Sending and receiving information identyfying applicability of functionality in a user equipment, and configuring a user equipment

Abstract

In an example, a method performed by a first network node for sending information is provided The method comprises sending information to a second network node. The information identifies applicability of functionality in a User Equipment (UE), wherein the functionality uses an artificial intelligence or machine learning (AI / ML) model.

Description

[0001] SENDING AND RECEIVING INFORMATION, AND CONFIGURING A USER EQUIPMENT

[0002] Background

[0003] Artificial Intelligence (Al) and Machine Learning (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 User Equipment (UE) side to reduce the signaling overhead and beam alignment latency; using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0004] In 3rd Generation Partnership Project (3GPP) New Radio (NR) standardization work, a new 3GPP Release 18 (Rel. 18) study item on AI / ML for the NR air interface started in May 2022. This study item explored 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 Rel. 18 is now considered in the context of a Rel. 19 work item. Additionally, during Rel. 19, a new study item addressing AI / ML 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. RLF, handover failure, mobility-related events predictions such as A3 / A5).

[0005] The use cases considered for beam prediction which will be standardized as part of 3GPP Rel. 19 work item consist of spatial beam prediction, and temporal beam prediction. The core idea of AI / ML applied to the RAN is to enable a UE to predict / infer certain performances or certain measurements on a given set A of resources based on experienced performances or performed measurements on a set B of resources, wherein the resources could be for example associated to reference signals (SSB / CSI-RS or P-RS resources) or frequencies, depending on the specific AI / ML use case.

[0006] For example, in the case of AI / ML-based beam management (which is considered by 3GPP in the context of Rel.19), the use case is to predict / infer the “best” beam (or beams) from a Set A of beams (SSB / CSI-RS resources) using measurement results from another Set B of beams (SSB / CSI-RS resources). In particular, according to 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.

[0007] Whether the UE can perform the AI / ML inference given a certain Set A / B of resources, depends on whether the UE has available an AI / ML model / functionality which can perform the inference / prediction on those Set A of resources given the measurements on the Set B. In other words, on whether the AI / ML model / functionality is applicable under that Set A / B configuration. For this reason, information related to whether an AI / ML model / functionality is applicable or not at the UE turns out to be a crucial information that the network needs to know, in order to properly configure the UE with an inference configuration that enables the AI / ML model / functionality to possibly outperform conventional non-AI / ML based schemes.

[0008] To this end, applicability reporting has been discussed during the Rel. 18 study item, to allow the UE to inform the gNB about the applicability of an AI / ML model / functionality while the UE is connected to this gNB. An AI / ML 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. The applicability of a UE-side AI / ML functionality might be a dynamic property, depending for example on whether the UE has an AI / ML model that is applicable given the current location of the UE (e.g. geographical location, or site / cell to which the UE is connected), or given the specific radio condition that the UE is experiencing, or given the current speed of the UE, or given other inputs / measurements performed by device-specific sensors or algorithms.

[0009] Some of these factors cannot be controlled / known by the gNB, because typically it is assumed that the UE-side model is not trained and generated by the gNB, Rather, it is typically assumed that the UE-side model is trained and generated by a node outside the RAN, such as an OTT server or CN function controlled by the UE-vendor or by the MNO.

[0010] In general, the applicability of an AI / ML model / functionality to perform inference under certain conditions depends on whether such AI / ML model / functionality has been trained under such conditions. If this is the case, the performances of an AI / ML-based inference scheme can outperform conventional methods, otherwise this might not be the case. For example, if network conditions, so-called NW-side additional conditions (such as transmitting power, antenna configuration, deployment, SSB configuration, etc.), at the time in which the UE is performing the inference do not match the network conditions during the training (e.g. performed by the UE at a previous point in time), then it is likely that the AI / ML performances will be worse than the performances achieved via conventional methods, e.g. AI / ML-based beam management will lead to poor / inaccurate results.

[0011] Two types of applicability reporting were identified during the Rel.18 study item and are currently being discussed in RAN2 for the normative phase, the so-called reactive approach and the proactive approach.

[0012] Figure 1 illustrates an example of proactive reporting of applicability. In this proactive example, the network enquires the UE capabilities and configures the UE to report the applicability of an AI / ML functionality and, based on the reported information the network configures the UE with an inference configuration, as follows:

[0013] • Step 1 : Network sends UECapabilityEnqiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities

[0014] • Step 2: UE sends UECapablitylnformation message to network, containing supported functionalities at the UE side

[0015] • Step 3: Network configures UE that it is allowed to provide its applicable functionalities

[0016] • Step 4: UE sends applicable functionalities to network upon change of applicable functionality / condition

[0017] • Step 5: Network sends inference configuration for the applicable functionalities to the UE

[0018] • Step 6: Start inference / monitoring based on network / UE activation / deactivation

[0019] Figure 2 illustrates an example of reactive reporting of applicability. In this example reactive approach, the network enquires the UE capabilities and configures the UE with the AI / ML functionality (possibly including the inference configuration) in response to which the UE is able to determine the applicability of the A / ML functionality and, in case the configured AI / ML functionality is applicable, the functionality could be up and running as soon as possible, without the need to an additional reconfiguration, as follows:

[0020] • Step 1 : Network sends UECapabilityEnquiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities.

[0021] • Step 2: UE sends UECapablitylnformation message to network, containing supported functionalities at the UE side.

[0022] • Step 3: Network provides network configurations and initiates UE to report its applicable functionalities. • Step 4: UE sends applicable functionalities to network.

[0023] • Step 5: Network sends updated inference configuration for applicable functionalities reported in Step 4 to the UE.

[0024] • Step 6: Start inference / monitoring based on network / UE activation / deactivation.

[0025] There currently exist certain challenges. For example, through the applicability reporting, the gNB has the possibility to provide the UE with an inference configuration that makes an AI / ML model / functionality applicable at the UE. This is because within the applicability reporting the UE can indicate whether an AI / ML functionality is applicable or not and / or further information about the AI / ML functionality, such as the applicability conditions under which the AI / ML model / functionality is applicable. Based on that the gNB may configure the UE with an inference configuration such that the applicability conditions are fulfilled and the AI / ML model / functionality can be operated by the UE.

[0026] However, this outlined scheme might be quite inefficient from a signalling overhead and latency point of view. In fact, in a first step, this scheme requires the gNB to configure the UE to report the applicability conditions, then in a second step, the UE has to indicate to the gNB the applicability conditions, and in a third step, the gNB can finally transmit to the UE the inference configuration.

[0027] From a signalling overhead point of view, the scheme is quite inefficient, because it implies the exchange of three different messages between the network and the UE, each of them potentially carrying significant amount of data. For example, the applicability reporting configuration transmitted by the gNB to the UE may contain all the network-conditions (so- called NW-side additional conditions) comprising for example the possible beam configurations that the network can operate. Similarly, the applicability reporting transmitted in response by the UE to the gNB may include the network conditions under which the AI / ML model / functionality is applicable.

[0028] From a latency point of view, this scheme is also quite inefficient, because before receiving an inference configuration, and hence before applying the AI / ML model / functionality, the UE needs to go through the outlined procedure above. This is particularly the case assuming that dynamic information, such as the applicability related to an AI / ML functionality, would be typically lost when the UE is in an Idle state.

[0029] How to allow the UE to timely receive an inference configuration from the gNB with minimum signalling overhead is a challenge, given the framework that 3GPP is discussing for configuring the UE with an AI / ML-related configuration. The objective of a more efficient approach would be to enable the UE to receive an inference configuration as soon as possible, with a minimum amount of information exchanged between the gNB and the UE. However, how to achieve this objective might not be straightforward given that the gNB needs to know the applicability conditions of the UE-sided AI / ML functionality, in order to provide a suitable AI / ML inference configuration to the UE.

[0030] Summary

[0031] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges, and may provide one or more technical advantages. For example, example methods disclosed herein enable a network node, e.g. RAN node, to provide a UE with an AI / ML model / functionality configuration for inference without the need to rely, at least in some cases, on the UE transmitting first an applicability report message prior to receive the inference configuration for the AI / ML model / functionality. This avoids the need to rely on at least two reconfiguration procedures, i.e. one for configuring the UE to report the UE applicability report, and one for the configuring the UE with the inference configuration.

[0032] One aspect of the present disclosure provides a method performed by a first network node for sending information. The method comprises sending information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0033] Another aspect of the present disclosure provides a method performed by a first network node for configuring a User Equipment, UE. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the method comprises receiving information from a second network node, wherein the information identifies applicability of the functionality, and sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

[0034] A further aspect of the present disclosure provides a method performed by a second network node for receiving information from a first network node. The method comprises receiving information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0035] An additional aspect of the present disclosure provides a method performed by a User Equipment, UE, for sending information to a first network node. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model. The method comprises sending information to the first network node, wherein the information identifies applicability of the functionality, and after sending the information to the first network node, transitioning to idle mode or inactive mode. The method also comprises, after transitioning to the idle mode or the inactive mode, deleting the information.

[0036] A still further aspect of the present disclosure provides a tangible, non-transient computer- readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a first network node for sending information. The operations comprise sending information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0037] Another aspect of the present disclosure provides a tangible, non-transient computer- readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a first network node for configuring a User Equipment, UE. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model. The operations comprise receiving information from a second network node, wherein the information identifies applicability of the functionality, and sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

[0038] An additional aspect of the present disclosure provides a tangible, non-transient computer- readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a second network node for receiving information from a first network node. The operations comprise receiving information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0039] A further aspect of the present disclosure provides a tangible, non-transient computer- readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a User Equipment, UE, for sending information to a first network node. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model. The operations comprise sending information to the first network node, wherein the information identifies applicability of the functionality and, after sending the information to the first network node, transitioning to idle mode or inactive mode. The operations also comprise, after transitioning to the idle mode or the inactive mode, deleting the information. Another aspect of the present disclosure provides apparatus in a first network node for sending information. The apparatus comprises processing circuitry and a memory. The apparatus is configured to send information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0040] A further aspect of the present disclosure provides apparatus in a first network node for configuring a User Equipment, UE. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model. The apparatus comprises processing circuitry and a memory. The apparatus is configured to receive information from a second network node, wherein the information identifies applicability of the functionality, and send, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

[0041] An additional aspect of the present disclosure provides apparatus in a second network node for receiving information from a first network node. The apparatus comprises processing circuitry and a memory. The apparatus is configured to receive information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

[0042] A still further aspect of the present disclosure provides apparatus in a User Equipment, UE, for sending information to a first network node. The UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model. The apparatus comprises processing circuitry and a memory. The apparatus is configured to send information to the first network node, wherein the information identifies applicability of the functionality and, after sending the information to the first network node, transition to idle mode or inactive mode. The apparatus is also configured to, after transitioning to the idle mode or the inactive mode, delete the information.

[0043] Brief Description of the Drawings

[0044] 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:

[0045] Figure 1 illustrates an example of proactive reporting of applicability;

[0046] Figure 2 illustrates an example of reactive reporting of applicability; Figure 3 depicts an example of a method performed by a first network node for sending information;

[0047] Figure 4 depicts an example of a method performed by a first network node for configuring a User Equipment;

[0048] Figure 5 depicts an example of a method performed by a second network node for receiving information from a first network node;

[0049] Figure 6 depicts an example of a method performed by a User Equipment for sending information to a first network node;

[0050] Figure 7 illustrates an examples of communications in a network according to examples of this disclosure;

[0051] Figure 8 illustrates an example of reporting of UE-side AI / ML applicability information to a second network node;

[0052] Figure 9 illustrates another example of reporting of UE-side AI / ML applicability information to a second network node;

[0053] Figure 10 illustrates an example method for retrieving of UE-side AI / ML applicability information from the second network node;

[0054] Figure 11 illustrates an example of another method for retrieving of UE-side AI / ML applicability information from the second network node;

[0055] Figure 12 illustrates an example of a method for retrieving of UE-side AI / ML applicability information from the second network node during a mobility procedure;

[0056] Figure 13 shows an example of a communication system in accordance with some embodiments;

[0057] Figure 14 shows a UE in accordance with some embodiments;

[0058] Figure 15 shows a network node in accordance with some embodiments; and

[0059] Figure 16 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.

[0060] ADDITIONAL EXPLANATION

[0061] 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.

[0062] Figure 3 depicts a method 300 in accordance with particular embodiments, such as for example a method performed by a first network node for sending information. The method 300 may be performed by a network node (e.g. the network node QQ110 or network node QQ300 as described later with reference to Figures 13 and 15 respectively). The method begins at step 302 with sending information to a second network node, wherein the information identifies applicability of functionality in a UE, wherein the functionality uses an artificial intelligence or machine learning (AI / ML) model.

[0063] In some examples, sending the information to the second network node stores the information at the second network node. The second network node may comprise for example a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, UCMF.

[0064] In some examples, the method 300 may comprise sending the information to the second network node in response to one or more of the following non-limiting examples:

[0065] • configuring the UE for UE-side data collection;

[0066] • determining that the UE stops the UE-side data collection;

[0067] • receiving the information from the UE;

[0068] • sending, to the UE, a configuration of the functionality based on the information;

[0069] • determining that the UE performs a connected mode mobility or leaves an area covered by the first network node or in which the information is valid;

[0070] • determining that the UE transitions to idle mode or connected mode.

