Method and apparatus for supporting terminal data collection in mobile communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting higher data transmission rates. The present disclosure provides a method for operating a data collection function (DCF) for performing wireless communication, the method comprising the steps of: transmitting a data collection request message to an access and mobility management function (AMF); receiving, from the AMF, a data collection response message; receiving, from a UE, a first message requesting a user plane (UP) connection; transmitting, to the UE, a second message including at least one of an identifier for the DCF, data collection binding ID information, or a transfer binding ID; and determining a transmission path of data collected by the UE on the basis of the first message and the second message.

Description

Method and device for supporting terminal data collection in a mobile communication system

[0001] The present invention relates to a wireless communication system, and more specifically, the present invention proposes a method for collecting terminal information for training a machine learning model running on a terminal. The machine learning model running on the terminal can be applied to operations for wireless communication performance within the terminal. The machine learning model can be used for the purpose of improving communication performance with a mobile communication base station or core network, or for improving the performance of terminal location measurement based on mobile communication signals.

[0002] 5G mobile communication technology defines a wide frequency band to enable fast transmission speeds and new services, and can be implemented not only in frequency bands below 6 GHz ('Sub 6 GHz'), such as 3.5 gigahertz (3.5 GHz), but also in ultra-high frequency bands called millimeter waves (mmWave), such as 28 GHz and 39 GHz ('Above 6 GHz'). In addition, for 6G mobile communication technology, which is referred to as a system beyond 5G, implementation in the terahertz band (e.g., the 3 terahertz (3 THz) band at 95 GHz) is being considered to achieve transmission speeds 50 times faster and ultra-low latency reduced to one-tenth compared to 5G mobile communication technology.

[0003] In the early stages of 5G mobile communication technology, aiming to satisfy service support and performance requirements for enhanced Mobile BroadBand (eMBB), Ultra-Reliable Low-Latency Communications (URLLC), and massive Machine-Type Communications (mMTC), technologies such as beamforming and Massive MIMO to mitigate path loss and increase transmission distance in ultra-high frequency bands, support for various numerologies (such as the operation of multiple subcarrier spacings) and dynamic operation of slot formats for the efficient utilization of ultra-high frequency resources, initial access techniques to support multi-beam transmission and broadband, definition and operation of Band-Width Parts (BWP), Low Density Parity Check (LDPC) codes for high-volume data transmission, new channel coding methods such as Polar Codes for the reliable transmission of control information, and L2 pre-processing (L2 Standardization has been carried out for pre-processing, network slicing which provides a dedicated network specialized for specific services, and other methods.

[0004] Currently, discussions are underway to improve and enhance the performance of the initial 5G mobile communication technology, taking into account the services that the 5G mobile communication technology was intended to support. Additionally, standardization of the physical layer is in progress for technologies such as V2X (Vehicle-to-Everything), which helps autonomous vehicles make driving decisions and enhance user convenience based on their own location and status information transmitted by the vehicle; NR-U (New Radio Unlicensed), which aims for system operation in unlicensed bands to comply with various regulatory requirements; NR terminal low power consumption technology (UE Power Saving); Non-Terrestrial Network (NTN), which is direct terminal-satellite communication for securing coverage in areas where communication with the terrestrial network is impossible; and positioning.

[0005] In addition, standardization is underway in the field of wireless interface architecture / protocols for technologies such as the Industrial Internet of Things (IIoT) to support new services through linkage and convergence with other industries, Integrated Access and Backhaul (IAB) which provides nodes to expand network service areas by integrating wireless backhaul links and access links, Mobility Enhancement including Conditional Handover and Dual Active Protocol Stack (DAPS) Handover, and 2-step Random Access (2-step RACH for NR) which simplifies random access procedures. Standardization is also underway in the field of system architecture / services for 5G baseline architectures (e.g., Service based Architecture, Service based Interface) to incorporate Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC), which provides services based on the location of the terminal.

[0006] When such 5G mobile communication systems are commercialized, connected devices, which are increasing explosively, will be connected to communication networks. Accordingly, it is expected that there will be a need to enhance the functionality and performance of 5G mobile communication systems and to integrate the operation of connected devices. To this end, new research is planned to be conducted on 5G performance improvement and complexity reduction, support for AI services, support for metaverse services, and drone communication using eXtended Reality (XR), Artificial Intelligence (AI), and Machine Learning (ML) to efficiently support Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR).

[0007] Furthermore, the advancement of these 5G mobile communication systems encompasses multi-antenna transmission technologies such as new waveforms to guarantee coverage in the terahertz band of 6G mobile communication technology, Full Dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas; metamaterial-based lenses and antennas to improve terahertz band signal coverage; high-dimensional spatial multiplexing technology using OAM (Orbital Angular Momentum); and Reconfigurable Intelligent Surface (RIS) technology; as well as Full Duplex technology for enhancing frequency efficiency and system networks in 6G mobile communication technology; AI-based communication technologies that realize system optimization by utilizing satellites and AI from the design stage and internalizing end-to-end AI support functions; and the realization of services of complexity exceeding the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources. It could serve as a foundation for the development of next-generation distributed computing technologies.

[0008] The present invention proposes a method for collecting data from a terminal to a mobile communication core network. Specifically, it proposes a method for selecting a path to transmit collected data to the core network according to the type or size of data collected by the terminal, and a method for establishing a connection between the mobile communication core network function and the terminal through the selected path.

[0009] To perform training on a machine learning model used to improve wireless communication performance at a terminal, data collected from the terminal can be transmitted to a machine learning model training server. Data collected from the terminal may be collected by network functions within the core network for the control and management of the mobile communication network operator and then transmitted to the machine learning model training server. In the case of signaling data exchanged between the network functions of the existing core network and the terminal, it is generally transmitted and received through the control plane. However, transmitting data collected from the terminal to be used for machine learning model training through the control plane may not be suitable. This is because it is not suitable for transmitting large amounts of data when considering the protocols, signaling messages, and wireless resource allocations supported by the existing control plane. To address this, the present invention proposes a method and apparatus for providing data collected from the terminal to network functions within the core network through the user plane rather than the control plane.

[0010] A method of operation of a data collection function (DCF) performing wireless communication according to one embodiment of the present disclosure may include: transmitting a data collection request message to an access and mobility management function (AMF); receiving a data collection response message from the AMF; transmitting a first message to a UE that includes at least one of a DCF identifier, data collection binding ID information, or transfer binding ID information; receiving a second message that includes UE capability information from the user equipment (UE); and determining a transmission path of data collected from the UE using the second message.

[0011] To improve wireless communication performance, information collected from the terminal can be transmitted to the core network while reducing the burden on the control plane. To perform training on a machine learning model used to improve wireless communication performance at the terminal, data collected from the terminal can be transmitted to a machine learning model training server. Data collected from the terminal can be collected by network functions within the core network for the control and management of the mobile communication network operator and then transmitted to the machine learning model training server.

[0012] FIG. 1 is a diagram illustrating the network structure and interface of a 5G system according to one embodiment of the present disclosure.

[0013] FIG. 2 is a flowchart illustrating a method for creating a user plane connection for data collection according to one embodiment of the present disclosure.

[0014] FIG. 3 is a flowchart illustrating a data collection method according to one embodiment of the present disclosure.

[0015] FIG. 4a is a flowchart illustrating a data collection method according to one embodiment of the present disclosure.

[0016] FIG. 4b is a flowchart illustrating a data collection method according to one embodiment of the present disclosure.

[0017] FIG. 5 is a block diagram schematically illustrating another example of the structure of a terminal according to one embodiment of the present disclosure.

[0018] FIG. 6 is a block diagram schematically illustrating another example of the structure of a network entity according to one embodiment of the present disclosure.

[0019] Hereinafter, an embodiment of the present disclosure will be described in detail with reference to the attached drawings.

[0020] In describing the present disclosure, technical details that are well known in the technical field to which the present disclosure belongs and are not directly related to the present disclosure are omitted. This is intended to convey the essence of the present disclosure more clearly without obscuring it by omitting unnecessary explanations. Furthermore, the terms described below are defined considering their functions within the present disclosure, and these definitions may vary depending on the intentions or practices of the user or operator. Therefore, their definitions should be based on the content throughout this specification.

[0021] In the following description of the present invention, specific descriptions of related known functions or configurations will be omitted if it is determined that such detailed descriptions may unnecessarily obscure the essence of the invention. Embodiments of the present invention will be described below with reference to the attached drawings.

[0022] The operating principle of the present invention will be explained in detail below with reference to the attached drawings. Furthermore, the terms described below are defined in consideration of their functions in the present invention. Since these may vary depending on the intentions or conventions of the user or operator, their definitions should be determined according to the content throughout this specification.

[0023] In describing the embodiments of this disclosure, technical details that are well known in the art to which this disclosure belongs and are not directly related to this disclosure are omitted. This is intended to convey the essence of this disclosure more clearly without obscuring it by omitting unnecessary explanations.

[0024] For the same reason, some components in the attached drawings have been exaggerated, omitted, or schematically depicted. Additionally, the dimensions of each component do not entirely reflect their actual dimensions. Identical or corresponding components in each drawing have been assigned the same reference numbers.

[0025] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to make the present disclosure complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Throughout the specification, like reference numerals refer to like components.

