Method of data quality measurement based selection

Abstract

The present disclosure describes methods of using sensing data quality level based AI / ML (artificial intelligence / machine learning) model operation 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, model performance can be significantly impacted due to data drift. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be adaptively set up between network and UE by using sensing data quality levels.

Description

[0001] 202406307

[0002] - 1 -

[0003] TITLE

[0004] Method of data quality measurement based selection

[0005] TECHNNICAL FIELD

[0006] The present disclosure relates to AI / ML based model operation with sensing data quality levels, where techniques for pre-configuring and signaling the specific information about sensing data quality level based model operation applicable to radio access network are presented.

[0007] BACKGROUND

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

[0009] Also for one-sided (AI / ML) model, UE-side (AI / ML) model is defined as an AI / ML model whose inference is performed entirely at the UE and network-side (AI / ML) model is defined as an AI / ML model whose inference is performed entirely at the network. Currently, AI / ML specification work is at the stage of work item discussion 202406307

[0010] - 2 - 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 (Al) / Machine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture.

[0011] 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.

[0012] 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.

[0013] US 2017372232A1 and US2021357699A1 describe how to identify one or more data quality issues in machine learning training data.

[0014] US2020374305A1 shows a real-time data quality check for online machine learning system.

[0015] US2021357795A1 shows how to generate the predicted dataset.

[0016] US2022138561 A1 explains about data filter for the refined training data. 202406307

[0017] - 3 -

[0018] US2022277221A1 shows how to generate the expert labels and US2022414464A1 considers federated machine learning for multiple data quality based sources.

[0019] US2023039828A1 also shows data quality control method and US20170244969A1 describes about extraction of feature amount.

[0020] BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is an exemplary table of assignment of sensing data quality level for UE. Figure 2 is an exemplary table of the indexed sensing capability levels.

[0022] Figure 3 is an exemplary flow chart of configuring levels of sensing data quality and / or sensing capability at network side.

[0023] Figure 4 is an exemplary flow chart of detecting sensing data quality level and / or sensing capability level at UE side.

[0024] Figure 5 is an exemplary signaling flow of configuration and measurement for sensing data quality and sensing capability levels.

[0025] Figure 6 is an exemplary block diagram of relationship among sensor modality, sensory dataset category and model feature set.

[0026] DETAILED DESCRIPTION

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

[0028] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are 202406307

[0029] - 4 - 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.

[0030] 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.

[0031] In some embodiments, a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a UE (directly or via another node) and / or with another network node. Examples of network nodes are NodeB, MeNB, ENB, a network node belonging to MCG or SCG, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), access point (AP), transmission points, transmission nodes, RRU, RRH, nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc), Operations & Maintenance (O&M), Operations Support System (OSS), Self Optimized Network (SON), positioning node (e.g. Evolved- Serving Mobile Location Centre (E-SMLC)), Minimization of Drive Tests (MDT), test equipment (physical node or software), etc. 202406307

[0032] - 5 -

[0033] 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.

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

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

[0036] For example, the disclosed embodiments may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off- the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function. 202406307

[0037] - 6 -

[0038] 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

[0039] 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.

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

[0041] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object- oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer 202406307

[0042] - 7 - 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”)).

[0043] 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.

[0044] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a 202406307

[0045] - 8 - 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

[0046] 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.

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

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

[0049] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures. 202406307

[0050] - 9 -

[0051] 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.

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

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

[0054] The disclosure is related to wireless communication system, which may be for example a 5G NR wireless communication system. More specifically, it represents a RAN of the wireless communication system, which is used exchange data with UEs via radio signals. For example, the RAN may send data to the UEs (downlink, DL), for instance data received from a core network (CN). The RAN may also receive data from the UEs (uplink, UL), which data may be forwarded to the CN. 202406307

[0055] - 10 -

[0056] 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.

[0057] 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.

