Method for adding VFL client

Abstract

One embodiment of the present specification provides a method by which a VFL server performs communication. The method comprises steps in which a VFL server: acquires, from an NRF, information about at least one candidate VFL client; determines a specific VFL client among the at least one candidate VFL client on the basis of the information about the candidate VFL client; transmits an indication for simulation training to an existing VFL group and the specific VFL client; receives a result of the simulation training from the existing VFL group and the specific VFL client on the basis of the indication; and, on the basis of the result of the simulation training, determines to add the specific VFL client to the existing VFL group.

Description

How to add a VFL client

[0001] This specification relates to mobile communication.

[0002] 3GPP (3rd generation partnership project) LTE (long-term evolution) is a technology designed to enable high-speed packet communication. Many methods have been proposed to achieve LTE goals, such as reducing costs for users and operators, improving service quality, expanding coverage, and increasing system capacity. As high-level requirements, 3GPP LTE demands reduced cost per bit, improved service availability, flexible use of frequency bands, a simple structure, open interfaces, and appropriate power consumption of terminals.

[0003] Work has begun at the ITU (International Telecommunication Union) and 3GPP to develop requirements and specifications for new radio (NR) systems. 3GPP must identify and develop the technical components necessary to successfully standardize NR in a timely manner, satisfying both urgent market demands and the longer-term requirements presented by the ITU-R (ITU Radio Communication Sector) IMT (International Mobile Telecommunications)-2020 process. Furthermore, NR must be able to utilize any spectrum band up to at least 100 GHz so that it can be used for wireless communication even in the distant future.

[0004] NR targets a single technical framework that covers all deployment scenarios, usage scenarios, and requirements, including eMBB (enhanced mobile broadband), mMTC (massive machine type communications), and URLLC (ultra-reliable and low latency communications). NR must inherently be forward compatible.

[0005] Add new clients through mock training.

[0006] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.

[0007] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.

[0008] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.

[0009] Figure 4 is a structural diagram of a next-generation mobile communication network.

[0010] FIG. 5 shows an example of a 5G system structure to which the implementation of the present specification is applied.

[0011] FIGS. 6 and FIGS. 7 illustrate examples of procedures for adding a new VFL client according to the disclosure of this specification.

[0012] FIG. 8 illustrates the procedure of a VFL server according to the disclosure of the present specification.

[0013] FIG. 9 illustrates the procedure of a specific VFL client according to the disclosure of this specification.

[0014] The following techniques, devices, and systems may be applied to various wireless multiple access systems. Examples of multiple access systems include code division multiple access (CDMA) systems, frequency division multiple access (FDMA) systems, time division multiple access (TDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and multicarrier frequency division multiple access (MC-FDMA) systems. CDMA may be implemented through wireless technologies such as universal terrestrial radio access (UTRA) or CDMA2000. TDMA may be implemented through wireless technologies such as global system for mobile communications (GSM), general packet radio service (GPRS), or enhanced data rates for GSM evolution (EDGE). OFDMA can be implemented through wireless technologies such as IEEE (Institute of Electrical and Electronics Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or E-UTRA (evolved UTRA). UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long-term evolution) is part of E-UMTS (evolved UMTS) using E-UTRA.3GPP LTE uses OFDMA in the downlink (DL) and SC-FDMA in the uplink (UL). Evolutions of 3GPP LTE include LTE-A (advanced), LTE-A Pro, and / or 5G NR (new radio).

[0015] For convenience of explanation, the implementation of this specification is described primarily in relation to 3GPP-based wireless communication systems. However, the technical characteristics of this specification are not limited thereto. For example, the following detailed description is provided based on a mobile communication system corresponding to a 3GPP-based wireless communication system, but aspects of this specification that are not limited to 3GPP-based wireless communication systems may be applied to other mobile communication systems.

[0016] For terms and technologies used in this specification that are not specifically described, reference may be made to wireless communication standard documents published prior to this specification.

[0017] In this specification, "A or B" may mean "only A," "only B," or "both A and B." Alternatively, in this specification, "A or B" may be interpreted as "A and / or B." For example, in this specification, "A, B or C" may mean "only A," "only B," "only C," or "any combination of A, B and C."

[0018] A slash ( / ) or a comma used in this specification may mean "and / or." For example, "A / B" may mean "A and / or B." Accordingly, "A / B" may mean "only A," "only B," or "both A and B." For example, "A, B, C" may mean "A, B or C."

[0019] In this specification, "at least one of A and B" may mean "only A," "only B," or "both A and B." Additionally, in this specification, the expressions "at least one of A or B" or "at least one of A and / or B" may be interpreted as synonymous with "at least one of A and B."

[0020] Additionally, in this specification, "at least one of A, B and C" may mean "only A," "only B," "only C," or "any combination of A, B and C." Furthermore, "at least one of A, B or C" or "at least one of A, B and / or C" may mean "at least one of A, B and C."

[0021] Additionally, parentheses used in this specification may mean "for example." Specifically, when indicated as "control information (PDCCH)," "PDCCH" may be proposed as an example of "control information." In other words, "control information" in this specification is not limited to "PDCCH," and "PDCCH" may be proposed as an example of "control information." Furthermore, even when indicated as "control information (i.e., PDCCH)," "PDCCH" may be proposed as an example of "control information."

[0022] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.

[0023] Although not limited thereto, the various descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification may be applied to various fields where wireless communication and / or connectivity between devices (e.g., 5G) is required.

[0024] The present specification will be described in more detail below with reference to the drawings. In the following drawings and / or description, the same reference numerals may refer to the same or corresponding hardware blocks, software blocks, and / or function blocks unless otherwise indicated.

[0025] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.

[0026] The 5G usage scenario shown in FIG. 1 is merely an example, and the technical features of this specification may be applied to other 5G usage scenarios not shown in FIG. 1.

[0027] The three main requirements categories for 5G are (1) enhanced mobile broadband (eMBB) category, (2) massive machine type communication (mMTC) category, and (3) ultra-reliable and low latency communications (URLLC) category.

[0028] Referring to FIG. 1, the communication system (1) includes wireless devices (100a to 100f), a base station (BS; 200), and a network (300). FIG. 1 illustrates a 5G network as an example of the network of the communication system (1), but the implementation of the present specification is not limited to a 5G system and may be applied to future communication systems beyond a 5G system.

[0029] The base station (200) and the network (300) can be implemented as wireless devices, and a specific wireless device can operate as a base station / network node in relation to another wireless device.

[0030] Wireless devices (100a to 100f) represent devices that perform communication using radio access technology (RAT) (e.g., 5G NR or LTE) and may also be referred to as communication / wireless / 5G devices. Wireless devices (100a to 100f) may include, but are not limited to, robots (100a), vehicles (100b-1 and 100b-2), extended reality (XR) devices (100c), portable devices (100d), home appliances (100e), IoT devices (100f), and artificial intelligence (AI) devices / servers (400). For example, vehicles may include vehicles with wireless communication capabilities, autonomous vehicles, and vehicles capable of performing communication between vehicles. Vehicles may include unmanned aerial vehicles (UAVs) (e.g., drones). XR devices may include AR / VR / mixed reality (MR) devices and may be implemented in the form of head-mounted devices (HMDs) and head-up displays (HUDs) mounted on vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signs, vehicles, robots, etc. Portable devices may include smartphones, smart pads, wearable devices (e.g., smartwatches or smart glasses), and computers (e.g., laptops). Home appliances may include TVs, refrigerators, and washing machines. IoT devices may include sensors and smart meters.

