Federated learning

Abstract

An embodiment of the present disclosure provides a method. The method may comprise the steps of: a first network entity receiving, from a second network entity associated with an application, a first request message including information associated with PFL activation and information associated with monitoring; selecting at least one PFL client to carry out a PFL function; and receiving a first report message including information associated with performance monitoring.

Description

Joint learning

[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] Personalized Federated Learning (PFL) that utilizes user privacy is being discussed. However, according to conventional technology, there is a problem in that specific methods for implementing PFL and PFL-related services have not been defined.

[0006] According to one embodiment of the present specification, a method is provided. The method may include the steps of: a first network entity receiving a first request message from a second network entity related to an application, the request message including information related to PFL activation and information related to monitoring; selecting at least one PFL client to perform a PFL function; and receiving a first report message including information related to performance monitoring.

[0007] According to one embodiment, a device for implementing the above method is provided.

[0008] According to one embodiment of the present specification, a method is provided. The method may include the steps of: the device transmitting a request message to a fourth network entity related to mobility, the request message related to a connection between the device and the fourth network entity; the device receiving a response message from the fourth network entity related to a connection between the device and the fourth network entity; the device receiving a second request message from a first network entity related to PFL, the request message including information related to PFL activation and information related to performance reporting; and the device receiving a first report message from the first network entity, the request message including information related to performance monitoring.

[0009] According to one embodiment, a device for implementing the above method is provided.

[0010] According to one embodiment of the present specification, a method is provided. The method may include the step of a second network entity related to an application transmitting to a first network entity a first request message containing information related to PFL activation and information related to monitoring.

[0011] According to one embodiment, a device for implementing the above method is provided.

[0012] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.

[0013] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.

[0014] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.

[0015] FIG. 4 shows an example of a 5G system structure to which the implementation of the present specification is applied.

[0016] FIGS. 5 and FIGS. 6 illustrate examples of registration procedures to which the implementation of the present specification applies.

[0017] FIG. 7 illustrates an example of a procedure related to a PFL according to one embodiment of the disclosure of the present specification.

[0018] FIG. 8 illustrates an example of operations according to one embodiment of the disclosure of the present specification.

[0019] 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 Multi-Carrier 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).

[0020] 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.

[0021] 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.

[0022] 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."

[0023] 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."

[0024] 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."

[0025] 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."

[0026] 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 (e.g., PDCCH)," "PDCCH" may be proposed as an example of "control information."

[0027] Technical features described individually within a single drawing in this specification may be implemented individually or simultaneously.

[0028] 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.

[0029] 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.

[0030] FIG. 1 shows an example of a communication system to which the implementation of the present specification is applied.

[0031] 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.

[0032] The three main requirement 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.

[0033] 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.

[0034] 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.

[0035] 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), Internet-Of-Things (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 (Augmented Reality) / VR (Virtual Reality) / MR (Mixed Reality) devices and may be implemented in the form of HMDs (Head-Mounted Devices) and HUDs (Head-Up Displays) 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.

[0036] 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.

[0037] 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).

[0038] 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) can 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.

[0039] 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.

[0040] 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).

[0041] 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

[0042] As described above, the numerical values ​​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. For example, 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).

[0043] 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

[0044] 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 eMTC (enhanced MTC). 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 with consideration 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.

[0045] FIG. 2 shows an example of a wireless device to which the implementation of the present specification applies.

[0046] 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.

[0047] 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).

[0048] 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).

[0049] 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).

[0050] 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.

[0051] Here, the processor (102) and memory (104) may be part of a communication modem / circuit / chip designed to implement 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.

[0052] 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).

[0053] 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 generally, the memory (204) may be placed outside the processing chip (201).

[0054] 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).

[0055] 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 code, instructions, and / or sets of instructions that perform descriptions, functions, procedures, proposals, methods, and / or 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 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.

[0056] 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.

[0057] 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, an RLC (Radio Link Control) layer, a PDCP (Packet Data Convergence Protocol) layer, an 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.

[0058] 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. 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 be composed of Random Access Memory (RAM), Dynamic RAM (DRAM), Read-Only Memory (ROM), Erasable Programmable ROM (EPROM), flash memory, volatile memory, non-volatile memory, hard drive, register, 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.

[0059] 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.

[0060] 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., mentioned 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).

[0061] 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).

[0062] 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.

[0063] In an implementation of the present specification, the UE may operate as a transmitting device in the uplink and as a receiving device in the downlink. In an implementation of the present 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 the present specification or to control a transceiver (106) to perform UE operations according to an implementation of the present 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 the present specification or to control a transceiver (206) to perform base station operations according to an implementation of the present specification.

[0064] In this specification, the base station may be referred to as Node B, eNode B, or gNB.

[0065] FIG. 3 shows an example of a UE to which the implementation of the present specification applies.

[0066] Referring to FIG. 3, the UE (100) can correspond to the first wireless device (100) of FIG. 2.

[0067] 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).

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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).

[0072] 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).

[0073] 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.

[0074] 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).

[0075] FIG. 4 shows an example of a 5G system structure to which the implementation of the present specification is applied.

[0076] The 5G system (5GS) structure consists of the following network functions (NF).

[0077] - AUSF (Authentication Server Function)

[0078] -AMF (Access and Mobility Management Function)

[0079] - DN (Data Network), for example, operator services, internet access, or third-party services

[0080] - USDF (Unstructured Data Storage Function)

[0081] - NEF (Network Exposure Function)

[0082] - I-NEF (Intermediate NEF)

[0083] - NRF (Network Repository Function)

[0084] - NSSF (Network Slice Selection Function)

[0085] - PCF (Policy Control Function)

[0086] - SMF (Session Management Function)

[0087] - UDM (Unified Data Management)

[0088] - UDR (Unified Data Repository)

[0089] - UPF (User Plane Function)

[0090] - UCMF (UE radio Capability Management Function)

[0091] - AF (Application Function)

[0092] - UE (User Equipment)

[0093] - (R)AN ((Radio) Access Network)

[0094] - 5G-EIR (5G-Equipment Identity Register)

[0095] - NWDAF (Network Data Analytics Function)

[0096] - CHF (CHarging Function)

[0097] 또한, 다음과 같은 네트워크 기능이 고려될 수 있다.

[0098] - N3IWF (Non-3GPP InterWorking Function)

[0099] - TNGF (Trusted Non-3GPP Gateway Function)

[0100] - W-AGF (Wireline Access Gateway Function)

[0101] Figure 4 shows the 5G system structure in a non-roaming case using a reference point representation showing how various network functions interact with each other.

[0102] In Figure 4, UDSF, NEF, and NRF are not described for clarity of the point-to-point diagram. However, all network functions shown can interact with UDSF, UDR, NEF, and NRF as needed.

[0103] 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.

[0104] The 5G system structure includes the following reference points.

[0105] - N1: Reference point between UE and AMF.

[0106] - N2: Reference point between (R)AN and AMF.

[0107] - N3: Reference point between (R)AN and UPF.

[0108] - N4: Reference point between SMF and UPF.

[0109] - N6: Reference point between the UPF and the data network.

[0110] - N9: Reference point between two UPFs.

[0111] The following reference points show the interactions that exist between the NF services of NF.

[0112] - N5: Reference point between PCF and AF.

[0113] - N7: Reference point between SMF and PCF.

