Method of multi-resolution model identification signaling

Abstract

The present disclosure describes methods for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication system by using the pre-configured AI / ML (artificial intelligence / machine learning) based multiple subsets of models in wireless mobile communication system including base station e.g., gNB, 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 assessment / monitoring of all identified models at UE side. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be set up between network and UE by using multi-resolution model identification signaling for ML operation.

Description

[0001] 202405143

[0002] 1

[0003] Description

[0004] Method of multi-resolution model identification signaling

[0005] TECHNICAL FIELD

[0006] The present disclosure relates to AI / ML based model operation with multi-resolution model identification signaling, where techniques for pre-configuring and signaling the specific information about multiple subsets of models 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.

[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 202405143

[0010] 2 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 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 (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.

[0011] 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.

[0012] US 2022400373 describes the method of determining neural network functions and configuring models for performing wireless communications management procedures.

[0013] US 2022108214 explains ML model management method for network data analytics function device, and US 2022337487 shows that a network entity 202405143

[0014] 3 determines at least one model parameter of a model for digitally analyzing input data depending on the at least one model parameter of a model, the network entity being configured to receive a model request.

[0015] WO 2023277780 contains a method of downloading of a compiled machine code version of a ML model to a wireless communication device.

[0016] WO 2022258149 provides a way for training a model in a server device based on training data in a user device, and WO 2022228666 shows about influencing training of a ML model based on a training policy provided by an actor node.

[0017] WO 2022161624 describes the method of receiving a request for retrieving or executing a ML model or a combination of ML models.

[0018] The present disclosure solves the cited problem above by the proposed embodiments and describes methods for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication system by using the pre-configured AI / ML (artificial intelligence / machine learning) based multiple subsets of models in wireless mobile communication system including base station e.g., gNB, 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 assessment / monitoring of all identified models at UE side. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be set up between network and UE by using multi-resolution model identification signaling for ML operation.

[0019] In the first embodiment , the method for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication systems is characterized by comprising the steps, configuring each subsets have different number of models or model IDs; quantizing the variation range of applicable conditions with multiple levels; setting criteria of selecting a subset of models and / or model of a specific subset; selecting a specific subset of models and / or model of a specific subset adaptively. 202405143

[0020] 4

[0021] In some embodiments of the method according to the first aspect is characterized by, that the overall subsets of models are represented as the list of multi-resolution model identification set.

[0022] In some embodiments of the method according to the first aspect is characterized by, that the variation range of applicable conditions is quantized with multiple levels as applicable conditions to guarantee target model performance with a specific model ID vary.

[0023] In some embodiments of the method according to the first aspect is characterized by, that the associated threshold values for the quantized variation range of applicable conditions are set with the configured parameters so that a specific subset of models and / or model of a specific subset is adaptively selected for variation adaptation to active model performance change and / or operation condition change.

[0024] In some embodiments of the method according to the first aspect is characterized by, that criteria of selecting a subset of models and / or model of a specific subset is based on the configured parameters such as model complexity levels, dataset size / distribution, dynamic / static ML features, environmental conditions (e.g., site), device ML conditions (e.g., available computing power) or any combination of those parameters.

[0025] In some embodiments of the method according to the first aspect is characterized by, that a specific subset of models for a given multi-resolution model identification set with the associated subsets of models is adaptively applied to perform service continuity with activation of a specific model where other models in subset are candidate models as inactive.

[0026] In some embodiments of the method according to the first aspect is characterized by, that adaptive selection of a specific subset of models and / or model of a specific 202405143

[0027] 5 subset is executed based on network side decision or on UE side autonomous decision.

[0028] In some embodiments of the method according to the first aspect is characterized by, that the indication message of adaptive selection of a specific subset of models and / or model of a specific subset is sent via L1 / L2 or RRC signaling.

[0029] In some embodiments of the method according to the first aspect is characterized by, that the number of models in a subset increases as variation range of the configured parameters with the associated applicable conditions gets larger.