[0031] In this specification, wireless devices (100a to 100f) may be referred to as user equipment (UE). The UE may include, for example, a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a PDA (personal digital assistant), a PMP (portable multimedia player), a navigation system, a slate PC, a tablet PC, an ultrabook, a vehicle, a vehicle with autonomous driving capabilities, a connected car, a UAV, an AI module, a robot, an AR device, a VR device, an MR device, a hologram device, a public safety device, an MTC device, an IoT device, a medical device, a fintech device (or financial device), a security device, a weather / environment device, a 5G service-related device, or a device related to the Fourth Industrial Revolution.

[0032] For example, a UAV can be an aircraft that is not on board and is navigated by radio control signals.

[0033] For example, a VR device may include a device for implementing objects or backgrounds in a virtual environment. For example, an AR device may include a device that implements objects or backgrounds in a virtual world by connecting them to objects or backgrounds in a real world. For example, an MR device may include a device that implements objects or backgrounds in a virtual world by merging them with objects or backgrounds in a real world. For example, a holographic device may include a device for implementing a 360-degree stereoscopic image by recording and playing back stereoscopic information using the phenomenon of light interference that occurs when two laser lights called holograms meet.

[0034] For example, a public safety device may include an image relay device or an image device that can be worn on a user's body.

[0035] For example, MTC devices and IoT devices may be devices that do not require direct human intervention or operation. For instance, MTC devices and IoT devices may include smart meters, vending machines, thermometers, smart light bulbs, door locks, or various sensors.

[0036] For example, a medical device may be a device used for the purpose of diagnosing, treating, alleviating, curing, or preventing a disease. For example, a medical device may be a device used to diagnose, treat, alleviate, or correct an injury or damage. For example, a medical device may be a device used for the purpose of examining, replacing, or modifying a structure or function. For example, a medical device may be a device used for the purpose of regulating pregnancy. For example, a medical device may include a therapeutic device, a driving device, a (in vitro) diagnostic device, a hearing aid, or a surgical device.

[0037] For example, a security device may be a device installed to prevent potential risks and maintain safety. For example, a security device may be a camera, closed-circuit TV (CCTV), a recorder, or a black box.

[0038] For example, a fintech device may be a device capable of providing financial services such as mobile payments. For example, a fintech device may include a payment device or a POS system.

[0039] For example, a weather / environment device may include a device for monitoring or predicting the weather / environment.

[0040] Wireless devices (100a to 100f) can be connected to a network (300) through a base station (200). AI technology may be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) through the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, a 5G (e.g., NR) network, and a network after 5G. The wireless devices (100a to 100f) may communicate with each other through the base station (200) / network (300), but they may also communicate directly (e.g., sidelink communication) without going through the base station (200) / network (300). For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (vehicle-to-vehicle) / V2X (vehicle-to-everything) communication). Also, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

[0041] Wireless communication / connections (150a, 150b, 150c) can be established between wireless devices (100a to 100f) and / or between wireless devices (100a to 100f) and base station (200) and / or between base station (200). Here, the wireless communication / connections can be established through various RATs (e.g., 5G NR), such as uplink / downlink communication (150a), sidelink communication (150b) (or D2D (device-to-device) communication), and communication between base stations (150c) (e.g., relay, IAB (integrated access and backhaul)). Through the wireless communication / connections (150a, 150b, 150c), wireless devices (100a to 100f) and base station (200) can transmit / receive wireless signals to / from each other. For example, wireless communication / connection (150a, 150b, 150c) may transmit / receive signals through various physical channels. To this end, based on various proposals in this specification, at least some of the following may be performed: a process for setting various configuration information for transmitting / receiving wireless signals, a process for various signal processing (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and a resource allocation process.

[0042] AI refers to the field of researching artificial intelligence or the methodologies to create it, while machine learning refers to the field of researching methodologies to define and solve various problems within the realm of artificial intelligence. Machine learning is also defined as an algorithm that improves performance on a task through continuous experience.

[0043] A robot can refer to a machine that automatically processes or operates given tasks based on its own capabilities. In particular, a robot equipped with the ability to perceive its environment, make independent judgments, and perform actions can be called an intelligent robot. Robots can be classified into industrial, medical, domestic, and military types depending on their purpose or field of use. Robots are equipped with drive units, including actuators or motors, to perform various physical movements, such as moving robot joints. Additionally, mobile robots include wheels, brakes, propellers, etc., in their drive units, enabling them to drive on the ground or fly in the air.

[0044] Autonomous driving refers to technology that drives itself, and an autonomous vehicle refers to a vehicle that drives without user intervention or with minimal user intervention. For example, autonomous driving can include technologies such as maintaining the driving lane, automatically adjusting speed like adaptive cruise control, driving automatically along a predetermined route, and automatically setting a route and driving once a destination is set. The term "vehicle" encompasses vehicles equipped solely with internal combustion engines, hybrid vehicles equipped with both internal combustion engines and electric motors, and electric vehicles equipped solely with electric motors; it can include not only automobiles but also trains and motorcycles. An autonomous vehicle can be viewed as a robot equipped with autonomous driving capabilities.

[0045] Augmented Reality is a collective term for VR, AR, and MR. VR technology provides real-world objects or backgrounds solely as CG images, AR technology provides virtual CG images superimposed on images of real objects, and MR technology is a CG technology that mixes and combines virtual objects with the real world. MR technology is similar to AR technology in that it displays real-world and virtual objects together. However, there is a difference in that while virtual objects in AR technology are used to complement real-world objects, virtual and real objects in MR technology are used as equal entities.

[0046] NR supports multiple numerologies or subcarrier spacings (SCS) to support various 5G services. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban areas, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.

[0047] The NR frequency band can be defined by two types of frequency ranges (FR1, FR2). The numerical values ​​of the frequency ranges may change. For example, the two types of frequency ranges (FR1, FR2) may be as shown in Table 1 below. For convenience of explanation, among the frequency ranges used in the NR system, FR1 may mean "sub 6GHz range" and FR2 may mean "above 6GHz range" and may be referred to as millimeter wave (mmW).

[0048] Frequency Range Definition Frequency Range Subcarrier Spacing FR1 450 MHz - 6000 MHz 15, 30, 60 kHz FR2 24 250 MHz - 52600 MHz 60, 120, 240 kHz

[0049] As described above, the numerical value of the frequency range of the NR system may change. For example, FR1 may include a band of 410 MHz to 7125 MHz as shown in Table 2 below. That is, FR1 may include a frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher. For example, the frequency band of 6 GHz (or 5850, 5900, 5925 MHz, etc.) or higher included within FR1 may include an unlicensed band. The unlicensed band may be used for various purposes, for example, for communication for vehicles (e.g., autonomous driving).

