Method of model grouping signaling

Abstract

Methods of using a pre-configured AI / ML (artificial intelligence / machine learning) based group model ID assignment in wireless mobile communication system including base station (e.g., gNB) and mobile station (e.g., UE). If an AI / ML model is applied to radio access network, signaling of model ID information exchange can be heavily congested based on different model execution environments with varying models. Therefore, model operation can be set up between the network and a UE by assigning a group model ID.

Description

[0001] TITLE

[0002] Method of model grouping signaling

[0003] TECHNNICAL FIELD

[0004] The present disclosure relates to AI / ML based model grouping identification, where techniques for pre-configuring and signaling the specific information about model grouping using associations between models and their properties are presented.

[0005] BACKGROUND

[0006] In 3GPP (Third Generation Partnership Project), one of the selected study items as of 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 the AI / ML study item is “Study on AI / ML for NR Air Interface”, and currently, RAN WG1 (Working Group 1 ) and WG2 are actively working on a specification. 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.

[0007] According to 3GPP, the main objective of this study item is to study an AI / ML frameworks for air-interface with target use cases by considering performance, complexity, and potential specification impacts. In particular, AI / ML models, terminology and descriptions to identify common and specific characteristics for a framework will be one of the key work scopes. Regarding AI / ML frameworks, various aspects are under consideration for investigation and one of key items is about lifecycle management (LCM) of AI / ML models where multiple stages are included as mandatory for model training, model deployment, model inference, model monitoring, model updating etc.

[0008] Earlier, in 3GPP TR 37.817 for Release 17, titled “Study on enhancement for Data Collection for NR and EN-DC”, UE (user equipment) mobility was also considered as one of the AI / ML use cases and one of the scenarios for model training / inference is that both functions are located within a 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 architectures.

[0009] For the above active standardization works, model identification (e.g., model ID) to support RAN-based AI / ML models is considered as very significant for both the network and the UE to meet any desired model operations (e.g., model training, inference, selection, switching, update, monitoring, etc.). Model ID information can be signaled to pair both network-side and UE-side models for various lifecycle management operations. However, if all physical models available on both sides are identified with their own model IDs separately, signaling overhead indicating model ID information can be very high especially when model ID based LCM is processed between a base station (BS / gNB) and multiple UEs.

[0010] Currently, there is no specification defined for signaling methods and network-UE behaviors when all models are identified with their own model ID information to support for RAN-based model operation. Therefore, a new mechanism for base station (BS / gNB)-UE behaviors and procedures is needed to avoid heavy signaling overhead on model operation using multiple specific AI / ML models and / or operation across different UEs. It is necessary to investigate any specification impact by considering model operation when there are traffic congestions due to signaling overhead with exchange of individual model ID information.

[0011] The disclosure of US 2022 400 373 A1 provides techniques and apparatus for determining neural network functions (NNFs) and configuring and using corresponding machine learning (ML) models for performing one or more ML-based wireless communications management procedures. An example method performed by a user equipment includes transmitting, to a base station (BS), UE capability information indicating at least one radio capability of the UE and at least one machine learning (ML) capability of the UE and receiving, from the BS based on the UE capability information, ML configuration information indicating at least one neural network function (NNF) and at least one ML model corresponding to the at least one NNF.

[0012] US 2022 108 214 A1 discloses a machine learning (ML) model management method for a network data analytics function (NWDAF) device. The NWDAF device performs at least one of an analytics logical function (AnLF) for network data and an ML model training logical function (MTLF).

[0013] US 2022 337 487 A1 discloses a network entity which 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 from a requesting entity over the communication network, the model request requesting the at least one model parameter of the model, to obtain the requested at least one model parameter by at least one of the following: executing a machine-learning model training algorithm, the machine-learning model training algorithm being configured to train the model with input data in order to determine at least one of the requested model parameter; searching a local data base for an existing model; or requesting the at least one model parameter from a further network entity; and to send the requested model parameter towards the requesting entity over the communication network.