[0114] - N8: Reference point between UDM and AMF.

[0115] - N10: Reference point between UDM and SMF.

[0116] - N11: Reference point between AMF and SMF.

[0117] - N12: Reference point between AMF and AUSF.

[0118] - N13: Reference point between UDM and AUSF.

[0119] - N14: Reference point between two AMFs.

[0120] - N15: Reference point between PCF and AMF for non-roaming scenarios, reference point between PCF and AMF of the visited network for roaming scenarios.

[0121] - 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)

[0122] - N22: Reference point between AMF and NSSF.

[0123] In some cases, two NFs may need to be connected to each other to service the UE.

[0124] The registration procedure is described. Refer to Section 4.2.2.2 of 3GPP TS 23.502 V16.3.0 (2019-12).

[0125] FIGS. 5 and FIGS. 6 illustrate examples of registration procedures to which the implementation of the present specification applies.

[0126] The UE must register with the network to receive services, enable mobility tracking, and enable reachability. The UE initiates the registration process using one of the following registration types.

[0127] - Initial registration for the 5GS; or

[0128] - Mobility registration update; or

[0129] - Periodic registration update; or

[0130] - Emergency registration

[0131] The general registration procedure of Figures 5 and 6 applies to all registration procedures described above, but the periodic registration update does not need to include all parameters used in other registration procedures.

[0132] The general registration procedure of Figures 5 and 6 is used when a UE is registered to a 3GPP connection when it is already registered to a non-3GPP connection, and vice versa. To register a UE to a 3GPP connection when it is already registered to a non-3GPP connection scenario, an AMF change may be required.

[0133] First, the procedure of Fig. 5 is explained.

[0134] (1) Step 1: The UE sends a Registration Request message to the (R)AN. The Registration Request message corresponds to the AN message.

[0135] A registration request message may include AN parameters. For NG-RAN, AN parameters include, for example, 5G-S-TMSI (5G SAE temporary mobile subscriber identity) or GUAMI (globally unique AMF ID), a selected PLMN (public land mobile network) ID (or PLMN ID and NID (network identifier)), and requested NSSAI (Requested network slice selection assistance information). AN parameters also include an establishment cause. The establishment cause provides the reason for requesting the establishment of an RRC connection. Whether and how the UE includes the requested NSSAI as part of the AN parameters depends on the value of the access stratum connection establishment NSSAI inclusion mode parameter.

[0136] The registration request message may include a registration type. The registration type indicates whether the UE wants to perform an initial registration (e.g., the UE is in the RM-DEREGISTERED state), or a mobility registration update (e.g., the UE is in the RM-REGISTERED state and initiates the registration process because the UE moves, or the UE wants to update a capability or protocol parameter, or requests a change to the set of network slices allowed for the UE to use), or a periodic registration update (e.g., the UE is in the RM-REGISTERED state and initiates the registration process due to the expiration of the periodic registration update timer), or an urgent registration (e.g., the UE is in the restricted service state).

[0137] When a UE performs initial registration, the UE specifies the UE ID in the registration request message as follows, listed in order of lowest priority.

[0138] i) If the UE has a valid EPS (evolved packet system) GUTI (globally unique temporary identifier), the 5G-GUTI mapped from the EPS GUTI;

[0139] ii) Native 5G-GUTI assigned by the PLMN for which the UE is attempting to register (if available);

[0140] iii) Native 5G-GUTI assigned by a PLMN equivalent to the PLMN for which the UE is attempting to register;

[0141] iv) Native 5G-GUTI assigned by other PLMNs (if available);

[0142] v) Otherwise, the UE includes SUCI (subscriber concealed identifier) ​​in the registration request message.

[0143] If the UE performing the initial registration has both a valid EPS GUTI and a native 5G-GUTI, the UE also marks the native 5G-GUTI as an additional GUTI. If one or more native 5G-GUTIs are available, the UE selects the 5G-GUTIs from items (ii)-(iv) in the list above in decreasing order of priority.

[0144] When the UE performs initial registration with native 5G-GUTI, the UE displays relevant GUAMI information in AN parameters. When the UE performs initial registration with SUCI, the UE does not display GUAMI information in AN parameters.

[0145] In the case of emergency registration, SUCI is included if the UE does not have a valid 5G-GUTI, and PEI is included if the UE does not have a SUPI (subscriber permanent identifier) ​​and does not have a valid 5G-GUTI. In other cases, a 5G-GUTI is included, which indicates the last serving AMF.

[0146] The registration request message may also include security parameters, PDU session status, etc. Security parameters are used for authentication and integrity protection. The PDU session status indicates a previously established PDU session in the UE. When the UE is connected to two AMFs belonging to different PLMNs via a 3GPP connection and a non-3GPP connection, the PDU session status indicates the established PDU session of the current PLMN in the UE.

[0147] (2) Step 2: (R)AN selects AMF.

[0148] If 5G-S-TMSI or GUAMI is not included, or if 5G-S-TMSI or GUAMI does not represent a valid AMF, (R)AN selects an AMF based on (R)AT and the requested NSSAI, where available.

[0149] If the UE is in the CM-CONNECTED state, (R)AN can forward a registration request message to the AMF based on the UE's N2 connection.

[0150] If (R)AN cannot select a suitable AMF, (R)AN performs AMF selection by forwarding a registration request message to the AMF configured in (R)AN.

[0151] (3) Step 3: (R)AN sends a registration request message to the new AMF. The registration request message corresponds to the N2 message.

[0152] The registration request message may include all information and / or part of the information contained in the registration request message received from the UE described in Step 1.

[0153] The registration request message may include N2 parameters. When NG-RAN is used, the N2 parameters include the selected PLMN ID (or PLMN ID and NID), location information and cell ID associated with the cell where the UE is camping, and a UE context request indicating that a UE context including security information in NG-RAN must be established. When NG-RAN is used, the N2 parameters also include the cause for establishment.

[0154] If the registration type indicated by the UE is a periodic registration update, steps 4-19 described below may be omitted.

[0155] (4) Step 4: If the UE's 5G-GUTI is included in the registration request message and the serving AMF has changed since the last registration procedure, the new AMF may call the Namf_Communication_UEContextTransfer service operation on the previous AMF, including the full registration request NAS (non-access stratum) message to request the UE's SUPI and UE context.

[0156] (5) Step 5: The previous AMF can respond to the new AMF for the Namf_Communication_UEContextTransfer call, including the UE's SUPI and UE context.

[0157] (6) Step 6: If SUCI is not provided by the UE or is not retrieved from the previous AMF, the new AMF may initiate the identity request procedure by sending an identity request message to the UE to request SUCI.

[0158] (7) Step 7: The UE may respond with an Identity Response message containing SUCI. The UE derives SUCI using the provided public key of the home PLMN (HPLMN).

[0159] (8) Step 8: The new AMF may decide to call AUSF to initiate UE authentication. In this case, the new AMF selects AUSF based on SUPI or SUCI.

[0160] (9) Step 9: Authentication / security may be established by UE, new AMF, AUSF and / or UDM.

[0161] (10) Step 10: If the AMF is changed, the new AMF may call the Namf_Communication_RegistrationCompleteNotify service operation to notify the previous AMF that UE registration is complete for the new AMF. If the authentication / security procedure fails, registration is rejected and the new AMF may call the Namf_Communication_RegistrationCompleteNotify service operation with a reject indication reason code for the previous AMF. The previous AMF may continue as if no UE context passing service operation was received.

