Configuration of the model identification type

Abstract

The present disclosure describes a novel method of using the pre-configured AI / ML (artificial intelligence / machine learning) with model type classification in wireless mobile communication system including base station e.g., gNB, TRP, TN, NTN and mobile station e.g., UE. In AI / ML model is applied to radio access network, signaling overhead can be significantly increased for frequent signaling exchanges with varying ML element information e.g., model, dataset, ML configuration parameter, etc. Therefore, model operation e.g., model training, inferencing, monitoring, updating, etc. can be set up between network and UE by configuring multiple model identification types for ML operation.

Description

[0001] 202407097

[0002] - 1 -

[0003] TITLE

[0004] Method of model identification type configuration

[0005] TECHNNICAL FIELD

[0006] The present disclosure relates to the field of AI / ML based model operation with model type classification, where techniques for configuring multiple model identification types applicable to radio access network are presented.

[0007] BACKGROUND

[0008] In 3GPP (Third Generation Partnership Project), one of the selected study items as the approved Release 18 package is AI / ML (artificial intelligence / machine learning) as described in the related document (RP-213599) addressed in 3GPP TSG (Technical Specification Group) RAN (Radio Access Network) meeting #94e. The official title of AI / ML study item is “Study on AI / ML for NR Air Interface”. The goal of this study item is to identify a common AI / ML framework and areas of obtaining gains using AI / ML based techniques with use cases. According to 3GPP, the main objective of this study item is to study AI / ML framework for air-interface with target use cases by considering performance, complexity, and potential specification impact. In particular, AI / ML model, terminology and description to identify common and specific characteristics for framework are included as one of key work scopes. Regarding AI / ML framework, various aspects are under consideration for investigation and one of key items is about lifecycle management of AI / ML model where multiple stages are included as mandatory for model training, model deployment, model inference, model monitoring, model updating etc. Also in 3GPP, two-sided (AI / ML) model is defined as a paired AI / ML model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network. Also for one-sided (AI / ML) model, UE-side (AI / ML) model is defined as an AI / ML model whose inference is performed entirely at the UE and network-side (AI / ML) model is defined as an AI / ML model whose inference is performed entirely at the network. Currently, AI / ML specification work is at the stage of work item discussion for Release 19. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection 202407097

[0009] - 2 - for NR and EN-DC, UE (user equipment) mobility was also considered as one of AI / ML use cases and one of scenarios for model training / inference is that both functions are located within RAN node. Followingly, in Release 18 the new work item of “Artificial Intelligence (Al) / Machine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture. For the above active standardization works, RAN-based AI / ML model is considered very significant for both network and UE to meet any desired model operations (e.g., model training, inference, selection, switching, update, monitoring, etc.). Model information can be signaled to pair both networkside and UE-side models for various lifecycle management (LCM) operations.

[0010] However, signaling overhead indicating model information can be very high especially when model based LCM is processed between base station (BS / gNB) and multiple UEs. In LCM, model training is one of the most important parts for model deployment and currently there is no specification defined for signaling methods and network-UE behaviors so as to identify the required dataset when model updating / re- training as any activated model can be also impacted due to model / data drift. When ML condition changes, the enabled AI / ML model(s) can be impacted for model performance due to data / model drift. In this case, model re-training / updating can be executed.

[0011] Current specifications lack a unified, low-overhead mechanism to identify, activate, and switch AI / ML models dynamically while minimizing signaling overhead and supporting multi-vendor deployments. Furthermore, upcoming 6G systems are expected to be Al-native, requiring standardized procedures for model identification and lifecycle management embedded into RAN protocols. The present invention addresses this gap by introducing structured ML identifiers and signaling procedures that enable efficient model activation, reuse, and adaptation across NG-RAN and future Al-native 6G architectures.

[0012] US2024086766A describes a method of receiving a request for retrieving or executing a machine learning model or a combination of ML models with a specified 202407097

[0013] - 3 - output feature and specified input data type and distribution of input values for a ML model or combination of ML models.

