Transfer of artificial intelligence data to a communication device

Abstract

A communication device (12) communicates with a communication network (10) about a transfer of artificial intelligence, AI, data (18) from an external node (16) to the communication device (12) via the communication network (10). In some embodiments, the external node (16) is external to the communication network (10). In some embodiments, the communication device (12), based on its communication with the communication network (10), receives AI data (18) as transferred from the external node (16) to the communication device (12) via the communication network (10). The communication device (12) may use the received AI data (18), or an inference made by the communication device (12) from the received AI data (18), to perform one or more functions for operating in the communication network (10).

Description

[0001] TRANSFER OF ARTIFICIAL INTELLIGENCE DATA TO A COMMUNICATION DEVICE

[0002] TECHNICAL FIELD

[0003] The present application relates generally to a communication device, and relates more particularly to the transfer of artificial intelligence data to such a device.

[0004] BACKGROUND

[0005] Artificial Intelligence (Al) such as Machine Learning (ML) is a promising tool to optimize the design of the air-interface in communication networks. Example use cases include using autoencoders for channel state information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy, using deep neural networks for classifying line-of-sight (LOS) and non-LOS (NLOS) conditions to enhance positioning accuracy, using reinforcement learning for beam selection at the network side and / or the user equipment (UE) side to reduce the signaling overhead and beam alignment latency, and using deep reinforcement learning to learn an optimal precoding policy for complex multiple-input multiple-output (MIMO) precoding problems, as a few examples.

[0006] Some approaches to exploiting Al in a communication network store Al data (e.g., an Al model) in a node external to the communication network, e.g., in the form of an Over-the- Top (OTT) server. This external node may or may not generate the Al data (e.g., by training the Al model), and in either case stores the Al data for later transferring the Al data to a communication device. Once the Al data is transferred to the communication device, the communication device may make an inference from the Al data. Where the Al data concerns an Al model, this advantageously offloads the burden of training the Al model, so that the communication device need not perform that resource-intensive task.

[0007] However, challenges exist with transferring the Al data from the external node to the communication device via the communication network. Indeed, especially where the Al data transfer is performed over-the-top (OTT), transferring the Al data threatens to jeopardize network resources, create security risks, and prove unsustainable as Al data transfers scale.

[0008] SUMMARY

[0009] According to some embodiments herein, a communication device and / or an external node communicate with a communication network about a transfer of artificial intelligence, Al, data from the external node to the communication device via the communication network. Such communication may be performed as part of, or for the purpose of, coordinating the transfer with the communication network and / or informing the communication network about the transfer. Alternatively or additionally, such communication may be performed as part of, or for the purpose of enabling the communication network to exert control over whether, when, and / or how the Al data is communicated over the communication network, or enabling the communication network to exert control over whether, when, and / or how the transfer is performed. By providing such control to the communication network, some embodiments herein advantageously conserve network resources, address security risks, and / or improve sustainability as Al data transfers scale. Some embodiments do so even in the case that the transfer is performed over-the-top (OTT) such that the transfer would otherwise be transparent to the communication network, e.g., whereby the transfer would otherwise be indistinguishable to the communication network from any other user data and / or with the communication network having no knowledge that the transfer is of Al data.

[0010] More particularly, embodiments herein include a method performed by a communication device. The method comprises communicating with a communication network about a transfer of artificial intelligence, Al, data from an external node to the communication device via the communication network. In some embodiments, the external node is external to the communication network. In some embodiments, the method further comprises, based on said communicating, receiving Al data as transferred from the external node to the communication device via the communication network. The method may also comprise using the received Al data, or an inference made by the communication device from the received Al data, to perform one or more functions for operating in the communication network.

[0011] Other embodiments herein include a method performed by a network node configured for use in a communication network. The method comprises communicating with a communication device and / or an external node about a transfer of artificial intelligence, Al, data from the external node to the communication device via the communication network. In some embodiments, the external node is external to the communication network.

[0012] Other embodiments herein include a method performed by an external node that is external to a communication network. The method comprises communicating with the communication network about a transfer of artificial intelligence, Al, data from the external node to a communication device via the communication network. In some embodiments, the method also comprises, based on said communicating, performing the transfer of the Al data from the external node to the communication device via the communication network.

[0013] Embodiments herein also include corresponding apparatus, computer programs, and carriers of those computer programs.

[0014] BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a block diagram of a communication network according to some embodiments.

[0016] Figure 2 is a block diagram of an AI / ML model life cycle management for Al according to some embodiments.

[0017] Figure 3 is a block diagram of an example use case of autoencoder (AE)-based two- sided CSI compression according to some embodiments. Figure 4 is a logic flow diagram of an exemplary method performed by a core network node in accordance with particular embodiments.

[0018] Figure 5 is a logic flow diagram of an exemplary method performed by a core network node in accordance with other embodiments.

[0019] Figure 6 is a logic flow diagram of an exemplary method performed by a core network node in accordance with other embodiments.

[0020] Figure 7 illustrates a logic flow diagram of a method performed by a wireless device in accordance with particular embodiments.

[0021] Figure 8 illustrates a logic flow diagram of a method performed by a node storing UE- side models in accordance with particular embodiments.

[0022] Figure 9 illustrates a logic flow diagram of a method performed by a core network node in accordance with particular embodiments.

[0023] Figure 10 illustrates a logic flow diagram of a method performed by a core network node in accordance with other embodiments.

[0024] Figure 11 illustrates a logic flow diagram of a method performed by a core network node in accordance with other embodiments.

[0025] Figure 12 illustrates a logic flow diagram of a method performed by a RAN node in accordance with particular embodiments.

[0026] Figure 13 illustrates a logic flow diagram of a method performed by a wireless device for obtaining at least one AI / ML model associated to one functionality, from a node outside the mobile network in accordance with particular embodiments.

[0027] Figure 14 illustrates a logic flow diagram of a method performed by a communication device in accordance with particular embodiments.

[0028] Figure 15 illustrates a logic flow diagram of a method performed by a network node configured for use in a communication network in accordance with particular embodiments.

[0029] Figure 16 illustrates a logic flow diagram of a method performed by an external node that is external to a communication network in accordance with particular embodiments.

[0030] Figure 17 is a block diagram of a communication device according to some embodiments.

[0031] Figure 18 is a block diagram of a network node according to some embodiments.

[0032] Figure 19 is a block diagram of an external node according to some embodiments.

[0033] Figure 20 is a block diagram of a communication system in accordance with some embodiments.

[0034] Figure 21 is a block diagram of a user equipment according to some embodiments.

[0035] Figure 22 is a block diagram of a network node according to some embodiments.

[0036] Figure 23 is a block diagram of a host according to some embodiments. Figure 24 is a block diagram of a virtualization environment according to some embodiments.

[0037] Figure 25 is a block diagram of a host communicating via a network node with a UE over a partially wireless connection in accordance with some embodiments.

[0038] DETAILED DESCRIPTION

[0039] Figure 1 shows a communication network 10 according to some embodiments, e.g., in the form of a 5G or 6G network. The communication network 10 provides communication service to a communication device 12, e.g., a user equipment (UE). The communication network 10 includes one or more network nodes 14 in this regard.

[0040] External to the communication network 10 is an external node 16. The external node 16 may be external to the communication network 10 in the sense that the external node 16 does not belong to the communication network 10 and / or is not under the control or management of the communication network’s operator.

[0041] The external node 16 in embodiments herein stores artificial intelligence (Al) data 18. The Al data 18 may for instance include an Al model (e.g., a machine learning, ML, model) and / or data associated with the Al model, some of the model’s data, meta data, parameters, variables, etc. In this case, the external node 16 may itself have trained the Al model, or one or more network nodes 14 in the communication network 10 may have trained the Al model. Either way, the external node 16 stores the Al data 18.

[0042] In order to provide this Al data 18 to the communication device 12, e.g., for use by the communication device 12 in making an inference from that Al data 18, the external node 16 must transfer the Al data 18 to the communication device 12 via (or over) the communication network 10. In some embodiments, this transfer occurs Over-the-Top (OTT), in which case the external node 16 operates as an OTT server and the communication device 12 operates as an OTT client. Although such an OTT transfer may otherwise have been transparent to the communication network 10, some embodiments herein nonetheless inform the communication network 10 about and / or involve the communication network 10 in the transfer.

[0043] Indeed, according to some embodiments herein, the communication device 12 and / or the external node 16 communicate with the communication network 10 about the transfer of the Al data 18 from the external node 16 to the communication device 12 via the communication network 10. Such communication may be performed as part of, or for the purpose of, coordinating the transfer with the communication network 10 and / or informing the communication network 10 about the transfer. Alternatively or additionally, such communication may be performed as part of, or for the purpose of enabling the communication network 10 to exert control over whether, when, and / or how the Al data 18 is communicated over the communication network 10, or enabling the communication network 10 to exert control over whether, when, and / or how the transfer is performed. By providing such control to the communication network 10, some embodiments herein advantageously conserve network resources, address security risks, and / or improve sustainability as Al data transfers scale.

[0044] Some embodiments herein are applicable in the following context where the external node 16 may be exemplified as an OTT server, the communication device 12 may be exemplified as a wireless device (WD) or user equipment (UE), the communication network 10 may be exemplified as a 5G or 6G network, the Al data 18 may be exemplified as an Al model (e.g., an ML model), and the network node(s) 14 may be exemplified as including an access node in the radio access network (RAN) and a core network node in a core network (CN) of the communication network 10.

[0045] Some embodiments herein are based on and / or applicable to the AI / ML model life cycle management (LCM) for Al as depicted in Figure 2. See, e.g., TR 38.843 V1.0.0.

[0046] Data Collection 20 in Figure 2 is a stage that collects and provides input data (raw data or pre-processed data) for Model Training, Model inference, and (Model) Management. AI / ML algorithm specific data preparation (e.g., data ingestion and data refinement) is not carried out in the Data Collection 20 stage.

[0047] Model Training 22 is a process that uses featured data in terms of training datasets and validation datasets to train an AI / ML model.

[0048] Model inference 26 is a process of using a deployed AI / ML model to produce a set of outputs based on a set of featured inputs.

[0049] Management 24 is a function that oversees the operation (e.g., selection / (de)activation / switching / fallback) and monitoring of AI / ML models or AI / ML functionalities. This function is also responsible for making decisions to ensure the proper inference operation based on data received from the Data Collection function and the Inference function.

[0050] Model Storage 28 is a function responsible for storing trained / updated models that can be used to perform the inference process. The Model Storage function, if any, may be primarily intended as a reference point when applicable, for protocol terminations, model transfer / delivery, and related processes. It should be stressed that its purpose does not encompass restricting the actual storage locations of models.

[0051] Model Transfer / Delivery 29 is used to deliver an AI / ML model to the Inference function 26.

[0052] The AI / ML models for AI / ML, at least for the New Radio (NR) NR air interface, can be categorized into the following two types: One-side AI / ML model and Two-sided AI / ML model.

[0053] The one-side AI / ML model can be a UE-sided AI / ML model whose inference is performed entirely at the UE, or a NW-sided AI / ML model whose inference is performed entirely at the network (NW). For one-sided AI / ML model(s), the training part may either be performed in the same node or in another node. In the case it is performed in another node, there is a need for a model transfer functionality (which is one of the challenges addressed by some embodiments herein).

[0054] The two-sided AI / ML model refers to a paired AI / ML Model(s) over which joint inference is performed across the UE and the NW, i.e. , the first part of the inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa. Figure 3 shows an example use case of autoencoder (AE)-based two-sided CSI compression, where an encoder 30 (UE-part of the two-sided AE model) is operated at a UE to compress the estimated wireless channel, and the output of the encoder (the compressed wireless channel information estimates) is reported from the UE to a gNB. The gNB uses a decoder 32 (NW- part of the two-sided AE model) to reconstruct the estimated wireless channel information.

[0055] Generally, then, some embodiments facilitate augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead, e.g., for realizing some use cases explored in 3GPP TR 38.843 V1.0.0.

[0056] More particularly, some embodiments enable channel state information (CSI) feedback enhancement. Some embodiments for example facilitate spatial-frequency domain CSI compression using a two-sided Al model, e.g., encompassing all pre-processing / post- processing, quantization / de-quantization. Alternatively or additionally, some embodiments facilitate time-domain CSI prediction using a UE-sided model.

[0057] Considered AI / ML model training collaborations include the following. Type 1 includes Joint training of the two-sided model at a single side / entity, e.g., UE-sided or Network-sided. Type 2 encompasses joint training of the two-sided model at network side and UE side, respectively. Type 3 entails separate training at network side and UE side, where the UE-side CSI generation part and the network-side CSI reconstruction part are trained by UE side and network side, respectively. Note that joint training means the generation model and reconstruction model should be trained in the same loop for forward propagation and backward propagation. Joint training could be done both at a single node or across multiple nodes (e.g., through gradient exchange between nodes). Note, though, that separate training includes sequential training starting with UE side training, or sequential training starting with NW side training [or parallel training] at UE and NW.

[0058] Other embodiments herein alternatively or additionally facilitate beam management (BM). The following are selected as representative sub-use cases. BM-Case1 : Some embodiments facilitate spatial-domain downlink beam prediction for Set A of beams based on measurement results of Set B of beams. AI / ML model training and inference may be performed at the NW side or at the UE side. Alternatively or additionally, Set A and Set B may be different (i.e. , Set B is NOT a subset of Set A), or Set B may be a subset of Set A. Note here that Set A may be for downlink (DL) beam prediction and Set B may be for DL beam measurement. Alternatively or additionally, AI / ML model input may include: (i) only Layer 1 Reference Signal Received Power (L1-RSRP) measurement based on Set B; (ii) L1- RSRP measurement based on Set B and assistance information; (iii) channel impulse response (CIR) based on Set B; or (iv) L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID.

[0059] BM-Case2: Some embodiments facilitate temporal Downlink beam prediction for Set A of beams based on the historic measurement results of Set B of beams. AI / ML model training and inference may be performed at the NW side or at the UE side. Set A and Set B may be different (i.e., Set B is NOT a subset of Set A), Set B may be a subset of Set A (Set A and Set B are not the same), or Set A and Set B may be the same. AI / ML model input may include measurement results of K (K>1) latest measurement instances with the following alternatives: (i) only L1-RSRP measurement based on Set B; (ii) L1-RSRP measurement based on Set B and assistance information; or (iii) L1-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID. Alternatively or additionally, AI / ML model output may be based on F predictions for F future time instances, where each prediction is for each time instance, e.g., at least F=1.

[0060] Other embodiments herein alternatively or additionally facilitate positioning accuracy enhancements. The following are selected as representative sub-use cases. Some embodiments facilitate direct AI / ML positioning, where UE location is the AI / ML model output. Such direct AI / ML positioning may for example include fingerprinting based on channel observation as the input of AI / ML model. Other embodiments facilitate AI / ML assisted positioning, where the AI / ML model output may be a new measurement and / or enhancement of existing measurements. For example, such may include line of sight (LOS) I non-LOS (NLOS) identification, timing and / or angle of measurement, likelihood of measurement, etc.

[0061] More specifically, the following Cases are considered: (i) Case 1 includes UE-based positioning with UE-side model, direct AI / ML or AI / ML assisted positioning; (ii) Case 2a includes UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning; (iii) Case 2b includes UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning; (iv) Case 3a includes NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning; and (v) Case 3b includes NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning. When applying AI / ML on air interface use cases, different levels of collaboration between network nodes and UEs can be considered.

[0062] One level of collaboration is no collaboration between network nodes and UEs. In this case, a proprietary ML model operating with the existing standard air-interface is applied at one end of the communication chain (e.g., at the UE side), and the model life cycle management (e.g., model selection / training, model monitoring, model retraining, model update) is done at the same node without inter-node assistance (e.g., assistance information provided by the network node). For example, in UE-sided AI / ML models, inference is performed at the UE, and data collection and training might also be done at the UE when no collaboration is foreseen between the UE and a network entity.

[0063] Another level of collaboration is limited collaboration between network nodes and UEs for one-sided models. In this case, a ML model is operating at one end of the communication chain (e.g., at the UE side), but this node gets assistance from the node(s) at the other end of the communication chain (e.g., a next generation Node B (gNB)) for its Al model life cycle management to some extent (e.g., for training / retraining the Al model, model update, model monitoring, model selection / fallback / switching). For example, in UE-sided AI / ML models, inference is performed at the UE with data collection. However, the UE may need to transmit the collected data to a network node so that training is performed in that network node. After training is performed, the UE-side AI / ML model needs to be transferred to the UE.

[0064] A further level of collaboration is joint ML operation between network notes and UEs for two-sided models. In this case, it is assumed that the Al model is split with one part located at the network (NW) side and the other part located at the UE side. Hence, the Al model requires joint inference between the NW and UE, and the Al model life cycle management involves both ends of a communication chain. UE-side model training

[0065] Some embodiments herein are applicable for any of several methods for the UE-side model training. In one approach, the training of the UE-side model is performed at the UE itself, i.e., the UE performs data collection, and based on that the UE performs AI / ML model training, and once the model is trained, the UE performs the inference. However, this approach might be too complex in practice or possibly not feasible given the limited computational resources of the UE, and the large computational complexity that the training operation might imply. Also, if models are dependent on location and / or region, a single UE would not cover an entire coverage area, so that models the UE trains by itself would be limited to the areas the UE moves around, so that every time the UE enters a new area its trained AI / ML models could be outdated.

