Method and device for supporting artificial intelligence model in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. Specifically, the present disclosure provides a method and a device for supporting an AI-based operation in a wireless communication system (or mobile communication system).

Description

Method and device for supporting artificial intelligence models in wireless communication systems

[0001] Embodiments of the present disclosure relate to a wireless communication system, and more particularly, to a device and method for supporting an artificial intelligence model in a wireless communication system.

[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 the sub-6GHz frequency band such as 3.5 gigahertz (3.5GHz), but also in the ultra-high frequency band called millimeter wave (mmWave) such as 28GHz and 39GHz ('Above 6GHz'). In addition, for 6G mobile communication technology, which is called the system after 5G communication (Beyond 5G), implementation in the terahertz (THz) band (for example, 3 THz band at 95GHz) is being considered to achieve a transmission speed that is 50 times faster than 5G mobile communication technology and an ultra-low latency time that is reduced to one-tenth.

[0003] In the early stages of 5G mobile communication technology, the goal is to support services and satisfy performance requirements for enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communications (URLLC), and massive Machine-Type Communications (mMTC). These include beamforming and massive MIMO to mitigate path loss of radio waves in ultra-high frequency bands and increase the transmission distance of radio waves, support for various numerologies (such as operation of multiple subcarrier intervals) and dynamic operation of slot formats for efficient use of ultra-high frequency resources, initial access technology to support multi-beam transmission and wideband, definition and operation of BWP (Bidth Part), new channel coding methods such as LDPC (Low Density Parity Check) codes for large-capacity data transmission and Polar Code for reliable transmission of control information, and L2 pre-processing (L2). Standardization has been made for network slicing, which provides dedicated networks specialized for specific services, and pre-processing.

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

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

[0006] Once these 5G mobile communication systems are commercialized, an explosive increase in connected devices will be connected to the communication network, necessitating enhanced functionality and performance of 5G mobile communication systems and integrated operation of these connected devices. To this end, new research will be conducted on improving 5G performance and reducing complexity, supporting AI services, supporting metaverse services, and drone communications by utilizing eXtended Reality (XR), Artificial Intelligence (AI), and Machine Learning (ML) to efficiently support Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR).

[0007] In addition, the development of these 5G mobile communication systems includes new waveforms to ensure coverage in the terahertz band of 6G mobile communication technology, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), Array Antenna, and Large Scale Antenna, metamaterial-based lenses and antennas to improve the coverage of terahertz band signals, high-dimensional spatial multiplexing technology using Orbital Angular Momentum (OAM), Reconfigurable Intelligent Surface (RIS) technology, as well as full duplex technology to improve the frequency efficiency and system network of 6G mobile communication technology, satellite, AI (Artificial Intelligence) from the design operation and internalize end-to-end AI support functions to realize system optimization, and ultra-high-performance communication and computing resources to provide services with complexity that exceeds the limits of terminal computing capabilities. It can serve as a basis for the development of next-generation distributed computing technologies that can be realized by utilizing them.

[0008] As described above and with the development of mobile communication systems, various services have become available, and methods for effectively providing these services are required.

[0009] Meanwhile, user terminals can use AI models to improve wireless communication performance, and multiple such AI models may exist. However, because terminals lack information about external factors, such as the surrounding environment, they cannot select an AI model that reflects these factors. Therefore, information must be provided to the terminal to appropriately select an AI model.

[0010] Furthermore, even if a terminal can perform operations based on an AI model, communication performance may be superior to conventional operations that do not utilize the AI ​​model, depending on certain conditions or environmental factors. Therefore, relevant information must be provided to the terminal so that it can activate or deactivate AI model-based operations.

[0011] That is, information needs to be provided so that the terminal can decide whether to use or select an artificial intelligence model, and a method and device in a wireless communication system for early support are needed.

[0012] A method and device according to one embodiment of the present disclosure are intended to provide a method and device for supporting artificial intelligence model-based operation in a wireless communication system.

[0013] In addition, a method and device according to one embodiment of the present disclosure aim to provide a method and device that provide information on whether to use an artificial intelligence model and for selecting a model.

[0014] A method performed by a terminal in a wireless communication system according to one embodiment of the present disclosure, comprising: transmitting a registration request message including capability information of the terminal for AI-based operations to a network entity; receiving an indicator indicating whether or not AI-based operations are permitted and policy information regarding AI-based operations from the network entity; and activating AI-based operations.

[0015] A method performed by a first network entity in a wireless communication system according to one embodiment of the present disclosure, the method comprising: receiving a registration request message including capability information of the terminal for AI-based operation from a terminal; selecting a second network entity based on the capability information of the terminal; transmitting an AI-based operation-related policy request message to the second network entity; receiving AI-based operation-related policy information from the second network entity; and transmitting the AI-based operation-related policy information to the terminal.

