1 and FFT size is 4096, N t k and N to set to 64 t' can be configured as shown in Table 4. In this case, T is calculated according to the SCS. As the window size doubles from 32, k = {3, 4, 5, 6} is used, and as k increases, N t The value of ' also increases.

[0246]

[0247] As another example, when FR1 and FFT size is 4096, N t k and N to set to 128 t ' can be configured as shown in Table 5. In this case, T is calculated according to the SCS. As the window size doubles from 64, k = {3, 4, 5, 6, 7, 8} is used, and as k increases, N t The value of ' also increases up to a maximum of 24.

[0248]

[0249] As another example, when FR2 and FFT size is 4096, N t k and N to set to 32 t ' can be configured as shown in Table 6. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6}, which is higher than that of FR1.

[0250]

[0251] As another example, when FR2 and FFT size is 4096, N t k and N to set to 64 t ' can be configured as shown in Table 7. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6, 7}, which is higher than that of FR1.

[0252]

[0253] As another example, when FR2 and FFT size is 4096, Nt k and N to set to 128 t ' can be configured as shown in Table 8. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6, 8, 9}, which is higher than that of FR1.

[0254]

[0255] For example, when FR1 and FFT size is 2048, N t k and N to set to 32 t ' can be configured as shown in Table 9. In this case, T is calculated according to the SCS. As the value of k increases, the resolution for channel measurements increases, but since the associated overhead also increases, k = {3, 4, 5} is used.

[0256]

[0257] As another example, when FR1 and FFT size is 2048, N t k and N to set to 64 t ' can be configured as shown in Table 10. In this case, T is calculated according to the SCS. As the window size increases twofold from 32, k = {3, 4, 5, 6} is used, and as k increases, N t The value of ' also increases.

[0258]

[0259] As another example, when FR1 and FFT size is 2048, N t k and N to set to 128 t ' can be configured as shown in Table 11. In this case, T is calculated according to the SCS. As the window size doubles from 64, k = {3, 4, 5, 6, 7, 8} is used, and as k increases, N t The value of ' also increases up to a maximum of 24.

[0260]

[0261] As another example, when FR2 and FFT size is 2048, N t k and N to set to 32 t ' can be configured as shown in Table 12. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6}, which is higher than that of FR1.

[0262]

[0263] As another example, when FR2 and FFT size is 2048, N t k and N to set to 64 t ' can be configured as shown in Table 13. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6, 7}, which is higher than that of FR1.

[0264]

[0265] As another example, when FR2 and FFT size is 2048, N t k and N to set to 128 t ' can be configured as shown in Table 14. In this case, T is calculated according to SCS. For higher precision, FR2 uses k = {3, 4, 5, 6, 8, 9}, which is higher than that of FR1.

[0266]

[0267] As another example, the granularity factor k is the Comb type N of the PRS (positioning reference signal). comb = {0, 2, 4, 6, 12}, subcarrier space Δf, and FFT size N FFT It is determined as shown in Table 15 according to [the example].

[0268]

[0269] As another example, a predetermined N t N according to = {32, 64, 128} t ' can be determined as shown in Table 16.

[0270]

[0271] As another example, the granularity factor k is the Comb type N of the PRS (positioning reference signal). comb = {0, 2, 4, 6, 12}, subcarrier space Δf, and FFT size N FFT It is determined as shown in Table 17 according to [the example].

[0272]

[0273] As another example, a predetermined N t N according to = {32, 64, 128} t ' can be determined as shown in Table 18.

[0274]

[0275]

[0276] Hereinafter, the configuration of a base station and a location management device capable of performing some or all of the embodiments described with reference to FIGS. 1 to 13 will be described with reference to the drawings. The foregoing description may be omitted to avoid redundant descriptions, and in such cases, the omitted content may be applied substantially identically to the following description, provided that it does not contradict the technical concept of the invention.

[0277] FIG. 14 is a drawing for explaining the configuration of a base station (1400) according to one embodiment.