[0066] Hence, alternative approaches for training UE-sided models include the possibility that a network node, e.g., a radio access node like a gNB or a core network (CN) node (e.g. like the Network Data Analytics Function, NWDAF), receives data collected from UEs and train an AI / ML model that at some point should be delivered / transferred to that UE or other UEs which will then apply it, use it, re-configure it, etc. Further, an Over-the-Top (OTT) server, possibly outside the mobile network the UE is attached or connected to (e.g., outside the 3GPP domain), may be in charge of receiving data collected by the UE for performing the training. This OTT server could be for example a UE-vendor specific server, or Smartphone vendor specific server, or a third-party server. This latter approach might be a reasonable candidate to be adopted by the industry because in order to have optimal performances, the trained data set should fit the inference operations at the device which may depend on UE-vendor specific implementations (e.g., software / hardware properties / capabilities).

[0067] Solutions may be realized for transferring or delivering an AI / ML model to a UE from a 3GPP-based entity or other network node (e.g., RAN node, Core Network node). Embodiments herein by contrast focus on transferring an AI / ML model to a UE from a server (e.g., GAM or OTT server). From the Functional Framework in Figure 2 above, this could be the case when either a model is trained, stored and transferred towards the UE from the UE- side OTT server, or whether when the model is trained in another node (e.g., a 3GPP-based node like a RAN- or CN-node) and then stored in the UE-side OTT server to be later transferred towards the UE.

[0068] Particularly, transferring an AI / ML model from an OTT server to the UE may be applicable for CSI feedback enhancement, for beam management with a UE-side model, or for positioning accuracy enhancement with a UE-side model.

[0069] Some embodiments herein use the following terminology:

[0070] Al: Al refers to an entity that mimics human cognition in order to perform a task, e.g., and learn from it.

[0071] ML: Machine learning is a subset of Al that uses algorithms trained on data to produce adaptable models that can perform a task.

[0072] AI / ML Model: A data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. That may sometimes be simply called a “model”. An AI / ML model may more generally be referred to as an Al model, where an Al model may be an ML model as an example. An AI / ML model herein is an Al model that may or may not be an ML model.

[0073] AI / ML data: AI / ML data refers to any data associated with AI / ML. AI / ML data in some embodiments may comprise an AI / ML model or data associated therewith.

[0074] AI / ML model delivery: A generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note: An entity could mean a network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc. AI / ML model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs. These outputs may be, for example, “prediction(s)”.

[0075] AI / ML model testing: A subprocess of training, to evaluate the performance of a final AI / ML model using a 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.

[0076] AI / ML model training: A process to train an AI / ML Model [by learning the input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference.

[0077] AI / ML model transfer: Delivery of an AI / ML model over the air interface in a manner that is not transparent to 3GPP signalling, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model. That may also be called “model transfer”.

[0078] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0079] Data collection: 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.

[0080] Federated learning / federated training: 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.

[0081] Functionality identification: A process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Note: 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.

[0082] Model activation: enable an AI / ML model for a specific function.

[0083] Model deactivation: disable an AI / ML model for a specific function.

[0084] Model download: Model transfer from the network to UE.

[0085] Model identification: A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. Note: The process / method of model identification may or may not be applicable. Note: Information regarding the AI / ML model may be shared during model identification.

[0086] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.

[0087] Model parameter update: Process of updating the model parameters of a model. Model selection: The process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Note: Model selection may or may not be carried out simultaneously with model activation.

[0088] Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific function.

[0089] Model update: Process of updating the model parameters and / or model structure of a model.

[0090] Model upload: Model transfer from UE to the network.

[0091] Network-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the network.

[0092] Offline field data: The data collected from field and used for offline training of the AI / ML model.

[0093] Offline training: 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: This definition only serves as a 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.

[0094] Online field data: The data collected from field and used for online training of the AI / ML model.

[0095] Online training: 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: the notion of (near) real-time vs. non real-time is context-dependent and is relative to the inference time-scale. Note: This definition only serves as a guidance. 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: Fine-tuning / re-training may be done via online or offline training.

[0096] Reinforcement Learning (RL): A process of training an AI / ML model from input (a.k.a. state) and a feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.

[0097] Semi-supervised learning: A process of training a model with a mix of labelled data and unlabelled data.

[0098] Supervised learning: A process of training a model from input and its corresponding labels.

[0099] Two-sided (AI / ML) model: 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. UE-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the

[0100] UE.

[0101] Unsupervised learning: A process of training a model without labelled data.

[0102] Proprietary-format models: ML models of vendor- / device-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared. Note: An example is a device-specific binary executable format.

[0103] Open-format models: ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared.

[0104] In the case that a UE-side model is stored in a node outside the communication network (e.g., a UE-vendor specific server / OTT Server), some embodiments address a need to transfer the model (or other data associated with the model, e.g., some of the model’s data, meta data, parameters, variables, etc.) from this entity towards the UE for proper AIML-based feature functioning.

[0105] This can, in principle, be done in a transparent way to the network. According to existing approaches, though, neither the radio access network (RAN) nor the Core Network (CN) nodes have the capability to be aware of such operations or exert control over them, which might be relevant since this is tightly related to the control plane operation, e.g., an AI / ML model might not be considered by the network as normal payload which is downloaded from a server, like a movie from a streaming server..

[0106] Furthermore, without visibility into UE-side model transfer activities, network operators may encounter difficulties in optimizing their networks. They may lack the necessary data to make informed decisions about network configuration, resource allocation, or capacity planning.

[0107] Moreover, transferring AI / ML models from OTT servers to UEs can introduce security risks, including the case on which the OTT server is not a trusted entity, or the model itself could prove to be risky.

[0108] Lastly, with the potential increase in UEs downloading AI / ML models from OTT servers, scalability emerges as a concern especially when the AI / ML models are localized models and thus needing frequent model exchange with the OTT server. The network must efficiently handle the growing data traffic associated with such model transfers. Without proper control mechanisms, scalability may become a significant operational challenge.

[0109] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. Some embodiments herein include methods for a wireless device (WD), for a mobile network node (MNN), and for a first node (e.g., outside the mobile network).

[0110] The wireless device (WD) may correspond to a User Equipment (UE). The WD may also comprise an Over-the-Top (OTT) client. A Wireless Device (WD) in this context may be a general mobile terminal or a User Equipment (UE) performing one or more specified functionalities. Embodiments herein may similarly apply, however, to any type of communication device, whether wireless or wired, such that the WD herein may be generalized as a communication device 12. A UE-side model herein may therefore be generalized as a device-side model where the WD is a communication device 12.

[0111] The mobile network node (MNN) may correspond to a Radio Access Network (RAN) node or function, such as a gNB, or a 6G RAN node, or to a core network (CN) node, such as the User Plane Function (UPF), the Access and Mobility Function (AMF), etc.

[0112] The first node referred to herein is a node that transfers Al data (e.g., an Al model) to the WD. Using an Al model as an example of the Al data 18 transferred, the first node may or may not be the same node that trains the model or assists with training of the model. In one embodiment, though, the first node performs the UE-side model training. Either way, since the first node stores the model, the first node may determine the need to transfer a model to the WD, e.g., itself or based on signaling received from another node or the WD. The first node may be a node outside the mobile / 3GPP network, e.g., an OTT server, in which case it may exemplify the external node 16 in Figure 1. Or, the first node may be represented by a logical function within a 3GPP network node, e.g., an application layer function within a 3GPP network node. This first node may accordingly also be referred to as an application-layer node, a cloud node, a model source node, an Al data source node, an Al data storage node, or a model storage node. In embodiments where the first node is outside of the network, the first node may be referred to as an external node 16, i.e. , that is external to the network. Unless otherwise indicated, though, any embodiments herein described with the first node being outside of the network may also be applicable to the case where the first node is inside of the network.

[0113] The MNN may accordingly correspond to a MNN of a mobile network, such as a Public Land Mobile Network (PLMN), in which the UE is registered and / or connected to, while the node outside the mobile network may corresponds to an OTT server, e.g., on which AIML models are stored.

[0114] Note that a 3GPP network is used as an example herein, but embodiments herein may apply to any communication network, not just a 3GPP network. Moreover, some embodiments herein are exemplified with a mobile network or a cellular network, but embodiments herein are not so limited. Accordingly, the MNN herein may be generalized to simply network node (NN) in other embodiments. Further, some embodiments herein are exemplified where the access network of the communication network is a radio access network (RAN), but embodiments herein are applicable to any type of access network.

[0115] An indication as used herein may be conveyed by any type of signaling which has the effect of directly or indirectly indicating something to the signaling’s recipient.

[0116] Method in a WD

[0117] Some embodiments herein include a method at a WD.

[0118] As a first step to this method, the WD transmits a first indication to a MNN (e.g., a gNB), indicating the need for downloading (and / or updating) an AI / ML model, e.g., from a node outside the mobile network, such as an OTT server.

[0119] In a dependent step, the first indication may correspond to a request from the WD to a first network node, wherein the request is on whether the first node outside the mobile network is allowed or not to transfer the AI / ML model to the WD to be used for UE-side AI / ML- based inference, or an indication for informing the MNN that the process of model transfer has started or is about to start.

[0120] In a first dependent step, the WD sends the said first indication to the MNN (e.g., a gNB, or CN node) upon receiving the indication indicating that the first node outside the network (e.g., OTT server) needs to transfer an AI / ML model of at least one AI / ML functionality to be used for UE-side model AI / ML-based inference. In one option, the indication may be received by the UE in the WD from the higher layers, internally at the UE. In another option, the indication may be received by the UE in the WD from the OTT Client in the WD. In yet another option, the indication may be received by the UE in the WD from the OTT Client in the WD, wherein the OTT Client in the WD receives that indication (or an equivalent indication also indicating the need for downloading or updating an AI / ML model) from an OTT server.

[0121] As a second dependent step to the method, in response to the transmitted indication, the WD receives a first response from the MNN, such as: an acceptance indication, or a rejection indication, and / or preferred means (e.g., configuration, model transfer technique, indication of the point in time in which the transfer is allowed, etc.) for the first node outside the mobile network to use for transferring the model. In one option, in response to the acceptance indication the UE starts to download or upload the AI / ML model. In another option, in response to the acceptance indication the UE starts to download or upload the AI / ML model based on one or more parameters provided by the MNN with the acceptance indication. Examples of the one or more parameters may comprise a bearer configuration, security configuration, downlink channel configuration(s), etc. As a third dependent step to this method, the WD transmits a second response to the first node outside the mobile network (e.g., in an OTT message from the OTT client to the OTT server) wherein the second response may comprise one or more of the information included in the first response transmitted by the MNN. When the first node outside the mobile network determines that the transfer is accepted based on the MNN response, this node starts transferring the AI / ML model to be later used for UE-side AI / ML-based inference. In response to determining that the transfer is accepted, the first node outside the mobile network indicates to the MNN that a model transfer starts or it is about to start, and the first network node allocates the resources for the transfer.

[0122] As a fourth dependent step to this method, the WD receives a pause / stop / suspending indication from the MNN for an ongoing AI / ML model transfer for which the WD had previously received an acceptance indication for the model transfer request. When the WD receives the pause / stop indication, WD indicates the pause / stop for the model transferring procedure to the first node outside the mobile network. As a consequence, the first node outside the mobile network stops transferring the AI / ML model to the WD.

[0123] As a fifth dependent step to this method, the WD receives a resume indication from the MNN for an AI / ML model transfer for which the WD had previously received a pause / stop indication for the model transfer request. When the WD receives the resume indication, WD indicates the resume indication for the model transferring procedure to the first node outside the mobile network. As a consequence, the first node outside the mobile network resumes / starts transferring the AIML model to the WD.

[0124] As a sixth dependent step to this method, the WD receives a pause / stop indication from the first node outside the mobile network for an ongoing AI / ML model transfer for which the WD had previously received an acceptance indication for the model transfer from the MNN. When the WD receives the pause / stop indication, WD indicates the pause / stop for the model transferring procedure to the MNN. As a consequence, the MNN may revoke the configurations associated to the transferring the AI / ML model to the WD.

[0125] As a seventh dependent step to this method, the WD receives a resume indication from the first node outside the mobile network for an AI / ML model transfer for which the WD had previously received a pause / stop indication for the model transfer request. When the WD receives the resume indication, WD indicates the resume indication for the model transferring procedure to the MNN. As a consequence, the MNN may indicate the acceptance / rejection of the resume request for the transferring of the AI / ML model to the WD. As a dependent step, the WD receives an indication from a first node outside the mobile network (e.g., OTT server), indicating that the UE needs to receive an AI / ML model (or parameters associated to the AI / ML model, e.g., during model update) of at least one AI / ML functionality to be used for UE-side model AI / ML-based inference. The indication may be included in an OTT message received in OTT Client in the WD. method in the MNN node e.g. gNodeB

[0126] Some embodiments herein comprise a second method at a Mobile Network Node (MNN) to which a first node outside the mobile network transmits a first indication request from the first node outside the mobile network indicating the need to transfer an AI / ML model of at least one AI / ML functionality to be used for UE-side AI / ML-based inference.

[0127] As a first dependent step, the first indication request may correspond to a request from the first node outside the mobile network to the MNN, requesting whether the first node outside the mobile network is allowed or not to transfer the AI / ML model to a WD to be used for UE-side AI / ML-based inference, or an indication for informing the MNN that the process of model transfer towards a WD (or a set of WDs) has started or is about to start. In one method, the transmission of the first indication request from the first node may be in response to receiving indication from the WD that the WD is capable of initiating a model transfer procedure from the first node outside the mobile network to the WD. In one method, the first indication request comprises a first message transmitted by the first node outside the mobile network to a CN node and a second message transmitted by the CN node to the RAN node, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the first node outside the mobile network.

[0128] As a second dependent step, in response to the transmitted first indication request, the MNN transmitting a first response comprising any of: an acceptance indication, or a rejection indication, and / or preferred means (e.g., configuration, model transfer technique, indication of the point in time in which the transfer is allowed, etc.) for the first node outside the mobile network to use for transferring the model. When the first node outside the mobile network determines that the transfer is accepted based on the MNN response, this second node starts transferring the AI / ML model to be used for UE-side AI / ML-based inference. In one method, the MNN response comprises a first message transmitted by a RAN node to a CN node and a second message transmitted by the CN node to the first node outside the mobile network, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the RAN node. As a third dependent step, the method further comprises the first node outside the mobile network transferring the AI / ML model to the WD for UE-side AI / ML-based inference, wherein the download is performed via the MNN, i.e. , using one or more Downlink (DL) resources of the MNN, e.g., of a serving cell in which the UE is connected to and associated to the MNN.

[0129] As a fourth dependent step, while the first node outside the mobile network is performing the AI / ML model transfer for UE-side AI / ML-based inference to the WD (e.g., in response to the acceptance indication), the first node outside the mobile network transmits a first indication to the MNN that the first node outside the mobile network stops and / or pauses the model transfer to the WD, or alternatively an indication that the WD has stopped and / or paused the reception of information such a purpose. In one method, the first indication comprises a first message transmitted by the first node outside the mobile network to a CN node and a second message transmitted by the CN node to the RAN node, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the first node outside the mobile network.

[0130] As a fifth dependent step, after the first node outside the mobile network has started transferring the model to the WD (e.g., in response to the acceptance indication), the first node receives a first indication from the MNN to stop and / or pause the model transfer to the WD. In one method, the first indication from the MNN comprises a first message transmitted by a RAN node to a CN node and a second message transmitted by the CN node to the first node outside the mobile network, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the RAN node. In another method, the first indication from the MNN comprises a first message transmitted by the CN node to the first node outside the mobile network.

[0131] As a sixth dependent step, after the first node outside the mobile network has started performing the transferring of the AI / ML model (e.g., in response to the acceptance indication) to the WD, the first node outside the mobile network transmits a first indication to the MNN informing that the download of the model to the WD has been completed. In one method, the first indication comprises a first message transmitted by the first node outside the mobile network to a CN node and a second message transmitted by the CN node to the RAN node, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the first node outside the mobile network. As a seventh dependent step, after the first node outside the mobile network stopped or paused performing model transfer, the node outside the mobile network transmits a first indication to the MNN informing that the download of the model to be used for UE-side AI / ML- based inference training needs to be resumed and / or re-started and / or re-configured. In one method, the first indication comprises a first message transmitted by the first node outside the mobile network to a CN node and a second message transmitted by the CN node to the RAN node, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the first node outside the mobile network.

[0132] As an eight dependent step, the first node receives a first indication from the MNN to resume / restart the model transfer to the WD that was previously stopped. In one method, the first indication from the MNN comprises a first message transmitted by a RAN node to a CN node and a second message transmitted by the CN node to the first node outside the mobile network, wherein the second message may comprise one or more of the information indicated in the first message transmitted by the RAN node. In another method, the first indication from the MNN comprises a first message transmitted by the CN node to the first node outside the mobile network.

[0133] Some embodiments herein simply refer to “model transfer for UE side inference” instead of model transfer for AI / ML model inference of at least one AI / ML functionality for UE side inference.

[0134] As used herein, the term “download” is used to indicate the transfer of the model for UE side inference by the node outside the mobile network to the WD, while the term transmission is used to indicate the transmission of control plane and / or user plane data or information to the RAN.

[0135] Some embodiments herein provide methods allowing a wireless device (WD) to indicate to a Mobile Network Node (MNN) the need for downloading and / or updating a UE- side AI / ML model from a node outside the mobile network. Based on the indication, the MNN may control the AI / ML model transfer to the WD from an external node storing these models for UE-side AI / ML-based inference.

[0136] Certain embodiments may provide one or more of the following technical advantage(s). Some embodiments enable communication between the Over-the-Top (OTT) server and a Mobile Network Node (MNN) or the intended User Equipment (UE) presents an avenue for introducing awareness and network-based (e.g., 3GPP-based) control into what might otherwise be considered a “transparent” UE-side model transfer process. This approach serves one or more purposes. Firstly, it mitigates the risk of the UE receiving transferred models in situations where there are insufficient wireless downlink (DL) resources to support such transfers effectively, which may degrade the UE’s performance. In other words, the awareness that the UE needs to receive an AI / ML model improves the UE’s performance and the overall network performance.