[0071] The method 300 may in some examples comprise receiving at least part of the information from the UE. The method 300 may also comprise, before receiving the at least part of the information from the UE, one or more of the following non-limiting examples:

[0072] • determining that the UE transitions to connected mode;

[0073] • determining that the UE connects to the first network node or another network node;

[0074] • determining that the UE registers with the first network node or another network node.

[0075] The another network node may comprise for example a Radio Access Network, RAN, node. In some examples, after receiving the at least part of the information from the UE, the UE transitions to idle mode or inactive mode.

[0076] In some examples, the method 300 comprises sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality. The functionality comprises for example a training configuration, monitoring configuration and / or inference configuration. The configuration may be sent for example in a Radio Resource Control, RRC, message or a RRC reconfiguration message. The information from the UE may in some examples be received from the UE in a Registration Area Update, RAU, or as part of a RAU procedure by the UE.

[0077] In some examples, the information identifying the applicability of the functionality identifies one or more of the following non-limiting examples:

[0078] • one or more conditions under which the functionality is applicable;

[0079] • one or more UE-side conditions, operated by the UE or another UE, during training of the functionality;

[0080] • one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality;

[0081] • a training configuration under which the functionality was trained.

[0082] The functionality that uses the AI / ML model comprises for example a UE positioning functionality.

[0083] The first network node comprises for example a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

[0084] In some examples, the information comprises one or more of the following non-limiting examples:

[0085] • an identifier of the UE;

[0086] • a classification of the UE;

[0087] • an identifier of the first network node;

[0088] • one or more nodes, cells and / or areas associated with the information;

[0089] • a time duration for validity of the information;

[0090] • an identifier of the functionality;

[0091] • a Public Land Mobile Network, PLMN, associated with the information.

[0092] Figure 4 depicts a method 400 in accordance with particular embodiments, such as for example a method performed by a first network node for configuring a User Equipment (UE), wherein the UE has a functionality that uses an artificial intelligence or machine learning (AI / ML) model. The method 400 may be performed by a network node (e.g. the network node QQ110 or network node QQ300 as described later with reference to Figures 13 and 15 respectively). The method begins at step 402 with receiving information from a second network node, wherein the information identifies applicability of the functionality, and step 404 with sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality. The second network node comprises for example a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, LICMF.

[0093] In some examples, the method 400 comprises, before receiving the information from the second network node, one or more of the following non-limiting examples:

[0094] • determining that the UE transitions to connected mode;

[0095] • determining that the UE connects to the first network node or another network node;

[0096] • determining that the UE registers with the first network node or another network node.

[0097] The another network node comprises for example a Radio Access Network, RAN, node.

[0098] The method 400 may also comprise, in some examples, before receiving the information from the second network node, sending a request for the information to the second network node. The request may be sent in response to one or more of the following non-limiting examples:

[0099] • determining that the UE registers with the second network node;

[0100] • determining that the UE supports or is capable of one or more functionalities that use an AI / ML model;

[0101] • determining to provide configuration of the functionality to the UE.

[0102] The configuration of the functionality may comprise for example a training configuration, monitoring configuration and / or inference configuration. The configuration may in some examples be sent in a Radio Resource Control, RRC, message or a RRC reconfiguration message. The information identifying the applicability of the functionality may identify one or more of the following non-limiting examples:

[0103] • one or more conditions under which the functionality is applicable;

[0104] • one or more UE-side conditions, operated by the UE or another UE, during training of the functionality;

[0105] • one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality;

[0106] • a training configuration under which the functionality was trained.

[0107] The functionality that uses the AI / ML model comprises for example a UE positioning functionality. The first network node may comprise for example a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF. The information maty comprise one or more of the following non-limiting examples:

[0108] • an identifier of the UE;

[0109] • a classification of the UE;

[0110] • an identifier of the first network node;

[0111] • one or more nodes, cells and / or areas associated with the information;

[0112] • a time duration for validity of the information;

[0113] • an identifier of the functionality;

[0114] • a Public Land Mobile Network, PLMN, associated with the information.

[0115] Figure 5 depicts a method 500 in accordance with particular embodiments, such as for example a performed by a second network node for receiving information from a first network node. The method 500 may be performed by a network node (e.g. the network node QQ110 or network node QQ300 as described later with reference to Figures 13 and 15 respectively). The method begins at step 502 with receiving information from the first network node, wherein the information identifies applicability of functionality in a User Equipment (UE), wherein the functionality uses an artificial intelligence or machine learning (AI / ML) model. The second network node may comprise for example a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, UCMF

[0116] In some examples, the method 500 also comprises storing the information at the second network node.

[0117] The information may be received from the first network node in response to one or more of the following non-limiting examples:

[0118] • configuration of the UE for UE-side data collection;

[0119] • the UE stopping the UE-side data collection;

[0120] • a configuration of the functionality in the UE based on the information;

[0121] • determining that the UE performs a connected mode mobility or leaves an area covered by the first network node or in which the information is valid;

[0122] • determining that the UE transitions to idle mode or connected mode;

[0123] • transition of the UE to connected mode;

[0124] • connection of the UE to the first network node or another network node;

[0125] • registering of the UE with the first network node or another network node. The another network node may comprise for example a Radio Access Network, RAN, node.

[0126] In some examples, the method 500 may comprise sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality. The configuration of the functionality comprises for example a training configuration, monitoring configuration and / or inference configuration. The configuration may be sent for example in a Radio Resource Control, RRC, message or a RRC reconfiguration message.

[0127] In some examples, the information from the first network node is received from the UE in a Registration Area Update, RAU, or as part of a RAU procedure by the UE. The information identifying the applicability of the functionality may identify one or more of the following nonlimiting examples:

[0128] • one or more conditions under which the functionality is applicable;

[0129] • one or more UE-side conditions, operated by the UE or another UE, during training of the functionality;

[0130] • one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality;

[0131] • a training configuration under which the functionality was trained.

[0132] The functionality that uses the AI / ML model may comprise for example a UE positioning functionality. The first network node may comprise for example a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

[0133] In some examples, the method 500 further comprises receiving further information from the first network node or a further network node, wherein the further information identifies further applicability of the functionality in the UE, the information received from the first network node is associated with a first set of conditions, and the further information received from the first network node or the further network node is associated with a second set of conditions. The further network node comprises for example a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

[0134] The method 500 may in some examples comprise sending the information or a subset of the information to the first network node or another network node. The information may be sent for example after receiving a request for the information of the subset of the information from the first network node or the another network node.

[0135] The information may comprise one or more of the following non-limiting examples: • an identifier of the UE;

[0136] • a classification of the UE;

[0137] • an identifier of the first network node;

[0138] • one or more nodes, cells and / or areas associated with the information;

[0139] • a time duration for validity of the information;

[0140] • an identifier of the functionality;

[0141] • a Public Land Mobile Network, PLMN, associated with the information.

[0142] Figure 6 depicts a method 600 in accordance with particular embodiments, such as for example a method performed by a User Equipment (UE) for sending information to a first network node, wherein the UE has a functionality that uses an artificial intelligence or machine learning (AI / ML) model. The method 600 may be performed by a UE or wireless device (e.g. the UE QQ112 or UE QQ200 as described later with reference to Figures 13 and 14 respectively). The method begins at step 602 with sending information to the first network node, wherein the information identifies applicability of the functionality. Step 604 comprises, after sending the information to the first network node, transitioning to idle mode or inactive mode. Step 606 comprises, after transitioning to the idle mode or the inactive mode, deleting the information.

[0143] Some alternative embodiments include a method performed by a User Equipment (UE) for sending information to a first network node, wherein the UE has a functionality that uses an artificial intelligence or machine learning (AI / ML) model. The method comprises sending information to the first network node, wherein the information identifies applicability of the functionality. This example method may optionally comprise, after sending the information to the first network node, transitioning to idle mode or inactive mode, and may also optionally comprise, after transitioning to the idle mode or the inactive mode, deleting the information.

[0144] The method 600 may in some examples comprise performing one or more actions comprising one or more of the following non-limiting examples:

[0145] • transitioning to connected mode;

[0146] • connecting to the first network node or another network node;

[0147] • registering with the first network node or the another network node.

[0148] In some examples, the method 600 comprises, after performing the one or more actions, receiving, from the first network node or the another network node, a configuration of the functionality based on the information identifying the applicability of the functionality. The method 600 may also in some examples comprise receiving, from the first network node or the another network node, the configuration of the functionality without sending, to the first network node or the another network node, the information between performing the one or more actions and receiving the configuration. The configuration of the functionality may comprise for example a training configuration, monitoring configuration and / or inference configuration. The configuration may be received for example in a Radio Resource Control, RRC, message or a RRC reconfiguration message. The another network node comprises for example a Radio Access Network, RAN, node. The method 600 may also in some examples comprise, after sending information to the first network node and before performing the one or more actions, deleting the information.

[0149] Sending the information to the first network node may be performed for example in a Registration Area Update, RAU, or as part of a RAU procedure. The information identifying the applicability of the functionality may identify one or more of the following non-limiting examples:

[0150] • one or more conditions under which the functionality is applicable;

[0151] • one or more UE-side conditions, operated by the UE or another UE, during training of the functionality;

[0152] • one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality;

[0153] • a training configuration under which the functionality was trained.

[0154] The functionality that uses the AI / ML model may comprise for example a UE positioning functionality. The first network node may comprise for example a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF. The information may comprise one or more of the following non-limiting examples:

[0155] • an identifier of the UE;

[0156] • a classification of the UE;

[0157] • an identifier of the first network node;

[0158] • one or more nodes, cells and / or areas associated with the information;

[0159] • a time duration for validity of the information;

[0160] • an identifier of the functionality;

[0161] • a Public Land Mobile Network, PLMN, associated with the information.

[0162] Below are provided further example embodiments. In the context of this disclosure the term “AI / ML functionality” may be called a “supported functionality” the UE can indicate by using UE capability signaling. A supported functionality is one or more functionalities for and / or associated to beam management and / or CSI reporting, or mobility operations, such as the reporting of time domain and / or spatial domain or frequency domain predictions (inference). It could be said as the ability the UE has to produce an output of an inference function. For example, reporting of time-domain prediction(s) of SSB and / or CSI-RS measurement information (e.g. predicted RSRP) may be considered as an AI / ML functionality which is a “supported functionality” by the UE when the UE reports a capability associated to it (via RRC or LPP signaling).

[0163] For example, “spatial domain prediction for beam management or mobility procedure e.g., handover or reconfiguration with sync, or Primary cell (PCell) change, or Primary Secondary Cell Group cell (PSCell) change” or a related functionality (e.g. reporting and inference of spatial domain info) may be a supported functionality in which the UE may report that is capable of performing and reporting inference / prediction of a set A of beams or cells (e.g. predicted L1 RSRP values of one or more beams or one or more SSB indexes of a cell or predicted L1 or L3 RSRP values of one or more cells) based on measurements performed on a set B of beams (e.g. measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell), in the case of spatial domain predictions.

[0164] For example, “frequency domain prediction for beam management or mobility procedure e.g., handover” or a related functionality (e.g. reporting and inference of frequency domain info) may be a supported functionality in which the UE may indicate that is capable of performing and reporting inference (e.g., prediction of the radio link quality of a set A of beams or cells (e.g. predicted L1 RSRP values of one or more beams or one or more SSB indexes of a cell or predicted L1 or L3 RSRP values of one or more cells) based on measurements performed on a set B of beams (e.g. measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell or one or more cells), in the case of frequency domain predictions. For example, “time domain prediction for beam management or a mobility procedure e.g., handover or reconfiguration with sync, or Primary cell (PCell) change, or Primary Secondary Cell Group cell (PSCell) change” or a related functionality (e.g. reporting and inference of time domain info) may be a supported functionality in which the UE may report that is capable of performing and reporting inference of a set of A of beams (e.g. predicted L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell in future time instances or the L1 / L3 RSRP value of one or more cells in the future time instances) based on measurements performed on a set B of beams or cells (e.g. measured L1 / L3 RSRP values of one or more beams or one or more SSB indexes of a cell and / or L1 / L3 RSRP value of one or more cells), in the case of time domain predictions.

[0165] For example, beam management - DL Tx beam prediction for both UE-sided model and NW-sided model, including: o Spatial-domain DL T ransmitted (Tx) beam prediction for Set A of beams based on measurement results of Set B of beams (“BM-Case1”) o Temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams (“BM-Case2”)

[0166] For example, positioning accuracy enhancements, including: o Direct AI / ML positioning, such as:

[0167] ■ UE-based positioning with UE-side model, direct AI / ML positioning

[0168] ■ UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning

[0169] ■ NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning o AI / ML assisted positioning, such as:

[0170] ■ UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning

[0171] ■ NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning

[0172] For example, CSI compression e.g., considering extending the spatial / frequency compression to spatial / temporal / frequency compression, cell / site specific models, CSI compression plus prediction (compared to Rel-18 non-AI / ML based approach) For example, “Radio Link Failure prediction of serving and / or neighbour cells” or a related functionality (e.g. reporting and inference of RLF prediction of serving and / or neighbour cell(s)) may be a supported functionality in which the UE may report that is capable of performing and reporting inference of an RLF in future time instances.