[0016] According to one embodiment of the present disclosure, wireless communication performance can be improved under various conditions and environments by supporting the use of an artificial intelligence model in a wireless communication system.

[0017] The effects that can be obtained from the present disclosure are not limited to the effects mentioned in the embodiments of the present disclosure, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0018] FIG. 1 illustrates a wireless communication system structure that supports artificial intelligence-based operations according to one embodiment of the present disclosure.

[0019] FIG. 2 illustrates a method for setting artificial intelligence-based operation-related policy information according to one embodiment of the present disclosure.

[0020] FIG. 3 illustrates a method for providing model selection and management assistance information to a terminal supporting artificial intelligence-based operations according to one embodiment of the present disclosure.

[0021] FIG. 4 illustrates components of a user terminal according to one embodiment of the present disclosure.

[0022] FIG. 5 illustrates components of a network entity according to one embodiment of the present disclosure.

[0023] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0024] The various embodiments of the present disclosure described below illustrate a hardware-based approach as an example. However, since the various embodiments of the present disclosure include techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0025] 3GPP, responsible for cellular mobile communications standards, is standardizing a new core network architecture, dubbed 5G core (5GC), to facilitate the evolution of existing 4G LTE systems into 5G systems. Compared to the evolved packet core (EPC), the network core for existing 4G systems, 5GC supports the following differentiated features:

[0026] First, 5GC introduces network slicing. As a 5G requirement, 5GC must support various terminal types and services (e.g., eMBB, URLLC, or mMTC services). Each type of service has different requirements for the core network. For example, eMBB services require high data rates, while URLLC services require high reliability and low latency. One technology proposed to meet these diverse service requirements is network slicing.

[0027] Network slicing virtualizes a single physical network to create multiple logical networks. Each network slice instance (NSI) can have different characteristics. Therefore, each NSI can satisfy diverse service requirements by possessing a network function (NF) tailored to its characteristics. If each terminal is assigned an NSI that matches the characteristics of the service it requires, multiple 5G services can be efficiently supported.

[0028] Second, 5GC can facilitate support for the network virtualization paradigm by separating mobility management and session management functions. In 4G LTE (long term evolution), services were provided through signaling exchanges with a single core device called the mobility management entity (MME), which was responsible for registration, authentication, mobility management, and session management for all terminals. However, in 5G, the number of terminals increases explosively, and the mobility and traffic / session characteristics that must be supported for each terminal type become more specialized. Therefore, supporting all functions with a single device like the MME inevitably reduces scalability by adding entities for each required function. Therefore, various functions are being developed based on a structure that separates mobility management and session management functions to improve scalability in terms of functional / implementation complexity and signaling load of the core device responsible for the control plane.

[0029] Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. Furthermore, when describing embodiments of the present disclosure, detailed descriptions of related known functions or configurations will be omitted if they are deemed to unnecessarily obscure the gist of the embodiments. Furthermore, the terms described below are defined in consideration of their functions in the embodiments, and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the contents throughout this specification.

[0030] For the same reason, some components in the attached drawings are exaggerated, omitted, or schematically depicted. Furthermore, the dimensions of each component do not entirely reflect its actual size. Identical or corresponding components in each drawing are assigned the same reference numbers.

[0031] The advantages and features of the present disclosure, and methods for achieving them, will become clearer with reference to the embodiments described below in detail with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided solely to ensure that the present disclosure is 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. Like reference numerals designate like elements throughout the specification.

[0032] At this time, each block of the processing flowchart drawings and combinations of the flowchart drawings can be performed by computer program instructions. These computer program instructions can be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flowchart block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to implement the function in a specific manner, so that the instructions stored in the computer-available or computer-readable memory can also produce a manufactured item that includes an instruction means for performing the functions described in the flowchart block(s). Since the computer program instructions can also be installed on a computer or other programmable data processing device, a series of operations are performed on the computer or other programmable data processing device to create a computer-executable process, and the instructions that cause the computer or other programmable data processing device to perform the operations for performing the functions described in the flowchart block(s) can also provide operations for performing the functions described in the flowchart block(s).

[0033] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions.

[0034] Here, the term '~ unit' used in various embodiments of the present disclosure means a software or hardware component such as an FPGA or ASIC, and the '~ unit' can perform certain roles. However, the '~ unit' is not limited to software or hardware. The '~ unit' may be configured to be on an addressable storage medium and may be configured to play one or more processors. Accordingly, as an example, the '~ unit' may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, 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 '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. Additionally, components and '~parts' may be implemented to regenerate one or more CPUs within a device or secure multimedia card.