[0014] WO 2023 277 780 A1 discloses systems and methods related to downloading of a compiled machine code version of a Machine Learning (ML) model to a wireless communication device (WCD). In one embodiment, a method performed by a WCD comprises receiving, from a server node, a complied machine code version of a ML model, the compiled machine code version of the ML model being one of a set of compiled machine code versions of ML models, wherein the compiled machine code version of the ML model received by the WCD is precompiled for a hardware of the WCD. The method further comprises performing one or more radio network operations using the compiled machine code version of the ML model. Related embodiment of a server node and a Radio Access Network (RAN) node and methods of operation thereof are also disclosed. The disclosure of WO 2022 258 149 A1 provides a way for training a model in a server device based on training data in a user device. Privacy of the training data is ensured, as the training data as such is not made available to the server device. The present disclosure therefore provides a user device for privacy preserving model training. The user device is configured to obtain a training set of user data; receive a master model from a server device; determine a parameter based on the master model, the parameter being a parameter to be optimized; generate a model update based on the parameter and the training set of user data; and transmit the model update to the server device.

[0015] WO 2022 228 666 A1 discloses systems and methods that relate to influencing training of a Machine Learning (ML) model based on a training policy provided by an actor node. In one embodiment, a method performed by a first node for training a ML model comprises receiving a training policy for a ML model from a second node, the training policy comprising information that indicates two or more accuracy or importance metrics for two or more ranges of values for a variable to be predicted by the ML model. The method further comprises training the ML model based on a training dataset and the training policy. In one embodiment, the first node is either a training and inferring node or a training node that operates to train the ML model, and the second node is an actor node to which predictions made using the ML model are to be provided.

[0016] WO 2022 161 624 A1 discloses a computer-implemented method performed by a network node. The method includes receiving a request for retrieving or executing a machine learning (ML) model or a combination of ML models. The request includes a first description of a specified output feature and specified input data type and distribution of input values for a ML model or combination of ML models. The method further includes obtaining an identification of a ML model, or a combination of ML models, having a second description that at least partially satisfies a match to the first description; identifying a candidate ML model, or combination of ML models, that produces the specified output feature of the first description based on a comparison of the first and second descriptions. The method further includes selecting a third description of the identified candidate ML model, or combination of ML models, based on a convergence.

[0017] BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The disclosed invention will be further discussed in the following based on preferred embodiments presented in the attached drawings. However, the disclosed invention may be embodied in many different forms and should not be construed as limited to said preferred embodiments. Rather, said preferred embodiments are provided for thoroughness and completeness, and fully convey the scope of the invention to the skilled person. The following detailed description refers to the attached drawings, in which:

[0019] Figure 1 is an exemplary block diagram of a group model ID assignment for on-device models at a UE side.

[0020] Figure 2 is an exemplary block diagram of a group model ID assignment for multiple grouped UEs.

[0021] Figure 3 is an exemplary block diagram of a two-sided model using a group model ID based UE group.

[0022] Figure 4 is an exemplary block diagram of a group model ID transmission for a single UE group.

[0023] Figure 5 is an exemplary block diagram of a group model ID transmission for multiple UE groups.

[0024] Figure 6 is an exemplary signaling flow of a group model ID assignment with a network-sided decision.

[0025] Figure 7 is an exemplary signaling flow of group model ID assignment with a UE-sided decision. Figure 8 is an exemplary signaling flow of a group model ID based model activation.

[0026] Figure 9 is an exemplary flow chart of a network side behavior for group model ID decision by network.

[0027] Figure 10 is an exemplary flow chart of a UE side behavior for group model ID decision by network.

[0028] Figure 11 is an exemplary flow chart of a network side behavior for group model ID decision by UE.

[0029] Figure 12 is an exemplary flow chart of a UE side behavior for group model ID decision by UE.

[0030] Figure 13 is an exemplary block diagram of a model ID type structure.

[0031] DETAILED DESCRIPTION

[0032] The detailed description set forth below, with reference to the 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.

[0033] 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.

[0034] 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.

[0035] 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), another UE, etc. 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.

[0036] Additionally, terminologies such as base station / gNodeB and UE should be considered non-limiting and in particular do 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.

[0037] As will be appreciated by one skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method, or computer program product.

[0038] 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.

[0039] 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. Furthermore, embodiments may take the form of a computer 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.

[0040] 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.

[0041] 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 read-only 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.

[0042] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object-oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

[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.

[0044] 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.

[0045] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and computer 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 are executed via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[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.

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

[0051] 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.

[0052] The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model selection using associations between models and index values. AI / ML based techniques are currently applied to many different applications and 3GPP also started to work on its technical investigation to apply multiple use cases based on the observed potential gains.

[0053] An 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 models for any use case or application, one of the challenging issues is to manage the lifecycle of AI / ML models. This is mainly because a data / model drift occurs during model deployment / inference which results in performance degradation of AI / ML model. Fundamentally, the dataset statistical changes occur after the model is deployed and the model inference capability is impacted while using unseen data as input.

