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

Abstract

The present disclosure relates to a 5G or 6G communication system for providing higher data transmission rates than the previous 4G communication system, such as LTE. A method performed by a base station in a wireless communication system according to various embodiments of the present disclosure may comprise the steps of: transmitting, to a user equipment, information for configuring location measurement; receiving, from the user equipment, first inference information about the location of the user equipment, the information being generated by using a first AI model located in the user equipment; and generating, on the basis of the first inference information, second inference information about the location of the user equipment by using a second AI model located in the base station.

Description

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

[0001] The present disclosure relates generally to wireless communication systems, and more particularly to a method and apparatus for performing position measurement based on an artificial intelligence (AI) model in a wireless communication system.

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

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

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

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

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

[0007] In wireless communication systems, artificial intelligence (AI) models can be used to measure the location of a terminal. To address security and overhead issues and achieve more precise location measurements, a two-sided AI model can be used. Accordingly, a method for measuring terminal location based on a two-sided AI model that includes both the terminal and the network is being considered.

[0008] According to various embodiments of the present disclosure, an object is to provide a device and method capable of effectively providing a service in a wireless communication system.

[0009] The technical problems to be achieved in this document are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0010] According to various embodiments of the present disclosure, in a wireless communication system, a method performed by a base station may include the steps of transmitting information for setting a location measurement to a user equipment, receiving, from the user equipment, first inference information about a location of the user equipment generated using a first AI model located in the user equipment, and generating, based on the first inference information, second inference information about a location of the user equipment using a second AI model located in the base station.

[0011] According to various embodiments of the present disclosure, in a wireless communication system, a method performed by a user equipment (UE) may include the steps of: receiving information for setting a location measurement from a base station; receiving, from the base station, first inference information about a location of the UE using a first artificial intelligence (AI) model located at the base station; and generating, based on the first inference information, second inference information about a location of the UE using a second AI model located at the UE.

[0012] According to various embodiments of the present disclosure, in a wireless communication system, a base station may include a transceiver and a controller coupled to the transceiver, and the controller may be configured to transmit information for setting a location measurement to a user equipment, receive, from the user equipment, first inference information about a location of the user equipment generated using a first AI model located in the user equipment, and generate second inference information about a location of the user equipment using a second AI model located in the user equipment based on the first inference information.

[0013] According to various embodiments of the present disclosure, in a wireless communication system, a user equipment (UE) may include a transceiver and a controller coupled to the transceiver, and the controller may be configured to receive, from a base station, information for setting a location measurement, receive, from the base station, first inference information about a location of the UE using a first artificial intelligence (AI) model located at the base station, and generate second inference information about a location of the UE using a second AI model located at the UE based on the first inference information.

[0014] According to various embodiments of the present disclosure, an object is to provide a device and method capable of effectively providing a service in a wireless communication system.

[0015] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0016] FIG. 1 illustrates a wireless communication system according to various embodiments of the present disclosure.

[0017] FIG. 2 illustrates a configuration of a base station in a wireless communication system according to various embodiments of the present disclosure.

[0018] FIG. 3 illustrates a configuration of a terminal in a wireless communication system according to various embodiments of the present disclosure.

[0019] FIG. 4 illustrates the flow of signals between a base station and a terminal for training or transferring an artificial intelligence (AI) model according to various embodiments of the present disclosure.

[0020] FIG. 5 illustrates a block diagram for cross-sectional AI model-based position measurement and double-sided AI model-based position measurement according to various embodiments of the present disclosure.

[0021] FIG. 6A illustrates the flow of signals between a base station and a terminal for network-first two-sided AI model-based location measurement according to various embodiments of the present disclosure.

[0022] FIG. 6b illustrates an operational flow of a base station for network-first two-sided AI model-based positioning according to various embodiments of the present disclosure.

[0023] FIG. 7A illustrates the flow of signals between a base station and a terminal for UE-first two-sided AI model-based location measurement according to various embodiments of the present disclosure.

[0024] FIG. 7b illustrates a terminal operation flow for UE-first two-sided AI model-based location measurement according to various embodiments of the present disclosure.

[0025] FIG. 8 illustrates the operation flow of various examples for two-sided AI model-based position measurement according to various embodiments of the present disclosure.

[0026] FIGS. 9A and 9B illustrate the flow of signals between a base station and a terminal for location measurement based on measurement information and a one-sided AI model according to various embodiments of the present disclosure.

[0027] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0028] The various embodiments of the present disclosure described below illustrate a hardware-based approach as an example. However, since the various embodiments of the present disclosure include techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0029] In the following description, terms referring to components of the device (control unit, controller, processor, artificial intelligence (AI) model, neural network (NN) model, etc.) and terms referring to data (signal, feedback, report, reporting, information, parameter, value, bit, codeword, etc.) are examples for convenience of explanation. Therefore, the present disclosure is not limited to the terms described below, and other terms having similar or equivalent technical meanings may be used.

[0030] Additionally, while this disclosure describes various embodiments using terminology used in certain communication standards (e.g., 3rd Generation Partnership Project (3GPP)), these are merely illustrative examples. The various embodiments of this disclosure can be easily modified and applied to other communication systems.

[0031] FIG. 1 illustrates a wireless communication system according to various embodiments of the present disclosure. FIG. 1 illustrates a base station (110), a terminal (120), and a terminal (130) as some of the nodes utilizing a wireless channel in the wireless communication system. While FIG. 1 illustrates only one base station, other base stations identical to or similar to base station (110) may be included.

[0032] The base station (110) is a network infrastructure that provides wireless access to terminals (120, 130). The base station (110) has coverage defined as a certain geographical area based on the distance at which a signal can be transmitted. In addition to the base station, the base station (110) may be referred to as an 'access point (AP)', 'eNodeB (eNB)', 'gNodeB (gNB)', '5th generation node', '6th generation node', 'wireless point', 'transmission / reception point (TRP)', or other terms having equivalent technical meanings.

[0033] Each of the terminals (120) and (130) is a device used by a user and communicates with the base station (110) via a wireless channel. In some cases, at least one of the terminals (120) and (130) may be operated without the user's intervention. That is, at least one of the terminals (120) and (130) is a device that performs machine type communication (MTC) and may not be carried by the user. Each of the terminal (120) and the terminal (130) may be referred to as a 'terminal', 'user equipment (UE),' 'mobile station,' 'subscriber station,' 'customer premises equipment (CPE),' 'remote terminal,' 'wireless terminal,' 'electronic device,' or 'user device,' or other terms having similar or equivalent technical meanings thereto.

[0034] The base station (110), the terminal (120), and the terminal (130) can transmit and receive wireless signals in the millimeter wave (mmWave) band (e.g., 28 GHz, 30 GHz, 38 GHz, 60 GHz, over 60 GHz, etc.). At this time, in order to improve the channel gain, the base station (110), the terminal (120), and the terminal (130) can perform beamforming. Here, the beamforming can include transmission beamforming and reception beamforming. That is, the base station (110), the terminal (120), and the terminal (130) can provide directionality to the transmission signal or the reception signal. To this end, the base station (110) and the terminals (120, 130) can select serving beams (112, 113, 121, 131) through a beam search or beam management procedure. After serving beams (112, 113, 121, 131) are selected, subsequent communication can be performed through resources that are in a QCL (quasi co-located) relationship with the resources that transmitted the serving beams (112, 113, 121, 131).

[0035] FIG. 2 illustrates a configuration of a base station in a wireless communication system according to various embodiments of the present disclosure. According to various embodiments of the present disclosure, the base station (110) may be conveniently referred to as a network. The configuration illustrated in FIG. 2 may be understood as the configuration of the base station (110). Terms such as "... unit" and "... unit" used hereinafter refer to a unit that processes at least one function or operation, and this may be implemented by hardware, software, or a combination of hardware and software.

[0036] Referring to FIG. 2, the base station (110) may include a wireless communication unit (210), a backhaul communication unit (220), a storage unit (230), and a control unit (240).

[0037] The wireless communication unit (210) performs functions for transmitting and receiving signals through a wireless channel. For example, the wireless communication unit (210) performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the wireless communication unit (210) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the wireless communication unit (210) restores a reception bit stream by demodulating and decoding a baseband signal. In addition, the wireless communication unit (210) up-converts a baseband signal into an RF (radio frequency) band signal and transmits it through an antenna, and down-converts an RF band signal received through the antenna into a baseband signal.

