Machine learning functionality applicability conditions

Abstract

A method is performed by a User Equipment (UE) (1100) supporting one or more Machine Learning (ML) functionalities The method comprises transmitting (702), to a first network node (1200), an information message. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

Description

MACHINE LEARNING FUNCTIONALITY APPLICABILITYTECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to communication networks, and particularly to methods, apparatus, and computer-readable medium relating to User Equipments (UEs) supporting one or more Machine Learning (ML) functionalities.BACKGROUND

[0002] Artificial Intelligence (Al) and ML have been investigated, both in academia and industry, as promising tools to optimize the design of the air-interface in wireless 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 the positioning accuracy; and using reinforcement learning for beam selection at the network side and / or the UE side to reduce the signaling overhead and beam alignment latency; using deep reinforcement learning to leam an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0003] In 3rd Generation Partnership Proj ect (3GPP) New Radio (NR) standardization work, a new release 18 study item on AI / ML for the NR air interface started in May 2022. This study item will explore the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases (CSI feedback, beam management, and positioning), this study item aims at laying the foundation for future airinterface use cases leveraging AI / ML techniques. The analysis carried out during the Release 18 is now considered in the context of Release 19. Additionally, during the release 19, a new study item addressing AIML for mobility has been approved. In the context of this new study item, 3GPP will investigate methods for cell-level measurement predictions, and mobility event predictions (e.g. Radio Link Failure (RLF), handover failure, mobility-related events predictions such as A3 / A5).Functional framework for AI / ML model Lifecycle Management (LCM)

[0004] Building an Al model, or any machine learning model, includes several development steps where the actual training of the Al model is just one step in a training pipeline. An important part in Al developing is the ML model LCM. This is illustrated in Figure 1, whichis an illustration of training and inference pipelines, and their interactions within a model lifecycle management procedure. The model lifecycle management typically comprises of:• A training (re-training) pipeline 101 that may include: o Data Ingestion 102: Data ingestion refers to gathering raw (training) data from a data storage. After data ingestion, there may also be a step that controls the validity of the gathered data. o Data Pre-Processing 104: Data pre-processing refers to some feature engineering applied to the gathered data, e.g., it may include data normalization and possibly a data transformation required for the input data to the Al model. o Model Training 106: Model training refers to the actual model training steps as previously outlined. o Model Evaluation 108: Model evaluation refers to benchmarking the performance to some model baseline. The iterative steps of model training and model evaluation continue until the acceptable level of performance (as previously exemplified) is achieved. o Model Registration 110: Model registration refers to registering the Al model, including any corresponding Al -metadata that provides information on how the Al model was developed, and possibly Al model evaluations performance outcomes.• A deployment stage 112 to make the trained (or re-trained) Al model part of the inference pipeline.• An inference pipeline 114 that may include: o Data Ingestion 116: Data ingestion refers to gathering raw (inference) data from a data storage. o Data Pre-Processing 118: Data pre-processing stage is typically identical to corresponding processing that occurs in the training pipeline. o Model Operational 120: Model operational refers to using the trained and deployed model in an operational mode. o Data and Model Monitoring 122: Data & model monitoring refers to validating that the inference data are from a distribution that aligns well with the training data, as well as monitoring model outputs for detecting any performance, or operational, drifts.• A drift detection stage 124 that informs about any drifts in the model operations.

[0005] Figure 2 shows a functional framework that can be used for studying LCM aspectsof AI / ML models, particularly at the Network (NW) - UE collaboration levels for the Al for Physical Layer (PHY) use cases. The framework comprises the following functions: a data collection function 202; a model training function 204; a model storage function 206; an inference function 208; and a management function 210. The arrows between the functions illustrate the following operations: the transfer of training data from the data collection function 202 to the model training function 204; the transfer of a trained / updated model from the model training function 204 to the model storage function 206; the transfer of the model from the model storage function 206 to the inference function 208; the transfer of inference data from the data collection function 202 and the inference function 208; the transfer of an inference output from the inference function 208 to the management function 210; the transfer of monitoring data from the data collection function 202 to the management function 210; the transfer of a selection / (de)activation / switching / fallback indication from the management function 210 to the inference function 208; the transfer of performance feedback / a retraining request from the management function 210 to the model training function 204; and the transfer of a model transfer / delivery request from the management function 210 to the model storage function 206.SUMMARYBeam prediction

[0006] The use cases of beam prediction which will be standardized as part of 3GPP Release 19 work item comprise spatial beam prediction, and temporal beam prediction. The core idea of this use case is to predict the “best” beam (or beams) from a Set A of beams using measurement results from another Set B of beams.

[0007] According to Technical Report (TR) 38.843, the spatial-domain beam prediction for Set A of beams is based on measurement results of Set B of beams, whereas the temporal beam prediction for Set A of beams is based on the historic measurement results of Set B of beams.

[0008] Set A and Set B of beams have not been defined yet, however, the following two examples illustrate some scenarios that will likely be studied in Release 18:- Set B is a subset of a Set A. This example is illustrated in Figure 3. Figure 3 illustrates a grid-of-beam type radiation pattern: Each row (resp. column) depicts a certain zenith (resp. azimuth) angle from the antenna array. Set A 302 has 8 beams and Set B 304 has 4 beams (indicated by dark circles). For example, Set A 302 is a set of 8 Synchronization Signal block (SSB) / CSI- reference signal (RS) beams shown in Figure 3 (both light and dark circles). The UE measures Set B 304 (the 4 beams indicated by dark circles). The AI / ML model should predict the best beam (or beams) in Set A 302 using only measurements from Set B 304.Set A and Set B correspond to two different sets of beams. This example is illustrated in Figure 4, where Set A 402 is a set of narrow beams and Set B 404 is a set of wide beams. For example, Set A 402 is a set of 30 narrow CSI-RS beams, and Set B 404 is a set of 8 wide SSB beams. The UE measures beams in Set B 404 and the AI / ML model should predict the best beam(s) from Set A 402.

[0009] The beam prediction can be performed in the gNB and in the UE, and the gain is twofold. From the UE point of view, the UE would be able to generate good radio measurement estimations without really measuring certain resources, thereby saving energy, whereas from the gNB point of view, the gNB can get good radio measurements estimation from the UE without providing the measuring resources, thereby limiting the overhead over the air-interface.

[0010] Whether the UE can perform the beam prediction on a certain set of resources with a certain accuracy, depends on the applicability conditions of an AIML model / function. In particular, an AIML model / function may be trained to perform the beam prediction under certain applicability conditions. Such applicability conditions may need to be fulfilled in order for the AIML model / function to generate the expected output, i.e. beam prediction for this use case, with enough accuracy. The applicability conditions may include a set of parameters / variables under which the AIML model / function was trained. Such set may include for example UE-specific conditions under which the model was trained, such as the UE speed, the UE antenna shape, UE sensors information such as UE orientation, motion sensors etc; whereas some other parameters / variables may depend on the specific network configuration under which the model was trained, e.g. the deployment scenario (e.g. indoor / outdoor), the carrier frequency, the gNB Transmit (TX) port number, the gNB TX power, etc.

[0011] In order to determine whether an AIML model / function is applicable or not, the UE may need to assess the applicability conditions of such AIML model / function with respect to the output (beam prediction) that may need to be generated and received input (e.g. radio measurement resources configured by the gNB).

[0012] Such applicability conditions may need to be checked in general for any AIML model / functionality, i.e. not only for the use case of beam prediction, because it is fundamental that while doing the inference, the UE / gNB status matches the UE / gNB status experienced during the training so that the trained data set can generate accurate predictions, based on the model inputs during the inference. Hence, taking as an example the use case of AIML for mobility, in order for the UE to generate accurate handover predictions or cell-level measurement predictions, it is fundamental that the configurations of neighboring cells during the inference matches the configuration during the training.Applicability reporting

[0013] Related to the discussion above, the applicability reporting has been discussed during the Release 18 study item. The applicability reporting allows the UE to inform the gNB about the applicability of a UE-side AIML model / functionality while the UE is connected to this gNB. An AIML model / functionality may be applicable or not depending on a number of factors, so called applicability conditions, that are only partly under the control of the gNB.

[0014] The applicability conditions can be categorized into:• UE-side conditions• NW-side conditions

[0015] The UE- and NW-side conditions are those UE and NW characteristics / configurations at the time of the UE-side model training, and around which the UE-side model was generated. In order for such an AIML model to properly operate and generate optimal results, it is necessary that during the inference those UE and NW characteristics / configurations matches the training phase.

[0016] More specifically, the UE side conditions may include the UE location, the UE speed, the inputs of various UE sensors, and various device characteristics / properties that may depend on the hardware / software versions of the UE chipset.