[0173] For example, “Handover Failure (HOF) prediction of a cell” or a related functionality (e.g. reporting and inference of HOF prediction of a cell) may be a supported functionality in which the UE may report that is capable of performing and reporting inference of an HOF in future time instances.

[0174] In the context of this disclosure the term the term “NW-side additional conditions” is used to identify any of the following operation parameters: - Set A and / or Set B of resources, represented e.g. by an ID associated to the set of resources or to the resources within the set.

[0175] Mapping relationship of Set A and Set B, including ordering to (a set of ID, or resource)

[0176] - Consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B.

[0177] - QCL assumption

[0178] - The order of model input and model output between RS and Tx beams can be predefined.

[0179] - gNB transmission power UE distribution

[0180] - gNB antenna height and / or other antenna properties

[0181] Network deployment scenarios (e.g., ISD, Umi / Uma)

[0182] NW-side resource configuration(s) which may be considered as NW implementationbased configurations which may possibly impact the inference performance for a UE sided model. For instance, beam and Tx port mapping relationship in the gNodeB for a given cell, NW antenna shape, Antenna dip angle, height of the tower / gNB, etc. NW load in terms of connected users, radio resource utilizations (PDCCH / RACH / PUCCH / PUSCH / PDSCH resource load, number of configured bearers, etc)

[0183] In the context of this disclosure the term UE-side additional conditions is used to identify any of the following operation parameters:

[0184] • UE speed

[0185] • UE battery status

[0186] • UE antenna properties (layout, Ml MO configuration, device orientation etc.)

[0187] • UE radio configuration

[0188] • UE traffic type

[0189] Each of the NW-side additional conditions or UE-side additional conditions, or groups of certain NW-side additional conditions, or groups of UE-side additional conditions may be represented by an associated ID.

[0190] In the context of this disclosure the term “environmental conditions” is used to identify any of the following operation parameters:

[0191] Delay spread statistics LoS / N LOS statistics

[0192] Doppler statistics

[0193] In an example of this disclosure, a method includes a step for a first network node (in the RAN) comprising the first network node identifying / determining a set of UE-side AI / ML applicability information, which can be identified from any of:

[0194] • The set of applicability conditions of one or more AI / ML models / functionalities included in the applicability report message transmitted by the UE.

[0195] • The training configuration configured by the first network to the UE for the UE-side model training, the training configuration comprising a radio resource configuration for training.

[0196] • The UE-side conditions operated by the UE at the time of UE-side model training wherein the UE-side conditions may be transmitted to the first network node by the UE, or configured by the first network.

[0197] • The NW-side conditions operated by the first network node at the time of the UE performing UE-side model training.

[0198] • One or more UE-side AI / ML applicability information transmitted by the UE e.g. in a UE Assistance Information message and / or in an RRC Reconfiguration Complete message.

[0199] In a second step, the first network node (e.g. gNodeB) transmitting the identified set of UE- side AI / ML applicability information to a second network node.

[0200] In a third step, the second network node storing the received identified set of UE-side AI / ML applicability information.

[0201] Some examples of this disclosure relate to retrieving the set of UE-side AI / ML applicability information from the CN.

[0202] In a fourth step for a third and second network node, comprising the UE connecting to a third network node (which may be the same as the first or a different RAN node), and the second network node at the CN determining whether for the said UE there is a UE-side AI / ML applicability information stored in the second network node. If for the said UE there is a UE- side AI / ML applicability information stored in the second network node, retrieving and transmitting the associated set of UE-side AI / ML applicability information to the third network node. In a fifth step for the first network node comprising the third network node (which may be the same as the first or a different RAN node), receiving the set of UE-side AI / ML applicability information associated to the UE.

[0203] In a sixth step for the first network node comprising the third network node (which may be the same as the first or a different RAN node) transmitting an inference configuration, monitoring configuration or a training configuration to the UE based on the received set of UE-side AI / ML applicability information.

[0204] The first and third network node could be mobile network node(s) such as the RAN node (e.g. gNodeB (gNB) or a 6G RAN node or function), or the LFM or LMF, or any other mobile network node responsible for receiving the applicability conditions of an AI / ML model / functionality from the gNB, or in charge of configuring resources for UE-side model training.

[0205] The second network node could be any mobile network node (or function within it) responsible for receiving from the first network node the above identified set of information and storing them. As an example, the mobile network node could be the AMF, or the NEF, or a UE capability management function (UCMF).

[0206] Examples of this disclosure provide a method at a UE in Connected state in which the UE reports to a first network node a set of UE-side AI / ML applicability information and, upon entering an Idle state (e.g. RRCJDLE) the UE deletes at least one of the UE-side AI / ML applicability information. In one option the UE enters the Idle state when it transitions from a Connected state (e.g. RRC_CONNECTED) e.g. upon reception of an RRC Release message without a suspend configuration.

[0207] Examples of this disclosure provide a method at a UE in Idle state in which the UE transitions to Connected state and receives an AI / ML configuration in the first RRC Reconfiguration, based on UE-side AI / ML applicability information previously reported by the UE when the UE was in Connected state.

[0208] In another option, the UE transmits UE-side AI / ML applicability information when it transitions to a Connected state from Idle when it triggers a Registration Area Update. The reason is that a Registration Area Update will trigger an update to the CN of the UE location (e.g. UE entering a new Tracking Area and / or Registration Area), so that the gNodeB has an opportunity to update the UE-side AI / ML applicability information in the AMF. Below are provided example enumerated embodiments according to examples of this disclosure.

[0209] Embodiments for a first network node

[0210] A1. A method at a first network node of a Radio Access Network (RAN) for transmitting an identified set of UE-side AI / ML applicability information to a second network node of a Core Network (CN).

[0211] A1* A method of A1 wherein prior to transmitting the identified set of UE-side AI / ML applicability information to the second network node, identifying a set of UE-side AI / ML applicability information associated to a UE, based on one or more of the following information available at the first network node:

[0212] • A first set of information associated to the applicability conditions of one or more AI / ML models / functionalities included in an applicability report message transmitted by the UE to the first network node

[0213] • A second set of information associated to the training configuration configured by the first network to the UE for the UE-side model training, the training configuration comprising at least a radio resource configuration

[0214] • A third set of information associated to the UE-side conditions operated by the UE at the time of UE-side model training transmitted to the first network node by the UE, or configured by the first network node to the UE

[0215] • A fourth set of information associated to the NW-side conditions operated by the first network node at the time of the UE performing UE-side data collection for the purpose of its model training

[0216] • A fifth set of information associated to the environment conditions in the area served in the first network node, where the environment conditions at least comprises the scattering environment (e.g. statistics of delay spread, LOS statistics) at the time of the UE performing UE-side model training

[0217] A2. The method of A1 , wherein the set of UE-side AI / ML applicability information includes the AI / ML applicability information associated to one or more AI / ML models / functionalities. A3. The method of A1 , wherein the set of UE-side AI / ML applicability information comprises applicability information for one or more AI / ML models / functionalities for one or more cells, or for one or more frequencies, or for one or more mobile network nodes, for one or more validity area.

[0218] A4. The method of A1 , wherein the set of UE-side AI / ML applicability information are transmitting by the first network node upon identifying the set of UE-side AI / ML applicability information, in response of one or more of the following events: o Upon configuring the UE for UE-side data collection for the purpose of model training o Upon receiving the applicability report message o Upon configuring the UE with an AI / ML inference configuration o Upon the UE stops the data collection for UE-side model training o Upon the UE performs a connected mode mobility or leaves the area covered by the first network node or the validity area o Upon transitioning the UE to an IDLE state, or upon transitioning the UE to CONNECTED from IDLE.

[0219] A5. The method of A1 , comprising receiving the set of UE-side AI / ML applicability information associated to the UE from the second network node in response of one or more of the following:

[0220] • The UE connecting to the first network node

[0221] • The UE registering to the second network node

[0222] • The first network node determining that the UE supports / is capable of one or more AI / ML models / functionalities.

[0223] • The first network node determining whether to provide an AI / ML inference configuration to the UE

[0224] • The first network node determining whether to provide an AI / ML training configuration to the UE

[0225] A6. The methods of A5, wherein the received set of UE-side AI / ML applicability information are a subset of the UE-side AI / ML applicability information associated to the UE stored at the second network node.

[0226] A7. The method of A5, wherein the first network node receives the set of UE-side AI / ML applicability information associated to the UE upon transmitting a request to the second network node.

[0227] A8. The method of A7, wherein the request comprises any of:

[0228] • The UE for which it is requested the set of UE-side AI / ML applicability information

[0229] • The one or more AI / ML models / functionalities for which it is requested the set of UE- side AI / ML applicability information.

[0230] • The one or more cells / frequencies / nodes / areas for which it is requested the set of UE-side AI / ML applicability information.

[0231] A9. The method of A5, wherein if no AI / ML applicability information is received from the second node, the first node assumes that the UE has no applicable AI / ML function in this situation. A10. The method according to A9 where if no AI / ML applicability information is received from the second node, configuring, requesting or otherwise triggering the UE to send potential AI / ML applicability information to the first node.

[0232] A11. The method of any of the previous methods, wherein the first network node transmits to the UE an inference configuration for UE-side model inference for one or more AI / ML models / functionalities based on the received set of UE-side AI / ML applicability information. A12. The method of any of the previous methods, wherein the first network node transmits to the UE a training configuration for UE-side model training of one or more AI / ML models / functionalities based on the received set of UE-side AI / ML applicability information. A13. The method according to A5 wherein the first network node forwards the information receive from the second network node to a third network node in response to a mobility procedure of the UE from the first to the third network node.

[0233] A13. The method according to A1* wherein the first network node transmits an indication to update the stored set of UE-side AI / ML applicability information at the second network node. A14. The method of A1, wherein the first network node is a mobile network node such as the RAN node (gNB), or the LFM.

[0234] Embodiments for a second network node

[0235] B1. A method at a second network node for receiving from the first network node a set of UE-side AI / ML applicability information associated to a UE, and storing it.

[0236] B2. The method of B1, wherein the storing comprises storing the set of UE-side AI / ML applicability information associated to the UE

[0237] B2*. The storing of the set of UE-side AI / ML applicability information comprises storing one or more of the following information:

[0238] • The identity of the UE

[0239] • Information related to the UE that enables the classification of multiple UEs with similar attributes / characteristics. The identity of the first network node

[0240] • The nodes, or the cells or the areas to which the UE-side AI / ML applicability information refer to.

[0241] • The time at which the set of UE-side AI / ML applicability information is received

[0242] • The expected duration until when the UE-side AI / ML applicability condition is expected to be valid. This is dependent upon UE willingness for how long to use AI / ML model for foreseeable future or for how long UE would like this information associated with applicability to be stored. Note: The validity timer for storage of information may also be attached by the NW depending upon expected duration where NW will not change the beam configurations. • The AI / ML model / functionality to which the set of UE-side AI / ML applicability information refers to

[0243] • The PLMN to which the set of UE-side AI / ML applicability information refers to B2**. The storing comprises storing multiple sets of AI / ML applicability information for a UE wherein each set is associated with a certain situation, e.g. a first information may be valid in situation A (e.g. when the UE is in area A) and a second information may be valid in situation B (e.g. when the UE is in area B).

[0244] B3. The method B1 comprising updating the stored set of UE-side AI / ML applicability information associated to a UE and to a first network node (alternatively: associated to a UE and to a set of nodes, cells or areas), based on a second set of UE-side AI / ML applicability information associated to the UE received from the first network node.

[0245] B3*. The method B1 comprising updating the stored set of UE-side AI / ML applicability information associated to a UE and to a first network node (alternatively: associated to a UE and to a set of nodes, cells or areas), in response of one or more of the following:

[0246] • Receiving indication from the first network node that the the NW-side conditions operated by the first network node are updated and different from the associated to the NW-side conditions reported by the UE in the applicability message.

[0247] • Receiving indication from the first network node that the stored UE applicability information associated with the first network node are no longer valid.

[0248] • A time duration has elapsed since the information was stored or last updated.

[0249] • A time duration has elapsed since the information associated to the UE or a certain functionality at the UE was last requested by first network node or any node.

[0250] B3**. The method of B3 compromising deleting the stored set of UE-side AI / ML applicability information associated to the UE and to the first network node

[0251] B4. The method of B1, comprising retrieving and transmitting to the third network node (which may be the same as first network node) the stored set of UE-side AI / ML applicability information associated to the UE in response of:

[0252] • Determining that the UE is connected or is connecting to the first network node

[0253] • Receiving a request from the first network node

[0254] • Receiving a request from a network node neighbor to the first network node

[0255] • Determining that the first network node is neighbour of network node

[0256] • Determining that the third network node is serving a cell or an area to which the UE- side AI / ML applicability refer to

[0257] B4*. The method of B4 wherein the retrieved set of UE-side AI / ML applicability information are transmitted to the third network node via a network node neighbor of the first network node B4**. The method according to B4 wherein the second network node sends the information only if the information is applicable to the UE when being served by the third node (for example, if the information kept by the second node is applicable only when the UE is associated with a node A, but not a node B, the second node would send the info to node A, but not to node B).