[0137] Secondly, it empowers various network nodes, such as those within the RAN (e.g., gNB) or Core Network (CN), to provide the OTT server with preferred methods or configuration-related information to optimize the model transfer process.

[0138] Thirdly, it ensures that the model is transferred to the UE only when the UE possesses the necessary capabilities for “seamless” reception (or as close as possible to that), including some internal considerations (e.g., available storage space, etc.). Additionally, this approach potentially enhances network security by allowing the network to validate the legitimacy of the entity transferring the model (or even the model transfers process itself), reducing the risk of malicious data infiltration into the Mobile Network or UE. Moreover, it enables proactive network management and resource allocation, facilitating the seamless integration of AI / ML models into the network without compromising the quality of service for other essential applications.

[0139] Another advantage is that an AI / ML model transfer operation from an OTT server to the UE may prioritize Quality of Service (QoS) requirements. Without this, if the network has specific QoS parameters for different services running at the UE, the QoS criteria necessary for transferring the model may not align with these, leading to suboptimal performance for normal and critical services. That would be mitigated with some embodiments herein since QoS may be set properly for the model transfer operation, when the UE indicates the operation to the network.

[0140] Note that, in this disclosure, the terms “ML-model”, “Al-model” or “AI / ML model” are interchangeable. An AI / ML model can be defined as a functionality or be part of a functionality that is deployed / implemented in a first node, e.g., a User Equipment, in the case of a UE- sided model. An AI / ML model can be defined as a feature or part of a feature that is implemented / supported in a first node. This first node can indicate the feature version to a second node. If the ML-model is updated, the feature version may be changed by the first node.

[0141] An AI / ML-model may correspond to a function which receives one or more inputs (e.g., measurements, configuration(s)) and provide as outcome one or more prediction(s) / estimates of a certain type (e.g., time-domain and / or spatial domain predictions of beam measurements). In one example, an ML-model may correspond to a function receiving as input the measurement of a reference signal at time instance to (e.g., transmitted in beam-X) and provide as outcome the prediction of the reference signal in timer tO+T. In another example, an ML-model may correspond to a function receiving as input the measurement of a reference signal X (e.g., transmitted in beam-x), such as an Synchronization Signal Block (SSB) whose index is ‘x’, and provide as outcome the prediction of other reference signals transmitted in different beams e.g., reference signal Y (e.g., transmitted in beam-x), such as an SSB whose index is ‘x’. Another example is a ML model for aid in CSI estimation, in such a setup the ML-model will be a specific ML-model with a UE and an ML-model within the NW side. Jointly both ML-models provide joint network. The function of the ML-model at the UE would be to compress a channel input, and the function of the ML-model at the NW side would be to decompress the received output from the UE. It is further possible to apply something similar for positioning, wherein the input may be a channel impulse in some form related to a certain reference point (typically a TP (transmit point)) in time. The purpose on the NW side would be to detect different peaks within the impulse response, that reflects the multipath experienced by the radio signals arriving at the UE side. For positioning, another way is to input multiple sets of measurements into an ML network and based on that, derive an estimated position of the UE. Another ML-model would be an ML-model to be able to aid the UE in channel estimation or interference estimation for channel estimation. The channel estimation could for example be for the Physical Downlink Shared Channel (PDSCH) and be associated with specific set of reference signals patterns that are transmitted from the NW to the UE. The ML-model will then be part of the receiver chain within the UE and may not be directly visible within the reference signal pattern as such that is configured / scheduled to be used between the NW and UE. Another example of an ML-model for CSI estimation is to predict a suitable Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI), Rank Indicator (Rl), CRI (CSI-RS resource indicator) or similar value into the future.

[0142] Another way to describe an AI / ML model is as follows:

[0143] In terms of the time / frequency / spatial domain, the output of the AI / ML model may be in a different time instance, or at a different frequency location, or at a different spatial direction, or a combination of time / frequency / space, than those of the model input. In one example (time domain), an ML-model may correspond to a function receiving as input the measurement of a reference signal at time instance to (e.g., transmitted in beam-X) and provide as outcome the prediction of the reference signal in time instance tO+T. In another example (spatial domain), an ML-model may correspond to a function receiving as input the measurement of a reference signal X (e.g., transmitted in beam-x), such as an SSB whose index is ‘x’, and provide as outcome the estimation / prediction of the link quality of other reference signals transmitted in different beams e.g., reference signal Y (e.g., transmitted in beam-y).

[0144] In terms of model structure, the ML model may be fully contained within the UE, or split between the UE and network. One example of split structure is a ML model for aid in CSI estimation, where a possible setup of the ML-model is a split model, which comprises a specific sub- ML-model within a UE and a sub- ML-model within the NW side which collaborate to generate a desired outcome for the overall ML model. The function of the sub- ML-model at the UE would be to compress a channel input, and the function of the sub- ML-model at the NW side would be to decompress the received output from the UE. It is further possible to apply something similar for positioning, wherein the input may be a channel impulse in some form related to a certain reference point in time. The purpose on the NW side would be to detect different peaks within the impulse response, that correspond to different reception directions of radio signals at the UE side.

[0145] One example of ML contained within the UE is ML enhanced positioning, e.g., an ML model implemented in the UE takes as input multiple sets of measurements (each corresponding to a DL signal from a different network node), and based on that derive an estimated position of the UE.

[0146] In terms of utility for physical layer, the ML model can be used for many functions, including channel estimation, Line Of Sight LOS / Non-Line Of Sight NLOS classification, beam selection, position estimation of the UE, link adaption, etc. For example, an ML-model that is able to aid the UE in channel estimation which may or may not incorporate interference estimation. The channel estimation could for example be for the PDSCH and be associated with a specific set of reference signals patterns that are transmitted from the NW to the UE. The ML-model will then be part of the receiver chain within the UE and may not be directly visible within the reference signal pattern as such that is configured / scheduled to be used between the NW and UE. Another example of an ML-model for CSI estimation is to predict a suitable CQI, PMI, Rl, or similar value into the future. The future may be a certain number of slots after the UE has performed the last measurement or targeting a specific slot in time within the future.

[0147] According to the method the UE is connected to the network (e.g., it may receive and transmit data and / or control information) i.e. , in RRC_CONNECTED state, and, being configured to perform a specific function by using an AI / ML-model (which may be referred as an AI / ML-model functionality e.g., beam measurement predictions in time-domain). The specific functionality or function of an AI / ML model can for example be for one of the following examples, which could also be grouped to as a functionality area (one or more AI / ML-model functionality per area), as follows:

[0148] • CSI reporting o CSI compression o CSI enhancements

[0149] • Beam management (BM) o In one option there may be a BM functionality of an AI / ML-model(s), wherein an AI / ML model (e.g., at the UE) is capable of performing the inference of one or more time-domain predictions related to beam management. For example, the UE may be configured by the network to report (e.g., on Physical Uplink Control Channel (PUCCH) and / or Physical Uplink Shared Channel, PUSCH) one or more time-domain predictions of SSB and / or CSI-RS and / or PTRS measurements), e.g., by receiving a reporting configuration for AI / ML. o In one option, there may be a BM functionality of an AI / ML-model(s) wherein an AI / ML model (e.g., at the UE) is capable of performing the inference of one or more spatial-domain predictions related to beam management. o In one option, there may be a BM functionality of an AI / ML-model(s) wherein an AI / ML model (e.g., at the UE) is capable of performing the inference of both time and spatial-domain predictions related to beam management. o The UE is considered to be configured with an AI / ML functionality when at least one action related to that functionality is configured, e.g., the UE is configured to report predictions of beam measurement to one of its configured serving cell(s) and / or CSI(s) and / or SSB(s) of a serving cell.

[0150] • Radio Resource Management (RRM) measurement o Such as mobility measurement, i.e., RSRP, RSRQ, Reference Signal Strength Indicator (RSSI), but also aspects related to radio link failure e.g., Radio Link Failure (RLF) predictions. Further, RLM related timers (T310) and counters (N310 and N311) related predictions could also be considered here. o Such as the measurement framework defined in §5.5., 3GPP TS 38.331 V17.5.0 comprising how the UE perform measurements (e.g., measurement configuration), what triggers measurement reports (e.g., event-triggered reports, periodic reports), and content to be included in measurement reports).

[0151] • Link adaptation

[0152] • Hybrid Automatic Repeat reQuest (HARQ) transmission

[0153] • Data transmission

[0154] • Data reception • Power control

[0155] • Positioning of the UE

[0156] • Random access transmission

[0157] • Energy efficiency (e.g., Discontinuous Reception, DRX, settings)

[0158] • LTM (L1 / L2 triggered mobility) o dsds o Conditional handoverdsds

[0159] • L3 mobility I Reconfiguration with sync o dsds

[0160] A “UE side model” may correspond to an AI / ML model in which the UE performs the inference. The AI / ML model training for a UE side model may either be performed at the UE and / or outside the mobile network, such as in an Over the Top (OTT) server, e.g., managed by the UE manufacturer. The solutions presented in the context herein do not focus on the entity which performs the training, but on the OTT servers that can potentially store the AIML models. The UE-side model may also be generically referred to as a device-side model.

[0161] Methods for the Wireless Device

[0162] Figure 7 illustrates a logic flow diagram of a method performed by a wireless device in accordance with particular embodiments. The method performed by a wireless device comprises the following steps:

[0163] 1. Receiving in a first message an indication / request from a node outside the mobile network (OTT server) to transfer a UE-side model (Block 160).

[0164] 2. (Optionally) Determining whether the WD is capable of supporting a model transfer procedure based one or more of the following conditions (Block 710): a. No change of Radio Resource Control (RRC) state ongoing, e.g. UE transiting from connected mode to idle mode, UE transiting from connected mode to idle mode b. No RRC reconfiguration procedures ongoing, e.g. Multi-Radio Dual Connectivity (MR-DC) configuration ongoing (e.g., Primary Secondary Cell Group Cell, PSCell, addition / change / release procedure ongoing), RRC Reconfiguration with sync procedure ongoing c. Satisfactory channel conditions, e.g. latest RSRP level above certain threshold, time T310 or T312 not started, Secondary Cell Group (SCG) failure recovery procedure not ongoing, fast Master Cell Group (MCG) link recovery not ongoing d. Transmission for high priority traffic not ongoing 3. In response of determining that the WD is capable of supporting a model transfer procedure, transmitting indication in a second message to the MNN (e.g., gNB) on whether that UE-side model transfer can be downloaded or not (Block 720) a. In some embodiments, the MNN is a RAN node (e.g., Central Unit, CU) and the UE uses a RRC message to transmit the second message. b. In some embodiments, the MNN is a core network node and the UE uses the Non-Access Stratum (NAS) container to carry the second message.

[0165] 4. Determining whether the UE-side AI / ML model can be downloaded (model transfer accepted) or not (model transfer rejected) by the node outside the mobile network (OTT server) toward the UE (Block 730), in response of any of: a. Receiving indication from a MNN in a third message that the UE- side model can be transferred. In some embodiments, this third message may include a configuration for receiving the model and such a configuration could consist of one or more of: i. The configuration may comprise a radio bearer configuration (Signaling Radio Bearer, SRB, or Data Radio Bearer, DRB), a Packet Data Convergence Protocol (PDCP) configuration, a resource allocation configuration ii. The conditions upon which the model transfer may start. For example, the RAN node may indicate that if the UE prediction accuracy drops below a certain threshold a model transfer procedure is allowed to start.

[0166] In one embodiment, the third message is provided in dedicated RRC signaling to a specific UE. In another embodiment, the third message is provided in System Information Block (SIB) signalling to all UEs in the cell, wherein the SIB signalling may indicate an indication associated to a specific UE-vendor so that all UEs of that specific UE vendor for which the model transmission / download can start. For example, the absence of the second message in SIB signalling may indicate that no UEs, or no UEs of a specific UE vendor are allowed to dowload the UE-side AIML-based model. b. Determining that the UE-side model should be transmitted / downloaded, because of fulfillment of certain conditions, e.g. the conditions indicated in the third message 5. Transmitting an indication to the first entity (e.g., OTT server), in a fourth message, that the UE-side model can be transmitted or not transmitted, wherein the transmission of such message may be in response of receiving the third message from the RAN node indicating acceptance of the model transfer, or upon determining that the WD is capable or not capable of supporting the model transfer procedure (Block 740).

[0167] Examples of the above can be seen in Figure 4 and Figure 5.

[0168] Figure 4 shows an example of a method in which the UE is directly informed by the OTT server about information related to mode transfer and how the RAN node can handle / control the process.

[0169] Figure 5 shows an example of an alternative method in which the UE is directly informed by the OTT server about information related to mode transfer and how RAN / CN nodes can handle / control the process.

[0170] Methods for the first node outside the mobile network

[0171] Figure 8 illustrates a logic flow diagram of a method performed by a node storing UE- side models in accordance with particular embodiments.

[0172] A method performed by a node storing UE-side models (eventually also model training) and in charge of transferring the model to a UE, comprising:

[0173] • Determining that a new model needs to be transferred to a UE (Block 800) on the basis of one or more of the following: o Key Performance Indicators, KPIs, (e.g. prediction accuracy of the model in use by the UE, throughput) of associated to the AI / ML model at the UE for a functionality is dropping below a certain level o UE exiting the area or the network in which the model currently in use by the UE is valid o UE completed data collection for the UE-side model training, i.e. OTT server received new data samples on which the model to be transferred has been trained.

[0174] • Transmitting a first message to the UE or to the MN N that a new model transfer can be initiated by the OTT server (Block 810). In the case of the first message is being sent to the MNN, then the first node outside the mobile network indicates to the MNN which UE(s) is(are) the intended recipient(s) of this model. • Determining that a model transfer can start in response of receiving a second message from the UE or from the MN N that a model transfer procedure can be initiated to the UE(s) (Block 820).

[0175] • In response of determining that that a model transfer can start, initiating the model transfer (Block 830).

[0176] Methods for the Core Network node (MNN node)

[0177] Figure 9 illustrates a logic flow diagram of a method performed by a core network node in accordance with particular embodiments.

[0178] A method performed by a Core Network node comprising:

[0179] 1. Receiving in a first message an indication / request from the first node (e.g.

[0180] OTT server) for transmitting a model to the UE(s) (Block 900). This first message may contain one or more of the following information: a. The identity of the UE, comprising for example a vendor identity b. The release version of the said UE comprising for example, 3GPP release version, hardware or software release of the UE. c. The functionality-based information associated to this model transfer, e.g. if the model is for enabling AI / ML-based CSI prediction or AI / ML- based beam management, or AI / ML-based positioning, or AIML-based mobility at the UE d. The model-ID of the model being transferred e. The size, e.g. in MB, of the model to be delivered f. An estimation of the time needed to transfer the model g. The validity of the model, e.g. the geographical area in which the model is valid, the amount of time for which the model will be valid (e.g. on the basis of the current UE speed) h. The expected performance improvements of the model to be transferred, e.g. the expected accuracy of the AIML model to be transferred i. The reason for a model transfer delivery, e.g. KPI dropping below certain level, UE exing an area or a network in which the model currently in use by the UE is valid. j. Time elapsed since the last model transfer for this UE

[0181] 2. Determining whether the UE-side AIML model can be transmitted (model transfer accepted) or not transmitted (model transfer rejected) by the node outside the mobile network (e.g. OTT server) (Block 910), in response of any of: a. Receiving the information in the first message b. Receiving indication from a RAN node (e.g., gNB) that the UE-side model can be transferred c. Receiving indication from the UE that the UE-side model can be transferred d. Receiving indication from the first entity (OTT server) that the data collection for the UE-side model training can be transferred to the first entity e. Determining that a model transfer should be performed to the UE, because of fulfillment of certain conditions. For example, that the UE have already been using a certain model for a given amount of time, or that the UE is exiting the area in which the model currently used by the UE is valid. f. Determining that a (previously) stopped model transmission can be resumed.

[0182] 3. (unless already having determined the next action in a previous step...) Transmitting in a second message an indication / request to a RAN node (e.g., gNB) indicating that in a first message an entity outside the mobile network (OTT server) is informing / requesting to transmit a model to the UE(s) (Block 920), wherein the second message may comprise: a. A request to the gNB to establish a bearer / QoS flow to transfer the said model b. The QoS profile, 5QI, of the traffic associated to the model transfer c. One or more of the information included in the first message received by the first entity.

[0183] 4. In response of determining that the collected data transmission is accepted / rejected the Core Network Node transmits in a third message further information (Block 930): a. To the first entity (OTT server), where this can convey one or more of the following information: i. an accept / reject message, ii. In case more than one model transfer is requested by the first entity, an indication of the model-ID(s) of the model(s) for which the model transfer is accepted or rejected. Alternatively, in case of functionality-based AIML, the functionality (e.g. AIML-based CSI prediction or AIML-based beam management, or AIML-based positioning, or AIML-based mobility) of the models for which the model transfer is accepted or rejected iii. The point in time in which the external node is allowed to start the model transfer iv. The maximum duration of the model transfer upon which the external node should stop the model transfer procedure v. The maximum amount of data that can be transferred for this model transfer procedure. For example, if a model is of a larger size than what indicated in this message, the first entity may not start the model transfer procedure b. To the RAN node, with further instructions / guidance on how the model transfer will / can be carried, etc.

[0184] 5. Transmitting indication to the UE in a fourth message that model transfer will start (Block 940). This message can be transmitted via NAS signalling and comprise configuration information for the transfer of the model. The configuration can comprise one or more of the following information: a. The QoS profile of the traffic associated to the model transfer b. Bearer configuration c. The point in time in which the external node is allowed to start the model transfer d. The maximum duration of the model transfer upon which the external node should stop the model transfer procedure e. The maximum amount of data that can be transferred for this model transfer procedure. For example, if a model is of a larger size than what indicated in this message, the first entity may not start the model transfer procedure

[0185] An example of the above method can be seen in Figure 6.