[0017] The NW-side conditions may be instead:• Mapping relationship of Set A and Set B, including ordering (a set of identifiers (IDs), or resource)• Consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B.• Quasi Co Location (QCL) assumption• gNB transmission power• UE distribution• antenna height• deployment scenarios (e.g., Inter Site Distance (ISD), Urban Micro-cells (Umi) / Urban Macro-cells (Uma))

[0018] In general, it is assumed that the UE- and NW-side conditions that the UE may need to experience during the inference cannot be known a priori by the gNB, especially if UE-side model is not trained and generated by the gNB. For example, whether the UE has an AIML model that is applicable given the current location of the UE, or given the current speed of the UE, is not something that the network can control or it can know. Similarly, the network cannot ‘remember’ the set of beams in which the UE performed the data collection for the purpose of UE-side model training, and hence it cannot know the set A / B configuration that the UE may need for the AIML inference. As said, the above is especially true if the UE-side model is not trained and generated by the gNB, which is the typical assumption. Rather, it is typically assumed that the UE-side model is trained and generated by a training entity / function / node outside the RAN, such as an Over-the-Top (OTT) server or Core Network (CN) function controlled by the UE-vendor or by the Mobile Network Operator (MNO). In such case, the gNB might not even know if a certain AIML model / functionality, that according to the UE capabilities it is supported by the UE, is available at the UE, e.g. the AIML model / functionality may not have been downloaded yet from the training entity, or simply the UE has not performed data collection the purpose of UE-side model training for the concerned model / functionality.

[0019] Thus, the applicability reporting is a crucial tool that allows the UE to report to the network information around the applicability of the AIML models / functionalities, and possibly to report to the gNB also the operating conditions (called above applicability conditions) that the UE may need in order to perform an efficient inference. Based on the reported applicability conditions, the network can identify the necessary inference configuration and decide whether to activate or not the AIML functionality.

[0020] Two types of applicability reporting were identified during the Release 18 study item, i.e. the proactive reporting and the reactive reporting. The reactive reporting implies the gNB inquiring the UE about the applicability of AIML model / functionality, and the UE responding with the AIML models / functionalities that are applicable, whereas with the proactive reporting UE signals to the network autonomously, i.e. without any inquiry, about the AIML model / functionalities that are applicable.

[0021] The former, i.e. reactive reporting can be used for example in response to a network configuration e.g. inference related configuration, including for example beam resourceconfiguration of Set A and / or Set B. The UE will then respond indicating if the AIML model / functionality is applicable based on this inference configuration.

[0022] The latter, i.e. the proactive reporting can be configured to the UE to allow the UE to report at any point in time a change in the applicability of an AIML model / functionality, i.e. an AIML model / functionality that was not applicable becomes applicable or vice versa. From signaling procedure point of view, an example of reactive reporting is illustrated in Figure 5, which comprises the following steps: step 502: Network sends UECapabilityEnquiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities; step 504: UE sends UECapability Information message to network, containing supported functionalities at the UE side; step 506: Network provides network configurations and initiates UE to report its applicable functionalities; step 508: UE sends applicable functionalities to network; step 510: Network sends updated inference configuration for applicable functionalities reported in Step 508 to the UE; and step 512: Start inference / monitoring based on network / UE activation / deactivation.

[0023] As shown in step 512, a “supported functionality” (e.g. beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) is activated, to refer to functionalities which are activated and for which a UE is performing inference, in response to a network configuration in step 506.

[0024] Even though the messages that may be needed to realize the reactive approach have not been discussed yet, it seems reasonable from a technical point of view, that step 506 is conveyed in an RRCReconfiguration message (carrying e.g. the inference configurations for the AIML inference), and step 508 is conveyed in an RRCReconfigurationComplete (where the UE can signal its applicable functionalities based on the inference configurations received in step 506).

[0025] From signaling procedure point of view, an example of proactive reporting is illustrated in Figure 6, which comprises the following steps: step 602: Network sends UECapability Enqiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities; step 604: UE sends UECapability Information message to network, containing supported functionalities at the UE side;step 606: Network configures UE that it is allowed to provide its applicable functionalities; step 608: UE sends applicable functionalities to network upon change of applicable functionality / conditi on; step 610: Network sends inference configuration for the applicable functionalities to the UE; and step 612: Start inference / monitoring based on network / UE activation / deactivation.

[0026] Even though the messages that may be needed to realize the proactive approach have not been discussed yet, it seems reasonable from a technical point of view, that step 606 is conveyed in an RRC Reconfiguration message configuring the UE to report the applicable functionalities via UE Assistance Information (UAI), and step 608 is conveyed, as a consequence, in the UE Assistance Information message itself. That is because the UAI was designed to give the possibility for the UE to signal at any point in time certain recommendations to the network, such as recommended Discontinuous Reception (DRX) or MIMO preferences.

[0027] For example, via UAI, the UE may signal to the gNB its DRX preference, its preferred MIMO layer configuration, its preferred maximum number of component carriers, etc, or indications to reduce device overheating (e.g. including various indications to reduce the number of MIMO layers, to reduce the maximum aggregated bandwidths, to reduce the number of component carriers, etc), or to indicated to the gNB in-device coexistence issues.

[0028] Hence, in the context of AIML, the UAI can be used by the UE to signal its recommended radio configuration in order for an AIML functionality to be applicable, or simply the UE can signal that a previously applicable AIML functionality is not any longer applicable, or vice versa.

[0029] There currently exist certain challenge(s). The legacy UAI framework is used by the UE to signal general recommendations to the network, which are in current specification not specifically related to a certain gNB, or cell or frequency. In fact, all the existing UAI information signalled by the UE to a first gNB to which the UE is currently connected may also be of interest to a second gNB to which the UE may be handed over at a later point in time.

[0030] On the other hand, a UE-side AIML functionality may be applicable when operating under a first gNB / cell / frequency, but it may not be applicable when the UE moves to a second gNB / cell / frequency. Or in another case, such UE-side AIML functionality may be applicable both in the first and second gNB / cell / frequency, but the applicability conditions may be different. In yet another case, the said UE-side AIML functionality may not be applicable onlyin the first gNB / cell / frequency, and in the second gNB / cell / frequency the UE may have another UE-side AIML functionality applicable.

[0031] Hence, given the above observations, the applicability conditions, and hence the configurations that the UE may need from the network in order to apply a certain AIML model / functionality, may depend on the specific gNB / cell / frequency in which the AIML model / functionality would operate. The information carried today in the UAI does not specify any validity information, e.g. gNB / cell / frequency, of the carried information, which would make it difficult / impossible for the network to properly configure the UE with an appropriate AIML inference configuration that in turn would make a UE-side AIML model / functionality applicable.

[0032] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges.

[0033] In a first aspect of the disclosure, a method is performed by a UE supporting one or more ML functionalities. The method comprises transmitting, to a first network node, an information message. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0034] In a second aspect of the disclosure, a method is performed by a first network node. The method comprises receiving, from a UE supporting one or more ML functionalities, an information message. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0035] In a third aspect of the disclosure, a method is performed by a second network node. The method comprises receiving an information message from a first network node. The firstnetwork node is connected to a UE supporting one or more ML functionalities. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0036] In a fourth aspect of the disclosure, there is provided a UE supporting one or more ML functionalities. The UE is configured to transmit, to a first network node, an information message. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0037] In a fifth aspect of the disclosure, there is provided a first network node. The first network node is configured to receive, from a UE supporting one or more ML functionalities, an information message. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0038] In a sixth aspect of the disclosure, there is provided a second network node. The second network node is configured to receive an information message from a first network node. The first network node is connected to a UE supporting one or more ML functionalities. The information message comprises an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more firstconditions for the one or more ML functionalities to be applicable by the UE. The information message further comprises a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid. The one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

[0039] In a seventh aspect of the disclosure, there is provided a computer-readable medium storing code which, when executed by processing circuitry of a UE, causes the UE to perform a method according to embodiments of the first aspect.

[0040] In an eighth aspect of the disclosure, there is provided a computer-readable medium storing code which, when executed by processing circuitry of a first network node, causes the first network node to perform a method according to embodiments of the second aspect.

[0041] In a ninth aspect of the disclosure, there is provided a computer-readable medium storing code which, when executed by processing circuitry of a second network node, causes the second network node to perform a method according to embodiments of the third aspect. In embodiments of the present disclosure, a UE indicates to the network information about which AI / ML functionality is applicable. In addition, the UE also indicates to the network when / whether that applicability information is valid. With this validity information, the function applicability information may be determined as invalid when the UE changes cell. For example, function X and Y may be determined as applicable when the UE is in a first cell, but when the UE moves to a second cell, the function X and Y may no longer be applicable. This can be indicated using the methods described herein.

[0042] Certain embodiments may provide one or more of the following technical advantage(s).

[0043] Embodiments of the present disclosure allow the UE to report different UE assistance information based on the gNB / cell / frequency to which the said assistance information relates. Based on that, the gNB receiving the UE Assistance Information can determine whether to provide the UE with appropriate inference configurations (e.g. in the event that the UE Assistance Information relate to applicability conditions for the gNB) and / or to inform neighbouring gNBs of the UE Assistance Information (e.g. in the event that the UE Assistance Information relates to applicability conditions of the neighbouring gNB). In the latter case, embodiments of the present disclosure allow neighbouring nodes to prepare, in advance, appropriate inference configurations for the UE, so that the UE can possibility continuing performing AIML inference without any discontinuity due to handovers.

