Method and system of advanced model identification with model-dependent parameters
Patent Information
- Application Number
- PCT/EP2026/052327
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-02-20
- Filing Date
- 2026-01-29
- Publication Date
- 2026-08-27
Smart Images
Figure EP2026052327_27082026_PF_FP_ABST
Abstract
Description
[0001] 202501057
[0002] - 1 -
[0003] TITLE
[0004] Method and system of advanced model identification with model-dependent parameters
[0005] TECHNICAL FIELD
[0006] The present invention disclosure relates to the field of wireless communication networks and artificial intelligence / machine learning (AI / ML) model identification. More specifically, it concerns adaptive model verification and identification mechanisms using intrinsic model characteristics to enhance model compatibility, security, and efficiency in networked environments such as 5G and beyond.
[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.
[0009] 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 onesided (AI / ML) model, UE-side (AI / ML) model is defined as an AI / ML model whose202501057
[0010] -2 -
[0011] 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.
[0012] Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection 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.
[0013] Followingly, in Release 18 the new work item of “Artificial Intelligence (AI)ZMachine 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 network-side and UE-side models for various lifecycle management (LCM) operations.
[0014] 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.
[0015] WO2024110160A1 describes a request reception for a machine learning model, wherein the request comprises information on model adaptation constraint for training of the machine learning model or an inference of the machine learning model with response to the access node being able to adapt the machine learning model using model adaptation constraint.202501057
[0016] - 3 -
[0017] WO2023211572A1 describes a method of implementing AI / ML for air interface optimization determining a collaboration level for AI / ML collaboration between a network and a device from among a plurality of predetermined collaboration levels.
[0018] US2021344469A1 shows that the machine learning model is implemented in the UE and the UE estimates one or more features of the second band based on measurements it performs on the reference signal transmitted from the dedicated transmitter in the first band.
[0019] US2022149980A1 shows the methods for dynamically selecting a link adaptation policy, where the method includes using channel quality information, additional information, and the ML model to select a link adaptation policy from a set of predefined link adaptation policies.
[0020] US2022150727A1 shows techniques for sharing machine learning models and an indication of transmission and reception points (TRPs) for which the machine learning models are applicable between wireless nodes such as UEs and BSs.
[0021] US2023153408A1 shows the method includes the steps of creating, using a machine learning model being trained and calculating, and updating parameters of the machine learning model based on the calculated loss.
[0022] This application proposes a novel unified model identification framework to ensure efficient model deployment, transfer, and management according to the claims 1 to 16 with their different embodiments. The existing 3GPP framework does not support a conditional, pre-configured AI / ML model switching mechanism, which can dynamically adapt to radio conditions, computational resources, and inference quality. Traditional model identification methods in wireless communication rely on explicit model versioning and dataset-based tracking, leading to high signaling costs, security concerns, and limited flexibility. Existing approaches, such as direct model transfer, often necessitate full model exchange or reference-based identification, restricting adaptability to network conditions.202501057
[0023] -4 -
[0024] According to an aspect, the present disclosure relates to a computer program product comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to the first aspect said at least one processor to carry out a method for exchanging data according to any one of the embodiments of the present disclosure. The computer program product can use any programming language, and can be in the form of source code, object code, or in any intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.
[0025] According to an aspect, the present disclosure relates to a computer-readable storage medium comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to any one of the embodiments of the present disclosure.
[0026] SUMMARY OF THE INVENTION
[0027] The invention disclosure provides a method for model identification using a hierarchical structure of model characteristic feature representations by extracting characteristic features of AI / ML model and generating a model identifier (model ID) with the overall model features in association with the assigned sub-identifiers (sub-IDs) to different elements of a model.
[0028] BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 is an exemplary flow chart of applying hierarchical AI / ML model identification process.
[0030] Figure 2 is an exemplary hierarchical model identification structure.
[0031] Figure 3 is an exemplary signaling flow of model matching procedure.
[0032] Figure 4 is an exemplary signaling flow of model activation.