[0258] B5. The method of B4, wherein transmitting the set of UE-side AI / ML applicability information associated to a UE comprises transmitting a subset of the stored UE-side AI / ML applicability information associated to the UE, including any of:

[0259] • The stored UE-side AI / ML applicability information valid for the third network node

[0260] • The stored UE-side AI / ML applicability information valid for neighbouring nodes of the third network node

[0261] • The stored UE-side AI / ML applicability information for one or more specific AI / ML models / functionalities.

[0262] • The stored UE-side AI / ML applicability information valid for the serving cells / frequencies configured to the UE.

[0263] • The stored UE-side AI / ML applicability information valid for neighbouring cells / frequencies

[0264] • The stored UE-side AI / ML applicability information valid for non serving cells / frequencies for the UE

[0265] B6. The method of B4, wherein the set of UE-side AI / ML applicability information associated to a UE is transmitted to the third network node along with the radio access capabilities associated to the UE.

[0266] B6. The method of B4 wherein if the second node lacks AI / ML applicability information associated to the UE and to the third network node, the second node indicates to the third node the absence of such info.

[0267] B6*. The method of B4 wherein if the second node lacks AI / ML applicability information associated to the UE and to the third network node, the second node indicates potential applicability information suggested by the third network node

[0268] B6**. The method of B6* wherein the second node suggest potential applicability information based on other applicability information obtain from other UE(s) of the similar attribute / characteristics.

[0269] B7. The method of B1 , wherein the second network node is a mobile network node or function within a mobile network node, such as the AMF, the NEF, or a UE capability management function (UCMF).

[0270] Embodiments for a UE C1. A method at a UE comprising:

[0271] Reporting to a first network node at a RAN a set of UE-side AI / ML applicability information and,

[0272] Upon entering an Idle state, deleting at least one of the UE-side AI / ML applicability information.

[0273] C2. A method of C1 , further comprising transitioning to a Connected state form an Idle state and receiving in a first RRC Reconfiguration message an AI / ML configuration.

[0274] C3. A method of C1 and C2, wherein the AI / ML configuration is base don the UE-side AI / ML applicability information previously reported by the UE when the UE was in Connected state. C4. A method of C1 , C2 and C3, further comprising transmitting UE-side AI / ML applicability information when transitioning to a Connected state from the Idle state when it triggers a Registration Area Update.

[0275] C5. A method of C4, wherein the Registration Area Update is a mobility triggered and / or when the UE is entering a new registration area.

[0276] As indicated above, certain embodiments may provide one or more of the following technical advantage(s). For example, example methods disclosed herein may enable the network node, e.g. RAN node, to provide the UE with an AI / ML model / functionality configuration for the inference without the need to rely, at least in some cases, on the UE transmitting first an applicability report message prior to receive the inference configuration for the AI / ML model / functionality. That avoids the need to rely on at least two reconfiguration procedures, i.e. one for configuring the UE to report the UE applicability report, and one for the configuring the UE with the inference configuration.

[0277] Hence, examples of this disclosure reduce the delay for the UE to start operating an AI / ML model / functionality, it reduces the signaling involved both in the uplink and downlink, and ultimately it reduces the UE energy consumption. The teachings of certain embodiments may improve network performance. The following provides further example embodiments f this disclosure.

[0278] First step - Identifying the set of UE-side AI / ML applicability information

[0279] Examples of this disclosure provide a method for a first network node (e.g. a gNodeB the UE is connected to) for identifying a set of UE-side AI / ML applicability information. The set of UE-side AI / ML applicability information may comprise one or more network (NW)-side additional conditions and / or one or more UE (UE)-side additional conditions. The NW-side additional conditions and / or UE side additional conditions are information available at the first network node, and may be comprise one or more information received from the UE or available already at the first network node. The set of UE-side AI / ML applicability information can hence include any of the following information or a combination of them:

[0280] • A first set of information associated to the applicability conditions of one or more AI / ML models / functionalities included in an applicability report message transmitted by the UE to the first network node o In this case, the UE may transmit, for example as part of an applicability report message, the applicability conditions such as the NW-side conditions and / or UE-side conditions, under which the one or more AI / ML models / functionality are applicable for the inference, as a result of the applicability evaluation of one or more AI / ML models / functionalities at the UE. The applicability report message may be transmitted in an RRC message, such as an RRC complete message (e.g. RRCReconfigurationComplete), or UElnformationResponse, or UEAssistancelnformation. The set of NW-side conditions and / or UE-side conditions transmitted in the applicability report message may be transmitted by the UE in response of receiving a configuration from the gNB to evaluate the applicability of one or more AI / ML model(s) / functionality(ies), wherein the configuration may be carried in an RRCReconfiguration, or in a UElnformationRequest. The configuration may include one or more NW / UE-side additional conditions that the UE applies to evaluate the applicability of the one or more AI / ML model(s) / functionality(ies). The one or more NW / UE-side additional conditions transmitted in the applicability report message may be selected from the one or more NW / UE- side additional conditions included in the said configuration.

[0281] The UE / NW-side additional conditions transmitted by the UE in the applicability report message may be associated to the first network node, e.g. gNB / LMF, to which the UE is connected, to the serving cells (SpCell, SCells), serving frequencies, but also they may be associated to other network nodes, e.g. neighbouring network nodes, neighbouring cells / frequencies (nonserving cells / frequencies). For example, the UE may be configured to transmit the UE / NW-side additional conditions associated to certain gNBs / cells / frequencies (indicated via CGIs / gNB-IDs) related to the applicability of certain AI / ML models / functionalities. o The first set of information includes the applicability conditions reported by the UE in a first applicability report message. Hence, by storing this information at the network (i.e. at the second network node), and retrieving them by the first network node prior to provide the inference configuration, it allows the first network node to retrieve the applicability conditions related to the AI / ML model(s) / functionality(ies) and associated to the first network node previously transmitted by the UE. Hence, the first network node can configure an inference configuration that makes the AI / ML model / functionality applicable without the need to for the UE to reporting a second applicability report message.

[0282] The first network node may transmit further information to the second network node, such as the radio configuration configured to the UE at the moment of the UE evaluating the applicability conditions.

[0283] • A second set of information associated to the training configuration configured by the first network to the UE for the UE-side model training o In this case, the training configuration comprising at least a radio resource configuration configured by the first network node to the UE during UE-side model training. The training configuration can comprise the NW-side additional conditions that are operated by the network at the time of UE-side training. For example, the gNB may receive a request from the UE to perform UE-side model training, and the gNB in response may provide a radio configuration for the UE to perform the UE-side model training. The radio configuration, e.g. a CSI measurement configuration can comprise the set A and / or B of resources that the UE uses for the UE-side model training, wherein each of the resources forming the set A / B can be represented by an associate ID. o By storing this information at the network (i.e. at the second network node), and retrieving them by the first network node prior to provide the inference configuration, it allows the first network node to retrieve the training configuration the UE operated for the training of UE-side model. Hence, the first network node can configure an inference configuration that makes the AI / ML model / functionality applicable, i.e. fitting the UE-trained data set, without the need to for the UE to report the applicability report message.

[0284] • A third set of information associated to the UE-side conditions operated by the UE at the time of UE-side model training transmitted to the first network node by the UE, or configured by the first network node to the UE o In this case, the third set of information may comprise the radio configuration configured by the first network node to the UE during the UE-side model training, which can comprise a plurality of radio configurations and associated parameters, such as the radio bearer configurations, the MCG cell group configuration (comprising e.g. the MAC, RLC, PHY configurations of the PCell and SCells), the SCG cell group configuration (comprising e.g. the MAC, RLC, PHY configurations of the PSCell and SCells), the radio measurement configurations including the measurement configuration of serving or non-serving / neighbouring cells / frequencies.

[0285] Further, the UE may transmit to the gNB, e.g. prior to the first network node providing the training configuration, the UE-side additional conditions which may comprise UE-specific information other that the radio configurations transmitted by the first network node. This UE-side additional conditions could comprise for example, the UE location, the latest beam-level radio measurements on SS / PBCH block or CSI-RS, and / or cell-level radio measurements of serving cells and / or neighboring cells, the UE battery status, etc. o By storing this information at the network (i.e. at the second network node), and retrieving them by the first network node prior to provide the inference configuration, it allows the first network node to retrieve the radio configuration and other UE-side additional conditions, that the UE operated during the training of UE-side model. Hence, the first network node can configure an inference configuration that makes the AI / ML model / functionality applicable, i.e. fitting the UE-trained data set, without the need to for the UE to report the applicability report message.

[0286] • A fourth set of information associated to the NW-side conditions operated by the first network node at the time of the UE performing UE-side model training. o The NW-side conditions may include for example, gNB transmission power, network deployment scenarios (e.g., ISD, Umi / Uma), gNB antenna height and / or other antenna properties such as beam and Tx port mapping relationship in the gNodeB for a given cell, NW antenna shape, antenna dip angle, gNB / cell load in terms of connected users, radio resource utilizations (in terms of PDCCH / RACH / PUCCH / PUSCH / PDSCH resource load, number of configured bearers, etc), neighbours node relations, etc. o By storing this information at the network (i.e. at the second network node), and retrieving them by the first network node prior to provide the inference configuration, it allows the first network node to retrieve the radio configuration at the first network node and deployment properties, that the first network node was operating at the time of UE performing the training of UE-side model. Hence, the first network node can configure an inference configuration that makes the AI / ML model / functionality applicable, i.e. fitting the UE-trained data set, without the need to for the UE to report the applicability report message.

[0287] The set of UE-side AI / ML applicability information may include an ID for each of the information included in the set (e.g. an associate ID associated to each of the information included), or it may include a specific value associated to each of the information included in the set.

[0288] The set of UE-side AI / ML applicability information may be specific for a certain AI / ML model / functionality, or it may be common to more than one AI / ML model / functionality.

[0289] The set of UE-side AI / ML applicability information may be specific for one or more cells, or for one or more frequencies, or for one or more nodes, or for one or more validity areas. For example, the UE may transmit to the first network node, the cells or the frequencies or the gNBs / LMFs or the validity area (list of cells / frequencies, geographical area, the PLMN), for which the applicability conditions of one or more AI / ML models / functionalities are valid. For example, the applicability conditions may include the NW-side additional conditions / UE-side additional conditions that makes a certain AI / ML model / functionality applicable in certain cells / frequencies / gNBs / LMF / area, or even throughout the whole PLMN. This implies the first network node receiving from the UE, the applicability conditions associated to applicable inference operations within one or more of serving cells / frequencies, within the serving network node (e.g. serving gNB / LMF), or for inference operations in neigburouing cells / frequencies, or neighbouring network nodes, e.g. neighbouring gNBs / LMFs. Hence the first network node may transmit to the second network node a set of UE-side AI / ML applicability information associated to multiple serving / non-serving cells / frequencies / gNBs / LMF or areas in which the UE is not currently located.

[0290] Second step - Transmitting the set of UE-side AI / ML applicability information to the second network node

[0291] In a second example method of this disclosure, the first network node transmits to the second network node at the CN the identified set of UE-side AI / ML applicability information. Along with the said set, the first network node may transmit: • The identity of the UE to which the set of transmitted UE-side AI / ML applicability information refers to (e.g. an S-TSMI, a 5G-S-TMSI, a 6G-S-TMSI, or a globally unique identifier, such as an IMSI)

[0292] • The cell(s), frequency(ies), network node(s)(e.g. gNB(s), LMF(s)) to which the set of transmitted UE-side AI / ML applicability information refers to. For example, the first network node may transmit the CGI, or the gNB / LMF ID, or the ARFCN of the frequency to which the set of transmitted UE-side AI / ML applicability information refers to

[0293] • A time reference (e.g. timestamp) associated to the point in time in which the set of transmitted UE-side AI / ML applicability information were identified

[0294] • The AI / ML model(s) / functionality(ies) to which the set of UE-side AI / ML applicability information refers to.

[0295] The set of UE-side AI / ML applicability information may be identified / updated and / or transmitted from the first network node to the second network node in difference cases (i.e. triggered by different situations):

[0296] • Upon configuring the UE for UE-side model training, i.e. at the time of providing the UE with a radio configuration for UE-side model training, or at the time of sending an indication to the UE to start performing the UE-side model training, the first network node may identify the NW / UE-side additional conditions that apply at that moment, and transmit them to second network node.

[0297] • Upon receiving an applicability report message from the UE, the first network node may identify the NW / UE-side additional conditions that apply at that moment and transmit them to the second network node. o In one option the first network node corresponds to a RAN node (e.g. gNodeB) which transmits to the second network node (e.g. AMF) the identified set of UE-side AI / ML applicability information when it receives from a UE the set of UE-side AI / ML applicability information e.g. in a UE Assistance Information and / or in n RRC Reconfiguration Complete message.

[0298] • Upon change in the NW-additional conditions operated in the first network node that has impact the applicability information associated to the UE. In such cases, the first network node can indicate the change to the second network node so that the applicability information regarding NW-additional conditions associated with the first network node and are no longer relevant can be discarded.