[0038] To this end, the wireless communication unit (210) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a digital to analog convertor (DAC), an analog to digital convertor (ADC), etc. In addition, the wireless communication unit (210) may include a plurality of transmission and reception paths. Furthermore, the wireless communication unit (210) may include at least one antenna array composed of a plurality of antenna elements. In terms of hardware, the wireless communication unit (210) may be composed of a digital unit and an analog unit, and the analog unit may be composed of a plurality of sub-units according to operating power, operating frequency, etc.

[0039] The wireless communication unit (210) can transmit and receive signals. To this end, the wireless communication unit (210) may include at least one transceiver. For example, the wireless communication unit (210) may transmit a synchronization signal, a reference signal, system information, messages, control information, or data. In addition, the wireless communication unit (210) may perform beamforming.

[0040] The wireless communication unit (210) transmits and receives signals as described above. Accordingly, all or part of the wireless communication unit (210) may be referred to as a "transmitter," a "receiver," or a "transmitting and receiving unit." Furthermore, in the following description, transmission and reception performed via a wireless channel are used to mean that the wireless communication unit (210) performs the processing described above.

[0041] The backhaul communication unit (220) provides an interface for performing communication with other nodes within the network. That is, the backhaul communication unit (220) converts a bit string transmitted from the base station (110) to another node, such as another access node, another base station, an upper node, a core network, etc., into a physical signal, and converts a physical signal received from another node into a bit string.

[0042] The storage unit (230) stores data such as basic programs, application programs, and setting information for the operation of the base station (110). The storage unit (230) may include a memory. The storage unit (230) may be configured as a volatile memory, a non-volatile memory, or a combination of volatile and non-volatile memories. In addition, the storage unit (230) provides the stored data according to a request from the control unit (240). According to one embodiment, the storage unit (230) may store learning data for AI-based position measurement and apply the stored learning data to a neural network structure of AI-based position measurement.

[0043] The control unit (240) controls the overall operations of the base station (110). For example, the control unit (240) transmits and receives signals through the wireless communication unit (210) or the backhaul communication unit (220). In addition, the control unit (240) can record and read data in the storage unit (230). In addition, the control unit (240) can perform the functions of the protocol stack required by the communication standard. To this end, the control unit (240) can include at least one controller or processor. According to various embodiments, the control unit (240) can control the base station to perform operations according to various embodiments described below.

[0044] The configuration of the base station (110) illustrated in FIG. 2 is merely an example of a base station, and examples of base stations that perform various embodiments of the present disclosure are not limited to the configuration illustrated in FIG. 2. That is, some configurations may be added, deleted, or changed according to various embodiments.

[0045] Although the base station is described as a single entity in FIG. 2, the present disclosure is not limited thereto. The base station according to various embodiments of the present disclosure may be implemented to form an access network having not only an integrated deployment but also a distributed deployment. According to one embodiment, the base station may be divided into a central unit (CU) and a digital unit (DU), and the CU may be implemented to perform upper layer functions (e.g., radio link control (RLC), packet data convergence protocol (PDCP), and radio resource control (RRC)) and the DU may be implemented to perform lower layer functions (e.g., medium access control (MAC), physical (PHY)). The DU of the base station may form beam coverage on a wireless channel.

[0046] FIG. 3 illustrates the configuration of a terminal in a wireless communication system according to various embodiments of the present disclosure. The configuration illustrated in FIG. 3 can be understood as the configuration of terminals (120, 130). Terms such as "...unit" and "...unit" used hereinafter refer to a unit that processes at least one function or operation, which can be implemented using hardware, software, or a combination of hardware and software.

[0047] Referring to FIG. 3, the terminal (120, 130) may include a communication unit (310), a storage unit (320), and a control unit (330).

[0048] The communication unit (310) performs functions for transmitting and receiving signals via a wireless channel. For example, the communication unit (310) performs a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the communication unit (310) generates complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the communication unit (310) restores a reception bit stream by demodulating and decoding the baseband signal. In addition, the communication unit (310) up-converts a baseband signal into an RF band signal and then transmits it through an antenna, and down-converts an RF band signal received through the antenna into a baseband signal. For example, the communication unit (310) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc.

[0049] In addition, the communication unit (310) may include a plurality of transmission and reception paths. Furthermore, the communication unit (310) may include an antenna unit. The communication unit (310) may include at least one antenna array composed of a plurality of antenna elements. In terms of hardware, the communication unit (310) may be composed of digital circuits and analog circuits (e.g., radio frequency integrated circuits (RFIC)). Here, the digital circuits and analog circuits may be implemented in a single package. In addition, the communication unit (310) may include a plurality of RF chains. The communication unit (310) may perform beamforming. The communication unit (310) may apply beamforming weights to a signal to be transmitted and received in order to impart directionality according to the settings of the control unit (330). According to one embodiment, the communication unit (310) may include an RF (radio frequency) block (or RF unit). The RF block may include first RF circuitry associated with the antenna and second RF circuitry associated with baseband processing. The first RF circuitry may be referred to as RF-A (antenna). The second RF circuitry may be referred to as RF-B (baseband).

[0050] In addition, the communication unit (310) can transmit and receive signals. For this purpose, the communication unit (310) can include at least one transceiver. The communication unit (310) can receive a downlink signal. The downlink signal can include a synchronization signal (SS), a reference signal (RS) (e.g., a cell-specific reference signal (CRS), a demodulation (DM)-RS), system information (e.g., MIB, SIB, remaining system information (RMSI), other system information (OSI)), a configuration message, control information, or downlink data. In addition, the communication unit (310) can transmit an uplink signal. The uplink signal may include a random access related signal (e.g., a random access preamble (RAP) (or Msg1 (message 1)), Msg3 (message 3)), a reference signal (e.g., a sounding reference signal (SRS), DM-RS), or a power headroom report (PHR).

[0051] Additionally, the communication unit (310) may include different communication modules to process signals of different frequency bands. Furthermore, the communication unit (310) may include multiple communication modules to support multiple different wireless access technologies. For example, different wireless access technologies may include Bluetooth low energy (BLE), wireless fidelity (Wi-Fi), WiGig (WiFi gigabyte), cellular networks (e.g., long term evolution (LTE), new radio (NR), etc.). In addition, different frequency bands may include super high frequency (SHF) (e.g., 2.5 GHz, 5 GHz) bands, millimeter wave (mm wave) (e.g., 38 GHz, 60 GHz, etc.) bands. In addition, the communication unit (310) may use the same type of wireless access technology on different frequency bands (e.g., unlicensed bands for licensed assisted access (LAA), citizens broadband radio service (CBRS) (e.g., 3.5 GHz)).

[0052] The communication unit (310) transmits and receives signals as described above. Accordingly, all or part of the communication unit (310) may be referred to as a "transmitter," a "receiver," or a "transmitting and receiving unit." Furthermore, in the following description, transmission and reception performed via a wireless channel are used to mean processing performed by the communication unit (310) as described above.

[0053] The storage unit (320) stores data such as basic programs, application programs, and setting information for the operation of the terminal (120). The storage unit (320) may be configured as volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. In addition, the storage unit (320) provides the stored data upon request from the control unit (330). In one embodiment, the storage unit (320) may store learning data for AI-based position measurement according to AI parameters or position measurement settings set by the base station.

[0054] The control unit (330) controls the overall operations of the terminal (120, 130). For example, the control unit (330) transmits and receives signals through the communication unit (310). In addition, the control unit (330) can record and read data in the storage unit (320). In addition, the control unit (330) can perform the functions of the protocol stack required by the communication standard. To this end, the control unit (330) may include at least one controller or processor. The control unit (330) may include at least one processor or microprocessor, or may be a part of a processor. In addition, a part of the communication unit (310) and the control unit (330) may be referred to as a CP (cellular processor). The control unit (330) may include various modules for performing communication. According to various embodiments, the control unit (330) may control the terminal to perform operations according to various embodiments described below.

[0055] The configuration of the terminals (120, 130) illustrated in FIG. 3 is merely an example of a terminal, and examples of terminals performing various embodiments of the present disclosure are not limited to the configuration illustrated in FIG. 3. That is, some configurations may be added, deleted, or changed according to various embodiments.

[0056] According to various embodiments of the present disclosure, the following describes an AI model included in a base station (110) or a terminal (120, 130). According to one embodiment, the base station (110) or the terminal (120, 130) may include an AI (artificial intelligence) model. According to one embodiment, an AI model learned based on a neural network may be operated through a control unit (240, 330) and a storage unit (230, 320) of the terminal (120, 130) or the base station (110). At this time, the control unit (240, 330) may be composed of one or more processors. The one or more processors may include the functions of a general-purpose processor such as a CPU, an application processor (AP), a digital signal processor (DSP), a graphics-only processor such as a GPU (graphics processing unit), a VPU (vision processing unit), or an artificial intelligence-only processor such as an NPU. One or more processors can be controlled to process input data according to predefined operating rules or artificial intelligence models stored in the storage unit (230, 320). Alternatively, if one or more processors are dedicated artificial intelligence processors, the dedicated artificial intelligence processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model. The dedicated artificial intelligence processors may not be included in the control unit (240, 330) but may be included as a separate component.