[0162] (11) Step 11: If the PEI is not provided by the UE or has not been retrieved from the previous AMF, the new AMF may initiate an Identity Request procedure by sending an Identity Request message to the UE to retrieve the PEI. The PEI is transmitted in encryption, except in cases where the UE cannot perform emergency registration and be authenticated.

[0163] (12) Step 12: Optionally, the new AMF can call the N5g-eir_EquipmentIdentityCheck_Get service operation to start ME ID checking.

[0164] Now, the procedure of Fig. 6 following the procedure of Fig. 5 is explained.

[0165] (13) Step 13: If you perform Step 14 below, the new AMF can select a UDM based on SUPI, and the UDM can select a UDR instance.

[0166] (14) Step 14: New AMFs can be registered with UDM.

[0167] (15) Step 15: The new AMF can select PCF.

[0168] (16) Step 16: The new AMF may optionally establish / modify AM policy associations.

[0169] (17) Step 17: The new AMF can send update / release SM context messages (e.g., Nsmf_PDUSession_UpdateSMContext and / or Nsmf_PDUSession_ReleaseSMContext) to the SMF.

[0170] (18) Step 18: If the new AMF and the previous AMF are in the same PLMN, the new AMF can send a request to modify the UE context to N3IWF / TNGF / W-AGF.

[0171] (19) Step 19: N3IWF / TNGF / W-AGF can send a UE context modification response to the new AMF.

[0172] (20) Step 20: After the new AMF receives a response message from N3IWF / TNGF / W-AGF in Step 19, the new AMF can register with UDM.

[0173] (21) Step 21: The new AMF sends a Registration Accept message to the UE.

[0174] The new AMF sends a registration acceptance message to the UE indicating that the registration request has been accepted. If the new AMF assigns a new 5G-GUTI, the 5G-GUTI is included. If the UE is already in the RM-REGISTERED state via another connection on the same PLMN, the UE uses the 5G-GUTI received in the registration acceptance message for both registrations. If the registration acceptance message does not include a 5G-GUTI, the UE uses the 5G-GUTI assigned to the existing registration for the new registration as well. If the new AMF assigns a new registration area, it transmits the registration area to the UE via the registration acceptance message. If the registration acceptance message does not contain a registration area, the UE considers the previous registration area to be valid. Mobility Restrictions are included when mobility restrictions apply to the UE and the registration type is not an urgent registration. The new AMF indicates the PDU session established for the UE in the PDU session state. The UE locally removes internal resources associated with PDU sessions that are not marked as established in the received PDU session state. When a UE connects to two AMFs belonging to different PLMNs via a 3GPP connection and a non-3GPP connection, the UE locally removes internal resources associated with the PDU session of the current PLMN that are not indicated as established in the received PDU session state. If PDU session state information is present in the registration acceptance message, the new AMF instructs the UE on the PDU session state.

[0175] The Allowed NSSAI provided in the registration acceptance message is valid in the registration area and applies to all PLMNs having a tracking area included in the registration area. The Mapping of Allowed NSSAI is to map the HPLMN S-NSSAI to each S-NSSAI of the Allowed NSSAI. The Mapping of Configured NSSAI is to map the HPLMN S-NSSAI to each S-NSSAI of the Configured NSSAI for the serving PLMN.

[0176] Additionally, the new AMF optionally performs UE policy association establishment.

[0177] (22) Step 22: If the UE succeeds in updating itself, it can send a Registration Complete message to the new AMF.

[0178] The UE can send a registration completion message to the new AMF to check if a new 5G-GUTI has been assigned.

[0179] (23) Step 23: In the case of registration via a 3GPP connection, if the new AMF does not release the signaling connection, the new AMF may send RRC Inactive Assistance information to the NG-RAN. In the case of registration via a non-3GPP connection, if the UE is in a CM-CONTENED state on the 3GPP connection, the new AMF may send RRC Inactive Assistance information to the NG-RAN.

[0180] (24) Step 24: AMF can perform information updates on UDM.

[0181] (25) Step 25: The UE can execute network slice-specific authentication and authorization (NSSAA) procedures.

[0182] For reference, in the disclosure of this specification, the terms terminal and User Equipment (UE) may be used interchangeably. For example, descriptions related to a terminal may apply to a UE, and descriptions related to a UE may apply to a terminal.

[0183] A study on 6G mobile communication systems, Release 20 / [FS_6G-REQ] Study on 6G Use Cases and Service Requirements (SP-241391), has been initiated in SA1, and agreed-upon candidate scenarios are scheduled to be added to TR 22.870. However, the discussion is limited to basic requirements, and the definitions of functional structures, procedures, and detailed protocols (stage 2 / stage 3) have not yet begun as studies have not started. In other words, the technology for implementing actual services has not been defined.

[0184] In particular, various services designed with 6G in mind, such as sensing services, immersive reality services, and / or multi-domestic services, are being discussed. These services are expected to provide users with more effective, high-quality services and Quality of Experience (QoE) by leveraging Artificial Intelligence (AI) technology. It is highly likely that various AI-related functions will be integrated into on-device AI terminals, base stations, and local / central network servers.

[0185] In various examples of the present disclosure, examples of system functions and procedures capable of effectively controlling personalized federated learning operations and / or functions in a mobile communication system are described, targeting 5G evolution / 6G systems in a zero-touch configuration / operation environment where network automation is extended.

[0186] Personalized Federated Learning (PFL) utilizing user privacy is being discussed. However, according to conventional technology, there is a problem in that specific methods for implementing PFL and PFL-related services have not been defined. For example, there is a problem in that operations and / or functions related to PFL cannot be effectively performed or / or controlled.

[0187] This specification proposes methods such as the following examples to solve the above problems. The methods presented below may be performed or used selectively, in combination, or complementarily.

[0188] According to various examples of the present disclosure, various federated learning functions are supported from the perspective of the entire system, and at the same time, customized services can be provided through AI / Machine Learning (AI / ML) models customized for individual users.

[0189] For example, in a system that supports personalized federated learning, individual users and / or local users can have the privacy of their individual data guaranteed. In addition, it can be guaranteed that customized services optimized for individual users and / or local users are provided.

[0190] In addition, the present specification specifies embodiments based on the structure, procedures, messages, etc. of a 5G mobile communication system, but these are merely examples. The scope of the present specification is not limited by the embodiments described below and may be applied to evolved forms of 6G mobile communication systems and / or mobile communication systems after 6G.

[0191] In various examples of the disclosure of this specification, the following description may apply to PFL. PFL may be an example of federated learning performed in a manner that protects user privacy. For example, a PFL client may possess a locally trained personalized model (e.g., an AI model). Based on the personalized model, the PFL client may transmit parameters (or information) related to PFL to a network (e.g., a server, a central server, a PFL server, etc.). The transmitted parameters (or information) may be reflected in a global model to improve the performance of the global model. However, user privacy may be protected by the PFL client not transmitting the original data collected by the PFL client (e.g., sensitive original data such as personal health information) itself to the network (e.g., a server, a central server, a PFL server, etc.). The global model may reflect various user experiences.