[0044] The teachings of certain embodiments may improve the performance of a UE when performing AIML inference.BRIEF DESCRIPTION OF THE DRAWINGS

[0045] For a better understanding of the embodiments of the present disclosure, and to show how it may be put into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0046] Fig. 1 is a schematic diagram illustrating training and inference pipelines, as well as their interactions within a model lifecycle management procedure;

[0047] Fig. 2 illustrates a functional framework for studying AI / ML model LCM aspects;

[0048] Fig. 3 illustrates a grid-of-beam type radiation pattern for a set of beams;

[0049] Fig. 4 illustrates grid-of-beam type radiation patterns for a set of narrow beams and a set of wide beams;

[0050] Fig. 5 illustrates an example signalling diagram for reactive reporting;

[0051] Fig. 6 illustrates an example signalling diagram for proactive reporting;

[0052] Fig. 7 is a flow chart illustrating a method in accordance with some embodiments;

[0053] Fig. 8 is a flow chart illustrating a method in accordance with some embodiments;

[0054] Fig. 9 is a flow chart illustrating a method in accordance with some embodiments;

[0055] Fig. 10 shows an example of a communication system in accordance with some embodiments;

[0056] Fig. 11 shows a UE in accordance with some embodiments;

[0057] Fig. 12 shows a network node in accordance with some embodiments; and

[0058] Fig. 13 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.DETAILED DESCRIPTION

[0059] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0060] For embodiments of the present disclosure, signalling of an applicability indication may imply any one or more of the following:• Indicating whether an AIML model / functionality is applicable or not applicable.• The UE-side conditions for the AIML model / functionality to be applicable• The NW-side conditions for the AIML model / functionality to be applicable, e.g., including the set A / set B of beams recommended by the UE for the AIML inference (see above)

[0061] In the present disclosure, the term ‘inference configuration’ may refer to a radio configuration transmitted by the gNB to the UE for configuring the UE to perform the AIML inference according to an AIML model / functionality.

[0062] Embodiments of the present disclosure relate to methods by which a UE may indicate to a network the applicable AI / ML related model / functionality for the UE (e.g., which AI / ML model / functionality is applicable, which AI / ML model / functionality is not applicable and / or the applicability conditions for the AIML model / functionality to be applicable or not applicable). In particular embodiments, this applicability info may be sent to the network using UE assistance information signalling.

[0063] Figure 7 depicts a method in accordance with particular embodiments. The method of Figure 7 may be performed by a UE or wireless device (e.g. the UE 1012 or UE 1100 as described later with reference to Figures 10 and 11 respectively) supporting one or more ML functionalities (e.g., an ML model).

[0064] The one or more ML functionalities may relate to any functionality of the UE and / or the network. For example, the ML functionalities may comprise one or more of: an ML model or functionality to compress or decompress information and data transmitted between the UE and the network (e.g., measurement reports such as CSI, etc); an ML model or functionality to classify line-of-sight and / or non-line-of-sight conditions between the UE and one or more network nodes; an ML model or functionality to select one or more transmission / reception beams at the UE and / or a network node; and an ML model or functionality to select or determine a precoding policy for MIMO at the UE and / or a network node.

[0065] The one or more ML functionalities may be applicable by the UE when one or more first conditions are fulfilled. The one or more first conditions may comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained. For example, the one or more ML functionalities may be applicable (e.g., used for inference) by the UE and / or the network when the radio configuration of the UE and / or the network at the point of inference matches or sufficiently corresponds to the radio configuration of the UE and / or the network under which the one or more ML functionalities were trained.

[0066] The method begins at step 702 with transmitting, to a first network node, aninformation message which may comprise assistance information (e.g., a UE Assistance Information Message). The information message may comprise an applicability indication and a validity indication.

[0067] The applicability indication may indicate one or more of: whether or not the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE.

[0068] The validity indication may indicate one or more second conditions (e.g., determined by the UE) relating to the UE for the applicability indication (e.g., and / or the information message itself) to be valid. For example, the validity indication may indicate one or more second conditions relating to the UE for the information message to be valid. The one or more second conditions may comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels. The applicability indication (and / or the information message itself) may be valid when the one or more second conditions are fulfilled. If the one or more second conditions are not fulfilled (e.g., the UE is not using the cell(s), cell type(s), signal(s), channel(s), transmission frequency(ies), is not connected to the network node(s), the applicability indication (and / or the information message itself) may be invalid.

[0069] The validity indication for at least one of the one or more second conditions may be implicit. For example, the implicit validity indication may comprise an absence of an explicit validity indication. The second condition for which the validity indication is implicit may be that the applicability indication is valid only for a radio environment in which the information message is transmitted by the UE (e.g., a cell ID, one or more transmission frequencies used by the UE, the network node, etc). That is, the absence of an explicit validity indication may be intended by the UE, and interpreted by the network node receiving the information message, as an implicit indication that the applicability indication or information message is valid only for the radio environment in which the information is transmitted (and is otherwise invalid).

[0070] Additionally or alternatively, the validity indication may comprise an explicit indication of at least one of the one or more second conditions.

[0071] The UE may transmit the information message (e.g., in step 702), retransmit the information message (e.g., in a step corresponding to step 702), and / or transmit an updated information message to the first network node responsive to: the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfilment of one or more radio conditions.

[0072] The configuration for transmitting information messages may indicate: at least one ML functionality for which the UE is allowed to provide the applicability indication; and / or at least one second condition for which the UE is allowed to provide the validity indication.

[0073] The method of Figure 7 may further comprise, at step 704, the UE receiving, from the first network node, one or more inference configurations associated with the one or more ML functionalities. The one or more inference configurations may be based on the information message. The one or more inference configurations may comprise information corresponding to the validity indication. For example, the one or more inference configurations may configure the UE to apply the one or more ML functionalities when both the one or more first and one or more second conditions are fulfilled.

[0074] The one or more inference configurations may comprise the first or second inference configurations discussed below in relation to Figures 8 and / or 9, and / or the inference configurations discussed below in the sections entitled “UE actions in response of transmitting the UE Assistance Information” and / or “Network behaviour”.

[0075] Figure 8 depicts a method in accordance with particular embodiments. The method of Figure 8 may be performed by a first network node, such as a Radio Access Network (RAN) node (e.g. the network node 1010 or network node 1200 as described later with reference to Figures 10 and 12 respectively).

[0076] The method begins at step 802 with receiving, from a UE supporting one or more ML functionalities (e.g., an ML model), an information message which may comprise assistance information (e.g., a UE Assistance Message). The one or more ML functionalities may relate to any functionality of the UE and / or the network. For example, the ML functionalities may comprise one or more of: an ML model or functionality to compress or decompress information and data transmitted between the UE and the network (e.g., measurement reports such as CSI, etc); an ML model or functionality to classify line-of-sight and / or non-line-of-sight conditions between the UE and one or more network nodes; an ML model or functionality to select one or more transmission / reception beams at the UE and / or a network node; and an ML model or functionality to select or determine a precoding policy for MIMO at the UE and / or a network node.

[0077] The one or more ML functionalities may be applicable by the UE when one or more first conditions are fulfilled. The one or more first conditions may comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained. For example, theone or more ML functionalities may be applicable (e.g., used for inference) by the UE and / or the network when the radio configuration of the UE and / or the network at the point of inference matches or sufficiently corresponds to the radio configuration of the UE and / or the network under which the one or more ML functionalities were trained.

[0078] The information message may comprise an applicability indication and a validity indication.

[0079] The applicability indication may indicate one or more of: whether or not the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE.

[0080] The validity indication may indicate one or more second conditions (e.g., determined by the UE) relating to the UE for the applicability indication (e.g., and / or the information message itself) to be valid. For example, the validity indication may indicate one or more second conditions relating to the UE for the information message to be valid. The one or more second conditions may comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels. The applicability indication (and / or the information message itself) may be valid when the one or more second conditions are fulfilled. If the one or more second conditions are not fulfilled (e.g., the UE is not using the cell(s), cell type(s), signal(s), channel(s), transmission frequency(ies), is not connected to the network node(s), the applicability indication (and / or the information message itself) may be invalid.

[0081] The validity indication for at least one of the one or more second conditions may be implicit. For example, the implicit validity indication may comprise an absence of an explicit validity indication. The second condition for which the validity indication is implicit may be that the applicability indication is valid only for radio environment in which the information message is transmitted by the UE (e.g., a cell ID, one or more transmission frequencies used by the UE, the network node, etc). That is, the absence of an explicit validity indication may be intended by the UE, and interpreted by the network node receiving the information message, as an implicit indication that the applicability indication or information message is valid only for the radio environment in which the information is transmitted (and is otherwise invalid).