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

[0059] The wireless device comprises one or more processors and one or more memories. The one or more processors may include for instance a central processing unit (CPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. The one or more memories may include any type of computer readable volatile and non-volatile memories (magnetic hard disk, solid-state disk, optical disk, electronic memory, etc.). The one or more memories may store a computer program product, in the form of a set of programcode instructions to be executed by the one or more processors to implement all or part of the steps of a method for exchanging data, performed at a UE’s side, according to any one of the embodiments disclosed herein. 202406307

[0060] - 11 -

[0061] 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.

[0062] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

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

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

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

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

[0067] AI / ML model transfer is a delivery of an AI / ML model over the air interface in manner that is not transparent to 3GPP signalling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model. 202406307

[0068] - 12 -

[0069] 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.

[0070] 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.

[0071] 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.

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

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

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

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

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

[0077] Model monitoring is A procedure that monitors the inference performance of the AI / ML model. 202406307

[0078] - 13 -

[0079] 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.

[0080] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0081] Model update is Process of updating the model parameters and / or model structure of model.

[0082] Model upload is Model transfer from UE to the network.

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

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

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

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

[0087] Online training is an AI / ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note is the notion of (near) real-time vs. non real-time is context- dependent and is relative to the inference time-scale. This definition only serves as guidance. 202406307

[0088] - 14 -

[0089] 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.

[0090] 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.

[0091] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

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

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

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

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

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

[0097] Open-format models is ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually 202406307

[0098] - 15 - recognizable between vendors and do not hide model design information from other vendors when shared.

[0099] 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. 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 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. When sensing data is used for ML model operation such as data collection or training / inferencing / monitoring / updating, it is important to manage model performance if sensing data quality is not stable or varying. In this method, multiple 202406307

[0100] - 16 - levels of sensing data quality derived from sensing signal can be configured. By setting a finite number of sensing data quality levels, UE having specific sensing data quality level can be prioritized to perform ML model operation between network side and UE side where sensing data quality can be categorized based on statistical measurement with the preset threshold. Quality level of sensing data quality can be determined to be high or low in the simplest way if applicable using 1 -bit indication.

[0101] For example, ML model operation resource is assigned to UE with high sensing data quality level so that the overall model performance can be enhanced such as model training, inferencing, updating or monitoring. If UE with low quality level of sensing data is selected, model performance can be degraded. Sensing (sensory) capability can be associated with configuration of sensing data quality if applicable where sensing capability indicates types of sensing data, multitude of sensory signals, etc.

[0102] For example, sensing interference level is higher than threshold level or too much interference is detected, ML dataset collection or LCM operation using sensory data can be delayed or de-activated. When there are multiple UEs with sensing signal capability, ML model operation can be based on sensing data collection and the associated sensing data quality level can be determined. Based on the determined sensing data quality levels of each UEs, UE model operation can be prioritized for resource use and ML information signaling between network side and UE side. For example, UEs with sensing data quality level above the preset threshold can be selected so that network-sided model can communicate with those selected UEs for one- / two-sided model. Configuration information about sensing data quality level measurement is provided to UE, then UE can locally determine its own sensing data quality level. If not, sensing data can be sent to network side so that sensing data quality level can be decided with prioritization by network side. In addition, sensing capability can be informed to network side so that network side can decide model configuration and / or UE selection. Therefore, UE or UE-sided model can be prioritized depending on UE sensing capability and / or the associated sensing data quality level measured. The pre-configured finite set of IDs for sensing data quality levels can be sent via system information or dedicated RRC signaling. UE sensing capability can be configured so that the related information can be signaled to 202406307

[0103] - 17 - network side for alignment. Any specific sensing capability can be requested by network side and UE identifies the supported sensing capability for reporting. If sensing capability can be quantized for multiple levels, each UE can provide the associated level that indicates specific description of sensing capability such as types of sensing data, multitude of sensory signals, etc. Based on the combinations of sensing data quality level and sensing capability level, network side can decide model configuration and / or UE selection so that UE or UE-sided model can be prioritized for resource and signaling. The pre-configured finite set of IDs for sensing capability levels can be sent via system information or dedicated RRC signaling.