[0014] US20240154709A1 describes the configuration message indicating a model identifications and measurement for generating a data set corresponding to the model ID.

[0015] US20240267755A1 describes the RRC (radio resource control) model including a model identifier, a model structure, or parameters that indicate the AI / ML model to be implemented by the device.

[0016] WO2023209577A1 describes a method of indicating and configuring machine learning model support, including a ML type and / or version information of at least one model associated with a certain functionality.

[0017] WO2024128636A1 describes a method for AI / ML model / functionality life cycle management including metadata related to the AI / ML model / functionality and assigning an identifier to the AI / ML model / functionality.

[0018] WO2024165946A1 describes a method of AI / ML model identifiers usage with signaling procedures required to be defined between the terminal device and the network to determine the validity of a given AI / ML model.

[0019] WO20241 68831 A1 describes a method of general framework for model / functionality identification with RAN awareness of AI / ML model through network function / server, RAN awareness of AI / ML model through UE report, and the model ID usage in different aspects of LCM.

[0020] BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is an exemplary ML identifier structural formats. 202407097

[0022] - 4 -

[0023] Figure 2 is an exemplary flow chart of configuring ML identifier formats at network side.

[0024] Figure 3 is an exemplary flow chart of switching model types at UE side.

[0025] Figure 4 is an exemplary flow chart of updating ML ID information after model type switching.

[0026] DETAILED DESCRIPTION

[0027] The detailed description set forth below, with reference to annexed drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the invention.

[0028] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0029] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do 202407097

[0030] - 5 - not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

[0031] In some embodiments, a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a UE (directly or via another node) and / or with another network node. Examples of network nodes are NodeB, MeNB, ENB, a network node belonging to MCG or SCG, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), access point (AP), transmission points, transmission nodes, RRU, RRH, nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc.), Operations & Maintenance (O&M), Operations Support System (OSS), Self Optimized Network (SON), positioning node (e.g. Evolved- Serving Mobile Location Centre (E-SMLC)), Minimization of Drive Tests (MDT), test equipment (physical node or software), etc.

[0032] In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device communicating with a network node and / or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc. 202407097

[0033] - 6 -

[0034] Additionally, terminologies such as base station / gNodeB and UE should be considered non-limiting and do in particular not imply a certain hierarchical relation between the two; in general, “gNodeB” could be considered as device 1 and “UE” could be considered as device 2 and these two devices communicate with each other over some radio channel. And in the following the transmitter or receiver could be either gNodeB (gNB), or UE.

[0035] As will be appreciated by one skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method, or program product. Accordingly, embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects.

[0036] For example, the disclosed embodiments may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off- the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function.

[0037] Furthermore, embodiments may take the form of a program product embodied in one or more computer readable storage devices storing machine readable code, computer readable code, and / or program code, referred hereafter as code. The storage devices may be tangible, non- transitory, and / or non-transmission. The storage devices may not embody signals. In a certain embodiment, the storage devices only employ signals for accessing code.

[0038] Any combination of one or more computer readable medium may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing the code. The 202407097

[0039] - 7 - storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0040] More specific examples (a non-exhaustive list) of the storage device would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a portable compact disc readonly memory (“CD-ROM”), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0041] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object- oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

[0042] Furthermore, the described features, structures, or characteristics of the embodiments may be combined in any suitable manner. In the following description, numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a 202407097

[0043] - 8 - thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that embodiments may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of an embodiment. Reference throughout this specification to “one embodiment,” “an embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment,” “in an embodiment,” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean “one or more but not all embodiments” unless expressly specified otherwise. The terms “including,” “comprising,” “having,” and variations thereof mean “including but not limited to,” unless expressly specified otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a,” “an,” and “the” also refer to “one or more” unless expressly specified otherwise.

[0044] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[0045] The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the storage device produce an article of 202407097

[0046] - 9 - manufacture including instructions which implement the function / act specified in the flowchart diagrams and / or block diagrams.

[0047] The code may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer implemented process such that the code which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[0048] The flowchart diagrams and / or block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products according to various embodiments. In this regard, each block in the flowchart diagrams and / or block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s).