[0054] In a similar aspect, the statistical property of a dataset and the relationship between input and output for the trained model can be changed with drift occurrence. In this context, model selection is a key issue for model performance maintenance as model performance such as inferencing and / or training is dependent on different model execution environments with varying configuration parameters.

[0055] To handle this issue, a collaboration between UE and gNB is highly important to track model performance and re-configure models corresponding to different environments. An AI / ML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift. Then, update feedback is provided to re-train / update the model or select alternative model. When an AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle AI / ML models in activation with re-configuration for wireless devices under operations such as model training, inference, updating, etc. Therefore, there is a need for specification for signaling methods and gNB-UE behaviors when a set of multiple specific AI / ML models are supported for RAN-based model operation. A new mechanism for gNB-UE behaviors and procedures is necessary to avoid any performance impact on model operation using multiple specific AI / ML models.

[0056] Based on the ML configuration for model properties to perform LCM operation, two or more models within a UE device or across multiple UE devices are assigned for the same model ID which is then called group model ID. For example, a model identifier is to be assigned for multiple models that can be grouped together at the UE side. As another example, for a list of available UE side models, a group model ID can be assigned to candidate models of each UEs to support the configured ML and LCM operation for one- or two-sided models. Assigning a group model ID to different models can be applicable to models located at network side. For group model ID signaling, the pre-configured mapping relationship with index information (through system information or RRC signaling) can be used to represent model properties (e.g., model specific characteristics such as attribute data) and the configured group model ID (optionally based on the associated model category, application, and / or functionality). And group model ID based LCM operation can be activated or deactivated through L1 / L2 / L3 signaling.

[0057] The first aspect of the invention discloses a method of configuring group model identification for a two-sided model operation in a network. The network comprises multiple artificial intelligence (Al)Zmachine learning (ML) models deployed on at least one user equipment (UE) for use in the two-sided model operation. The method according to the first aspect comprises the steps:

[0058] • Receive grouping criteria,

[0059] • Assign a group model identifier (ID) to each model of the multiple AI / ML models, thereby generating group model IDs, wherein each group model ID exclusively corresponds to an element of the grouping criteria, and

[0060] • Activate the two-sided model operation by activating models with the same group model ID via L1 / L2 / L3 signaling.

[0061] Advantageously, the multiple AI / ML models are deployed on a single UE of the at least one UE.

[0062] Advantageously, the multiple AI / ML models are distributedly deployed on different UEs of the at least one UE.

[0063] Advantageously, the group model ID of a model is assigned to a network-sided model, the network-sided model being an AI / ML model which jointly operates with the model during the two-sided model operation.

[0064] Advantageously, the grouping criteria are based on a similarity in:

[0065] • pre-configured measurements of different combinations of model properties of the AI / ML models, and / or

[0066] • type, structure, category, application, functionality, or performance of the AI / ML models, and / or

[0067] • attribute or meta data of the AI / ML models, use cases or scenarios for ML signaling purposes.

[0068] Advantageously, a pre-configuring mapping relationship with index information of the AI / ML models and the group model ID is generated, the mapping relationship signaled via RRC signaling or system information to activate the two-sided model operation.

[0069] Advantageously, multiple UEs with ML encoders perform a LCM operation in cooperating with a network-sided ML decoder, wherein the multiple UEs have been assigned the same group model ID during the LCM operation or AI / ML models on different UEs have been assigned the same group model ID during the LCM operation.

[0070] Advantageously, a single UE group with multiple UEs are assigned with an identical group model ID.

[0071] Advantageously, there are multiple UE groups so that each UE groups can be assigned with group model IDs separately while UEs belonging to the same group have the same group model ID.

[0072] Advantageously, the group model IDs are determined for assignment at the network side so that the UEs can use the assigned group model ID for one or multiple models.

[0073] Advantageously, the UE assigns the group model ID for models on the UE side, the assignment based on a group model ID assignment configuration which is sent by the network, the UE further sending a confirmation message.

[0074] Advantageously, the network side assigns the group model ID and the UE identifies candidate models applicable to the group model ID, the UE further sending an indication message to the network, confirming the activation of the group model ID based models. Advantageously, model configuration updates are performed via a group model ID based Life Cylce Management (LCM) operation, using either common / dedicated control signaling or data channel signaling.