[0050] Frequency Range Definition Frequency Range Subcarrier Spacing FR1 4 10 MHz - 7 125 MHz 15, 30, 60 kHz FR2 24 250 MHz - 5 2600 MHz 60, 120, 240 kHz

[0051] Here, the wireless communication technology implemented in the wireless device of this specification may include LTE, NR, and 6G, as well as narrowband IoT (NB-IoT) for low-power communication. For example, NB-IoT technology may be an example of low-power wide-area network (LPWAN) technology and may be implemented according to standards such as LTE Cat NB1 and / or LTE Cat NB2, but is not limited to the names mentioned above. Additionally, or generally, the wireless communication technology implemented in the wireless device of this specification may perform communication based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology and may be referred to by various names such as enhanced MTC (eMTC). For example, LTE-M technology may be implemented in at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-bandwidth limited), 5) LTE-MTC, 6) LTE MTC, and / or 7) LTE M, and is not limited to the names mentioned above. Additionally or generally, wireless communication technology implemented in the wireless device of this specification may include at least one of ZigBee, Bluetooth, and / or LPWAN for low-power communication, and is not limited to the names mentioned above. For example, ZigBee technology may create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4, and may be referred to by various names.

[0052] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.

[0053] In FIG. 2, the first wireless device (100) and / or the second wireless device (200) may be implemented in various forms depending on the use example / service. For example, {the first wireless device (100) and the second wireless device (200)} may correspond to at least one of {wireless devices (100a–100f) and base station (200)}, {wireless devices (100a–100f) and wireless devices (100a–100f)} and / or {base station (200) and base station (200)} of FIG. 1. The first wireless device (100) and / or the second wireless device (200) may be composed of various components, devices / parts and / or modules.

[0054] The first wireless device (100) may include at least one transceiver such as a transceiver (106), at least one processing chip such as a processing chip (101), and / or one or more antennas (108).

[0055] The processing chip (101) may include at least one processor, such as a processor (102), and at least one memory, such as a memory (104). Additionally and / or generally, the memory (104) may be placed outside the processing chip (101).

[0056] The processor (102) can control the memory (104) and / or the transceiver (106) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. For example, the processor (102) may process information within the memory (104) to generate a first information / signal and transmit a wireless signal containing the first information / signal through the transceiver (106). The processor (102) may receive a wireless signal containing a second information / signal through the transceiver (106) and process the second information / signal to store the obtained information in the memory (104).

[0057] Memory (104) may be connected to the processor (102) so as to be operable. Memory (104) may store various types of information and / or instructions. Memory (104) may store firmware and / or software code (105) that implements code, instructions, and / or a set of instructions that perform the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (102). For example, firmware and / or software code (105) may implement instructions that perform the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (102). For example, firmware and / or software code (105) may control the processor (102) to perform one or more protocols. For example, firmware and / or software code (105) may control the processor (102) to perform one or more wireless interface protocol layers.

[0058] Here, the processor (102) and memory (104) may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). A transceiver (106) may be connected to the processor (102) and may transmit and / or receive a wireless signal through one or more antennas (108). Each transceiver (106) may include a transmitter and / or receiver. The transceiver (106) may be interchangeably used with an RF (radio frequency) unit. In this specification, the first wireless device (100) may represent a communication modem / circuit / chip.

[0059] The second wireless device (200) may include at least one transceiver such as a transceiver (206), at least one processing chip such as a processing chip (201), and / or one or more antennas (208).

[0060] The processing chip (201) may include at least one processor, such as a processor (202), and at least one memory, such as a memory (204). Additionally and / or alternatively, the memory (204) may be placed outside the processing chip (201).

[0061] The processor (202) can control the memory (204) and / or the transceiver (206) and may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. For example, the processor (202) may process information within the memory (204) to generate a third information / signal and transmit a wireless signal containing the third information / signal through the transceiver (206). The processor (202) may receive a wireless signal containing a fourth information / signal through the transceiver (206) and process the fourth information / signal to store the obtained information in the memory (204).

[0062] Memory (204) may be connected to the processor (202) so as to be operable. Memory (204) may store various types of information and / or instructions. Memory (204) may store firmware and / or software code (205) that implements instruction code, instructions, and / or sets of instructions that perform descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (202). For example, firmware and / or software code (205) may implement instructions that perform descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification when executed by the processor (202). For example, firmware and / or software code (205) may control the processor (202) to perform one or more protocols. For example, firmware and / or software code (205) may control the processor (202) to perform one or more wireless interface protocol layers.

[0063] Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement a RAT (e.g., LTE or NR). A transceiver (206) may be connected to the processor (202) and transmit and / or receive a wireless signal through one or more antennas (208). Each transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeably used with an RF unit. In this specification, the second wireless device (200) may represent a communication modem / circuit / chip.

[0064] Hereinafter, hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as a PHY (physical) layer, a MAC (media access control) layer, a RLC (radio link control) layer, a PDCP (packet data convergence protocol) layer, a RRC (radio resource control) layer, and an SDAP (service data adaptation protocol) layer). One or more processors (102, 202) may generate one or more PDUs (protocol data units), one or more SDUs (service data units), messages, control information, data, or information according to the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification. One or more processors (102, 202) may generate a signal (e.g., baseband signal) including a PDU, SDU, message, control information, data, or information according to the description, function, procedure, proposal, method, and / or operation flowchart disclosed in this specification and provide it to one or more transceivers (106, 206). One or more processors (102, 202) may receive a signal (e.g., baseband signal) from one or more transceivers (106, 206) and may obtain a PDU, SDU, message, control information, data, or information according to the description, function, procedure, proposal, method, and / or operation flowchart disclosed in this specification.

[0065] One or more processors (102, 202) may be referred to as a controller, a microcontroller, a microprocessor, and / or a microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, and / or a combination thereof. For example, one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more digital signal processing devices (DSPDs), one or more programmable logic devices (PLDs), and / or one or more field programmable gate arrays (FPGAs) may be included in one or more processors (102, 202). For example, one or more processors (102, 202) may be composed of a set of communication control processors, application processors (APs), electronic control units (ECUs), central processing units (CPUs), graphic processing units (GPUs), and memory control processors.

[0066] One or more memories (104, 204) may be connected to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, codes, instructions, and / or commands. One or more memories (104, 204) may consist of random access memory (RAM), dynamic RAM (DRAM), read-only memory (ROM), erasable programmable ROM (EPROM), flash memory, volatile memory, non-volatile memory, hard drives, registers, cache memory, computer read storage media, and / or combinations thereof. One or more memories (104, 204) may be located inside and / or outside of one or more processors (102, 202). Additionally, one or more memories (104, 204) may be connected to one or more processors (102, 202) through various technologies such as wired or wireless connections.

[0067] One or more transceivers (106, 206) may transmit user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification to one or more other devices. One or more transceivers (106, 206) may receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this specification from one or more other devices. For example, one or more transceivers (106, 206) may be connected to one or more processors (102, 202) and may transmit and receive wireless signals. For example, one or more processors (102, 202) may control one or more transceivers (106, 206) to transmit user data, control information, wireless signals, etc., to one or more other devices. Additionally, one or more processors (102, 202) can control one or more transceivers (106, 206) to receive user data, control information, wireless signals, etc. from one or more other devices.