[0186] Figure 10 illustrates a logic flow diagram of a method performed by a core network node in accordance with particular embodiments.

[0187] A method performed by a Core Network node comprising:

[0188] 1. Receiving in a first message an indication / request from a first entity outside 3GPP network (e.g. OTT server) to stop / pause the model transfer to the UE(s) (Block 1000). This first message may contain one or more of the following information: a. The functionality-based information associated to this model transfer, e.g. if the model is for enabling AIML-based CSI prediction or AIML- based beam management, or AIML-based positioning, or AIML-based mobility at the UE b. The model-1 D of the model being transferred c. If the indication is to pause the model transfer, for how long the model transfer is paused d. The cause of the stop / pause indication. For example in case of stop indication, the cause may be the completion of the model transfer procedure. Otherwise, the cause could be that the UE moves to an area in which the model transfer is not possible, or the UE does not have the capability to sustain a model transfer procedure (e.g. high priority traffic to prioritize, radio link failure or handover failure occurred at the UE, etc.)

[0189] 2. Transmitting in a second message an indication / request to a RAN node (e.g., gNB) to stop / pause the model transfer procedure the second message may comprise one or more of the information included in the first message (Block 1010)

[0190] 3. In response of determining that the collected data transmission is stopped / pause the Core Network Node may revoke the transport bearers allocated for the model transfer (Block 1020).

[0191] Figure 11 illustrates a logic flow diagram of a method performed by a core network node in accordance with particular embodiments.

[0192] A method performed by a Core Network node comprising:

[0193] 1. Receiving in a first message an indication / request from WD to start the model transfer (Block 1100). This first message signalled via NAS signalling that may contain one or more of the following information: a. The functionality-based information associated to this model transfer, e.g. if the model is for enabling AIML-based CSI prediction or AIML- based beam management, or AIML-based positioning, or AIML-based mobility at the UE b. The model-ID of the model being transferred c. The size, e.g. in MB, of the model to be delivered d. An estimation of the time needed to transfer the model e. The validity of the model, e.g. the geographical area in which the model is valid, the amount of time for which the model will be valid (e.g. on the basis of the current UE speed) f. The expected performance improvements of the model to be transferred, e.g. the expected accuracy of the AIML model to be transferred g. The reason for a model transfer delivery, e.g. KPI dropping below certain level, UE exing an area or a network in which the model currently in use by the UE is valid.

[0194] 2. Transmitting in a second message an indication / request to a RAN node (e.g., gNB) indicating that the WD is requesting to a model transfer (Block 1110), wherein the second message may comprise: a. An identity of the UE b. The identity of the UE, comprising for example a vendor identity c. The release version of the said UE comprising for example, 3GPP release version, hardware or software release of the UE. d. Time elapsed since the last model transfer for this UE e. The size, e.g. in MB, of the model to be delivered f. An estimation of the time needed to transfer the model g. A request to the gNB to establish a bearer / QoS flow to transfer the said model h. The QoS profile, 5QI, of the traffic associated to the model transfer i. One or more of the information included in the first message received by the first entity.

[0195] 3. Determining whether the UE-side AIML model can be transmitted (model transfer accepted) or not transmitted (model transfer rejected) by the node outside the mobile network (e.g. OTT server) (Block 1120), in response of any of: a. Receiving the information in the first message. For example, the CN node may determine that a model transfer should be performed to the UE, because of fulfillment of certain conditions. For example, that the UE have already been using a certain model for a given amount of time, or that the UE is exiting the area in which the model currently used by the UE is valid. b. Receiving indication from a RAN node (e.g., gNB) that the UE-side model can be transferred in response of the second message c. Determining that a (previously) stopped model transmission can be resumed.

[0196] 4. In response of determining that the collected data transmission is accepted / rejected the Core Network Node transmits in a third message to the WD further information (Block 1130). This third message signalled via NAS signalling that may comprise one or more of the following information: a. an accept / reject message, b. The QoS profile of the traffic associated to the model transfer c. Bearer configuration d. The point in time in which the external node is allowed to start the model transfer e. The maximum duration of the model transfer upon which the external node should stop the model transfer procedure f. The maximum amount of data that can be transferred for this model transfer procedure. For example, if a model is of a larger size than what indicated in this message, the first entity may not start the model transfer procedure

[0197] Methods for the RAN node (MNN node)

[0198] Figure 12 illustrates a logic flow diagram of a method performed by a RAN node in accordance with particular embodiments.

[0199] A method performed by a RAN node comprising:

[0200] 1. Receiving in a first message an indication / request from a Core Network node or a UE, related to information linked to a UE-side model transfer from a node outside the mobile network (OTT server) (Block 1200).

[0201] 2. Determining whether the UE-side AIML model can be transmitted (model transfer accepted) or not transmitted (model transfer rejected) by the node outside the mobile network (OTT server) (Block 1210), in response of any of: a. Receiving indication from the UE that the UE-side model can be transferred as per methods of the wireless device b. Receiving indication from a Core Network node that the UE-side model can be transferred. This indication may indicate the QoS flow including the 5QI to which the model transmission should be associated. c. Determining that the UE-side model should be transmitted to the UE, because of fulfillment of certain conditions. For example, the network may need to establish a high priority bearer that the UE should prioritize over the model transfer. Or the UE is handed-over to a cell or gNB not supporting the transmission of the model or for which the model transmission is not allowed given for example the lack of radio resources or congestion. d. Determining that the (new) model is needed in the UE. For example, if after a certain amount the UE has been using the same (outdated) model. e. Determining that a stopped model transmission can be resumed. For example, if the cell load conditions change, or if QoS requirements for the transmission of the AIML model can be guaranteed, the gNB may determine that the OTT server can resume the transmission of the UE-side AIML model.

[0202] And wherein the decision on whether the UE-side model can be transmitted or not transmitted may depend on one or more of the following conditions: a. Admission control policies. For example, if the network determines overload in the cell, lack of radio resources, the gNB may reject the AIML model transmission. b. QoS conditions. For example, if the model cannot be transmitted with the desired QoS (e.g. the gNB cannot guarantee the requirement of a certain 5QI to which the transmission of the model is associated to), the gNB may reject the model transmission c. Current UE configuration. For example, if the UE is configured with a high priority DRB, the gNB may reject the AIML model transmission

[0203] 3. In response of determining that the UE-side model transmission is accepted, the gNB determining the configuration to provide to the UE for its reception (Block 1220), e.g.: a. Establishing a new bearer configuration (SRB or DRB) b. Allocating radio resources

[0204] 4. Transmitting indication in a first message (Block 1230): a. To the Core Network node that UE-side model transfer can be transmitted or not transmitted by the node outside the mobile network (OTT server), and wherein the first message may contain, if the model can be transmitted, the determined methods or configuration for the wireless device to be able to receive the UE-side model. b. To the Wireless Device / UE that UE-side model transfer can be transmitted or not transmitted by the node outside the mobile network (OTT server), and wherein the first message may contain, if the collected data can be transmitted the determined methods or configuration for the wireless device to be able to receive the UE-side model.

[0205] The first message may further comprise any of the following information:

[0206] • In one embodiment the first message may be also to resume the transmission of a previously started and then stopped transmission of AIM L model(s).

[0207] • In one embodiment the first message may also include one ore more indications of the one or more specific model(s) for which the transmission can start / be resumed, i.e. the model IDs.

[0208] • In one embodiment, the first message includes an indication of the point in time in which the transmission of the UE-side AIML model can start.

[0209] In a separate embodiment, transmitting indication in a second message to the wireless device or to the Core Network node that a started UE-side AI / ML model transmission from a node outside the mobile network has to be stopped. This indication may comprise the release of the bearer previously configured for the transmission of the model. The decision to stop the transmission of the model may depend on admission control or traffic pre-emption policies. For example, the network may determine higher priority traffic to serve in the cell, and shortage of radio resources. The decision may also depend on configuring the UE to perform handover to a second RAN network node for which the transmission of the model is not possible (e.g., overload in the second RAN network node, or second RAN node not capable of supporting the transmission of the UE-side AI / ML model).

[0210] In case the transmission of the UE-side AI / ML model can be resumed, the network may indicate to the UE or to the Core Network node to stop the transmission without clearing the already stored / transferred information / data. The network may further indicate for how long the model transmission is stopped, or the point in time, e.g., absolute or relative time stamp, in which the transmission can be resumed.

[0211] Extension of the method to the RAN split architecture

[0212] In a RAN split architecture (comprising a central unit (CU) and at least one distributed unit (DU)), if the model transfer operation happens in large scale (e.g., multiple UEs at the same time) might lead to an overload situation at the DU serving the cells involved in the model transfer procedure. In such scenario a coordination between the CU and the DU is required to control the overload situation caused by the OTT model transfer mechanism.

[0213] In split RAN architecture, a method performed by the CU, sending an indication to the DU indicating the start of the model transfer operation by the OTT server upon starting the model transfer by the OTT server. In split RAN architecture, a method performed by the DU, sending an indication to the CU indicating the stop / pause request of the model transfer operation by the OTT server upon starting detecting overload situation at the DU. Determining the overload situation might be done by using proprietary implementations e.g., based on the DU temperature or based on the amount of the allocated radio resources in the cells involved in the model transfer operations or it can be done based on existing metrics like composite available capacity measured per cell or per beam.

[0214] In another embodiment, the DU may send start / resume indication to the CU if the overload situation at the DU is resolved / canceled.

[0215] The CU, in response to receiving the stop / pause indication from the DU, may request the core network or the over the top server to stop / pause the model transfer operations.

[0216] Embodiments related to the contents of various messages.

[0217] As mentioned above in the method performed by the WD, a first indication was a first step to this second method, the WD forwards the first indication request to a MNN (e.g., a gNB), where the indication may correspond to a request on whether the first node outside the mobile network is allowed or not to transfer the AI / ML model to the WD to be used for UE-side AI / ML- based inference, or an indication for informing the MNN that the process of model transfer has started or is about to start. Such a first indication could consist of one or more of the following:

[0218] 1. An indication indicating the need for the transfer of an AI / ML model from the OTT server to the WD.

[0219] 2. An indication of the functionality for which the associated AIML model is to be used.

[0220] 3. An indication of the size of the AIML model that needs to be transferred from the OTT server to the WD.

[0221] 4. An indication of the identity of the AIML model that needs to be transferred from the OTT server to the WD.

[0222] 5. An indication of the expected performance indicators of the AIML model that needs to be transferred from the OTT server to the WD.

[0223] 6. An indication of the inputs parameters that needs be made available from the MNN to enable the inference of the AIML model to be transferred. For example, such a list of input parameters could be in terms of the expected periodicity of a reference signal that the MNN shall transmit to enable the inference of the AIML model that needs to be transferred. As mentioned above in the method performed by the WD, in response to the transmitted indication, the WD receives a first response from the MNN, such as: an acceptance indication, or a rejection indication, and / or preferred means (e.g., configuration, model transfer technique, indication of the point in time in which the transfer is allowed, etc.) for the first node outside the mobile network to use for transferring the model. Such an indication could consist of one or more of the following:

[0224] 1. An indication whether the request for the AIML model transfer has been accepted or not.

[0225] 2. An indication of the time duration for which the said acceptance / rejection is valid. The WD shall assume that the indicated acceptance / rejection decision is valid for the duration mentioned in the indication. After the expiry of such a time duration, the WD can retransmit the request to get acceptance from the MNN for the AIML model transfer.

[0226] 3. An indication of the point in time when the WD can initiate the AIML model transfer from the OTT server.

[0227] 4. An indication of the radio condition under which the WD is allowed to initiate the AIML model transfer. Such a radio condition could be in terms of the serving cell being above a certain RSRP threshold or RSRQ threshold or SI NR threshold etc.

[0228] Note that although some embodiments herein were exemplified with respect to transfer of the AI / ML model, the embodiments herein are extendable to the transfer of a part of the model or the transfer of any data that defines, governs, or is otherwise associated with the model. Some embodiments for example are extendable to the transfer of some of the model’s data, meta data, parameters, variables, etc. Some embodiments are accordingly extendable to the transfer of any AI / ML data as defined herein.

[0229] Figure 13 illustrates a logic flow diagram of a method performed by a wireless device for obtaining at least one AI / ML model associated to one functionality, from a node outside the mobile network in accordance with particular embodiments. The method comprises determining that a download an AI / ML model and / or to update a stored AI / ML model is needed (Block 1300). The method also comprises transmitting a first indication to a Mobile Network Node (MNN) that a download an AI / ML model and / or to update a stored AI / ML model is needed (Block 1310).

[0230] In some embodiments, the first indication which the UE transmits may correspond to a request to a first network node. In some embodiments, the request is on whether the first node outside the mobile network is allowed or not to transfer the AIML model to the WD to be used for UE-side AIML-based inference, or an indication for informing the MNN that the process of model transfer has started or is about to start. In some embodiments, the first indication is transmitted by the WD in response to the reception by the UE of a previous indication indicating that the first node outside the mobile network (e.g., OTT server) needs to transfer an AIML model of at least one AI / ML functionality to be used for UE-side model AIML-based inference. In some embodiments, the indication from the first network node outside the mobile network is received by a User Equipment (UE) in the WD from the higher layers, or from an OTT Client in the WD.

[0231] In some embodiments, the method further comprises, in response to the transmitted first indication, the WD receiving a first response from the MNN (Block 1320). In some embodiments, the first response may correspond to one or more of: an acceptance indication, or a rejection indication, and / or preferred means (e.g., configuration, model transfer technique, indication of the point in time in which the transfer is allowed, etc.) for the first node outside the mobile network to use for transferring the model.

[0232] In view of the modifications and variations herein, Figure 14 illustrates a logic flow diagram of a method performed by a communication device 12 in accordance with particular embodiments. The method comprises communicating with a communication network 10 about a transfer of artificial intelligence, Al, data 18 from an external node 16 to the communication device 12 via the communication network 10 (Block 1400). In some embodiments, the external node 16 is external to the communication network 10.

[0233] In some embodiments, said communicating is performed as part of, or for the purpose of at least coordinating the transfer with the communication network 10. In other embodiments, said communicating is performed as part of, or for the purpose of at least informing the communication network 10 about the transfer. In yet other embodiments, said communicating is performed as part of, or for the purpose of at least informing the communication network 10 about the transfer being from an external node 16 that is external to the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of at least requesting permission from the communication network 10 for the external node 16 to perform the transfer. In still yet other embodiments, said communicating is performed as part of, or for the purpose of at least enabling the communication network 10 to exert control over whether, when, and / or how the Al data 18 is communicated over the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of at least enabling the communication network 10 to exert control over whether, when, and / or how the transfer is performed. In still yet other embodiments, said communicating is performed as part of, or for the purpose of at least enabling the communication network 10 to exert control over a security of the transfer and / or a security of the Al data 18.

[0234] In some embodiments, said communicating comprises transmitting and / or receiving signaling between the communication device 12 and the communication network 10. In some embodiments, the signaling is about the transfer of Al data 18 from the external node 16 to the communication device 12.

[0235] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating a request or need for the transfer of Al data 18 from the external node 16 to the communication device 12.

[0236] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 informing the communication network 10 about the transfer.

[0237] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a need for the transfer. In other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a functionality for which the Al data 18 is to be used by the communication device 12. In yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a size of the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least an estimated time duration, or a minimum estimated time duration, of the transfer. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a geographical area in which the Al data 18 is valid or a time duration for which the Al data 18 will be valid. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least an identity associated with the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least information about an expected performance of the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a reason for the transfer. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least one or more input parameters that need to be made available from the communication network 10 to enable an inference by the communication device 12 from the Al data 18. In some embodiments, said signaling is conveyed in Message B. In some embodiments, said signaling is transmitted to an access node in the communication network 10.

[0238] In some embodiments, said communicating comprises receiving signaling from the communication network 10 indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network 10. In some embodiments, the received signaling indicates how the transfer is, or is allowed, to be performed via the communication network 10, in terms of a configuration for the transfer. In some embodiments, the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration. In some embodiments, the signaling indicates at least whether a request by the communication device 12 for the transfer has been accepted. In other embodiments, the signaling indicates at least a time duration for which acceptance or rejection of a request by the communication device 12 for the transfer is valid. In yet other embodiments, the signaling indicates at least a point in time when the communication device 12 is allowed to initiate the transfer. In still yet other embodiments, the signaling indicates at least a radio condition under which the communication device 12 is allowed to initiate the transfer. In still yet other embodiments, the signaling indicates at least a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data 18 for the transfer. In still yet other embodiments, the signaling indicates at least a maximum allowed data size of the transfer. In still yet other embodiments, the signaling indicates at least a maximum allowed duration of the transfer. In some embodiments, said received signaling is conveyed in Message C. In some embodiments, the received signaling is received from an access node of the communication network 10 and / or via access stratum, AS, signaling. In some embodiments, the received signaling is received from a core network node of the communication network 10 and / or via non-access stratum, NAS, signaling. In some embodiments, the method further comprises propagating at least some of the signaling received from the communication network 10 to the external node 16 (Block 1410). In some embodiments, at least some of the signaling is propagated to the external node 16 via Message D.

[0239] In some embodiments, the external node 16 acts as an over-the-top, OTT, server. In some embodiments, the communication device 12 acts as an OTT client, and the transfer is an OTT transfer of the Al data 18 from the OTT server to the OTT client via the communication network 10.

[0240] In some embodiments, the Al data 18 comprises an Al model or data associated therewith. In some embodiments, the Al model is a trained Al model. In some embodiments, the Al model is a device-side Al model.