[0075] Advantageously, group model ID based LCM operations are applied to dynamic / semi-persistent scheduling or other scheduling types depending on different conditions, where:

[0076] • Activating / deactivating group model ID based LCM operations are based on the configured triggering measure, and

[0077] • The Network or the UE side decide on the scheduling types.

[0078] A second aspect of this invention discloses a method of forming a model ID type structure comprising hierarchical model ID types to categorize different models with a model ID assignment, where:

[0079] • A static model ID is assigned for any dedicated model, or

[0080] • A semi-static model ID is assigned for any dedicated model based on different applications and / or configurations, or

[0081] • A dynamic model ID is assigned for ML / LCM operations and / or during ML / LCM operation, or

[0082] • A group-common model ID is assigned for multiple models based on common properties configured by the network side or the UE side, or

[0083] • A device-specific model ID is assigned for any specific on-device model, or

[0084] • A categorized model ID type which maps each model to different types of model IDs depending on any conditions or configurations when the grouped model IDs are assigned to the UE or a UE group.

[0085] A third aspect of this invention discloses an apparatus for method of configuring group model identification by applying the same group model ID to multiple models within UE and / or across a UE group 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 an above-described method and the apparatus is designed for the use in a base station (gNB). A fourth aspect of this invention discloses an apparatus for method of configuring group model identification by applying the same group model ID to multiple models within UE and / or across a UE group 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 an above-described method and the apparatus is designed for the use in a user equipment (UE).

[0086] A fifth aspect of this invention discloses a base station (gNB) comprising above-described apparatus.

[0087] A sixth aspect of this invention discloses a User Equipment (UE) comprising an of above-described apparatus.

[0088] A seventh aspect of this invention discloses a wireless communication system comprising at least an above-described base station (gNB) and at least an above-described user equipment (UE).

[0089] For group model ID assignment, a finite set of available (supported) models are grouped based on the pre-configured measurement of different combinations of model properties or model type / structure / functionality / performance similarity for any specific LCM operation or ML signaling purpose (the criteria may depend on implementation-specific parameters of those combinations). Or different models can be grouped together (offline or online) to have the same group model ID based on different use cases or scenarios for ML signaling purposes based on either similarity or non-similarity based measures. Group model ID based LCM operation can be applied to dynamic / semi-persistent scheduling or other scheduling type depending on different conditions, where activating / deactivating group model ID based LCM operation can be based on the configured triggering measure and the decision of scheduling types can be made by network or UE side. If there is any model configuration update to be done during group model ID based LCM operation, either common or dedicated control signaling can be used while data channel can be used as well.

[0090] Figure 1 is an exemplary block diagram of a group model ID assignment for on-device models at UE side model. In this example, a device contains seven AI / ML models (e.g., model A to model G) and they are grouped together such as group model ID #1 (models A, B, C), group model ID #2 (models D, E), and group model ID #3 (models F, G) based on the pre-configured group model assignment criteria (e.g., similarity of model properties or model attribute data of type / structure / functionality, etc.). Different number of group model IDs can be assigned to various sets of available models within a device if necessary.

[0091] Figure 2 is an exemplary block diagram of a group model ID assignment for multiple UEs as a group. In this example, there are three UE devices and the group model ID is assigned to model B (UE #1 ), model D (UE #2), and model G (UE #3). Different UE devices with different models can have the same group model ID assigned to them based on the pre-configured group model assignment criteria (e.g., similarity of model properties or model attribute data of type / structure / functionality, etc.). Different number of group model IDs can be assigned to various sets of available models across multiple UE devices if necessary.

[0092] Figure 3 is an exemplary block diagram of a two-sided model using group model ID based UE group. In this example, autoencoder-based ML is used between the network and the UEs so that there are multiple UE devices having their own ML encoder models, respectively, where each of the encoder models can be different in their model attribute data. However, based on the pre-configured group model assignment criteria, the same group model ID is assigned to them for LCM operation and the related signaling can be exchanged using the assigned group model ID between network and multiple UEs. Multiple UEs with ML encoders perform LCM operation (e.g., model training, inferencing, etc.) cooperating with network side having a ML decoder, where those connected UEs with ML encoders have the assigned group model ID during LCM operation. Figure 4 is an exemplary block diagram of group model ID transmission for a single UE group. In this example, a single UE group with multiple UEs (e.g., UE #1 to UE #K) is assigned a group model ID so that the related ML signaling can be exchanged using the same group model ID across the grouped UEs.