[0030] In some embodiments of the method according to the first aspect is characterized by, that multi-resolution model identification set information is sent as part of system information or dedicated RRC message or L1 / L2 signaling.

[0031] In some embodiments of the method according to the first aspect is characterized by, that a subset of the available model IDs is selected and applied to UE either (semi-)statically with RRC re-configuration or dynamically with L1 or L2 message (e.g., PDCCH or MAC CE).

[0032] In some embodiments of the method according to the first aspect is characterized by, that a specific Information Element (IE) within the RRC message for messaging of multi-resolution model identification set is used to convey both a subset of the available model IDs and the associated parameter information (e.g., MultiResModellDSet RRC IE carrying subset IDs and the associated model IDs).

[0033] In some embodiments of the method according to the first aspect is characterized by, that multi-resolution model identification set is indexed as table with multiple subsets of model IDs.

[0034] In some embodiments of the method according to the first aspect is characterized by, that varying numbers of model IDs for each subsets are configured to have 202405143

[0035] 6 different subsets of model IDs with varying numbers of model IDs in the associated subset.

[0036] In some embodiments of the method according to the first aspect is characterized by, that a specific size of the indexed subsets of multi-resolution model identification set and the associated model IDs is determined depending on deployment scenarios and / or ML model applications / functionalities.

[0037] According to a second aspect, the present disclosure relates to an apparatus for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication system, 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 according to the first aspect.

[0038] According to a third aspect, the present disclosure relates to an user equipment comprising an apparatus according to a second aspect.

[0039] According to a third aspect, the present disclosure relates to a gNB comprising an apparatus according to a second aspect.

[0040] Wireless communication system for methods for multi-resolution model identification signaling by configuring multiple subsets consisting of models, wherein the wireless communication systems comprises user equipment according to the third aspect, gNB according the fourth aspect, 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 according to the first aspect. 202405143

[0041] 7

[0042] BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an exemplary table of multi-resolution model ID set.

[0044] Figure 2 is an exemplary flow chart of configuring multi-resolution model identification set at network side.

[0045] Figure 3 is an exemplary flow chart of applying multi-resolution model identification set at UE side.

[0046] Figure 4 is an exemplary signaling flow of determining multi-resolution model identification subset at network side.

[0047] Figure 5 is an exemplary signaling flow of determining multi-resolution model identification subset at network side.

[0048] Figure 6 is an exemplary flow chart of adapting multi-resolution model identification set.

[0049] DETAILED DESCRIPTION

[0050] 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 202405143

[0051] 8 disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the invention.

[0052] 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.

[0053] 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.

[0054] 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 202405143

[0055] 9

[0056] (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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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, 202405143

[0061] 10 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.

[0062] 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

[0063] 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.

[0064] 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.

[0065] 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 202405143

[0066] 11

[0067] “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”)).

[0068] 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 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. 202405143

[0069] 12

[0070] 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 fimctions / acts specified in the flowchart diagrams and / or block diagrams

[0071] 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.

[0072] 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.

[0073] 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). 202405143

[0074] 13

[0075] 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.

[0076] 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.

[0077] 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.

[0078] [1]

[0079] [2] 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.

[0080] [3] 202405143

[0081] 14

[0082] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

[0083] 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.

[0084] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0085] 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.

[0086] 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.

[0087] AI / ML model transfer is a delivery of an AI / ML model over the air interface in manner that is not transparent to 3GPP signalling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model.

[0088] 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.

[0089] 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. 202405143

[0090] 15

[0091] 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.

[0092] 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.

[0093] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0094] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0095] Model download means Model transfer from the network to UE.

[0096] 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.

[0097] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.

[0098] 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.

[0099] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature. 202405143

[0100] 16

[0101] Model update is process of updating the model parameters and / or model structure of model.

[0102] Model upload is Model transfer from UE to the network.