[0192] In various examples of the disclosure of this specification, the following description may apply to user interaction. User interaction may reflect an individual's behavioral patterns. A PFL client may provide optimized services by applying the results of user interaction to a model within the PFL client (e.g., a personalized model). Additionally, based on the results of user interaction, the quality of data and the performance of the model may be improved. Furthermore, the PFL client may also improve the data quality and / or performance of the global model by transmitting parameters (or information) related to PFL based on the results of user interaction and the model within the PFL client to a network (e.g., a server, a central server, a PFL server, etc.).

[0193] In the disclosure of this specification, a PFL client may be at least one of the following examples:

[0194] - Device (e.g., user device). Devices include, for example, User Equipment (UE), smartphones, health check devices for specific purposes, etc.

[0195] - Local server (in home environment or in private 5G network, etc.)

[0196] In the disclosure of this specification, the operation of a PFL client may be applied to at least one of the various examples described above. Additionally, in the disclosure of this specification, a UE or device may be used as a representative example of a PFL client. Descriptions related to a UE or device may be applied to a PFL client. Furthermore, the names of the PFL client and the names of the examples described above are merely examples, and descriptions related to a PFL client in the disclosure of this specification may be applied to a client that performs FL operations with consideration for user privacy.

[0197] In the disclosure of this specification, the PFL server may be at least one of the following examples:

[0198] - Servers, Application Functions (AFs), network entities related to applications, Central cloud servers, servers included in carrier network AFs and / or NWDAFs (e.g., Central cloud servers), servers included in third-party AFs (e.g., Central cloud servers), etc.

[0199] In the disclosure of this specification, the operation of the PFL server may be applied to at least one of the various examples described above. Additionally, in the disclosure of this specification, a network entity related to an AF or application may be used as a representative example of the PFL server. Descriptions related to network entities related to an AF or application may be applied to the PFL client. Furthermore, the names of the PFL server and the names of the examples described above are merely examples, and descriptions related to the PFL server in the disclosure of this specification may be applied to a server or network entity related to FL operation considering user privacy.

[0200] PFL explains an example of Supporting Customized Intelligence using Personalized Federated Learning.

[0201] In everyday life, users seek personalized AI assistance for a more convenient lifestyle while maintaining the privacy of user-specific data.

[0202] For this purpose, PFL, a powerful AI technology, can be considered. By training locally personalized models on individual data within user devices or trusted local environments, PFL enables the creation of customized healthcare solutions, such as personalized disease prediction and treatment plans, while preserving individual patient privacy. Furthermore, it can facilitate the creation of customized smart home care solutions that support personalized patterns and health trends, while ensuring the privacy of resident data such as heart rate and sleep patterns.

[0203] This type of personalized AI assistance can help users detect early signs of health problems based on personal health data and may lead to specific user behaviors.

[0204] The following may be considered as prerequisites related to PFL.

[0205] In a smart home environment, PFL client operations such as the following examples can be performed. For example, individual healthcare devices can acquire patient health data using sensing functions. Smart home devices / servers connected to sensors, cameras, home appliances, etc., can acquire the patient's lifestyle patterns. For example, individual healthcare devices or smart home devices / servers are equipped with personalized federated learning capabilities and can be connected to a central server of a medical center or service provider via a 6G system.

[0206] Examples of post-conditions related to PFL are as follows. For instance, individual users can use personalized intelligent AI services while maintaining their privacy.

[0207] Regarding PFL, some or all of the following existing features may be utilized. The 5G system supports horizontal federated learning and vertical federated learning without UE participation in TS 23.288 V19.1.0. The 5G system provides support for member UE selection for federated learning in TS 23.501 V19.2.1 and TS 23.502 V19.2.0.

[0208] Regarding PFL, the following examples may be required. For example, subject to user consent, operator policy, and trusted third-party requests, 6G systems must be able to support mechanisms for collecting user-specific data to support personalized AI while maintaining privacy. For example, subject to user consent, operator policy, and trusted third-party requests, 6G systems must be able to support mechanisms for monitoring the performance of personalized AI-ML models and exposing state information of AI / ML sessions to third-party AI / ML applications.

[0209] Various examples according to one embodiment of the disclosure of this specification are technically implemented, and examples of methods for implementing the requirements of the system are described.

[0210] [1] In some implementations, a procedure to verify subscriber information and / or SLA may be performed.

[0211] For example, a PFL client (e.g., a network of a terminal or local server) may perform a registration step (or procedure) to the network. A network node verifying subscriber information may, during the registration step (or procedure), determine whether the PFL client is capable of using AI functions (e.g., PFL functions) based on the subscriber information. For example, the network node verifying subscriber information may be a UDM. However, this is merely an example, and the scope of disclosure of this specification is not limited to UDM. For example, regardless of the name of the network node, a network node capable of verifying subscriber information may be a network node verifying subscriber information. Additionally, during the registration step (or procedure), the network node verifying subscriber information may, by checking protocols such as Service Level Agreements (SLAs) with the carrier and third-party service providers, authorize whether the PFL client (e.g., a network of a terminal or local server) is a legitimate user / terminal and / or local server. A network node verifying subscriber information can enable a PFL client (e.g., a terminal or a local server's network) to utilize the PFL function in a mobile communication system after verifying that the PFL client is capable of using an AI function (e.g., a PFL function) and / or authorizing that the PFL client (e.g., a terminal or a local server's network) is a legitimate user / terminal and / or local server.

[0212] [2] In some implementations, PFL clients (e.g., terminals and local servers) can perform the action of registering PFL functions.

[0213] For example, a PFL client may transmit capability information related to a PFL function to a network (e.g., Network Repository Function (NRF), and / or a management function as an example in FIG. 7). For example, capability information related to a PFL function may be information that the PFL client supports an operation related to the PFL. For example, before using a PFL function, the PFL client may register (e.g., save) a PFL function by transmitting the FL function (e.g., PFL function) and / or related information to a node that registers / manages capabilities for a specific function (e.g., NRF, and / or a management function as an example in FIG. 7). Additionally, the PFL client may update the PFL function if necessary.

[0214] For example, the PFL function can be utilized later by third network nodes or another PFL client to find a candidate PFL client (to perform co-work).

[0215] For example, PFL functions may be used for authentication and / or authorization to use PFL functions.

[0216] [3] Examples of user interaction and / or user-related data considered in the disclosure of this specification are described.

[0217] Data and / or user-related data obtained by a PFL client based on user interaction may include at least one of the following examples:

[0218] - Data directly entered by the user through a device (e.g., PFL client) (e.g., objective data such as weight and height, subjective data such as one's health-related habits, etc.);

[0219] - Data perceived by IoT sensors (e.g., PFL client, IoT sensors included in the PFL client, or IoT sensors controlled by the PFL client, etc.) (e.g., personal health-related data such as heart rate, body temperature, etc., data regarding the local space such as indoor temperature / humidity); and / or

[0220] - Data recognized by local servers (e.g., PFL clients) or devices (e.g., PFL clients) (e.g., various data that can be collected by household appliances or robots).

[0221] However, the examples described above are merely examples of data obtained based on user interaction and / or data related to the user, and the scope of disclosure of this specification is not limited thereto. Data obtained based on user interaction and / or data related to the user may include any data that the PFL client can obtain through interaction with the user, and / or any data that the user inputs to the PFL client.