[0093] Figure 5 is an exemplary block diagram of a group model ID transmission for multiple UE groups. In this example, there are multiple UE groups (e.g., UE group #1 to UE group #P) so that each UE groups are assigned with group model IDs separately, while UEs belonging to the same group have the same group model ID. Based on the ML configuration sets and / or model properties, a group model ID per UE group can be assigned even if physical models of different UEs can be different to each other.

[0094] Figure 6 is an exemplary signaling flow of group model ID assignment with a network-sided decision. In this example, a group model ID is determined for assignment at the network side so that on-device model(s) at the UE side can use the assigned group model ID for one or multiple models.

[0095] Figure 7 is an exemplary signaling flow of a group model ID assignment with a UE-sided decision. In this example, the UE determines on-device models to be matched with a group model ID assignment configuration so that the network side can identify on-device model(s) assigned with a group model ID where mapping relationship information about group model ID and model properties can be included in a group model ID assignment configuration sent by the network. UEs can then autonomously determine the group model ID and confirm this group model ID to network.

[0096] Figure 8 is an exemplary signaling flow of a group model ID based model activation. In this example, one or more models assigned with a group model ID are activated. In this scenario, the network-side performs the group model ID assignment and the UE identifies candidate on-device models applicable to the group model ID so that an indication message can confirm activation of the group model ID based models. Figure 9 is an exemplary flow chart of a network side behavior for a group model ID decision by a network. In this example, applicability of a group model ID assignment is performed by the network side based on on-device model information sent by the UE. The group model ID is then assigned to specific model(s) for the UE or a UE group.

[0097] Figure 10 is an exemplary flow chart of UE side behavior for a group model ID decision by a network. In this example, the UE provides the on-device model information to the network so that the group model ID assignment can proceed. The on-device model information can vary depending on a ML information request from the network or a pre-configured signaling exchange.

[0098] Figure 11 is an exemplary flow chart of network side behavior for a group model ID decision by a UE. In this example, the network side provides a group model ID assignment configuration so that a group model ID assignment can proceed at the UE.

[0099] Figure 12 is an exemplary flow chart of UE side behavior for a group model ID decision by a UE. In this example, applicability of the group model ID assignment is performed by the UE side by determining on-device models to be matched with the group model ID assignment configuration.

[0100] Figure 13 is an exemplary block diagram of a model ID type structure. In this example, there are hierarchical model ID types to categorize different models with a model ID assignment. For example, a static model ID is assigned to be kept identical for any dedicated model(s). A semi-static model ID can be changed for any dedicated model based on different applications and / or configurations. A dynamic model ID is assigned differently for every other ML / LCM operations and / or during ML / LCM operation. A group-common model ID is assigned for multiple models based on common properties configured by the network or the device. A device-specific model ID is assigned for any specific on-device model, not for multiple models with different devices. When a group model ID is applied to a UE or a UE group, the above model ID types can be referenced to map each model to different types of model IDs depending on any given conditions or configurations.

[0101] Abbreviations

[0102] BWP Bandwidth part CBG Code block group CLI Cross Link Interference CP Cyclic prefix CQI Channel quality indicator CPU CSI processing unit CRB Common resource block CRC Cyclic redundancy check CRI CSI-RS Resource Indicator CSI Channel state information CSI-RS Channel state information reference signal CSI-RSRP CSI reference signal received power CSI-RSRQ CSI reference signal received quality CSI-SINR CSI signal-to-noise and interference ratio CW Codeword DCI Downlink control information DL Downlink DM-RS Demodulation reference signals DRX Discontinuous Reception EPRE Energy per resource element IAB-MT Integrated Access and Backhaul - Mobile Terminal L1 -RSRP Layer 1 reference signal received power LI Layer Indicator MCS Modulation and coding scheme PDCCH Physical downlink control channel PDSCH Physical downlink shared channel PSS Primary Synchronisation signal PUCCH Physical uplink control channel QCL Quasi co-location PMI Precoding Matrix Indicator PRB Physical resource block PRG Precoding resource block group PRS Positioning reference signal PT-RS Phase-tracking reference signal RB Resource block RBG Resource block group Rl Rank Indicator RIV Resource indicator value RP Resource Pool RS Reference signal SCI Sidelink control information SL CR Sidelink Channel Occupancy Ratio SL CBR Sidelink Channel Busy Ratio SLIV Start and length indicator value SR Scheduling Request SRS Sounding reference signal SS Synchronisation signal SSS Secondary Synchronisation signal SS-RSRP SS reference signal received power SS-RSRQ SS reference signal received quality SS-SINR SS signal-to-noise and interference ratio TB Transport Block TCI Transmission Configuration Indicator TDM Time division multiplexing UE User equipment UL Uplink