[0082] Additionally or alternatively, the validity indication may comprise an explicit indication of at least one of the one or more second conditions.

[0083] The method may further comprise the first network node determining, based on the information message, the one or more second conditions.

[0084] The first network node may receive the information message (e.g., in step 802), aretransmitted information message (e.g., in a step corresponding to step 802), and / or an updated information message from the UE responsive to: the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfilment of one or more radio conditions.

[0085] Thus, in the first example set out above, prior to step 802 the first network node may transmit an indication of a configuration for transmitting information messages (such as the UE assistance information). The configuration for transmitting information messages may indicate: at least one ML functionality for which the UE is allowed to provide the applicability indication; and / or at least one second condition for which the UE is allowed to provide the validity indication.

[0086] The method of Figure 8 may further comprise the first network node determining one or more first inference configurations associated with the one or more ML functionalities. The one or more first inference configurations may correspond to the inference configurations discussed in relation to Figure 7 or below in the sections entitled “UE actions in response of transmitting the UE Assistance Information” and / or “Network behaviour”.

[0087] The one or more first inference configurations may be based on the information message. The one or more first inference configurations may comprise information corresponding to the validity indication. For example, the one or more inference configurations may configure the UE to apply the one or more ML functionalities when both the one or more first and one or more second conditions are fulfilled.

[0088] At step 804 of Figure 8, the first network node transmits, to the UE, the one or more first inference configurations.

[0089] The method of Figure 8 may further comprise the first network node transmitting, to a second network node (e.g., a RAN node) capable of communicating with the UE: the information message; or at least part of the information message. The at least part of the information message may comprise the applicability indication and at least one second condition associated with radio resources of the second network node. This step may correspond to step 902 discussed in relation to Figure 9.

[0090] The second network node be a neighbour network node of the first network node (e.g. , a network node with which the first network node has a direct interface, such as an Xn interface) and / or or a target network node for the UE. For example, the first network node may be capable of handing over the UE to the second network node. As such, the applicability indication and validity indication may be of interest to the second network node as the second network nodemay serve the UE in future.

[0091] The method of Figure 8 may further comprise the first network node receiving, from the second network node, one or more second inference configurations. This step may correspond to step 904 discussed in relation to Figure 9. The one or second inference configurations may correspond to the inference configurations discussed in relation to Figure 7 or discussed below in the sections entitled “UE actions in response of transmitting the UE Assistance Information” and / or “Network behaviour”.

[0092] The one or more second inference configurations may be based on the information message or the at least part of the information message transmitted to the second network node. The one or more second inference configurations may comprise information corresponding to the validity indication. That is, the one or more second inference configurations may configure the UE to apply the one or more ML functionalities when both the one or more first and one or more second conditions are fulfilled.

[0093] The method of Figure 8 may further comprise the first network node transmitting, to the UE, the one or more second inference configurations.

[0094] Figure 9 depicts a method in accordance with particular embodiments. The method of Figure 9 may be performed by a second network node, such as a RAN node (e.g. the network node 1010 or network node 1200 as described later with reference to Figures 10 and 12 respectively).

[0095] The method begins at step 902 with receiving an information message from a first network node (e.g., a RAN node). The first network node may be connected to a UE supporting one or more ML functionalities (e.g., an ML model). The second network node may be a neighbour network node of the first network node (e.g., the second network node may have a direct interface with the first network node) and / or a target network node for the UE. For example, the first network node may be capable of handing over the UE to the second network node.

[0096] The information message may comprise an applicability indication and validity indication. The information message, applicability indication, and / or validity indication may correspond to those discussed above in relation to Figures 7 and / or 8.

[0097] The applicability indication may indicate one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE.

[0098] The validity indication may indicate one or more second conditions relating to the UE for the applicability indication to be valid.

[0099] The method of Figure 9 may further comprise the second network node determining one or more second inference configurations associated with the one or more ML functionalities. The one or more second inference configurations may be based on the information message.

[0100] The one or more second inference configurations may correspond to the one or more second inference configurations discussed in relation to Figure 8. The one or second inference configurations may also correspond to the inference configurations discussed in relation to Figure 7 or below in the sections entitled “UE actions in response of transmitting the UE Assistance Information” and / or “Network behaviour”.

[0101] At step 904, the method comprises transmitting, to the first network node, the one or more second inference configurations.

[0102] The above embodiments are now discussed in more detail. While the embodiments below discuss validity indications (also referred to herein as “validity info”) that indicates a validity of assistance information, it should be appreciated that the described validity indications may also be utilized (in complementary embodiments) to indicate a validity of applicability conditions and / or applicability indications, rather than the entirety of the assistance information.

[0103] Furthermore, whilst the embodiments below and herein may discuss “assistance information” included in a “UE Assistance Information message”, it should be appreciated that any appropriate information type and / or appropriate message type may be utilized to notify the network of the discussed validity indications and applicability indications.UE sends validity info for assistance info

[0104] As described above, the UE can indicate which AI / ML related model / functionality is applicable and not. Additionally or alternatively, the UE can indicate for the AIML model / functionality the applicability conditions for the said AIML model / functionality to be applicable. These applicability indications (which may also be referred to herein as applicability info or applicability information) may correspond to the applicability indications discussed above in relation to Figures 7 to 9.

[0105] However, the applicability of the AIML model / functionality may change when the UE changes situation (e.g., changes radio environment or radio configuration). Therefore, according to some embodiments, the UE may transmit a validity indication (which may also be referred to herein as validity info or validity information) associated with the assistance information (i.e. the assistance info which is carrying the function applicability information).Therefore, in some cases, an AIML model / functionality may be applicable when associated to a certain validity info, but it may not be applicable when associated to another validity info, or it may have different applicability conditions when associated to different validity info. This validity info may correspond to the validity indication discussed above in relation to Figures 7 to 9.

[0106] The validity info may indicate (explicitly or implicitly) the situations in which the assistance info is valid or not. For example, the assistance info may only be valid when the UE is associated to a certain radio resource, e.g. to a certain cell or channel or signal or frequency or type of cell (macro / pico), etc. This means that, if the UE were to be associated to a different radio resource, the assistance information may be (at least partly) invalid, or that the validity of the assistance information is unknown. The UE sends this validity info (e.g., as part of step 702 of Figure 7 or step 802 of Figure 8) to the network, allowing the network to know in which situations the assistance info is valid. The network may then, based on the validity info, determine in which situations the assistance info is valid.

[0107] For example, the UE may consider the assistance information valid only in the current cell and not valid (or that the validity is unknown) when moving to another cell. As such, the UE may indicate that the assistance information is not valid (or that the validity is unknown) if the UE changes / is to change cell. In another approach, the assistance information is associated with a validity duration, e.g. a few minutes or until a certain time.

[0108] In some embodiments, the assistance info may only be considered valid in the situation (e.g., the radio environment) that the UE was in when the UE sent the assistance info to the network. For example, the assistance information may only be considered valid for a current cell serving the UE. In this case, explicit validity info may not need to be sent to the network. Instead, the UE and the network may both be configured to determine (e.g., via an implicit validity indication included in the assistance information) that the assistance information is valid only in the current situation (e.g. in the current cell / radio resource / configuration / etc.). In this case, validity info signalling (particularly explicit validity info signaling) may not need to be supported by the UE and network.

[0109] In some embodiments, the validity info may be signaled to the network (e.g., fields may be added to UE signalling to make it possible for the UE to signal validity info) but, where the UE omits such fields, it may be interpreted as the assistance information being valid only within the current situation (e.g. in the current cell / radio resource / configuration, or serving cells / gNBs, etc.). That is, the validity indication may be an implicit indication, such as the absence of an explicit validity indication. However, if the UE wants to indicate that the validityinfo is valid also in other situations, the UE can indicate those other situations, e.g., explicitly indicate other cells which the assistance info is also valid in.

[0110] In other embodiments, if for a certain validity info the UE does not indicate the applicability conditions for an AIML model / functionality, e.g. the UE Assistance Information associated to a certain validity info is empty, then the UE may not have an available AIML model / functionality for the said validity info. That is, there may be no available AIML model / functionality to operate in the cells / gNBs / frequencies associated to such validity info.Assistance info valid in sets of radio resources (e.g. cells)

[0111] The UE may determine and indicate to the network that the assistance information is valid when associated to a set of one or more radio resources, e.g. to a set of cells, a set of channels, a set of signals, a set of frequencies, and / or a set of cell types (macro / pico), etc. In another example, the set of radio resources are those resources associated to a certain gNB. For example, the assistance information may be valid in an area (e.g., a set of cells) bigger than just one cell. The UE could then indicate the set of cells to the network. The set of cells can be expressed with a group identifier for cells, e.g. using a Tracking Area Code, a Registration Area Code, a Public Land Mobile Network (PLMN), an non-public network identifier, etc.