[0057] According to one embodiment, the predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rule or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed in the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above. The control unit (240, 330) may learn an occurring event, a determined judgment, or collected or input information through the learning algorithm. The control unit (240, 330) may store the learning results in the storage unit (230, 320) (e.g., memory).

[0058] An artificial intelligence model (AI model) may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the AI ​​model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the AI ​​model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a long short term memory (LSTM), or deep Q-Networks.

[0059] In one embodiment, the control unit (240, 330) may execute an algorithm for performing operations related to AI-based positioning (e.g., for convenience of explanation, interchangeably used with position measurement, position calculation, etc.). In one embodiment, an AI model learned to perform operations related to AI-based position measurement may be configured as hardware in the control unit (240, 330), included as software, or configured through a combination of hardware and software. In other words, the control unit (240, 330) may include a control unit for AI-based position measurement. The control unit for AI-based position measurement may perform prediction of AI-based position, identification of predicted performance for position, determination of whether to report the identified result, and determination of whether to use AI-based position calculation. In addition, according to various embodiments, the control unit (240, 330) may include an update unit. The update unit can obtain data updated by the base station alone or by a learning procedure between the terminal and the base station (e.g., data related to the position measurement results between the terminal and the base station), and reconfigure the values ​​of parameters constituting the neural network (e.g., neural network structure, node layer-by-layer information, weight information between nodes) based on the data. Signaling for setting the parameters constituting the neural network is described in detail below according to various embodiments of the present disclosure. The AI-based position measurement control unit and the update unit may be a set of commands or codes stored in the storage unit (230, 320), and may be commands / codes or a storage space that stores commands / codes that are at least temporarily resided in the control unit (240, 330), or may be a part of the circuitry constituting the control unit (240, 330).According to various embodiments, the control unit (240, 330) can control the base station (110) or the terminal (120, 130) to perform operations according to various embodiments described below.

[0060] According to various embodiments of the present disclosure, various technical contents for performing positioning (hereinafter, interchangeably with position measurement, position calculation, etc.) of a terminal are described below.

[0061] According to various embodiments, a method using positioning signals transmitted through downlink and uplink of a terminal and a base station in the present disclosure may be referred to as RAT (Radio Access Technology) dependent positioning. In addition, other positioning methods may be referred to as RAT-independent positioning. Specifically, in the case of an LTE system, RAT-dependent positioning techniques may include methods such as Observed Time Difference Of Arrival (OTDOA), Uplink Time Difference Of Arrival (UTDOA), or Enhanced Cell Identification (E-CID). In the case of an NR system, methods such as Downlink Time Difference Of Arrival (DL-TDOA), Downlink Angle-of-Departure (DL-AOD), Multi-Round Trip Time (Multi-RTT), NR E-CID, Uplink Time Difference Of Arrival (UL-TDOA), and Uplink Angle-of-Arrival (UL-AOA) may be included. In contrast, RAT-independent positioning techniques may include methods such as Assisted Global Navigation Satellite Systems (A-GNSS), Sensors, Wireless Local Area Networks (WLAN), and Bluetooth.

[0062] According to various embodiments, for RAT-dependent positioning in the interface between a base station and terminals (e.g., uplink and downlink, hereinafter referred to as Uu), a positioning protocol such as LPP (LTE Positioning Protocol), LPPa (LTE Positioning Protocol Annex), or NRPPa (NR Positioning Protocol Annex) may be used. LPP may be regarded as a positioning protocol defined between a terminal and a location server (LS), and LPPa or NRPPa may be regarded as a protocol defined between a base station and a location server. Here, the location server is an entity that manages location measurements and may perform the function of a Location Management Function (LMF). The location server may also be referred to as LMF or another name. For both LTE and NR systems, LPP may be supported.

[0063] According to various embodiments, the positioning protocol defined between a base station and a location server may be referred to as LPPa in an LTE system. According to one embodiment, the positioning protocol defined between a base station and a location server may be referred to as NRPPa in an NR system, and various functions may be additionally performed, including the roles performed by LPPa described above.

[0064] According to various embodiments, NR systems may support more positioning techniques than LTE systems. Therefore, various positioning techniques may be supported through the aforementioned positioning information transmission. For example, while positioning is performed cell-wise in LTE systems, NR systems may perform positioning based on TRPs. Therefore, information related to TRP-based positioning may be exchanged between terminals, base stations, or location servers.

[0065] According to various embodiments of the present disclosure, general location measurement (e.g., positioning) is discussed in Rel-16 and Rel-17 of 3GPP standards for position estimation in user cases and commercial use cases of the industrial internet of things (IIoT), which is an application service of 5G communication. According to one embodiment, recent standards aim to have target horizontal positioning accuracies of within 0.2 m (e.g., 90% accuracy) for IIoT and within 1 m (e.g., 90% accuracy) for commercial use cases. To this end, as mentioned above, the standard introduces RAT-dependent positioning techniques in Rel-16, various accuracy improvement schemes in Rel-17, and sidelink positioning, carrier phase positioning, and bandwidth aggregation schemes in Rel-18. Furthermore, methods to achieve high positioning accuracy in various scenarios, including heavy non-line-of-sight (NLOS) environments, through AI-based positioning approaches are continuously being discussed.

[0066] Most 3GPP positioning methods, except for some UE-based positioning methods, involve location management function (LMF)-based positioning.

[0067] As described above, in this LMF-based positioning, the LMF can exchange information with the terminal via LPP and with the base station (e.g., gNB) via NRPPa. To this end, the LMF can provide assistance data to the terminal via LPP and receive capability reports, location information (e.g., measurement results, absolute positions), etc. from the terminal. In addition, the LMF can provide assistance data to the base station via NRPPa and receive cell information, measurement results, etc. from the base station. The position measurement techniques using the above-described terminal / base station proprietary measurements may be conveniently referred to as legacy positioning methods hereinafter.

[0068] Positioning methods may include RAT-dependent positioning (E-CID, DL-TDoA, UL-TDoA, DL-AoD, UL-AoA), RAT-independent positioning (GNSS, WLAN, Bluetooth, Terrestrial beacon system, Barometric pressure sensor, Motion sensor), etc. However, the non-AI based positioning methods discussed so far may have significantly reduced accuracy in heavy NLOS scenarios. In other words, due to the absence of multiple LOS paths, non-AI based positioning techniques may have the disadvantage of not being able to perform well in terms of accuracy, and positioning techniques using AI networks may be discussed to complement this.

[0069] According to various embodiments of the present disclosure, an artificial intelligence (AI) / machine learning (ML) based approach is more efficient than a non-AI based approach in terms of feature extraction, environment awareness, and complex problem modeling / processing. A location measurement method and device using the AI / ML based approach are described in detail below.

[0070] According to various embodiments of the present disclosure, AI-based positioning techniques may be used to improve accuracy and perform more environmentally adaptive positioning, as described above. AI-based positioning techniques may include one-sided AI model-based positioning, specific examples of which are provided below.

[0071] - Case 1: UE-based positioning with UE-side model, which may include direct AI / ML or AI / ML assisted positioning.

[0072] - Case 2a: UE-assisted / LMF-based positioning with UE-side model, which may include AI / ML assisted positioning.

[0073] - Case 2b: UE-assisted / LMF-based positioning with LMF-side model, which may include direct AI / ML positioning.

[0074] - Case 3a: NG-RAN node assisted positioning with gNB-side model, which may include AI / ML assisted positioning.

[0075] - Case 3b: NG-RAN node assisted positioning with LMF-side model, which may include direct AI / ML positioning.

[0076] According to the various specific examples described above, in the case of single-sided AI model-based positioning, position measurement can be performed solely using terminal or base station measurement results. However, if the process of transmitting terminal (or base station) measurement results to train a single-sided AI model as described above is performed, security / privacy issues may arise due to the transmission of position-related data, or overhead issues due to the transmission of raw data.

[0077] According to various embodiments of the present disclosure, a two-sided AI model-based positioning technique may be considered to solve the above-described problem. For example, the following various embodiments disclose a method and apparatus for designing a system in which a terminal and a network (e.g., a base station) perform positioning based on a one-sided or two-sided AI model to solve the above-described problem. More specifically, the following embodiments describe a procedure in which a network notifies a terminal of a positioning type according to the requirements of a positioning application (e.g., a terminal or a base station), and an information exchange procedure for two-sided model positioning inference. In addition, various embodiments of the present disclosure disclose a method for more efficient and accurate location measurement without separate intervention of a core network entity such as an LMF, thereby suggesting a solution for solving security / privacy issues, overhead issues, or UE-side model complexity issues.