[0278] Referring to FIG. 14, a base station performing AI / ML-based positioning includes a transmitter (1420), a receiver (1430), and a control unit (1410) that controls the operation of the transmitter and the receiver. The control unit (1410) receives a measurement request from a location management function (LMF) including a timing reporting granularity factor k, a time domain window size Nt, and a number of reported samples Nt', measures a sounding reference signal (SRS) for positioning transmitted from a terminal to obtain a time domain channel response, determines Nt' samples based on the timing granularity T determined based on k and a basic time unit Tc among Nt consecutive time domain samples, and transmits measurement information for the determined Nt' samples to the location management function.

[0279] The control unit (1410) controls the overall operation of the base station (1400). The control unit (1410) may include at least one processor and may be configured to perform the functions, procedures, and / or methods proposed in this disclosure by executing a program or instruction stored in memory. The control unit (1410) may implement layers of a communication protocol and may control the transmitter (1420) and the receiver (1430) to transmit and receive signals with a terminal or other network node.

[0280] The transmitter (1420) and the receiver (1430) may include an RF (Radio Frequency) unit for transmitting and receiving wireless signals, and may be collectively referred to as a transceiver. The transmitter (1420) and the receiver (1430) may be connected to one or more antennas to communicate with a terminal via a wireless channel or with a core network entity (e.g., LMF) via a backhaul network. The transmitter (1420) may be configured to convert a baseband signal from the control unit (1410) into a wireless signal and transmit it, and the receiver (1430) may be configured to convert the received wireless signal into a baseband signal and transmit it to the control unit (1410).

[0281] The control unit (1410) obtains from the location management function (LMF) a timing reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t A measurement request including ' can be received.

[0282] A measurement request may be a message instructing a base station to measure the terminal's uplink signal, e.g., SRS, and report the result for AI / ML-based positioning. In one example, the measurement request may be received via the NR Positioning Protocol A (NRRPPa) protocol.

[0283] The parameters included in the measurement request can be configured to determine the specific method of measurement and reporting to be performed by the base station. Specifically, the time domain window size N t may refer to the total interval size of continuous time-domain samples that the base station must acquire. For example, the number of time-domain samples may consist of 32, 64, 128, etc. Additionally, the number of samples to be reported N t' is the whole N t It may refer to the number of valid samples that must actually be selected and reported out of the samples. Depending on the example, the number of valid samples may consist of 8, 16, 24, etc.

[0284] Additionally, the time reporting particle size factor k may refer to a parameter that determines the time resolution used when reporting timing information of a measured sample. According to one example, k may be set to a value of one of a plurality of integers including at least 3, 4, and 5. For example, k may be selected within a range including 3, 4, and 5, e.g., from 0 to 5, taking into account the balance between measurement precision and reporting overhead.

[0285] According to one example, the control unit (1410) can determine whether it can support a combination of parameters included in a received measurement request. If the base station receives a combination of parameters (N) requested from a location management device t , N t If measurement according to ', k) cannot be supported, the control unit (1410) may, instead of performing the measurement and reporting the result, send a message to the location management device indicating that measurement information according to the measurement request cannot be provided, such as Measurement Failure. This is to respond to the capability of the base station, the current load situation, or cases where the requested parameter combination is invalid.

[0286] The control unit (1410) can obtain a time-domain channel response by measuring a sounding reference signal (SRS) for positioning transmitted from the terminal. According to one example, the terminal can transmit an SRS for positioning to the base station in a periodic, semi-persistent, or aperioditic manner depending on the settings of the base station or the location management device. The control unit (1410) can estimate the uplink radio channel characteristics between the terminal and the base station using the received SRS.

[0287] Specifically, the control unit (1410) can obtain a time domain channel response by first calculating a frequency domain channel response based on a received SRS signal and converting it to a time domain through a signal processing process such as an inverse Fourier transform (IFFT). This time domain channel response may be in the form of a Channel Impulse Response (CIR) or Power Delay Profile (PDP) representing the power or amplitude of a signal according to a time delay.