[0068] One or more transceivers (106, 206) may be connected to one or more antennas (108, 208). Additionally and / or generally, one or more transceivers (106, 206) may include one or more antennas (108, 208). One or more transceivers (106, 206) may be configured to transmit and receive user data, control information, wireless signals / channels, etc., as described in the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein through one or more antennas (108, 208). In this specification, one or more antennas (108, 208) may be a plurality of physical antennas or a plurality of logical antennas (e.g., antenna ports).

[0069] One or more transceivers (106, 206) can convert received user data, control information, wireless signals / channels, etc. from RF band signals to baseband signals in order to process received user data, control information, wireless signals / channels, etc. using one or more processors (102, 202). One or more transceivers (106, 206) can convert processed user data, control information, wireless signals / channels, etc. from baseband signals to RF band signals using one or more processors (102, 202). To this end, one or more transceivers (106, 206) may include (analog) oscillators and / or filters. For example, one or more transceivers (106, 206) can up-convert an OFDM baseband signal into an OFDM signal through an (analog) oscillator and / or filter under the control of one or more processors (102, 202) and transmit the up-converted OFDM signal at a carrier frequency. One or more transceivers (106, 206) can receive an OFDM signal at a carrier frequency and down-convert the OFDM signal into an OFDM baseband signal through an (analog) oscillator and / or filter under the control of one or more processors (102, 202).

[0070] Although not illustrated in FIG. 2, the wireless device (100, 200) may include additional components. The additional components (140) may be configured in various ways depending on the type of the wireless device (100, 200). For example, the additional components (140) may include at least one of a power unit / battery, an input / output (I / O) device (e.g., audio I / O port, video I / O port), a driving unit, and a computing unit. The additional components (140) may be connected to one or more processors (102, 202) through various technologies, such as wired or wireless connections.

[0071] In an implementation of this specification, the UE may operate as a transmitting device in the uplink (UL; uplink) and as a receiving device in the downlink (DL; downlink). In an implementation of this specification, the base station may operate as a receiving device in the UL and as a transmitting device in the DL. For technical convenience, it is generally assumed that the first wireless device (100) operates as a UE and the second wireless device (200) operates as a base station. For example, a processor (102) connected to, mounted on, or released to the first wireless device (100) may be configured to perform UE operations according to an implementation of this specification or to control a transceiver (106) to perform UE operations according to an implementation of this specification. A processor (202) connected to, mounted on, or released to the second wireless device (200) may be configured to perform base station operations according to an implementation of this specification or to control a transceiver (206) to perform base station operations according to an implementation of this specification.

[0072] In this specification, the base station may be referred to as Node B, eNode B, or gNB.

[0073] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.

[0074] Referring to FIG. 3, the UE (100) can correspond to the first wireless device (100) of FIG. 2.

[0075] The UE (100) includes a processor (102), memory (104), transceiver (106), one or more antennas (108), a power management module (141), a battery (142), a display (143), a keypad (144), a SIM (Subscriber Identification Module) card (145), a speaker (146), and a microphone (147).

[0076] The processor (102) may be configured to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. The processor (102) may be configured to control one or more other components of the UE (100) to implement the descriptions, functions, procedures, proposals, methods, and / or operation flowcharts disclosed herein. Layers of a wireless interface protocol may be implemented in the processor (102). The processor (102) may include an ASIC, other chipsets, logic circuits, and / or data processing devices. The processor (102) may be an application processor. The processor (102) may include at least one of a DSP, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a modem (modulator and demodulator). An example of the processor (102) is the SNAPDRAGON manufactured by Qualcomm®. TM Series processor, EXYNOS made by Samsung® TM Series processors, A Series processors made by Apple®, HELIO made by MediaTek® TM Series processors, ATOM made by Intel® TM It can be found in series processors or corresponding next-generation processors.

[0077] Memory (104) is coupled to the processor (102) so as to be operable and stores various information for operating the processor (102). Memory (104) may include ROM, RAM, flash memory, memory card, storage medium and / or other storage device. When the implementation is implemented in software, the technology described herein may be implemented using modules (e.g., procedures, functions, etc.) that perform the descriptions, functions, procedures, proposals, methods and / or operation flowcharts disclosed herein. Modules may be stored in memory (104) and executed by the processor (102). Memory (104) may be implemented within the processor (102) or outside the processor (102), in which case it may be communicatively coupled to the processor (102) through various methods known in the technology.

[0078] A transceiver (106) is coupled to operate with a processor (102) and transmits and / or receives a wireless signal. The transceiver (106) includes a transmitter and a receiver. The transceiver (106) may include a baseband circuit for processing a wireless frequency signal. The transceiver (106) controls one or more antennas (108) to transmit and / or receive a wireless signal.

[0079] The power management module (141) manages the power of the processor (102) and / or the transceiver (106). The battery (142) supplies power to the power management module (141).

[0080] The display (143) outputs the result processed by the processor (102). The keypad (144) receives input to be used by the processor (102). The keypad (144) can be displayed on the display (143).

[0081] A SIM card (145) is an integrated circuit for securely storing an International Mobile Subscriber Identity (IMSI) and associated keys, and is used to identify and authenticate a subscriber in a mobile device such as a mobile phone or computer. Additionally, contact information can be stored on many SIM cards.

[0082] The speaker (146) outputs sound-related results processed by the processor (102). The microphone (147) receives sound-related input to be used by the processor (102).

[0083] Figure 4 is a structural diagram of a next-generation mobile communication network.

[0084] 5GC (5G Core) may include various components, and FIG. 5 includes some of them, such as AMF (Access and Mobility Management Function) (410), SMF (Session Management Function) (420), PCF (Policy Control Function) (430), UPF (User Plane Function) (440), AF (Application Function) (450), UDM (Unified Data Management) (460), and N3IWF (Non-3GPP (3rd Generation Partnership Project) Inter Working Function) (490).

[0085] The UE (100) is connected to the data network via the UPF (440) through the NG-RAN (Next Generation Radio Access Network) including the gNB (20).

[0086] The UE (100) can also receive data services through untrusted non-3GPP access, such as a WLAN (Wireless Local Area Network). To connect the non-3GPP access to the core network, an N3IWF (490) may be deployed.

[0087] The illustrated N3IWF (490) performs the function of managing interworking between non-3GPP access and 5G systems. When the UE (100) is connected to non-3GPP access (e.g., WiFi referred to as IEEE 801.11), the UE (100) can be connected to the 5G system through the N3IWF (490). The N3IWF (490) performs control signing with the AMF (410) and connects to the UPF (440) via the N3 interface for data transmission.

[0088] The illustrated AMF (410) can manage access and mobility in a 5G system. The AMF (410) can perform the function of managing Non-Access Stratum (NAS) security. The AMF (410) can perform the function of handling mobility in an idle state.

[0089] The illustrated UPF (440) is a type of gateway through which user data is transmitted and received. The UPF node (440) can perform all or part of the user plane functions of the S-GW (Serving Gateway) and P-GW (Packet Data Network Gateway) of 4th generation mobile communication.