[0299] • Upon configuring the UE with an AI / ML inference configuration or at the time of providing a new / updated AI / ML inference configuration, the first network node may identify the NW / UE-side additional conditions that apply at that moment and transmit them to the second network node.

[0300] • Upon the UE stops the data collection for UE-side model training: o According to this method, the first network node identifies the set of UE-side AI / ML applicability information at the time of the UE stops the data collection for UE-side model training. For example, the UE may indicate to the first network node that the data collection for UE-side model training can be stopped. In response, the first network node may release / deconfigure the radio configuration for the UE-side model training, and it may identify the set of UE-side AI / ML applicability information which may comprise for example the one or more information from any of the first / second / third / fourth set of information that were applied during the UE-side model training. For example, if the first network node configured the UE with different radio resource configurations, or different training configurations (including the radio resource configuration for training purposes), during the UE side model training, then the set of AI / ML applicability information can comprise these multiple different configurations. In another example, if different NW side additional conditions were applied by the first network node during the UE side model training, then the set of AI / ML applicability information can comprise these multiple different NW-side additional conditions. In another example, if different UE side additional conditions were applied by the UE during the UE side model training, then the set of AI / ML applicability information can comprise these multiple different UE-side additional conditions.

[0301] • Upon the UE performs a connected mode mobility or leaves the area covered by the first network node or the validity area: o According to this method, the first network node identifies the set of UE-side AI / ML applicability information at the time of the UE performing a connected mode mobility to a target cell / frequency / node (gNB, LMF), or moves to a different area. In this case, the first network node may identify the set of UE- side AI / ML applicability information which may comprise for example the one or more information from any of the first / second / third / fourth set of information that were applied during the UE-side model training performed in the source cell / frequency / gNB / LMF or that were received from the UE in the applicability report message transmitted to the first network node in the source cell / frequency / gNB / LMF. • Upon the UE changes the RRC state: o According to this method, the first network node identifies the set of UE-side AI / ML applicability information at the time of the UE transitioning to an Idle state while connected to the first network node. In this case, the first network node may identify the set of UE-side AI / ML applicability information which may comprise for example the one or more information from any of the first / second / third / fourth set of information that were applied during the UE- side model training performed in the first network node or that were received from the UE in the applicability report message transmitted to the first network node, prior to the UE changing its RRC state to Idle. For example, the set of UE-side AI / ML applicability information may be identified upon transmitting an RRC release message, or an RRC release message with suspend configuration, or upon determining that the UE has entered an RRC idle state. o In one option, in further details, the first network node corresponds to a RAN node (e.g. gNodeB) which transmits to the second network node (a core network node e.g. AMF - Authentication and Mobility Function) the identified set of UE-side AI / ML applicability information in response to the first network node transitioning the UE to an IDLE state (e.g. RRCJDLE), e.g., when the first network node transmits to the UE an RRC release message (without a suspend configuration) to transition the UE to the IDLE state. In one suboption the first network node (e.g. gNB) sends the set of UE-side AI / ML applicability information to the second network node (e.g. AMF) within a N2 CONTEXT RELEASE REQUEST MESSAGE or an N2 CONTEXT RELEASE COMPLETE, during or at the end of the procedure between the gNodeB and the AMF for releasing the CN / RAN connecting (e.g. NG-1 connectivity). o In another option, the first network node sends to the second network node at the core network (e.g. AMF) the set of UE-side AI / ML applicability information when the first network node and / or the second network node determines to release a CN / RAN connection (e.g. a logical NG-AP signalling connection, and / or an associated N3 User Plane connections and RAN I RRC signalling and resources).

[0302] ■ The initiation of the release by the first network node may be due to one or more of: O&M Intervention, Unspecified Failure, (R)AN (e.g. Radio) Link Failure, User Inactivity, Inter-System Redirection, request for establishment of QoS Flow for IMS voice, Release due to UE generated signalling connection release, mobility restriction, etc. This may be an aN (Access Node) or gNodeB initiated release.

[0303] ■ The initiation of the release by the second network node (e.g. AMF) may be due to one or more of: Unspecified Failure, etc.

[0304] • Upon transmitting and / or updating the second network ndoe with UE capabilities. o In one option the first network node corresponds to a RAN node (e.g. gNodeB) which transmits to the second network node (e.g. AMF) the identified set of UE-side AI / ML applicability information when it transmits (updates) UE capabilities (e.g. UE Radio Capability information) to the second network node.

[0305] ■ In one sub-option the first network node stores the set of UE-side AI / ML applicability information while the UE is in Connected state and, when there is a need to update the UE capabilities at the second network node (e.g. AMF) the first network node also includes the latest set of UE-side AI / ML applicability information e.g. reported by the UE.

[0306] ■ In one sub-option the first network node sends the set of UE-side AI / ML applicability information to the second network node (e.g. AMF) in a N2 UE Applicability Info Indication message.

[0307] ■ In one sub-option the first network node sends the set of UE-side AI / ML applicability information to the second network node (e.g. AMF) in a N2 UE Capability Info Indication message. o In one option the first network node corresponds to a RAN node (e.g. gNodeB) which transmits to the second network node (a core network node e.g. AMF) the identified set of UE-side AI / ML applicability information in response to a request from the second network node.

[0308] ■ In one sub-option the request corresponds to a N2: UE Applicability Match Request, in response to which the first network node (e.g. gNB) transmits the N2: UE Applicability Match Response.

[0309] ■ In one sub-option the request corresponds to a UE Capability Match Request, which means that the first network node (e.g. gNB) responds with an N2: UE Capability Match Response, including both the UE Radio Capabilities and the set of UE-side AI / ML applicability information.

[0310] In one option, the second network node receives from the first network node a message requesting and / or confirming the release of the CN / RAN connection (e.g. a logical NG-AP signaling connection, and / or an associated N3 User Plane connections and RAN I RRC signaling and resources). And, in response to that, the second network node stores the latest received set of UE-side AI / ML applicability information. This implies that the second network node may have received various sets of UE-side AI / ML applicability information while the RAN / CN connection was up and running e.g. when the UE triggers handovers, etc. Then, when the RAN / CN connection is to be release the second network nmode (e.g. aMF) stores the latest set of UE-side AI / ML applicability information received from the first network node.

[0311] Third step - Storing and updating the set of UE-side AI / ML applicability information at the second network node

[0312] The second network node upon receiving the set of UE-side AI / ML applicability information stores it. The set of received UE-side AI / ML applicability information may be stored along with one or more of the following information for identifying the said set:

[0313] • The identity of the first network node that transmitted the set of UE-side AI / ML applicability information, e.g. the gNB / LMF ID

[0314] • The nodes, or the cells or the freguencies or the areas to which the UE-side AI / ML applicability information are valid, e.g. the set of CGIs, gNB / LMF IDs, area IDs, or freguency identity (ARFCN) for which the received UE-side AI / ML applicability information refer to

[0315] • The time at which the set of UE-side AI / ML applicability information is received

[0316] The set of UE-side AI / ML applicability information, stored in the second network node (e.g. AMF), is associated at the second network node with a UE identifier, so it may be later retrieved e.g. when the UE tries to transition from IDLE state to CONNECTED state. The UE identifier may be a UE identifier assigned by the core network e.g. a 5G S-TMSI and / or a SUCI and / or an I MSI , or any form of CN context identifier and / or a Non-Access Stratum (NAS) identifier. A different identifier may be associated to the UE depending on whether the UE is registered or not e.g. for a registered UE, the 5G-S-TMSI (or 6G-S-TMSI) is used, otherwise a non-temporary identifier is used (globally unigue).

[0317] The second network node may also store the received UE-side AI / ML applicability information according to any of the following example methods:

[0318] • For each gNB / LMF / cell / freguency / area, the second network node stores the received UE-side AI / ML applicability information, wherein the UE-side AI / ML applicability information conveys information related to the AI / ML applicability in the gNB / LMF / cell / frequency / area for a certain UE o According to this method, the first entry can be the gNB / LMF / cell / frequency / area, and the second entry associated to the first entry can be the UE identity and the third entity associated to the first / second entry can be the related set of UE-side AI / ML applicability information valid for the first / second entry. o In an alternative method, the third entry may be the identity of an AI / ML model / functionality, and the fourth entry may be the set of UE-side AI / ML applicability information associated to the first / second / third entry.

[0319] • For each UE, the second network node stores the associated received UE-side AI / ML applicability information, wherein the UE-side AI / ML applicability information conveys information related to the AI / ML applicability in multiple different gNBs / LMFs / cells / frequencies / areas o According to this method, the first entry can be the UE identity, and the second entry associated to the first entry can be the identity of the gNB / LMF / cell / frequency / area and the third entity associated to the first / second entry can be the related set of UE-side AI / ML applicability information valid for the first / second entry. o In an alternative method, the third entry may be the identity of an AI / ML model / functionality, and the fourth entry may be the set of UE-side AI / ML applicability information associated to the first / second / third entry.

[0320] For a given UE, the set of UE-side AI / ML applicability information may be stored together with the UE radio access capabilities.

[0321] For a given UE, the set of UE-side AI / ML applicability information may be discarded if an indication is received from the first Network node indicating that the stored information is no longer valid. Additionally, the set of UE-side AI / ML applicability information may be discarded if the information has not been requested by one or more network node for a given time duration.

[0322] A first Network node may indicate a change in the NW-additional conditions in which it operates making the stored information for a given one or more UEs indicating the outdated NW-additional conditions of the first network node irrelevant anymore. In response, the set of UE-side AI / ML applicability information corresponding to those UEs may be discarded. Fourth step - Retrieving the set of UE-side AI / ML applicability information at / from the second network node

[0323] The second network node retrieves the previously stored UE-side AI / ML applicability information. The retrieval can occur in the following cases:

[0324] • The UE connecting to the first network node (or to a third network node) o According to this method, the UE may perform a connected mode mobility procedure to the first network node (target node of the mobility procedure), or it may enter RRC connected mode by connecting to the first network node. o In one method, upon completing the connection to the first network node, the first network node may request the second network node to transmit the UE- side AI / ML applicability information associated to the said UE. o In another method, the second network node is notified that the UE connected to the first network node, and the second network node may transmit the UE-side AI / ML applicability information for the said UE, without the request from the first network node o In another method, prior to executing the mobility procedure to the first network node (target node), the source network node may request the second network node to provide the UE-side AI / ML applicability information associated to the first network node. This request can be transmitted for example during or before the HO preparation concerning the first network node as target node of a mobility procedure. Alternative!, the second network node can inform the source network node about the UE-side AI / ML applicability information associated to the first network node, based on information of neighbour nodes relations that are available at the second network node. For example, the second network node may know that the first network node is a neighbor node of the source network node, and hence it may provide the source network node with the UE-side AI / ML applicability information relevant for the first network node.

[0325] In such case, the UE-side AI / ML applicability information concerning the first network node may be transmitted by the source network node as part of the HO preparation message, with or without the UE radio access capabilities.

[0326] • The UE registering to the second network node. o According to this method, as part of a registration acceptance the second network node may transmit to the first network node the UE-side AI / ML applicability information associated to the first network node which in this case is the node to which the UE connected.

[0327] • The first or third network node determining that the UE supports / is capable of one or more AI / ML models / functionalities o According to this method, before requesting the UE-side AI / ML applicability information to the second network node, the first network node based on the UE radio access capabilities whether the UE supports / is capable of AI / ML and of which specific AI / ML model / functionality. For example, the second network node may first transmit to the first network node the radio access capabilities, and based on this information the first network node may determine whether to request the UE-side AI / ML applicability information. The first network node may also determine if the UE supports AI / ML models / functionalities of interest, in which case the first network node transmits a request specific for the UE-side AI / ML applicability information associated to one or more supported AI / ML models / functionalities. Otherwise it does not send the request.

[0328] • The first or third network node determining whether to provide an AI / ML inference configuration to the UE o According to this method, before requesting the UE-side AI / ML applicability information to the second network node, the first network node determines whether to configure an AI / ML inference configuration. This determination can be based on the UE radio access capabilities and on whether the UE supports / is capable of AI / ML and of which specific AI / ML model / functionality (as disclosed in the previous method). Additionally, the determination can be based on other conditions: for example, given the current radio conditions (e.g. UE in bad coverage or close to cell border), or UE location, the first network node may determine that AI / ML may provide enhanced performances. Or the first network node may determine that AI / ML may provide enhanced energy savings at the UE and / or at the first network node. Or the first network node may determine that AI / ML may provide enhanced scheduling performances, beam selections, handover decisions, more accurate radio measurements, or more accurate event predictions, etc. o If it is determined to configure the AI / ML inference configuration to the UE, the request is transmitted, otherwise it is not

[0329] • The first or third network node determining whether to provide an AI / ML training configuration to the UE o According to this method, before configuring the UE with a radio resource configuration for UE-side model training, the first network node may transmit a request to the second network node for the UE-side AI / ML applicability information. This method can be used for example to determine those UE- side AI / ML applicability information associated to AI / ML models / functionalities for which the UE has already performed the UE-side model training. Hence the radio resources configuration for the training could be such that it is for train the UE on different AI / ML models / functionalities not yet trained, or for retraining certain AI / ML models / functionalities under different NW- / UE-side conditions.