[0288] In this case, the control unit (1410) has a time domain window size N t Based on the information, the entire observation interval in the time domain can be set. That is, the control unit (1410) is not an infinite time domain, but N t A channel response consisting of consecutive time domain samples can be acquired or extracted. Here, each sample may be a data point distinguished according to the basic time unit Tc of the NR system or a set time granularity. The N thus acquired t N consecutive samples are valid in the subsequent step. tIt can serve as pool data for selecting ' 1' samples.

[0289] The control unit (1410) is N t Among n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Can determine ' s samples. According to one example, the time particle size T is T = 2 k A value determined by * Tc, which may represent the time resolution for reporting timing information of selected samples. Tc can be constructed based on the subcarrier spacing (SCS) and FFT size (Nf) of the NR system. That is, Tc may represent the minimum time unit determined by Tc = 1 / (Δf * Nf).

[0290] The control unit (1410) is the total N t Among the time-domain samples, N contains the most significant information for AI / ML-based positioning. t A process of selecting ' samples can be performed. According to one example, this selection process can be performed based on power or amplitude. Specifically, the control unit (1410) [can perform] the N t Measure the signal strength of each of the n consecutive samples, and the number (N) set in order of having the strongest power among them t A sample size of ') can be selected and determined as a valid sample.

[0291] For example, the total window size (N t ) is 128 and the number of samples to be reported (N tWhen ') is set to 8, the control unit (1410) can extract the top 8 samples with the highest power values ​​among 128 samples. Through this, the control unit (1410) can efficiently compress and extract information on the most dominant paths among the multipath characteristics of the wireless channel.

[0292] The control unit (1410) determines N t Measurement information for ' samples can be transmitted to a location management device. The measurement information can be transmitted by being included in an NRPPa (NR Positioning Protocol A) message, which is the interface protocol between the base station and the LMF, for example, in a Measurement Report. The measurement information is the previously selected N t It may include amplitude or power information and timing information for each of the samples.

[0293] For example, the timing information of each sample may be reported as a relative value to a specific reference time, rather than as an absolute time value. In this case, the reporting resolution of the timing information follows a previously set timing granularity T. For instance, the timing information may be expressed by quantization into integer multiples of T.

[0294] The location management device can infer the location of the terminal by utilizing measurement information received from the base station as input data for an AI / ML positioning model.

[0295] Thus, according to the present disclosure, a base station has a whole-time domain channel response (N t Instead of transmitting all samples (N), valid samples (N) that contribute significantly to AI / ML model performance tBy selecting only ' ) and reporting with optimized temporal resolution (T according to k value), high-precision positioning performance can be secured while drastically reducing transmission data overhead.

[0296] As described above, the k value can accept any continuous integer value and can also be supported in the form of a limited supported set, taking into account the trade-off between implementation complexity, reporting overhead, and measurement precision. For example, for the FR1 band, the k value is set to the set {3, 4, 5}, or optionally applied up to {3, 4, 5, 6} in some extended scenarios. This can be adaptively set to a value that ensures channel measurement resolution above a certain level while preventing excessive reporting overhead. Meanwhile, for the FR2 band or scenarios requiring higher precision positioning, the range of the k value can be extended to {3, 4, 5, 6} or {3, 4, 5, 6, 7} to further improve temporal resolution. Additionally, it may include the possibility of applying a k value of 8 or higher.

[0297] For example, when k is 3, the timing resolution becomes T = 8·Tc; when k is 4, it can be set to T = 16·Tc; when k is 5, to T = 32·Tc; and when k is 6, to T = 64·Tc. Here, since Tc depends on the applied SCS and FFT sizes, the actual time resolution may vary depending on the frequency band or system configuration even when using the same k value. A timing resolution structure defined around k in this way allows for flexible control of measurement precision and reporting overhead at the network level in AI / ML-based positioning. The above k value is signaled from the LMF to the base station (gNB), and the LMF sends a set of parameters related to time-domain measurement to the base station, such as the time reporting granularity factor k and the time-domain window size N. t , and the number of samples to be reported Nt A measurement request message containing ' can be transmitted. That is, the k value is transmitted to the gNB through the measurement control information (measurement configuration / parameters) within the NRPPa message. Accordingly, the base station can quantize the timing information of time-domain samples into units of T based on the k value received from the LMF and report an NRPPa-based Measurement Report. To this end, the terminal can configure SRS-PosResource and SRS-PosResourceSet through the SRS-Config information element (IE) of the RRC layer to enable the above time-domain measurement. Accordingly, the terminal transmits an SRS for positioning to the base station in a periodic, semi-persistent, or aperioditic manner depending on the network configuration, and the base station can receive the SRS, calculate a time-domain channel response, and generate measurement information to be reported to the LMF.