[0078] Figure 4 illustrates the signal flow between a base station and a terminal for training or transferring an artificial intelligence (AI) model according to various embodiments of the present disclosure. More specifically, AI-based positioning techniques can be used to achieve high-accuracy location measurements in environments including heavy NLOS scenarios.

[0079] In step (410), the terminal may transmit information regarding terminal capabilities to a base station (e.g., a network). In one embodiment, the terminal capability information transmitted by the terminal may include information regarding an AI model included in the terminal. For example, the terminal may transmit information regarding the AI ​​model, including whether the AI ​​model deployed on the terminal can be used, the performance and available capacity of the AI ​​model on the terminal side, to the base station.

[0080] In step (420), the terminal or the base station may collect data for location measurement. According to one embodiment, the terminal or the base station may collect a data set for training an AI model, and the data set may include terminal measurement results (e.g., UE measurements). For example, the terminal may transmit to the base station a data set including measurement results regarding at least one of a channel impulse response (CIR), a reference signal time difference (RSTD), a downlink-positioning reference signal (DL-PRS), a reference signal received power (RSRP), or a power delay profile (PDP). The data set that the terminal collects for AI model training and transmits to the base station may be transmitted in a format such as {training input, training label} = {CIR, location}. However, according to various embodiments of the present disclosure, the above-described data set or measurement result information is merely an example, and various measurement results that can be measured on the terminal side, including positioning measurement results by PRS or various reference signals, may be included without limitation.

[0081] In step (430), the base station may train an AI model for positioning. For example, the base station may train an AI / ML model based on a data set received from the terminal. According to various embodiments, the AI ​​model trained by the base station may include various models that function through various neural network algorithms.

[0082] In step (440), the base station may transmit the trained AI model to the terminal. In one embodiment, the AI ​​model information transmitted by the base station may include at least one of information for deploying the trained AI model itself to the terminal, or information for updating an AI model already deployed to the terminal.

[0083] In step (450), the terminal may perform location estimation using input values ​​for location measurement based on an AI model deployed on the terminal. In one embodiment, the terminal may obtain location inference results based on the trained AI model.

[0084] As described above, a specific process for an AI model-based positioning method for more accurate location measurement in heavy NLOS situations is disclosed, and this can be applied not only to terminal-side AI models but also to positioning techniques using cross-sectional AI models at the base station or LMF side. However, even in this case, as described above, since raw data, such as measurement results, are transmitted and received, security and privacy issues may arise. In addition, since measurements and inferences are ultimately made at one entity, either the terminal, base station, or LMF, it may be difficult to obtain sufficient results in terms of accuracy.

[0085] FIG. 5 illustrates a block diagram for single-sided AI model-based positioning and double-sided AI model-based positioning according to various embodiments of the present disclosure. More specifically, in addition to single-sided AI positioning, double-sided AI positioning techniques are described according to various embodiments of the present disclosure.

[0086] Referring to the block diagram (510) for cross-sectional AI model-based position measurement, the terminal-side AI model can acquire terminal measurement results as model input and perform AI-based positioning inference. The general process by which the terminal acquires an estimated position is specifically described in FIG. 4.

[0087] According to various embodiments of the present disclosure, a positioning technique may be performed in which both a single-sided AI model and a base station-side AI model are used for AI model-based position measurement. Referring to a block diagram (520) for double-sided AI model-based position measurement, a terminal-side AI model may obtain a terminal measurement result as a model input, perform AI-based positioning inference, and obtain an intermediate AI feature as a result thereof. According to one embodiment, unlike a single-sided AI model-based positioning process, the terminal may transmit the obtained intermediate AI feature to the base station instead of the measurement result, and the base station may perform AI-based positioning inference by considering both the intermediate AI feature received from the terminal and the base station measurement result (e.g., gNB measurement) as inputs.

[0088] As shown in block diagram (520), when performing double-sided AI positioning, the terminal or base station can utilize both terminal measurement results (UE measurements) (e.g., RSTD, DL-PRS RSRP, CIR, or PDP) and network measurement results (network (NW) measurements) (e.g., relative time of arrival (RTOA), uplink-sounding reference signal (UL-SRS) RSRP, or UL-AoA). Accordingly, AI positioning techniques based on block diagram (520) according to various embodiments of the present disclosure can be expected to have improved performance compared to single-sided AI positioning, and can also solve security / privacy issues in that terminal (or base station) measurement results are transmitted through encrypted intermediate AI characteristics.

[0089] According to various embodiments of the present disclosure, as described above, by utilizing two-sided AI positioning, efficiency improvements can be expected in high-reliability use cases or private (personal) positioning use cases.

[0090] According to various embodiments of the present disclosure, a method for a terminal and a network to perform positioning based on a one-sided or two-sided AI model may basically include the following procedures.

[0091] 1. A procedure in which a base station informs a terminal of the positioning type according to the requirements of the positioning application.

[0092] - The positioning type may include at least one of legacy, single-sided AI, or double-sided AI.

[0093] 2. Procedure for exchanging information necessary for positioning a two-sided AI model.

[0094] - Information exchanged for AI model positioning may include at least one of a UE capability report, a positioning type, or information about an AI model deployed on the terminal.

[0095] As described above, the specific processes by which a terminal or base station acquires an estimated location based on a two-sided AI model are described below. However, depending on various embodiments, the steps described below may not all be considered essential components, and some steps may be omitted. In other words, the embodiments described below may be performed by including at least one of all, some, or a combination of the steps.

[0096] Figure 6a illustrates the signal flow between a base station and a terminal for network-first, two-sided AI model-based positioning according to various embodiments of the present disclosure. More specifically, Figure 6a illustrates a process in which positioning is performed primarily by an AI model deployed at the terminal, and then positioning is performed based on this by an AI model deployed at the base station.

[0097] In step (610), the terminal may report terminal capability information to the base station. In one embodiment, the capability information transmitted by the terminal to the base station may include capability information regarding an AI model or AI model inference included in the terminal.

[0098] According to various embodiments of the present disclosure, the terminal capability information may include at least one of information regarding whether the terminal supports AI (e.g., whether a terminal-side AI model is deployed) according to the degree of terminal implementation, performance-related capabilities of the terminal-side AI model (e.g., AI computing capabilities), size-related capabilities of the terminal-side AI model, supportable model representation formats (MRFs) of the terminal-side AI model, or information regarding whether to report when resource restrictions due to heat generation, power, etc. occur (or are resolved). Here, the information regarding whether to report resource restrictions may include information operating depending on whether the terminal will perform a power saving mode for the terminal-side AI model or connect or disconnect the power connection when the resource restrictions occur or are resolved. According to one embodiment, the performance-related capabilities of the AI ​​model may include information regarding at least one of input / output (I / O) memory bandwidth or AI-driven floating-point operations per second (FLOPS), and the AI ​​model size-related capabilities may include at least one of AI model parameters, information regarding memory, or information regarding storage. According to various embodiments of the present disclosure, the information included in the capability information of the terminal is not limited to the examples or names described above, and may further include various information required by the base station to drive the AI ​​model of the terminal, as long as it has an equivalent or similar function.

[0099] According to various embodiments of the present disclosure, a terminal may transmit capability information of the terminal to a base station through various methods. According to one embodiment, the terminal may directly transmit capability information including all information regarding the terminal's capabilities to the base station. According to one embodiment, the terminal may transmit whether an AI model on the terminal side is operable through a 1-bit indicator. According to one embodiment, the terminal may transmit information indicating a category to the base station using a table in which the capabilities of the terminal-side AI model are predefined by category. The table in which the capabilities of the terminal-side AI model are predefined by category may be preset for the terminal and the base station. Table 1 below illustrates an example in which terminal capability information is predefined as a table by category.

[0100]

[0101] However, according to various embodiments of the present disclosure, the format of the capability information of the terminal in Table 1 described above is only an example, and the category table used by the terminal to transmit the capability information may further include various parameter information such as whether an AI model is in operation, whether to report on resource constraints, etc., in addition to the described FLOPS and AI memory, and the format of transmitting the capability information of the terminal may be transmitted by being included in one of the various parameters of the terminal capability information defined in the existing 3GPP, in addition to an instruction through a bit or category.