[0103] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0104] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0105] 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.

[0106] Online field data is the data collected from field and used for online training of the AI / ML model.

[0107] 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.

[0108] 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. 202405143

[0109] 17

[0110] 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.

[0111] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0112] Supervised learning is a process of training model from input and its corresponding labels.

[0113] 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.

[0114] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0115] Unsupervised learning is a process of training model without labelled data.

[0116] 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.

[0117] 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.

[0118] [4]

[0119] [5] 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 202405143

[0120] 18 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.

[0121] [6]

[0122] [7] 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.

[0123] [8]

[0124] [9] 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.

[0125]

[0010]

[0126]

[0011] 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.

[0127]

[0012]

[0128]

[0013] 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, 202405143

[0129] 19 etc.). The one or more memories may store a computer program product, in the form of a set of program-code 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.

[0130]

[0014]

[0131]

[0015] 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.

[0132] 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. It is mainly because the data / model drift occurs during model deployment / inference and it results in performance degradation of AI / ML model.

[0133] 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. To handle this issue, collaboration between UE and gNB is highly 202405143

[0134] 20 important to track model performance and re-configure model corresponding to different environments.

[0135] 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. Therefore, signaling overhead can highly increase for model ID decision and assignment. In this method, multiple subsets consisting of models (e.g., in the form of model IDs) are set where each subsets have different number of models or model IDs.

[0136] The overall subsets of models are represented as the list of multi-resolution model identification set. For example, M = {Mi , M2, ... , MR} where Mr(r= 1 , 2, ... , R) represents a subset of models or model IDs within the list of multi-resolution model identification set. Applicable conditions to guarantee target model performance with a specific model ID can vary and the variation range of applicable conditions is quantized with multiple levels so that the associated threshold values are set with the configured parameters so that a specific subset of models and / or model of a specific subset is adaptively selected for variation adaptation to active model performance change and / or operation condition change. Criteria of selecting a subset of models and / or model of a specific subset is based on the configured parameters such as model complexity levels, dataset size / distribution, dynamic / static ML features, environmental conditions (e.g., site), device ML conditions (e.g., available computing power) or any combination of those parameters. 202405143

[0137] 21

[0138] Given multi-resolution model identification set with the associated subsets of models, a specific subset of models is adaptively applied to perform service continuity with activation of a specific model where other models in subset are candidate models as inactive. Adaptive selection of a specific subset of models and / or model of a specific subset is executed based on network side decision or on UE side autonomous decision where the indication message of adaptive selection can be sent via L1 / L2 or RRC signaling. Regarding multi-resolution model identification set with the associated subsets of models, the number of models in a subset increases as variation range of the configured parameters with the associated applicable conditions gets larger.

[0139] For example, when the mentioned variation range is high and dynamically changed, the selected subset of models becomes more granular with higher number of models. On the other hand, when variation range is low and statically changed, the selected subset of models becomes less granular with lower number of models. Therefore, when a subset of models has small number of models or model IDs, it means that inactive models as potential candidacy for activation are fewer than other subset of models with higher number of models or model IDs that might have higher frequent adaptation. Multi-resolution model identification set information can be signaled as part of system information or dedicated RRC message or L1 / L2 signaling. A subset of the available model IDs is selected and applied to UE either (semi-)statically with RRC re-configuration or dynamically with L1 or L2 message (e.g., PDCCH or MAC CE). Regarding messaging of multi-resolution model identification set, a specific Information Element (IE) within the RRC message can be used to convey both a subset of the available model IDs and the associated parameter information. Multi-resolution model identification set can be indexed as table with multiple subsets of model IDs.