[0298] In this disclosure, in an AI / ML-based positioning structure, the position management device (LMF) does not individually transmit parameters related to time domain measurement to the base station (gNB), but rather a time reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t ' can be bundled into a single measurement configuration set and transmitted. In this case, the measurement configuration set may further include measurement type indicator information regarding whether the time domain measurement is sample-based or path-based. Such a measurement configuration set can be signaled through NRPPa, which is an interface between the LMF and the base station.

[0299] According to one example, the base station may predefine a supported set of time reporting granularity factors for the k value included in the measurement configuration set, or notify the LMF during the response to the measurement request. That is, the base station provides a range or set of supported k values ​​in the form of capability information, and the LMF can configure the measurement request by selecting a k value within that range. If the LMF requests (N t , N t If the combination of ', k) falls outside the base station's supported range, the base station may not perform the measurement and report a Measurement Failure, suggest an alternative parameter combination, or fallback to a path-based measurement instead of a sample-based measurement.

[0300] Additionally, the timing information reporting in the present disclosure may be defined as reporting a relative time value with respect to a reference time, rather than an absolute time value. Time domain measurement parameters (k, N t , N t ') can be defined in conjunction with the physical layer settings of the PRS or SRS. For example, the comb type of the PRS, the subcarrier spacing Δf, and the FFT size N. FFT An appropriate value of k can be determined depending on the combination of, and the time domain window size N t As the number of reported samples N increases, in order to maintain AI / ML-based inference performance t It can also be set to increase in steps. In addition, different sets of candidate k values ​​may be applied to reflect the different channel characteristics and required precision of the FR1 band and FR2 band.

[0301] Accordingly, the terminal provides observation data for positioning by transmitting or receiving PRS or SRS according to the settings of the RRC layer, and the base station calculates a time-domain channel response using the received signal, and then generates measurement information by quantizing the timing information of the samples according to the time resolution defined by the value of k. Meanwhile, considering the entire measurement process above, the LMF [considers] k, N t , N t By controlling a set of measurement configurations including ', the observation range, amount of information, and timing resolution can be adjusted at the network level, and as a result, the balance between positioning accuracy and reporting overhead can be effectively controlled.

[0302] According to this, a method and apparatus can be provided for optimizing high-dimensional original measurement information into low-dimensional measurement information as input data for an AI / ML model to infer the location of a terminal in a wireless communication system.

[0303] FIG. 15 is a drawing for explaining the configuration of a position management device (1500) according to one embodiment.

[0304] Referring to FIG. 15, a location management device performing AI / ML-based positioning includes a transmitter (1520), a receiver (1530), and a control unit (1510) that controls the operation of the transmitter and the receiver, and the control unit (1510) is a base station, having a timing reporting granularity factor k and a time domain window size N t , and the number of samples to be reported N t A measurement request including ' can be transmitted, and measurement information can be received from the base station in response to the measurement request. The measurement information is N obtained based on the sounding reference signal (SRS) for positioning transmitted from the terminal. tAmong n consecutive time domain samples, N determined according to the time grain size T determined based on k and the base time unit Tc t It can include information about ' 1 sample.

[0305] A Location Management Function (LMF, 1500) is a core network entity or server that is responsible for managing and performing positioning of a terminal (UE) in a wireless communication network such as a 5G system (5GS). The LMF communicates with a base station (NG-RAN node, gNB) via the NRPPa (NR Positioning Protocol A) protocol and communicates with a terminal via LPP (LTE Positioning Protocol) to provide assistance data required for positioning or to transmit measurement commands.