[0090] The UPF (440) acts as a boundary point between the next generation radio access network (NG-RAN) and the core network, and is an element that maintains the data path between the gNB (20) and the SMF (420). Additionally, when the UE (100) moves across the area served by the gNB (20), the UPF (440) acts as a mobility anchor point. The UPF (440) can perform the function of handling PDUs. For mobility within the NG-RAN (Next Generation Radio Access Network defined in 3GPP Release-15 or later), packets can be routed through the UPF. Additionally, the UPF (440) may also function as an anchor point for mobility with other 3GPP networks (RANs defined prior to 3GPP Release-15, e.g., UTRAN, E-UTRAN (Evolved-UMTS (Universal Mobile Telecommunications System) Terrestrial Radio Access Network)) or GERAN (GSM (Global System for Mobile Communication) / EDGE (Enhanced Data rates for Global Evolution) Radio Access Network). The UPF (440) may correspond to a termination point of a data interface toward a data network.

[0091] The illustrated PCF (430) is a node that controls the operator's policy.

[0092] The illustrated AF (450) is a server for providing various services to the UE (100).

[0093] The illustrated UDM (460) is a type of server that manages subscriber information, such as the HSS (Home subscriber Server) of 4th generation mobile communication. The UDM (460) stores and manages the subscriber information in a Unified Data Repository (UDR).

[0094] The illustrated SMF (420) can perform the function of assigning the IP (Internet Protocol) address of the UE. Also, the SMF (420) can control the PDU (protocol data unit) session.

[0095] For reference, the reference numerals for AMF (410), SMF (420), PCF (430), UPF (440), AF (450), UDM (460), N3IWF (490), gNB (20), or UE (100) may be omitted below.

[0096] Fifth-generation mobile communication supports multiple numerologies or subcarrier spacings (SCS) to support various 5G services. For example, when the SCS is 15 kHz, it supports a wide area in traditional cellular bands; when the SCS is 30 kHz / 60 kHz, it supports dense-urban environments, lower latency, and wider carrier bandwidth; and when the SCS is 60 kHz or higher, it supports a bandwidth greater than 24.25 GHz to overcome phase noise.

[0097] FIG. 5 shows an example of a 5G system structure to which the implementation of the present specification is applied.

[0098] The 5G system (5GS) structure consists of the following network functions (NF).

[0099] - AUSF (Authentication Server Function)

[0100] - AMF (Access and Mobility Management Function)

[0101] - DN (Data Network), 예를 들어 운영자 서비스, 인터넷 접속 또는 타사 서비스

[0102] - USDF (Unstructured Data Storage Function)

[0103] - NEF (Network Exposure Function)

[0104] - I-NEF (Intermediate NEF)

[0105] - NRF (Network Repository Function)

[0106] - NSSF (Network Slice Selection Function)

[0107] - PCF (Policy Control Function)

[0108] - SMF (Session Management Function)

[0109] - UDM (Unified Data Management)

[0110] - UDR (Unified Data Repository)

[0111] - UPF (User Plane Function)

[0112] - UCMF (UE radio Capability Management Function)

[0113] - AF (Application Function)

[0114] - UE (User Equipment)

[0115] - (R)AN ((Radio) Access Network)

[0116] - 5G-EIR (5G-Equipment Identity Register)

[0117] - NWDAF (Network Data Analytics Function)

[0118] - CHF (CHarging Function)

[0119] In addition, the following network functions may be considered.

[0120] - N3IWF (Non-3GPP InterWorking Function)

[0121] - TNGF (Trusted Non-3GPP Gateway Function)

[0122] - W-AGF (Wireline Access Gateway Function)

[0123] Figure 5 shows the 5G system structure in a non-roaming case using a reference point representation that shows how various network functions interact with each other.

[0124] In Fig. 5, for clarity of the point-to-point diagram, UDSF, NEF, and NRF are not described. However, all network functions shown can interact with UDSF, UDR, NEF, and NRF as needed.

[0125] For clarity, the connection between UDR and other NFs (e.g., PCF) is not shown in FIG. 4. For clarity, the connection between NWDAF and other NFs (e.g., PCF) is not shown in FIG. 4.

[0126] The 5G system structure includes the following reference points.

[0127] - N1: Reference point between UE and AMF.

[0128] - N2: Reference point between (R)AN and AMF.

[0129] - N3: Reference point between (R)AN and UPF.

[0130] - N4: Reference point between SMF and UPF.

[0131] - N6: Reference point between the UPF and the data network.

[0132] - N9: Reference point between two UPFs.

[0133] The following reference points show the interactions that exist between the NF services of NF.

[0134] - N5: Reference point between PCF and AF.

[0135] - N7: Reference point between SMF and PCF.

[0136] - N8: Reference point between UDM and AMF.

[0137] - N10: Reference point between UDM and SMF.

[0138] - N11: Reference point between AMF and SMF.

[0139] - N12: Reference point between AMF and AUSF.

[0140] - N13: Reference point between UDM and AUSF.

[0141] - N14: Reference point between two AMFs.

[0142] - N15: Reference point between PCF and AMF for non-roaming scenarios, reference point between PCF and AMF of the visited network for roaming scenarios.

[0143] - N16: Reference point between two SMFs (in the case of roaming, between the SMF of the visited network and the SMF of the home network)

[0144] - N22: Reference point between AMF and NSSF.

[0145] In some cases, two NFs may need to be connected to each other to service the UE.

[0146] <VFL (Vertical Federated Learning)>

[0147] Research on integrating AI / ML into communication systems is being conducted in 3GPP Release 18 and Release 19. In Release 18, standardization work was carried out by integrating HFL (Horizontal Federated Learning) into communication systems. In Release 19, VFL (Vertical Federated Learning) was applied, and after conducting a study to perform federated learning by integrating VFL into network nodes in the core network using AIML-CN, which is currently the RE-19 Item, standardization work is proceeding based on the conclusions.

[0148] Since Rel-18, the application of HFL to NWDAF has led to discussions regarding NWDAF handling procedures. In the Rel-18 HFL procedures, standardization work was carried out on the process by which the FL server determines and handles whether an FL client is removed or newly added due to various factors (capability change, high load, etc.) of the FL client NWDAF. In an HFL environment, the FL server provides ML models to FL clients for training. Furthermore, even if a new FL client is added, it can immediately perform training using the shared model and deliver the results.

[0149] By applying the VFL environment to NWDAF, NWDAFs acting as clients can train individual models based on local data. Subsequently, NWDAFs acting as servers can integrate these models to build the final global model. Specification work has been conducted on the basic architecture for VFL support, and related details are currently being discussed. Similar to the HFL environment, a method is required to maintain the VFL process when new VFL clients are added in the VFL environment.

[0150] However, in the case of VFL, each VFL client has different characteristics and has a different local ML model. In addition, since only training results are shared, there is a characteristic that ML models are not shared between VFL servers and VFL clients.

[0151] Therefore, when a new VFL client needs to be added to a VFL environment, it does not possess a trained model; consequently, the newly added VFL client begins training alongside the existing VFL servers and clients that have already been trained in the VFL environment. In this case, when the newly added VFL client performs VFL processes with the existing trained VFL clients, the accuracy of the entire VFL model may be affected. Additionally, more training may be required to achieve the performance necessary to participate in inference. For example, when a new VFL client is added, the time required to obtain VFL results may be longer.

[0152] In this specification, a method for reducing the time required to derive a learning result may be proposed when a new VFL client is added in a VFL environment.

[0153] In this specification, a VFL processor may refer to training. Accordingly, information related to a VFL processor may be information related to training.