[0222] For example, the user can store their own health information, such as their physical data (e.g., weight, and / or height), blood pressure, and / or blood sugar levels, through the device's health app. Sensors attached to or built into the device can detect and periodically store the user's heart rate and body temperature.

[0223] It is assumed that the user has agreed that such information (e.g., data obtained based on user interactions and / or data related to the user) may be used as data for training and federated learning of AI models related to the individual's health in the future.

[0224] The terminal may be a PFL client. The terminal may receive a PFL activation request. For example, the terminal may receive a PFL activation request from a network (e.g., the management function of FIG. 7). When the terminal receives a PFL activation request, such information (e.g., data obtained based on user interaction and / or data related to the user) may be used as local data input for AI model training and / or federated learning.

[0225] The terminal can perform local model training without transmitting the relevant information (e.g., data acquired based on user interaction and / or user-related data) to the PFL server.

[0226] As a result, a local model capable of making personalized health suggestions based on personal data (e.g., need for increased hydration, need to increase sleep time, and / or recommend a hospital visit / internal medicine consultation, etc.) can be generated / stored on the terminal. Personalized health suggestions may be examples of local inference information of the local model.

[0227] The terminal may provide local inference information to the user, and / or transmit the local model or the result value of the local model (e.g., local inference information) to the PFL server to obtain more accurate inference information.

[0228] Meanwhile, the terminal can perform PFL monitoring during this process. For example, user satisfaction with the terminal's local inference information itself can be collected as service experience and / or QoE. Additionally, during this local model training process, AIML model information regarding the AI ​​algorithm itself (e.g., model accuracy, training time, and / or inference time, etc.) can be collected.

[0229] For example, monitoring information collected by a PFL client (e.g., terminal) may include at least one of service experience, QoE, and / or AIML model information (e.g., model accuracy, training time, and / or inference time, etc.).

[0230] For example, a PFL client (e.g., a terminal) can transmit collected monitoring information to a PFL server. The monitoring information can be utilized to assist in determining the next steps of the PFL. For example, the PFL server can adjust the values ​​of parameters used in the model to increase the level of model refinement and send them locally (e.g., to the PFL client).

[0231] [4] PFL monitoring

[0232] A core network function of a mobile communication system (e.g., a management function) may receive requests for PFL function activation (or PFL activation) and / or PFL monitoring requests from a third-party server. The core network function (e.g., a management function) may select an appropriate PFL client and monitor the performance of PFL execution.

[0233] For example, performance monitoring (e.g., information related to performance monitoring) may mean one or more of the examples below:

[0234] - QoS for the session for PFL operation;

[0235] - PFL client service experience, QoE, etc.;

[0236] - Model accuracy and / or model performance for PFL (e.g., values ​​representing model performance such as Mean Squared Error, Mean Absolute Error, R-squared, etc.);

[0237] - Success status of PFL activation / deactivation of the PFL client, performance information related to PFL execution (e.g., training time, whether the model was updated, and / or whether a custom model was created, etc.); and / or

[0238] - Information related to the AIML model, such as model parameters (e.g., weights and / or biases), model gradients, and / or metadata such as the size of the local data or training time. For example, metadata may include model parameters, model gradients, and / or the size of the local data, and / or the training time of the local data. Information related to the AIML model may include metadata.

[0239] 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.

[0240] FIG. 7 illustrates an example of a procedure related to a PFL according to one embodiment of the disclosure of the present specification.

[0241] In the example of FIG. 7, the PFL client may be a terminal or a server. The terminal may be, for example, a smart home device.

[0242] In the example of FIG. 7, the server may be, for example, a server that supports functions and / or operations related to PFL. For example, the server may be a PFL server. For example, the PFL server may be a 3rd party AF.

[0243] 1. A registration procedure may be performed. During the registration procedure, whether the subscriber information of the PFL client supports PFL and user consent may be verified.

[0244] In some implementations, step 1 may be performed optionally. For example, step 1 may be performed only when the PFL client is a terminal.

[0245] For example, a PFL client may be a terminal. In this case, the terminal may perform a registration procedure to access the core network of the mobile communication system. For example, the terminal may perform a registration procedure according to the examples of FIGS. 5 and 6.

[0246] According to the prior art, while a registration procedure is being performed, a network entity included in the CN NFs (e.g., a network entity related to mobility control, such as an AMF) may verify subscriber information and / or user consent. According to one embodiment of the disclosure of this specification, a network entity included in the CN NFs (e.g., a network entity related to mobility control, such as an AMF) may additionally verify subscriber information, such as whether the terminal can become a PFL client and / or whether the terminal can operate as a PFL client. For reference, in the disclosure of this specification, network entities related to mobility control and network entities related to mobility may be used as terms with the same meaning.

[0247] For example, the terminal's subscriber information may include user consent. For example, user consent may be user consent for the collection of UE data. User consent indicates whether the user has provided consent for the collection, distribution, and / or analysis of UE-related data. User consent may be provided by purpose (e.g., analysis, model training). For example, User consent Purpose (UcPorpose) may include one or more of the following:

[0248] "ANALYTICS": User consent for analysis;

[0249] "MODEL_TRAINING": User consent for model training;

[0250] "NW_CAP_EXPOSURE": User consent for network capability exposure; and / or

[0251] "EDGEAPP_UE_LOCATION": User consent for the manipulation of UE information for the purpose of discovering UE location by Edge Applications (EDGEAPP) Edge Application Server (EAS) objects.

[0252] According to one embodiment of the disclosure of the present specification, in the step of checking subscriber information of a terminal capable of operating as a PFL client (e.g., an operation performed by a functional node after receiving a message of step 1 and / or step 2), it can be checked whether the user consent included in the subscriber information includes information that the "MODEL_TRAINING" item is available.

[0253] When a terminal successfully connects to the network, the AMF or UDM node of the core network that holds the UE's context information can notify the Management function of the registration status of the terminal that can operate as a PFL client.

[0254] A PFL client may be a local server. In this case, the local server can be connected to a network capable of performing the role of a PFL client through offline command and / or configuration processes. For example, the local server can establish an environment capable of interacting with a management function. For instance, if the local server is an Operations, Administration, and Maintenance (OAM) server, the OAM server and the management function can interact through wired network configurations and commands established by the operator.

[0255] 2. The PFL client may send a request message to the management function. For example, the request message may include information about the function related to the PFL and / or information related to authentication and / or authorization related to the PFL.

[0256] For example, a PFL client can register function information related to the PFL (e.g., AI-related capability information capable of performing PFL functions) and send a request message to a management function included in the network to perform authentication / authorization for the use of the PFL functions.

[0257] For example, the message of Step 2 may be transmitted via signaling of the control plane, such as a Non Access Stratum (NAS) message of the prior art or a service operation between NFs. The message of Step 2 may also be transmitted via a secured user plane tunnel that can be established between the terminal and the NF. With respect to the message of Step 2, prior art messages or parameters may be applied as is or extended, and / or new messages and protocols may be defined.