[0112] As noted above, the UE may indicate, in an information message (e.g., a UE Assistance Information message) the validity info and the associated applicability conditions for one or more AIML model / functionality. The validity info could be represented by an identifier of the cells, the gNBs, the frequencies in which the applicability conditions of an AIML model / functionality are valid for. For example, the UE may include the list of cells or gNBs or frequencies associated to which certain applicability conditions are valid for one or more AIML models / functionalities.First and second assistance info

[0113] The UE may determine first assistance information valid when associated with a first radio resource (or set of radio resources), and the UE may determine second assistance information valid when associated with a second radio resource (or set of radio resources). The UE sends both the first and second assistance info to the network (e.g., in a UE Assistance Information message and / or the information message discussed in relation to Figures 7 to 9) and indicates validity info for the first assistance info and validity info for the second assistance info. Depending on whether the UE is associated with the first or second radio resource, the network may apply the corresponding assistance information.UE resends assistance info when moving to second radio resource

[0114] In some embodiments, the UE may not indicate that the assistance information is only applicable when associated with a certain radio resource, but instead, the UE may trigger a new transmission of assistance information (e.g., in a UE Assistance Information message and / or the information message discussed in relation to Figures 7 to 9) in case the UE changes radio resource. The new assistance information would be adapted to be valid when associated with the new radio resource. For example, if the UE moves from cell A to cell B and the assistance info is valid then the UE re-sends the assistance info to cell B. However, if the UE later moves to cell C where the assistance info is not valid, the UE does not send the assistance info to cell C, or the UE sends other (e.g., updated) assistance information (which may be empty assistance info).Regarding the one-second-rule

[0115] In some embodiments, if the UE is moved (e.g. due to a mobility procedure such as handover) from a first radio resource / cell / network node etc. to a second radio resource / cell / network node etc. the UE may determine if previously indicated assistance information is valid when associated with the second radio resource. If the assistance information is still valid, the UE may resend the assistance information (e.g., in a UE Assistance Information message and / or the information message discussed in relation to Figures 7 to 9) after moving to the second radio resource if the UE sent the assistance information shortly before the mobility procedure (e.g., one second or less). However, if the UE determines that the assistance information is not valid in the second cell, the UE may refrain from sending anything to the second network node.When to transmit the applicability conditions including the validity info

[0116] The UE may determine that assistance information (e.g., the applicability conditions) that the UE has already sent to the network has a different validity than indicated. For example, it may also be valid in a cell which the UE didn’t indicate yet. The UE may then send updated validity info (e.g., in an updated information message) to the network, which the network may then apply to updated already -received assistance information.

[0117] In another example, an AIML model / functionality associated to a certain validity info that was indicated as applicable in a previous UE Assistance Information message may no longer be considered applicable for the same validity info, or vice versa. This can happen for anumber of different reasons, such as change in the UE-side conditions, or change in the NW- side conditions. For example, the UE may have received from the network a new configuration that affects the applicability of the AIML model / functionality for the concerned validity info. The UE may then send updated validity info and / or an updated applicability indication (e.g., in an updated information message) to the network.

[0118] In yet another example, the AIML model / functionality associated to a certain validity info (that was indicated as applicable in a previous UE Assistance Information message) may still be applicable, but it is considered by the UE to be applicable under different applicability conditions (e.g. different NW-side conditions such as different set A / B). The UE may then send an updated applicability indication (e.g., in an updated information message) to the network.

[0119] In further embodiments, the UE may additionally or alternatively transmit the UE Assistance Information message upon fulfilling certain radio conditions. For example, the UE may determine that the cell quality of a neighbouring cell is becoming better than the cell quality of the serving cell. In this case, the UE may transmit the UE Assistance Information message to the gNB including the applicability conditions and the related validity info associated to such neighbouring cell. In one method, this transmission may only occur if the applicability conditions and the related validity info associated to such neighbouring cell were not previously sent, or were not sent in the last time window. This embodiment may apply to any case in which the UE transmits a radio measurement report following any mobility event, e.g. A3, A5.

[0120] In some embodiments, the UE may transmit the UE Assistance Information message (including the validity info for the applicability conditions) if it has received a radio configuration (which may correspond to the configuration for transmitting information messages discussed above in relation to Figures 7 and 8). For example, the UE may transmit the UE Assistance Information message only if it has received a radio configuration. The radio configuration may configure the UE to perform measurements in cells / gNBs / frequencies associated to such validity info. In this case, the UE does not transmit the applicability conditions associated to cells / frequencies that the UE has not been configured to measure.Configuration of the UE Assistance Information

[0121] The configurations discussed in this section may correspond to the configuration for transmitting information messages discussed above in relation to Figures 7 and 8.

[0122] In one method, the validity info for which the related applicability conditions shouldbe reported by the UE are indicated by the gNB. For example, the gNB may include in the configuration of the UE Assistance Information the list of cells / gNBs / frequencies for which the UE is allowed to report its applicability conditions. The gNB for example may exclude from the configuration those gNBs towards which there is no direct (e.g., Xn) interface, or it may exclude all those cells which are not hosted by the said gNB.

[0123] In another method, the gNB may configure the UE to report the applicability conditions and the associated validity info for any AIML model / functionality that the UE has currently available.

[0124] In yet another method, the gNB may configure the UE to report the applicability conditions and the associated validity info only for certain AIML model / functionality. The gNB can, for example, determine from the UE capability the AIML models / functionalities that the UE supports, and from such information, the gNB can configure the UE to report the applicability conditions only for the AIML models / functionalities that are of interest of the gNB. If the UE does not include any applicability conditions for a configured AIML model / functionality associated to a certain validity info, then this is interpreted as the UE not having available the AIML model / functionality associated to the said validity info, i.e. no AIML model / functionality available to operate in the cells / gNBs / frequencies associated to the said validity info.UE actions in response of transmitting the UE Assistance Information

[0125] In response to transmitting the UE Assistance Information according to the above methods, the UE may receive one or more inference configurations (e.g., the one or more (first or second) inference configurations discussed in relation to Figures 7 to 9) associated to the AIML models / functionalities signalled in the UE Assistance Information message. This may correspond to steps 704 of Figure 7 and step 804 of Figure 8. The inference configurations may be valid as per the validity info signalled in the UE Assistance Information message. For example, the network may provide the inference configurations for certain cells / gNBs / frequencies and indicate that the UE should apply those inference configurations when operating / connecting to those cells / gNBs / frequencies. In such case, the inference configurations also include the validity info.

[0126] For example, the inference configurations may be transmitted by the gNB as part of a mobility command, such as Radio Resource Control (RRC) reconfiguration with sync for the Primary Cell (PCell), or for the Primary Secondary Cell (SCell) (PSCell) change / addition. In another example, the inference configurations are stored by the UE memory in a local variable,and applied only if and when the UE connects to a cell / gNB / frequency whose validity info is present in at least one of the said inference configurations. For example, the UE applies at least one of the stored inference configurations when it executes the handover to a target PCell or the PSCell change / addition. In yet another example, the inference configuration(s) are included in a Conditional Handover (HO) (CHO) or Conditional PSCell Addition / Change (CP AC) configuration for a certain candidate target Special Cell (SpCell), so that the UE applies one or more of such inference configurations if the UE executes the handover or PCell change / addition towards such candidate target SpCell.Network behaviour

[0127] The network (e.g., a first network node) may receive assistance information from the UE (e.g., as part of step 702 of Figure 7 and / or 802 of Figure 8) and may consider it valid or invalid according to the validity info. If the situation changes for the UE, e.g., the UE is handed over to another radio resource (e.g., handed over from the first network node to a second network node), the network may then consider the assistance information invalid or obsolete.

[0128] One approach to achieve this is that a first network node associated with the first radio resource omits the assistance information received from the UE when sending information about the UE to a second network node. For example, the UE's context may be adjusted so the assistance information is removed from it before being sent to the second network node. This ensures that the second network node does not have any assistance information which is invalid. For example, if the UE includes (in the assistance information) applicability conditions associated to validity info that are not of interest for the second network node (e.g. validity info associated to any other node different from the second), the first network node does not transmit said applicability conditions to the second network node.

[0129] Another approach to achieve this is for the first network node to send the assistance information to the second network node, but the second network node ignores, or otherwise does not make use of, the assistance information that it receives from the first network node. This has the benefit that, when the UE is moved back to the first network node, the assistance information may again be valid and hence could be used by the first network node.

[0130] In other embodiments, the first network node determines from the UE Assistance Information and from the validity info therein included, whether the signalled applicability indications are of interest for the first network node or for another network node. For example, if the validity info pertains the first network node, the first network node determines that the applicability conditions are for the first network node to configure the AIML inference. In suchcase, the first network node may select the AIML models / functionalities that the UE may apply when being configured, for example, with a certain cell or frequency hosted / controlled by the first network node. Accordingly, the first network node may select a proper inference configuration such that the said AIML models / functionalities can be applied by the UE.