[0140] For each subset of model IDs, varying numbers of model IDs are configured where Model_ID_Subset # / is 7th subset of multi-resolution model identification set and MID / (n) is nth model ID in 7th subset. Different subsets of model IDs can have varying numbers of model IDs in the associated subset. Depending on deployment 202405143

[0141] 22 scenarios and / or ML model applications / functionalities, a specific size of the indexed subsets of multi-resolution model identification set and the associated model IDs can be determined. Applicable condition information can be defined as a wide range of parameters related to ML model operation, single-Zmulti-sided model operation and / or LCM phases and the categories of ML condition information is based on any combinations of {dataset_attribute_data, model_attribute_data, LCM_attribute_data, site_attribute_data, device_attribute_data, etc.}.

[0142] In UE mobility use case, the UE experiences varying channel conditions. Based on quantized mobility metrics, a subset of models are selected by network side so that AI / ML model in operation is optimized for high-speed environments, reducing signaling overhead and improving inference accuracy. Beyond UE mobility use case, this multi-resolution model ID approach is applicable to varying scenarios in radio access networks, and the general steps include quantization of applicable conditions into multiple levels, configuration of subsets of model identifiers corresponding to each level, and adaptive selection of a subset based on current operational parameters.

[0143] Figure 1 shows an exemplary table of multi-resolution model ID set. In this example, multi-resolution model identification set can be indexed as table with multiple subsets of model IDs. For each subsets of model IDs, varying numbers of model IDs are configured where Model_ID_Subset # / is 7th subset of multi-resolution model identification set and MIDz(n) is nth model ID in 7th subset. Different subsets of model IDs can have varying numbers of model IDs in the associated subset. Depending on deployment scenarios and / or ML model applications / functionalities, a specific size of the indexed subsets of multi-resolution model identification set and the associated model IDs can be determined.

[0144] Figure 2 shows an exemplary flow chart of configuring multi-resolution model identification set at network side. In this example, model identification resolution for variation adaptation to performance change and / or operation condition change is set as ML configuration information at network side. 202405143

[0145] 23

[0146] Multi-resolution model identification set information can be signaled as part of RRC message or L1 / L2 signaling. A subset of the available model IDs can be applied to UE either (semi-)statically with RRC re-configuration or dynamically with L1 or L2 message (e.g., PDCCH or MAC CE).

[0147] Figure 3 shows an exemplary flow chart of applying multi-resolution model identification set at UE side. In this example, given a set of multi-resolution model identification, a subset of the available model IDs is adaptively applied to perform service continuity with activation of specific model ID(s). Adaptive selection of subset of the available model IDs and / or model ID(s) of a specific subset is executed based on network side decision or on UE side autonomous decision.

[0148] Figure 4 shows an exemplary signaling flow of determining multi-resolution model identification subset at network side. In this example, adaptive selection of subset of the available model IDs and / or model ID(s) of a specific subset is executed based on network side decision. ML configuration with multi-resolution model identification set is performed on network side, where one or more subsets of the available model IDs within multi-resolution model identification set are provided to UE. Based on the configured measurement of ML conditions (e.g., on-device ML model applicability, use of sensory data, UE mobility, site), measurement results are fed back to network side so that a specific subset of multi-resolution model identification and / or the associated model ID(s) can be determined at network side. Indication message (e.g., via L1 / L2 signaling) is sent to UE so as to enable model ID(s) within the indicated subset.

[0149] Figure 5 shows an exemplary signaling flow of determining multi-resolution model identification subset at network side. In this example, adaptive selection of subset of the available model IDs and / or model ID(s) of a specific subset is executed based on UE side autonomous decision. Based on the configured measurement of ML conditions (e.g., on-device ML model applicability, use of sensory data, UE mobility, site), measurement results are directly used to determine subset of the available model IDs and / or model ID(s) of a specific subset at UE side autonomously. 202405143

[0150] 24

[0151] Indication message (e.g., via L1 / L2 signaling) is sent to network side so as to inform the UE autonomous decision for alignment with network side as confirmation.