[0104] Sensing capability description depends on different sensory signal types as an example so that device category can be associated with sensing capability such as smartphone, in-vehicle telematics, loT device, etc. having different multitude of sensory signals.

[0105] A finite list of levels for sensing data quality and sensing capability can be jointly configured at network side. When RRC connection is set up, the initial information about sensing capability can be provided to network via UE capability information messaging. Depending on ML model operation and the associated applications or deployment scenarios, any specific level(s) of sensing data quality and sensing capability can be pre-determined so that UEs can be selected who meet the specific level(s). If index or ID based indication is used for UE selection, sensing dataset ID and / or sensing data quality level ID can be used for signaling purpose.

[0106] Based on the requested measure of sensing data quality level and sensing capability updates, UE or UE-sided model can be decided to perform ML model operation when the measured level is above the preset threshold or meets prioritization criteria.

[0107] Therefore, UE or UE-sided model can be prioritized depending on UE sensing capability and / or the associated sensing data quality level measured. If there is no associated ML operation for UE, then the measurement results can be only indicated to network side if applicable. Network side provides configuration information about the preset level IDs of sensing data quality levels and sensing capability levels with 202406307

[0108] - 18 - the related threshold information. Based on the requested measurement, UE executes measurements and determines its own sensing data quality level and sensing capability level. The determined levels can trigger any configured ML model operation at UE autonomously and / or send the measurement response so that any related re-configuration can be set at network side before further one-Ztwo-sided model operation. Based on the collection of dataset of sensory information, drift can be detected where model input feature set is related to sensory data. Depending on applicable multi-sensory data information, model operation can be changed such as 1 ) ML model enable / disable, 2) ML model selection, 3) ML model switching. Sensing measurement data format or ID can be preset with sensing signal type ID (e.g., LiDAR, Radar, WiFi sensing, BT sensing, etc.) associated with device sensing capability. Specific subset of sensor modalities of sensory data collection can be used for various ML model LCM operations (e.g., dataset collection / training / inferencing / updating). Priority index information can be configured for selective sensory dataset to be used for ML model based LCM operation (e.g., training, inferencing, updating, monitoring) e.g., {application, functionality, model info, LCM info}. Mapping relation information about 1 ) sensory modality and sensory dataset category and / or 2) drift type and sensory dataset category and / or sensory modality can be pre-determined via offline measurement or training.

[0109] In addition, multiple levels of frequent measurements are configured to collect more data or less data so as to ensure the network configures the measurement parameters accordingly to compensate for model performance degradation. Collecting more data and adjusting the measurement parameters dynamically is an effective approach to address data quality issues. The gNB / UE can be configured to collect data more frequently, which can help capture changes in data quality over time. As the model performance degrades, the network can dynamically adjust the measurement parameters. This can help maintain model performance even in the face of varying data quality. The data quality levels can still be useful for the usage of high-quality data for critical model operations, while the dynamic adjustment of measurement configuration can help improve the overall data quality over time. Specifically, mapping relation information about data quality level and data collation size are defined to send the indication message about index of the matching data 202406307

[0110] - 19 - collation size based on the measured data quality. In case of poor data quality at the UE / gNB, the synthetic data generation complement the missing data or data quality to improve the model performance. AI / ML based synthetic data generation models can be used to create realistic high-quality data that can be used to support the existing dataset.

[0111] This can help improve the overall data quality for better model performance. Also it can fill in missing values, generating data matching the target statistical characteristics.

[0112] For example, a mapping to the signaling flow is applied so that the sensing data quality level ID and the sensing capability ID are explicitly carried within standardized 3GPP signaling messages. For example, the quality level ID and / or capability ID may be included in an RRC UE Capability information message, in an RRC Reconfiguration message, or broadcast via a System InformationBlock (SIB). In order to ensure smooth integration into existing specifications, backward compatibility is maintained by allowing UEs that do not support sensing-based AI / ML operations to simply ignore such information elements (lEs).