[0306] In particular, in an AI / ML-based positioning environment according to one embodiment of the present disclosure, a location management device (1500) can determine and request compression parameters for time-domain channel measurements to be performed by a base station, and input compressed measurement information (Path-based measurement) received from the base station into an AI / ML model to perform the function of estimating (Inference) the location of a terminal.

[0307] The control unit (1510) controls the overall operation of the location management device (1500). The control unit (1510) may include at least one processor and may be configured to execute a program, algorithm, or AI / ML model stored in memory to perform the AI / ML-based positioning function, procedure, and / or method proposed in this disclosure. The control unit (1510) may process measurement data received from a base station (gNB) or a terminal (UE), determine parameters required for positioning, and perform position estimation calculations.

[0308] The transmitting unit (1520) and the receiving unit (1530) may include a wired or wireless communication interface for transmitting and receiving signals and data with an external device (e.g., a base station, another node of a core network, etc.), and may be collectively referred to as a transceiver or a communication unit. The transmitting unit (1520) and the receiving unit (1530) may perform the function of transmitting a measurement request message to a base station or receiving a measurement result report from a base station through a predetermined interface protocol (e.g., NRPPa, LPP, etc.).

[0309] The control unit (1510) is a base station, with a timing reporting granularity factor k and a time domain window size N. t , and the number of samples to be reported N t A measurement request including ' can be transmitted. The measurement request may be a message instructing the base station to measure the terminal's uplink signal, e.g., SRS, and report the result for AI / ML-based positioning. In one example, the measurement request may be transmitted via the NR Positioning Protocol A (NRRPPa) protocol.

[0310] The parameters included in the measurement request can be configured to determine the specific method of measurement and reporting to be performed by the base station. Specifically, the time domain window size N t may refer to the total interval size of continuous time-domain samples that the base station must acquire. For example, the number of time-domain samples may consist of 32, 64, 128, etc. Additionally, the number of samples to be reported N t ' is the whole N tIt may refer to the number of valid samples that must actually be selected and reported out of the samples. Depending on the example, the number of valid samples may consist of 8, 16, 24, etc.

[0311] Additionally, the time reporting particle size factor k may refer to a parameter that determines the time resolution used when reporting timing information of a measured sample. According to one example, k may be set to a value of one of a plurality of integers including at least 3, 4, and 5. For example, k may be selected within a range including 3, 4, and 5, e.g., from 0 to 5, taking into account the balance between measurement precision and reporting overhead.

[0312] According to one example, the base station can determine whether it can support a combination of parameters included in a received measurement request. If the base station receives a combination of parameters (N) requested from a location management device t , N t If measurement according to ', k) cannot be supported, the control unit (1510) may receive a message from the base station, such as Measurement Failure, indicating that measurement information according to the measurement request cannot be provided, instead of receiving the measurement result. This is to respond to the capability of the base station, the current load situation, or cases where the requested parameter combination is invalid.

[0313] The control unit (1510) may receive measurement information in response to a measurement request from the base station. According to one example, the terminal may transmit an SRS for positioning to the base station in a periodic, semi-persistent, or aperioditic manner, depending on the settings of the base station or the location management device. The base station may estimate the uplink radio channel characteristics between the terminal and the base station using the received SRS.

[0314] Specifically, the base station can obtain a time-domain channel response by first calculating a frequency-domain channel response based on the received SRS signal and converting it to the time-domain through signal processing processes such as the Fast Inverse Fourier Transform (IFFT). This time-domain channel response may be in the form of a Channel Impulse Response (CIR) or Power Delay Profile (PDP), which represents the signal power or amplitude according to time delay.

[0315] In this case, the base station has a time domain window size N t Based on the information, the entire observation interval in the time domain can be set. That is, the base station is not in an infinite time domain, but N t A channel response consisting of consecutive time domain samples can be acquired or extracted. Here, each sample may be a data point distinguished according to the basic time unit Tc of the NR system or a set time granularity. The N thus acquired t N consecutive samples are valid in the subsequent step. t It can serve as pool data for selecting ' 1' samples.