[0152] Figure 6 shows an exemplary flow chart of adapting multi-resolution model identification set. In this example, given multi-resolution model identification set with the associated subsets of models, a specific subset of models is adaptively applied to perform service continuity with activation of a specific model where other models in subset are candidate models as inactive. Model identification resolution for variation adaptation to performance change and / or operation condition change is set as ML configuration information. Adaptive selection of subset of the available model IDs and / or model ID(s) of a specific subset is executed. Applicable conditions to guarantee target model performance with a specific model ID can vary and the variation range of applicable conditions is quantized with multiple levels so that the associated threshold values are set with the configured parameters so that a specific subset of models and / or model of a specific subset is adaptively selected for variation adaptation to active model performance change and / or operation condition change.

Claims

20240514325Patent claims1 . A method for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication systems, comprising:• Configuring each subsets have different number of models or model IDs;• Quantizing the variation range of applicable conditions with multiple levels;• Setting criteria of selecting a subset of models and / or model of a specific subset;• Selecting a specific subset of models and / or model of a specific subset adaptively.

2. The method according to previous claim 1 , wherein the overall subsets of models are represented as the list of multi-resolution model identification set.

3. The method according to one of the previous claims, wherein the variation range of applicable conditions is quantized with multiple levels as applicable conditions to guarantee target model performance with a specific model ID vary.

4. The method according to one of the previous claims, wherein the associated threshold values for the quantized variation range of applicable conditions are set with the configured parameters so that a specific subset of models and / or model of a specific subset is adaptively selected for variation adaptation to active model performance change and / or operation condition change.

5. The method according to one of the previous claims, wherein criteria of selecting a subset of models and / or model of a specific subset is based on the configured parameters such as model complexity levels, dataset size / distribution, dynamic / static ML features, environmental conditions (e.g., site), device ML conditions (e.g., available computing power) or any combination of those parameters.202405143266. The method according to one of the previous claims, wherein a specific subset of models for a given multi-resolution model identification set with the associated subsets of models is adaptively applied to perform service continuity with activation of a specific model where other models in subset are candidate models as inactive.

7. The method according to one of the previous claims, wherein adaptive selection of a specific subset of models and / or model of a specific subset is executed based on network side decision or on UE side autonomous decision.

8. The method according to one of the previous claims, wherein the indication message of adaptive selection of a specific subset of models and / or model of a specific subset is sent via L1 / L2 or RRC signaling.

9. The method according to one of the previous claims, wherein the number of models in a subset increases as variation range of the configured parameters with the associated applicable conditions gets larger.

10. The method according to one of the previous claims, wherein multi-resolution model identification set information is sent as part of system information or dedicated RRC message or L1 / L2 signaling.11 . The method according to one of the previous claims, wherein a subset of the available model IDs is selected and applied to UE either (semi-)statically with RRC re-configuration or dynamically with L1 or L2 message (e.g., PDCCH or MAC CE).

12. The method according to one of the previous claims, wherein a specific Information Element (IE) within the RRC message for messaging of multi-resolution model identification set is used to convey both a subset of the available model IDs and the associated parameter information.

13. The method according to one of the previous claims, wherein multi-resolution model identification set is indexed as table with multiple subsets of model IDs.2024051432714. The method according to one of the previous claims, wherein varying numbers of model IDs for each subsets are configured to have different subsets of model IDs with varying numbers of model IDs in the associated subset.

15. The method according to one of the previous claims, wherein a specific size of the indexed subsets of multi-resolution model identification set and the associated model IDs is determined depending on deployment scenarios and / or ML model applications / functionalities.

16. Apparatus for multi-resolution model identification signaling by configuring multiple subsets consisting of models in a wireless communication system, 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 15.

17. User Equipment comprising an apparatus according to claim 16.

18. gNB comprising an apparatus according to claim 16.

19. Wireless communication system for methods for multi-resolution model identification signaling by configuring multiple subsets consisting of models, wherein the wireless communication systems comprises user equipment according to claim 17, gNB according to claim 18, 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 15.

Images