[0035] Hereinafter, a base station is an entity that performs resource allocation of a terminal, and may be at least one of an eNode B (eNB), a Node B, a BS (base station), a RAN (radio access network), an AN (access network), a RAN node, a NR NB, a gNB, a wireless access unit, a base station controller, or a node on a network. The terminal may include a user equipment (UE), a mobile station (MS), a cellular phone, a smartphone, a computer, or a multimedia system capable of performing a communication function. In various embodiments of the present disclosure, a case where the terminal is a UE will be described as an example. In addition, although various embodiments of the present disclosure are described below using a system based on LTE, LTE-A, or NR as an example, various embodiments of the present disclosure may be applied to other communication systems having a similar technical background or channel type. In addition, various embodiments of the present disclosure may be applied to other communication systems with some modifications within a range that does not significantly depart from the scope thereof at the discretion of a person having skilled technical knowledge.

[0036] While this disclosure describes various embodiments using terminology used in certain communication standards (e.g., 3rd Generation Partnership Project (3GPP)), these are merely illustrative examples. The various embodiments of this disclosure can be easily modified and applied to other communication systems. Below, some terms used in the core network of this disclosure are predefined.

[0037] AMF: Access and Mobility Management Function

[0038] NF: Network Function

[0039] NWDAF: Network Data Analytics Function

[0040] CN: Core Network

[0041] CNF: Containerized Network Function

[0042] PCF: Policy Control Function

[0043] SMF: Session Management Function

[0044] UDM: User Data Management

[0045] UPF: User Plane Function

[0046] The operating principles of embodiments according to the present disclosure are described in detail with reference to the attached drawings. The meanings of terms used to describe the embodiments can be determined by the contents throughout this specification.

[0047] The terms "network entity" or "network function" and objects used in this disclosure, terms referring to messages, terms referring to identification information, and the like, are provided for convenience of explanation. Therefore, the present invention is not limited to the terms described below, and other terms referring to objects with equivalent technical meanings may be used.

[0048] For convenience, embodiments according to the present disclosure may be described using terms and names defined in the 5G system standards, but the meanings thereof are not limited by the terms and names, and may be equally applied to systems conforming to other standards.

[0049] FIG. 1 illustrates the structure of a wireless communication system supporting artificial intelligence-based operations according to one embodiment of the present disclosure.

[0050] The structure of a wireless communication system supporting artificial intelligence-based operations may include various network functions (NFs), and FIG. 1 may exemplify some of them, such as an access and mobility management function (AMF), a session management function (SMF), a unified data management (UDM), a data network (DN) or a local part of DN that enables local access to the data network, a user plane function (UPF), a (radio) access network (R)AN, and / or a user equipment (UE).

[0051] The terminal may utilize an artificial intelligence model (e.g., a machine learning model) to perform operations such as channel state information prediction, channel state information compression, and positioning to improve wireless communication performance. For example, the terminal may determine the use of an artificial intelligence model to perform the operations, and if multiple artificial intelligence models are available, at least one model may be selected to perform the operations to improve wireless communication performance.

[0052] Each NF can support the following functions:

[0053] An AMF can be a function or device responsible for both access to a wireless access network and mobility management of terminals. AMF can provide functions for access and mobility management at the terminal level, and by default, one AMF can be connected to each terminal.

[0054] (R)AN can wirelessly transmit and receive data with terminals, and can transmit and receive terminal user plane data with UPF. In addition, it can perform terminal access and mobility management in conjunction with AMF.

[0055] A DN (Data Network) can represent, for example, operator services, Internet access, or third-party services. The DN can transmit downlink protocol data units (PDUs) to the UPF or receive PDUs transmitted from a terminal (UE) from the UPF. The local part of the DN is a portion of the DN that can represent a data network with local access and a short data transmission path. It can also be used to refer to a DN where edge application servers are deployed to support edge computing services.

[0056] PCF can receive information about packet flows from application servers and provide functions to determine policies such as mobility management and session management. Specifically, PCF can support functions such as supporting a unified policy framework for controlling network operations, providing policy rules so that control plane functions (e.g., AMF, SMF, etc.) can enforce the policy rules, and implementing a front end for accessing relevant subscription information for policy decision-making within a unified data repository (UDR).

[0057] SMF provides session management functions, and if a terminal has multiple sessions, each session can be managed by a different SMF.

[0058] UDM can store terminal subscription information, context used by the terminal within the network, or policy data.

[0059] The UPF can forward a downlink PDU received from a DN to a terminal via (R)AN, and can forward an uplink PDU received from a terminal via (R)AN to the DN.

[0060] FIG. 2 illustrates a method for setting policy information related to AI-based operation according to one embodiment of the present disclosure.