[0049] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures.

[0050] Although various arrow types and line types may be employed in the flowchart and / or block diagrams, they are understood not to limit the scope of the corresponding embodiments. Indeed, some arrows or other connectors may be used to indicate only the logical flow of the depicted embodiment. For instance, an arrow may indicate a waiting or monitoring period of unspecified duration between enumerated steps of the depicted embodiment. It will also be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, can be implemented by special purpose hardware-based 202407097

[0051] - 10 - systems that perform the specified functions or acts, or combinations of special purpose hardware and code.

[0052] The description of elements in each figure may refer to elements of proceeding figures. Like numbers refer to like elements in all figures, including alternate embodiments of like elements.

[0053] The detailed description set forth below, with reference to the figures, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. For instance, although 3GPP terminology, from e.g., 5G NR, may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the present disclosure.

[0054] The disclosure is related to wireless communication system, which may be for example a 5G NR wireless communication system. More specifically, it represents a RAN of the wireless communication system, which is used exchange data with UEs via radio signals. For example, the RAN may send data to the UEs (downlink, DL), for instance data received from a core network (CN). The RAN may also receive data from the UEs (uplink, UL), which data may be forwarded to the CN.

[0055] In the examples illustrated, the RAN comprises one base station, BS. Of course, the RAN may comprise more than one BS to increase the coverage of the wireless communication system. Each of these BSs may be referred to as NB, eNodeB (or eNB), gNodeB (or gNB, in the case of a 5G NR wireless communication system), an access point or the like, depending on the wireless communication standard(s) implemented.

[0056] The UEs are located in a coverage of the BS. The coverage of the BS corresponds 202407097

[0057] - 11 - for example to the area in which UEs can decode a PDCCH transmitted by the BS.

[0058] An example of a wireless device suitable for implementing any method, discussed in the present disclosure, performed at a UE corresponds to an apparatus that provides wireless connectivity with the RAN of the wireless communication system, and that can be used to exchange data with said RAN. Such a wireless device may be included in a UE. The UE may for instance be a cellular phone, a wireless modem, a wireless communication device, a handheld device, a laptop computer, or the like. The UE may also be an Internet of Things (loT) equipment, like a wireless camera, a smart sensor, a smart meter, smart glasses, a vehicle (manned or unmanned), a global positioning system device, etc., or any other equipment that may run applications that need to exchange data with remote recipients, via the wireless device.

[0059] The wireless device comprises one or more processors and one or more memories. The one or more processors may include for instance a central processing unit (CPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. The one or more memories may include any type of computer readable volatile and non-volatile memories (magnetic hard disk, solid-state disk, optical disk, electronic memory, etc.). The one or more memories may store a computer program product, in the form of a set of programcode instructions to be executed by the one or more processors to implement all or part of the steps of a method for exchanging data, performed at a UE’s side, according to any one of the embodiments disclosed herein.

[0060] The wireless device can comprise also a main radio, MR, unit. The MR unit corresponds to a main wireless communication unit of the wireless device, used for exchanging data with BSs of the RAN using radio signals. The MR unit may implement one or more wireless communication protocols, and may for instance be a 3G, 4G, 5G, NR, WiFi, WiMax, etc. transceiver or the like. In preferred embodiments, the MR unit corresponds to a 5G NR wireless communication unit.

[0061] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs. 202407097

[0062] - 12 -

[0063] AI / ML model delivery is a generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note is An entity could mean network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

[0064] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0065] AI / ML model testing is a subprocess of training, to evaluate the performance of final AI / ML model using dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.

[0066] AI / ML model training is a process to train an AI / ML Model [by learning the input / output relationship] in data driven manner and obtain the trained AI / ML Model for inference.

[0067] AI / ML model transfer is a delivery of an AI / ML model over the air interface in manner that is not transparent to 3GPP signaling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model.

[0068] AI / ML model validation is a subprocess of training, to evaluate the quality of an AI / ML model using dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0069] Data collection is a process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference.

