UE signalling applicatiblity or inapplicability of ai / ML functionalities based on network-provided interference configuration

Abstract

In an embodiment, a method performed by a user equipment (UE) for signaling an applicability of Artificial Intelligence Machine Learning (AI / ML) functionalities comprises receiving, from a network node, a plurality of inference related configurations associated with at least one supported functionality; determining an applicability status for each inference related configuration of the plurality of inference related configurations, wherein the applicability status indicates whether the inference related configuration is applicable or non-applicable. The method also comprises transmitting a first indication comprising one or more of an applicability indication indicating that an AI / ML model functionality is determined to be applicable and an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable according to one or more inference related configurations.

Description

UE SIGNALLING APPLICATIBLITY OR INAPPLICABILITY OF AI / ML FUNCTIONALITIES BASEDON NETWORK-PROVIDED INTERFERENCE CONFIGURATIONRELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 667,868, filed July 5, 2024, the disclosure of which is hereby incorporated herein by reference in its entiretyTECHNICAL FIELD

[0002] The present disclosure relates to methods for a User Equipment (UE) to signal the applicability or inapplicability of Artificial Intelligence / Machine Learning (AI / ML) functionalities based on network provided measurement and interference configuration. A user equipment and network node to perform these methods are also disclosed.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-mterface 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 preceding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

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

[0005] Building the Al model, or any machine learning model, includes several development steps where the actual training of the Al model is just one step in a training pipeline. An important part in Al developing is the ML model lifecycle management (LCM). This is illustrated in Figure 1, which is an illustration of training and inference pipelines, and their interactions within a model lifecycle management procedure. The model lifecycle management typically consists of:• A training (re-training) pipeline. a. Data Ingestion: Data ingestion refers to gathering raw (training) data from a data storage. After data ingestion, there may also be a step that controls the validity of the gathered data. b. Data Pre-Processing: Data pre-processing refers to some feature engineering applied to the gathered data, e.g., it may include data normalization and possibly a data transformation required for the input data to the Al model. c. Model Training: Model training refers to the actual model training steps as previously outlined. d. Model Evaluation: Model evaluation refers to benchmarking the performance to some model baseline. The iterative steps of model training and model evaluation continue until the acceptable level of performance (as previously exemplified) is achieved. e. Model Registration: Model registration refers to registering the Al model, including any corresponding Al-metadata that provides information on how the Al model was developed, and possibly Al model evaluations performance outcomes.• A deployment stage to make the trained (or re-trained) Al model part of the inference pipeline.• An inference pipeline. a. Data Ingestion: Data ingestion refers to gathering raw (inference) data from a data storage. b. Data Pre-Processing: Data pre-processing stage is typically identical to corresponding processing that occurs in the training pipeline.c. Model Operational: Model operational refers to using the trained and deployed model in an operational mode. d. Data and Model Monitoring: Data & model monitoring refers to validating that the inference data are from a distribution that aligns well with the training data, as well as monitoring model outputs for detecting any performance, or operational, drifts.• A drift detection stage that informs about any drifts in the model operations.

[0006] As an example, Figure 1 illustrates training and inference pipelines and their interactions within a model lifecycle management procedure according to one or more embodiments of the present disclosure. Similarly, Figure 2 illustrates a functional framework that can be used for studying different Network (NW)-UE collaboration levels for the Al for PHY use cases according to one or more embodiments of the present disclosure.

[0007] Among the AI / ML models being discussed in the Rel-18 study item on AI / ML for the NR air interface is the so-called One-sided AI / ML model, which can be a UE-sided AI / ML model whose inference is performed entirely at the UE (which is the focus of the disclosure), or a NW-sided AI / ML model whose inference is performed entirely at the NW.

[0008] The use case of beam prediction which will be standardized as part of 3GPP Rel. 19 work item consists of spatial beam prediction, and temporal beam prediction. 3GPP aims to specify predictions of the “best” beam (or beams) from a Set A of beams using measurement results from another Set B of beams.

[0009] 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.

[0010] Figure 3 illustrates Set A and Set B beams according to one or more embodiments of the present disclosure.

[0011] Set A and Set B of beams have not been specified yet, however, the following two examples may be considered as references:• Set B is a subset of a Set A. For example, Set A is a set of 8 Synchronization Signal Block (SSB) / CSI Reference Signal (RS) beams shown in Figure 3 (both light and dark circles). The UE measures Set B (the 4 beams indicated by dark circles). The AI / ML model should predict the best beam (or beams) in Set A using only measurements from Set B.