[0330] In one option, the first or third network node receives the set of UE-side AI / ML applicability information associated to the UE when it tries to transition the UE to a CONNECTED state (e.g. RRC_CONNECTED), e.g., in response to receiving an RRC Setup Request or an RRC Setup Complete. And, before the first or third network node configures the UE with an AI / ML functionality configuration (e.g. inference configuration).

[0331] In one option, the first or third network node (e.g. a gNodeB in which the UE is trying to transition to Connected state) triggers the retrieval of the set of UE-side AI / ML applicability information from the second network node (e.g. AMF in which the UE is registered) when it receives an RRC Setup Complete from a UE. That RRC Setup Complete and a previously received RRC Setup Request includes a UE identifier (e.g. 5G-S-TMSI), or two parts of a UE identifiers, based on which the third network node is able to identify the second network node (e.g. the AMF) in which the set of UE-side AI / ML applicability information is stored. Then, when the third network node transmits to the second network node the INITIAL UE MESSAGE, at some point the third network node may receive an INITIAL CONTEXT SETUP REQUEST message including the stored set of UE-side AI / ML applicability information. o In one sub-option, the third network node includes in the INITIAL UE MESASAGE an indication that it wants to receive the set of UE-side AI / ML applicability information from the second network node. Notice that this may be useful in case the third network node is capable of an AI / ML functionality, otherwise there would be no reason to get from the second network node the set of UE-side AI / ML applicability information. o In one sub-option, the second network node may receive in the INITIAL UE MESASAGE an indication that the third network node wants to receive the set of UE-side AI / ML applicability information stored in the second network node. ■ In one sub-sub-option, when that indication is not included, the second network node may delete the set of UE-side AI / ML applicability information.

[0332] ■ In one sub-sub-option, when that indication is not included, the second network node keep the set of UE-side AI / ML applicability information stored, so that it may be later requested by another RAN node e.g. after a handover, connected mode mobility procedure, or transitions to Idle and connected.

[0333] The request, if it is transmitted by the first network node, may comprise one or more of the following information:

[0334] • The identity of the UE for which it is requested the set of UE-side AI / ML applicability information

[0335] • The identity of one or more cells / frequencies / nodes / areas for which it is requested the set of UE-side AI / ML applicability information, i.e. the first network node requests whether there are stored UE-side AI / ML applicability information valid for the concerned cells / frequencies / nodes / areas. o For example, the first network node may request whether for certain CGIs or the gNB / LMF-IDs there are stored UE-side AI / ML applicability information associated to the said UE. The indicated cells could be cells / frequencies hosted by the first network node or neighbouring cells / frequencies possibly hosted by a different RAN network node, or they could be the serving cells currently configured to the UE (e.g. SpCell and / or SCells), or non serving cells / frequencies for the UE. The indicated gNB / LMF ID could be the ID of the first network node, or the IDs of one or more neighbouring nodes or the CGIs / frequency identities of neighbouring cells / frequencies. o According to this method, if for the said UE there are stored UE-side AI / ML applicability information associated to multiple cells / frequencies / nodes / areas, the second network node only selects / retrieves the UE-side AI / ML applicability information for the requested cells / frequencies / nodes / areas

[0336] • The one or more AI / ML models / functionalities for which it is requested the set of UE- side AI / ML applicability information, i.e. the first network node requests whether there are stored UE-side AI / ML applicability information valid for the certain AI / ML models / functionalities o The first network node may determine if the UE supports certain AI / ML models / functionalities of interest that can be configured for the UE-side inference, and hence indicate in the request message, a request for the UE- side AI / ML applicability information associated to such AI / ML models / functionalities of interest. o According to this method, if for the said UE there are stored UE-side AI / ML applicability information associated to multiple AI / ML models / functionalities, the second network node only selects / retrieves the UE-side AI / ML applicability information associated to the requested AI / ML models / functionalities

[0337] An example embodiment combining some of the previous steps for storing and retrieveing the set of AI / ML applicability information is shown.

[0338] In case the second network node did not send any AI / ML applicability information relevant for the first node, the first node may trigger a procedure for the first UE to AI / ML applicability information to the first node. This may comprise requesting the UE to send the information, or providing a configuring to the UE which allows the UE to (spontaneously) send such information. This has the benefit that the second node may have had AI / ML applicability information which is relevant for the first node but for some reason, e.g. too long time passed so the information became obsolete / considered invalid / etc. so that the second node did discard the information or by other means refrain from sending it to the first node. In this case it may be so that the UE anyway has AI / ML applicability information which is valid / relevant for the first node, but the first node would need to reacquire it.

[0339] Fifth step - Transmitting the set of UE-side AI / ML applicability information from the second network node to the first network node

[0340] According to this example method, the UE transmits the UE-side AI / ML applicability information retrieved as per the fourth method. The transmitted UE-side AI / ML applicability information may comprise the entire UE-side AI / ML applicablity information associated to the concerned UE and stored at the second network node, or a subset of it. For example, if for the concerned UE there are stored UE-side AI / ML applicability information associated to multiple AI / ML models / functionalities, the second network node only transmits to the first network node the UE-side AI / ML applicability information associated to the requested AI / ML models / functionalities, if requested by the first network node. In another example, if for the said UE there are stored UE-side AI / ML applicability information associated to multiple cells / frequencies / nodes / areas, the second network node only transmit to the first network node the UE-side AI / ML applicability information for the requested cells / frequencies / nodes / areas, if requested by the first network node. In yet another example, the entire set of UE-side AI / ML applicability information associated to the concerned UE are transmitted to the first network node, and then it is the first network node that selects among the received UE-side AI / ML applicability information those information that are relevant / of interest, e.g. only those associated to certain cells / frequencies / nodes / areas or to certain AI / ML models / functionalities.

[0341] In one method the said set of UE-side AI / ML applicability information are transmitted to the first network node along with the radio access capabilities.

[0342] In case the second node did not retrieve any AI / ML applicability information which was relevant for the UE in the targeted situation (e.g. not relevant for the first node) the network may indicate this by either absence of any information of by an explicit indication to the first node.

[0343] Sixth step - Transmitting an inference configuration based on the set of UE-side AI / ML applicability information received from the second network node

[0344] Upon receiving the set of UE-side AI / ML applicability information, the first network node may determine whether based on the received set of UE-side AI / ML applicability information an inference configuration should be provided to the UE, or whether a radio resource configuration for the UE-side model training should be provided to the UE.

[0345] The decision can be based for example on whether the UE-side AI / ML applicability information fits the NW-side additional conditions that the first network node is operating or can operate (e.g. whether the current gNB / cell load, or the first network node is sharing the same spatial filters of the second network node, or the first network node share the same associated ID for the set A / B as the second network node, or the current transmitting power or the current NW deployment, or the set A and / or B of resources including the future time frame to predict and the associated ID fits the information contained in the set of UE-side AI / ML applicability information) or the UE-side additional conditions that are valid for the UE at the moment, or that the first network node may configure. For example, based on the UE location, or based on the radio measurements received by the UE or derived at the first network node, the first network node may want to configure the UE with an inference configuration for the UE to predict radio measurements on certain resources (set A), or certain events, based on measurement on certain resources (set B); however from the set of UE-side AI / ML applicability information the first network node may determine that certain AI / ML model(s) / functionality(ies) may not be applicable for the desired set A of resources, and / or they may not be applicable if the UE is configured to perform measurements on the desired set B of resources. Hence, as a result, the first network node may determine to not configure the AI / ML inference configuration to enable certain AI / ML models / functionalities at the UE, or conversely to configure the AI / ML inference configuration. In the latter case, the first network node may provide an inference configuration that fits the set of received UE-side AI / ML applicability information. For example, the first network node may configure as part of the inference configuration one or more sets A and / or B that may make an AI / ML model / functionality applicable at the UE, the first network node may provide the UE with a radio configuration that may make an AI / ML model / functionality applicable at the UE, the first network node may tune certain NW-specific parameters (e.g. antenna configuration, transmitting power, etc) in order to make an AI / ML model / functionality applicable at the UE, the first network node may start transmitting certain reference signals (SSB / CSI-RS) in order make an AI / ML model / functionality applicable at the UE, etc.

[0346] The inference configuration can be conveyed in an RRC Reconfiguration message, and it can convey the configuration for one or more AI / ML model(s) / functionality(ies). The inference configuration can comprise one or more inference configurations, each providing different operating conditions for the UE to operate with the concerned AI / ML models / functionalities, e.g. different possible sets A and / or B of resources, different possible radio configurations (MAC / RLC / PHY configuration), different fallback configurations (that the UE uses if the concerned AI / ML models / functionalities are fulfilling certain performance requirements), etc.

[0347] In response of receiving such inference configuration, the UE may transmit in response to the network node an applicability report message (e.g. via U EAssistanceinformation, RRCReconfigurationComplete message, UElnformationResponse etc) containing indication on whether the concerned AI / ML models / functionalities, for which the inference configuration was provided by the first network node, are applicable or not applicable, an indication of the one or more configurations included in the inference configuration that make the AI / ML model / functionality applicable, e.g. which of the set(s) A and / or B, which of the possible radio configurations (MAC / RLC / PHY configurations) make the AI / ML model / functionality applicable.

[0348] In one option, that is transmitted by the third network node to the UE in the first RRC Reconfiguration message after security activation, which is the same message in which the DRBs are being configured for the UE entering CONNNECTED state.

[0349] In one option, when the UE receives the inference configuration, monitoring configuration or a training configuration, the UE transmits in response a second set of AI / ML applicability information to the third network node (e.g. in an RRC Reconfiguration Complete). That may occur in case the UE the AI / ML functionality, for the provided configuration, is not applicable. Then, the third network may send the second set of AI / ML applicability information to the second network node e.g. to update the AI / ML applicability information in the second network node for that UE.

[0350] Example seventh method - Transmitting a monitoring configuration based on the set of UE- side AI / ML applicability information received from the second network node

[0351] Upon receiving the set of UE-side AI / ML applicability information, the first network node may determine whether based on the received set of UE-side AI / ML applicability information an inference configuration should be provided to the UE, or whether a radio resource configuration for the UE-side model monitoring should be provided to the UE.

[0352] The decision can be based for example on whether the UE-side AI / ML applicability information partially fits the NW-side additional conditions that the first network node is operating or can operate, the first network node may have a certain set A / B configuration which the second node have not assessed the applicability. Hence prior to providing an inference configuration, the first node provides monitoring configuration to assess the applicability of the NW / UE / environement- conditions that are different in the first and second node.

[0353] Example eighth method - The first node transmitting UE-side AI / ML applicability information to a third node

[0354] The first node may, as described above, receive UE-side AI / ML applicability information from the second node. The first node may forward this information to other nodes which the UE should be served by. This could be implemented by storing the information together with a UE context. If the UE is to be moved to be served by a different node (e.g. at handover or similar procedure), that UE context may then be forwarded to that different node. And if further mobility procedures will be performed for this UE the AI / ML applicability information may be carried over to other later nodes as well.

[0355] Further examples

[0356] Figure 7 illustrates an example of communications in a network according to examples of this disclosure, between a UE 702, gNodeB (gNB) 704, AMF 706 and a new gNB 708. The UE 702 is in RRC Connected state, and the gNB 704 stores a set of UE-side AI / ML applicability information. The gNB 704 sends a RRC Release (without suspend configuration) 706 to UE 702, so the UE transitions to RRC Idle state. The gNB 704 also sends a N2 UE Context Release Request 708 including the set of UE-side AI / ML applicability information 708 to AMF 706. The AMF 706 stores a set of UE-side AI / ML applicability information in step 710, e.g. as stored by and / or received from gNB 704. The AMF then sends a N2 UE Context Release Command 712 to gNB 704, which deletes the set of UE-side AI / ML applicability information in step 714.

[0357] The UE 702 then sends a RRC Setup Request 716 to new gNB 708, and the new gNB 708 sends a RRC Setup message 718 to the UE 702. The UE is then in RRC Connected state. The UE sends RRC Setup Complete 720 to the new gNB 708.

[0358] The new gNB sends Initial UE message 722 to the AMF 706, and NAS signalling 724 occurs between AMF 76 and UE 702. The AMF 706 then in step 726 retrieves the set of UE side AI / ML applicability information, e.g. as stored in step 710. The AMF 706 then sends an initial context setup request 728 including the set of UE-side AI / ML applicability information to the new gNB 708, and the the set of UE-side AI / ML applicability information is stored by the new gNB 708 in step 730. The new gNB 708 sends Security Mode Command 732 to UE 702, and the UE 702 replies to the new gNB 708 with Security Mode Complete message 734.

[0359] The new gNB 708 sends a RRC Reconfiguration message 736 including AI / ML configuration, e.g. inference configuration based on the set of UE-side AI / ML applicability information 736, to the UE 702, and the UE 702 replies to the new gNB 708 with a RRC Reconfiguration Complete message 738.