[0026] Hereinafter, a base station (hereinafter BS) is an entity that performs resource allocation for terminals and may be at least one of gNode B, eNode B, Node B (or xNode B (where x is an alphabet including g and e)), a radio access unit, a base station controller, a satellite, an airborn, or a node on a network. A terminal (user equipment, hereinafter UE) may include a Mobile Station (MS), a Vehicular, a Satellite, an Airborn, a cellular phone, a smartphone, a computer, or a multimedia system capable of performing communication functions. In this disclosure, a Downlink (DL) refers to a radio transmission path for a signal transmitted by a base station to a terminal, and an Uplink (UL) refers to a radio transmission path for a signal transmitted by a terminal to a base station. Additionally, a Sidelink (SL) may exist, which refers to a radio transmission path for a signal transmitted by a terminal to another terminal.

[0027] In addition, while LTE, LTE-A, or 5G systems may be described below as examples, embodiments of the present disclosure may also be applied to other communication systems having similar technical backgrounds or channel types. For example, 5G-Advance or NR-Advance or 6th generation mobile communication technology (6G) developed after 5G mobile communication technology (or new radio, NR) may be included, and the 5G below may be a concept that includes existing LTE, LTE-A, and other similar services. Furthermore, the present disclosure may be applied to other communication systems with some modifications made at the discretion of a person with skilled technical knowledge, without significantly departing from the scope of the present disclosure.

[0028] At this point, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing instruction means to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0029] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specific logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For example, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order according to their corresponding functions.

[0030] In this embodiment, the term "part" refers to a software or hardware component such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit), and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and 'parts' may be implemented to utilize one or more CPUs within the device or secure multimedia card. Also, in the embodiments, 'parts' may include one or more processors.

[0031] Terms used in the following description to identify connection nodes, terms referring to network entities or network functions (NFs), terms referring to messages, terms referring to interfaces between network entities, terms referring to various identification information, etc., are examples provided for the convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms referring to objects having equivalent technical meanings may be used.

[0032] For convenience of explanation below, some terms and names defined in the 3GPP (3rd generation partnership project) LTE (long term evolution) standards and / or 3GPP NR (new radio) standards may be used. However, the present disclosure is not limited by the above terms and names and may be equally applied to systems conforming to other standards.

[0033] Specific terms used in the following description are provided to aid in understanding the present disclosure, and the use of such specific terms may be modified in other forms without departing from the technical spirit of the present disclosure.

[0034] 3GPP, which is responsible for cellular mobile communication standards, has named a new core network structure "5G Core" (5GC) and is proceeding with standardization to facilitate the evolution from 4G LTE systems to 5G systems. Compared to the Evolved Packet Core (EPC), which is the network core for 4G, 5GC supports the following differentiated features.

[0035] Network Slice functionality is introduced in 5GC. As a requirement for 5G, 5GC must support various types of terminals and services (e.g., enhanced Mobile Broadband (eMBB), Ultra Reliable Low Latency Communications (URLC), and Massive Machine Type Communications (mMTC)). Each of these terminals / services has different requirements for the core network. For example, eMBB services may require a high data rate, while URLLC services may require high stability and low latency. Network Slice technology has been proposed to satisfy these diverse service requirements.

[0036] Network slicing refers to a method of creating multiple logical networks (e.g., network slices) by virtualizing a single physical network. An active network slice can be referred to as a network slice instance, and each network slice instance (hereinafter NSI) can have different characteristics. Mobile operators can satisfy various service requirements for terminals / services by configuring network functions (hereinafter NF) suitable for the characteristics of each NSI. For example, mobile operators can efficiently support various 5G services (e.g., eMBB, URLLC, or mMTC) by allocating an NSI that matches the characteristics of the service required by each terminal.

[0037] 5GC facilitates support for network virtualization paradigms by separating mobility management functions and session management functions. In 4G LTE, all terminals can receive services from the network through signaling exchanges with a single core entity called the Mobility Management Entity (MME), which is responsible for registration, authentication, mobility management, and session management functions. In 5G, as the number of terminals (e.g., including MTC terminals) increases explosively and the mobility and traffic / session characteristics that must be supported vary depending on the terminal type, having a single entity (e.g., MME) support all functions inevitably leads to reduced scalability, which requires adding entities for specific functions. Therefore, to improve scalability in terms of the functional / implementation complexity and signaling load of the core entity responsible for the control plane, various functions are being developed based on a structure that separates mobility management functions and session management functions.

[0038] FIG. 1 is a diagram illustrating the network structure and interface of a 5G system according to one embodiment of the present disclosure.

[0039] Figure 1 illustrates an example of a wireless communication system structure that supports machine learning-based operations.

[0040] FIG. 1 may include a wireless communication system structure that supports terminal information collection for machine learning model training.

[0041] A 5G system architecture supporting machine learning-based operation may include various network functions (NF), and FIG. 1 may include at least one of an access and mobility management function (AMF), a session management function (SMF), unified data management (UDM), a data network (DN) or a local part of a DN capable of local access to a data network, a user plane function (UPF), a (radio) access network ((R)AN), user equipment (UE), a Network Data Analytics Function (NWDAF), or a Data Collection Function (DCF).

[0042] The terminal may use a machine learning model to perform operations such as channel state information prediction, channel state information compression, beam management, and positioning to improve wireless communication performance. For example, the terminal may decide to use a machine learning model to perform the specific operations mentioned above, and if multiple machine learning models are used, it may select one model to perform operations for improving wireless communication performance. The terminal may receive requests for data collection and configuration information for data collection from network devices such as a RAN, DCF, or NWDAF.

[0043] Each NF can support the following functions.

[0044] - AMF can provide functions for connectivity and mobility management at the UE level, and each UE can be connected to one AMF by default.

[0045] - (R)AN can transmit and receive data wirelessly with the terminal and can transmit and receive terminal user plane data with the UPF. In addition, it can perform access and mobility management of the terminal in conjunction with the AMF (access and mobility management function).

[0046] - DN can refer to, for example, operator services, internet access, or third-party services. DN can transmit downlink protocol data units (PDUs) to the UPF or receive PDUs transmitted from the UE from the UPF. Local part of DN can refer to a data network that is part of the DN and allows for local access, resulting in a short data transmission path. It can be used to refer to a DN where edge application servers supporting edge computing services are deployed.

[0047] - The PCF can receive information about packet flows from the application server and provide functions for determining policies such as mobility management and session management. Specifically, the PCF can support functions such as supporting a unified policy framework to control network behavior, providing policy rules so that control plane function(s) (e.g., AMF, SMF, etc.) can enforce policy rules, and implementing a front end to access relevant subscription information for policy decisions within the unified data repository (UDR).

[0048] - SMF provides session management functions, and if a UE has multiple sessions, each session can be managed by a different SMF.

[0049] - UDM stores user subscription data, policy data, etc. It can store user consent information regarding the collection, storage, and processing of device-related information used for machine learning training, inference, etc.

[0050] - UPF can forward downlink PDUs received from DN to UE via (R)AN, and uplink PDUs received from UE to DN via (R)AN.

[0051] - The DCF can collect terminal-related information and provide configuration information for collecting terminal-related information to the terminal or RAN. The DCF can be defined as a new network function or as a new function or device included in an existing NF (e.g., NWDAF) and deployed and operated. Additionally, the DCF can perform the function of transmitting information collected from the terminal to a network device or server that performs machine learning. Furthermore, the DCF can perform a review and analysis of the information collected from the terminal before transmitting it to a machine learning device.

[0052] FIG. 2 is a flowchart illustrating a method for creating a user plane connection for data collection according to one embodiment of the present disclosure.

[0053] FIG. 2 may include a method and apparatus for a DCF to generate a user plane connection for data collection.

[0054] Referring to FIG. 2, in step S201, the Data collection Function (DCF) (211) may receive a data collection request from a server performing machine learning training. The data collection request may be transmitted to the DCF (211) via a device such as a Network exposure function as an AF request. At this time, a specific DCF (211) may be selected and the data collection request transmitted by considering the machine learning training model target or machine learning application use case information (e.g., beam management, CSI prediction, CSI compression, positioning, etc.).

[0055] In step S203, the DCF (211) may transmit a terminal data collection request to the AMF (205). The conditions under which the DCF (211) decides to transmit the terminal data collection request may be at least one of the following.

[0056] - In the previous step, a data collection request can be received from the machine learning training server (Over the top server, training server).

[0057] - DCF (211) can decide on data collection itself based on operator policy or local configuration.

[0058] The DCF (211) can determine the terminal to be collected data before transmitting a terminal data collection request to the AMF (205). The considerations for selecting the terminal to be collected data may include at least one of the following.

[0059] A terminal that supports the function of performing data collection and transfer for machine learning model training (UE data collection and transfer capability): The information may be defined as a type of UE capability. The UE data collection capability information may be defined separately from the UE data transfer capability and may be defined to include information about data that can be collected from the terminal (201). For example, the UE data collection capability may include at least one of machine learning model information or information indicating the purpose of using the machine learning model, or may be defined in correspondence with such information. The machine learning model information or information indicating the purpose of using the machine learning model may be defined as information or an index that can indicate a use case, such as beam management, CSI prediction, or positioning. Additionally, the machine learning model information and the information indicating the purpose of using the machine learning model may include information indicating which device the trained machine learning model is running on (e.g., may include information indicating a UE-side model, network-side model, LMF-side model, etc.). Here, a UE-side model may be information indicating that it is a machine learning model running within the terminal for operations performed on the terminal (201).