[0241] In some embodiments, the method also comprises, based on the communicating with the communication network 10, receiving the Al data 18 as transferred from the external node 16 to the communication device 12 via the communication network 10 (Block 1410).

[0242] In some embodiments, the method further comprises, after the transfer, by the communication device 12, making an inference from the Al data 18 (Block 1420).

[0243] In some embodiments, the Al data 18 is specific to a type and / or vendor of the communication device 12.

[0244] In some embodiments, the external node 16 is specific to a vendor of the communication device 12. In some embodiments, the transfer is an application layer transfer at an application layer of the communication device 12.

[0245] In some embodiments, the method further comprises using the Al data 18, or an inference made by the communication device 12 from the Al data 18, to perform one or more functions for operating in the communication network 10 (Block 1430).

[0246] In some embodiments, the communication device 12 is a wireless device, WD, wherein the communication network 10 is a mobile network, and wherein the external node 16 is a first node outside of the mobile network.

[0247] Figure 15 illustrates a logic flow diagram of a method performed by a network node 14 configured for use in a communication network 10 in accordance with particular embodiments. The method comprises communicating with a communication device 12 and / or an external node 16 about a transfer of artificial intelligence, Al, data 18 from the external node 16 to the communication device 12 via the communication network 10 (Block 1500). In some embodiments, the external node 16 is external to the communication network 10.

[0248] In some embodiments, said communicating is performed as part of, or for the purpose of, at least coordinating the transfer with the communication device 12 and / or the external node 16. In other embodiments, said communicating is performed as part of, or for the purpose of, at least the communication device 12 and / or the external node 16 informing the communication network 10 about the transfer. In yet other embodiments, said communicating is performed as part of, or for the purpose of, at least the communication device 12 and / or the external node 16 informing the communication network 10 about the transfer being from an external node 16 that is external to the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least the communication device 12 and / or the external node 16 requesting permission from the communication network 10 for the external node 16 to perform the transfer. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over whether, when, and / or how the Al data 18 is communicated over the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over whether, when, and / or how the transfer is performed. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over a security of the transfer and / or a security of the Al data 18.

[0249] In some embodiments, said communicating comprises transmitting and / or receiving signaling between the communication device 12 and the communication network 10, and / or between the external node 16 and the communication network 10. In some embodiments, the signaling is about the transfer of Al data 18 from the external node 16 to the communication device 12.

[0250] In some embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating a request or need for the transfer of Al data 18 from the external node 16 to the communication device 12.

[0251] In some embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 informing the communication network 10 about the transfer.

[0252] In some embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a need or request for the transfer. In other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a functionality for which the Al data 18 is to be used by the communication device 12. In yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a size of the Al data 18. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least an estimated time duration, or a minimum estimated time duration, of the transfer. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a geographical area in which the Al data 18 is valid or a time duration for which the Al data 18 will be valid. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least an identity associated with the Al data 18. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least information about an expected performance of the Al data 18. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least a reason for the transfer. In still yet other embodiments, said communicating comprises receiving signaling from the communication device 12 and / or the external node 16 indicating at least one or more input parameters that need to be made available from the communication network 10 to enable an inference by the communication device 12 from the Al data 18. In some embodiments, said signaling is received from the communication device 12 in Message B, or from the external node 16 in Message A. In some embodiments, the network node 14 is an access node in the communication network 10. In some embodiments, said communicating comprises transmitting signaling from the communication network 10 to the communication device 12 and / or the external node 16 indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network 10. In some embodiments, the transmitted signaling indicates how the transfer is, or is allowed, to be performed via the communication network 10, in terms of a configuration for the transfer. In some embodiments, the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration. In some embodiments, the transmitted signaling indicates at least whether a request by the communication device 12 and / or the external node 16 for the transfer has been accepted. In other embodiments, the transmitted signaling indicates at least a time duration for which acceptance or rejection of a request for the transfer is valid. In yet other embodiments, the transmitted signaling indicates at least a point in time when the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, the transmitted signaling indicates at least a radio condition under which the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, the transmitted signaling indicates at least a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data 18 for the transfer. In still yet other embodiments, the transmitted signaling indicates at least a maximum allowed data size of the transfer. In still yet other embodiments, the transmitted signaling indicates at least a maximum allowed duration of the transfer. In some embodiments, said transmitted signaling is transmitted to the communication device 12 in Message C, or to the external node 16 in Message D. In some embodiments, the transmitted signaling is access stratum, AS, signaling, and / or the network node 14 is an access node in the communication network 10. In some embodiments, the transmitted signaling is non-access stratum, NAS, signaling, and / or the network node 14 is a core network node. In some embodiments, the method further comprises receiving at least some of the signaling from the communication device 12 and wherein transmitting the signaling comprises transmitting the signaling to the external node 16 in order to propagate at least some of the signaling from the communication device 12 to the external node 16 (Block 1510).

[0253] In some embodiments, the external node 16 acts as an over-the-top, OTT, server. In some embodiments, the communication device 12 acts as an OTT client, and the transfer is an OTT transfer of the Al data 18 from the OTT server to the OTT client via the communication network 10.

[0254] In some embodiments, the Al data 18 comprises an Al model or data associated therewith. In some embodiments, the Al model is a trained Al model. In some embodiments, the Al model is a device-side Al model. In some embodiments, the Al data 18 is specific to a type and / or vendor of the communication device 12.

[0255] In some embodiments, the external node 16 is specific to a vendor of the communication device 12.

[0256] In some embodiments, the transfer is an application layer transfer at an application layer of the communication device 12.

[0257] In some embodiments, the method further comprises, based on said communicating, one or more of controlling whether, when, and / or how the Al data 18 is communicated over the communication network 10, controlling whether, when, and / or how the transfer is performed, or controlling or evaluating a security of the transfer and / or a security of the Al data 18 (Block 1520).

[0258] In some embodiments, the method further comprises, based on said communicating, deciding whether and / or when the transfer is allowed. In other embodiments, the method further comprises, based on said communicating, alternatively or additionally validating a legitimacy of the external node 16 and / or of the Al data 18. In yet other embodiments, the method further comprises, based on said communicating, alternatively or additionally allocating resources in the communication network 10 for the transfer. In still yet other embodiments, the method further comprises, based on said communicating, alternatively or additionally setting a quality of service, QoS, in the communication network 10 for the transfer. In still yet other embodiments, the method further comprises, based on said communicating, alternatively or additionally performing network configuration, resource allocation, and / or capacity planning.

[0259] In some embodiments, the method further comprises, based on said communicating with the communication device 12 and / or the external node 16, communicating with one or more other network nodes in the communication network 10 about the transfer (Block 1530).

[0260] In some embodiments, the network node 14 is an access node in an access network of the communication network 10. In some embodiments, the method further comprises communicating with a core network node in a core network of the communication network 10 about the transfer (Block 1540). In some embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least whether a request by the communication device 12 and / or the external node 16 for the transfer has been accepted. In other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a time duration for which acceptance or rejection of a request for the transfer is valid. In yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a point in time when the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a radio condition under which the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data 18 for the transfer. In still yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a maximum allowed data size of the transfer. In still yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a maximum allowed duration of the transfer. In still yet other embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating at least a configuration for the transfer. In some embodiments, communicating with the core network node comprises transmitting signaling to the core network node indicating whether, when, and / or how the transfer is to be performed or is allowed to be performed. In some embodiments, the signaling is transmitted in Message C.

[0261] In some embodiments, the network node 14 is a core network node in a core network of the communication network 10. In some embodiments, the method further comprises communicating with an access node in an access network of the communication network 10 about the transfer (Block 1550). In some embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a need or request for the transfer. In other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a functionality for which the Al data 18 is to be used by the communication device 12. In yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a size of the Al data 18. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least an estimated time duration, or a minimum estimated time duration, of the transfer. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a geographical area in which the Al data 18 is valid or a time duration for which the Al data 18 will be valid. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least an identity associated with the Al data 18. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least information about an expected performance of the Al data 18. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least a reason for the transfer. In still yet other embodiments, communicating with the access node comprises transmitting signaling to the access node indicating at least one or more input parameters that need to be made available from the communication network 10 to enable an inference by the communication device 12 from the Al data 18. In some embodiments, the signaling is transmitted in Message B. In some embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least whether a request by the communication device 12 and / or the external node 16 for the transfer has been accepted. In other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a time duration for which acceptance or rejection of a request for the transfer is valid. In yet other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a point in time when the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In yet other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a radio condition under which the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In yet other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data 18 for the transfer. In yet other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a maximum allowed data size of the transfer. In yet other embodiments, communicating with the access node comprises receiving signaling from the access node indicating at least a maximum allowed duration of the transfer. In some embodiments, communicating with the access node comprises receiving signaling from the access node indicating whether, when, and / or how the transfer is to be performed or is allowed to be performed. In some embodiments, the signaling is received in Message C.

[0262] In some embodiments, the communication device 12 is a wireless device, WD, wherein the communication network 10 is a mobile network, and wherein the external node 16 is a first node outside of the mobile network.

[0263] Figure 16 illustrates a logic flow diagram of a method performed by an external node 16 that is external to a communication network 10 in accordance with particular embodiments. The method comprises communicating with the communication network 10 about a transfer of artificial intelligence, Al, data 18 from the external node 16 to a communication device 12 via the communication network 10 (Block 1600).

[0264] In some embodiments, said communicating is performed as part of, or for the purpose of, at least coordinating the transfer with the communication network 10. In other embodiments, said communicating is performed as part of, or for the purpose of, at least informing the communication network 10 about the transfer. In yet other embodiments, said communicating is performed as part of, or for the purpose of, at least informing the communication network 10 about the transfer being from an external node 16 that is external to the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least requesting permission from the communication network 10 for the external node 16 to perform the transfer. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over whether, when, and / or how the Al data 18 is communicated over the communication network 10. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over whether, when, and / or how the transfer is performed. In still yet other embodiments, said communicating is performed as part of, or for the purpose of, at least enabling the communication network 10 to exert control over a security of the transfer and / or a security of the Al data 18.

[0265] In some embodiments, communicating comprises transmitting and / or receiving signaling between the external node 16 and the communication network 10. In some embodiments, the signaling is about the transfer of Al data 18 from the external node 16 to the communication device 12.

[0266] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating a request or need for the transfer of Al data 18 from the external node 16 to the communication device 12.

[0267] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 informing the communication network 10 about the transfer.

[0268] In some embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a need for the transfer. In other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a functionality for which the Al data 18 is to be used by the communication device 12. In yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a size of the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least an estimated time duration, or a minimum estimated time duration, of the transfer. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a geographical area in which the Al data 18 is valid or a time duration for which the Al data 18 will be valid. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least an identity associated with the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least information about an expected performance of the Al data 18. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least a reason for the transfer. In still yet other embodiments, said communicating comprises transmitting signaling to the communication network 10 indicating at least one or more input parameters that need to be made available from the communication network 10 to enable an inference by the communication device 12 from the Al data 18. In some embodiments, said signaling is conveyed in Message A. In some embodiments, said signaling is transmitted to a core network node in a core network of the communication network 10.

[0269] In some embodiments, said communicating comprises receiving signaling from the communication network 10 indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network 10. In some embodiments, the received signaling indicates how the transfer is, or is allowed, to be performed via the communication network 10, in terms of a configuration for the transfer. In some embodiments, the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration. In some embodiments, the signaling indicates at least whether a request by the external node 16 and / or the communication device 12 for the transfer has been accepted. In other embodiments, the signaling indicates at least a time duration for which acceptance or rejection of a request by the communication device 12 and / or the external node 16 for the transfer is valid. In yet other embodiments, the signaling indicates at least a point in time when the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, the signaling indicates at least a radio condition under which the communication device 12 and / or the external node 16 is allowed to initiate the transfer. In still yet other embodiments, the signaling indicates at least a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data 18 for the transfer. In still yet other embodiments, the signaling indicates at least a maximum allowed data size of the transfer. In still yet other embodiments, the signaling indicates at least a maximum allowed duration of the transfer. In some embodiments, said received signaling is conveyed in Message D. In some embodiments, the received signaling is received from a core network node of the communication network 10.

[0270] In some embodiments, the external node 16 acts as an over-the-top, OTT, server. In some embodiments, the communication device 12 acts as an OTT client, and the transfer is an OTT transfer of the Al data 18 from the OTT server to the OTT client via the communication network 10.

[0271] In some embodiments, the Al data 18 comprises an Al model or data associated therewith. In some embodiments, the Al model is a trained Al model. In some embodiments, the Al model is a device-side Al model. In some embodiments, the method further comprises, before the transfer, training the Al model and / or storing the Al model (Block 1610).

[0272] In some embodiments, the Al data 18 is specific to a type and / or vendor of the communication device 12.

[0273] In some embodiments, the external node 16 is specific to a vendor of the communication device 12.

[0274] In some embodiments, the transfer is an application layer transfer at an application layer of the communication device 12.

[0275] In some embodiments, the communication device 12 is a wireless device, WD. In some embodiments, the communication network 10 is a mobile network, and the external node 16 is a first node outside of the mobile network.

[0276] In some embodiments, the method also comprises, based on the communicating with the communication network 10, performing the transfer of the Al data 18 from the external node 16 to the communication device 12 via the communication network 10.

[0277] Embodiments herein also include corresponding apparatuses. Embodiments herein for instance include a communication device 12 configured to perform any of the steps of any of the embodiments described above for the communication device 12.

[0278] Embodiments also include a communication device 12 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication device 12. The power supply circuitry is configured to supply power to the communication device 12.

[0279] Embodiments further include a communication device 12 comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication device 12. In some embodiments, the communication device 12 further comprises communication circuitry.

[0280] Embodiments further include a communication device 12 comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the communication device 12 is configured to perform any of the steps of any of the embodiments described above for the communication device 12.

[0281] Embodiments moreover include a user equipment (UE). The UE comprises an antenna configured to send and receive wireless signals. The UE also comprises radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the communication device 12. In some embodiments, the UE also comprises an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry. The UE may comprise an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry. The UE may also comprise a battery connected to the processing circuitry and configured to supply power to the UE.

[0282] Embodiments herein also include a network node 14 configured to perform any of the steps of any of the embodiments described above for the network node 14.

[0283] Embodiments also include a network node 14 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the network node 14. The power supply circuitry is configured to supply power to the network node 14.

[0284] Embodiments further include a network node 14 comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the network node 14. In some embodiments, the network node 14 further comprises communication circuitry.

[0285] Embodiments further include a network node 14 comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the network node 14 is configured to perform any of the steps of any of the embodiments described above for the network node 14.

[0286] Embodiments herein also include an external node 16 configured to perform any of the steps of any of the embodiments described above for the external node 16.

[0287] Embodiments also include an external node 16 comprising processing circuitry and power supply circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the external node 16. The power supply circuitry is configured to supply power to the external node 16.

[0288] Embodiments further include an external node 16 comprising processing circuitry. The processing circuitry is configured to perform any of the steps of any of the embodiments described above for the external node 16. In some embodiments, the external node 16 further comprises communication circuitry.

[0289] Embodiments further include an external node 16 comprising processing circuitry and memory. The memory contains instructions executable by the processing circuitry whereby the external node 16 is configured to perform any of the steps of any of the embodiments described above for the external node 16.

[0290] More particularly, the apparatuses described above may perform the methods herein and any other processing by implementing any functional means, modules, units, or circuitry. In one embodiment, for example, the apparatuses comprise respective circuits or circuitry configured to perform the steps shown in the method figures. The circuits or circuitry in this regard may comprise circuits dedicated to performing certain functional processing and / or one or more microprocessors in conjunction with memory. For instance, the circuitry may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs), special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as read-only memory (ROM), random-access memory, cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory may include program instructions for executing one or more telecommunications and / or data communications protocols as well as instructions for carrying out one or more of the techniques described herein, in several embodiments. In embodiments that employ memory, the memory stores program code that, when executed by the one or more processors, carries out the techniques described herein.

[0291] Figure 17 for example illustrates a communication device 12 as implemented in accordance with one or more embodiments. As shown, the communication device 12 includes processing circuitry 1710 and communication circuitry 1720. The communication circuitry 1720 (e.g., radio circuitry) is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. Such communication may occur via one or more antennas that are either internal or external to the communication device 1700.

[0292] The processing circuitry 1710 is configured to perform processing described above, e.g., in Figure 14, such as by executing instructions stored in memory 1730. The processing circuitry 1710 in this regard may implement certain functional means, units, or modules.

[0293] Figure 18 illustrates a network node 14 as implemented in accordance with one or more embodiments. As shown, the network node 14 includes processing circuitry 1810 and communication circuitry 1820. The communication circuitry 1820 is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. The processing circuitry 1810 is configured to perform processing described above, e.g., in Figure 15, such as by executing instructions stored in memory 1830. The processing circuitry 1810 in this regard may implement certain functional means, units, or modules.

[0294] Figure 19 illustrates an external node 16 as implemented in accordance with one or more embodiments. As shown, the external node 16 includes processing circuitry 1910 and communication circuitry 1920. The communication circuitry 1920 is configured to transmit and / or receive information to and / or from one or more other nodes, e.g., via any communication technology. The processing circuitry 1910 is configured to perform processing described above, e.g., in Figure 16, such as by executing instructions stored in memory 1930. The processing circuitry 1910 in this regard may implement certain functional means, units, or modules.

[0295] Those skilled in the art will also appreciate that embodiments herein further include corresponding computer programs.

[0296] A computer program comprises instructions which, when executed on at least one processor of an apparatus, cause the apparatus to carry out any of the respective processing described above. A computer program in this regard may comprise one or more code modules corresponding to the means or units described above.

[0297] Embodiments further include a carrier containing such a computer program. This carrier may comprise one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0298] In this regard, embodiments herein also include a computer program product stored on a non-transitory computer readable (storage or recording) medium and comprising instructions that, when executed by a processor of an apparatus, cause the apparatus to perform as described above.