[0154] In this specification, when a new VFL client is added to a VFL environment, a method for pre-training the new VFL client so that it can be effectively added to an existing VFL process may be proposed.

[0155] Through this, training time can be reduced and the VFL process operated efficiently, enabling enhanced functionality in 5G / 6G systems with VFL applied environments.

[0156] In a VFL environment, a VFL server can configure the VFL client(s) to participate in training. New VFL clients may be added during training. In this case, a method can be proposed to reduce training time and increase the efficiency of new VFL clients' participation in training.

[0157] The VFL server in this specification may be set to NWDAF or AF.

[0158] The VFL server can trigger the addition / re-selection of VFL clients during the VFL process. The VFL server can perform discovery for new VFL clients through NRF.

[0159] The VFL server may decide to add a new VFL client. In this case, the VFL server may create a mock training group by adding the new VFL client to the existing VFL client(s) currently in training. The VFL server may allow the created mock training group to learn / train.

[0160] The VFL server can check accuracy by monitoring the learning / training results of the mock training group.

[0161] If the accuracy exceeds a certain threshold, the VFL server can maintain the VFL process by replacing the existing training group with a mock training group. For example, the VFL server can stop the VFL process using the existing training group and proceed with the VFL process using the mock training group.

[0162] This method can prevent the problem of accuracy degradation caused by the addition of new VFL clients (e.g., NWDAF) because new VFL clients are pre-trained in a mock training group and replaced after verifying their accuracy.

[0163] This method can reduce training time by preventing iterative learning (repetitive learning performed until convergence to a certain result) caused by the addition of new VFL clients, as the VFL process through the existing training group is maintained until the mock training group completes learning / training.

[0164] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.

[0165] FIGS. 6 and FIGS. 7 illustrate examples of procedures for adding a new VFL client according to the disclosure of this specification.

[0166] In accordance with the disclosure of this specification, the VFL server may determine to add a new VFL client. Based on this, the VFL server may create and train a simulated training group and perform accuracy monitoring thereon.

[0167] The method proposed in this specification is described based on the procedures of 5GS, but it is not limited to 5GS and can be extended and applied to the procedures of future mobile communication systems such as 6GS.

[0168] The methods and procedures presented below may be performed or used selectively, in combination, or complementarily.

[0169] Conventional service operations / procedures are extended, and each procedure can be performed through this.

[0170] Alternatively, a new operation / procedure is defined, and each procedure can be performed through it.

[0171] In each procedure, conventional parameters may be reused. Alternatively, new parameters may be defined and used in each procedure.

[0172] This specification shows an example where NWDAF is used as a VFL client, but is not limited thereto and may include any network node capable of acting as an AF or other client.

[0173] 0) step 0

[0174] The VFL server can discover clients through NRF to select the first client for the VFL.

[0175] At this time, the VFL server can receive the ML Model Interoperability indicator of each candidate client from the NRF.

[0176] Based on the ML Model Interoperability indicator, the VFL server can select a client for a specific feature of VFL.

[0177] For example, based on the ML Model Interoperability indicator, in case the client is excluded from the VFL process, the VFL server may preferentially select a candidate client with alternative client(s) capable of ML model sharing as the client NWDAF.

[0178] The ML Model Interoperability indicator may include information on whether there are alternative client(s) with which the candidate client can share the ML model.

[0179] The VFL server may store ML Model Interoperability indicator information for each of the alternate client NWDAF(s) of each client NWDAF.

[0180] The ML Model Interoperability indicator of each candidate VFL client can be stored / managed in the NRF as a new NF profile parameter. In this case, the VFL server can obtain the information through an interaction procedure with the NRF if necessary.

[0181] 1-3) Step 1 - Step 3

[0182] The VFL server can check the status of the current VFL client(s) of the VFL process, such as NF load and time availability change. Based on this, the VFL server can determine whether to exclude each current VFL client(s) from the said VFL process. The VFL server can store relevant information.

[0183] For example, if the VFL server decides to exclude a specific VFL client among the current VFL client(s) from the VFL process, the VFL server may store information about the specific VFL client (e.g., terminated client NWDAF).

[0184] In the following, the group of current VFL client(s) of the VFL process is referred to as the existing training group.

[0185] 4-5) Step 4 - Step 5

[0186] The VFL server can perform an NF discovery procedure with NRF to select new clients to be added.

[0187] The VFL server may send a request message to the NRF to select a new client to be added. The request message may include information related to the VFL processor (training) (e.g., service region, NF type (NWDAF), ML model interoperability indicator, VFL client capability, VFL related information).

[0188] Based on the request message, the VFL server may receive a response message from the NRF. The response message may include information about the candidate client (e.g., candidate NWDAF ID(s), ML model interoperability indicator).

[0189] Based on this, the VFL server can determine new clients to add to the VFL process.

[0190] For example, based on the ML Model Interoperability indicator, in preparation for the case where the client is excluded from the VFL process, the VFL server may preferentially select candidate clients with alternative client(s) capable of ML model sharing as client NWDAF. For example, based on the ML Model Interoperability indicator, the VFL server may determine new clients to add to the VFL process.

[0191] 6) Step 6

[0192] The VFL server can create a mock training group (a group including the VFL client(s) from the existing training group and the new VFL client) by adding a determined new client to the existing training group.

[0193] The VFL server may transmit at least one of the following information to a new VFL client:

[0194] - Analytics ID

[0195] - VFL Association ID

[0196] - Information regarding the initial ML model to be used in the new VFL client mentioned above

[0197] - VFL Process Information

[0198] The VFL client(s) of the mock training group may be VFL client(s) of the existing training group and new VFL clients.

[0199] The VFL client(s) in the mock training group can use existing ML models.

[0200] The VFL server can send an indication to the VFL client(s) in the existing training group (e.g., each of multiple VFL clients) that mock training has started.

[0201] Based on this, the simulated training group can perform training using the ML model used in the existing VFL process.

[0202] 7) Step 7

[0203] To add a new VFL client to an existing training group, the VFL server can periodically check the accuracy of the mock training (or ML model) performed on the results of the mock training group.

[0204] For example, VFL client(s) of a mock training group (VFL client(s) in the existing training group and new VFL clients) can periodically calculate the accuracy of the ML model and send it to the VFL server.

[0205] For example, the VFL server can request the accuracy of the ML model from the VFL client(s) of the mock training group (VFL client(s) of the existing training group and new VFL clients) via a query. Based on this, the VFL client(s) of the mock training group (VFL client(s) of the existing training group and new VFL clients) can calculate the accuracy of the ML model and send it to the VFL server.

[0206] For example, the VFL server can receive the results of mock training from the VFL client(s) of the mock training group (VFL client(s) in the existing training group and new VFL clients). Based on these results, the VFL server can verify the accuracy of the ML model.

[0207] Here, accuracy may refer to the accuracy of the ML model used by the VFL client(s) of the mock training group. The ML model may be one used by the mock training group, the existing training group, and the new training group (VFL client(s) in the existing training group and the new VFL clients) to carry out the VFL process. For example, the ML model used by the mock training group and the existing training group (or the new training group) to carry out the VFL process may all be the same. Alternatively, the ML model may be changed during the VFL process.