[0360] Figure 8 illustrates an example of reporting of UE-side AI / ML applicability information to the second network node as a result of the AI / ML model / functionality applicability evaluation at the UE. As shown in Figure 8, the UE determines the availability / applicability of one or more AI / ML models / functionalities, and transmits the applicability functionality reporting containing for example the NW / UE side additional conditions to make the one or more AI / ML models / functionalities applicable. The first network node extracts the NW / UE side AI / ML applicability information and transmit them (or a subset of them) to the second network node for storing.

[0361] In the Figure 8 and in all the following figures, it is assumed for simplicity that the UE-side AI / ML applicability information reporting is transmitted upon extracting the NW / UE-side AI / ML applicability information, however the transmission of this message may take place according to different criteria as described in any of the example methods described above. Figure 9 illustrates an example of reporting of UE-side AI / ML applicability information to the second network node as a result of a training session at the UE. As shown in Figure 8, the first network node configures the UE to perform training. The configuration can be triggered for example as a response to a request from the UE to perform the UE-side model training, or it can be triggered upon the first network node determining that an AI / ML model / functionality is not available for the UE to operate under the first network node or under certain UE / NW side conditions within the first network node, or upon determining that an AI / ML model / functionality is not fulfilling certain perform results during the inference in the first network node. The first network node then extracts the NW / UE side additional conditions based on what transmitted by the UE in the training request (if the training request is transmitted), and / or based on the NW / UE-side additional conditions available at the first network node, and / or based on the training configuration transmitted to the UE (e.g. based on the set A and / or B of resource indicated in the training configuration and for which the UE should perform the data collection for the UE-side model training), and / or based on the radio configuration configured to the UE during the UE-side model training. The UE-side AI / ML applicability information are transmitted to the second network node for storing.

[0362] Figure 10 illustrates an example method for retrieving of UE-side AI / ML applicability information from the second network node. As shown in Figure 10, upon a UE connecting to the first network node (e.g. upon the UE performing a mobility procedure to the first network node, or upon the UE entering RRC connected state from RRC idle / inactive state in the first network node), the first network node may retrieve the UE radio access capabilities, e.g. from the second network node, or from the source network node in case of a mobility procedure. Based on the AI / ML models / functionalities that the UE supports / is capable of, and / or based on whether the first network node wants to configure an inference / training configuration, the first network node transmits a request to the second network node for the transmission of the UE-side AI / ML applicability information for the concerned UE. Upon receiving this information, the first network node determines whether to configure the UE for the AI / ML inference and / or UE-side model training.

[0363] Figure 11 illustrates an example of another method for retrieving of UE-side AI / ML applicability information from the second network node. As shown in Figure 11, the second network node is informed that the UE has connecting to the first network node (e.g. the UE registers to the second network node, or during attach procedure the second network node is informed about the UE connection to the first network node). The second network node may then transmit to the first network node the UE radio access capabilities and the UE-side AI / ML applicability information. Upon receiving this information, the first network node determines whether to configure the UE for the AI / ML inference and / or UE-side model training.

[0364] Figure 12 illustrates an example of a method for retrieving of UE-side AI / ML applicability information from the second network node during the mobility procedure. In the example shown in Figure 12, the source network node may request the second network node to transmit the UE-side AI / ML applicability information related to the first network node. This can happen for example, prior the source network node issues an HO preparation for the HO (ordinary HO, or conditional HO) of the UE to the first network node. Or the second network node may transmit the UE-side AI / ML applicability information to the source network node based on knowledge of neighbor node relations available at the second network node, without the source network node sending any request. The source network node may transmit the retrieved UE-side AI / ML applicability information to the first network node (target node of the mobility procedure), e.g. as part of the HO preparation message, with or without the UE radio access capabilities. Upon the UE connecting to the first network node following a successful execution of the mobility procedure, the first network node determines whether to configure the UE with an AI / ML inference / training configuration based on the received UE- side AI / ML applicability information associated to the concerned UE.

[0365] Figure 13 shows an example of a communication system QQ100 in accordance with some embodiments.

[0366] In the example, the communication system QQ100 includes a telecommunication network QQ102 that includes an access network QQ104, such as a radio access network (RAN), and a core network QQ106, which includes one or more core network nodes QQ108. The access network QQ104 includes one or more access network nodes, such as network nodes QQ110a and QQ110b (one or more of which may be generally referred to as network nodes QQ110), 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 network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network QQ102 includes one or more Open- RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network QQ102 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 QQ102, including one or more network nodes QQ110 and / or core network nodes QQ108.

[0367] Examples of an ORAN network node include an open radio unit (0-Rll), 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 A1, F1, W1, E1 , E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes QQ110 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs QQ112a, QQ112b, QQ112c, and QQ112d (one or more of which may be generally referred to as UEs QQ112) to the core network QQ106 over one or more wireless connections.

[0368] 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 QQ100 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 QQ100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0369] The UEs QQ112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes QQ110 and other communication devices. Similarly, the network nodes QQ110 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs QQ112 and / or with other network nodes or equipment in the telecommunication network QQ102 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 QQ102.

[0370] In the depicted example, the core network QQ106 connects the network nodes QQ110 to one or more host computing systems, such as host QQ116. 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 QQ106 includes one more core network nodes (e.g., core network node QQ108) 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 QQ108. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (ALISF), Subscription Identifier Deconcealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0371] The host QQ116 may be under the ownership or control of a service provider other than an operator or provider of the access network QQ104 and / or the telecommunication network QQ102. The host QQ116 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.

[0372] As a whole, the communication system QQ100 of Figure 13 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. In some examples, the telecommunication network QQ102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network QQ102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network QQ102. For example, the telecommunications network QQ102 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.

[0373] In some examples, the UEs QQ112 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 QQ104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network QQ104. 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).

[0374] In the example, the hub QQ114 communicates with the access network QQ104 to facilitate indirect communication between one or more UEs (e.g., UE QQ112c and / or QQ112d) and network nodes (e.g., network node QQ110b). In some examples, the hub QQ114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub QQ114 may be a broadband router enabling access to the core network QQ106 for the UEs. As another example, the hub QQ114 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 QQ110, or by executable code, script, process, or other instructions in the hub QQ114. As another example, the hub QQ114 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 QQ114 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub QQ114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub QQ114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub QQ114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices. The hub QQ114 may have a constant / persistent or intermittent connection to the network node QQ110b. The hub QQ114 may also allow for a different communication scheme and / or schedule between the hub QQ114 and UEs (e.g., UE QQ112c and / or QQ112d) , and between the hub QQ114 and the core network QQ106. In other examples, the hub QQ114 is connected to the core network QQ106 and / or one or more UEs via a wired connection. Moreover, the hub QQ114 may be configured to connect to an M2M service provider over the access network QQ104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes QQ110 while still connected via the hub QQ114 via a wired or wireless connection. In some embodiments, the hub QQ114 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 QQ110b. In other embodiments, the hub QQ114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node QQ110b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0375] Figure 14 shows a UE QQ200 in accordance with some embodiments. The UE QQ200 presents additional details of some embodiments of the UE QQ112 of Figure 13. 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- loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0376] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0377] The UE QQ200 includes processing circuitry QQ202 that is operatively coupled via a bus QQ204 to an input / output interface QQ206, a power source QQ208, a memory QQ210, a communication interface QQ212, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 14. 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.

[0378] The processing circuitry QQ202 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 QQ210. The processing circuitry QQ202 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 QQ202 may include multiple central processing units (CPUs). The processing circuitry QQ202 may be configured to cause the UE QQ202 to perform the methods as described with reference to Figure 6.

[0379] In the example, the input / output interface QQ206 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 QQ200. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device. In some embodiments, the power source QQ208 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 QQ208 may further include power circuitry for delivering power from the power source QQ208 itself, and / or an external power source, to the various parts of the UE QQ200 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source QQ208. Power circuitry may perform any formatting, converting, or other modification to the power from the power source QQ208 to make the power suitable for the respective components of the UE QQ200 to which power is supplied.

[0380] The memory QQ210 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 QQ210 includes one or more application programs QQ214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data QQ216. The memory QQ210 may store, for use by the UE QQ200, any of a variety of various operating systems or combinations of operating systems.

[0381] The memory QQ210 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory QQ210 may allow the UE QQ200 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory QQ210, which may be or comprise a device-readable storage medium.

[0382] The processing circuitry QQ202 may be configured to communicate with an access network or other network using the communication interface QQ212. The communication interface QQ212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna QQ222. The communication interface QQ212 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 QQ218 and / or a receiver QQ220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter QQ218 and receiver QQ220 may be coupled to one or more antennas (e.g., antenna QQ222) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0383] In the illustrated embodiment, communication functions of the communication interface QQ212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0384] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface QQ212, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0385] 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.

[0386] 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 QQ200 shown in Figure 14.

[0387] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-loT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0388] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators. Figure 15 shows a network node QQ300 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., 0-Rll, 0-Dll, O-CU).

[0389] 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).

[0390] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cel l / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0391] The network node QQ300 includes a processing circuitry QQ302, a memory QQ304, a communication interface QQ306, and a power source QQ308. The network node QQ300 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 QQ300 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node QQ300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory QQ304 for different RATs) and some components may be reused (e.g., a same antenna QQ310 may be shared by different RATs). The network node QQ300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node QQ300, 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 QQ300.

[0392] The processing circuitry QQ302 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 QQ300 components, such as the memory QQ304, to provide network node QQ300 functionality. For example, the processing circuitry QQ302 may be configured to cause the network node to perform the methods as described with reference to Figure 3, 4 and / or 5.

[0393] In some embodiments, the processing circuitry QQ302 includes a system on a chip (SOC). In some embodiments, the processing circuitry QQ302 includes one or more of radio frequency (RF) transceiver circuitry QQ312 and baseband processing circuitry QQ314. In some embodiments, the radio frequency (RF) transceiver circuitry QQ312 and the baseband processing circuitry QQ314 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 QQ312 and baseband processing circuitry QQ314 may be on the same chip or set of chips, boards, or units.

[0394] The memory QQ304 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 QQ302. The memory QQ304 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 QQ302 and utilized by the network node QQ300. The memory QQ304 may be used to store any calculations made by the processing circuitry QQ302 and / or any data received via the communication interface QQ306. In some embodiments, the processing circuitry QQ302 and memory QQ304 is integrated.

[0395] The communication interface QQ306 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 QQ306 comprises port(s) / terminal(s) QQ316 to send and receive data, for example to and from a network over a wired connection. The communication interface QQ306 also includes radio front-end circuitry QQ318 that may be coupled to, or in certain embodiments a part of, the antenna QQ310. Radio front-end circuitry QQ318 comprises filters QQ320 and amplifiers QQ322. The radio front-end circuitry QQ318 may be connected to an antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry may be configured to condition signals communicated between antenna QQ310 and processing circuitry QQ302. The radio front-end circuitry QQ318 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 QQ318 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters QQ320 and / or amplifiers QQ322. The radio signal may then be transmitted via the antenna QQ310.

[0396] Similarly, when receiving data, the antenna QQ310 may collect radio signals which are then converted into digital data by the radio front-end circuitry QQ318. The digital data may be passed to the processing circuitry QQ302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0397] In certain alternative embodiments, the network node QQ300 does not include separate radio front-end circuitry QQ318, instead, the processing circuitry QQ302 includes radio frontend circuitry and is connected to the antenna QQ310. Similarly, in some embodiments, all or some of the RF transceiver circuitry QQ312 is part of the communication interface QQ306. In still other embodiments, the communication interface QQ306 includes one or more ports or terminals QQ316, the radio front-end circuitry QQ318, and the RF transceiver circuitry QQ312, as part of a radio unit (not shown), and the communication interface QQ306 communicates with the baseband processing circuitry QQ314, which is part of a digital unit (not shown).

[0398] The antenna QQ310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna QQ310 may be coupled to the radio frontend circuitry QQ318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna QQ310 is separate from the network node QQ300 and connectable to the network node QQ300 through an interface or port. The antenna QQ310, communication interface QQ306, and / or the processing circuitry QQ302 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 QQ310, the communication interface QQ306, and / or the processing circuitry QQ302 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.

[0399] The power source QQ308 provides power to the various components of network node QQ300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source QQ308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node QQ300 with power for performing the functionality described herein. For example, the network node QQ300 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 QQ308. As a further example, the power source QQ308 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.

[0400] Embodiments of the network node QQ300 may include additional components beyond those shown in Figure 15 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 QQ300 may include user interface equipment to allow input of information into the network node QQ300 and to allow output of information from the network node QQ300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node QQ300. In some embodiments providing a core network node, such as core network node 108 of FIGURE 13, some components, such as the radio front-end circuitry QQ318 and the RF transceiver circuitry QQ312 may be omitted.

[0401] Figure 16 is a block diagram illustrating a virtualization environment QQ400 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments QQ400 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 QQ400 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.

[0402] Applications QQ402 (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.

[0403] Hardware QQ404 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 QQ406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs QQ408a and QQ408b (one or more of which may be generally referred to as VMs QQ408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer QQ406 may present a virtual operating platform that appears like networking hardware to the VMs QQ408.