[0102] In step (620), the base station may transmit positioning parameter settings to the terminal. More specifically, the base station may generate configuration information for positioning measurements as follows based on terminal capability information received from the terminal, and configure the same to the terminal. In one embodiment, although not illustrated in FIG. 6A, the base station may also transmit information for configuring terminal-specific position measurements of the terminal (e.g., measurement configuration information for legacy position measurements) to the terminal.

[0103] According to various embodiments of the present disclosure, a base station may set a positioning type for a terminal. Here, the positioning type may include at least one of a non-AI-based legacy positioning type, a single-sided AI model-based positioning type, or a two-sided AI model-based positioning type. According to one embodiment, the base station may identify the positioning type based on terminal capability information, the accuracy required for position measurement, or the subject of the positioning application (e.g., the terminal or base station that is the subject of positioning). Here, in addition to the terminal capability information, the base station may obtain additional information about the terminal, or may identify the accuracy required for position measurement in advance based on at least one of information received from the core network, or information about the communication environment identified by the base station. In addition, the subject of positioning considered for identifying the positioning type may include the subject performing (or performing first) positioning based on the AI ​​model (e.g., the entity requesting positioning information). For example, in situations where a terminal requires real-time location information, such as in a navigation application, the subject of positioning may be the terminal itself. Alternatively, in situations requiring indoor positioning, such as in a smart factory, the subject of positioning may be the base station.

[0104] According to various embodiments of the present disclosure, a base station may predefine the positioning type to be set to a terminal as a type by index as shown in Table 2 below.

[0105]

[0106] According to Table 2 described above, for example, index #0 may mean that when the AI ​​model on the terminal side cannot be operated, positioning is set to be performed using a legacy method; index #1 may mean that when the AI ​​model on the terminal side can be operated, single-sided positioning based on the AI ​​model on the base station side is set to be performed; index #2 may mean that when the AI ​​model on the terminal side can be operated, single-sided positioning based on the AI ​​model on the terminal side is set to be performed; index #3 may mean that when the AI ​​model on the terminal side can be operated, positioning is set to be performed using the AI ​​model on the terminal side first among two-sided positioning based on both the AI ​​models on the terminal side and the base station side; and index #4 may mean that when the AI ​​model on the terminal side can be operated, positioning is set to be performed using the AI ​​model on the base station side first among two-sided positioning based on both the AI ​​models on the terminal side and the base station side. A table in which the positioning types set by the base station to the terminal are predefined by index may be predefined for the terminal and the base station.

[0107] In one embodiment, if positioning types, such as those in Table 2 described above, are predefined, the base station may set an index for at least one positioning type to the terminal. At this time, depending on the system (or communication) environment, the positioning type set by the base station to the terminal may be determined by Table 3 below.

[0108]

[0109] According to Table 3 described above, for example, if the terminal is a low-cost terminal, or if there is no AI model, or if the performance of the AI ​​model is poor, the base station can instruct the terminal to use a non-AI-based positioning technique by setting index #0 among the positioning types. If the accuracy required by the positioning application (e.g., the terminal) is low and there are no required restrictions, the base station can set indices #0 to #2 among the positioning types regardless, or can instruct the terminal to determine its preferred method by setting at least one and all of indices #0 to #2. As described above, the base station can set various positioning types to the terminal through various methods by taking into consideration various circumstances such as terminal-side AI model information of the terminal, system requirements, etc.

[0110] However, according to various embodiments of the present disclosure, the method for setting the positioning type in Tables 2 and 3 described above is merely an example, and it is obvious that the positioning type may be included and transmitted in one of the various parameters of the configuration information of the base station defined in the existing 3GPP, or may be indicated by considering more diverse requirements.

[0111] According to various embodiments of the present disclosure, the information transmitted by the base station to the terminal may further set various information in addition to the positioning type.

[0112] In one embodiment, the base station may configure information related to the terminal-side AI model to the terminal. For example, the base station may instruct the terminal to transmit a trained AI model. At this time, the base station may further configure at least one of the model pool of the AI ​​model for positioning transmitted to the terminal, the AI ​​model identifier, the structure of the AI ​​model, or various parameters related to the AI ​​model (e.g., weights, memory capacity, etc.). The signaling regarding the AI ​​model transmitted from the base station to the terminal may correspond to the steps of FIG. 4. For another example, if the AI ​​model has already been deployed on the terminal side, or the terminal includes an AI model trained for positioning, the base station may transmit only additional information to assist in training the terminal-side AI model. The additional information to assist in training the AI ​​model may include at least one of a reference network-side AI model or reference data sets. As described above, the terminal may receive the AI ​​model directly from the base station, or may receive additional information to assist in training the terminal-side AI model, thereby continuously training the AI ​​model deployed on the terminal.

[0113] In one embodiment, the base station may configure the terminal with measurement information to be used as input to the AI ​​model. More specifically, the base station may configure the terminal to use at least one of CIR, PDP, RSTD, or DL-PRS RSRP as input information for the terminal-side AI model. However, this is merely an example, and any other parameters for the terminal's location measurement results may be included.

[0114] In one embodiment, the base station may set information about the model output inferred by the terminal to the terminal. More specifically, when performing two-sided AI model inference, the base station may first set information about intermediate AI features, which include the output of AI model-based position inference performed by the terminal. For example, as illustrated in FIGS. 6A and 6B , in the case of terminal-first (e.g., UE-first) inference, the base station may set information about the inference output of the terminal-side AI model (e.g., intermediate AI features generated by the terminal) to the terminal. In one embodiment, the base station may further set additional information as information about the intermediate AI feature to the terminal. The additional information set by the base station may set whether the intermediate AI feature is inferred using an encoded latent vector or a soft / hard UE position. Details regarding the intermediate AI feature set by the base station are specifically described with reference to FIG. 8.

[0115] According to various embodiments of the present disclosure, various positioning parameters, including the above-described positioning type, input / output type of the AI ​​model, whether to transmit the AI ​​model, etc., may be set to the terminal in the form of a predefined table as shown in Table 4 below.

[0116]

[0117] According to Table 4 described above, for example, the base station can set at least one of various positioning types, terminal measurement information to be used as input for AI inference, intermediate AI characteristic information, or AI model transmission method to the terminal, taking into account various circumstances such as terminal-side AI model information of the terminal, system requirements, etc. For example, in the case of non-AI-based positioning, AI-related parameters do not need to be set, and in the case of single-sided AI model-based positioning (e.g., PC (parameter configuration) #1 to #3), information about intermediate AI characteristics does not need to be set, and only whether to use terminal measurement for input or transmit an AI model can be set.

[0118] However, according to various embodiments of the present disclosure, the method for setting positioning parameters through the above-described Tables 4 to 3 bits is merely an example, and it can be included in and transmitted as one of various upper parameters of the configuration information of the base station defined in the existing 3GPP, or it can indicate various configuration mapping relationships using more bits. For example, in addition to the table including the mapping relationship, the base station can also transmit each configuration information parameter to the terminal as separate information.

[0119] In step (630), the terminal may perform inference for location measurement using a terminal-side AI model. According to one embodiment, the terminal may obtain an inference result based on positioning information set by the base station and a terminal-proprietary location measurement result. More specifically, the terminal may perform terminal-specific (proprietary) location measurement according to input measurement information set by the base station, and may perform AI model inference using the location measurement result as input. The terminal may generate intermediate AI characteristics as a result of the inference in the form of an output set by the base station. According to one embodiment, the terminal may also train the terminal-side AI model based on information regarding AI model transmission received from the base station and the terminal location measurement result.

[0120] In step (640), the terminal can report the generated intermediate AI characteristics to the base station. Unlike typical measurement results, the intermediate AI characteristics transmitted by the terminal are encrypted, thereby addressing security / privacy issues during the signaling process.

[0121] In step (650), the base station may perform inference for location measurement through the base station-side AI model. According to one embodiment, the base station may obtain an inference result based on the intermediate AI characteristic received from the terminal and the base station-only location measurement result. More specifically, the base station may perform base station-only location measurement, and may perform AI model inference using the base station's location measurement result and the intermediate AI characteristic as input. According to one embodiment, in the case of terminal-first inference as shown in FIGS. 6A and 6B, the base station may perform location measurement (or inference) using the inference output reported by the terminal and the base station-only location measurement result information (e.g., RTOA, UL-SRS RSRP, UL-AoA).

[0122] In this way, the inference result for the location measurement generated by the base station through step (650) can use both the location measurement result of the terminal and the location measurement result of the base station, and thus can have higher accuracy even in an NLOS environment compared to the cross-sectional AI model location measurement.