[0061] 1. The terminal may transmit a registration request message to the AMF. If the terminal supports artificial intelligence (AI)-based operations, the terminal may include AI-based operation UE capability information in the registration request message and transmit it. In other words, the terminal may include information about its capabilities for AI-based operations in the registration request message and transmit it. The terminal's AI-based operation UE capability may include at least one of the following information:

[0062] - An indicator or index indicating that the terminal supports AI-based operations.

[0063] Information about AI-based operations or functions supported by the terminal. For example, a list of operations such as CSI (channel state information) compression, CSI prediction, and positioning.

[0064] - Information about the artificial intelligence (e.g., machine learning) model supported by the terminal (model identifier, etc.)

[0065] The registration request message that the terminal transmits to the AMF may include information such as the terminal identifier and the terminal device identifier (PEI; Permanent Equipment Identifier or IMEI; International Mobile Equipment Identity).

[0066] 2. When the AMF receives a registration request message containing AI-based operation UE capability information, it can verify information related to the corresponding terminal device. The AMF may consider the terminal device identifier (PEI or IMEI) to determine whether AI-based operations are supported.

[0067] For example, AMF may perform actions such as determining whether AI-based actions can be performed on the terminal type or device itself based on information set by local configuration or operator policy, and whether AI-based actions are prohibited on the terminal type or device.

[0068] Alternatively, the AMF may provide a terminal device identifier to the Equipment Identity Register (EIR) and receive terminal device-related information from the EIR to determine the terminal device status related to AI-based operations. The AMF may include operations for determining whether the terminal type or device can perform AI-based operations and whether AI-based operations are prohibited on the terminal type or device related to AI-based operations.

[0069] 3. AMF can obtain subscriber information from UDM. AMF can check whether AI-based operations are authorized within subscriber information.

[0070] 4. If the registration request includes the AI-based operation UE capability, the AMF can select a PCF that can provide AI-based operation-related policies. Alternatively, even if the AI-based operation UE capability is not included, the AMF can select a PCF that supports the AI-based UE operation capability according to its own configured policies.

[0071] Additionally, if AMF has AI-based operation support permission information for the corresponding terminal in the subscriber information obtained from UDM, it can select a PCF that can provide AI-based operation related policies.

[0072] The PCF selected by the AMF in operation 4 may be the same PCF that provides the existing terminal policy or access and mobility management policy, and the terminal policy or AM (Access and Mobility) policy provided by the PCF may include policies related to the AI-based operation of the terminal. In other words, the AMF may select a PCF considering support for AI-based operation policies.

[0073] 5. The AMF can send a policy association request message to the PCF selected in the above 4 operations. The AMF can request AI-based operation-related policies from the PCF. The AMF can send at least one of the following information to the PCF: an AI-based operation policy request indicator, terminal location information (cell ID, TAI, GPS coordinates, RAN ID, etc.), terminal identifier, terminal device identifier, terminal current access type (RAT information), frequency (e.g., used frequency band information, carrier frequency information), and AI-based operation capability.

[0074] 6. The PCF can generate an AI-based operation-related policy based on the information received from the AMF. To generate an AI-based operation-related policy, the PCF can obtain and use detailed terminal location information or terminal location area characteristic information from other network functions (e.g., GMLC, LMF, NWDAF, etc.). The PCF can send a policy association response message to the AMF that includes AI-based operation-related policy information, a terminal identifier, a policy association ID, and policy effective area / time information. The AI-based operation-related policy information can include at least one piece of information such as a model selection assistance rule and an AI-based operation activation rule.

[0075] A model selection assistance rule can refer to a rule for selecting an artificial intelligence model (or machine learning model) used for AI-based operations to improve wireless communication performance on a terminal. For example, it can include information such as region-based model selection rule information and time-based model selection rule information.

[0076] AI-based operation activation rule information may include rules for activating / deactivating AI-based operations on a terminal. For example, it may include rules directing the activation or deactivation of AI-based operations in a specific region.

[0077] When a model selection assistance rule and an AI-based operation activation rule include rules that operate on a region basis, the model selection assistance rule may include regional topology characteristics (e.g., terminal or base station deployment density, etc.) that can be used for region-based model selection and AI-based operation activation operations, and regional wireless channel characteristic assistance information (e.g., regional characteristic information that can vary in wireless channel characteristics, such as information that can distinguish between an urban area and a suburban area) as in the following example.

[0078]

[0079]

[0080] Regional topology information and regional wireless channel characteristic auxiliary information can be displayed as specific index information assigned by the operator and shared and used between network functions and terminals.

[0081] In the embodiment according to the present disclosure, a method for AMF to obtain AI-based operation-related policy information from PCF has been described, but AMF may obtain AI-based operation-related policy information from another AI-based operation-related network function or may determine AI-based operation-related policy by utilizing information set by AMF itself.