[0404] The VMs QQ408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer QQ406. Different embodiments of the instance of a virtual appliance QQ402 may be implemented on one or more of VMs QQ408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment. In the context of NFV, a VM QQ408 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 QQ408, and that part of hardware QQ404 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 QQ408 on top of the hardware QQ404 and corresponds to the application QQ402.

[0405] Hardware QQ404 may be implemented in a standalone network node with generic or specific components. Hardware QQ404 may implement some functions via virtualization. Alternatively, hardware QQ404 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 QQ410, which, among others, oversees lifecycle management of applications QQ402. In some embodiments, hardware QQ404 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 QQ412 which may alternatively be used for communication between hardware nodes and radio units.

[0406] 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, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non- computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0407] 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.

Claims

Claims1. A method (300) performed by a first network node for sending information, the method comprising: sending (302) information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

2. The method of claim 1 , wherein sending (302) the information to the second network node stores the information at the second network node.

3. The method of claim 2, wherein the second network node comprises a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, UCMF.

4. The method of any of claims 1 to 3, comprising sending (302) the information to the second network node in response to one or more of: configuring the UE for UE-side data collection; determining that the UE stops the UE-side data collection; receiving the information from the UE; sending, to the UE, a configuration of the functionality based on the information; determining that the UE performs a connected mode mobility or leaves an area covered by the first network node or in which the information is valid; determining that the UE transitions to idle mode or connected mode.

5. The method of any of claims 1 to 4, comprising receiving at least part of the information from the UE.

6. The method of claim 5, comprising, before receiving the at least part of the information from the UE, one or more of: determining that the UE transitions to connected mode; determining that the UE connects to the first network node or another network node; determining that the UE registers with the first network node or another network node;7. The method of claim 6, wherein the another network node comprises a Radio Access Network, RAN, node.

8. The method of any of claims 5 to 7, wherein, after receiving the at least part of the information from the UE, the UE transitions to idle mode or inactive mode.

9. The method of any of claims 1 to 8, comprising sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

10. The method of claim 9, wherein the configuration of the functionality comprises a training configuration, monitoring configuration and / or inference configuration.

11. The method of claim 9 or 10, wherein the configuration is sent in a Radio Resource Control, RRC, message or a RRC reconfiguration message.

12. The method of any of claims 1 to 11 , wherein the information from the UE is received from the UE in a Registration Area Update, RAU, or as part of a RAU procedure by the UE.

13. The method of any of claims 1 to 12, wherein the information identifying the applicability of the functionality identifies one or more of: one or more conditions under which the functionality is applicable; one or more UE-side conditions, operated by the UE or another UE, during training of the functionality; one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality; a training configuration under which the functionality was trained.

14. The method of any of claims 1 to 13, wherein the functionality that uses the AI / ML model comprises a UE positioning functionality.

15. The method of any of claims 1 to 14, wherein the first network node comprises a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

16. The method of any of claims 1 to 15, wherein the information comprises one or more of: an identifier of the UE; a classification of the UE; an identifier of the first network node; one or more nodes, cells and / or areas associated with the information;a time duration for validity of the information; an identifier of the functionality; a Public Land Mobile Network, PLMN, associated with the information.

17. A method (400) performed by a first network node for configuring a User Equipment, UE, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the method comprising: receiving (402) information from a second network node, wherein the information identifies applicability of the functionality; and sending (404), to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

18. The method of claim 17, wherein the second network node comprises a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, UCMF.

19. The method of claim 17 or 18, comprising, before receiving (402) the information from the second network node, one or more of: determining that the UE transitions to connected mode; determining that the UE connects to the first network node or another network node; determining that the UE registers with the first network node or another network node;20. The method of claim 19, wherein the another network node comprises a Radio Access Network, RAN, node.

21. The method of any of claims 17 to 20, comprising, before receiving (402) the information from the second network node, sending a request for the information to the second network node.

22. The method of any of claims 17 to 21, wherein the request is sent in response to one or more of: determining that the UE registers with the second network node; determining that the UE supports or is capable of one or more functionalities that use an AI / ML model; determining to provide configuration of the functionality to the UE.

23. The method of any of claims 17 to 22, wherein the configuration of the functionality comprises a training configuration, monitoring configuration and / or inference configuration.

24. The method of any of claims 17 to 23, wherein the configuration is sent in a Radio Resource Control, RRC, message or a RRC reconfiguration message.

25. The method of any of claims 17 to 24, wherein the information identifying the applicability of the functionality identifies one or more of: one or more conditions under which the functionality is applicable; one or more UE-side conditions, operated by the UE or another UE, during training of the functionality; one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality; a training configuration under which the functionality was trained.

26. The method of any of claims 17 to 25, wherein the functionality that uses the AI / ML model comprises a UE positioning functionality.

27. The method of any of claims 17 to 26, wherein the first network node comprises a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

28. The method of any of claims 17 to 27, wherein the information comprises one or more of: an identifier of the UE; a classification of the UE; an identifier of the first network node; one or more nodes, cells and / or areas associated with the information; a time duration for validity of the information; an identifier of the functionality; a Public Land Mobile Network, PLMN, associated with the information.

29. A method (500) performed by a second network node for receiving information from a first network node, the method comprising: receiving (502) information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

30. The method of claim 29, comprising: storing the information at the second network node.

31. The method of claim 29 or 30, wherein the second network node comprises a core network node, Access and Mobility Management Function, AMF, Network Exposure Function, NEF, or a UE capability management function, LICMF.

32. The method of any of claims 29 to 31 , wherein the information is received from the first network node in response to one or more of: configuration of the UE for UE-side data collection; the UE stopping the UE-side data collection; a configuration of the functionality in the UE based on the information; determining that the UE performs a connected mode mobility or leaves an area covered by the first network node or in which the information is valid; determining that the UE transitions to idle mode or connected mode; transition of the UE to connected mode; connection of the UE to the first network node or another network node; registering of the UE with the first network node or another network node;33. The method of claim 32, wherein the another network node comprises a Radio Access Network, RAN, node.

34. The method of any of claims 29 to 33, comprising sending, to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

35. The method of claim 34, wherein the configuration of the functionality comprises a training configuration, monitoring configuration and / or inference configuration.

36. The method of claim 34 or 35, wherein the configuration is sent in a Radio Resource Control, RRC, message or a RRC reconfiguration message.

37. The method of any of claims 29 to 36, wherein the information from the first network node is received from the UE in a Registration Area Update, RAU, or as part of a RAU procedure by the UE.

38. The method of any of claims 29 to 37, wherein the information identifying the applicability of the functionality identifies one or more of: one or more conditions under which the functionality is applicable; one or more UE-side conditions, operated by the UE or another UE, during training of the functionality; one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality; a training configuration under which the functionality was trained.

39. The method of any of claims 29 to 38, wherein the functionality that uses the AI / ML model comprises a UE positioning functionality.

40. The method of any of claims 29 to 39, wherein the first network node comprises a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

41. The method of any of claims 29 to 40, comprising receiving further information from the first network node or a further network node, wherein the further information identifies further applicability of the functionality in the UE, the information received from the first network node is associated with a first set of conditions, and the further information received from the first network node or the further network node is associated with a second set of conditions.

42. The method of claim 41 , wherein the further network node comprises a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

43. The method of any of claims 29 to 42, comprising sending the information or a subset of the information to the first network node or another network node.

44. The method of claim 43, wherein the information is sent after receiving a request for the information of the subset of the information from the first network node or the another network node.

45. The method of any of claims 29 to 44, wherein the information comprises one or more of: an identifier of the UE; a classification of the UE; an identifier of the first network node;one or more nodes, cells and / or areas associated with the information; a time duration for validity of the information; an identifier of the functionality; a Public Land Mobile Network, PLMN, associated with the information.

46. A method (600) performed by a User Equipment, UE, for sending information to a first network node, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the method comprising: sending (602) information to the first network node, wherein the information identifies applicability of the functionality; after sending the information to the first network node, transitioning (604) to idle mode or inactive mode; and after transitioning to the idle mode or the inactive mode, deleting (606) the information.

47. The method of claim 46, comprising performing one or more actions comprising one or more of: transitioning to connected mode; connecting to the first network node or another network node; registering with the first network node or the another network node.

48. The method of claim 47, comprising, after performing the one or more actions, receiving, from the first network node or the another network node, a configuration of the functionality based on the information identifying the applicability of the functionality.

49. The method of claim 48, comprising receiving, from the first network node or the another network node, the configuration of the functionality without sending, to the first network node or the another network node, the information between performing the one or more actions and receiving the configuration.

50. The method of claim 48 or 49, wherein the configuration of the functionality comprises a training configuration, monitoring configuration and / or inference configuration.

51. The method of any of claims 48 to 50, wherein the configuration is received in a Radio Resource Control, RRC, message or a RRC reconfiguration message.

52. The method of any of claims 47 to 51 , wherein the another network node comprises a Radio Access Network, RAN, node.

53. The method of any of claims 47 to 52, comprising, after sending (602) information to the first network node and before performing the one or more actions, deleting the information.

54. The method of any of claims 46 to 53, wherein sending (602) the information to the first network node is performed in a Registration Area Update, RAU, or as part of a RAU procedure.

55. The method of any of claims 46 to 54, wherein the information identifying the applicability of the functionality identifies one or more of: one or more conditions under which the functionality is applicable; one or more UE-side conditions, operated by the UE or another UE, during training of the functionality; one or more network-side conditions, operated by a network including the first network node or another network, during training of the functionality; a training configuration under which the functionality was trained.

56. The method of any of claims 46 to 55, wherein the functionality that uses the AI / ML model comprises a UE positioning functionality.

57. The method of any of claims 46 to 56, wherein the first network node comprises a base station, Radio Access Network, RAN, node, gNodeB, gNB, or location management function, LMF.

58. The method of any of claims 46 to 57, wherein the information comprises one or more of: an identifier of the UE; a classification of the UE; an identifier of the first network node; one or more nodes, cells and / or areas associated with the information; a time duration for validity of the information; an identifier of the functionality; a Public Land Mobile Network, PLMN, associated with the information.

59. A tangible, non-transient computer-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a first network node for sending information, the operations comprising: sending (302) information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

60. The computer-readable medium of claim 59, comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform the method (300) of any of claims 2 to 16.

61. A tangible, non-transient computer-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a first network node for configuring a User Equipment, UE, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the operations comprising: receiving (402) information from a second network node, wherein the information identifies applicability of the functionality; and sending (404), to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

62. The computer-readable medium of claim 61 , comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform the method (400) of any of claims 18 to 28.

63. A tangible, non-transient computer-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a second network node for receiving information from a first network node, the operations comprising: receiving (502) information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

64. The computer-readable medium of claim 63, comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform the method (500) of any of claims 30 to 45.

65. A tangible, non-transient computer-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations in a User Equipment, UE, for sending information to a first network node, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the operations comprising: sending (602) information to the first network node, wherein the information identifies applicability of the functionality; after sending the information to the first network node, transitioning (604) to idle mode or inactive mode; and after transitioning to the idle mode or the inactive mode, deleting (606) the information.

66. The computer-readable medium of claim 65, comprising instructions that, when executed by processing circuitry, cause the processing circuitry to perform the method (600) of any of claims 47 to 58.

67. A computer-readable medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to carry out the method (300, 400, 500, 600) according to any of claims 1 to 58.

68. A computer program, comprising instructions that, when executed by processing circuitry, cause the processing circuitry to carry out the method (300, 400, 500, 600) according to any of claims 1 to 58.

69. A carrier containing the computer program of claim 68, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer-readable medium.

70. Apparatus in a first network node for sending information, the apparatus comprising processing circuitry and a memory, the apparatus configured to: send (302) information to a second network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

71. The apparatus of claim 70, wherein the apparatus is configured to perform the method (300) of any of claims 2 to 16.

72. Apparatus in a first network node for configuring a User Equipment, UE, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the apparatus comprising processing circuitry and a memory, the apparatus configured to: receive (402) information from a second network node, wherein the information identifies applicability of the functionality; and send (404), to the UE, a configuration of the functionality based on the information identifying the applicability of the functionality.

73. The apparatus of claim 72, wherein the apparatus is configured to perform the method (400) of any of claims 18 to 28.

74. Apparatus in a second network node for receiving information from a first network node, the apparatus comprising processing circuitry and a memory, the apparatus configured to: receive (502) information from the first network node, wherein the information identifies applicability of functionality in a User Equipment, UE, wherein the functionality uses an artificial intelligence or machine learning, AI / ML, model.

75. The apparatus of claim 74, wherein the apparatus is configured to perform the method (500) of any of claims 30 to 45.

76. Apparatus in a User Equipment, UE, for sending information to a first network node, wherein the UE has a functionality that uses an artificial intelligence or machine learning, AI / ML, model, the apparatus comprising processing circuitry and a memory, the apparatus configured to: send (602) information to the first network node, wherein the information identifies applicability of the functionality; after sending the information to the first network node, transition (604) to idle mode or inactive mode; and after transitioning to the idle mode or the inactive mode, delete (606) the information.

77. The apparatus of claim 76, wherein the apparatus is configured to perform the method (600) of any of claims 47 to 58.

Images