[0131] If the validity info (additionally or alternatively) pertains to a second network node, the first network node may transmit parts of the received UE Assistance Information in a first message to the second network node. This may correspond to step 902 of Figure 9. For example, the first network node may extract from the UE Assistance Information the applicability conditions of the one or more AIML models / functionalities pertaining to the second network node, and transmit those to the second network node (e.g., via the Xn interface).

[0132] The first message may be transmitted as part of an HO preparation for an ordinary handover or for a conditional handover, or for conditional PSCell change / addition.

[0133] The second network node may then determine one or more inference configurations (e.g., one or more second inference conditions as described above) based on the applicability conditions included in the first message. For example, the second node may select the AIML models / functionalities that the UE may apply when moving to the second node, and it may select an appropriate inference configuration that such AIML models / functionalities can be applied by the UE. The one or more inference configuration may be transmitted by the second node to the first node in a second message. This may correspond to step 904 of Figure 9. At least part of this second message, e.g., the inference configuration(s), could be transmitted by the first network node to the UE as part of the HO command (e.g. together with the RRC reconfiguration with sync). In another case, the inference configuration(s) are included in the CHO or CPAC configuration for a candidate target SpCell, and stored by the UE.

[0134] Figure 10 shows an example of a communication system 1000 in accordance with some embodiments. In the example, the communication system 1000 includes a telecommunication network 1002 that includes an access network 1004, such as a radio access network (RAN), and a core network 1006, which includes one or more core network nodes 1008. The access network 1004 includes one or more access network nodes, such as network nodes 1010a and 1010b (one or more of which may be generally referred to as network nodes 1010), or any other similar 3rd Generation 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 networknodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 1002 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1002 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 1002, including one or more network nodes 1010 and / or core network nodes 1008.

[0135] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), 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 Al, Fl, Wl, El, 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 O-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 1010 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 1012a, 1012b, 1012c, and 1012d (one or more of which may be generally referred to as UEs 1012) to the core network 1006 over one or more wireless connections.

[0136] 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 1000 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 1000 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0137] The UEs 1012 may be any of a wide variety of communication devices, includingwireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1010 and other communication devices. Similarly, the network nodes 1010 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1012 and / or with other network nodes or equipment in the telecommunication network 1002 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 1002.

[0138] In the depicted example, the core network 1006 connects the network nodes 1010 to one or more host computing systems, such as host 1016. 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 1006 includes one more core network nodes (e.g., core network node 1008) 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 1008. 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 (AUSF), 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).

[0139] The host 1016 may be under the ownership or control of a service provider other than an operator or provider of the access network 1004 and / or the telecommunication network 1002. The host 1016 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.

[0140] As a whole, the communication system 1000 of Figure 10 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.

[0141] In some examples, the telecommunication network 1002 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1002 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1002. For example, the telecommunications network 1002 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.

[0142] In some examples, the UEs 1012 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 1004 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1004. 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).

[0143] In the example, the hub 1014 communicates with the access network 1004 to facilitate indirect communication between one or more UEs (e.g., UE 1012c and / or 1012d) and network nodes (e.g., network node 1010b). In some examples, the hub 1014 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1014 may be a broadband router enabling access to the core network 1006 for the UEs. As another example, the hub 1014 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 1010, or by executable code, script, process, or other instructions in the hub 1014. As another example, the hub 1014 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 1014 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub 1014 may retrieve VR assets, video, audio,or other media or data related to sensory information via a network node, which the hub 1014 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1014 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0144] The hub 1014 may have a constant / persistent or intermittent connection to the network node 1010b. The hub 1014 may also allow for a different communication scheme and / or schedule between the hub 1014 and UEs (e.g., UE 1012c and / or 1012d), and between the hub 1014 and the core network 1006. In other examples, the hub 1014 is connected to the core network 1006 and / or one or more UEs via a wired connection. Moreover, the hub 1014 may be configured to connect to an M2M service provider over the access network 1004 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1010 while still connected via the hub 1014 via a wired or wireless connection. In some embodiments, the hub 1014 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 1010b. In other embodiments, the hub 1014 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1010b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0145] Figure 11 shows a UE 1100 in accordance with some embodiments. The UE 1100 presents additional details of some embodiments of the UE 1012 of Figure 10. 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 / playback device, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), an Augmented Reality (AR) or Virtual Reality (VR) 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-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0146] A UE may support device-to-device (D2D) communication, for example by implementing a 3 GPP 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).

[0147] The UE 1100 includes processing circuitry 1102 that is operatively coupled via a bus 1104 to an input / output interface 1106, a power source 1108, a memory 1110, a communication interface 1112, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 11. 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.

[0148] The processing circuitry 1102 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 1110. The processing circuitry 1102 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 1102 may include multiple central processing units (CPUs). The processing circuitry 1102 may be configured to cause the UE 1102 to perform the methods as described with reference to Figure 7.

[0149] In the example, the input / output interface 1106 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 1100. 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 senseinput 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.

[0150] In some embodiments, the power source 1108 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 1108 may further include power circuitry for delivering power from the power source 1108 itself, and / or an external power source, to the various parts of the UE 1100 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1108. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1108 to make the power suitable for the respective components of the UE 1100 to which power is supplied.

[0151] The memory 1110 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 1110 includes one or more application programs 1114, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1116. The memory 1110 may store, for use by the UE 1100, any of a variety of various operating systems or combinations of operating systems.

[0152] The memory 1110 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 (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1110 may allow the UE 1100 to accessinstructions, 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 1110, which may be or comprise a device-readable storage medium.

[0153] The processing circuitry 1102 may be configured to communicate with an access network or other network using the communication interface 1112. The communication interface 1112 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1122. The communication interface 1112 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 1118 and / or a receiver 1120 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1118 and receiver 1120 may be coupled to one or more antennas (e.g., antenna 1122) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0154] In the illustrated embodiment, communication functions of the communication interface 1112 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 / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0155] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1112, 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 livevideo feed of a patient).

[0156] 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.

[0157] 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 smart watch, a fitness tracker, 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 1100 shown in Figure 11.

[0158] 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-IoT 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.

[0159] 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 controlleroperating 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.

[0160] Figure 12 shows a network node 1200 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).

[0161] 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).

[0162] 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-cell / 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).

[0163] The network node 1200 includes a processing circuitry 1202, a memory 1204, a communication interface 1206, and a power source 1208. The network node 1200 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 1200 comprisesmultiple 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 1200 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1204 for different RATs) and some components may be reused (e.g., a same antenna 1210 may be shared by different RATs). The network node 1200 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1200, 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 1200.

[0164] The processing circuitry 1202 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 1200 components, such as the memory 1204, to provide network node 1200 functionality. For example, the processing circuitry 1202 may be configured to cause the network node to perform the methods as described with reference to Figure 8 or 9.

[0165] In some embodiments, the processing circuitry 1202 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1202 includes one or more of radio frequency (RF) transceiver circuitry 1212 and baseband processing circuitry 1214. In some embodiments, the radio frequency (RF) transceiver circuitry 1212 and the baseband processing circuitry 1214 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 1212 and baseband processing circuitry 1214 may be on the same chip or set of chips, boards, or units.

[0166] The memory 1204 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 1202. The memory 1204 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 1202 and utilized by the network node 1200. The memory 1204 may be used to store any calculations made by the processing circuitry 1202 and / or any data received via the communication interface 1206. In some embodiments, the processing circuitry 1202 and memory 1204 is integrated.

[0167] The communication interface 1206 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 1206 comprises port(s) / terminal(s) 1216 to send and receive data, for example to and from a network over a wired connection. The communication interface 1206 also includes radio front-end circuitry 1218 that may be coupled to, or in certain embodiments a part of, the antenna 1210. Radio front-end circuitry 1218 comprises filters 1220 and amplifiers 1222. The radio front-end circuitry 1218 may be connected to an antenna 1210 and processing circuitry 1202. The radio front-end circuitry may be configured to condition signals communicated between antenna 1210 and processing circuitry 1202. The radio front-end circuitry 1218 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 1218 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1220 and / or amplifiers 1222. The radio signal may then be transmitted via the antenna 1210. Similarly, when receiving data, the antenna 1210 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1218. The digital data may be passed to the processing circuitry 1202. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0168] In certain alternative embodiments, the network node 1200 does not include separate radio front-end circuitry 1218, instead, the processing circuitry 1202 includes radio front-end circuitry and is connected to the antenna 1210. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1212 is part of the communication interface 1206. In still other embodiments, the communication interface 1206 includes one or more ports or terminals 1216, the radio front-end circuitry 1218, and the RF transceiver circuitry 1212, as part of a radio unit (not shown), and the communication interface 1206 communicates with the baseband processing circuitry 1214, which is part of a digital unit (not shown).

[0169] The antenna 1210 may include one or more antennas, or antenna arrays, configuredto send and / or receive wireless signals. The antenna 1210 may be coupled to the radio frontend circuitry 1218 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1210 is separate from the network node 1200 and connectable to the network node 1200 through an interface or port.

[0170] The antenna 1210, communication interface 1206, and / or the processing circuitry 1202 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 1210, the communication interface 1206, and / or the processing circuitry 1202 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.