[0299] Embodiments further include a computer program product comprising program code portions for performing the steps of any of the embodiments herein when the computer program product is executed by a computing device. This computer program product may be stored on a computer readable recording medium.

[0300] Figure 20 shows an example of a communication system 2000 in accordance with some embodiments.

[0301] In the example, the communication system 2000 includes a telecommunication network 2002 that includes an access network 2004, such as a radio access network (RAN), and a core network 2006, which includes one or more core network nodes 2008. The access network 2004 includes one or more access network nodes, such as network nodes 2010a and 2010b (one or more of which may be generally referred to as network nodes 2010), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 2002 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 2002 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 2002, including one or more network nodes 2010 and / or core network nodes 2008.

[0302] Examples of an ORAN network node include an open radio unit (0-Rll), an open distributed unit (0-Dll), an open central unit (O-CU), including an O-CU control plane (O-CU- CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1 , E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 2010 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 2012a, 2012b, 2012c, and 2012d (one or more of which may be generally referred to as UEs 2012) to the core network 2006 over one or more wireless connections.

[0303] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 2000 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 2000 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0304] The UEs 2012 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 2010 and other communication devices. Similarly, the network nodes 2010 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 2012 and / or with other network nodes or equipment in the telecommunication network 2002 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 2002.

[0305] In the depicted example, the core network 2006 connects the network nodes 2010 to one or more hosts, such as host 2016. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 2006 includes one more core network nodes (e.g., core network node 2008) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 2008. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (ALISF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0306] The host 2016 may be under the ownership or control of a service provider other than an operator or provider of the access network 2004 and / or the telecommunication network 2002, and may be operated by the service provider or on behalf of the service provider. The host 2016 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0307] As a whole, the communication system 2000 of Figure 20 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low- power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0308] In some examples, the telecommunication network 2002 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 2002 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 2002. For example, the telecommunications network 2002 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0309] In some examples, the UEs 2012 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 2004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 2004. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0310] In the example, the hub 2014 communicates with the access network 2004 to facilitate indirect communication between one or more UEs (e.g., UE 2012c and / or 2012d) and network nodes (e.g., network node 2010b). In some examples, the hub 2014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 2014 may be a broadband router enabling access to the core network 2006 for the UEs. As another example, the hub 2014 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 2010, or by executable code, script, process, or other instructions in the hub 2014. As another example, the hub 2014 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 2014 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 2014 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 2014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 2014 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0311] The hub 2014 may have a constant / persistent or intermittent connection to the network node 2010b. The hub 2014 may also allow for a different communication scheme and / or schedule between the hub 2014 and UEs (e.g., UE 2012c and / or 2012d), and between the hub 2014 and the core network 2006. In other examples, the hub 2014 is connected to the core network 2006 and / or one or more UEs via a wired connection. Moreover, the hub 2014 may be configured to connect to an M2M service provider over the access network 2004 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 2010 while still connected via the hub 2014 via a wired or wireless connection. In some embodiments, the hub 2014 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 2010b. In other embodiments, the hub 2014 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 2010b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0312] Figure 21 shows a UE 2100 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB- loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0313] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0314] The UE 2100 includes processing circuitry 2102 that is operatively coupled via a bus 2104 to an input / output interface 2106, a power source 2108, a memory 2110, a communication interface 2112, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 21. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0315] The processing circuitry 2102 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 2110. The processing circuitry 2102 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 2102 may include multiple central processing units (CPUs).

[0316] In the example, the input / output interface 2106 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 2100. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0317] In some embodiments, the power source 2108 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 2108 may further include power circuitry for delivering power from the power source 2108 itself, and / or an external power source, to the various parts of the UE 2100 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 2108. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 2108 to make the power suitable for the respective components of the UE 2100 to which power is supplied.

[0318] The memory 2110 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 2110 includes one or more application programs 2114, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 2116. The memory 2110 may store, for use by the UE 2100, any of a variety of various operating systems or combinations of operating systems.

[0319] The memory 2110 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 2110 may allow the UE 2100 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 2110, which may be or comprise a device-readable storage medium.

[0320] The processing circuitry 2102 may be configured to communicate with an access network or other network using the communication interface 2112. The communication interface 2112 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 2122. The communication interface 2112 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 2118 and / or a receiver 2120 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 2118 and receiver 2120 may be coupled to one or more antennas (e.g., antenna 2122) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0321] In the illustrated embodiment, communication functions of the communication interface 2112 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11 , Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0322] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 2112, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0323] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0324] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smartwatch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 2100 shown in Figure 21.

[0325] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-loT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0326] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0327] Figure 22 shows a network node 2200 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0328] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0329] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cel l / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0330] The network node 2200 includes a processing circuitry 2202, a memory 2204, a communication interface 2206, and a power source 2208. The network node 2200 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 2200 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 2200 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 2204 for different RATs) and some components may be reused (e.g., a same antenna 2210 may be shared by different RATs). The network node 2200 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 2200, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 2200.

[0331] The processing circuitry 2202 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 2200 components, such as the memory 2204, to provide network node 2200 functionality.

[0332] In some embodiments, the processing circuitry 2202 includes a system on a chip (SOC). In some embodiments, the processing circuitry 2202 includes one or more of radio frequency (RF) transceiver circuitry 2212 and baseband processing circuitry 2214. In some embodiments, the radio frequency (RF) transceiver circuitry 2212 and the baseband processing circuitry 2214 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 2212 and baseband processing circuitry 2214 may be on the same chip or set of chips, boards, or units.

[0333] The memory 2204 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 2202. The memory 2204 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 2202 and utilized by the network node 2200. The memory 2204 may be used to store any calculations made by the processing circuitry 2202 and / or any data received via the communication interface 2206. In some embodiments, the processing circuitry 2202 and memory 2204 is integrated.

[0334] The communication interface 2206 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 2206 comprises port(s) / terminal(s) 2216 to send and receive data, for example to and from a network over a wired connection. The communication interface 2206 also includes radio front-end circuitry 2218 that may be coupled to, or in certain embodiments a part of, the antenna 2210. Radio front-end circuitry 2218 comprises filters 2220 and amplifiers 2222. The radio front-end circuitry 2218 may be connected to an antenna 2210 and processing circuitry 2202. The radio front-end circuitry may be configured to condition signals communicated between antenna 2210 and processing circuitry 2202. The radio front-end circuitry 2218 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 2218 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 2220 and / or amplifiers 2222. The radio signal may then be transmitted via the antenna 2210. Similarly, when receiving data, the antenna 2210 may collect radio signals which are then converted into digital data by the radio front-end circuitry 2218. The digital data may be passed to the processing circuitry 2202. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0335] In certain alternative embodiments, the network node 2200 does not include separate radio front-end circuitry 2218, instead, the processing circuitry 2202 includes radio front-end circuitry and is connected to the antenna 2210. Similarly, in some embodiments, all or some of the RF transceiver circuitry 2212 is part of the communication interface 2206. In still other embodiments, the communication interface 2206 includes one or more ports or terminals 2216, the radio front-end circuitry 2218, and the RF transceiver circuitry 2212, as part of a radio unit (not shown), and the communication interface 2206 communicates with the baseband processing circuitry 2214, which is part of a digital unit (not shown).

[0336] The antenna 2210 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 2210 may be coupled to the radio front-end circuitry 2218 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 2210 is separate from the network node 2200 and connectable to the network node 2200 through an interface or port.

[0337] The antenna 2210, communication interface 2206, and / or the processing circuitry 2202 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 2210, the communication interface 2206, and / or the processing circuitry 2202 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0338] The power source 2208 provides power to the various components of network node 2200 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 2208 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 2200 with power for performing the functionality described herein. For example, the network node 2200 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 2208. As a further example, the power source 2208 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0339] Embodiments of the network node 2200 may include additional components beyond those shown in Figure 22 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 2200 may include user interface equipment to allow input of information into the network node 2200 and to allow output of information from the network node 2200. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 2200.

[0340] Figure 23 is a block diagram of a host 2300, which may be an embodiment of the host 2016 of Figure 20, in accordance with various aspects described herein. As used herein, the host 2300 may be or comprise various combinations hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, container, or processing resources in a server farm. The host 2300 may provide one or more services to one or more UEs.

[0341] The host 2300 includes processing circuitry 2302 that is operatively coupled via a bus 2304 to an input / output interface 2306, a network interface 2308, a power source 2310, and a memory 2312. Other components may be included in other embodiments. Features of these components may be substantially similar to those described with respect to the devices of previous figures, such as Figures 21 and 22, such that the descriptions thereof are generally applicable to the corresponding components of host 2300.

[0342] The memory 2312 may include one or more computer programs including one or more host application programs 2314 and data 2316, which may include user data, e.g., data generated by a UE for the host 2300 or data generated by the host 2300 for a UE. Embodiments of the host 2300 may utilize only a subset or all of the components shown. The host application programs 2314 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (WC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAG, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of UEs (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application programs 2314 may also provide for user authentication and licensing checks and may periodically report health, routes, and content availability to a central node, such as a device in or on the edge of a core network. Accordingly, the host 2300 may select and / or indicate a different host for over-the-top services for a UE. The host application programs 2314 may support various protocols, such as the HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0343] Figure 24 is a block diagram illustrating a virtualization environment 2400 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 2400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 2400 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface.

[0344] Applications 2402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0345] Hardware 2404 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 2406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 2408a and 2408b (one or more of which may be generally referred to as VMs 2408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 2406 may present a virtual operating platform that appears like networking hardware to the VMs 2408.

[0346] The VMs 2408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 2406. Different embodiments of the instance of a virtual appliance 2402 may be implemented on one or more of VMs 2408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0347] In the context of NFV, a VM 2408 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 2408, and that part of hardware 2404 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 2408 on top of the hardware 2404 and corresponds to the application 2402.

[0348] Hardware 2404 may be implemented in a standalone network node with generic or specific components. Hardware 2404 may implement some functions via virtualization. Alternatively, hardware 2404 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 2410, which, among others, oversees lifecycle management of applications 2402. In some embodiments, hardware 2404 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 2412 which may alternatively be used for communication between hardware nodes and radio units.

[0349] Figure 25 shows a communication diagram of a host 2502 communicating via a network node 2504 with a UE 2506 over a partially wireless connection in accordance with some embodiments. Example implementations, in accordance with various embodiments, of the UE (such as a UE 2012a of Figure 20 and / or UE 2100 of Figure 21), network node (such as network node 2010a of Figure 20 and / or network node 2200 of Figure 22), and host (such as host 2016 of Figure 20 and / or host 2300 of Figure 23) discussed in the preceding paragraphs will now be described with reference to Figure 25.

[0350] Like host 2300, embodiments of host 2502 include hardware, such as a communication interface, processing circuitry, and memory. The host 2502 also includes software, which is stored in or accessible by the host 2502 and executable by the processing circuitry. The software includes a host application that may be operable to provide a service to a remote user, such as the UE 2506 connecting via an over-the-top (OTT) connection 2550 extending between the UE 2506 and host 2502. In providing the service to the remote user, a host application may provide user data which is transmitted using the OTT connection 2550.

[0351] The network node 2504 includes hardware enabling it to communicate with the host 2502 and UE 2506. The connection 2560 may be direct or pass through a core network (like core network 2006 of Figure 20) and / or one or more other intermediate networks, such as one or more public, private, or hosted networks. For example, an intermediate network may be a backbone network or the Internet.

[0352] The UE 2506 includes hardware and software, which is stored in or accessible by UE 2506 and executable by the UE’s processing circuitry. The software includes a client application, such as a web browser or operator-specific “app” that may be operable to provide a service to a human or non-human user via UE 2506 with the support of the host 2502. In the host 2502, an executing host application may communicate with the executing client application via the OTT connection 2550 terminating at the UE 2506 and host 2502. In providing the service to the user, the UE's client application may receive request data from the host's host application and provide user data in response to the request data. The OTT connection 2550 may transfer both the request data and the user data. The UE's client application may interact with the user to generate the user data that it provides to the host application through the OTT connection 2550.

[0353] The OTT connection 2550 may extend via a connection 2560 between the host 2502 and the network node 2504 and via a wireless connection 2570 between the network node 2504 and the UE 2506 to provide the connection between the host 2502 and the UE 2506. The connection 2560 and wireless connection 2570, over which the OTT connection 2550 may be provided, have been drawn abstractly to illustrate the communication between the host 2502 and the UE 2506 via the network node 2504, without explicit reference to any intermediary devices and the precise routing of messages via these devices.

[0354] As an example of transmitting data via the OTT connection 2550, in step 2508, the host 2502 provides user data, which may be performed by executing a host application. In some embodiments, the user data is associated with a particular human user interacting with the UE 2506. In other embodiments, the user data is associated with a UE 2506 that shares data with the host 2502 without explicit human interaction. In step 2510, the host 2502 initiates a transmission carrying the user data towards the UE 2506. The host 2502 may initiate the transmission responsive to a request transmitted by the UE 2506. The request may be caused by human interaction with the UE 2506 or by operation of the client application executing on the UE 2506. The transmission may pass via the network node 2504, in accordance with the teachings of the embodiments described throughout this disclosure. Accordingly, in step 2512, the network node 2504 transmits to the UE 2506 the user data that was carried in the transmission that the host 2502 initiated, in accordance with the teachings of the embodiments described throughout this disclosure. In step 2514, the UE 2506 receives the user data carried in the transmission, which may be performed by a client application executed on the UE 2506 associated with the host application executed by the host 2502. In some examples, the UE 2506 executes a client application which provides user data to the host 2502. The user data may be provided in reaction or response to the data received from the host 2502. Accordingly, in step 2516, the UE 2506 may provide user data, which may be performed by executing the client application. In providing the user data, the client application may further consider user input received from the user via an input / output interface of the UE 2506. Regardless of the specific manner in which the user data was provided, the UE 2506 initiates, in step 2518, transmission of the user data towards the host 2502 via the network node 2504. In step 2520, in accordance with the teachings of the embodiments described throughout this disclosure, the network node 2504 receives user data from the UE 2506 and initiates transmission of the received user data towards the host 2502. In step 2522, the host 2502 receives the user data carried in the transmission initiated by the UE 2506.

[0355] One or more of the various embodiments improve the performance of OTT services provided to the UE 2506 using the OTT connection 2550, in which the wireless connection 2570 forms the last segment.

[0356] In an example scenario, factory status information may be collected and analyzed by the host 2502. As another example, the host 2502 may process audio and video data which may have been retrieved from a UE for use in creating maps. As another example, the host 2502 may collect and analyze real-time data to assist in controlling vehicle congestion (e.g., controlling traffic lights). As another example, the host 2502 may store surveillance video uploaded by a UE. As another example, the host 2502 may store or control access to media content such as video, audio, VR or AR which it can broadcast, multicast or unicast to UEs. As other examples, the host 2502 may be used for energy pricing, remote control of non-time critical electrical load to balance power generation needs, location services, presentation services (such as compiling diagrams etc. from data collected from remote devices), or any other function of collecting, retrieving, storing, analyzing and / or transmitting data.

[0357] In some examples, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There may further be an optional network functionality for reconfiguring the OTT connection 2550 between the host 2502 and UE 2506, in response to variations in the measurement results. The measurement procedure and / or the network functionality for reconfiguring the OTT connection may be implemented in software and hardware of the host 2502 and / or UE 2506. In some embodiments, sensors (not shown) may be deployed in or in association with other devices through which the OTT connection 2550 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software may compute or estimate the monitored quantities. The reconfiguring of the OTT connection 2550 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not directly alter the operation of the network node 2504. Such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary UE signaling that facilitates measurements of throughput, propagation times, latency and the like, by the host 2502. The measurements may be implemented in that software causes messages to be transmitted, in particular empty or ‘dummy’ messages, using the OTT connection 2550 while monitoring propagation times, errors, etc.

[0358] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0359] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer- readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0360] Some embodiments herein may be enumerated as follows. Group A Embodiments

[0361] A1. A method performed by a communication device, the method comprising: communicating with a communication network about a transfer of artificial intelligence, Al, data from an external node to the communication device via the communication network, wherein the external node is external to the communication network.

[0362] A2. The method of embodiment A1 , wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication network; informing the communication network about the transfer; informing the communication network about the transfer being from an external node that is external to the communication network; requesting permission from the communication network for the external node to perform the transfer; enabling the communication network to exert control over whether, when, and / or how the Al data is communicated over the communication network; enabling the communication network to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network to exert control over a security of the transfer and / or a security of the Al data.

[0363] A3. The method of any of embodiments A1-A2, wherein said communicating comprises transmitting and / or receiving signaling between the communication device and the communication network, wherein the signaling is about the transfer of Al data from the external node to the communication device.

[0364] A4. The method of any of embodiments A1-A3, wherein said communicating comprises transmitting signaling to the communication network indicating a request or need for the transfer of Al data from the external node to the communication device.

[0365] A5. The method of any of embodiments A1-A4, wherein said communicating comprises transmitting signaling to the communication network informing the communication network about the transfer.

[0366] A6. The method of any of embodiments A1-A5, wherein said communicating comprises transmitting signaling to the communication network indicating one or more of: a need for the transfer; a functionality for which the Al data is to be used by the communication device; a size of the Al data; an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data is valid or a time duration for which the Al data will be valid; an identity associated with the Al data; information about an expected performance of the Al data; a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network to enable an inference by the communication device from the Al data.

[0367] A7. The method of any of embodiments A4-A6, wherein said signaling is conveyed in Message B in Figure 2 or Figure 3.

[0368] A8. The method of any of embodiments A4-A7, wherein said signaling is transmitted to an access node in the communication network.

[0369] A9. The method of any of embodiments A1-A8, wherein said communicating comprises receiving signaling from the communication network indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network.