[0070] Federated learning I federated training is a machine learning technique that trains an AI / ML model across multiple decentralized edge nodes e.g., UEs, gNBs each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples. 202407097

[0071] - 13 -

[0072] Functionality identification is a process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Note is Information regarding the AI / ML functionality may be shared during functionality identification. Where AI / ML functionality resides depends on the specific use cases and sub use cases.

[0073] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0074] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0075] Model download means Model transfer from the network to UE.

[0076] Model identification is A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. The process / method of model identification may or may not be applicable and regarding the AI / ML model may be shared during model identification.

[0077] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.

[0078] Model parameter update is Process of updating the model parameters of model. Model selection is the process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Model selection may or may not be carried out simultaneously with model activation.

[0079] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0080] Model update is Process of updating the model parameters and / or model structure of model.

[0081] Model upload is Model transfer from UE to the network. 202407097

[0082] - 14 -

[0083] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0084] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0085] Offline training is an AI / ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note is This definition only serves as guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions.

[0086] Online field data is the data collected from field and used for online training of the AI / ML model.

[0087] Online training is an AI / ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note is the notion of (near) real-time vs. non real-time is context- dependent and is relative to the inference time-scale. This definition only serves as guidance.

[0088] There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note is Fine- tuning / re-training may be done via online or offline training. This note could be removed when we define the term fine-tuning.

[0089] Reinforcement Learning (RL) is a process of training an AI / ML model from input (a.k.a. state) and feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.

[0090] Semi-supervised learning is a process of training model with mix of labelled data and unlabeled data. 202407097

[0091] - 15 -

[0092] Supervised learning is a process of training model from input and its corresponding labels.

[0093] Two-sided (AI / ML) model is a paired AI / ML Model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e, the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

[0094] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0095] Unsupervised learning is a process of training model without labelled data.

[0096] Proprietary-format models is ML models of vendor-Zdevice-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared.

[0097] Open-format models is ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared.

[0098] The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model online training by configuring a set of UE behaviors. AI / ML based techniques are currently applied to many different applications and 3GPP also started to work on its technical investigation to apply to multiple use cases based on the observed potential gains. AI / ML lifecycle can be split into several stages such as data collection / pre- processing, model training, model testing / validation, model deployment / update, model monitoring etc., where each stage is equally important to achieve target performance with any specific model(s). In applying AI / ML model for any use case or application, one of the challenging issues is to manage the lifecycle of AI / ML model. 202407097

[0099] - 16 -

[0100] It is mainly because the data / model drift occurs during model deployment / inference and it results in performance degradation of AI / ML model. Fundamentally, the dataset statistical changes occur after model is deployed and model inference capability is also impacted with unseen data as input. In a similar aspect, the statistical property of dataset and the relationship between input and output for the trained model can be changed with drift occurrence.

[0101] In this context, model training or re-training is one of key issues for model performance maintenance as model performance such as inferencing and / or training is dependent on different model execution environment with varying configuration parameters. To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments. AI / ML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift and update feedback is then provided to re-train / update the model or select alternative model. When AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle AI / ML model in activation with reconfiguration for wireless devices under operations such as model training, inference, updating, etc.

[0102] For determining information about model identification (e.g., model ID), frequent model ID assignment / re-assignment processes might occur due to model drift related to model performance variation and / or model applicable condition change. In addition, if all identified models at UE side are to be assessed and monitored, the associated signaling overhead and computing power demand can increase significantly. And UEs often have a list of active / inactive ML models, each assigned a unique identifier. And the network and UEs may have to take frequent signaling exchanges to determine the related configuration. This can lead to increased signaling overhead and reduced radio resource efficiency. For example, more than one ML models are in active between gNB and UE where multiple UEs have their own on-device models in operation. In addition, each model might be in different LCM phases such as data collection, training, inferencing or monitoring, resulting in 202407097

[0103] - 17 - high signaling overhead for model-related resource transfers (e.g., datasets, model parameters, architectures, hyperparameters).