[0082] 7. The AMF can transmit an indicator indicating whether AI-based operations are permitted or enabled to the terminal, along with policy information related to AI-based operations. During this process, the AMF can transmit policy information related to AI-based operations to the RAN, and the RAN can then decide whether to use the policy information and provide the information to the terminal.

[0083] 8. The terminal may perform a model selection assistance rule operation or an AI-based operation activation rule operation based on an indicator indicating whether AI-based operation is permitted or possible received from an AMF or a base station and an AI-based operation-related policy. For example, if the terminal receives regional topology information (base station density or terminal density) corresponding to the area where the terminal is currently located and a regional wireless channel characteristic assistance information (UMa) value or an index value corresponding thereto, the terminal may decide to perform AI-based operation activation for an area with a specific base station / terminal density and a specific wireless channel characteristic assistance information (Uma) value, may choose to use an AI model (or a machine learning model, a deep learning model) trained for an area with a specific base station / terminal density and a specific wireless channel characteristic assistance information (Uma) value, and may use the AI ​​model for operations such as CSI compression / prediction.

[0084] FIG. 3 illustrates a method for providing model selection and management assistance information to a terminal supporting AI-based operations according to one embodiment of the present disclosure. FIG. 3 also describes a method for providing AI-based operation-related assistance information to a terminal.

[0085] 1. The terminal may send a request to the AMF for AI model selection / lifecycle management assistance information. This request may be sent if the terminal supports AI-based operations. The terminal may include AI-based operation UE capability information in the request message and send it. The terminal's AI-based operation UE capability may include at least one of the following information:

[0086] - An indicator or index indicating that the terminal supports AI-based operations.

[0087] Information about AI-based operations or functions supported by the terminal. For example, a list of operations such as CSI (channel state information) compression, CSI prediction, and positioning.

[0088] - Information about artificial intelligence (e.g., machine learning) models supported by the terminal (e.g., list of model identifiers)

[0089] The registration request message that the terminal transmits to the AMF may include information such as the terminal identifier and terminal device identifier (PEI or IMEI).

[0090] 2. When AMF receives an AI model selection / lifecycle management assistance information request message, it can perform authorization for the corresponding service. AMF can perform at least one of the following authorization actions or support-enablement check actions.

[0091] The AMF can check whether the RAN to which the current terminal is connected supports / allows AI-based operations (whether AI-based operations are supported or permitted). The AMF can check whether AI-based operations are supported / allowed in the region where the current terminal is located. The AMF can include operations such as checking whether the terminal type or device itself can perform AI-based operations and whether AI-based operations are prohibited on the terminal type or device based on information set by local configuration or operator policy.

[0092] The AMF can check the status of terminal devices related to AI-based operations by linking with the terminal device identifier provided to the Equipment Identity Register (EIR). The AMF can perform operations on terminal devices related to AI-based operations, such as checking whether the terminal type or device itself can perform AI-based operations and whether AI-based operations are prohibited on the terminal type or device. The AMF can obtain subscriber information from the UDM. The AMF can check information on whether AI-based operations are authorized within the subscriber information.

[0093] 3. If the registration request includes AI-based operation UE capability and AI-based operation support is allowed / possible, the AMF may perform an operation of obtaining AI model selection / lifecycle management assistance information from an AI operation-related network function (e.g., NWDAF). According to one embodiment, the AMF may search for and select an AI operation-related network function that supports the AI ​​model selection / lifecycle management assistance information provision service function. This search and selection operation may utilize AI operation-related NF information locally configured in the AMF, or may search for and select an AI operation-related network function by providing terminal device type / identifier information, terminal identifier, AI model selection / lifecycle management assistance support information, terminal location information, cell ID, RAN ID, RAT information, Frequency (e.g., used frequency band information, carrier frequency information), etc. to the NRF (Network Repository Function).

[0094] The AMF may request AI model selection / lifecycle management assistance information to the selected AI operation-related network function (e.g., NWDAF). (Assistance information request) The AMF may transmit at least one of an AI-based operation policy request indicator, terminal location information (cell ID, TAI, GPS coordinates, RAN ID, etc.), terminal identifier, terminal device identifier, terminal current access type, and AI-based operation capability to the AI ​​operation-related network function. In order to include detailed location information of the terminal in the request message, the AMF may request and obtain detailed location information of the terminal from the GMLC (Gateway Mobile Location Center) or the LMF (Location Management Function), and provide the information to the AI ​​operation-related network function.

[0095] 4. AI operation-related network functions (e.g., NWDAF) can determine AI model selection / lifecycle management assistance information by considering information received from the AMF. NF can obtain and use detailed terminal location information or terminal location area characteristic information from other network functions (e.g., GMLC, LMF, etc.) to determine AI model selection / lifecycle management assistance information.