[0316] The base station is N t Among n consecutive time domain samples, N based on the time grain size T determined based on k and the base time unit Tc. t Can determine ' 1 sample

[0317] According to one example, the time particle size T is T = 2 kA value determined by * Tc, which may represent the time resolution for reporting timing information of selected samples. Tc can be constructed based on the subcarrier spacing (SCS) and FFT size (Nf) of the NR system. That is, Tc may represent the minimum time unit determined by Tc = 1 / (Δf * Nf).

[0318] The base station is the total N t Among the time-domain samples, N contains the most significant information for AI / ML-based positioning. t A process of selecting ' samples can be performed. According to one example, this selection process can be performed based on power or amplitude. Specifically, the base station can perform the above N t Measure the signal strength of each of the n consecutive samples, and the number (N) set in order of having the strongest power among them t A sample size of ') can be selected and determined as a valid sample.

[0319] For example, the total window size (N t ) is 128 and the number of samples to be reported (N t When ') is set to 8, the base station can extract the top 8 samples with the highest power values ​​out of 128 samples. Through this, the base station can efficiently compress and extract information on the most dominant paths among the multipath characteristics of the wireless channel.

[0320] The control unit (1510) determines N t Measurement information for ' samples can be received from the base station. The measurement information can be received by including it in an NRPPa (NR Positioning Protocol A) message, which is the interface protocol between the base station and the LMF, for example, in a Measurement Report. The measurement information is the previously selected Nt It may include amplitude or power information and timing information for each of the samples.

[0321] For example, the timing information of each sample may be reported as a relative value to a specific reference time, rather than as an absolute time value. In this case, the reporting resolution of the timing information follows a previously set timing granularity T. For instance, the timing information may be expressed by quantization into integer multiples of T.

[0322] The control unit (1510) can infer the location of the terminal by utilizing the measurement information received from the base station as input data for the AI / ML positioning model.

[0323] Thus, according to the present disclosure, a base station has a whole-time domain channel response (N t Instead of transmitting all samples (N), valid samples (N) that contribute significantly to AI / ML model performance t By selecting only ' ) and reporting with optimized temporal resolution (T according to k value), high-precision positioning performance can be secured while drastically reducing transmission data overhead.

[0324] According to this, a method and apparatus can be provided for optimizing high-dimensional original measurement information into low-dimensional measurement information as input data for an AI / ML model to infer the location of a terminal in a wireless communication system.

[0325] The aforementioned embodiments may be supported by standard documents disclosed in at least one of the wireless access systems IEEE 802, 3GPP, and 3GPP2. That is, steps, configurations, and parts in the embodiments that are not described to clearly reveal the technical concept may be supported by the aforementioned standard documents. Furthermore, all terms disclosed in this specification may be explained by the standard documents disclosed above.

[0326] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented by hardware, firmware, software, or a combination thereof.

[0327] In the case of implementation by hardware, the method according to the embodiments may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, or microprocessors.

[0328] In the case of implementation by firmware or software, the method according to the embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. Software code may be stored in a memory unit and executed by a processor. The memory unit may be located inside or outside the processor and may exchange data with the processor by various means already known.

[0329] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" described above may generally refer to computer-related entities, hardware, combinations of hardware and software, software, or running software. For example, the aforementioned components may be, but are not limited to, processes driven by a processor, processors, controllers, control processors, objects, execution threads, programs, and / or computers. For example, both the application running on the controller or processor and the controller or processor may be components. One or more components may reside within a process and / or execution thread, and the components may be located on a single device (e.g., a system, a computing device, etc.) or distributed across two or more devices.

[0330] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain, not limit, the scope of the technical concept is not limited by these embodiments. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

[0331]

[0332] CROSS-REFERENCE TO RELATED APPLICATION

[0333] This patent application claims priority pursuant to Section 119(a) of the U.S. Patent Act (35 USC §119(a)) to Patent Application No. 10-2025-0009745 filed in Korea on January 22, 2025 and Patent Application No. 10-2026-0012221 filed in Korea on January 21, 2026, all of which are incorporated by reference into this patent application. Additionally, this patent application claims priority in countries other than the United States for the same reasons as above, all of which are incorporated by reference into this patent application.