[0171] The power source 1208 provides power to the various components of network node 1200 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1208 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1200 with power for performing the functionality described herein. For example, the network node 1200 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 1208. As a further example, the power source 1208 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.

[0172] Embodiments of the network node 1200 may include additional components beyond those shown in Figure 12 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 1200 may include user interface equipment to allow input of information into the network node 1200 and to allow output of information from the network node 1200. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1200. In some embodiments providing a core network node, such as core network node 108 of FIG. 10, some components, such as the radio front-end circuitry 1218 and the RF transceiver circuitry 1212 may be omitted.

[0173] Figure 13 is a block diagram illustrating a virtualization environment 1300 in whichfunctions 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 1300 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 1300 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface. Virtualization may facilitate distributed implementations of a network node, UE, core network node, or host.

[0174] Applications 1302 (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.

[0175] Hardware 1304 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 1306 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1308a and 1308b (one or more of which may be generally referred to as VMs 1308), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1306 may present a virtual operating platform that appears like networking hardware to the VMs 1308.

[0176] The VMs 1308 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1306. Different embodiments of the instance of a virtual appliance 1302 may be implemented on one or more of VMs 1308, 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 volumeserver hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0177] In the context of NFV, a VM 1308 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 1308, and that part of hardware 1304 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 1308 on top of the hardware 1304 and corresponds to the application 1302.

[0178] Hardware 1304 may be implemented in a standalone network node with generic or specific components. Hardware 1304 may implement some functions via virtualization. Alternatively, hardware 1304 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 1310, which, among others, oversees lifecycle management of applications 1302. In some embodiments, hardware 1304 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 1312 which may alternatively be used for communication between hardware nodes and radio units.

[0179] Although the computing devices described herein (e.g., UEs, network nodes) 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, andfunctionality 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.

[0180] 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.

[0181] The following groups of numbered statements set out embodiments of the disclosure:Group AThe following are methods steps performed by a UE according to embodiments of the present disclosure:Al. A method for a UE to transmit a UE Assistance Information message comprising validity info and the associated applicability conditions for one or more AIML model / functionality.A2. The method of embodiment Al, wherein the validity info could be a cell, a gNB, a frequency, or a list of cells or gNBs or frequencies, to which the applicability conditions are valid for.A3. The method of embodiment Al, wherein the validity info for which the related applicability conditions should be reported by the UE are indicated by the gNB.A4. The method of embodiment Al, wherein the validity info for which the related applicability conditions should be reported by the UE are associated to the AIML models / functionalities that the UE has available.A5. The method of embodiment Al, wherein the AIML models / functionalities for which the UE should be report the validity info and the associated applicability conditions are indicated by the gNB.A6. The method of embodiment Al, wherein if no validity info are included in the UE Assistance Information message, the associated applicability conditions for the one or more AIML model / functionality are valid for the gNB to which the UE is currently connected, or for the current UE serving cells, or for the UE current serving frequencies.A7. The method of embodiment Al, wherein the applicability conditions include any of the following information:• Indication indicating that the AIML model / functionality is applicable• Indication indicating that the AIML model / functionality is not applicable• The UE-side conditions for the AIML model / functionality to be applicable• The NW-side conditions for the AIML model / functionality to be applicableA8. The method of embodiment Al, wherein the UE Assistance Information is transmitted in response of any of the following:• Changing in the applicability conditions associated to a validity info for AIML model / functionality, with respect to the applicability conditions associated to the same validity info for the same AIML model / functionality indicated in a previous UE Assistance Information message• Fulfilling certain radio conditions• Receiving configuration for performing radio measurements in cells, gNBs, frequencies associated to the validity infoA9. The method of embodiment Al, wherein in response of transmitting the UE Assistance Information message, the UE receives one or more inference configurations for one or more AIML models / functionalities, wherein the one or more inference configurations are applied bythe UE when operating in the cells / gNBs / frequencies associated to the validity info included in the UE Assistance Information.Group BThe following are methods steps performed by a network node (e.g., a gNB) according to embodiments of the present disclosure:Bl. The method for first gNB to receive from a UE a UE Assistance Information message comprising the validity info and the associated applicability conditions for one or more AIML model / functionality.B2. The method of embodiment Bl, wherein the first gNB determines from the validity info whether the applicability conditions are of interest for the first gNB itself or for the second gNB.B3. The method of embodiment B2, wherein, in response of determining that the applicability conditions are of interest for the second gNB, the first gNB transmits a first indication including at least part of the content of the received UE Assistance Information message to the second gNB.B4. The method of embodiment B3, wherein in response of transmitting the first indication, the first gNB receives a second indication including one or more inference configurations associated to the one or more AIML models / functionalities that the UE applies when operating in the cells / gNBs / frequencies associated to the validity info included in the first indicationB5. The method of embodiment B4, wherein the first gNB transmits at least part of the second indication to the UE.B6. The method of embodiment B2, wherein, in response of determining that the applicability conditions are of interest for the first gNB, the first gNB transmits one or more inference configurations associated to the one or more AIML models / functionalities that the UE applies when operating in the cells / frequencies controlled by the first gNB.Group C EmbodimentsCl . A method performed by a User Equipment, UE, supporting one or more Machine Learning, ML, functionalities, the method comprising:- transmitting, to a first network node, an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid.C2. The method of embodiment Cl, further comprising determining the one or more second conditions.C3. The method of embodiment Cl or C2, wherein the validity indication for at least one of the one or more second conditions is implicit.C4. The method of embodiment C3, wherein the second condition for which the validity indication is implicit is that the applicability indication is valid only for a radio environment in which the information message is transmitted by the UE.C5. The method of embodiment C3 or C4, wherein the implicit validity indication comprises an absence of an explicit validity indication.C6. The method of any of embodiments Cl to C5, wherein the validity indication comprises an explicit indication of at least one of the one or more second conditions.C7. The method of any of embodiments Cl to C6, wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.C8. The method of any of embodiments Cl to C7, wherein the one or more ML functionalities are applicable by the UE when the one or more first conditions are fulfilled and / or wherein the one or more first conditions are valid when the one or more second conditions are fulfilled.C9. The method of embodiment C8, wherein the one or more first conditions comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained.CIO. The method of any of embodiments Cl to C9, wherein the UE transmits the information message, retransmits the information message, and / or transmits an updated information message to the first network node responsive to:- the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfillment of one or more radio conditions.Cl 1. The method of embodiment CIO, wherein the configuration for transmitting information messages indicates: at least one ML functionality for which the UE is allowed to provide the applicability indication; and / or at least one second condition for which the UE is allowed to provide the validity indication.Cl 2. The method of any of embodiments Cl to Cl l, further comprising receiving, from the first network node, one or more inference configurations associated with the one or more ML functionalities, wherein the one or more inference configurations are based on the information message.Cl 3. The method of embodiment Cl 2, wherein the one or more inference configurations comprise information corresponding to the validity indication.Cl 4. The method of any of embodiments Cl to Cl 3, wherein the validity indication indicates one or more second conditions relating to the UE for the information message to be valid.C15. The method of any of embodiments Cl to C14, wherein the information message comprises assistance information.Cl 6. The method of any of embodiments Cl to Cl 5, wherein the one or more ML functionalities includes an ML model.Group D EmbodimentsDI. A method performed by a first network node, the method comprising:- receiving, from a User Equipment, UE, supporting one or more Machine Learning, ML, functionalities, an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid.D2. The method of embodiment DI, further comprising determining, based on the information message, the one or more second conditions.D3. The method of embodiment DI or D2, wherein the validity indication for at least one of the one or more second conditions is implicit.D4. The method of embodiment D3, wherein the second condition for which the validity indication is implicit is that the applicability indication is valid only for radio environment in which the information message is transmitted by the UE.D5. The method of embodiment D3 or D4, wherein the implicit validity indication comprises an absence of an explicit validity indication.D6. The method of any of embodiments DI to D5, wherein the validity indication comprises an explicit indication of at least one of the one or more second conditions.D7. The method of any of embodiments DI to D6, wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells, one or more network nodes, one or more cell types; one or more signals; one or more frequencies; and one or more channels.D8. The method of any of embodiments DI to D7, wherein the one or more ML functionalities are applicable by the UE when the one or more first conditions are fulfilled and / or wherein the one or more first conditions are valid when the one or more second conditions are fulfilled.D9. The method of embodiment D8, wherein the one or more first conditions comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained.DIO. The method of any of embodiments DI to D9, wherein the first network node receives the information message, a retransmitted information message, and / or an updated information message from the UE responsive to:- the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfillment of one or more radio conditions.Dll. The method of embodiment DIO, wherein the configuration for transmitting information messages indicates: at least one ML functionality for which the UE is allowed to provide the applicability indication; at least one second condition for which the UE is allowed to provide the validity indication.D12. The method of any of embodiments DI to DI 1, further comprising: determining one or more first inference configurations associated with the one or more ML functionalities, wherein the one or more first inference configurations are based on the information message; and- transmitting, to the UE, the one or more first inference configurations.D13. The method of embodiment D12, wherein the one or more first inference configurations comprise information corresponding to the validity indication.D14. The method of any of embodiments DI to D13, further comprising transmitting, to a second network node capable of communicating with the UE:- the information message; or at least part of the information message, wherein the at least part of the information message comprises the applicability indication and at least one second condition associated with radio resources of the second network node.D15. The method of embodiment DI 4, further comprising:- receiving, from the second network node, one or more second inference configurations, wherein the one or more second inference configurations are based on the information message or the at least part of the information message transmitted to the second network node; and- transmitting, to the UE, the one or more second inference configurations.DI 6. The method of embodiment DI 5, wherein the one or more second inference configurations comprise information corresponding to the validity indication.DI 7. The method of any of embodiments DI to DI 6, wherein the validity indication indicates one or more second conditions relating to the UE for the information message to be valid.DI 8. The method of any of embodiments DI to DI 7, wherein the information message comprises assistance information.D19. The method of any of embodiments DI to D18, wherein the one or more ML functionalities includes an ML model.D20. The method of any of embodiments DI to DI 9, wherein the first network node is a Radio Access Network, RAN, node.Group EEL A method performed by a second network node, the method comprising:- receiving an information message from a first network node, wherein the first network node is connected to a User Equipment, UE, supporting one or more Machine Learning, ML, functionalities, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid.E2. The method of embodiment El, further comprising: determining one or more second inference configurations associated with the one or more ML functionalities, wherein the one or more second inference configurations are based on the information message; and- transmitting, to the first network node, the one or more second inference configurations.E3. The method of any of embodiments El to E2, wherein the second network node and / or the first network node are Radio Access Network, RAN, nodes.Group F EmbodimentsFl. A User Equipment, UE, the UE comprising: processing circuitry configured to cause the user equipment to perform any of the steps of any of the Group C embodiments; and power supply circuitry configured to supply power to the processing circuitry.F2. A network node, the network node comprising: processing circuitry configured to cause the network node to perform any of the steps of any of the Group D and Group E embodiments; power supply circuitry configured to supply power to the processing circuitry.F3. A user equipment, UE, the 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 cause the user equipment to perform any of the steps of any of the Group C 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.