[0096] 5. The AI ​​operation-related network function can send a response message to the AMF that includes AI model selection / lifecycle management assistance information, a terminal identifier, a policy association ID, and policy effective region / time information. The AI ​​model selection / lifecycle management assistance information can include at least one piece of information, such as model selection assistance information and AI-based operation activation information.

[0097] Model selection assistance information may refer to assistance information used to select an artificial intelligence model (e.g., a machine learning or deep learning model) used for AI-based operations to improve wireless communication performance in a terminal. For example, model selection assistance information may include information such as region-based model selection assistance information and time-based model selection assistance information.

[0098] AI-based operation activation assistance information may include information that can be used as an aid in determining whether to activate or deactivate AI-based operations on a terminal. For example, it may include assistance information for activating or deactivating AI-based operations in a specific region.

[0099] Model selection assistance information and AI-based operation activation information may include regional topology characteristics (e.g., terminal or base station deployment density, etc.) and regional wireless channel characteristic assistance information (e.g., regional characteristic information where wireless channel characteristics may vary, such as information that can distinguish between urban and suburban areas), which can be used for region-based model selection and AI-based operation activation operations, when the model selection assistance information and AI-based operation activation information include rules that operate based on a region.

[0100] Regional wireless channel characteristic auxiliary information is described in [Table 1] mentioned above.

[0101] 6. The AMF may transmit an indicator indicating whether AI-based operation is permitted or possible to the terminal and AI-based operation activation assistance information. According to one embodiment, the AMF may provide the AI-based operation activation assistance information to the UE by matching the Model selection assistance information and AI-based operation activation information described in operation 5 with the AI-based operation UE capability of the terminal. For example, if a model identifier is included in the AI-based operation UE capability, the AMF may map a specific model identifier and the Model selection assistance information and the AI-based operation activation information and provide them to the UE. According to one embodiment, only one of the Model selection assistance information and the AI-based operation activation information may be provided.

[0102] 7. The terminal may use the indicator indicating whether AI-based operation is permitted or possible and the AI-based operation activation assistance information (Model selection assistance information and AI-based operation activation information) received from the AMF via the base station to perform a model selection assistance rule operation or an AI-based operation activation rule operation. For example, when the terminal receives regional topology information (base station density or terminal density) corresponding to the area where the terminal is currently located and regional wireless channel characteristic assistance information (UMa) values ​​or index values ​​corresponding thereto, the terminal may decide to perform AI-based operation activation for an area with a specific base station / terminal density and a specific wireless channel characteristic assistance information (Uma) value, may choose to use an AI model (e.g., a machine learning model, a deep learning model, etc.) trained for an area with a specific base station / terminal density and a specific wireless channel characteristic assistance information (Uma) value, and may use the AI ​​model for operations such as CSI compression / prediction.

[0103] FIG. 4 illustrates an example of the functional structure of a terminal according to one embodiment of the present disclosure. The configuration illustrated in FIG. 4 can be understood as a configuration of a terminal. Terms such as "... unit" and "... device" used hereinafter refer to a unit that processes at least one function or operation, which can be implemented using hardware, software, or a combination of hardware and software. The terminal of FIG. 4 may correspond to the terminals of FIGS. 1 to 3.

[0104] Referring to FIG. 4, the terminal may include a communication unit (405), a storage unit (410), and a control unit (415).

[0105] The communication unit (405) can perform functions for transmitting and receiving signals via a wireless channel. For example, the communication unit (405) can perform a conversion function between a baseband signal and a bit stream according to the physical layer specifications of the system. For example, when transmitting data, the communication unit (405) can generate complex symbols by encoding and modulating a transmission bit stream. In addition, when receiving data, the communication unit (405) can restore a reception bit stream by demodulating and decoding a baseband signal. In addition, the communication unit (405) can upconvert a baseband signal to an RF band signal and transmit it through an antenna, and downconvert an RF band signal received through the antenna to a baseband signal. For example, the communication unit (405) can include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc.

[0106] In addition, the communication unit (405) may include a plurality of transmit / receive paths. Furthermore, the communication unit (405) may include at least one antenna array composed of a plurality of antenna elements. In terms of hardware, the communication unit (405) may be composed of digital circuits and analog circuits (e.g., radio frequency integrated circuits (RFIC)). Here, the digital circuits and analog circuits may be implemented in a single package. In addition, the communication unit (405) may include a plurality of RF chains. Furthermore, the communication unit (405) may perform beamforming.

[0107] The communication unit (405) can transmit and receive signals as described above. Accordingly, all or part of the communication unit (405) may be referred to as a "transmitter," a "receiver," or a "transmitting and receiving unit." Furthermore, in the following description, transmission and reception performed via a wireless channel are used to mean that processing as described above is performed by the communication unit (405).