[0370] A10. The method of embodiment A9, wherein the received signaling indicates how the transfer is, or is allowed, to be performed via the communication network, in terms of a configuration for the transfer.

[0371] A11. The method of embodiment A9, wherein the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration.

[0372] A12. The method of any of embodiments A9-A11 , wherein the signaling indicates one or more of: whether a request by the communication device for the transfer has been accepted; a time duration for which acceptance or rejection of a request by the communication device for the transfer is valid; a point in time when the communication device is allowed to initiate the transfer; a radio condition under which the communication device is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

[0373] A13. The method of any of embodiments A9-A11 , wherein said received signaling is conveyed in Message C in Figure 2.

[0374] A14. The method of any of embodiments A9-A13, wherein the received signaling is received from an access node of the communication network and / or via access stratum, AS, signaling.

[0375] A15. The method of any of embodiments A9-A13, wherein the received signaling is received from a core network node of the communication network and / or via non-access stratum, NAS, signaling.

[0376] A16. The method of any of embodiments A9-A15, further comprising propagating at least some of the signaling received from the communication network to the external node.

[0377] A17. The method of embodiment A16, wherein at least some of the signaling is propagated to the external node via Message D in Figure 1.

[0378] A18. The method of any of embodiments A1-A17, wherein the external node acts as an over- the-top, OTT, server, wherein the communication device acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data from the OTT server to the OTT client via the communication network.

[0379] A19. The method of any of embodiment A1-A18, wherein the Al data comprises an Al model or data associated therewith.

[0380] A20. The method of embodiment A19, wherein the Al model is a trained Al model.

[0381] A21. The method of any of embodiments A19-A20, wherein the Al model is a device-side Al model.

[0382] A22. The method of any of embodiments A1-A21 , further comprising, after the transfer, by the communication device, making an inference from the Al data.

[0383] A23. The method of any of embodiments A1-A22, wherein the Al data is specific to a type and / or vendor of the communication device.

[0384] A24. The method of any of embodiments A1-A23, wherein the external node is specific to a vendor of the communication device.

[0385] A25. The method of any of embodiments A1-A24, wherein the transfer is an application layer transfer at an application layer of the communication device.

[0386] A26. The method of any of embodiments A1-A25, further comprising using the Al data, or an inference made by the communication device from the Al data, to perform one or more functions for operating in the communication network.

[0387] A27. The method of any of embodiments A1-A26, wherein the communication device is a wireless device, WD, wherein the communication network is a mobile network, and wherein the external node is a first node outside of the mobile network.

[0388] Group B Embodiments

[0389] B1. A method performed by a network node configured for use in a communication network, the method comprising: communicating with a communication device and / or an external node about a transfer of artificial intelligence, Al, data from the external node to the communication device via the communication network, wherein the external node is external to the communication network.

[0390] B2. The method of embodiment B1 , wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication device and / or the external node; the communication device and / or the external node informing the communication network about the transfer; the communication device and / or the external node informing the communication network about the transfer being from an external node that is external to the communication network; the communication device and / or the external node requesting permission from the communication network for the external node to perform the transfer; enabling the communication network to exert control over whether, when, and / or how the Al data is communicated over the communication network; enabling the communication network to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network to exert control over a security of the transfer and / or a security of the Al data.

[0391] B3. The method of any of embodiments B1-B2, wherein said communicating comprises transmitting and / or receiving signaling between the communication device and the communication network, and / or between the external node and the communication network, wherein the signaling is about the transfer of Al data from the external node to the communication device.

[0392] B4. The method of any of embodiments B1-B3, wherein said communicating comprises receiving signaling from the communication device and / or the external node indicating a request or need for the transfer of Al data from the external node to the communication device.

[0393] B5. The method of any of embodiments B1-B4, wherein said communicating comprises receiving signaling from the communication device and / or the external node informing the communication network about the transfer.

[0394] B6. The method of any of embodiments B1-B5, wherein said communicating comprises receiving signaling from the communication device and / or the external node indicating one or more of: a need or request for the transfer; a functionality for which the Al data is to be used by the communication device; a size of the Al data; an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data is valid or a time duration for which the Al data will be valid; an identity associated with the Al data; information about an expected performance of the Al data; a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network to enable an inference by the communication device from the Al data.

[0395] B7. The method of any of embodiments B4-B6, wherein said signaling is received from the communication device in Message B in Figure 2 or Figure 3, or from the external node in Message A of Figure 4.

[0396] B8. The method of any of embodiments B4-B7, wherein the network node is an access node in the communication network.

[0397] B9. The method of any of embodiments B1-B8, wherein said communicating comprises transmitting signaling from the communication network to the communication device and / or the external node indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network.

[0398] B10. The method of embodiment B9, wherein the transmitted signaling indicates how the transfer is, or is allowed, to be performed via the communication network, in terms of a configuration for the transfer.

[0399] B11. The method of embodiment B9, wherein the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration.

[0400] B12. The method of any of embodiments B9-B11 , wherein the transmitted signaling indicates one or more of: whether a request by the communication device and / or the external node for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device and / or the external node is allowed to initiate the transfer; a radio condition under which the communication device and / or the external node is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer. B13. The method of any of embodiments B9-B11, wherein said transmitted signaling is transmitted to the communication device in Message C in Figure 2, or to the external node in Message D in Figure 3 or Figure 4.

[0401] B14. The method of any of embodiments B9-B13, wherein the transmitted signaling is access stratum, AS, signaling, and / or the network node is an access node in the communication network.

[0402] B15. The method of any of embodiments B9-B13, wherein the transmitted signaling is non- access stratum, NAS, signaling, and / or the network node is a core network node.

[0403] B16. The method of any of embodiments B9-B15, further comprising receiving at least some of the signaling from the communication device and wherein transmitting the signaling comprises transmitting the signaling to the external node in order to propagate at least some of the signaling from the communication device to the external node.

[0404] B17. Reserved.

[0405] B18. The method of any of embodiments B1-B17, wherein the external node acts as an over- the-top, OTT, server, wherein the communication device acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data from the OTT server to the OTT client via the communication network.

[0406] B19. The method of any of embodiment B1-B18, wherein the Al data comprises an Al model or data associated therewith.

[0407] B20. The method of embodiment B19, wherein the Al model is a trained Al model.

[0408] B21. The method of any of embodiments B19-B20, wherein the Al model is a device-side Al model.

[0409] B22. Reserved.

[0410] B23. The method of any of embodiments B1-B22, wherein the Al data is specific to a type and / or vendor of the communication device. B24. The method of any of embodiments B1-B23, wherein the external node is specific to a vendor of the communication device.

[0411] B25. The method of any of embodiments B1-B24, wherein the transfer is an application layer transfer at an application layer of the communication device.

[0412] B26. The method of any of embodiments B1-B25, further comprising, based on said communicating, one or more of: controlling whether, when, and / or how the Al data is communicated over the communication network; controlling whether, when, and / or how the transfer is performed; or controlling or evaluating a security of the transfer and / or a security of the Al data.

[0413] B27. The method of any of embodiments B1-B27, further comprising, based on said communicating: deciding whether and / or when the transfer is allowed; validating a legitimacy of the external node and / or of the Al data; allocating resources in the communication network for the transfer; setting a quality of service, QoS, in the communication network for the transfer; and / or performing network configuration, resource allocation, and / or capacity planning.

[0414] B28. The method of any of embodiments B1-B27, further comprising, based on said communicating with the communication device and / or the external node, communicating with one or more other network nodes in the communication network about the transfer.

[0415] B29. The method of any of embodiments B1-B28, wherein the network node is an access node in an access network of the communication network.

[0416] B30. The method of embodiment B29, further comprising communicating with a core network node in a core network of the communication network about the transfer.

[0417] B31. The method of embodiment B30, wherein communicating with the core network node comprises transmitting signaling to the core network node indicating one or more of: whether a request by the communication device and / or the external node for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device and / or the external node is allowed to initiate the transfer; a radio condition under which the communication device and / or the external node is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data for the transfer; a maximum allowed data size of the transfer; a maximum allowed duration of the transfer; or a configuration for the transfer.

[0418] B32. The method of embodiment B30, wherein communicating with the core network node comprises transmitting signaling to the core network node indicating whether, when, and / or how the transfer is to be performed or is allowed to be performed.

[0419] B33. The method of any of embodiments B31-B32, wherein the signaling is transmitted in Message C of Figure 3.

[0420] B34. The method of any of embodiments B1-B28, wherein the network node is a core network node in a core network of the communication network.

[0421] B35. The method of embodiment B34, further comprising communicating with an access node in an access network of the communication network about the transfer.

[0422] B36. The method of embodiment B35, wherein communicating with the access node comprises transmitting signaling to the access node indicating one or more of: a need or request for the transfer; a functionality for which the Al data is to be used by the communication device; a size of the Al data; an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data is valid or a time duration for which the Al data will be valid; an identity associated with the Al data; information about an expected performance of the Al data; a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network to enable an inference by the communication device from the Al data. B37. The method of embodiment B36, wherein the signaling is transmitted in Message B of Figure 4.

[0423] B38. The method of embodiment B35, wherein communicating with the access node comprises receiving signaling from the access node indicating one or more of: whether a request by the communication device and / or the external node for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device and / or the external node is allowed to initiate the transfer; a radio condition under which the communication device and / or the external node is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

[0424] B39. The method of embodiment B38, wherein communicating with the access node comprises receiving signaling from the access node indicating whether, when, and / or how the transfer is to be performed or is allowed to be performed.

[0425] B40. The method of any of embodiments B38-B39, wherein the signaling is received in Message C of Figure 4.

[0426] B41. The method of any of embodiments B1-B40, wherein the communication device is a wireless device, WD, wherein the communication network is a mobile network, and wherein the external node is a first node outside of the mobile network.

[0427] Group Z Embodiments

[0428] Z1. A method performed by an external node that is external to a communication network, the method comprising: communicating with the communication network about a transfer of artificial intelligence, Al, data from the external node to a communication device via the communication network.

[0429] Z2. The method of embodiment Z1, wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication network; informing the communication network about the transfer; informing the communication network about the transfer being from an external node that is external to the communication network; requesting permission from the communication network for the external node to perform the transfer; enabling the communication network to exert control over whether, when, and / or how the Al data is communicated over the communication network; enabling the communication network to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network to exert control over a security of the transfer and / or a security of the Al data.

[0430] Z3. The method of any of embodiments Z1-Z2, wherein said communicating comprises transmitting and / or receiving signaling between the external node and the communication network, wherein the signaling is about the transfer of Al data from the external node to the communication device.

[0431] Z4. The method of any of embodiments Z1-Z3, wherein said communicating comprises transmitting signaling to the communication network indicating a request or need for the transfer of Al data from the external node to the communication device.

[0432] Z5. The method of any of embodiments Z1-Z4, wherein said communicating comprises transmitting signaling to the communication network informing the communication network about the transfer.

[0433] Z6. The method of any of embodiments Z1-Z5, wherein said communicating comprises transmitting signaling to the communication network indicating one or more of: a need for the transfer; a functionality for which the Al data is to be used by the communication device; a size of the Al data; an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data is valid or a time duration for which the Al data will be valid; an identity associated with the Al data; information about an expected performance of the Al data; a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network to enable an inference by the communication device from the Al data.

[0434] Z7. The method of any of embodiments Z4-Z6, wherein said signaling is conveyed in Message A in Figure 4.

[0435] Z8. The method of any of embodiments Z4-Z7, wherein said signaling is transmitted to a core network node in a core network of the communication network.

[0436] Z9. The method of any of embodiments Z1-Z8, wherein said communicating comprises receiving signaling from the communication network indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network.

[0437] Z10. The method of embodiment Z9, wherein the received signaling indicates how the transfer is, or is allowed, to be performed via the communication network, in terms of a configuration for the transfer.

[0438] Z11. The method of embodiment Z9, wherein the configuration is a bearer configuration, a security configuration, a downlink channel configuration, a configuration of allocated resources allocated for the transfer, or a Packet Data Convergence Protocol configuration.

[0439] Z12. The method of any of embodiments Z9-Z11, wherein the signaling indicates one or more of: whether a request by the external node and / or the communication device for the transfer has been accepted; a time duration for which acceptance or rejection of a request by the communication device and / or the external node for the transfer is valid; a point in time when the communication device and / or the external node is allowed to initiate the transfer; a radio condition under which the communication device and / or the external node is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

[0440] Z13. The method of any of embodiments Z9-Z11, wherein said received signaling is conveyed in Message D in Figure 3 or Figure 4.

[0441] Z14. Reserved.

[0442] Z15. The method of any of embodiments Z9-Z13, wherein the received signaling is received from a core network node of the communication network.

[0443] Z16. Reserved

[0444] Z17. Reserved.

[0445] Z18. The method of any of embodiments Z1-Z17, wherein the external node acts as an over- the-top, OTT, server, wherein the communication device acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data from the OTT server to the OTT client via the communication network.

[0446] Z19. The method of any of embodiment Z1-Z18, wherein the Al data comprises an Al model or data associated therewith.

[0447] Z20. The method of embodiment Z19, wherein the Al model is a trained Al model.

[0448] Z21. The method of any of embodiments Z19-Z20, wherein the Al model is a device-side Al model.

[0449] Z22. The method of any of embodiments Z19-Z21, further comprising, before the transfer, training the Al model and / or storing the Al model.

[0450] Z23. The method of any of embodiments Z1-Z22, wherein the Al data is specific to a type and / or vendor of the communication device.

[0451] Z24. The method of any of embodiments Z1-Z23, wherein the external node is specific to a vendor of the communication device. Z25. The method of any of embodiments Z1-Z24, wherein the transfer is an application layer transfer at an application layer of the communication device.

[0452] Z26. The method of any of embodiments Z1-Z25, wherein the communication device is a wireless device, WD, wherein the communication network is a mobile network, and wherein the external node is a first node outside of the mobile network.

[0453] Group X Embodiments

[0454] X1. A method at a WD for obtaining at least one AI / ML model associated to one functionality, from a node outside the mobile network, comprising:

[0455] Determining that a download an AI / ML model and / or to update a stored AI / ML model is needed,

[0456] - Transmitting a first indication to a Mobile Network Node (MNN) that a download an AI / ML model and / or to update a stored AI / ML model is needed.

[0457] X2. A method according to X1 , wherein the first indication which the UE transmits may correspond to a request to a first network node, wherein the request is on whether the first node outside the mobile network is allowed or not to transfer the AIML model to the WD to be used for UE-side AIML-based inference, or an indication for informing the MNN that the process of model transfer has started or is about to start.

[0458] X3. A method according to X2, wherein the first indication is transmitted by the WD in response to the reception by the UE of a previous indication indicating that the first node outside the mobile network (e.g., OTT server) needs to transfer an AIML model of at least one AI / ML functionality to be used for UE-side model AIML-based inference.

[0459] X4. A method according to X3, wherein the indication from the first network node outside the mobile network is received by a User Equipment (UE) in the WD from the higher layers, or from an OTT Client in the WD.

[0460] X5. A method according to X1 , further comprising, in response to the transmitted first indication, the WD receiving a first response from the MNN.

[0461] X6. A method according to X5, wherein the first response may correspond to one or more of: an acceptance indication, or a rejection indication, and / or preferred means (e.g., configuration, model transfer technique, indication of the point in time in which the transfer is allowed, etc.) for the first node outside the mobile network to use for transferring the model. Group C Embodiments

[0462] C1. A communication device configured to perform the method of any of the Group A embodiments.

[0463] C2. A communication device comprising processing circuitry configured to perform the method of any of the Group A embodiments.

[0464] C3. A communication device comprising: communication circuitry; and processing circuitry configured to perform the method of any of the Group A embodiments.

[0465] C4. A communication device comprising: processing circuitry configured to perform the method of any of the Group A embodiments; and power supply circuitry configured to supply power to the communication device.

[0466] C5. A communication device comprising: processing circuitry and memory, the memory containing instructions executable by the processing circuitry whereby the communication device is configured to perform the method of any of the Group A embodiments.

[0467] C6. The communication device of any of embodiments C1-C5, wherein the communication device is a wireless communication device.

[0468] C7. A user equipment (UE) comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry; the processing circuitry being configured to perform the method of any of the Group A embodiments; an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE.

[0469] C8. A computer program comprising instructions which, when executed by at least one processor of a communication device, causes the communication device to perform the method of any of the Group A embodiments.

[0470] C9. A carrier containing the computer program of embodiment C7, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0471] C10. A network node configured to perform the method of any of the Group B embodiments.

[0472] C11. A network node comprising processing circuitry configured to perform the method of any of the Group B embodiments.

[0473] C12. A network node comprising: communication circuitry; and processing circuitry configured to perform the method of any of the Group B embodiments.

[0474] C13. A network node comprising: processing circuitry configured to perform the method of any of the Group B embodiments; power supply circuitry configured to supply power to the network node.

[0475] C14. A network node comprising: processing circuitry and memory, the memory containing instructions executable by the processing circuitry whereby the network node is configured to perform the method of any of the Group B embodiments.

[0476] C15. The network node of any of embodiments C10-C14, wherein the network node is a base station.

[0477] C16. A computer program comprising instructions which, when executed by at least one processor of a network node, causes the network node to perform the method of any of the Group B embodiments. C17. The computer program of embodiment C16, wherein the network node is a base station.

[0478] C18. A carrier containing the computer program of any of embodiments C16-C17, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0479] C19. An external node configured to perform the method of any of the Group Z embodiments.

[0480] C20. An external node comprising processing circuitry configured to perform the method of any of the Group Z embodiments.

[0481] C21. An external node comprising: communication circuitry; and processing circuitry configured to perform the method of any of the Group Z embodiments.