[0104] It is necessary to investigate an efficient mechanism to help reduce the overall signaling overhead along with resource efficiency improvement. In this method, two types of ML models are classified such as Type-1 (as dedicated model to be used exclusively for a single connection link between a base station and a specific UE device or through sidelink) and Type-2 (as non-dedicated model to be used across multiple connection links for different UEs, possibly across different base stations, for similar tasks or applications (e.g., CSI prediction, beamforming inferencing)). The example use case for Type-1 model is that high-mobility UE requiring a beamforming for optimal signal strength activates Type-1 based beamforming model when moving rapidly across different coverage areas. On the other hand, the example use case for Type-2 model is that a group of UEs in a specific area for general mobility predictions (e.g., effective for the common characteristics of the group) activates Type-2 based model that is same for UE group. Mapping relation information is configured between the model IDs and the two types of models.

[0105] For Type-1 model, model ID is dynamically generated and allocated for each unique connection and the model ID is released after the link is terminated.

[0106] For Type-2 model, model ID is shared across multiple connections and can be reused for other UEs. In addition, priority levels to manage model access for multiple connections are jointly applied if applicable. To reduce the signaling overhead when applying models, the model ID is signaled which points to the pre-configured model and its associated parameters (instead of transmitting full model configurations repeatedly). For Type-1 model signaling, the model ID for the dedicated model is sent to UE by network when initiating the connection with a specific UE. Since the model is unique to that connection, the mapping relation about model IDs and model types allows easy adaptation of the model based on real-time connection parameters (e.g., signal quality, mobility). Model adaptation instructions can be sent by simply referencing the model ID and updating parameters dynamically such as switching between Type-1 and Type-2 models. 202407097

[0107] - 18 -

[0108] For Type-2 model signaling, the model ID for the non-dedicated model is broadcast by network to the UEs in the area when multiple UEs need to use the same nondedicated model. UEs subscribe to the model by referencing its model ID associated with Type-2 identifier without requiring new model delivery. The signaling overhead is minimized by broadcasting shared models to all UEs, and UEs use this model ID for their connection without requesting individual models using Type-1 / Type-2 identifier. For both types of models, dynamic adaptation is supported by updating the model's performance based on feedback from the UE. Mapping relation information (e.g., look-up table) that relates model IDs to their associated types and associated entities is configured. For example, model configuration is set and model IDs are assigned for both dedicated and non-dedicated models along with their mapping relations. For a dedicated model of Type-1 , the gNB signals the specific model ID to the UE when establishing the connection. For a non-dedicated model of Type-2, the gNB broadcasts the model ID for the shared model to all UEs in the region. The network dynamically updates the model parameters based on UE feedback, referencing the model ID to avoid signaling overhead. The mapping relation between model IDs and their respective types can be dynamically adjusted based on real-time network conditions and usage patterns. For instance, if a dedicated model is frequently underutilized, its identifier can be reassigned to a non-dedicated model to optimize resource allocation. When a model is identified as underperforming or redundant, it can be flagged for reassignment or deactivation, thus reducing the signaling required to maintain active connections. For non-dedicated models, the identifiers can be linked to multiple entities (e.g., UE devices and base stations) through a shared identifier pool. This pool can facilitate quick reassignment of model identifiers based on current demand, ensuring that resources are allocated efficiently across the network. Structural formats of ML identifiers containing the pre-configured ID information are preset and full / sub-set of those formats are provided to UE devices via system information or dedicated RRC signaling. Type ID indicates either Type-1 or Type-2 for dedicated model and non-dedicated model, respectively, and model ID indicates a unique sequence number to represent each ML model. Device / Group ID indicates UE-specific identifier or groupwise identifier to represent a single UE device 202407097

[0109] - 19 - or multiple UE devices where Group ID represents a cluster of UEs and BSs using the indicated same model.

[0110] Priority ID indicates a specific level or prioritization to support a specific ML identifier format with the associated model information for ML operation. Switch between Type-1 and Type-2 is applicable based on any given certain criteria such as usage patterns and performance. Network resources are dynamically allocated based on the distribution of Type-1 and Type-2 models.