[0258] In some implementations, the management function may determine whether to permit the PFL client to act as a PFL client and / or to perform PFL-related functions (or operations). For example, the management function may receive a request message of step 2 from the PFL client (e.g., terminal). In this case, based on the terminal's subscriber information and / or pre-configured local policy information, the management function may determine whether to permit the PFL client to act as a PFL client and / or to allow the PFL client to perform PFL-related functions (or operations). For example, if the terminal's subscriber information includes information regarding the terminal being able to act as a PFL client and / or information regarding the terminal being able to perform PFL-related functions (or operations), the management function may permit the PFL client to act as a PFL client and / or to allow the PFL client to perform PFL-related functions (or operations).

[0259] In some implementations, subscriber information may also include user consent as described in step 1. Refer to step 1 for a description of user consent. In this case, based on the terminal's subscriber information and / or pre-configured local policy information, the management function may determine whether to permit the PFL client to operate as a PFL client and / or the PFL client to perform PFL-related functions (or operations). For example, based on at least one of the following cases: where the user consent included in the subscriber information is related to "MODEL_TRAINING"; where the terminal's subscriber information includes information related to the terminal being able to operate as a PFL client; and / or where the terminal's subscriber information includes information related to the terminal being able to perform PFL-related functions (or operations).

[0260] Here, the terminal's subscriber information may be stored in the Management function in advance through the interaction between the Management function and the UDM, or through the operator's configuration. In some implementations, the Management function may request subscriber information from the UDM based on receiving a request message from the PFL client, and receive the terminal's subscriber information from the UDM.

[0261] In some implementations, functional information related to PFL may also be referred to as AI-related capability information. Functional information related to PFL (e.g., AI-related capability information capable of performing PFL functions) may include one or more of the examples below. AI-related capability information may include one or more of the examples below:

[0262] FL capability type: PFL;

[0263] Accuracy checking capability;

[0264] Model performance (e.g., training time, inference time) checking function; and / or

[0265] PFL QoE verification function, etc.

[0266] 3. The server may transmit a request message to a management function. The request message may include at least one of information related to PFL client selection (e.g., reference information or condition information), information related to PFL activation, and / or information related to requesting monitoring related to the PFL (e.g., performance monitoring related to the PFL). For example, by transmitting a request message, the server may request the management function to select an appropriate PFL client and / or activate the PFL and monitor the performance of the PFL. The request message may include information related to PFL client selection (e.g., reference information or condition information) (e.g., terminal location information, terminal type information, QoS / QoE related information provided to the terminal, etc.).

[0267] For example, a server (e.g., a PFL server) may decide to use the PFL method (or operation or function) with the support of a mobile communication system to perform application layer services. In this case, the server (e.g., a PFL server) may request the network's management function to perform PFL activation and subsequent performance monitoring.

[0268] For reference, although the NEF is not shown in the example of Fig. 7, if the PFL server is a 3rd party server, the PFL server can access the management function through the NEF. For example, in this case, the PFL server can send a request message to the management function via the NEF.

[0269] 4. The management function can select PFL clients. For example, the management function can select one or more PFL clients to perform PFL.

[0270] For example, based on information included in a request message received from a PFL server, the management function may select one or more PFL clients to perform PFL locally. For example, the management function that received a request message from at least one PFL client in step 2 may select one or more PFL clients to perform PFL based on information related to the selection of PFL clients in step 3 (e.g., reference information or condition information).

[0271] 5. The management function may send a request message to one or more selected PFL clients. For example, the one or more PFL clients may include the PFL client illustrated in FIG. 7. If there are two or more PFL clients, the one or more PFL clients may include the PFL client of FIG. 7 and at least one PFL client.

[0272] For example, the management function can request selected PFL clients to perform PFL activation and / or subsequent performance monitoring.

[0273] For example, the request message of Step 7 may include information related to PFL activation and / or information related to performance monitoring (e.g., information related to performance monitoring related to PFL). For example, information related to PFL activation may be information requesting (or instructing) the PFL client to activate functions and / or functions related to PFL. For example, information related to performance monitoring related to PFL may be information requesting the PFL client to monitor performance related to PFL.

[0274] For example, information related to performance monitoring included in the request message of Step 5 (e.g., information related to performance monitoring related to PFL) may include one or more of the following information:

[0275] - Information requesting QoS for a session for PFL operation;

[0276] - Information requesting PFL client service experience, QoE, etc.;

[0277] - Information requesting model accuracy and model performance for PFL;

[0278] - Information requesting the success or failure of PFL activation / deactivation of the PFL client, and information related to PFL execution (e.g., training time, whether the model was updated, whether a custom model was created, etc.); and / or

[0279] - Information requesting information related to the AIML model, such as model parameters (e.g., weights and / or biases), model gradients, and / or metadata such as the size of the local data or training time.

[0280] In some implementations, based on the one or more pieces of information included in the request message of step 5, the PFL client in step 8 may transmit a report message containing information corresponding to the one or more pieces of information.

[0281] In some implementations, the request message of step 5 may not include one or more of the above information, but may only include information related to performance monitoring (e.g., information related to performance monitoring related to PFL). In this case, even if the information related to performance monitoring (e.g., information related to performance monitoring related to PFL) does not include information requesting specific information, the PFL client may send a report message in step 8 that includes one or more of the information related to performance monitoring in step 8.

[0282] In some implementations, if necessary, the management function may request performance monitoring from network nodes as well as PFL clients to obtain QoS-related information available from network nodes. In this case, network nodes may report information related to performance monitoring to the server.

[0283] 6-7. A PFL client may perform user interactions and / or PFL work tasks. For example, based on the receipt of a request message, a PFL client may perform user interactions and / or PFL work tasks (or processes, or procedures, or functions, or actions). In some implementations, step 6 may be performed optionally.

[0284] For example, a PFL client performs a PFL work task (or process, or procedure, or function, or operation) based on information set locally and / or information received from a PFL server.

[0285] For example, in step 6, the PFL client can collect necessary information through interaction with the user and perform PFL work tasks (or procedures, functions, or actions) based on the collected information.

[0286] In some implementations, information obtained based on user interaction may be information that the PFL client obtains in real time. Alternatively, information obtained based on user interaction may be pre-set preference information and / or pre-collected statistical information.

[0287] 8. A PFL client can send a report message to a management function. For example, the report message may include information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance).

[0288] For example, a PFL client can report to the management function information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance) collected during PFL work tasks (or processes, or procedures, or functions, or operations) performed locally.

[0289] For example, information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance) included in a message reported by a PFL client may include one or more of the following information:

[0290] - Measured QoS for the session for PFL operation;

[0291] - PFL client's measured service experience, measured QoE, etc.;

[0292] - Measured PFL model accuracy and / or model performance (e.g., values ​​representing model performance such as Mean Squared Error, Mean Absolute Error, R-squared, etc.);

[0293] - Whether PFL activation / deactivation was measured successful, performance-related information measured during PFL execution (e.g., training time, whether the model was updated, and / or whether a custom model was created, etc.); and / or

[0294] - Information related to the AIML model, such as measured model parameters (e.g., weights and / or biases), model gradients, and / or measured metadata such as the size of the local data or training time. For example, the metadata may include model parameters, model gradients, and / or the size of the local data, and / or the training time of the local data. Information related to the AIML model may include metadata.

[0295] 9. The management node can collect information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance).

[0296] For example, the Management function can collect information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance) from one or more PFL clients.

[0297] In some implementations, if the management node immediately includes information related to performance monitoring (or information related to PFL performance monitoring, or information related to PFL performance) received from each PFL client in the report message of step 10 and transmits it, step 9 may be performed optionally.