Claims

CLAIMS1. A method performed by a User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, the method comprising:- transmitting (702), to a first network node (1200), an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

2. The method of claim 1, further comprising determining the one or more second conditions.

3. The method of claim 1 or 2, wherein the validity indication for at least one of the one or more second conditions is implicit.

4. The method of claim 3, wherein the second condition for which the validity indication is implicit is that the applicability indication is valid only for a radio environment in which the information message is transmitted by the UE.

5. The method of claim 3 or 4, wherein the implicit validity indication comprises an absence of an explicit validity indication.

6. The method of any of claims 1 to 5, wherein the validity indication comprises an explicit indication of at least one of the one or more second conditions.

7. The method of any of claims 1 to 6, wherein the one or more ML functionalities are applicable by the UE when the one or more first conditions are fulfilled and / or wherein the one or more first conditions are valid when the one or more second conditions are fulfilled.

8. The method of claim 7, wherein the one or more first conditions comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained.

9. The method of any of claims 1 to 8, wherein the UE transmits the information message, retransmits the information message, and / or transmits an updated information message to the first network node responsive to:- the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfillment of one or more radio conditions.

10. The method of claim 9, wherein the configuration for transmitting information messages indicates: at least one ML functionality for which the UE is allowed to provide the applicability indication; and / or at least one second condition for which the UE is allowed to provide the validity indication.

11. The method of any of claims 1 to 10, further comprising receiving (704), from the first network node, one or more inference configurations associated with the one or more ML functionalities, wherein the one or more inference configurations are based on the information message.

12. The method of claim 11, wherein the one or more inference configurations comprise information corresponding to the validity indication.

13. The method of any of claims 1 to 12, wherein the validity indication indicates one or more second conditions relating to the UE for the information message to be valid.

14. The method of any of claims 1 to 13, wherein the information message comprises assistance information and / or wherein the one or more ML functionalities includes an ML model.

15. A method performed by a first network node (1200), the method comprising:- receiving (802), from a User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

16. The method of claim 15, further comprising determining, based on the information message, the one or more second conditions.

17. The method of claim 15 or 16, wherein the validity indication for at least one of the one or more second conditions is implicit.

18. The method of claim 17, wherein the second condition for which the validity indication is implicit is that the applicability indication is valid only for radio environment in which the information message is transmitted by the UE.

19. The method of claim 17 or 18, wherein the implicit validity indication comprises an absence of an explicit validity indication.

20. The method of any of claims 15 to 19, wherein the validity indication comprises an explicit indication of at least one of the one or more second conditions.

21. The method of any of claims 15 to 20, wherein the one or more ML functionalities are applicable by the UE when the one or more first conditions are fulfilled and / or wherein the one or more first conditions are valid when the one or more second conditions are fulfilled.

22. The method of claim 21, wherein the one or more first conditions comprise: one or more conditions relating to a radio configuration of the UE under which the one or more ML functionalities were trained; and / or one or more conditions relating to a radio configuration of the network under which the one or more ML functionalities were trained.

23. The method of any of embodiments 15 to 22, wherein the first network node receives the information message, a retransmitted information message, and / or an updated information message from the UE responsive to:- the UE receiving, from the first network node, an indication of a configuration for transmitting information messages; a change in a radio resource utilized by the UE; a change in the applicability indication; a change in the validity indication; and / or fulfillment of one or more radio conditions.

24. The method of claim 23, wherein the configuration for transmitting information messages indicates: at least one ML functionality for which the UE is allowed to provide the applicability indication; at least one second condition for which the UE is allowed to provide the validity indication.

25. The method of any of claims 15 to 24, further comprising: determining one or more first inference configurations associated with the one or more ML functionalities, wherein the one or more first inference configurations are based on the information message; and- transmitting (804), to the UE, the one or more first inference configurations.

26. The method of claim 25, wherein the one or more first inference configurations comprise information corresponding to the validity indication.

27. The method of any of claims 15 to 26, further comprising transmitting, to a second network node (1200) capable of communicating with the UE:- the information message; or at least part of the information message, wherein the at least part of the information message comprises the applicability indication and at least one second condition associated with radio resources of the second network node.

28. The method of claim 27, further comprising:- receiving, from the second network node, one or more second inference configurations, wherein the one or more second inference configurations are based on the information message or the at least part of the information message transmitted to the second network node; and- transmitting, to the UE, the one or more second inference configurations.

29. The method of claim 28, wherein the one or more second inference configurations comprise information corresponding to the validity indication.

30. The method of any of claims 15 to 29, wherein the validity indication indicates one or more second conditions relating to the UE for the information message to be valid.

31. The method of any of claims 15 to 20, wherein the information message comprises assistance information and / or wherein the one or more ML functionalities includes an ML model.

32. A method performed by a second network node (1200), the method comprising:receiving (902) an information message from a first network node (1200), wherein the first network node is connected to a User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

33. The method of claim 32, further comprising: determining one or more second inference configurations associated with the one or more ML functionalities, wherein the one or more second inference configurations are based on the information message; and- transmitting (904), to the first network node, the one or more second inference configurations.

34. The method of claim 32 or 33, wherein the validity indication for at least one of the one or more second conditions is implicit.

35. A User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, the UE configured to:- transmit (702), to a first network node (1200), an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resourcesassociated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

36. The UE of claim 35, further configured to perform the method of any of claims 2 to 14.

37. A first network node (1200) configured to:- receive (802), from a User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, an information message, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or more channels.

38. The first network node of claim 37, further configured to perform the method of any of claims 16 to 31.

39. A second network node (1200) configured to: receive (902) an information message from a first network node (1200), wherein the first network node is connected to a User Equipment, UE, (1100) supporting one or more Machine Learning, ML, functionalities, wherein the information message comprises: o an applicability indication indicating one or more of: whether the one or more ML functionalities are applicable by the UE; and one or more first conditions for the one or more ML functionalities to be applicable by the UE; and o a validity indication indicating one or more second conditions relating to the UE for the applicability indication to be valid; wherein the one or more second conditions comprise the UE utilizing radio resources associated with one or more of: one or more cells; one or more network nodes; one or more cell types; one or more signals; one or more frequencies; and one or morechannels.

40. The second network node of claim 39, further configured to perform the method of claim 33 or 34.

41. A computer-readable medium storing code which, when executed by processing circuitry (1102) of a user equipment (1100), causes the user equipment to perform a method according to any of claims 1 to 14.

42. A computer-readable medium storing code which, when executed by processing circuitry(1202) of a first network node (1200), causes the first network node to perform a method according to any of claims 15 to 31.

43. A computer-readable medium storing code which, when executed by processing circuitry (1202) of a second network node (1200), causes the second network node to perform a method according to any of claims 32 to 34.

Images