[0033] DETAILED DESCRIPTION
[0034] The detailed description set forth below, with reference to annexed drawings, is intended as a description of various configurations and is not intended to represent202501057
[0035] - 5 -
[0036] 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.
[0037] 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.
[0038] 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 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.
[0039] 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 node202501057
[0040] -6 -
[0041] 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.
[0042] 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.
[0043] 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.
[0044] 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.202501057
[0045] -7 -
[0046] 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.
[0047] 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
[0048] 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 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.
[0049] 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.202501057
[0050] - 8 -
[0051] 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”)).
[0052] 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 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 of202501057
[0053] - 9 -
[0054] 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.
[0055] 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
[0056] 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 manufacture including instructions which implement the function / act specified in the flowchart diagrams and / or block diagrams.
[0057] 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.
[0058] 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 a202501057
[0059] - 10 -
[0060] module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s).
[0061] 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.
[0062] 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 systems that perform the specified functions or acts, or combinations of special purpose hardware and code.
[0063] 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.
[0064] 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 this202501057
[0065] - 11 -
[0066] disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the present disclosure.
[0067] 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.
[0068] 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.
[0069] The UEs are located in a coverage of the BS. The coverage of the BS corresponds for example to the area in which UEs can decode a PDCCH transmitted by the BS.
[0070] 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.202501057
[0071] - 12 -
[0072] 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.
[0073] 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.
[0074] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.
[0075] 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.
[0076] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.
[0077] 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.202501057
[0078] - 13 -
[0079] 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.
[0080] 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.
[0081] 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.
[0082] 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.
[0083] 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.
[0084] 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.
[0085] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.
[0086] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.
[0087] Model download means Model transfer from the network to UE.202501057
[0088] - 14 -
[0089] 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.
[0090] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.
[0091] 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.
[0092] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.
[0093] Model update is Process of updating the model parameters and / or model structure of model.
[0094] Model upload is Model transfer from UE to the network.
[0095] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.
[0096] Offline field data is the data collected from field and used for offline training of the AI / ML model.
[0097] 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.202501057
[0098] - 15 -
[0099] Online field data is the data collected from field and used for online training of the AI / ML model.
[0100] 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.
[0101] 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.
[0102] 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.
[0103] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.
[0104] Supervised learning is a process of training model from input and its corresponding labels.
[0105] 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.
[0106] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.202501057
[0107] - 16 -
[0108] Unsupervised learning is a process of training model without labelled data.
[0109] 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.
[0110] 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.
[0111] 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).
[0112] 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. It is mainly because the data / model drift occurs during model deployment and 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. 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.202501057
[0113] - 17 -
[0114] 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 re-configuration for wireless devices under operations such as model training, inference, updating, etc. 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 signaling overhead can highly increase for model ID decision and assignment. When there are multiple models for model transfer / delivery, significant increase of signaling overhead and the limited UE capability supporting models to be transferred can be critical for the deployment of target models at UE side. In this method, a set of unique model identifiers using intrinsic model characteristics (e.g., model architecture / structure type, layer information, activation function, hyperparameters, loss function, model parameters, input dataset information, performance metric, input feature priority, etc.) are pre-configured for different model applications and functionalities with the associated models.