[0298] 10. The management function can send report messages to the server.

[0299] For example, the Management function can report information related to performance monitoring received from multiple PFL clients (or information related to PFL performance monitoring, or information related to PFL performance) to the PFL server by processing it individually, in an integrated form, or selectively according to the PFL server's requests and operator policy criteria.

[0300] 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.

[0301] FIG. 8 illustrates an example of operations according to one embodiment of the disclosure of the present specification.

[0302] For reference, the procedure illustrated in FIG. 8 is merely an example, and the scope of disclosure of this specification is not limited by the example of FIG. 8.

[0303] For example, regarding the example of FIG. 8, the operations described in the examples of FIG. 1 through 7 may also be applied. For example, even if the operations, contents, etc. are not directly described in the example of FIG. 8, the operations, contents, etc. described in various examples of the disclosure of this specification may be applied.

[0304] In the example of FIG. 8, the first network entity may be a management function.

[0305] In the example of FIG. 8, the device may be a UE or a server. For example, the device may be any device that supports PFL functionality.

[0306] The second network entity may be a network entity related to the application. For example, the second network entity may be a PFL server and / or AF.

[0307] In step (S801), the second network entity can send the first request message to the first network entity.

[0308] For example, a first network entity may receive a first request message from a second network entity related to the application, the message including information related to Personalized Federated Learning (PFL) activation and information related to monitoring.

[0309] In some implementations, the first request message may further include information related to PFL client selection. In this case, at step (S802), the first network entity may select at least one PFL client to perform the PFL function based on the information regarding PFL client selection.

[0310] In step (S802), the first network entity can select at least one PFL client.

[0311] For example, the first network entity may select at least one PFL client to perform a PFL function (or operation, or procedure). The at least one PFL client may include a device. The device may be permitted to use the PFL function.

[0312] In step (S803), the first network entity can send a second request message to the device.

[0313] For example, the first network entity may send a second request message to the at least one PFL client, the message including information related to PFL activation and information related to performance reporting.

[0314] In some implementations, information related to performance reporting may include at least one of i) information related to requesting Quality of Service (QoS) for a session for PFL operation, ii) information related to requesting information related to service experience, iii) information related to requesting information related to the accuracy of the PFL model, iv) information related to requesting information related to the performance of the PFL model, v) information related to requesting information related to the success or failure of PFL activation or deactivation, vi) information related to requesting information related to the performance of the PFL operation, and vii) information related to requesting information related to the AIML model.

[0315] In step (S804), the device can transmit a first report message to a first network entity.

[0316] For example, a first network entity may receive a first report message from the device that includes information related to performance monitoring.

[0317] In some implementations, information related to performance monitoring may include at least one of i) Quality of Service (QoS) measured for a session for PFL operation, ii) information related to the measured service experience, iii) information related to the accuracy of the measured PFL model, iv) information related to the performance of the measured PFL model, v) information related to the success of the measured PFL activation or deactivation, vi) information related to the measured performance of the PFL operation, and vii) information related to the Artificial Intelligent Machine Learning (AIML) model.

[0318] In some implementations, the first network entity may receive a third request message from the device containing capability information related to the PFL. The third request message may be received before or after step (S802).

[0319] In some implementations, a first network entity may obtain subscriber information of the device from a third network entity related to user data. Based on the subscriber information of the device, the device may be permitted to use the PFL function.

[0320] In some implementations, the subscriber information of the device may include at least one of information that the device supports the PFL function or information related to user consent regarding the device's data collection.

[0321] In some implementations, the first network entity may transmit to the second network entity a second report message containing information related to the performance monitoring or information based on the information related to the performance monitoring.

[0322] In some implementations, if the device is a UE, prior to step (S803), the device may perform the following actions. For example, the device may transmit a request message to the fourth network entity regarding a connection between the device and the fourth network entity related to mobility. The device may receive a response message from the fourth network entity regarding a connection between the device and the fourth network entity.

[0323] In some implementations, the first network node (e.g., Management function) can receive FL capability-related profile information (e.g., information regarding PFL execution capability) of individual objects (e.g., VFL client) and register the individual objects. The first network node (e.g., Management function) can receive PFL-related requests from VFL clients and / or AF / servers. The first network node (e.g., Management function) can collect, monitor, and / or analyze necessary information, such as PFL-related capability. It selects PFL clients and assigns / reassigns work tasks for PFL functions. In some implementations, the first network node (e.g., Management function) can also activate / deactivate the PFL functions of PFL clients. The first network node (e.g., Management function) can receive monitoring information from PFL clients. The first network node (e.g., Management function) can expose monitoring information to other PFL clients, other network nodes, and external servers.

[0324] In some implementations, a network node (e.g., AF / server) can send a request for PFL function activation to a first network node (e.g., Management function). The network node (e.g., AF / server) can receive performance monitoring results regarding PFL execution from a core network node (e.g., Management function).

[0325] This specification may have various effects.

[0326] For example, personalized federated learning (PFL) can be effectively supported.

[0327] For example, a PFL that utilizes user privacy can be effectively supported. For example, specific measures for implementing the PFL and services related to the PFL can be defined. For example, actions and / or functions related to the PFL can be effectively performed or / or controlled.

[0328] For example, various federated learning functions are supported from an overall system perspective, while customized services can be provided through AI / Machine Learning (AI / ML) models tailored to individual users.

[0329] For example, in a system that supports personalized federated learning, individual users and / or local users can have the privacy of their individual data guaranteed. In addition, it can be guaranteed that customized services optimized for individual users and / or local users are provided.

[0330] 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.

[0331] For reference, the operation of the terminal (e.g., UE, PFL client) described in this specification may be implemented by the device of FIGS. 1 to 3 described above. For example, the terminal may be the first device (100) or the second device (200) of FIG. 2. For example, the operation of the terminal described in this specification may be processed by one or more processors (102 or 202). The operation of the terminal described in this specification may be stored in one or more memories (104 or 204) in the form of an instruction / program (e.g., instruction, executable code) executable by one or more processors (102 or 202). One or more processors (102 or 202) may control one or more memories (104 or 204) and one or more transceivers (105 or 206) and execute the instruction / program stored in one or more memories (104 or 204) to perform the operation of the terminal (e.g., UE) described in the disclosure of this specification.

[0332] Additionally, instructions for performing the operation of the terminal described in the disclosure of this specification may be stored in a non-volatile computer-readable storage medium. The storage medium may be included in one or more memories (104 or 204). And, the instructions recorded in the storage medium may perform the operation of the terminal described in the disclosure of this specification by being executed by one or more processors (102 or 202).

[0333] For reference, the operation of a network node (e.g., AMF, SMF, PCF, UDM, management function, PFL server, CN NFs, AF, etc.) or a base station (e.g., NG-RAN, gNB, RAN, eNB, (R)AN, etc.) described in this specification may be implemented by the device of FIGS. 1 to 3, which will be described below. For example, the network node or base station may be the first device (100) or the second device (200) of FIG. 2. For example, the operation of a network node or base station described in this specification may be processed by one or more processors (102 or 202). The operation of a terminal described in this specification may be stored in one or more memories (104 or 204) in the form of an instruction / program (e.g., instruction, executable code) executable by one or more processors (102 or 202). One or more processors (102 or 202) can control one or more memories (104 or 204) and one or more transceivers (106 or 206) and execute instructions / programs stored in one or more memories (104 or 204) to perform the operation of a network node or base station as described in the disclosure of this specification.