[0108] The storage unit (410) can store data such as basic programs, application programs, and setting information for the operation of the terminal. The storage unit (410) can be composed of volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. In addition, the storage unit (410) can provide stored data upon request from the control unit (415).

[0109] The control unit (415) can control the overall operations of the terminal. For example, the control unit (415) can transmit and receive signals through the communication unit (405). In addition, the control unit (415) records and reads data in the storage unit (410). In addition, the control unit (415) can perform the functions of the protocol stack required by the communication standard. To this end, the control unit (415) may include at least one processor or microprocessor, or may be a part of a processor. In addition, a part of the communication unit (405) and the control unit (415) may be referred to as a CP (communication processor). According to various embodiments, the control unit (415) can control to perform synchronization using a wireless communication network. For example, the control unit (415) can control the terminal to perform operations according to various embodiments described below.

[0110] According to various embodiments of the present disclosure, a terminal may be composed of a mobile equipment (ME) and a universal mobile telecommunications service (UMTS) subscriber identity module (USIM). The ME may include a mobile terminal (MT) and terminal equipment (TE). The MT may be a part where a wireless access protocol operates, and the TE may be a part where a control function operates. For example, in the case of a wireless communication terminal (e.g., a mobile phone), the MT and the TE may be integrated, and in the case of a laptop, the MT and the TE may be separate. The present disclosure may express the ME and the USIM as distinct entities depending on the operation of each component, but is not limited thereto, and may express the ME and the USIM as a terminal (e.g., UE) including the ME, or it is of course possible to describe various embodiments of the present disclosure by expressing the ME as a terminal.

[0111] FIG. 5 illustrates an example of a functional structure of a core network object according to one embodiment of the present disclosure. It illustrates the configuration of a core network object in a wireless communication system according to various embodiments of the present disclosure. The configuration illustrated in FIG. 5 can be understood as a configuration of a device having the function of at least one of the network entities including the AMF of FIG. 1. Terms such as "... unit" and "... device" used hereinafter mean a unit that processes at least one function or operation, which can be implemented by hardware, software, or a combination of hardware and software. The network entity of FIG. 5 may correspond to the network entity illustrated in FIGS. 1 to 3.

[0112] Referring to FIG. 5, the core network object is configured to include a communication unit (505), a storage unit (510), and a control unit (515).

[0113] The communication unit (505) may provide an interface for performing communication with other devices within the network. That is, the communication unit (505) may convert a bit string transmitted from a core network object to another device into a physical signal, and may convert a physical signal received from another device into a bit string. That is, the communication unit (505) may transmit and receive signals. Accordingly, the communication unit (505) may be referred to as a modem, a transmitter, a receiver, or a transceiver. In this case, the communication unit (505) may enable the core network object to communicate with other devices or systems via a backhaul connection (e.g., a wired backhaul or a wireless backhaul) or via a network.

[0114] The storage unit (510) can store data such as basic programs, application programs, and configuration information for the operation of core network objects. The storage unit (510) can be composed of volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. In addition, the storage unit (510) can provide stored data upon request from the control unit (515).

[0115] The control unit (515) can control the overall operations of the core network object. For example, the control unit (515) can transmit and receive signals through the communication unit (505). In addition, the control unit (515) records and reads data from the storage unit (510). For this purpose, the control unit (515) can include at least one processor. According to various embodiments of the present disclosure, the control unit (515) can control synchronization using a wireless communication network. For example, the control unit (515) can control the core network object to perform operations according to various embodiments described below.

[0116] The terms used in the above description to identify connection nodes, terms referring to network entities, terms referring to messages, terms referring to interfaces between network entities, terms referring to various identification information, etc. are provided for convenience of explanation. Therefore, the present disclosure is not limited to the above-described terms, and other terms referring to objects with equivalent technical meanings may be used.

[0117] The operations of the embodiments described above can be realized by providing a memory device storing program code in any component within the device. That is, the control unit within the device can execute the operations described above by reading and executing the program code stored in the memory device through a processor or a CPU (Central Processing Unit).

[0118] The various components and modules of the entity or terminal device described in the present disclosure may be operated using hardware circuits, such as logic circuits based on complementary metal oxide semiconductors, firmware, software, and / or hardware and firmware and / or software embedded in a machine-readable medium. For example, various electrical structures and methods may be implemented using electrical circuits such as transistors, logic gates, and application-specific semiconductors.

[0119] The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0120] When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.

[0121] These programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic disc storage devices, compact disc-ROMs (CD-ROMs), digital versatile discs (DVDs) or other forms of optical storage devices, magnetic cassettes, or may be stored in memories formed by a combination of some or all of these. In addition, each configuration memory may include multiple copies.

[0122] Additionally, the program may be stored on an attachable storage device that is accessible via a communication network, such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a storage area network (SAN), or a combination thereof. Such a storage device may be connected to a device implementing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device implementing an embodiment of the present disclosure.