[0482] C22. An external node comprising: processing circuitry configured to perform the method of any of the Group Z embodiments; power supply circuitry configured to supply power to the external node.

[0483] C23. An external node comprising: processing circuitry and memory, the memory containing instructions executable by the processing circuitry whereby the external node is configured to perform the method of any of the Group Z embodiments.

[0484] C24. Reserved

[0485] C25. A computer program comprising instructions which, when executed by at least one processor of an external node, causes the external node to perform the method of any of the Group Z embodiments.

[0486] C26. Reserved

[0487] C27. A carrier containing the computer program of any of embodiments C25-C26, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0488] Group D Embodiments

[0489] D1. A host configured to operate in a communication system to provide an over-the-top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a network node in a cellular network for transmission to a user equipment (UE), the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments to transmit the user data from the host to the UE.

[0490] D2. The host of the previous embodiment, wherein: the processing circuitry of the host is configured to execute a host application that provides the user data; and the UE comprises processing circuitry configured to execute a client application associated with the host application to receive the transmission of user data from the host.

[0491] D3. A method implemented in a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: providing user data for the UE; and initiating a transmission carrying the user data to the UE via a cellular network comprising the network node, wherein the network node performs any of the operations of any of the Group B embodiments to transmit the user data from the host to the UE.

[0492] D4. The method of the previous embodiment, further comprising, at the network node, transmitting the user data provided by the host for the UE.

[0493] D5. The method of any of the previous 2 embodiments, wherein the user data is provided at the host by executing a host application that interacts with a client application executing on the UE, the client application being associated with the host application.

[0494] D6. A communication system configured to provide an over-the-top (OTT) service, the communication system comprising: a host comprising: processing circuitry configured to provide user data for a user equipment (UE), the user data being associated with the over-the-top service; and a network interface configured to initiate transmission of the user data toward a cellular network node for transmission to the UE, the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments to transmit the user data from the host to the UE.

[0495] D7. The communication system of the previous embodiment, further comprising: the network node; and / or the UE.

[0496] D8. A host configured to operate in a communication system to provide an over-the-top (OTT) service, the host comprising: processing circuitry configured to initiate receipt of user data; and a network interface configured to receive the user data from a network node in a cellular network, the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments to receive the user data from a user equipment (UE) for the host.

[0497] D9. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application that receives the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0498] D10. The host of the any of the previous 2 embodiments, wherein the initiating receipt of the user data comprises requesting the user data.

[0499] D11. A method implemented by a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: at the host, initiating receipt of user data from the UE, the user data originating from a transmission which the network node has received from the UE, wherein the network node performs any of the steps of any of the Group B embodiments to receive the user data from the UE for the host. D12. The method of the previous embodiment, further comprising at the network node, transmitting the received user data to the host.

[0500] D13. A host configured to operate in a communication system to provide an over-the-top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), wherein the UE comprises a communication interface and processing circuitry, the communication interface and processing circuitry of the UE being configured to perform any of the operations of any of the Group A embodiments to receive the user data from the host.

[0501] D14. The host of the previous embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit the user data to the UE from the host.

[0502] D15. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application, thereby providing the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0503] D16. A method implemented by a host operating in a communication system that further includes a network node and a user equipment (UE), the method comprising: providing user data for the UE; and initiating a transmission carrying the user data to the UE via a cellular network comprising the network node, wherein the UE performs any of the operations of any of the Group A embodiments to receive the user data from the host.

[0504] D17. The method of the previous embodiment, further comprising: at the host, executing a host application associated with a client application executing on the UE to receive the user data from the host application.

[0505] D18. The method of the previous embodiment, further comprising: at the host, transmitting input data to the client application executing on the UE, the input data being provided by executing the host application, wherein the user data is provided by the client application in response to the input data from the host application.

[0506] D19. A host configured to operate in a communication system to provide an over-the-top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), wherein the UE comprises a communication interface and processing circuitry, the communication interface and processing circuitry of the UE being configured to perform any of the steps of any of the Group A embodiments to transmit the user data to the host.

[0507] D20. The host of the previous embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit the user data from the UE to the host.

[0508] D21. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application, thereby providing the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0509] D22. A method implemented by a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: at the host, receiving user data transmitted to the host via the network node by the UE, wherein the UE performs any of the steps of any of the Group A embodiments to transmit the user data to the host.

[0510] D23. The method of the previous embodiment, further comprising: at the host, executing a host application associated with a client application executing on the UE to receive the user data from the UE.

[0511] D24. The method of the previous 2 embodiments, further comprising: at the host, transmitting input data to the client application executing on the UE, the input data being provided by executing the host application, wherein the user data is provided by the client application in response to the input data from the host application.

Claims

CLAIMSWhat is claimed is:

1. A method performed by a communication device (12), the method comprising: communicating (1400) with a communication network (10) about a transfer of artificial intelligence, Al, data (18) from an external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10); based on said communicating, receiving (1410) Al data (18) as transferred from the external node (16) to the communication device (12) via the communication network (10); and using (1430) the received Al data (18), or an inference made by the communication device (12) from the received Al data (18), to perform one or more functions for operating in the communication network (10).

2. The method of claim 1 , wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication network (10); informing the communication network (10) about the transfer; informing the communication network (10) about the transfer being from an external node (16) that is external to the communication network (10); requesting permission from the communication network (10) for the external node (16) to perform the transfer; enabling the communication network (10) to exert control over whether, when, and / or how the Al data (18) is communicated over the communication network (10); enabling the communication network (10) to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network (10) to exert control over a security of the transfer and / or a security of the Al data (18).

3. The method of any of claims 1-2, wherein said communicating comprises transmitting and / or receiving signaling between the communication device (12) and the communication network (10), wherein the signaling is about the transfer of Al data (18) from the external node (16) to the communication device (12).

4. The method of any of claims 1-3, wherein said communicating comprises transmitting signaling to the communication network (10): indicating a request or need for the transfer of Al data (18) from the external node (16) tothe communication device (12); and / or informing the communication network (10) about the transfer.

5. The method of any of claims 1-4, wherein said communicating comprises transmitting signaling to the communication network (10) indicating one or more of: a need for the transfer; a functionality for which the Al data (18) is to be used by the communication device (12); a size of the Al data (18); an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data (18) is valid or a time duration for which the Al data (18) will be valid; an identity associated with the Al data (18); information about an expected performance of the Al data (18); a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network (10) to enable an inference by the communication device (12) from the Al data (18).

6. The method of any of claims 1-5, wherein said communicating comprises receiving signaling from the external node (16) indicating whether, when, and / or how the transfer is, can be, or is requested to be performed via the communication network (10).

7. The method of any of claims 1-6, wherein said communicating comprises receiving signaling from the communication network (10) indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network (10).

8. The method of claim 7, wherein the signaling indicates one or more of: whether a request by the communication device (12) for the transfer has been accepted; a time duration for which acceptance or rejection of a request by the communication device (12) for the transfer is valid; a point in time when the communication device (12) is allowed to initiate the transfer; a radio condition under which the communication device (12) is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data (18)for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

9. The method of any of claims 1-8, wherein the external node (16) acts as an over-the-top, OTT, server, wherein the communication device (12) acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data (18) from the OTT server to the OTT client via the communication network (10).

10. The method of any of claim 1-9, wherein the Al data (18) comprises a trained device-side Al model or data associated therewith.

11. A method performed by a network node (14) configured for use in a communication network (10), the method comprising: communicating with a communication device (12) and / or an external node (16) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10).

12. The method of claim 11 , wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication device (12) and / or the external node (16); the communication device (12) and / or the external node (16) informing the communication network (10) about the transfer; the communication device (12) and / or the external node (16) informing the communication network (10) about the transfer being from an external node (16) that is external to the communication network (10); the communication device (12) and / or the external node (16) requesting permission from the communication network (10) for the external node (16) to perform the transfer; enabling the communication network (10) to exert control over whether, when, and / or how the Al data (18) is communicated over the communication network (10); enabling the communication network (10) to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network (10) to exert control over a security of the transfer and / or a security of the Al data (18).

13. The method of any of claims 11-12, wherein said communicating comprises transmitting and / or receiving signaling between the communication device (12) and the communication network (10), and / or between the external node (16) and the communication network (10), wherein the signaling is about the transfer of Al data (18) from the external node (16) to the communication device (12).

14. The method of any of claims 11-13, wherein said communicating comprises receiving signaling from the communication device (12) and / or the external node (16): indicating a request or need for the transfer of Al data (18) from the external node (16) to the communication device (12); and / or informing the communication network (10) about the transfer.

15. The method of any of claims 11-14, wherein said communicating comprises receiving signaling from the communication device (12) and / or the external node (16) indicating one or more of: a need or request for the transfer; a functionality for which the Al data (18) is to be used by the communication device (12); a size of the Al data (18); an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data (18) is valid or a time duration for which the Al data (18) will be valid; an identity associated with the Al data (18); information about an expected performance of the Al data (18); a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network (10) to enable an inference by the communication device (12) from the Al data (18).

16. The method of any of claims 11-15, wherein said communicating comprises transmitting signaling from the communication network (10) to the communication device (12) and / or the external node (16) indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communication network (10).

17. The method of claim 16, wherein the transmitted signaling indicates one or more of:whether a request by the communication device (12) and / or the external node (16) for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a radio condition under which the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data (18) for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

18. The method of any of claims 11-17, wherein the external node (16) acts as an over-the- top, OTT, server, wherein the communication device (12) acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data (18) from the OTT server to the OTT client via the communication network (10).

19. The method of any of claim 11-18, wherein the Al data (18) comprises a trained deviceside Al model or data associated therewith.

20. The method of any of claims 11-19, further comprising, based on said communicating, one or more of: controlling whether, when, and / or how the Al data (18) is communicated over the communication network (10); controlling whether, when, and / or how the transfer is performed; or controlling or evaluating a security of the transfer and / or a security of the Al data (18).

21. The method of any of claims 11-20, further comprising, based on said communicating: deciding whether and / or when the transfer is allowed; validating a legitimacy of the external node (16) and / or of the Al data (18); allocating resources in the communication network (10) for the transfer; setting a quality of service, QoS, in the communication network (10) for the transfer; and / or performing network configuration, resource allocation, and / or capacity planning.

22. The method of any of claims 11-21, further comprising, based on said communicating with the communication device (12) and / or the external node (16), communicating with one or moreother network nodes in the communication network (10) about the transfer, wherein the network node (14) is an access node in an access network of the communication network (10), wherein the method further comprises communicating with a core network node in a core network of the communication network (10) about the transfer, wherein communicating with the core network node comprises transmitting signaling to the core network node indicating one or more of: indicating whether, when, and / or how the transfer is to be performed or is allowed to be performed; whether a request by the communication device (12) and / or the external node (16) for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a radio condition under which the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data (18) for the transfer; a maximum allowed data size of the transfer; a maximum allowed duration of the transfer; or a configuration for the transfer.

23. The method of any of claims 11-22, wherein the network node (14) is a core network node in a core network of the communication network (10), wherein the method further comprises communicating with an access node in an access network of the communication network (10) about the transfer, wherein communicating with the access node comprises: transmitting signaling to the access node indicating one or more of: a need or request for the transfer; a functionality for which the Al data (18) is to be used by the communication device (12); a size of the Al data (18); an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data (18) is valid or a time duration for which the Al data (18) will be valid; an identity associated with the Al data (18); information about an expected performance of the Al data (18); a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; orone or more input parameters that need to be made available from the communication network (10) to enable an inference by the communication device (12) from the Al data (18); and / or receiving signaling from the access node indicating one or more of: whether, when, and / or how the transfer is to be performed or is allowed to be performed; whether a request by the communication device (12) and / or the external node (16) for the transfer has been accepted; a time duration for which acceptance or rejection of a request for the transfer is valid; a point in time when the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a radio condition under which the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data (18) for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

24. A method performed by an external node (16) that is external to a communication network (10), the method comprising: communicating with the communication network (10) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to a communication device (12) via the communication network (10); and based on said communicating, performing the transfer of the Al data (18) from the external node (16) to the communication device (12) via the communication network (10).

25. The method of claim 24, wherein said communicating is performed as part of, or for the purpose of, one or more of: coordinating the transfer with the communication network (10); informing the communication network (10) about the transfer; informing the communication network (10) about the transfer being from an external node (16) that is external to the communication network (10); requesting permission from the communication network (10) for the external node (16) to perform the transfer; enabling the communication network (10) to exert control over whether, when, and / orhow the Al data (18) is communicated over the communication network (10); enabling the communication network (10) to exert control over whether, when, and / or how the transfer is performed; or enabling the communication network (10) to exert control over a security of the transfer and / or a security of the Al data (18).

26. The method of any of claims 24-25, wherein said communicating comprises transmitting and / or receiving signaling between the external node (16) and the communication network (10), wherein the signaling is about the transfer of Al data (18) from the external node (16) to the communication device (12).

27. The method of any of claims 24-26, wherein said communicating comprises transmitting signaling to the communication network (10) indicating: a request or need for the transfer of Al data (18) from the external node (16) to the communication device (12); and / or informing the communication network (10) about the transfer.

28. The method of any of claims 24-27, wherein said communicating comprises transmitting signaling to the communication network (10) indicating one or more of: a need for the transfer; a functionality for which the Al data (18) is to be used by the communication device (12); a size of the Al data (18); an estimated time duration, or a minimum estimated time duration, of the transfer; a geographical area in which the Al data (18) is valid or a time duration for which the Al data (18) will be valid; an identity associated with the Al data (18); information about an expected performance of the Al data (18); a status of the transfer in terms of whether the transfer is started, paused, stopped, or completed; a reason for the transfer; or one or more input parameters that need to be made available from the communication network (10) to enable an inference by the communication device (12) from the Al data (18).

29. The method of any of claims 24-28, wherein said communicating comprises receiving signaling from the communication network (10) indicating whether, when, and / or how the transfer is, or is allowed, to be performed or is allowed to be performed, via the communicationnetwork (10).

30. The method of claim 29, wherein the signaling indicates one or more of: how the transfer is, or is allowed, to be performed via the communication network (10), in terms of a configuration for the transfer; whether a request by the external node (16) and / or the communication device (12) for the transfer has been accepted; a time duration for which acceptance or rejection of a request by the communication device (12) and / or the external node (16) for the transfer is valid; a point in time when the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a radio condition under which the communication device (12) and / or the external node (16) is allowed to initiate the transfer; a quality of service, QoS, profile of traffic that is, or is allowed, to convey the Al data (18) for the transfer; a maximum allowed data size of the transfer; or a maximum allowed duration of the transfer.

31. The method of any of claims 24-30, wherein the external node (16) acts as an over-the- top, OTT, server, wherein the communication device (12) acts as an OTT client, and wherein the transfer is an OTT transfer of the Al data (18) from the OTT server to the OTT client via the communication network (10).

32. The method of any of claim 24-31, wherein the Al data (18) comprises a trained deviceside Al model or data associated therewith.

33. A communication device (12) configured to: communicate with a communication network (10) about a transfer of artificial intelligence, Al, data (18) from an external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10); based on said communicating, receive Al data (18) as transferred from the external node(16) to the communication device (12) via the communication network (10); and use the received Al data (18), or an inference made by the communication device (12) from the received Al data (18), to perform one or more functions for operating in the communication network (10).

34. The communication device (12) of claim 33, configured to perform the method of any of claims 2-10.

35. A network node (14) configured for use in a communication network (10), the network node (14) configured to: communicate with a communication device (12) and / or an external node (16) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10).

36. The network node (14) of claim 35, configured to perform the method of any of claims 12- 23.

37. An external node (16) configured to be external to a communication network (10), the external node (16) configured to: communicate with the communication network (10) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to a communication device (12) via the communication network (10); and based on said communicating, perform the transfer of the Al data (18) from the external node (16) to the communication device (12) via the communication network (10).

38. The external node (16) of claim 37, configured to perform the method of any of claims 25- 32.

39. A computer program comprising instructions which, when executed by at least one processor of a communication device (12), causes the communication device (12) to perform the method of any of claims 1-10.

40. A computer program comprising instructions which, when executed by at least one processor of a network node (14), causes the network node (14) to perform the method of any of claims 11-23.

41. A computer program comprising instructions which, when executed by at least one processor of an external node (16), causes the external node (16) to perform the method of any of claims 24-32.

42. A carrier containing the computer program of any of claims 39-41 , wherein the carrier isone of an electronic signal, optical signal, radio signal, or computer readable storage medium.

43. A communication device (12) comprising: communication circuitry; and processing circuitry configured to: communicate with a communication network (10) about a transfer of artificial intelligence, Al, data (18) from an external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10); based on said communicating, receive Al data (18) as transferred from the external node (16) to the communication device (12) via the communication network (10); and use the received Al data (18), or an inference made by the communication device (12) from the received Al data (18), to perform one or more functions for operating in the communication network (10).

44. The communication device (12) of claim 43, the processing circuitry configured to perform the method of any of claims 2-10.

45. A network node (14) configured for use in a communication network (10), the network node (14) comprising: communication circuitry; and processing circuitry configured to communicate with a communication device (12) and / or an external node (16) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to the communication device (12) via the communication network (10), wherein the external node (16) is external to the communication network (10).

46. The network node (14) of claim 45, the processing circuitry configured to perform the method of any of claims 12-23.

47. An external node (16) configured to be external to a communication network (10), the external node (16) comprising: communication circuitry; and processing circuitry configured to: communicate with the communication network (10) about a transfer of artificial intelligence, Al, data (18) from the external node (16) to a communicationdevice (12) via the communication network (10); and based on said communicating, perform the transfer of the Al data (18) from the external node (16) to the communication device (12) via the communication network (10).

48. The external node (16) of claim 47, the processing circuitry configured to perform the method of any of claims 25-32.

Images