[0060] A terminal with user consent information for terminal data collection: A data collection request may be sent only if the terminal has user consent information or privacy profile information stored in the subscriber information that indicates the user has consented to the collection of terminal data, corresponding to information such as the terminal's identifier (SUPI or GPSI). In the case of UE positioning, which is the purpose of use for a machine learning model, the LCS privacy profile may be checked to determine whether information indicating that the terminal consents to the collection of location-related information is stored in the core network (UDM or UDR).

[0061] Radio access type or Radio access technology information

[0062] Frequency band information

[0063] DCF (211) can search for and discover an AMF (205) that manages the terminal (201) through UDM or NRF, an AMF (205) registered by the terminal (201), or an AMF (205) that stores and manages the UE context for the terminal (201), and send a data collection request.

[0064] AMF (205) can send a data collection request to a RAN node (203) to which the terminal (201) is currently wirelessly connected, taking into account the information received from DCF (211).

[0065] In step S205, if the RAN (203) can successfully perform the data collection request, it can send a response to the data collection request to the DCF (211).

[0066] In step S207, the RAN (203) can perform a setting operation for the data collection target terminal (201). Information for UE measurement setting can be provided to the terminal (201) so that the terminal can acquire the data to be collected.

[0067] In step S209, the terminal (201) can perform UE measurement based on information provided by the RAN (203) and can store and manage the collected information within the terminal. The terminal (201) may store the collected data in a layer that processes the Access stratum, which is a lower layer of the modem, or transfer the collected data to an upper layer that processes the Non-Access stratum, which is an upper layer. Alternatively, the terminal (201) may transfer the UE measurement information obtained through Access stratum signaling to an upper layer of the modem, or transfer it to terminal equipment outside the modem within the terminal to store and manage it.

[0068] In step S213, the DCF (211) may perform an operation to receive data collected by the terminal (201) simultaneously with or after the data collection request. To perform UE data transfer, the following operations may be performed.

[0069] - Selection of transmission path for data collected from the terminal: It is possible to select whether to receive the terminal collected data to the control plane or to receive it to the user plane. This selection can be determined by considering at least one of the control plane status information (at least one of CP congestion status, AMF congestion level, or control plane interface congestion level with the RAN core network) and the size of the collected data (the information may use reference information regarding the predicted data size of the terminal set in the DCF, or at least one of the collected data size information included in the data collection progress / result information received from the terminal through direct signaling exchange with the terminal), or information on a machine learning model to be trained on the collected data, use case information to which the machine learning model to be trained on the collected data is applied, terminal subscriber information (e.g., information on whether the terminal is allowed to transmit the collected data through the user plane), and UE capability information (e.g., information on whether the terminal can transmit the collected information through the user plane to the core network). According to one embodiment, the DCF may obtain and consider at least one of the following information from the AMF or RAN: CP congestion status, information on the congestion or overload of the AMF, or the congestion of the control plane interface with the core network of the RAN. According to one embodiment, the DCF may obtain information on data collected from a terminal (size of data collected from the terminal) and perform an operation to make a decision on data transfer path selection (selection of CP or UP).For example, through step 5-a, information regarding the progress or result of data collection can be requested from the terminal, and in response, information regarding the size of the collected data, etc., can be received from the terminal as part of the data collection information. According to one embodiment, in step S211, through the step, the DCF (211) can provide information such as a DCF identifier and a data collection / transfer binding ID to the terminal.

[0070] According to various embodiments, the DCF (211) may determine that terminal (201) is allowed to transmit data collected through the user plane and that terminal (201) supports the data transfer over UP related function only for terminals that support the data transfer over UP related function. According to one embodiment, the DCF (211) may determine whether to perform data transfer collected using UP by obtaining subscriber information from the UDM or UDR indicating whether the terminal is allowed to transmit data collected through the user plane for the terminal. UE capability information regarding whether the terminal (201) supports the data transfer function over UP may be obtained from the AMF (205), or the network function managing the UE capability information may be obtained from the UCMF. When performing a Registration operation with the AMF (205) to provide information to the DCF (211) about whether it supports data transfer via UP, the terminal (201) can transmit UE capability information to the AMF (205) about whether it supports the function for data transfer via UP.

[0071] When DCF (211) determines terminal data transfer, it may assign a data collection binding ID or a data transfer binding ID based on a specific terminal and the data information collected by that terminal. The data collection / transfer binding ID may be expressed in various forms, such as a data collection / transfer association ID or context ID, index, reference ID, correlation ID, etc. The data collection / transfer binding ID may be assigned and managed according to the purpose for which the collected data is used (purpose information that may be defined according to use case or machine learning model information, etc.) or the training server, which is the final data transfer destination. In addition, in the case of the data collection / transfer binding ID, if the transmission method of the collected terminal data is determined to be data transfer via UP, it may be assigned / stored / managed in correspondence with the UP connection information (connection or session information established on the user plane between the terminal and DCF). Additionally, the data collection / transfer binding ID may be stored and managed in correspondence with a terminal identifier (e.g., SUPI or GPSI).According to one embodiment, the DCF can generate UE data collection / transfer context information for the purpose of managing data collection and transmission on a terminal basis, and store and manage data collection binding ID or data transfer binding ID, data collection purpose (use case, ML model information), data collection final destination information (OTT server, training server), selected data transfer method (data transfer via CP or data transfer via UP), data collection request execution information (data collection request time stamp), etc.

[0072] In step S215, if the DCF (211) decides to perform the transmission of collected terminal data, it may transmit a message to the AMF (205) comprising at least one of a terminal identifier, a collection data transmission request indicator, a UP connection request indication (which may be included if the DCF decides to perform the transmission of collected terminal data through the UP), a DCF identifier, DCF user plane information (which may include at least one of address information required to establish a UP connection with the DCF, such as an FQDN or IP address), a DNN, an S-NSSAI, a data collection / transfer binding ID, and security information required for security regarding the UP connection between the DCF and the terminal (such as security protocol information). According to one embodiment, the DCF (211) may call the Namf_comm_N1N2Transfer service to transmit the message to the AMF.

[0073] In step S217, the AMF (205) may receive a request for data transfer from the DCF (211) and, according to the method of the request for data transfer from the terminal, may generate and manage terminal data transfer information. For example, if the AMF (205) receives a request for data transfer from the DCF (211) and a request for data transfer from the terminal and DCF UP information, the AMF (205) may store the information within the AMF (205). According to one embodiment, storage of the information may not be performed in step S217, and may be generated after receiving an acknowledgment from the terminal (201) that data transfer can be performed.

[0074] AMF (205), taking into account the information received from DCF (211), can transmit a message (through the RAN) to the terminal (201) that is currently connected to the RAN (203) that the terminal (201) that needs to perform data collection transmission has at least one of the following: a data collection transmission request indicator, a UP connection request indication (which may be included if DCF decides to perform data collection transmission through the UP), DCF user plane information (which may include at least one of the address information required to establish a UP connection with DCF, such as an FQDN or IP address), a DNN, an S-NSSAI, a data collection / transfer binding ID, and security information required for security regarding the UP connection between DCF and the terminal (security protocol information, etc.).

[0075] When the AMF (205) receives a data transmission request message from the DCF (211) in step S215, depending on the connection status between the terminal (201) and the AMF, it can perform paging to establish a NAS layer signaling connection with the terminal, secure connectivity with the terminal, and then transmit the above information to the terminal (201).

[0076] In step S221, the terminal (201) may perform the following operations by considering the information within the message received through the AMF (205). When the terminal (201) receives an UP connection request indication or DCF UP information, it may perform an operation to establish a UP connection to the DCF (211) using the information included in the DCF UP information. The operation may include the following.

[0077] - If DNN / S-NSSAI information is received, a new PDU session can be created using the received DNN / S-NSSAI information, or if a PDU session corresponding to the DNN / S-NSSAI has already been created, the operation to reuse the existing PDU session can be performed.

[0078] - If the DCF address information included in the UP information of the DCF is an FQDN, the terminal (201) can send a DNS query to a DNS server configured within the terminal to obtain an IP address for the DCF (211). The DNS server address may be the address of a DNS server configured or operated by a core network operator or an operator that is the entity operating the DCF. The DNS server address information may be a DNS server address provided to the terminal during the process of the terminal (201) creating a PDU session. Alternatively, the DNS server address may be configured as an EASDF (edge ​​application server discovery function) address used in the core network and provided to the terminal.

[0079] - The terminal (201) can perform a creation or selection operation for a PDU session to transmit a DCF UP connection message, and then transmit a UP connection message for the DCF (211) to the DCF via a path to the user plane (through the created or selected PDU session) using the DCF address information included in the DCF UP information. The UP connection message for the DCF may include information such as a data collection / transfer binding ID, a UE identifier, and information related to the collected data (collected data metadata, size of the collected data). The UP connection message for the DCF (211) transmitted by the terminal (201) may be transmitted as part of a specified protocol message (e.g., AIML data collection / transfer protocol) defined between the terminal (201) and the DCF (211).