[0123] Figure 6b illustrates the operational flow of a base station for network-first, two-sided AI model-based positioning according to various embodiments of the present disclosure. More specifically, Figure 6b illustrates a process in which positioning is first performed by an AI model deployed on a terminal, and then positioning is then performed based on this by an AI model deployed on a base station.

[0124] In step (605), the base station may receive terminal capability information. In one embodiment, the capability information transmitted by the terminal to the base station may include capability information regarding an AI model or AI model inference included in the terminal. Step (605) of FIG. 6B may correspond to step (610) of FIG.

[0125] In step (615), the base station may transmit positioning configuration information to the terminal. More specifically, the base station may generate configuration information for various positioning measurements based on terminal capability information received from the terminal and configure this information for the terminal. Step (615) of FIG. 6b may correspond to step (620) of FIG. 6a.

[0126] In step (625), the base station may receive terminal-side AI inference results from the terminal. More specifically, the base station may receive intermediate AI characteristic information generated by the terminal based on positioning information set by the base station and terminal-specific measurement results. Step (625) of FIG. 6b may correspond to steps (630) and (640) of FIG. 6a.

[0127] In step (635), the base station may generate a base station-side AI inference result based on the terminal-side AI inference result and measurement result. More specifically, the base station may perform location measurement dedicated to the base station and perform AI model inference using the base station's location measurement result and intermediate AI characteristics received from the terminal as input. Step (635) of FIG. 6b may correspond to step (650) of FIG. 6a.

[0128] Figure 7a illustrates the signal flow between a base station and a terminal for UE-first, two-sided AI model-based positioning according to various embodiments of the present disclosure. More specifically, Figure 7a illustrates a process in which positioning is performed primarily by an AI model deployed at the base station, and then positioning is performed based on this by an AI model deployed at the terminal.

[0129] In step (710), the base station may receive UE capability information from the terminal. In one embodiment, the capability information received by the base station from the terminal may include capability information regarding an AI model or AI model inference included in the terminal.

[0130] According to various embodiments of the present disclosure, the terminal capability information may include at least one of information regarding whether the terminal supports AI (e.g., whether a terminal-side AI model is deployed) according to the degree of terminal implementation, performance-related capabilities of the terminal-side AI model (e.g., AI computing capabilities), size-related capabilities of the terminal-side AI model, supportable model representation formats (MRFs) of the terminal-side AI model, or information regarding whether to report when resource restrictions due to heat generation, power, etc. occur (or are resolved). Here, the information regarding whether to report resource restrictions may include information operating depending on whether the terminal will perform a power saving mode for the terminal-side AI model or connect or disconnect the power connection when the resource restrictions occur or are resolved. According to one embodiment, the performance-related capabilities of the AI ​​model may include information regarding at least one of input / output (I / O) memory bandwidth or AI-driven floating-point operations per second (FLOPS), and the AI ​​model size-related capabilities may include at least one of AI model parameters, information regarding memory, or information regarding storage. According to various embodiments of the present disclosure, the information included in the capability information of the terminal is not limited to the examples or names described above, and may further include various information required by the base station to drive the AI ​​model of the terminal, as long as it has an equivalent or similar function.

[0131] According to various embodiments of the present disclosure, a base station may receive capability information of a terminal from a terminal through various methods. In one embodiment, the terminal may directly transmit capability information including all information regarding the terminal's capabilities to the base station. In one embodiment, the terminal may transmit whether an AI model on the terminal side is operable through a 1-bit indicator. In one embodiment, the terminal may transmit information indicating a category to the base station using a table in which the capabilities of the terminal-side AI model are predefined by category. The table in which the capabilities of the terminal-side AI model are predefined by category may be preset for the terminal and the base station. Table 1 described above in Figure 6a illustrates an example in which terminal capability information is predefined as a table by category.

[0132] However, according to various embodiments of the present disclosure, the format of the capability information of the terminal described above is only an example, and the category table used by the terminal to transmit the capability information may further include various parameter information such as whether an AI model is in operation, whether to report on resource constraints, in addition to the described FLOPS and AI memory, and the format of transmitting the capability information of the terminal may be transmitted by being included in one of the various parameters of the terminal capability information defined in the existing 3GPP, in addition to an instruction through a bit or category.

[0133] In step (720), the base station may transmit positioning parameter settings to the terminal. More specifically, the base station may generate configuration information for positioning measurements as follows based on terminal capability information received from the terminal, and configure the same to the terminal. In one embodiment, although not illustrated in FIG. 7A, the base station may also transmit information for configuring terminal-specific position measurements of the terminal (e.g., measurement configuration information for legacy position measurements) to the terminal.

[0134] According to various embodiments of the present disclosure, a base station may set a positioning type for a terminal. Here, the positioning type may include at least one of a non-AI-based legacy positioning type, a single-sided AI model-based positioning type, or a two-sided AI model-based positioning type. According to one embodiment, the base station may identify the positioning type based on terminal capability information, the accuracy required for position measurement, or the subject of the positioning application (e.g., the terminal or base station that is the subject of positioning). Here, in addition to the terminal capability information, the base station may obtain additional information about the terminal, or may identify the accuracy required for position measurement in advance based on at least one of information received from the core network, or information about the communication environment identified by the base station. In addition, the subject of positioning considered for identifying the positioning type may include the subject performing (or performing first) positioning based on the AI ​​model (e.g., the entity requesting positioning information). For example, in situations where a terminal requires real-time location information, such as in a navigation application, the terminal may be the subject of positioning. Alternatively, in situations requiring indoor positioning, such as in a smart factory, the subject of positioning may be a base station.

[0135] According to various embodiments of the present disclosure, a base station may predefine the positioning type to be set to a terminal as a type by index as shown in Table 2 described above in FIG. 6a.

[0136] According to Table 2 described above in FIG. 6a, for example, index #0 may mean that when the AI ​​model on the terminal side cannot be operated, positioning is set to be performed using a legacy method, index #1 may mean that when the AI ​​model on the terminal side can be operated, single-sided positioning based on the AI ​​model on the base station side is set to be performed, index #2 may mean that when the AI ​​model on the terminal side can be operated, single-sided positioning based on the AI ​​model on the terminal side is set to be performed, index #3 may mean that when the AI ​​model on the terminal side can be operated, positioning is set to be performed using the AI ​​model on the terminal side first among two-sided positioning based on both the AI ​​models on the terminal side and the base station side, and index #4 may mean that when the AI ​​model on the terminal side can be operated, positioning is set to be performed using the AI ​​model on the base station side first among two-sided positioning based on both the AI ​​models on the terminal side and the base station side. A table in which the positioning types set by the base station to the terminal are predefined by index may be predefined for the terminal and the base station.

[0137] In one embodiment, if positioning types, such as those in Table 2 described above, are predefined, the base station may set an index for at least one positioning type to the terminal. At this time, depending on the system (or communication) environment, the positioning type set by the base station to the terminal may be determined by Table 3 described above in FIG. 6A.

[0138] According to Table 3 described above, for example, if the terminal is a low-cost terminal, or if there is no AI model, or if the performance of the AI ​​model is poor, the base station can instruct the terminal to use a non-AI-based positioning technique by setting index #0 among the positioning types. If the accuracy required by the positioning application (e.g., the terminal) is low and there are no required restrictions, the base station can set indices #0 to #2 among the positioning types regardless, or can instruct the terminal to determine its preferred method by setting at least one and all of indices #0 to #2. As described above, the base station can set various positioning types to the terminal through various methods by taking into consideration various circumstances such as terminal-side AI model information of the terminal, system requirements, etc.

[0139] However, according to various embodiments of the present disclosure, the method for setting the positioning type in Tables 2 and 3 described above is merely an example, and it is obvious that the positioning type may be included and transmitted in one of the various parameters of the configuration information of the base station defined in the existing 3GPP, or may be indicated by considering more diverse requirements.

[0140] According to various embodiments of the present disclosure, the information transmitted by the base station to the terminal may further set various information in addition to the positioning type.

[0141] In one embodiment, the base station may configure information related to the terminal-side AI model to the terminal. For example, the base station may instruct the terminal to transmit a trained AI model. At this time, the base station may further configure at least one of the model pool of the AI ​​model for positioning transmitted to the terminal, the AI ​​model identifier, the structure of the AI ​​model, or various parameters related to the AI ​​model (e.g., weights, memory capacity, etc.). The signaling regarding the AI ​​model transmitted from the base station to the terminal may correspond to the steps of FIG. 4. For another example, if the AI ​​model has already been deployed on the terminal side, or the terminal includes an AI model trained for positioning, the base station may transmit only additional information to assist in training the terminal-side AI model. The additional information to assist in training the AI ​​model may include at least one of a reference network-side AI model or reference data sets. As described above, the terminal may receive the AI ​​model directly from the base station, or may receive additional information to assist in training the terminal-side AI model, thereby continuously training the AI ​​model deployed on the terminal.