[0012] Figure 3 is an example where Set B is a subset of Set A. The figure illustrates a gnd- of-beam type radiation pattern: Each row (resp. column) depicts a certain zenith (resp. azimuth)angle from the antenna array. Set A has 8 beams and Set B has 4 beams (indicated by dark circles).

[0013] Figure 4 illustrates another example of Set A and Set B beams according to one or more embodiments of the present disclosure. Set A and Set B correspond to two different sets of beams. For example, Set A is a set of 30 narrow CSI-RS beams, and Set B is a set of 8 wide SSB beams. The UE measures beams in Set B and the AI / ML model should predict the best beam(s) from Set A.

[0014] The beam prediction can be performed (e.g., by an AI / ML model) in the gNB (e g , the radio access network node) and / or in the UE, and the gain is twofold. From the UE point of view, the UE would be able to generate good radio measurement estimations without really measuring certain resources (e.g. actual SSBs, CSI-RS or other RS(s)), thereby saving energy, whereas from the gNB point of view, the gNB can get good radio measurements estimation from the UE without providing the measuring resources, thereby limiting the overhead over the airinterface.

[0015] Whether the UE can perform the beam prediction on a certain set of resources with a certain accuracy, depends on so called applicability conditions of an AI / ML model / function. In particular, an AI / ML model / function may be trained to perform the beam prediction under certain applicability conditions e.g. speed, location, beam configuration(s), deployment, etc.Such applicability conditions need to be fulfilled in order for the AI / ML model / function to generate the expected output, i.e. beam prediction for this use case, with enough accuracy. The applicability conditions may include a set of parameters / variables under which the AI / ML model / function was trained e.g. a given Set B for the inference of a Set A. Such set may include for example UE-specific conditions under which the model was trained, as the UE speed, the UE antenna shape, UE sensors information such as UE orientation, motion sensors etc.; whereas some other parameters / variables may depend on the specific network configuration under which the model was trained, e.g. the deployment scenario (e g. indoor / outdoor), the carrier frequency, the gNB TX port number, the gNB Transmit (TX) power, etc.

[0016] In order to determine whether an AI / ML model / function is applicable or not, the UE needs to assess the applicability conditions of such AI / ML model / function with respect to the output (beam prediction) that needs the generated and received input (e.g. radio measurement resources configured by the gNB).

[0017] Related to the discussion above, the applicability reporting has been discussed during the Rel.18 study item. The applicability reporting allows 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 / MLmodel / 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. For example, whether the UE has an AI / ML model that is applicable given the current location of the UE, or given the current speed of the UE, is not something that the network can control or it can know, 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 Over the Top (OTT) server or Core Network (CN) function controlled by the UE- vendor or by the Mobile Network Operator (MNO).

[0018] Two types of applicability reporting were identified during the Rel.18 study item, i.e. the proactive reporting and the reactive reporting. The reactive reporting implies the gNB inquiring the UE about the applicability of AI / ML model / functionality, and the UE responding with the AI / L models / functionalities that are applicable, whereas with the proactive reporting UE signals to the network autonomously, i.e. without any inquiry, about the AI / ML model / functionalities that are applicable.

[0019] The former, i.e. reactive reporting can be used for example in response to a network configuration, e.g. inference related configuration, including for example beam resource configuration of Set A and / or Set B. The UE will then respond indicating if the AI / ML model / functionality is applicable based on this inference configuration.

[0020] The latter, i.e. the proactive reporting can be configured to the UE to allow the UE to report at any point in time a change in the applicability of an AI / ML model / functionality, i.e. an AI / ML model / functionality that was not applicable becomes applicable or vice versa

[0021] From signaling procedure point of view, a summary is provided in Figure 5 which illustrates a flowchart of a method for reactive reporting according to one or more embodiments of the present disclosure.

[0022] Step 1 : Network sends UECapabilityEnquiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities.

[0023] Step 2: UE sends UECapablitylnformation message to network, containing supported functionalities at the UE side.

[0024] Step 3: Network provides network configurations and initiates UE to report its applicable functionalities.

[0025] Step 4: UE sends applicable functionalities to network.

[0026] Step 5: Network sends updated inference configuration for applicable functionalities reported in Step 4 to the UE. (see Q2-6)

[0027] Step 6: Start inference / monitoring based on network / UE activation / deactivation.

[0028] As shown in step 6, a “supported functionality” (e.g., beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) is activated, to refer to functionalities which are activated and for which a UE is performing inference [1], in response to a network configuration in Step 3

[0029] Figure 6 illustrates a flowchart of a method for proactive reporting according to one or more embodiments of the present disclosure.