[0208] 8) Step 8

[0209] Based on the results confirmed in step 7, the VFL server may decide to change the VFL training group.

[0210] For example, if the accuracy checked in step 7 exceeds the threshold, the VFL server may decide to replace the existing training group with a mock training group and proceed with the VFL process (training).

[0211] 9) Step 9

[0212] Based on the decision of step 8, the VFL server may send a VFL training request containing an indication that the training group has been replaced to the VFL client(s) of the mock training group (VFL client(s) in the existing training group and new VFL clients).

[0213] In this case, if training conditions such as the ML model change, the VFL server may transmit at least one of the following information to the VFL client(s) of the mock training group (VFL client(s) in the existing training group and new VFL clients):

[0214] - Analytics ID

[0215] - VFL Correlation ID

[0216] - VFL related information

[0217] Afterwards, the mock training group becomes a new training group and can perform the VFL process (training).

[0218] 10) Step 10

[0219] The VFL server can send a termination flag to the VFL client(s) of the existing training group.

[0220] Based on this, the VFL server can notify the VFL client(s) of the existing training group that the training group has changed.

[0221] Based on this, the VFL server can notify that it will not receive training results for existing training groups.

[0222] The following actions can be performed:

[0223] - The first network control node (e.g., Server NWDAF or Server AF) can create a mock training group to add new VFL clients in the VFL environment.

[0224] - The first network control node (e.g., server NWDAF or server AF) can check the accuracy results obtained from training from the VFL client(s) in the mock training group and decide to replace the training group.

[0225] - The first network control node (e.g., Server NWDAF or Server AF) can notify the VFL client(s) of the existing training group that they have been excluded from future training when a replacement is decided.

[0226] - The first network control node (e.g., Server NWDAF or Server AF) may request the VFL client of the mock training group to perform training when replacement is decided.

[0227] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.

[0228] FIG. 8 illustrates the procedure of a VFL server according to the disclosure of the present specification.

[0229] 1. A VFL (Vertical Federated Learning) server can obtain information about at least one candidate VFL client from an NRF (Network Repository Function).

[0230] 2. Based on information regarding the candidate VFL clients, the VFL server may determine a specific VFL client among at least one candidate VFL client.

[0231] 3. The above VFL server can transmit an indication of mock training to existing VFL groups and the specific VFL client.

[0232] The above mock training can be performed by the above existing VFL group and the above specific VFL client.

[0233] 4. Based on the above indication, the VFL server can receive the results of the mock training from the existing VFL group and the specific VFL client.

[0234] 5. Based on the results of the above simulation training, the VFL server may decide to add the specific VFL client to the existing VFL group.

[0235] Based on the decision of the VFL server to add the specific VFL client to the existing VFL group, the VFL server may send a training request to the existing VFL group and the specific VFL client.

[0236] The above training request may include an indication that the training group has been changed from the existing VFL group to a new VFL group.

[0237] The new VFL group may include the existing VFL group and the specific VFL client.

[0238] The above training request may include at least one of an Analytics ID, a VFL Correlation ID, or VFL-related information.

[0239] Based on the decision of the VFL server to add the specific VFL client to the existing VFL group, the VFL server may send a VFL message to the existing VFL group.

[0240] The VFL message may include i) information that training by the existing VFL group has ended and ii) information that the results of training by the existing VFL group will not be received.

[0241] The result of the above simulation training may be information regarding the accuracy of the above simulation training.

[0242] The step of the VFL server deciding to add the specific VFL client to the existing VFL group can be performed based on the accuracy of the mock training exceeding a threshold.

[0243] The information regarding the at least one candidate VFL client may include an interoperability indicator for each of the at least one candidate VFL client.

[0244] The above interoperability indicator may be information regarding whether the VFL client can be replaced with another VFL client for the training.

[0245] The step of the VFL server determining the specific VFL client among the at least one candidate VFL client can be performed based on the interoperability indicator.

[0246] The step of the VFL server obtaining information about at least one candidate VFL client from the NRF may include: the step of the VFL server sending a request message to the NRF; and the step of the request message including at least one of a service area for training, a Network Function (NF) type, interoperability indicator information, the capability of a VFL client, or training-related information, and the step of the VFL server receiving information about at least one candidate VFL client from the NRF based on the request message.

[0247] The above candidate VFL client, the above specific VFL client, and the VFL client included in the above existing VFL group may be NWDAF (Network Data Analytics Function).

[0248] The following drawings are prepared to illustrate a specific example of the present specification. The names of specific devices or specific signals / messages / fields described in the drawings are presented as examples, and therefore the technical features of the present specification are not limited to the specific names used in the following drawings.

[0249] FIG. 9 illustrates the procedure of a specific VFL client according to the disclosure of this specification.

[0250] 1. A specific VFL client can receive an indication of mock training from a VFL server.

[0251] 2. Based on the above indication, the specific VFL client can perform the above mock training with the existing VFL group.

[0252] 3. The specific VFL client above may transmit the results of the mock training to the VFL server.

[0253] 4. The specific VFL client above may receive a training request from the VFL server.

[0254] The above training request may include an indication that the training group has been changed from the existing VFL group to a new VFL group.

[0255] The new VFL group may include the existing VFL group and the specific VFL client.

[0256] 5. Based on the above training request, the specific VFL client may perform training with the existing VFL group.

[0257] The above training request may include at least one of an Analytics ID, a VFL association ID, or VFL-related information.

[0258] The result of the above simulation training may be information regarding the accuracy of the above simulation training.

[0259] The specific VFL client mentioned above and the VFL client included in the existing VFL group mentioned above may be NWDAF.

[0260] Hereinafter, a device for performing communication according to some embodiments of the present specification will be described.

[0261] For example, the device may include a processor, a transceiver, and memory.

[0262] For example, the processor can be configured to be operablely coupled with memory and the processor.

[0263] The operation performed by the above processor may include: a step in which a VFL (Vertical Federated Learning) server obtains information about at least one candidate VFL client from a NRF (Network Repository Function); a step in which, based on the information about the candidate VFL client, the VFL server determines a specific VFL client among the at least one candidate VFL client; a step in which the VFL server transmits an indication for mock training to an existing VFL group and the specific VFL client; a step in which the mock training is performed by the existing VFL group and the specific VFL client, and based on the indication, the VFL server receives the results of the mock training from the existing VFL group and the specific VFL client; and a step in which, based on the results of the mock training, the VFL server decides to add the specific VFL client to the existing VFL group.

[0264] Hereinafter, a processor of a device for providing communication according to some embodiments of the present specification will be described.

[0265] The operation performed by the above processor may include: a step in which a VFL (Vertical Federated Learning) server obtains information about at least one candidate VFL client from a NRF (Network Repository Function); a step in which, based on the information about the candidate VFL client, the VFL server determines a specific VFL client among the at least one candidate VFL client; a step in which the VFL server transmits an indication for mock training to an existing VFL group and the specific VFL client; a step in which the mock training is performed by the existing VFL group and the specific VFL client, and based on the indication, the VFL server receives the results of the mock training from the existing VFL group and the specific VFL client; and a step in which, based on the results of the mock training, the VFL server decides to add the specific VFL client to the existing VFL group.