[0080] - After receiving a UP connection request message, the DCF (211) can perform an authentication security procedure for the terminal and perform the following operations. The DCF (211) can consider the information within the received UP connection request message, assign a UP connection ID to the UP connection created with the terminal, and manage it in correspondence with data collection / transfer binding ID information. According to one embodiment, multiple UP Connection IDs and data collection / transfer binding IDs may be assigned and used between a single terminal and the DCF. For example, if the terminal (201) performs data collection and transmission for multiple use cases, a different data collection / transfer binding ID may be assigned and used for each use case. Additionally, multiple UP connection IDs may also be assigned and managed for each data set collected by the terminal or for each use case of the data collected by the terminal (201).

[0081] - After confirming that the DCF (211) can successfully perform the terminal's UP connection request, it may send a response message to the UP connection request indicating that the UP connection has been successfully created to the terminal. The response message may include at least one of the UP connection ID or the data collection / transfer binding ID information. The DCF (211) may associate the terminal / DCF with the UP connection created using at least one of the UP connection ID or the data collection / transfer binding ID information, and may be used to identify which data among the collected data the UP connection is intended to transmit (for example, it may be used to identify the created UP connection with which use case or data for training a machine learning model).

[0082] In step S223, if the terminal (201) successfully completes the creation of a UP connection for data transfer with the DCF (211) in the preceding step, it may send an acknowledgment to UP connection established for data transfer message to the AMF. The message may include the result of creating a UP connection to transfer data collected by the terminal (201) to the DCF (211) via UP, a UP connection ID, or a data collection / transfer binding ID.

[0083] In step S225, the AMF (205) can transmit the acknowledgment to UP connection established for data transfer message received from the terminal (201) to the DCF (211). If the acknowledgment to UP connection established for data transfer message contains result information indicating that the terminal (201) has successfully established a UP Connection with the DCF (211), the AMF (205) can store and manage UP connection context information within the AMF. The UP connection context information may include at least one of DCF information (identifier and address information), a UP connection ID, and a data collection / transfer binding ID.

[0084] In step S227, the terminal (201) can transmit the collected data through an UP connection with the DCF (211) successfully created in the previous step. When transmitting the collected data, the UP connection ID or Data collection / transfer binding ID can be transmitted together.

[0085] In step S229, the DCF (211) can store and manage data to be used for learning received from the terminal (201). The DCF (211) can perform an operation to verify whether the received data is data collected in accordance with the data collection settings. The DCF (211) can identify the machine learning model training server to which the data to be used for learning transmitted by the terminal (201) should be transmitted and transmit the collected data. This step may be transmitted along with the response message to the data collection request requested by the machine learning model training server in step S201.

[0086] In step S231, the machine learning model training server can perform the operation of setting the trained machine learning model on the terminal after successfully performing machine learning training using the data collection requested from the DCF.

[0087] FIG. 3 is a flowchart illustrating a data collection method according to one embodiment of the present disclosure.

[0088] Referring to FIG. 3, in step S301, the Data collection Function (DCF) (311) may receive a data collection request from a server performing machine learning. The data collection request may be transmitted to the DCF (311) via a device such as a Network exposure function as an AF request. At this time, a specific DCF (311) may be selected and the data collection request transmitted, taking into account the machine learning learning model target or machine learning application use case information (e.g., beam management, CSI prediction, CSI compression, positioning, etc.).

[0089] In step S303, the DCF (311) may transmit a terminal data collection request to the AMF. The conditions under which the DCF (311) decides to transmit the terminal data collection request may be at least one of the following.

[0090] - In the previous step, a data collection request can be received from the machine learning training server (Over the top server, training server).

[0091] - DCF (311) can decide on data collection itself based on operator policy or local configuration.

[0092] DCF (311) can determine the terminal to be collected data before transmitting a terminal data collection request to AMF. The considerations for selecting the terminal to be collected data may include at least one of the following.

[0093] A terminal supporting the capability to perform data collection and transfer for machine learning model training (UE data collection and transfer capability): Such information may be defined as a type of UE capability. UE data collection capability information may be defined separately from UE data transfer capability and may include information regarding data that can be collected by the terminal. For example, UE data collection capability may include at least one of machine learning model information or information indicating the purpose of using the machine learning model, or may be defined in correspondence with such information. Machine learning model information or information regarding the purpose of using the machine learning model may be defined as information or an index that can represent use cases, such as beam management, CSI prediction, or positioning. Additionally, machine learning model information and information regarding the purpose of using the machine learning model may include information indicating which device the trained machine learning model is running on (e.g., may include information indicating a UE-side model, network-side model, LMF-side model, etc.). Here, a UE-side model may be information indicating that it is a machine learning model running within the terminal for operations performed on the terminal.

[0094] A terminal with user consent information for terminal data collection: A data collection request may be sent only if the terminal has user consent information or privacy profile information stored in the subscriber information that indicates the user has consented to the collection of terminal data, corresponding to information such as the terminal's identifier (SUPI or GPSI). In the case of UE positioning, which is the purpose of use for a machine learning model, the LCS privacy profile may be checked to determine whether information indicating that the terminal consents to the collection of location-related information is stored in the core network (UDM or UDR).

[0095] Radio access type or Radio access technology information

[0096] Frequency band information

[0097] DCF (311) can search for and discover an AMF that manages the terminal through UDM or NRF, an AMF that is registered with the terminal, or an AMF that stores and manages the UE context for the terminal, and send a data collection request.

[0098] AMF (305) can send a data collection request to a RAN node to which the terminal (301) is currently wirelessly connected, taking into account the information received from DCF (311).

[0099] In step S305, if the RAN (303) can successfully perform the data collection request, it can send a response to the data collection request to the DCF (311).

[0100] In step S307, the RAN (303) can perform a configuration operation for the data collection target terminal. Information for UE measurement configuration can be provided to the terminal so that the terminal can acquire the data to be collected.

[0101] In step S309, the terminal (301) can perform UE measurement based on information provided by the RAN (303) and can store and manage the collected information within the terminal. The terminal (301) may store the collected data in a layer that processes the Access stratum, which is a lower layer of the modem, or transfer the collected data to an upper layer that processes the Non-Access stratum, which is an upper layer. Alternatively, the terminal (301) may transfer the UE measurement information obtained through Access stratum signaling to an upper layer of the modem, or transfer it to terminal equipment outside the modem within the terminal to store and manage it.

[0102] In step S311, the terminal (301) may decide to transmit the data collected through the preceding step. The terminal (301) may make a selection regarding the path for transmitting the collected data to be used for machine learning training. The terminal (301) may select the transmission path for the collected data between CP or UP by utilizing information such as the size of the collected data, preset information within the terminal, terminal user preference selection, machine learning training data path selection rules received from the core network, and whether the terminal supports the capability to transfer the collected machine learning data to the user plane via the core network function (UE capability to transfer data to NF via UP).

[0103] When the terminal (301) selects a data transmission path, it may transmit a data transmission request message for the selected path to the AMF. In the embodiment of FIG. 3, the operation of the terminal (301) selecting the data transfer via UP method and transmitting a data transmission request message (data to be transmitted within the core network) collected in the previous step is described. The data transfer via UP request message transmitted by the terminal (301) may include at least one of the following: a terminal identifier, a data collection / transfer binding ID, an indicator for requesting the creation of an UP connection for the transmission of collected data (e.g., a data transfer over UP indication or an UP connection request indication), and collected data information (size, purpose of use, ML model information, etc.).

[0104] In step S313, the AMF (305) receives a request message from a terminal for the transmission of collected data to be used for training a machine learning model (or a request for a UP connection with a core network function for data transmission), and if the message contains information such as a request to create a UP connection for the transmission of collected data or a request for transmission through a user plane, the AMF can determine whether the terminal is authorized or allowed to transmit the data collected through the user plane to a network function (DCF) that performs data collection functions within the core network. This operation can be determined by obtaining subscriber information from information configured within the AMF or from a UDM or UDR. For example, if information is stored within the UDM or UDR indicating that the terminal is allowed to transmit the data collected through the user plane to a network function (e.g., DCF) within the core network, and the AMF confirms this, the AMF can determine that the terminal is authorized or allowed to transmit the data collected through the user plane to a network function (DCF) that performs data collection functions within the core network. The AMF can perform search and selection operations for a target DCF to transmit data collected by the terminal. For DCF selection, the AMF may consider at least one of a terminal identifier, terminal location information (e.g., TAI, cell ID), terminal collection information purpose information, ML model information, whether a UP connection request is made, terminal device type information, and a data collection / transfer binding ID transmitted by the terminal. The AMF (305) may use DCF information set within the AMF to obtain address information for the DCF, or request DCF information by providing information that can be considered for the DCF selection to the NRF.

[0105] In step S315, the AMF (305) may transmit to the previously selected DCF (311) a UP connection request message or a UP connection configuration request message containing at least one of the information received from the terminal (301) (terminal identifier, data collection / transfer binding ID, UP connection creation request indicator for data transfer, at least one of the collected data information (size, purpose of use, ML model information, etc.).

[0106] In step S317, when the DCF (311) receives a data transmission request message or a UP connection request message received through the AMF (305), it may perform authentication / authorization for the request (authentication and authorization for the data transmission request itself or the UP connection request message for data transmission) and perform operations for establishing and receiving a successful connection with the terminal and the data to be transmitted. The specific operations of the DCF (311) may include at least one of the following.