[0111] 6G is being prepared in 3GPP with Release 20 studies and Release 21 normative work, with AI / ML identified as a core IMT-2030 scenario. Unlike 5G, where Al is often an add-on, Al-native RAN assumes AI / ML is embedded across layers with standardized control and lifecycle. The disclosed Type-1 / Type-2 model framework provides Day-1 life-cycle control for 6G AI / ML models via RRC / NG-RAN procedures, enabling testable, multi-vendor behavior. Therefore, the invention forms a baseline mechanism to activate, switch, and fallback 6G AI / ML models consistently across devices and vendors.

[0112] In alignment with 3GPP Releasel 8 / 19 studies on AI / ML for NR and NG-RAN, the invention introduces a signaling-efficient mechanism for identifying and managing AI / ML models across UE and network entities. Each model is associated with a structured ML-identifier comprising at least a type identifier (indicating Type-1 dedicated or Type-2 shared), a model identifier (unique within scope), and optional fields. For Type-2 models, the network broadcasts a catalog of ML-identifiers via SIB, enabling multiple UEs to subscribe without per-UE model delivery. For Type-1 models, the network signals activation through RRC message (e.g., RRCReconfiguration) and supports fast switching or fallback using MAC CE. Inter-node propagation of ML-identifiers and performance feedback occurs over NG-RAN interfaces (F1 , Xn, E1 ), ensuring coordinated reuse and dynamic adaptation. Switching between Type-1 and Type-2 is executed by KPI-driven triggers with hysteresis and minimum dwell timers, reducing signaling overhead while maintaining performance. This identifier-based lifecycle control is Al-native by design, 202407097

[0113] - 20 - providing a baseline for 6G RAN where AI / ML functions are embedded across protocol layers. By standardizing identifier semantics, signaling containers, and lifecycle procedures, the invention enables multi-vendor interoperability, large-scale model reuse, and integration with system-level analytics (e.g., NWDAF).

[0114] Figure 1 shows an exemplary ML identifier structural formats. In this example, structural formats of ML identifiers containing the pre-configured ID information are preset and full / sub-set of those formats are provided to UE devices via system information or dedicated RRC signaling. Type ID indicates either Type-1 or Type-2 for dedicated model and non-dedicated model, respectively. Model ID indicates a unique sequence number to represent each ML model. Device / Group ID indicates UE-specific identifier or groupwise identifier to represent a single UE device or multiple UE devices where Group ID represents a cluster of UEs and BSs using the indicated same model. Priority ID indicates a specific level or prioritization to support a specific ML identifier format with the associated model information for ML operation. Switch between Type-1 and Type-2 is applicable based on any given certain criteria such as usage patterns and performance. Network resources are dynamically allocated based on the distribution of Type-1 and Type-2 models.

[0115] Figure 2 shows an exemplary flow chart of configuring ML identifier formats at network side. In this example, at network side two types of ML models are classified (e.g., Type-1 / 2) and mapping relation information about model IDs and model types is generated so that the associated ML identifier formats are configured for one or more target UEs. Mapping relation information about model IDs and model types with the associated ML identifier format information are provided to UEs via system information or dedicated RRC signaling. Any updates about the configured mapping relation information about model IDs and model types with the associated ML identifier format information are sent to UEs via L1 / L2 or RRC signaling if applicable.

[0116] Figure 3 shows an exemplary flow chart of switching model types at UE side. In this example, based on the configured information about mapping relation between model IDs and model types with the associated ML identifier format information, UE- side model is activated and also triggered to switch between different model types 202407097

[0117] - 21 - and / or ML identifier formats along with the associated parameter IDs. Triggering criteria is implementation-specific, and model type can be converted according to model usage or other associated ID changes. Switching decision about different model types and / or ML identifier formats is based on the indication message (e.g., L1 / L2 signaling) sent by network side or UE autonomous decision if applicable. Figure 4 shows an exemplary flow chart of updating ML ID information after model type switching. In this example, the conversion between Type-1 and Type-2 (e.g., based on usage patterns and performance) is applicable. The performance of models is monitored to identify any underutilized dedicated / non-dedicated models so that model type can be converted from Type-1 to Type-2 or vice versa with / without the associated ID re-use or update.