[0113] The disclosed invention resolves a fundamental challenge specifically concerning the dynamic and variable quality of sensory data from UEs. While existing systems may support basic data collection, they fail to provide a robust and scalable method for a network node (e.g., gNB) to efficiently manage and optimize ML model performance by proactively assessing and leveraging a diverse range of UE sensing capabilities and the real-time quality of their generated data, providing a novel solution by defining and utilizing hierarchical, quantifiable levels of sensing data quality and sensing capability. This allows a network node to dynamically configure and receive reports on these levels from UEs. By implementing a joint prioritization scheme that analyzes both the reported capability and quality levels, the network can intelligently select UEs for specific ML tasks, allocate network resources, and manage signaling overhead. This approach ensures that critical ML operations, such as model training or inference, are performed with UEs providing the most suitable and high-quality data, thereby mitigating performance degradation and enhancing overall network efficiency. Backward compatibility is also supported by allowing legacy UEs that do 202406307

[0114] - 20 - not implement sensing-based AI / ML operations to ignore such new lEs. By anchoring the signaling in well-defined RRC and MAC procedures, and by providing explicit identifiers for sensing-related quality and capability, the invention achieves efficient resource utilization and enables practical feasibility.

[0115] Figure 1 shows an exemplary table of assignment of sensing data quality level for UE. In this example, when there are multiple UEs with sensing signal capability, ML model operation can be based on sensing data collection and the associated sensing data quality level can be determined. Based on the determined sensing data quality levels of each UEs, UE model operation can be prioritized for resource use and ML information signaling between network side and UE side. For example, UEs with sensing data quality level above the preset threshold can be selected so that network-sided model can communicate with those selected UEs for one- / two-sided model.

[0116] Configuration information about sensing data quality level measurement is provided to UE, then UE can locally determine its own sensing data quality level. If not, sensing data can be sent to network side so that sensing data quality level can be decided with prioritization by network side. In addition, sensing capability can be informed to network side so that network side can decide model configuration and / or UE selection. Therefore, UE or UE-sided model can be prioritized depending on UE sensing capability and / or the associated sensing data quality level measured. The pre-configured finite set of IDs for sensing data quality levels can be sent via system information or dedicated RRC signaling.

[0117] Figure 2 shows an exemplary table of the indexed sensing capability levels. In this example, UE sensing capability can be configured so that the related information can be signaled to network side for alignment. Any specific sensing capability can be requested by network side and UE identifies the supported sensing capability for reporting. If sensing capability can be quantized for multiple levels, each UE can provide the associated level that indicates specific description of sensing capability such as types of sensing data, multitude of sensory signals, etc. Based on the combinations of sensing data quality level and sensing capability level, network side 202406307

[0118] - 21 - can decide model configuration and / or UE selection so that UE or UE-sided model can be prioritized for resource and signaling.

[0119] The pre-configured finite set of IDs for sensing capability levels can be sent via system information or dedicated RRC signaling. Sensing capability description depends on different sensory signal types as an example so that device category can be associated with sensing capability such as smartphone, in-vehicle telematics, loT device, etc. having different multitude of sensory signals.

[0120] Figure 3 shows an exemplary flow chart of configuring levels of sensing data quality and / or sensing capability at network side. In this example, a finite list of levels for sensing data quality and sensing capability can be jointly configured at network side. When RRC connection is set up, the initial information about sensing capability can be provided to network via UE capability information messaging. Depending on ML model operation and the associated applications or deployment scenarios, any specific level(s) of sensing data quality and sensing capability can be pre-determined so that UEs can be selected who meet the specific level(s). If index or ID based indication is used for UE selection, sensing dataset ID and / or sensing data quality level ID can be used for signaling purpose.