[0266] Hereinafter, a non-volatile computer-readable medium storing one or more instructions for providing mobile communication according to some embodiments of the present specification will be described.

[0267] According to some embodiments of the present disclosure, the technical features of the present disclosure may be directly implemented in hardware, software executed by a processor, or a combination of both. For example, a method performed by a wireless device in wireless communication may be implemented in hardware, software, firmware, or any combination thereof. For example, software may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or other storage media.

[0268] In some examples, storage media are coupled to the processor so that the processor can read information from the storage media. Alternatively, the storage media can be integrated into the processor. The processor and storage media can reside in an ASIC. In other examples, the processor and storage media can reside as separate components.

[0269] Computer-readable media may include tangible and non-volatile computer-readable storage media.

[0270] For example, non-volatile computer-readable media may include RAM (Random Access Memory) such as SDRAM (Synchronization Dynamic Random Access Memory), ROM (Read-Only Memory), and NVRAM (Non-Volatile Random Access Memory); read-only memory (EEPROM); flash memory; magnetic or optical data storage media; or other media that can be used to store instructions or data structures. Non-volatile computer-readable media may also include combinations of the above.

[0271] Additionally, the method described herein may be realized at least partially by a computer-readable communication medium that transmits or transmits code in the form of instructions or data structures and can be accessed, read, and / or executed by a computer.

[0272] According to some embodiments of the present disclosure, a non-transient computer-readable medium stores one or more instructions thereon. The stored one or more instructions can be executed by a processor of a base station.

[0273] One or more stored commands may include the steps of: a VFL (Vertical Federated Learning) server obtaining information about at least one candidate VFL client from an NRF (Network Repository Function); a VFL server determining a specific VFL client among the at least one candidate VFL client based on the information about the candidate VFL client; a VFL server transmitting an indication for mock training to an existing VFL group and the specific VFL client; the mock training being performed by the existing VFL group and the specific VFL client, and based on the indication, the VFL server receiving the results of the mock training from the existing VFL group and the specific VFL client; and, based on the results of the mock training, the VFL server deciding to add the specific VFL client to the existing VFL group.

[0274] This specification may have various effects.

[0275] For example, VFL clients can be efficiently added in the VFL process.

[0276] The effects obtainable through the specific examples of this specification are not limited to those listed above. For example, there may be various technical effects that a person with ordinary skill in the related art can understand or derive from this specification. Accordingly, the specific effects of this specification are not limited to those explicitly described herein, but may include various effects that can be understood or derived from the technical features of this specification.

[0277] The claims described in this specification may be combined in various ways. For example, the technical features of the method claims in this specification may be combined to be implemented as a device, and the technical features of the device claims in this specification may be combined to be implemented as a method. Furthermore, the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a device, and the technical features of the method claims and the technical features of the device claims in this specification may be combined to be implemented as a method. Other implementations are within the scope of the following claims.

Claims

1. As a method, A step in which a VFL (Vertical Federated Learning) server obtains information about at least one candidate VFL client from an NRF (Network Repository Function); A step in which the VFL server determines a specific VFL client among the at least one candidate VFL client based on information regarding the candidate VFL client; The step of the above VFL server transmitting an indication for mock training to an existing VFL group and the above specific VFL client; The above mock training is performed by the above existing VFL group and the above specific VFL client, and Based on the above indication, the VFL server receives the results of the mock training from the existing VFL group and the specific VFL client; and A method comprising the step of, based on the results of the above-mentioned simulation training, deciding to add the specific VFL client to the existing VFL group on the VFL server.

2. In Paragraph 1, Based on the decision of the VFL server to add the specific VFL client to the existing VFL group, the VFL server further includes the step of sending a training request to the existing VFL group and the specific VFL client. The above training request includes an indication that the training group has been changed from the existing VFL group to a new VFL group, and A method comprising the new VFL group, the existing VFL group, and the specific VFL client.

3. In Paragraph 2, A method in which the above training request includes at least one of an Analytics ID, a VFL Correlation ID, or VFL-related information.

4. In any one of paragraphs 1 through 3, Based on the decision of the VFL server to add the specific VFL client to the existing VFL group, the VFL server further includes the step of sending a VFL message to the existing VFL group. A method in which a VFL message includes i) information that training by the existing VFL group has ended and ii) information that the results of training by the existing VFL group will not be received.

5. In any one of paragraphs 1 through 4, A method in which the result of the above simulation training is information about the accuracy of the above simulation training.

6. In any one of paragraphs 1 through 5, The step of the VFL server deciding to add the specific VFL client to the existing VFL group is performed based on the accuracy of the mock training exceeding a threshold.

7. In any one of paragraphs 1 through 6, The information regarding at least one candidate VFL client includes an interoperability indicator for each of the at least one candidate VFL client, and The above interoperability indicator is information regarding whether the VFL client can be replaced with another VFL client for the training, and The step of the VFL server determining the specific VFL client among the at least one candidate VFL client is performed based on the interoperability indicator.

8. In any one of paragraphs 1 through 7, The step of the above VFL server obtaining information about the at least one candidate VFL client from the above NRF is: The step of the above VFL server transmitting a request message to the above NRF; and The above request message includes at least one of the service area for training, NF (Network Function) type, interoperability indicator information, VFL client capability, or training-related information, and A method comprising the step of the VFL server receiving information about at least one candidate VFL client from the NRF based on the above request message.

9. In any one of paragraphs 1 through 8, A method in which the above candidate VFL client, the above specific VFL client, and the VFL client included in the above existing VFL group are NWDAF (Network Data Analytics Function).

10. As a method, A step in which a specific VFL client receives an indication for mock training from a VFL server; Based on the above indication, the step of the specific VFL client performing the mock training with the existing VFL group; The step of the specific VFL client transmitting the results of the mock training to the VFL server; The step of the specific VFL client receiving a training request from the VFL server; and The above training request includes an indication that the training group has been changed from the existing VFL group to a new VFL group, and The new VFL group mentioned above includes the existing VFL group and the specific VFL client, and A method comprising the step of a specific VFL client performing training with an existing VFL group based on the above training request.

11. In Paragraph 10, The above training request is a method that includes at least one of an analytics ID, a VFL association ID, or VFL related information.

12. In Paragraph 10 or 11, A method in which the result of the above simulation training is information about the accuracy of the above simulation training.

13. In any one of paragraphs 10 through 12, A method in which the above specific VFL client and the VFL client included in the above existing VFL group are NWDAF.

14. As a VFL server performing communication, At least one transmitter / receiver; It includes at least one processor, The operation performed by the above-mentioned at least one processor is a VFL server that is a method according to any one of claims 1 to 9.

15. As a specific VFL client performing communication, At least one transmitter / receiver; It includes at least one processor, The operation performed by the above at least one processor is a specific VFL client that is a method according to any one of claims 10 to 13.

16. As an apparatus in mobile communication, At least one processor; and It includes at least one memory that stores instructions and is operablely electrically connected to at least one processor, and A device in which the operation performed based on the execution of the above instruction by the at least one processor is a method according to any one of claims 1 to 9.

17. A non-volatile computer-readable storage medium that records instructions, A non-volatile computer-readable storage medium that, when the above instructions are executed by one or more processors, causes the one or more processors to perform a method according to any one of claims 1 through 9.

Images