[0118] For example, if a dedicated model (Type-1 ) is frequently underutilized, its identifier can be reassigned to a non-dedicated model to optimize resource allocation. When a model is identified as underperforming or redundant, it can be flagged for reassignment or deactivation, thus reducing the signaling required to maintain active connections. Therefore, model identification process can be simpler as well. Based on the proposed method, signaling overhead in model identification process (e.g., by using shared model identifiers for non-dedicated models) can be reduced and resource allocation efficiency by supporting two types of models can be also improved.

Claims

202407097- 22 -CLAIMS1 . A method of model identification type configuration in a wireless communication system by configuring two types of ML models, comprising:• Classifying ML models into Type-1 and Type-2;• Setting mapping relation between model IDs and the classified model types;• Applying dynamic adaptation of models between Type-1 and Type-2;• Configuring multiple ML identifier structural formats.

2. The method according to previous claim 1 , wherein Type-1 model is a dedicated model to be used exclusively for a single connection link between a base station and a specific UE device or through sidelink).

3. The method according to previous claim 1 , wherein Type-2 is a non-dedicated model to be used across multiple connection links for different UEs, possibly across different base stations, for similar tasks or applications (e.g., CSI prediction, beamforming inferencing).

4. The method according to one of the previous claims, wherein mapping relation information is configured between the model IDs and the two types of models.

5. The method according to one of the previous claims, wherein Type-1 based model ID is dynamically generated and allocated for each unique connection.

6. The method according to one of the previous claims, wherein Type-2 based model ID is shared across multiple connections for reuse among multiple UEs.

7. The method according to one of the previous claims, wherein priority levels to manage model access for multiple connections are jointly applied with Type-1 and Type-2.202407097- 23 -8. The method according to one of the previous claims, wherein UEs subscribe to the model by referencing its model ID associated with Type-2 ID without requiring new model delivery.

9. The method according to one of the previous claims, wherein dynamic adaptation between Type-1 and Type-2 is supported by updating the model's performance based on feedback from the UE.

10. The method according to one of the previous claims, wherein the signaling overhead is minimized by broadcasting shared models to all UEs, and UEs use this model ID for their connection without requesting individual models using the combined Type-2 ID.11 . The method according to one of the previous claims, wherein model ID used for dedicated model is reassigned to a non-dedicated model to optimize resource allocation.

12. The method according to one of the previous claims, wherein model IDs used for non-dedicated models can be linked to multiple entities (e.g., UE devices and base stations) through a shared identifier pool.

13. The method according to one of the previous claims, wherein structural formats of ML identifiers containing the pre-configured ID information are preset and full / sub- set of those formats are provided to UE devices via system information or dedicated RRC signaling.

14. The method according to one of the previous claims, wherein Type ID indicates either Type-1 or Type-2 for dedicated model and non-dedicated model, respectively.

15. The method according to one of the previous claims, wherein priority ID indicates a specific level or prioritization to support a specific ML identifier format with the associated model information for ML operation.202407097- 24 -16. The method according to one of the previous claims, wherein switching between Type-1 and Type-2 is applicable based on any given certain criteria such as usage patterns and performance.

17. The method according to one of the previous claims, wherein network resources are dynamically allocated based on the distribution of Type-1 and Type-2 models.

18. The method according to any of the previous claims, wherein one or more on- device ML models can be pre-activated as candidate model status for model switching depending on the indicated specific combination(s) of model identification types.

19. Apparatus for method of model identification type configuration in a wireless communication system by configuring two types of ML models, comprising, the apparatus comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 18.

20. User Equipment comprising an apparatus according to claim 19.

21. gNB comprising an apparatus according to claim 19.

22. Wireless communication system for model identification type configuration in a by configuring two types of ML models, wherein the wireless communication systems comprises user equipment according to claim 20, gNB according to claim 21 , whereby the user equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 18.

Images