[0121] Figure 4 shows an exemplary flow chart of detecting sensing data quality level and / or sensing capability level at UE side. In this example, based on the requested measure of sensing data quality level and sensing capability updates, UE or UE-sided model can be decided to perform ML model operation when the measured level is above the preset threshold or meets prioritization criteria. Therefore, UE or UE-sided model can be prioritized depending on UE sensing capability and / or the associated sensing data quality level measured. If there is no associated ML operation for UE, then the measurement results can be only indicated to network side if applicable.

[0122] Figure 5 shows an exemplary signaling flow of configuration and measurement for sensing data quality and sensing capability levels. In this example, network side provides configuration information about the preset level IDs of sensing data quality levels and sensing capability levels with the related threshold information. Based on 202406307

[0123] - 22 - the requested measurement, UE executes measurements and determines its own sensing data quality level and sensing capability level. The determined levels can trigger any configured ML model operation at UE autonomously and / or send the measurement response so that any related re-configuration can be set at network side before further one-Ztwo-sided model operation.

[0124] Figure 6 shows an exemplary block diagram of relationship among sensor modality, sensory dataset category and model feature set. In this example, based on the collection of dataset of sensory information, drift can be detected where model input feature set is related to sensory data. Depending on applicable multi-sensory data information, model operation can be changed such as 1 ) ML model enable / disable, 2) ML model selection, 3) ML model switching. Sensing measurement data format or ID can be preset with sensing signal type ID (e.g., LiDAR, Radar, WiFi sensing, BT sensing, etc.) associated with device sensing capability. Specific subset of sensor modalities of sensory data collection can be used for various ML model LCM operations (e.g., dataset collection / training / inferencing / updating). Priority index information can be configured for selective sensory dataset to be used for ML model based LCM operation (e.g., training, inferencing, updating, monitoring) e.g., {application, functionality, model info, LCM info}. Mapping relation information about 1 ) sensory modality and sensory dataset category and / or 2) drift type and sensory dataset category and / or sensory modality can be pre-determined via offline measurement or training.

Claims

202406307- 23 -CLAIMS1. A method of data quality measurement based selection by configuring multiple levels of sensing data quality derived from sensing signal in a wireless communication system, comprising:• Setting a finite number of sensing data quality levels;• Prioritizing sensing data quality levels;• Associating priority of ML model operation with UE sensing capability and sensing data quality levels.

2. The method according to previous claim 1 , wherein UE having specific sensing data quality level is prioritized to perform ML model operation between network side and UE side so that sensing data quality is categorized based on statistical measurement with the preset threshold.

3. The method according to one of the previous claims, wherein quality level of sensing data quality is determined to be high or low in the simplest way if applicable (e.g., using 1 -bit indication).

4. The method according to one of the previous claims, wherein ML model operation resource is assigned to UE with high sensing data quality level so that the overall model performance is enhanced such as model training, inferencing, updating or monitoring.

5. The method according to one of the previous claims, wherein sensing (sensory) capability is associated with configuration of sensing data quality if applicable where sensing capability indicates types of sensing data, multitude of sensory signals, etc.

6. The method according to one of the previous claims, wherein ML dataset collection or LCM operation using sensory data is delayed or de-activated when sensing interference level is higher than threshold level or too much interference is detected.202406307- 24 -7. The method according to one of the previous claims, wherein ML model operation is based on sensing data collection and the associated sensing data quality level is determined when there are multiple UEs with sensing signal capability.

8. The method according to one of the previous claims, wherein UE model operation is prioritized for resource use and ML information signaling between network side and UE side based on the determined sensing data quality levels of each UEs.

9. The method according to one of the previous claims, wherein UEs with sensing data quality level above the preset threshold is selected so that network-sided model can communicate with those selected UEs for one- / two-sided model.

10. The method according to one of the previous claims, wherein configuration information about sensing data quality level measurement is provided to UE so that UE can locally determine its own sensing data quality level.11 . The method according to one of the previous claims, wherein sensing data is sent to network side so that sensing data quality level is decided with prioritization by network side.