[0142] In one embodiment, the base station may configure the terminal with measurement information to be used as input to the AI ​​model. More specifically, the base station may configure the terminal to use at least one of RTOA, UL-SRS RSRP, or UL-AoA as input information for the base station-side AI model. However, this is merely an example, and any other parameters for the base station's location measurement results may be included.

[0143] In one embodiment, the base station may set information about the model output inferred by the base station to the terminal. More specifically, when performing two-sided AI model inference, the base station may set information about intermediate AI features, which include the output of the AI ​​model-based position inference first performed by the base station, to the terminal. For example, as illustrated in FIGS. 7A and 7B , in the case of base station-first (e.g., NW-first) inference, the base station may set information about the inference input of the terminal-side AI model (e.g., the intermediate AI features generated by the base station) to the terminal. In one embodiment, the base station may further set additional information as information about the intermediate AI features to the terminal. The additional information set by the base station may set whether the intermediate AI features are inferred using an encoded latent vector or a soft / hard UE position. Details regarding the intermediate AI features set by the base station are specifically described with reference to FIG. 8.

[0144] According to various embodiments of the present disclosure, various positioning parameters including the positioning type described above, the input / output type of the AI ​​model, whether to transmit the AI ​​model, etc., may be set to the terminal in the form of a predefined table as shown in Table 4 described above in FIG. 6A. However, since FIGS. 7A and 7B are cases of base station-first inference, the output intermediate AI characteristics of Table 4 may include input intermediate AI characteristics to be input to the terminal.

[0145] According to Table 4 described above, for example, the base station can set at least one of various positioning types, terminal measurement information to be used as input for AI inference, intermediate AI characteristic information, or AI model transmission method to the terminal, taking into account various circumstances such as terminal-side AI model information of the terminal, system requirements, etc. For example, in the case of non-AI-based positioning, AI-related parameters do not need to be set, and in the case of single-sided AI model-based positioning (e.g., PC (parameter configuration) #1 to #3), information about intermediate AI characteristics does not need to be set, and only whether to use terminal measurement for input or transmit an AI model can be set.

[0146] However, according to various embodiments of the present disclosure, the method for setting positioning parameters through the above-described Tables 4 to 3 bits is merely an example, and it can be included in and transmitted as one of various upper parameters of the configuration information of the base station defined in the existing 3GPP, or it can indicate various configuration mapping relationships using more bits. For example, in addition to the table including the mapping relationship, the base station can also transmit each configuration information parameter to the terminal as separate information.

[0147] In step (730), the base station may perform inference for location measurement using a base station-side AI model. According to one embodiment, the base station may obtain an inference result based on positioning information set for the terminal and a base station-specific location measurement result. More specifically, the base station may perform base station-specific location measurement and perform AI model inference using the location measurement result as input. The base station may generate intermediate AI characteristics as a result of the inference in the form of an output set for the terminal. According to one embodiment, the terminal may also train the terminal-side AI model based on information regarding AI model transmission transmitted by the base station and the terminal location measurement result.

[0148] In step (740), the base station can transmit the generated intermediate AI characteristics to the terminal. Unlike typical measurement results, the intermediate AI characteristics transmitted by the base station are encrypted, thereby resolving security / privacy issues during the signaling process.

[0149] In step (750), the terminal may perform inference for location measurement through the terminal-side AI model. According to one embodiment, the terminal may obtain an inference result based on the intermediate AI characteristic received from the base station and the terminal-only location measurement result. More specifically, the terminal may perform terminal-only location measurement, and may perform AI model inference using the terminal's location measurement result and the intermediate AI characteristic as input. According to one embodiment, in the case of base station-first inference as shown in FIGS. 7A and 7B, the terminal may perform location measurement (or inference) using the base station's transmitted inference output and terminal-only location measurement result information (e.g., RSTD, DL-PRS RSRP, CIR, PDP).

[0150] In this way, the inference result for the location measurement generated by the terminal through step (750) can use both the location measurement result of the terminal and the location measurement result of the base station, and thus can have higher accuracy even in an NLOS environment compared to the cross-sectional AI model location measurement.

[0151] Figure 7b illustrates a UE-first, two-sided AI model-based positioning flow diagram for a UE according to various embodiments of the present disclosure. More specifically, Figure 7b illustrates a process in which positioning is first performed by an AI model deployed at a base station, and then positioning is then performed based on this by an AI model deployed at the terminal.

[0152] In step (705), the terminal may transmit terminal capability information to the base station. In one embodiment, the capability information transmitted by the terminal to the base station may include capability information regarding an AI model or AI model inference included in the terminal. Step (705) of FIG. 7B may correspond to step (710) of FIG. 7A.

[0153] In step (715), the terminal may receive positioning configuration information from the base station. More specifically, the base station may generate configuration information for various positioning measurements based on terminal capability information received from the terminal and configure the information for the terminal. Step (715) of FIG. 7b may correspond to step (720) of FIG. 7a.

[0154] In step (725), the terminal may receive base station-side AI inference results from the base station. More specifically, the terminal may receive intermediate AI characteristic information generated based on base station-specific measurement results. Step (725) of FIG. 7b may correspond to steps (730) and (740) of FIG. 7a.

[0155] In step (735), the terminal may generate a terminal-side AI inference result based on the base station-side AI inference result and measurement result. More specifically, the terminal may perform terminal-specific location measurement and perform AI model inference using the terminal's location measurement result and intermediate AI characteristics received from the base station as input. Step (735) of FIG. 7b may correspond to step (750) of FIG. 7a.

[0156] FIG. 8 illustrates the operational flow of various examples for two-sided AI model-based positioning according to various embodiments of the present disclosure. More specifically, FIG. 8 specifically describes the intermediate AI characteristics and their settings described in FIGS. 6A to 7B . Furthermore, although FIG. 8 illustrates the case of terminal-first inference, it is of course equally applicable to the case of base station-first inference. In other words, the intermediate AI characteristics disclosed in FIG. 8 may include both cases in which the terminal-side AI model infers as well as cases in which the base station-side AI model infers.

[0157] According to various embodiments of the present disclosure, an intermediate AI characteristic may be inferred and transmitted based on an encoded latent vector (810). In one embodiment, a terminal (or base station) may obtain an inference result through an AI model by inputting a dedicated measurement result. While (810) of FIG. 8 illustrates a CIR as an input for the dedicated measurement result, this is merely an example, and various position measurement parameters may be used depending on whether the terminal is dedicated or the base station is dedicated. In one embodiment, the intermediate AI characteristic inferred using the encoded latent vector may include the inference result in the form of an encrypted latent vector. In order to obtain and transmit the inference result using the latent vector, the dimension of the encoded latent vector must be set by the base station or transmitted as additional information from the terminal or base station. Here, the intermediate AI characteristic (810) inferred and transmitted based on the encoded latent vector may have a relatively high transmission overhead, but may have higher accuracy and stability in terms of security or privacy protection.

[0158] According to various embodiments of the present disclosure, an intermediate AI characteristic may be inferred and transmitted based on a soft UE position (820). In one embodiment, a terminal (or base station) may obtain an inference result through an AI model by inputting a dedicated measurement result. While (820) of FIG. 8 illustrates a CIR as an input for the dedicated measurement result, this is merely an example, and various position measurement parameters may be used depending on whether the terminal is dedicated or the base station is dedicated. In one embodiment, the intermediate AI characteristic inferred based on the soft terminal position may include an inference result as a value based on a grid for soft terminal position mapping. In one embodiment, the value based on the grid for terminal position mapping for the soft terminal position may include a probability of the terminal position predicted by the terminal-side AI model based on the terminal measurement result. In order to obtain and transmit the inference result based on the soft terminal position, the size of each cell of the grid or the overall size of the map (or grid) may be further set by the base station, or may be transmitted as additional information from the terminal or the base station. Here, the intermediate AI characteristic (820) inferred and transmitted according to the soft terminal position can have a relatively low transmission overhead.

[0159] According to various embodiments of the present disclosure, an intermediate AI characteristic may be inferred and transmitted based on a hard UE position (830). In one embodiment, a terminal (or base station) may obtain an inference result through an AI model by inputting a dedicated measurement result. Although (830) of FIG. 8 illustrates a CIR as an input for a dedicated measurement result, this is merely an example, and it is to be understood that various position measurement parameters may be used based on a terminal-only or base station-only configuration. In one embodiment, the intermediate AI characteristic inferred based on a hard UE position may include a value of a terminal position predicted by a terminal-side AI model based on the terminal's measurement result. Here, the intermediate AI characteristic (830) inferred and transmitted based on a hard UE position may require a small amount of data, and thus may have a low transmission overhead.