Claims

CLAIMS1 . A method of configuring group model identification for a two-sided model operation in a network, the network comprising multiple artificial intelligence (Al) / machine learning (ML) models deployed on at least one user equipment (UE) for use in the two-sided model operation, the method comprising the steps:• Receive grouping criteria,• Assign a group model identifier (ID) to each model of the multiple AI / ML models, thereby generating group model IDs, wherein each group model ID exclusively corresponds to an element of the grouping criteria, and• Activate the two-sided model operation by activating models with the same group model ID via L1 / L2 / L3 signaling.

2. Method according to claim 1 , characterized in that the multiple AI / ML models are deployed on a single UE of the at least one UE.

3. Method according to claim 1 or 2, characterized in that the multiple AI / ML models are distributedly deployed on different UEs of the at least one UE.

4. Method according to one of the previous claims, characterized in that the group model ID of a model is assigned to a network-sided model, the network-sided model being an AI / ML model which jointly operates with the model during the two-sided model operation.

5. Method according to one of the previous claims, characterized in that the grouping criteria are based on a similarity in:• pre-configured measurements of different combinations of model properties of the AI / ML models, and / or• type, structure, category, application, functionality, or performance of the AI / ML models, and / or• attribute or meta data of the AI / ML models,• use cases or scenarios for ML signaling purposes.

6. Method according to one of the previous claims, characterized in that a pre-configuring mapping relationship with index information of the AI / ML models and the group model ID is generated, the mapping relationship signaled via RRC signaling or system information to activate the two-sided model operation.

7. Method according to one of the previous claims, characterized in that multiple UEs with ML encoders perform a LCM operation in cooperating with a network-sided ML decoder, wherein the multiple UEs have been assigned the same group model ID during the LCM operation or AI / ML models on different UEs have been assigned the same group model ID during the LCM operation.

8. Method according to one of the previous claims, characterized in that a single UE group with multiple UEs are assigned with an identical group model ID.

9. Method according to previous claims 1 to 5, where there are multiple UE groups so that each UE groups can be assigned with group model IDs separately while UEs belonging to the same group have the same group model ID.

10. Method according to one of the previous claims, characterized in that the group model IDs are determined for assignment at the network side so that the UEs can use the assigned group model ID for one or multiple models.11 . Method according to one of the previous claims, characterized in that the UE assigns the group model ID for models on the UE , the assignment based on a group model ID assignment configuration which is sent by the network, the UE further sending a confirmation message.

12. Method according to one of claims 1 to 10, characterized in that the network side assigns the group model ID and the UE identifies candidate models applicable to the group model ID, the UE further sending an indication message to the network, confirming the activation of the group model ID based models.

13. Method according to one of the previous claims, characterized in that model configuration updates are performed via a group model ID based Life Cylce Management (LCM) operation, using either common / dedicated control signaling or data channel signaling.

14. Method according to one of the previous claims, characterized in that group model ID based LCM operations are applied to dynamic / semi-persistent scheduling or other scheduling types depending on different conditions, where:• Activating / deactivating group model ID based LCM operations are based on the configured triggering measure, and• The Network or the UE side decide on the scheduling types.

15. Method of forming a model ID type structure, comprising hierarchical model ID types to categorize different models with a model ID assignment, where:• A static model ID is assigned for any dedicated model, or• A semi-static model ID is assigned for any dedicated model based on different applications and / or configurations, or• A dynamic model ID is assigned for ML / LCM operations and / or during ML / LCM operation, or• A group-common model ID is assigned for multiple models based on common properties configured by the network side or the UE side, or• A device-specific model ID is assigned for any specific on-device model, or• A categorized model ID type which maps each model to different types of model IDs depending on any conditions or configurations when the grouped model IDs are assigned to the UE or a UE group.

16. Apparatus for method of configuring group model identification by applying the same group model ID to multiple models within UE and / or across a UE group 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 and the apparatus is designed for the use in a base station(gNB).

17. Apparatus for method of configuring group model identification by applying the same group model ID to multiple models within UE and / or across a UE group 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 and the apparatus is designed for the use in a user equipment (UE).

18. Base station (gNB) comprising an apparatus according to claim 16.

19. User Equipment comprising an apparatus according to claim 15.

20. Wireless communication system, comprising at least a base station (gNB) according to claim 16 and at least a user equipment (UE) according to claim 17.

Images