[0107] - Selection of transmission path for data collected from the terminal: The terminal can select whether to receive collected data to the control plane or to the user plane. According to one embodiment, the terminal can select and perform the data transmission method requested by the terminal or perform it in a different way. The selection can determine whether to perform data transfer to the user plane by considering at least one of the control plane status information (at least one of CP congestion status, AMF congestion level, or control plane interface congestion level with the RAN core network) and the size of collected data (the information may use reference information regarding the size of data collected by the terminal configured in the DCF, or at least one of the collected data size information included in the data collection progress / result information received from the terminal through direct signaling exchange with the terminal), or information on a machine learning model to be trained on the collected data, use case information to which the machine learning model to be trained on the collected data is applied, terminal subscriber information (e.g., information on whether the terminal is allowed to transmit data collected through the user plane), and UE capability information (e.g., information on whether the terminal can transmit information collected through the user plane to the core network). According to one embodiment, the DCF may obtain and consider at least one of the following: CP congestion status, AMF congestion or overload information, or control plane interface congestion with the RAN core network from the AMF or RAN.According to one embodiment, the DCF may obtain information about data collected from a terminal (at least one of the size of data collected from the terminal, use case information, ML information, and data collection / transfer binding ID) and perform an operation to make a decision on data transfer path selection (selection of CP or UP).

[0108] According to various embodiments, the DCF (311) may determine to perform data collection to the user plane only for terminals that are allowed to transmit data collected through the user plane and that the terminal supports the data transfer over UP related function. According to one embodiment, the DCF (311) may determine whether to perform data transmission using the UP by obtaining subscriber information from the UDM or UDR indicating whether the terminal is allowed to transmit data collected through the user plane. UE capability information regarding whether the terminal (301) supports the data transmission function over the UP may be obtained from the AMF, or the network function managing the UE capability information may be obtained from the UCMF. When performing a Registration operation with an AMF to provide information on whether the terminal supports data transfer via UP to the DCF, the terminal may transmit UE capability information to the AMF regarding whether the AMF supports the function for data transfer via UP, or when transmitting a data transfer request to the AMF in step S311, the terminal may include UE capability information.

[0109] When the DCF (311) determines terminal data transmission, it may assign a data collection binding ID or a data transfer binding ID based on a specific terminal and the data information collected by that terminal. In this case, instead of assigning a new ID according to the DCF operation method, the data collection / transfer binding ID assigned in the previous step S303 or the ID provided by the terminal may be reused. The data collection / transfer binding ID may be expressed in various forms such as a data collection / transfer association ID or context ID, index, reference ID, correlation ID, etc. The data collection / transfer binding ID may be assigned and managed according to the purpose for which the collected data is used (purpose information that may be defined according to use case or machine learning model information, etc.) or the training server which is the final data transmission destination. Additionally, in the case of the data collection / transfer binding ID, if the transmission method of the collected terminal data is determined to be data transfer via UP, it may be assigned / stored / managed in correspondence with the UP connection information (connection or session information established on the user plane between the terminal and the DCF). In addition, the data collection / transfer binding ID can be stored and managed in correspondence with a terminal identifier (e.g., SUPI or GPSI).According to one embodiment, the DCF can generate UE data collection / transfer context information for the purpose of managing data collection and transmission on a terminal basis, and store and manage data collection binding ID or data transfer binding ID, data collection purpose (use case, ML model information), data collection final destination information (OTT server, training server), selected data transfer method (data transfer via CP or data transfer via UP), data collection request execution information (data collection request time stamp), etc.

[0110] In step S319, if the DCF (311) decides to perform the transmission of collected terminal data, it may transmit a message to the AMF (305) comprising at least one of a terminal identifier, a collection data transmission request indicator, a UP connection request indication (which may be included if the DCF decides to perform the transmission of collected terminal data through the UP), a DCF identifier, DCF user plane information (which may include at least one of address information required to establish a UP connection with the DCF, such as an FQDN or IP address), a DNN, an S-NSSAI, a data collection / transfer binding ID, and security information required for security regarding the UP connection between the DCF and the terminal (such as security protocol information). According to one embodiment, the DCF (311) may call the Namf_comm_N1N2Transfer service to transmit the message to the AMF (305).

[0111] In step S321, the AMF (305) receives a request for data transfer from the DCF (311) and can generate and manage terminal data transfer information according to the method of the request for data transfer from the terminal. For example, if the DCF (311) determines a data transfer via UP and receives a request for data transfer from the terminal and DCF UP information from the DCF (311), the AMF can store the information within the AMF. According to one embodiment, storage of the information may not be performed in step S317, but may be generated after receiving an acknowledgment from the terminal (301) that data transfer can be performed.

[0112] AMF (305), taking into account the information received from DCF (311), may transmit a message (through the RAN) to the terminal that is currently connected to the terminal that needs to perform data collection transmission, including at least one of the following: a data collection transmission request indicator, a UP connection request indication (which may be included if DCF decides to perform data collection transmission through the UP), DCF user plane information (which may include at least one of the address information required to establish a UP connection with DCF, such as an FQDN or IP address), DNN, S-NSSAI, data collection / transfer binding ID, and security information required for security regarding the UP connection between DCF and the terminal (security protocol information, etc.).

[0113] When the AMF (305) receives a data transmission request message from the DCF (311) in step S313, depending on the connection status between the terminal and the AMF, it can perform paging to establish a NAS layer signaling connection with the terminal (301) to secure connectivity with the terminal and then transmit the above information to the terminal.

[0114] In step S323, the terminal (301) may perform the following operations by considering the information within the message received through the AMF (305). When the terminal (301) receives an UP connection request indication or DCF UP information, it may perform an operation to establish a UP connection to the DCF (311) using the information included in the DCF UP information. The operation may include the following.

[0115] - If DNN or S-NSSAI information is received, create a new PDU session using the received DNN / S-NSSAI information, or if a PDU session corresponding to the DNN / S-NSSAI has already been created, perform the operation to reuse the existing PDU session.

[0116] - If the DCF address information included in the UP information of the DCF (311) is an FQDN, the terminal (301) can send a DNS query to a DNS server configured within the terminal to obtain an IP address for the DCF. The DNS server address may be the address of a DNS server configured or operated by a core network operator or an operator that is the entity operating the DCF. The DNS server address information may be a DNS server address provided to the terminal during the process of the terminal creating a PDU session. Alternatively, the DNS server address may be configured as an EASDF (edge ​​application server discovery function) address used in the core network and provided to the terminal.

[0117] - The terminal (301) can perform a creation or selection operation for a PDU session to transmit a DCF UP connection message, and then transmit a UP connection message for the DCF to the DCF via a path to the user plane (through the created or selected PDU session) using the DCF address information included in the DCF UP information. The UP connection message for the DCF may include information such as a data collection / transfer binding ID, a UE identifier, and information related to collected data (collected data metadata, size of collected data). The UP connection message for the DCF transmitted by the terminal may be transmitted as part of a specified protocol message (e.g., AIML data collection / transfer protocol) defined between the terminal and the DCF.

[0118] - After receiving a UP connection request message, the DCF (311) can perform an authentication security procedure for the terminal and perform the following operations. The DCF (311) can consider the information within the received UP connection request message, assign a UP connection ID to the UP connection created with the terminal, and manage it in correspondence with data collection / transfer binding ID information. According to one embodiment, multiple UP Connection IDs and data collection / transfer binding IDs may be assigned and used between a single terminal and the DCF. For example, if the terminal (301) performs data collection and transmission for multiple use cases, a different data collection / transfer binding ID may be assigned and used for each use case. Additionally, multiple UP connection IDs may also be assigned and managed for each data set collected by the terminal or for each use case of the data collected by the terminal.

[0119] - After confirming that the DCF (311) can successfully perform the terminal's UP connection request, it may send a response message to the UP connection request to the terminal indicating that a UP connection has been successfully created. The response message may include at least one of UP connection ID or data collection / transfer binding ID information. The DCF (311) may associate the terminal / DCF with the UP connection created using at least one of the UP connection ID or data collection / transfer binding ID information, and may be used to identify which data among the collected data the UP connection is intended to transmit (for example, it may be used to identify the created UP connection with which use case or data for training a machine learning model).

[0120] In step S325, if the terminal (301) successfully completes the creation of a UP connection for data transfer with the DCF in the preceding step, it may send an acknowledgment to UP connection established for data transfer message to the AMF (305). The message may include the result of creating a UP connection for transferring data collected by the terminal to the DCF via the UP, a UP connection ID, or a data collection / transfer binding ID.

[0121] In step S327, the AMF (305) can transmit the acknowledgment to UP connection established for data transfer message received from the terminal (301) to the DCF. If the acknowledgment to UP connection established for data transfer message contains result information indicating that the terminal has successfully established a UP Connection with the DCF, the AMF (305) can store and manage UP connection context information within the AMF. The UP connection context information may include at least one of DCF information (identifier and address information), UP connection ID, and data collection / transfer binding ID.

[0122] In step S329, the terminal (301) can transmit the collected data through an UP connection with the DCF successfully created in the previous step. When transmitting the collected data, the UP connection ID or Data collection / transfer binding ID can be transmitted together.

[0123] In step S331, the DCF (311) can store and manage data to be used for training received from the terminal. The DCF (311) can perform an operation to check whether the received data is data collected in accordance with the data collection settings. The DCF (311) can identify the machine learning model training server to which the data to be used for training transmitted by the terminal should be transmitted and transmit the collected data. This step may be transmitted along with a response message to the data collection request requested by the machine learning model training server in step 0.