Claims

1. In a method for a base station to perform AI / ML-based positioning, From the location management function (LMF), timing reporting granularity factor k and time domain window size N t , and the number of samples to be reported N t A step of receiving a measurement request including '; A step of obtaining a time-domain channel response by measuring a sounding reference signal (SRS) for positioning transmitted from a terminal; The above N t Among the n consecutive time domain samples, N based on the time grain size T determined based on the above k and the basic time unit Tc. t Step to determine ' number of samples; and The N determined above t A method comprising the step of transmitting measurement information for ' 1 sample to the position management device.

2. In Paragraph 1, The above N t The step of determining the number of samples is, The above N t N consecutive time-domain samples in order of strongest power t Method for determining ' 1 sample.

3. In Paragraph 1, The above basic time unit Tc is, It is configured based on the above subcarrier spacing and FFT (fast Fourier transform) magnitude, and The above measurement information is, The above selected N t It includes amplitude and timing information for each of the samples, The above timing information is, A method reported as a value relative to a reference time.

4. In Paragraph 1, The above k is, A method of being set to one of a plurality of integers including at least 3, 4 and 5.

5. In Paragraph 1, The parameter combination (N) requested by the base station from the location management device t , N t A method further comprising the step of transmitting a message to the location management device indicating that measurement information according to the measurement request cannot be provided when measurement according to ', k) cannot be supported.

6. A method in which a location management function (LMF) performs AI / ML-based positioning, As a base station, timing reporting granularity factor k, time domain window size N t , and the number of samples to be reported N t A step of transmitting a measurement request including '; and The method includes the step of receiving measurement information from the base station in response to the measurement request. The above measurement information is N obtained based on the SRS (sounding reference signal) for positioning transmitted from the terminal. t Among the n consecutive time domain samples, N determined according to the time grain size T determined based on the above k and the basic time unit Tc t A method for including information on ' samples.

7. In Paragraph 6, The received N above t Information on the ' samples is The above N t A method of information on samples determined in order of having the strongest power among a number of consecutive time domain samples.

8. In Paragraph 6, The above basic time unit Tc is, It is configured based on the above subcarrier spacing and FFT (fast Fourier transform) magnitude, and The above measurement information is the determined N t It includes amplitude and timing information for each of the samples, The above timing information is a method in which it is reported as a value relative to a reference time.

9. In Paragraph 6, The above k is, A method of being set to one of a plurality of integers including at least 3, 4 and 5.

10. In Paragraph 6, The above base station includes a combination of parameters (N) in the measurement request. t , N t A method further comprising the step of receiving a message indicating that measurement information according to the measurement request cannot be provided, instead of receiving measurement information from the base station, when measurement according to ', k) cannot be supported.

11. In a base station performing AI / ML-based positioning, Transmitter; Receiver; and It includes a control unit that controls the operation of the transmitting unit and the receiving unit, and The above control unit is, From the location management function (LMF), timing reporting granularity factor k and time domain window size N t , and the number of samples to be reported N t Receive a measurement request including ', A time-domain channel response is obtained by measuring the sounding reference signal (SRS) for positioning transmitted from the terminal, and The above N t Among the n consecutive time domain samples, N based on the time grain size T determined based on the above k and the basic time unit Tc. t Determine ' 1 sample, The N determined above t A base station that transmits measurement information for ' samples' to the above-mentioned location management device.

12. In Paragraph 11, The above control unit is, The above N t N consecutive time-domain samples in order of strongest power t Base station determining the number of samples.

13. In Paragraph 11, The above basic time unit Tc is, It is configured based on the above subcarrier spacing and FFT (fast Fourier transform) magnitude, and The above measurement information is, The above selected N t It includes amplitude and timing information for each of the samples, The above timing information is, Base station reported as a value relative to reference time.

14. In Paragraph 11, The above k is, A base station set to one of a plurality of integers including at least 3, 4 and 5.

15. In Paragraph 11, The above control unit is, The parameter combination (N) requested by the base station from the location management device t , N t A base station that transmits a message to the location management device indicating that measurement information according to the measurement request cannot be provided when measurement according to ', k) cannot be supported.

Images