[0123] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed singularly or plurally, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in plural may be composed of singular elements, or components expressed in singular may be composed of plural elements.

[0124] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims described below, but also by equivalents thereof.

Claims

1. A method performed by an AMF (access and mobility management function) entity of a wireless communication system, A step of receiving a first message for requesting first information about an AI (artificial intelligence) model from a terminal via a base station; A step for identifying whether AI-based operation of the above terminal is permitted; A step of obtaining said first information from a network function entity; A method comprising the step of transmitting a second message including the first information to the terminal via the base station.

2. In paragraph 1, The first message contains information on the terminal's capabilities for AI-based operations, A method wherein the above capability information includes at least one of an indicator indicating whether the terminal supports AI-based operations, information indicating a function of an AI-based operation supported by the terminal, or information on an AI model supported by the terminal.

3. In paragraph 1, The step of identifying whether the AI-based operation of the above terminal is permitted is as follows: A method performed based on at least one of subscriber information for the terminal, the type of the terminal, and the location of the terminal.

4. In paragraph 1, The step of obtaining the first information from the above network function entity comprises: A step of exploring the above network function entity, and a step of transmitting a third message for requesting the first information to the network function entity; and A method comprising the step of receiving a fourth message including the first information from the network function entity.

5. In paragraph 4, The third message includes at least one of an instruction for requesting a policy regarding AI-based operation, information about the location of the terminal, an identifier of the terminal, a device identifier of the terminal, an access type of the terminal, or a capability of the terminal. A method, wherein the first information includes at least one of second information about the deployment density of terminals or base stations in an area and third information about wireless channel characteristics in an area.

6. In a method performed by a terminal of a wireless communication system, A step of transmitting a first message to an access and mobility management function (AMF) via a base station to request first information about an artificial intelligence (AI) model; A step of receiving a second message including the first information from the AMF via the base station; and A method comprising the step of selecting an AI model or activating or deactivating an AI model-based operation based on the first information.

7. In paragraph 6, The first message contains information on the terminal's capabilities for AI-based operations, The above capability information includes at least one of an indicator indicating whether the terminal supports AI-based operations, information indicating the function of AI-based operations supported by the terminal, or information on an AI model supported by the terminal. A method, wherein the first information includes at least one of second information about the deployment density of terminals or base stations in an area and third information about wireless channel characteristics in an area.

8. In the AMF (access and mobility management function) entity of a wireless communication system, Transmitter and receiver; and Including a control unit connected to the above transmitter and receiver, The above control unit: Receive a first message from the terminal to request first information about an AI (artificial intelligence) model via a base station, Identify whether AI-based operations of the above terminal are permitted, Obtaining the first information from a network function entity, An AMF entity configured to transmit a second message including the first information to the terminal via the base station.

9. In paragraph 8, The first message contains information on the terminal's capabilities for AI-based operations, An AMF entity including at least one of the following capability information: an indicator indicating whether the terminal supports AI-based operations, information indicating the function of AI-based operations supported by the terminal, or information on an AI model supported by the terminal.

10. In paragraph 8, The above control unit, An AMF entity configured to identify whether AI-based operation of the terminal is permitted based on at least one of subscriber information for the terminal, the type of the terminal, and the location of the terminal.

11. In paragraph 8, The above control unit; Searching for the network function entity to obtain the first information from the network function entity, Transmitting a third message to the network function entity to request the first information, and An AMF entity further configured to receive a fourth message including the first information from the network function entity.

12. In paragraph 11, An AMF entity, wherein the third message comprises at least one of an instruction for requesting an AI-based operation policy, information about the location of the terminal, an identifier of the terminal, a device identifier of the terminal, an access type of the terminal, or a capability for AI-based operation of the terminal.

13. In paragraph 8, An AMF entity, wherein the first information includes at least one of second information about the deployment density of terminals or base stations in an area and third information about wireless channel characteristics in an area.

14. In the terminal of a wireless communication system, Transmitter and receiver; and Including a control unit connected to the above transmitter and receiver, The above control unit: Transmitting a first message to the AMF (access and mobility management function) via the base station to request first information about the AI ​​(artificial intelligence) model, Receive a second message including the first information from the AMF via the base station, and A terminal configured to select an AI model or activate or deactivate an operation based on the AI ​​model based on the first information.

15. In paragraph 14, The first message contains information on the terminal's capabilities for AI-based operations, The above capability information includes at least one of an indicator indicating whether the terminal supports AI-based operations, information indicating the function of AI-based operations supported by the terminal, or information on an AI model supported by the terminal. A terminal, wherein the first information includes at least one of second information about the deployment density of terminals or base stations in an area and third information about wireless channel characteristics in an area.

Images