[0115] A hierarchical model identification structure is configured to consist of source model ID and multiple characteristic element-based sub-IDs, where a source model ID is uniquely identified to represent a full set of model characteristic elements and model sub-IDs (e.g., granular-level identification) are uniquely identified to represent the granular breakdown of model characteristic elements. For example, model sub-IDs are indicated as Sub-ID-1 for model architecture, Sub-ID-2 for layer information, Sub-ID-3 for model parameter set, and Sub-ID-4 for input datatset information. The number of model sub-IDs is configured by network side along with source model ID for assignment of model characteristic elements to each sub-ID.202501057
[0116] - 18 -
[0117] To support the hierarchical model identification structure, RRC Setup and RRC Reconfiguration Messages are used to support characteristic element-based model identifiers. For model matching procedure between UE and network entity, UE firstly extracts the necessary model characteristic elements and transmits model characteristic element-based sub-ID information via RRC signaling. Model compatibility is checked at network side for model matching based on the received sub-IDs. If match is confirmed, model is activated at UE after receiving confirmation message about model matching. If a model is partially matched, a targeted model update (only mismatched sub-IDs) is sent to UE. If a no match occurs, a recommended model update (e.g., based on the indicated sub-ID information) or alternative model is sent. Regarding RRC message for modification, UECapabilityEnquiry message (sent by gNB to UE) is modified so that the gNB queries the UE for supported AI / ML models using model characteristic elementbased identification. Specifically, a request field for model characteristic elementbased identification is added to specify whether the gNB requests source model ID or specific sub-IDs. For UE response with model characteristic element-based identification, UECapabilitylnformation message (sent by UE to gNB) is modified to add fields such as ModelElementID to represent a source model identifier, SubModellDList to represent list of hierarchical model sub-IDs, and ModelVerto encode versioning information for compatibility checks.
[0118] For signaling of model selection, compatibility, and updates, RRCReconfiguration message (sent by gNB to UE) is also modified to add ModelCompatFlag to indicate the level of model compatibility, and ModelUpdateReq to trigger a partial update of non-matching sub-IDs for targeted model updates. If model mismatch is detected, partial updates (instead of full model transfer) is performed via MismatchedSublDs to identify the specific parts of model characteristic elements for updating. For latencysensitive AI / ML model applications (e.g., beam prediction), a fast model verification is executed via L1 (layer 1) or L2 (layer 2) signaling. For example, MAC CE is used for lightweight model verification without RRC overhead by sending indication of sub-ID matching degree (e.g., fully matched, not matched, or partially matched). As another example, any specific sub-ID based model characteristic element(s) can be202501057
[0119] - 19 -
[0120] exchanged between UE and gNB via L1 signaling for dynamic model update in association with the indicated sub-ID(s).
[0121] Figure 1 shows an exemplary flow chart of applying hierarchical AI / ML model identification process between UE and network side. In this example, the overall framework of hierarchical model identification in wireless networks is illustrated.
[0122] For model matching procedure between UE and network entity, UE firstly extracts the necessary model characteristic elements and transmits model characteristic elementbased sub-ID information via RRC signaling. Model compatibility is checked at network side for model matching based on the received sub-IDs. If match is confirmed, model is activated at UE after receiving confirmation message about model matching. If a model is partially matched, a targeted model update (only mismatched sub-IDs) is sent to UE. If a no match occurs, a recommended model update (e.g., based on the indicated sub-ID information) or alternative model is sent.
[0123] Figure 2 shows an exemplary hierarchical model identification structure. In this example, a hierarchical structure for AI / ML model identification consists of a source model ID and multiple model sub-IDs that represent granular model characteristics. The network assigns these IDs to uniquely identify and manage models efficiently. Source model ID (ModelElementID) is a unique identifier representing the overall AI / ML model as pre-configured for different AI / ML applications and functionalities. For hierarchical model sub-IDs (SubModellDList), each sub-ID represents a distinct model characteristic element. As an example breakdown of this figure, Sub-ID-1 to Sub-ID-6 is assigned to identify different model characteristic elements. The network dynamically assigns and configures model sub-IDs and only mismatched sub-IDs are updated to minimize overhead. For AI / ML model matching and updates, the UE sends sub-IDs to the network for model verification and the network confirms full match, partial match, or mismatch. In this figure, if only Sub-ID-2 differs, then only the layer configuration is updated. If only Sub-ID-6 differs, then only the performance metric is updated, which reduces unnecessary full model replacements.202501057
[0124] - 20 -
[0125] Figure 3 shows an exemplary signaling flow of model matching procedure. In this example, gNB requests a specific model characteristic elements with the associated sub-IDs (e.g., via UECapabilityEnquiry). UE responds with sub-model IDs (e.g., via UECapabilitylnformation). gNB processes the received UECapabilitylnformation. Figure 4 shows an exemplary signaling flow of model activation. In this example, RRCReconfiguration message (sent by gNB to UE) is also modified to add ModelCompatFlag to indicate the level of model compatibility, and ModelUpdateReq to trigger a partial update of non-matching sub-IDs for targeted model updates. If model mismatch is detected, partial updates (instead of full model transfer) is performed via MismatchedSublDs to identify the specific parts of model characteristic elements for updating. UE confirms receipt of updated parameters and activates the ML model after targeted model updates is sent to the UE (e.g., specifying which model sub-components require updating). Once the model is active, it is used for Al-driven network tasks with the activated model operation (e.g., CSI feedback, beam selection).