[0160] According to various embodiments of the present disclosure, as described in FIGS. 6A to 7B , a base station can adaptively determine intermediate AI characteristics based on key performance indicators (KPIs) of a positioning application, and can set information about the determined intermediate AI characteristics to a terminal. For example, in cases where high accuracy and critical security are required, the base station can determine an encoded latent vector as an intermediate AI characteristic and set the terminal accordingly.

[0161] According to various embodiments of the present disclosure, the intermediate AI characteristics and their names illustrated in FIG. 8 are merely examples and are not limited thereto, and the intermediate AI characteristics may further include various AI inference methods for location measurement or positioning in addition to latent vectors or soft / hard terminal positions, and accordingly, it may also include the base station additionally setting the necessary information to the terminal.

[0162] Figures 9a and 9b illustrate signal flows between a base station and a terminal for location measurement based on measurement information and a one-sided AI model according to various embodiments of the present disclosure. Figures 9a and 9b differ from Figures 6a to 7b described above in that the AI ​​model is deployed only in one measurement application to perform inference, but like these, they disclose a technique for using measurement results from both the terminal and the base station as inputs for location estimation.

[0163] Referring to FIG. 9A, in step (905), the terminal may transmit terminal capability information to the base station. According to one embodiment, the terminal capability information transmitted by the terminal to the base station may include various capability information included by the terminal for performing terminal location measurement, which may correspond to step (610) of FIG. 6A or step (710) of FIG. 7A.

[0164] In step (915), the base station may transmit information to the terminal for setting positioning parameters. In one embodiment, the base station may transmit setting information to the terminal for the base station-side AI model to infer positioning, which may correspond to step (620) of FIG. 6A or step (720) of FIG. 7A.

[0165] In step (925), the base station may transmit information to the terminal for configuring terminal-specific location measurements (e.g., CIR, PDP, RSTD, DL-PRS RSRP, etc.). According to one embodiment, the configuration information transmitted by the base station to the terminal may include configuration parameters necessary for performing terminal-specific location measurements.

[0166] In step (935), the terminal may perform location measurement based on location measurement configuration information and terminal-specific location measurement. Accordingly, the terminal may report the acquired measurement results to the base station.

[0167] In step (945), the base station may perform inference on location based on a base station-side AI model. More specifically, the base station may perform inference for location measurement using an AI model based on base station measurement results obtained through base station-specific location measurement, along with terminal measurement results received from the terminal.

[0168] As described above, even though the base station uses only the AI ​​model on the base station side, since both the terminal's measurement results and the base station's measurement results are used as inputs, more accurate location measurement inference results can be obtained.

[0169] Referring to FIG. 9b, at step (910), the terminal may transmit terminal capability information to the base station. According to one embodiment, the terminal capability information transmitted by the terminal to the base station may include various capability information included by the terminal for performing terminal location measurement, which may correspond to step (610) of FIG. 6a or step (710) of FIG. 7a.

[0170] In step (920), the base station may transmit information to the terminal for setting positioning parameters. In one embodiment, the base station may transmit setting information to the terminal for the terminal-side AI model to infer positioning, which may correspond to step (620) of FIG. 6A or step (720) of FIG. 7A.

[0171] In step (930), the base station may transmit information to the terminal for configuring base station-only location measurements (e.g., RTOA, UL-SRS RSRP, UL-AOA, etc.). According to one embodiment, the configuration information transmitted by the base station to the terminal may include configuration parameters necessary for performing base station-only location measurements.

[0172] In step (940), the base station may perform location measurement based on location measurement configuration information and base station-specific location measurement. Accordingly, the base station may transmit the acquired measurement results to the terminal.

[0173] In step (950), the terminal may perform inference regarding location based on a terminal-side AI model. More specifically, the terminal may perform inference for location measurement using an AI model based on terminal measurement results obtained through terminal-specific location measurement, along with base station measurement results received from the base station.

[0174] As described above, even though the terminal uses only the terminal-side AI model, since both the terminal's measurement results and the base station's measurement results are used as inputs, it is possible to obtain inference results for more accurate location measurement.

[0175] However, according to various embodiments of the present disclosure, there may be more advantages when using the double-sided AI model-based positioning technique of FIGS. 6A to 7B compared to the position measurement according to FIGS. 9A and 9B.

[0176] According to the double-sided AI model-based positioning technique of FIGS. 6A to 7B, first, since there may be no reporting signaling of terminal / base station measurement results, which are positioning-related data, it may be safer in terms of security / privacy issues. In addition, the single-sided AI model-based positioning technique may incur excessive overhead in the process of transmitting and receiving raw data such as terminal / base station measurement results, or errors may occur in the quantization process to reduce overhead, so using the double-sided AI model-based positioning technique may be more effective. In addition, since the double-sided AI model uses AI models at both the terminal and the base station, it is excellent in reducing complexity and cost by deploying heavier AI operations at the base station and deploying light AI operations at the terminal. However, if a single-sided AI model deployed only at the terminal is used, complexity may increase because the terminal's AI model needs to perform all operations.

[0177] The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0178] When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.

[0179] These programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic disc storage devices, compact disc-ROM (CD-ROM), digital versatile discs (DVDs) or other forms of optical storage devices, magnetic cassettes, or may be stored in memories formed by a combination of some or all of these. In addition, each configuration memory may include multiple copies.

[0180] Additionally, the program may be stored on an attachable storage device that is accessible via a communication network, such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a storage area network (SAN), or a combination thereof. Such a storage device may be connected to a device implementing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device implementing an embodiment of the present disclosure.

[0181] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed singularly or plurally, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in plural may be composed of singular elements, or components expressed in singular may be composed of plural elements.

[0182] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims described below, but also by equivalents thereof.

Claims

1. In a wireless communication system, a base station is Transceiver; and Including a controller coupled with the above transceiver, The above controller, Transmit information to the terminal (user equipment) to set up location measurement, Receive first inference information about the location of the terminal generated using the first AI model located in the terminal from the terminal, and A base station configured to generate second inference information regarding the location of the terminal using a second AI model located at the base station based on the first inference information.

2. In claim 1, the controller, A base station further configured to receive terminal capability information including information regarding the first AI model from the terminal.

3. In claim 2, A base station comprising information for setting the above location measurement, which is generated based on the terminal capability information and includes information for training the first AI model.

4. In claim 1, A base station for setting the above location measurement, which sets at least one of information on the type of location measurement or the type of output information of the first AI model.

5. In claim 4, A base station including an indicator indicating one of the following: location measurement using one-sided AI, location measurement using two-sided AI, or location measurement using a legacy method.

6. In a wireless communication system, a user equipment (UE) is Transceiver; and Including a controller coupled with the above transceiver, The above controller, Receive information from a base station to set up location measurement, From the base station, first inference information regarding the location of the terminal is received using the first AI (artificial intelligence) model located at the base station, and A terminal configured to generate second inference information regarding the location of the terminal using a second AI model located in the terminal based on the first inference information.

7. In claim 6, the controller, A terminal further configured to transmit terminal capability information including information regarding the second AI model to the base station.

8. In claim 7, A terminal comprising information for setting the above location measurement, which is generated based on the terminal capability information and includes information for training the second AI model.

9. In claim 6, Information for setting the above location measurement is a terminal that sets at least one of information on the type of location measurement or the type of input information of the second AI model.

10. In claim 9, A terminal including an indicator indicating one of the following types of location measurement: location measurement using one-sided AI, location measurement using two-sided AI, or location measurement using a legacy method.

11. In a wireless communication system, a method performed by a base station, A step of transmitting information for setting up location measurement to a terminal (user equipment); A step of receiving, from the terminal, first inference information about the location of the terminal generated using the first AI model located in the terminal; and A method comprising the step of generating second inference information regarding the location of the terminal using a second AI model located at the base station based on the first inference information.

12. In claim 11, the method comprises: A method further comprising the step of receiving terminal capability information including information regarding the first AI model from the terminal.

13. In claim 12, A method wherein information for setting the above location measurement is generated based on the terminal capability information and includes information for training the first AI model.

14. In claim 11, Information for setting the above location measurement is a method for setting at least one of information on the type of location measurement or the type of output information of the first AI model.

15. In claim 14, A method comprising an indicator indicating one of the following: location measurement using one-sided AI, location measurement using two-sided AI, or location measurement using a legacy method, wherein the information regarding the type of said location measurement is provided.

Images