12. The method according to one of the previous claims, wherein sensing capability is informed to network side so that network side can decide model configuration and / or UE selection.

13. The method according to one of the previous claims, wherein UE or UE-sided model is prioritized depending on UE sensing capability and / or the associated sensing data quality level measured.

14. The method according to one of the previous claims, wherein the pre-configured finite set of IDs for sensing data quality levels is sent via system information or dedicated RRC signaling.202406307- 25 -15. The method according to one of the previous claims, wherein UE sensing capability is configured so that the related information is signaled to network side for alignment.

16. The method according to one of the previous claims, wherein any specific sensing capability is requested by network side and UE identifies the supported sensing capability for reporting.

17. The method according to one of the previous claims, wherein each UE can provide the associated level that indicates specific description of sensing capability such as types of sensing data, multitude of sensory signals, etc. if sensing capability is quantized for multiple levels.

18. The method according to one of the previous claims, wherein network side can decide model configuration and / or UE selection so that UE or UE-sided model is prioritized for resource and signaling based on the combinations of sensing data quality level and sensing capability level.

19. The method according to one of the previous claims, wherein the pre-configured finite set of IDs for sensing capability levels is sent via system information or dedicated RRC signaling.

20. The method according to one of the previous claims, wherein a finite list of levels for sensing data quality and sensing capability is jointly configured at network side.

21. The method according to one of the previous claims, wherein the initial information about sensing capability is provided to network via UE capability information messaging when RRC connection is set up.

22. The method according to one of the previous claims, wherein any specific level(s) of sensing data quality and sensing capability is pre-determined so that UEs is selected who meet the specific level(s).202406307- 26 -23. The method according to one of the previous claims, wherein sensing dataset ID and / or sensing data quality level ID is used for signaling purpose if index or ID based indication is used for UE selection.

24. The method according to one of the previous claims, wherein UE or UE-sided model is decided to perform ML model operation when the measured level is above the preset threshold or meets prioritization criteria based on the requested measure of sensing data quality level and sensing capability updates.

25. The method according to one of the previous claims, wherein UE or UE-sided model is prioritized depending on UE sensing capability and / or the associated sensing data quality level measured.

26. The method according to one of the previous claims, wherein the measurement results is only indicated to network side if there is no associated ML operation for UE.

27. The method according to one of the previous claims, wherein network side provides configuration information about the preset level IDs of sensing data quality levels and sensing capability levels with the related threshold information.

28. The method according to one of the previous claims, wherein model operation is changed such as 1 ) ML model enable / disable, 2) ML model selection, 3) ML model switching depending on applicable multi-sensory data information.

29. The method according to one of the previous claims, wherein sensing measurement data format or ID is preset with sensing signal type ID (e.g., LiDAR, Radar, WiFi sensing, BT sensing, etc.) associated with device sensing capability.

30. The method according to one of the previous claims, wherein specific subset of sensor modalities of sensory data collection is used for various ML model LCM operations (e.g., dataset collection / training / inferencing / updating).202406307- 27 -31 . The method according to one of the previous claims, wherein priority index information is configured for selective sensory dataset to be used for ML model based LCM operation (e.g., training, inferencing, updating, monitoring) e.g., {application, functionality, model info, LCM info}.

32. The method according to one of the previous claims, wherein mapping relation information about 1 ) sensory modality and sensory dataset category and / or 2) drift type and sensory dataset category and / or sensory modality is pre-determined via offline measurement or training.

33. The method according to one of the previous claims, wherein multiple levels of frequent measurements are configured to collect more data or less data.

34. Apparatus for data quality measurement based selection by configuring multiple levels of sensing data quality derived from sensing signal 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 33.

35. User Equipment comprising an apparatus according to claim 34.

36. gNB comprising an apparatus according to claim 34.

37. Wireless communication system for data quality measurement based selection by configuring multiple levels of sensing data quality derived from sensing signal, wherein the wireless communication systems comprises user equipment according to claim 35, gNB according to claim 36, 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 33.

Images