[0124] In step S333, the machine learning model training server can perform the operation of setting the trained machine learning model on the terminal after successfully performing machine learning training using the data collection requested from the DCF.

[0125] FIG. 4a is a flowchart illustrating a data collection method according to one embodiment of the present disclosure. FIG. 4b is a flowchart illustrating a data collection method according to one embodiment of the present disclosure.

[0126] Referring to FIGS. 4a and 4b, in step S401, the Data collection Function (DCF) (411) may receive a data collection request from a server performing machine learning. The data collection request may be transmitted to the DCF via a device such as a Network exposure function as an AF request. At this time, a specific DCF may be selected and the data collection request transmitted by considering the machine learning learning model target or machine learning application use case information (e.g., beam management, CSI prediction, CSI compression, positioning, etc.).

[0127] In step S403, the DCF (411) may transmit a terminal data collection request to the AMF (405). The conditions under which the DCF decides to transmit the terminal data collection request may be at least one of the following.

[0128] - In the previous step, a data collection request can be received from the machine learning training server (Over the top server, training server).

[0129] - DCF can decide on data collection on its own based on operator policy or local configuration.

[0130] DCF (411) can determine the terminal to be collected data before transmitting a terminal data collection request to AMF. The considerations for selecting the terminal to be collected data may include at least one of the following.

[0131] A terminal supporting the capability to perform data collection and transfer for machine learning model training (UE data collection and transfer capability): Such information may be defined as a type of UE capability. UE data collection capability information may be defined separately from UE data transfer capability and may include information regarding data that can be collected by the terminal. For example, UE data collection capability may include at least one of machine learning model information or information indicating the purpose of using the machine learning model, or may be defined in correspondence with such information. Machine learning model information or information regarding the purpose of using the machine learning model may be defined as information or an index that can represent use cases, such as beam management, CSI prediction, or positioning. Additionally, machine learning model information and information regarding the purpose of using the machine learning model may include information indicating which device the trained machine learning model is running on (e.g., may include information indicating a UE-side model, network-side model, LMF-side model, etc.). Here, a UE-side model may be information indicating that it is a machine learning model running within the terminal for operations performed on the terminal.

[0132] A terminal with user consent information for terminal data collection: A data collection request may be sent only if the terminal has user consent information or privacy profile information stored in the subscriber information that indicates the user has consented to the collection of terminal data, corresponding to information such as the terminal's identifier (SUPI or GPSI). In the case of UE positioning, which is the purpose of use for a machine learning model, the LCS privacy profile may be checked to determine whether information indicating that the terminal consents to the collection of location-related information is stored in the core network (UDM or UDR).

[0133] Radio access type or Radio access technology information

[0134] Frequency band information

[0135] DCF (411) can search for and discover an AMF (405) that manages the terminal through UDM (408) or NRF, an AMF registered by the terminal, or an AMF that stores and manages the UE context for the terminal, and send a data collection request.

[0136] AMF (405) can send a data collection request to a RAN node (403) to which the terminal is currently wirelessly connected, taking into account the information received from DCF (411).

[0137] In step S405, if the RAN (403) can successfully perform the data collection request, it can send a response to the data collection request to the DCF (411).

[0138] In step S407, the RAN (403) can perform a configuration operation for the data collection target terminal. Information for UE measurement configuration can be provided to the terminal so that the terminal can acquire the data to be collected.

[0139] In step S409, the terminal (401) can perform UE measurement based on information provided by the RAN (403) and store and manage the collected information within the terminal. The terminal (401) may store the collected data in a layer that processes the Access stratum, which is a lower layer of the modem, or transfer the collected data to an upper layer that processes the Non-Access stratum, which is an upper layer. Alternatively, the terminal may transfer the UE measurement information obtained through Access stratum signaling to an upper layer of the modem, or transfer it to terminal equipment outside the modem within the terminal to store and manage it.

[0140] The terminal (401) can select the DNN or S-NSSAI to be used or select a PDU session when transmitting data collected by the terminal to the user plane via the network function (DCF) within the core network by applying URSP rules or UE local configuration.

[0141] According to one embodiment, when the terminal (401) transmits data collected according to a UE data collection transfer rule received from the core network or a UE data collection transfer rule within the UE local configuration set within the terminal to a core network function, it can determine whether to use a control plane or a user plane.

[0142] The terminal (401) may decide to transmit the data collected through the preceding step. The terminal (401) may make a selection regarding the path for transmitting the collected data to be used for machine learning training. The terminal (401) may select the transmission path for the collected data between CP or UP by utilizing information such as the size of the collected data, preset information within the terminal, selection of terminal user preferences, machine learning training data path selection rules received from the core network, and whether the terminal supports the capability to transmit the machine learning collected data through the user plane via the core network function (UE capability to transfer data to NF via UP). The information regarding whether the terminal supports the capability to transmit the machine learning collected data through the user plane via the core network function (UE capability to transfer data to NF via UP) may be included in the protocol configuration option and transmitted by the terminal. Alternatively, the information regarding whether the terminal supports the capability to transmit the machine learning collected data through the user plane via the core network function may be expressed as information regarding the support of the data transfer client function within the terminal, included in the PCO, and included in the PDU session creation request information transmitted by the terminal.

[0143] In step S411, if the terminal (401) selects a data transmission path, it may transmit a data transmission request message for the selected path to the AMF (405). In the embodiment of FIG. 4, an operation is described in which the terminal selects the data transfer via UP method and transmits a data transmission request message (data to be transmitted within the core network) collected in the previous step.

[0144] The data transfer via UP request message transmitted by the terminal (401) may be transmitted by being included within a PDU Session Establishment creation or modification request message, and may be transmitted by including at least one of the following information: a terminal identifier, a DNN, an S-NSSAI, a data collection / transfer binding ID, an UP connection creation request indicator for the transmission of collected data (e.g., may be expressed as a data transfer over UP indication or an UP connection request indication), and at least one of the collected data information (size, purpose of use, ML model information, etc.).

[0145] In step S413, the AMF (405) can determine, by considering the information transmitted by the terminal (e.g., a UP connection creation request indicator for the transmission of collected data), that the PDU session creation request is intended to transmit collected data to a network function (DCF) within the core network. Alternatively, the AMF can obtain SMF selection subscription data stored in the UDM (it can identify SMF selection subscription data corresponding to the given DNN or S-NSSAI information or the DNN or S_NSSAI information transmitted by the terminal) and use it for SMF discovery and selection. SMF selection subscription data corresponding to the DNN or S-NSSAI or a combination of both may be stored within the UDM, and for the given DNN / S-NSSAI, the terminal's AMF (405) can select an SMF that supports the corresponding function. SMF (407) can register information in NRF regarding whether it supports a session management function to support a user plane connection for transmitting terminal collected data to a function within the core network, and AMF (405) can obtain information in SMF that supports such function by requesting it from NRF. According to one embodiment, SMF information regarding whether it supports a session management function to support a user plane connection for transmitting terminal collected data to a function within the core network may be stored in AMF (405) along with SMF address information.

[0146] In this way, the AMF (405) can send a request to create a PDU session to the selected SMF, and the message that the AMF sends to the SMF may include information received from the terminal in the previous step.

[0147] In step S415, if the SMF (407) receives a request message from the terminal (401) for the transmission of collected data to be used for training a machine learning model (or a request for a UP connection with a core network function for data transmission) or a request message for creating a PDU session containing such data, or receives a request message for creating a PDU session for a specific DNN / S-NSSAI, it can determine whether the data collected by the terminal through the user plane is authenticated or allowed to be transmitted to a network function (DCF) that performs a data collection function within the core network. Additionally, if the PDU session creation request message received through the AMF contains information on whether the terminal's machine learning collected data is supported to be transmitted to the core network function through the user plane (UE capability to transfer data to NF via UP) or information on the terminal's data transfer client support, the SMF can determine that a DCF selection is required.

[0148] The operation can be verified by obtaining subscriber information from the information configured within the SMF or from the UDM or UDR. For example, if information is stored indicating that data collected by the terminal through the user plane within the UDM or UDR is allowed to be transmitted to a network function (e.g., DCF) within the core network (this information may be stored as Session Management subscription data for a specific DNN / S-NSSAI, or may be stored in the UDM or UDR as separate subscriber information that is not Session Management subscription data), and the SMF confirms this, the SMF (407) can determine that the terminal is authorized or allowed to transmit data collected by the terminal through the user plane to a network function (DCF) that performs data collection functions within the core network.

[0149] In step S417, the SMF (407) can perform a search and selection operation for a target DCF to transmit data collected by the terminal (401). For DCF selection, the SMF (407) may consider at least one of a terminal identifier, terminal location information (e.g., TAI, cell ID), terminal collection information purpose information, ML model information, whether a UP connection request was made, terminal device type information, and a data collection / transfer binding ID transmitted by the terminal. To obtain address information for the DCF, the SMF (407) may use DCF information set within the SMF or request DCF information while providing information to the NRF that can be considered for the DCF selection.