[0126] Figure 4 shows an exemplary signaling flow of model activation.
Claims
202501057- 21 -CLAIMS1. A method for hierarchical AI / ML model identification model identification with model-dependent parameters in a wireless communication system, comprising:• Configuring a hierarchical model identification structure with a source model ID and multiple characteristic element-based model sub-IDs;• Transmitting a model characteristic element-based sub-ID list from a UE to a network entity, using RRC signaling, to indicate supported model configurations; and• Determining model compatibility at the network entity based on the received sub-IDs and classifying model compatibility.
2. The method of claim 1 , wherein a source model ID uniquely represents an AI / ML model.
3. The method according to one of the previous claims, wherein multiple characteristic element-based model sub-IDs represent granular-level model characteristics extracted from a source model having the necessary model characteristic elements.
4. The method according to one of the previous claims, wherein granular-level model characteristics include (but not limited to) model architecture, layer configuration, activation functions, hyperparameters, loss functions, model parameters, dataset information, performance metrics, and input feature prioritization.
5. The method according to one of the previous claims, wherein model compatibility classification comprises:• Full match (e.g., the UE model matches a stored model in the network);• Partial match (e.g., some sub-IDs mismatch, requiring targeted updates);and• No match (e.g., the model must be replaced or newly deployed).
6. The method according to one of the previous claims, wherein targeted model update is performed by transmitting only the mismatched sub-IDs and corresponding updates instead of full model replacement.
7. A method for signaling AI / ML model compatibility using RRC messages,comprising:202501057- 22 -• Modifying an UECapabilityEnquiry message (sent by a gNB to a UE) to include a request for model characteristic element-based sub-IDs;• Modifying an UECapabilitylnformation message (sent by a UE to a gNB) to include ModelElementID (a source model identifier), SubModellDList (list of hierarchical model sub-IDs), and ModelVer (encoding of model versioning information);• Modifying an RRCReconfiguration message (sent by a gNB to a UE) to include ModelCompatFlag (indicator of model compatibility) and ModelUpdateReq (request for partial model update in case of mismatched sub-IDs); and• Transmitting targeted model updates to the UE, using the MismatchedSublDs field to specify which model sub-components require updating.
8. A method for fast model verification in AI / ML applications using L1 / L2 signaling, comprising:• Using MAC CE for lightweight model verification by indicating sub-ID matching status and providing model sub-ID updates; and• Transmitting specific sub-ID based model characteristic elements between the UE and the gNB via L1 signaling to enable dynamic model updates.
9. The method according to one of the previous claims, wherein the source model ID and sub-IDs are pre-configured based on model applications, functionalities, and network deployment scenarios.
10. The method according to one of the previous claims, wherein the number of model sub-IDs is dynamically configured by the network side based on AI / ML model optimization.11.The method according to one of the previous claims, wherein the UE stores a preconfigured mapping table between source model ID and characteristic-based sub-IDs for efficient model identification.
12. The method according to one of the previous claims, wherein the RRCReconfiguration message further includes a new field to recommend an alternative compatible model in case of mismatch.202501057- 23 -13. Apparatus for model identification with model-dependent parameters in a communication network, 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 12.
14. User Equipment comprising an apparatus according to claim 13.
15. gNB comprising an apparatus according to claim 13.
16. Wireless communication system for, wherein the wireless communication systems comprises user equipment according to claim 14, gNB according to claim 15, 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 12.