[0334] Additionally, instructions for performing the operation of a network node or base station described in the disclosure of this specification may be stored in a non-volatile (or non-transient) computer-readable storage medium. The storage medium may be contained in one or more memories (104 or 204). And, the instructions recorded in the storage medium may perform the operation of a network node or base station described in the disclosure of this specification by being executed by one or more processors (102 or 202).

[0335] Although preferred embodiments have been described by way of example above, the disclosure of this specification is not limited to such specific embodiments, and may be modified, changed, or improved in various forms within the spirit of this specification and the categories described in the claims.

[0336] In the exemplary system described above, methods are described based on a flowchart as a series of steps or blocks, but are not limited to the order of the described steps, and some steps may occur in a different order or simultaneously with other steps as described above. Furthermore, a person skilled in the art will understand that the steps shown in the flowchart are not exclusive, and that other steps may be included, or that one or more steps of the flowchart may be omitted without affecting the scope of rights.

[0337] 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. A first network entity receiving a first request message from a second network entity related to an application, the message including information related to Personalized Federated Learning (PFL) activation and information related to monitoring; A step of selecting at least one PFL client to perform PFL functions, The above at least one PFL client includes a device, and The above device is permitted to use the PFL function; The first network entity transmits a second request message to at least one PFL client, the message including information related to PFL activation and information related to performance reporting; and A method comprising the step of the first network entity receiving a first report message from the device, the first report message including information related to performance monitoring.

2. In Paragraph 1, A method further comprising the step of the first network entity receiving a third request message from the device, the request message including capability information related to the PFL.

3. In Paragraph 1 or 2, The above first network entity further includes the step of obtaining subscriber information of the device from a third network entity related to user data, and A method in which the device is allowed to use the PFL function based on subscriber information of the device.

4. In Paragraph 3, A method in which subscriber information of the above device includes at least one of information that the device supports the PFL function or information related to user consent regarding data collection of the device.

5. In any one of paragraphs 1 through 4, A method comprising at least one of the following: information related to performance monitoring, wherein the information related to the above performance monitoring comprises: i) Quality of Service (QoS) measured for a session for PFL operation; ii) information related to the measured service experience; iii) information related to the accuracy of the measured PFL model; iv) information related to the performance of the measured PFL model; v) information related to the success or failure of the measured PFL activation or deactivation; vi) information related to the measured performance of the PFL operation; and vii) information related to an Artificial Intelligent Machine Learning (AIML) model.

6. In any one of paragraphs 1 through 5, A method comprising at least one of the following: information related to the performance report above, i) information related to requesting Quality of Service (QoS) for a session for PFL operation; ii) information related to requesting information related to the service experience; iii) information related to requesting information related to the accuracy of the PFL model; iv) information related to requesting information related to the performance of the PFL model; v) information related to requesting information related to the success or failure of PFL activation or deactivation; vi) information related to requesting information related to the performance of the PFL operation; and vii) information related to requesting information related to the AIML model.

7. In any one of paragraphs 1 through 6, A method further comprising the step of the first network entity transmitting to the second network entity a second report message containing information related to performance monitoring or information based on information related to performance monitoring.

8. In paragraphs 1 through 7, The above first request message further includes information related to PFL client selection, and A method in which at least one PFL client is selected to perform the PFL function based on information regarding the selection of a PFL client.

9. At least one transmitter / receiver; At least one processor; and It includes at least one memory that stores instructions and can be connected to operate with at least one processor, and The operation adapted to be performed by at least one processor is: a first network entity which is a method according to any one of claims 1 to 8.

10. A step in which the device transmits a request message related to a connection between the device and the fourth network entity to a fourth network entity related to mobility; The device receives a response message from the fourth network entity regarding a connection between the device and the fourth network entity; The device receives a second request message from a first network entity related to Personalized Federated Learning (PFL), the message including information related to PFL activation and information related to performance reporting. The above device is permitted to use the PFL function; and A method comprising the step of the device receiving a first report message containing information related to performance monitoring from the first network entity.

11. In Paragraph 10, A method comprising further including the step of the device transmitting to the first network entity a third request message containing capability information related to the PFL.

12. In Paragraph 10 or 11, A method in which subscriber information of the above device includes at least one of information that the device supports the PFL function or information related to user consent regarding data collection of the device.

13. In any one of paragraphs 10 through 12, A method comprising at least one of the following: information related to performance monitoring, wherein the information related to the above performance monitoring comprises: i) Quality of Service (QoS) measured for a session for PFL operation; ii) information related to the measured service experience; iii) information related to the accuracy of the measured PFL model; iv) information related to the performance of the measured PFL model; v) information related to the success or failure of the measured PFL activation or deactivation; vi) information related to the measured performance of the PFL operation; and vii) information related to an Artificial Intelligent Machine Learning (AIML) model.

14. In any one of paragraphs 10 through 13, A method comprising at least one of the following: information related to the performance report above, i) information related to requesting Quality of Service (QoS) for a session for PFL operation; ii) information related to requesting information related to the service experience; iii) information related to requesting information related to the accuracy of the PFL model; iv) information related to requesting information related to the performance of the PFL model; v) information related to requesting information related to the success or failure of PFL activation or deactivation; vi) information related to requesting information related to the performance of the PFL operation; and vii) information related to requesting information related to the AIML model.

15. At least one transmitter / receiver; At least one processor; and It includes at least one memory that stores instructions and can be connected to operate with at least one processor, and The operation adapted to be performed by at least one processor is: a device which is a method according to any one of claims 10 to 14.

16. A second network entity related to the application transmits a first request message to a first network entity, the message including information related to Personalized Federated Learning (PFL) activation and information related to monitoring, and The above first request message relates to the selection of at least one PFL client to perform a PFL function by the above first network entity, and The above at least one PFL client includes a device, and A method in which the above device is allowed to use the above PFL function.

17. In Paragraph 16, A method further comprising the step of the second network entity receiving from the first network entity a second report message containing information related to performance monitoring or information based on said information related to performance monitoring.

18. In Paragraph 17, A method in which the above performance monitoring information is included in a first report message received by the first network entity from the device.

19. In any one of paragraphs 16 through 18, A method comprising at least one of the following: information related to performance monitoring, wherein the information related to the above performance monitoring comprises: i) Quality of Service (QoS) measured for a session for PFL operation; ii) information related to the measured service experience; iii) information related to the accuracy of the measured PFL model; iv) information related to the performance of the measured PFL model; v) information related to the success or failure of the measured PFL activation or deactivation; vi) information related to the measured performance of the PFL operation; and vii) information related to an Artificial Intelligent Machine Learning (AIML) model.

20. In paragraphs 16 through 19, The above first request message further includes information related to PFL client selection, and A method in which at least one PFL client to perform the PFL function is selected by the first network entity based on information regarding the selection of a PFL client.

21. At least one transmitter / receiver; At least one processor; and It includes at least one memory that stores instructions and can be connected to operate with at least one processor, and The operation adapted to be performed by at least one processor is: a second network entity related to an application which is a method according to any one of claims 16 to 20.

Images