[0150] In step S419, the SMF (407) may transmit to the selected DCF an UP connection request message or an UP connection configuration request message containing at least one of the following: information received from the terminal (401) (at least one of terminal identifier, data collection / transfer binding ID, UP connection creation request indicator for data collection transfer, and data collection information (size, purpose of use, ML model information, etc.)), and at least one of the UE IP address. The request message may also be expressed as a UE collected data transfer context create request.

[0151] In step S421, when the DCF (411) receives a data transmission request message or a UP connection request message received through the SMF (407), it may perform authentication / authorization for the request (authentication and authorization for the data transmission request itself or the UP connection request message for data transmission) and perform operations for establishing and receiving a successful connection with the terminal and the data to be transmitted. The specific operations of the DCF (411) may include at least one of the following.

[0152] - Selection of transmission path for data collected from the terminal: The terminal can select whether to receive collected data to the control plane or to the user plane. According to one embodiment, the terminal can select and perform the data transmission method requested by the terminal or perform it in a different way. The selection can determine whether to perform data transfer to the user plane by considering at least one of the control plane status information (at least one of CP congestion status, AMF congestion level, or control plane interface congestion level with the RAN core network) and the size of collected data (the information may use reference information regarding the size of data collected by the terminal configured in the DCF, or at least one of the collected data size information included in the data collection progress / result information received from the terminal through direct signaling exchange with the terminal), or information on a machine learning model to be trained on the collected data, use case information to which the machine learning model to be trained on the collected data is applied, terminal subscriber information (e.g., information on whether the terminal is allowed to transmit data collected through the user plane), and UE capability information (e.g., information on whether the terminal can transmit information collected through the user plane to the core network). According to one embodiment, the DCF may obtain and consider at least one of the following: CP congestion status, AMF congestion or overload information, or control plane interface congestion with the RAN core network from the AMF or RAN.According to one embodiment, the DCF may obtain information about data collected from a terminal (at least one of the size of data collected from the terminal, use case information, ML information, and data collection / transfer binding ID) and perform an operation to make a decision on data transfer path selection (selection of CP or UP).

[0153] According to various embodiments, the DCF (411) may determine to perform data collection to the user plane only for terminals that are allowed to transmit data collected through the user plane and that the terminal supports the data transfer over UP related function. According to one embodiment, the DCF (411) may determine whether to perform data transmission using the UP by obtaining subscriber information from the UDM (408) or UDR indicating whether the terminal is allowed to transmit data collected through the user plane. UE capability information regarding whether the terminal supports the data transmission function over the UP may be obtained from the AMF (405), or the network function managing the UE capability information may be obtained from the UCMF. When the terminal (401) performs a Registration operation with the AMF to provide information on whether the DCF supports data transfer via UP, it may transmit UE capability information to the AMF regarding whether the AMF supports the function for data transfer via UP, or when the terminal (401) transmits a data transfer request to the AMF in step S413, it may include UE capability information.

[0154] When the DCF (411) determines terminal data transmission, it may assign a data collection binding ID or a data transfer binding ID based on a specific terminal and the data information collected by that terminal. In this case, instead of assigning a new ID according to the DCF operation method, the data collection / transfer binding ID assigned in the previous step S403 or the ID provided by the terminal may be reused. The data collection / transfer binding ID may be expressed in various forms such as a data collection / transfer association ID or context ID, index, reference ID, correlation ID, etc. The data collection / transfer binding ID may be assigned and managed according to the purpose for which the collected data is used (purpose information that may be defined according to use case or machine learning model information, etc.) or the training server which is the final data transmission destination. Additionally, in the case of the data collection / transfer binding ID, if the transmission method of the collected terminal data is determined to be data transfer via UP, it may be assigned / stored / managed in correspondence with the UP connection information (connection or session information established on the user plane between the terminal and the DCF). In addition, the data collection / transfer binding ID can be stored and managed in correspondence with a terminal identifier (e.g., SUPI or GPSI).According to one embodiment, the DCF can generate UE data collection / transfer context information for the purpose of managing data collection and transmission on a terminal basis, and store and manage data collection binding ID or data transfer binding ID, data collection purpose (use case, ML model information), data collection final destination information (OTT server, training server), selected data transfer method (data transfer via CP or data transfer via UP), data collection request execution information (data collection request time stamp), etc.

[0155] In step S421, if the DCF (411) decides to perform the transmission of collected terminal data, it may transmit a message to the SMF containing at least one of the following: a terminal identifier, a collection data transmission request indicator, a UP connection request indication (which may be included if the DCF decides to perform the transmission of collected terminal data through the UP), a DCF identifier, DCF user plane information (which may include at least one of address information required to establish a UP connection with the DCF, such as an FQDN or IP address), a data collection / transfer binding ID, and security information required for security regarding the UP connection between the DCF and the terminal (such as security protocol information). The above information may be included in the PCO and transmitted to the terminal. According to one embodiment, steps S419 and S421 may be performed after step S423, but must be completed before step S425.

[0156] In step S423, the SMF (407) can select and set a UPF to set a transmission path for data to be transmitted to the DCF using the address on the user plane of the selected DCF or DCF UP information.

[0157] In step S425, the SMF (407) may transmit a message to the AMF that includes at least one of the following: a UP connection request indication (which may be included if the DCF decides to perform the transmission of collected terminal data through the UP), a DCF identifier, DCF user plane information (which may include at least one of the address information required to establish a UP connection with the DCF, such as an FQDN or IP address), a data collection / transfer binding ID, and security information required for security regarding the UP connection between the DCF and the terminal (such as security protocol information).

[0158] SMF (407) or AMF (405) can receive a request for data transfer from DCF (411) and generate and manage data transfer information according to the method of data transfer from the collected terminal. For example, SMF (407) can store the information in SMF when DCF determines data transfer via UP and receives a request for data transfer from the collected terminal and DCF UP information from DCF (411).

[0159] In step S427, the AMF (405), taking into account the information received from the DCF (411), may transmit a message (through the RAN) to the terminal that is currently connected to the terminal that needs to perform the collection data transmission, including at least one of the following: a collection data transmission request indicator, a UP connection request indication (which may be included if the DCF decides to perform the collection terminal data transmission through the UP), DCF user plane information (which may include at least one of the address information required to establish a UP connection with the DCF, such as an FQDN or an IP address), a data collection / transfer binding ID, and security information required for security regarding the UP connection between the DCF and the terminal (such as security protocol information).

[0160] When the AMF (405) receives the message from the SMF (407), depending on the connection status between the terminal and the AMF, it can perform paging to establish a NAS layer signaling connection with the terminal, secure connectivity with the terminal, and then transmit the above information to the terminal.

[0161] In step S429, the terminal (401) may perform the following operations by considering the information within the message received through the AMF (405). When the terminal (401) receives an UP connection request indication or DCF UP information, it may perform an operation to establish a UP connection to the DCF using the information included in the DCF UP information. The operation may include the following.

[0162] - If the DCF address information included in the UP information of the DCF is an FQDN, the terminal (401) can send a DNS query to a DNS server configured within the terminal to obtain an IP address for the DCF. The DNS server address may be the address of a DNS server configured or operated by a core network operator or an operator that is the entity operating the DCF. The DNS server address information may be a DNS server address provided to the terminal during the process of the terminal creating a PDU session. Alternatively, the DNS server address may be configured as an EASDF (edge ​​application server discovery function) address used in the core network and provided to the terminal.

[0163] - The terminal (401) can perform a creation or selection operation for a PDU session to transmit a DCF UP connection message, and then transmit a UP connection message for the DCF to the DCF via a path to the user plane (through the created or selected PDU session) using the DCF address information included in the DCF UP information. The UP connection message for the DCF may include information such as a data collection / transfer binding ID, a UE identifier, and information related to collected data (collected data metadata, size of collected data). The UP connection message for the DCF transmitted by the terminal may be transmitted as part of a specified protocol message (e.g., AIML data collection / transfer protocol) defined between the terminal and the DCF.

[0164] - DCF (411) can perform an authentication security procedure for the terminal after receiving a UP connection request message and can perform the following operations. DCF can assign a UP connection ID to the UP connection created with the terminal by considering the information in the received UP connection request message and manage it in correspondence with data collection / transfer binding ID information. According to one embodiment, multiple UP Connection IDs and data collection / transfer binding IDs may be assigned and used between a single terminal and DCF. For example, if the terminal performs data collection and transmission for multiple use cases, a different data collection / transfer binding ID may be assigned and used for each use case. Additionally, multiple UP connection IDs may also be assigned and managed for each data set collected by the terminal or for each use case of the data collected by the terminal.

[0165] - After confirming that the DCF (411) can successfully perform the terminal's UP connection request, it may send a response message to the UP connection request to the terminal indicating that a UP connection has been successfully established. The response message may include at least one of the UP connection ID or the data collection / transfer binding ID information. The terminal may associate the UP connection created with the terminal / DCF using at least one of the UP connection ID or the data collection / transfer binding ID information, and may be used to identify which data among the collected data the UP connection is intended to transmit (for example, it may be used to identify the created UP connection in association with which use case or data for training a machine learning model).

[0166] In step S431, if the terminal (401) successfully completes the creation of a UP connection for data transfer with the DCF in the preceding step, it may send an acknowledgment to UP connection established for data transfer message to the AMF. The message may include the result of creating a UP connection to transfer data collected by the terminal to the DCF via the UP, a UP connection ID, or a data collection / transfer binding ID.

[0167] In step S433, the AMF (405) can transmit the acknowledgment to UP connection established for data transfer message received from the terminal (401) to the DCF (411). If the acknowledgment to UP connection established for data transfer message contains result information indicating that the terminal has successfully established a UP Connection with the DCF, the AMF (405) can store and manage UP connection context information within the AMF. The UP connection context information may include at least one of DCF information (identifier and address information), a UP connection ID, and a data collection / transfer binding ID.

[0168] In step S435, the terminal (401) can transmit the collected data through an UP connection with the DCF successfully created in the previous step. When transmitting the collected data, the UP connection ID or Data collection / transfer binding ID can be transmitted together.

[0169] In step S437, the DCF (411) can store and manage data to be used for training received from the terminal (401). The DCF (411) can perform an operation to check whether the received data is data collected in accordance with the data collection settings. The DCF (411) can identify the machine learning model training server to which the data to be used for training transmitted by the terminal should be transmitted and transmit the collected data. This step may be transmitted along with a response message to the data collection request requested by the machine learning model training server in step 0.

[0170] In step S439, the machine learning model training server can perform the operation of setting the trained machine learning model on the terminal after successfully performing machine learning training using the data collection requested from the DCF.

[0171] The methods of FIGS. 2 to 4 may be used together. For example, the order of FIGS. 2 to 4 is not limited to the present embodiment.

[0172] FIG. 5 is a block diagram illustrating the structure of a network entity according to one embodiment of the present disclosure. The network entity of FIG. 5 can be implemented as the RAN, AMF, SMF, UPF, data collection function, and training server shown in FIG. 2 to 4.

[0173] Referring to FIG. 5, the network entity (501) may include a transceiver (502), a processor (503), and a memory (504). The network entity (501) may include at least one of an electronic device, a server, a UE, a terminal, a network entity, an AP, a base station, a RAN, an AMF, an SMF, a UDM, a UPF, a DCF, and a training server. In the present disclosure, the control unit may be defined as a circuit or an application-specific integrated circuit or at least one processor.

[0174] The transceiver (502) can transmit and receive signals with an external electronic device.

[0175] The processor (503) can control the overall operation of the network entity (501) according to the embodiment proposed in the present disclosure. For example, the processor (503) can control the signal flow between each block to perform operations according to the flowchart described above. Specifically, the processor (503) can control the operation of the network entity illustrated in FIGS. 1 to 4, for example.

[0176] The memory (504) can store at least one of the information transmitted and received through the transceiver (502) and the information generated through the processor (503).

[0177] FIG. 6 is a block diagram illustrating the structure of an electronic device according to one embodiment of the present disclosure. The electronic device of FIG. 6 may be implemented as a terminal (or UE) illustrated in FIG. 1 to FIG. 4.

[0178] Referring to FIG. 6, the electronic device (601) may include a transceiver (602), a processor (603), and a memory (604). The electronic device (601) may include at least one of an electronic device, a server, a UE, a terminal, an AP, or a base station. In the present disclosure, the processor may be defined as a circuit or an application-specific integrated circuit or at least one processor.

[0179] The transceiver (602) can transmit and receive signals with an external electronic device.

[0180] The processor (603) can control the overall operation of the electronic device according to the embodiment proposed in the present disclosure. For example, the processor (603) can control the signal flow between each block to perform operations according to the flowchart described above. Specifically, the processor (603) can control, for example, the base station or electronic device illustrated in FIGS. 1 to 4.

[0181] The memory (604) can store at least one of the information transmitted and received through the transceiver (602) and the information generated through the processor (603).

[0182] It should be noted that the system configuration diagrams, method example diagrams, device configuration diagrams, etc., illustrated in FIGS. 1 to 6 above are not intended to limit the scope of the rights of the present disclosure. That is, all configurations or operations described in FIGS. 1 to 6 above should not be interpreted as essential components for the implementation of the present disclosure, and may be implemented within a scope that does not impair the essence of the present disclosure even if only some components are included.

[0183] Methods according to the claims or embodiments described in the specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0184] When implemented in software, a computer-readable storage medium may be provided for storing one or more programs (software modules). One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. One or more programs may include instructions that cause the electronic device to execute methods according to the claims or embodiments described in the specification of this disclosure.

[0185] Such programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), magnetic disc storage devices, CD-ROM (Compact Disc-ROM), Digital Versatile Discs (DVDs), or other forms of optical storage devices, magnetic cassettes. Alternatively, they may be stored in memory composed of some or all of these. Additionally, each constituent memory may include multiple units.

[0186] Additionally, the program may be stored on an attachable storage device accessible via a communication network such as the Internet, Intranet, Local Area Network (LAN), Wide LAN (WLAN), or Storage Area Network (SAN), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.

[0187] In the specific embodiments of the present disclosure described above, the components included in the present disclosure are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression is selected to suit the situation presented for convenience of explanation, and the present disclosure is not limited to singular or plural components; even if a component is expressed in the plural form, it may be composed in the singular form, or even if a component is expressed in the singular form, it may be composed in the plural form.

Claims

1. In a method of operation for a DCF (data collection function) that performs wireless communication, A step of transmitting a data collection request message to the AMF (access and mobility management function); A step of receiving a data collection response message from the above AMF; A step of receiving a first message from a UE (user equipment) requesting a UP (user plane) connection; A step of transmitting a second message to the UE, comprising at least one of an identifier for the DCF, data collection binding ID information, or a transfer binding ID; and A method comprising the step of determining a transmission path of data collected from the UE based on the first message and the second message.

2. In Paragraph 1, Step of establishing a connection between the above UE and UP; and A method comprising the step of receiving the collected data from the UE via the UP connection, using the data collection binding ID or the transfer binding ID.

3. In paragraph 1, the step of determining the transmission path is, A method further comprising the step of determining the UP (user plane) as the transmission path based on at least one of the status information of the CP (control plane), the size of the collected data, information on a machine learning model to perform learning through the collected data, terminal subscriber information, and UE capability information received from the UE.

4. In Paragraph 1, When collected data is transmitted from the UE via a UP connection, the data collection binding ID or the transfer binding ID is assigned in correspondence with connection or session information on the UP between the UE and the DCF, or A method in which the above data collection binding ID or the above transfer binding ID is assigned in correspondence with SUPI (subscription permanent identifier) ​​or GPSI (generic public subscription identifier).

5. In Paragraph 2, The method further includes the step of transmitting the collected data received from the above UE to a machine learning model training server. A method in which machine learning is performed on the collected data and the learned machine learning model is set as the UE.

6. In a method of operation of a UE (user equipment) performing wireless communication, A step of transmitting a first message requesting a UP (user plane) connection to a DCF (data collection function); and The method includes the step of receiving a second message from the DCF, the second message comprising at least one of an identifier for the DCF, data collection binding ID information, or a transfer binding ID. A method for determining the transmission path of data collected from the UE based on the first message and the second message.

7. In Paragraph 6, Step of establishing the above DCF and UP connection; and A method comprising the step of transmitting the collected data to the DCF via the UP connection using the data collection binding ID or the transfer binding ID.

8. In Paragraph 6, A method in which the UP is determined as the transmission path based on at least one of the following: status information of the CP (control plane), the size of the collected data, information on a machine learning model to perform learning through the collected data, terminal subscriber information, and UE capability information transmitted from the UE.

9. In Paragraph 6, When collected data is transmitted from the UE via a UP connection, the data collection binding ID or the transfer binding ID is assigned in correspondence with connection or session information on the UP between the UE and the DCF, or A method in which the above data collection binding ID or the above transfer binding ID is assigned in correspondence with SUPI (subscription permanent identifier) ​​or GPSI (generic public subscription identifier).

10. In Paragraph 7, A method in which, when machine learning training on the collected data is performed by a machine learning model training server, the trained machine learning model is set as the UE.

11. In a data collection function (DCF) that performs wireless communication, Transmitter / receiver; and It includes a processor, and the processor is: Send a data collection request message to the AMF (access and mobility management function), and Receive a data collection response message from the above AMF, and Receives a first message requesting a UP (user plane) connection from the UE (user equipment), and Transmit a second message to the UE that includes at least one of an identifier for the above DCF, data collection binding ID information, or a transfer binding ID, and A DCF that determines the transmission path of data collected from the UE based on the first message and the second message.

12. In paragraph 11, the above processor is: Establish a connection between the above UE and UP, and The above data collection binding ID or the above transfer binding ID, and a DCF that receives collected data from the UE via the above UP connection.

13. In paragraph 11, the above processor is: A DCF that determines the UP (user plane) as the transmission path based on at least one of the following: status information of the CP (control plane), the size of the collected data, information on a machine learning model to perform learning through the collected data, terminal subscriber information, and UE capability information received from the UE.

14. In a UE (user equipment) performing wireless communication, Transmitter / receiver; and It includes a processor, and the processor is: A first message requesting a UP (user plane) connection is transmitted to the DCF (data collection function), and A second message is received from the DCF, comprising at least one of an identifier for the DCF, data collection binding ID information, or a transfer binding ID, and A UE in which the transmission path of data collected from the UE is determined based on the first message and the second message.

15. In paragraph 14, the above processor is: Establish the above DCF and UP connections, and A UE that transmits the collected data to the DCF via the UP connection, using the data collection binding ID or the transfer binding ID.

Images