[0030] Step 1 : Network sends UECapabilityEnqiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities

[0031] Step 2: UE sends UECapablitylnformation message to network, containing supported functionalities at the UE side

[0032] Step 3: Network configures UE that it is allowed to provide its applicable functionalities

[0033] Step 4: UE sends applicable functionalities to network upon change of applicable functi onality / condition

[0034] Step 5: Network sends inference configuration for the applicable functionalities to the UE

[0035] Step 6: Start mference / monitoring based on network / UE activation / deactivation.SUMMARY

[0036] Various embodiments described herein provide for a method for signaling an applicability of AI / ML functionalities to a network node. The method includes receiving a plurality of inference related configurations associated with at least one supported functionality, then determining an applicability status for each of the inference related configurations. Then the UE can transmit an indication of the applicability indication, indicating whether the AI / ML model functionality is applicable or inapplicable, to the network. The method further includes storing one or more inference related configurations.

[0037] In an embodiment, a method performed by a user equipment (UE) for signaling an applicability of Artificial Intelligence Machine Learning (AI / ML) functionalities comprises receiving, from a network node, a plurality of inference related configurations associated with at least one supported functionality; determining an applicability status for each inference related configuration of the plurality of inference related configurations, wherein the applicability status indicates whether the inference related configuration is applicable or non-applicable. The method also comprises transmitting a first indication comprising one or more of an applicability indication indicating that an AI / ML model functionality is determined to be applicable and aninapplicability indication indicating that the AI / ML model functionality is not determined to be applicable according to one or more inference related configurations.

[0038] In an embodiment, in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be applicable, the method further comprises performing one or more of activating the supported functionality for the at least one of the plurality of inference related configurations, applying the at least one of the plurality of inference related configurations, monitoring whether at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO becomes non-applicable at time Tl, and monitoring whether the at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO but not applied or selected for the AI / ML inference of the concerned AI / ML model functionality at time TO, it is selected to be applied for the AI / ML inference of the concerned AI / ML model functionality at time Tl .

[0039] In an embodiment, in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be non-applicable, the method further comprises deactivating the supported functionality or inference(s)) for the at least one of the plurality of inference related configurations, monitoring whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl, and monitoring whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl, and whether such of the east one of the one or more stored inference related configurations are to be applied at time Tl for the AI / ML inference of the concerned AI / ML functionality.

[0040] In an embodiment, the one or more inference related configurations for which a supported functionality is considered applicable are determined by the UE on the basis of the training performed for the said AI / ML model functionality or based on a provided UE capabilities for different use cases of AI / ML.

[0041] In an embodiment, the one or more inference related configurations are determined by the UE on the basis of the historical model inference performed for the said AI / ML model functionality.

[0042] In an embodiment, the one or more inference related configurations determined by the UE are transmitted as part of the first indication.

[0043] In an embodiment, he applicability indication is transmitted to the network node (810) in response to one or more of receiving the one or more inference related configurationsassociated to the AI / ML model functionality, determining that the AI / ML model functionality is applicable according to at least one of the one or more inference related configurations for which it was determined that the AI / ML model / functionality was not applicable at a previous point in time, and determining that the AI / ML model / functionality is applicable according to at least one of the one or more AI / ML inference related configurations for which the applicability indication was not transmitted at a previous point in time.

[0044] In an embodiment, the inapplicability indication is transmitted implicitly as part of the applicability indication.

[0045] In an embodiment, the one or more inference related configurations are stored by the UE.

[0046] In an embodiment, the one or more stored inference related configurations may be associated with the stored corresponding configuration(s) for a supported functionality and / or stored corresponding (in)applicability information and / or stored inference performance.

[0047] In an embodiment, the stored inference related configurations are considered in order to determine the applicability or inapplicability of the AI / ML model / functionality.

[0048] In an embodiment, in response to transmitting the inapplicability indication for an AI / ML model / functionality the method further comprises deactivating the concerned AI / ML model / functionality, wherein the UE considers itself to not be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be not applicable, i.e. the UE does not apply any longer the one or more inference related configurations.

[0049] In an embodiment, in response to transmitting the applicability indication for an AI / ML model / functionality, the method further comprises activating the concerned AI / ML model / functionality, wherein the UE considers itself to be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be applicable, i.e. it applies the one or more inference related configurations.

[0050] In an embodiment, the inference related configuration comprises one or more of a set A and / or set B of radio resources; network-side operation properties; and UE-side operation properties.

[0051] In an embodiment, the set A and / or set B of radio resources comprise one or more of a set of Synchronization Signal Block (SSB) for a cell; a set of Channel State Information Reference Signal (CSLRS) resources for a cell; a set of Synchronization Signal (SS) Physical Broadcast Channel (PBCH) block resource sets for a cell; a set of cells; a set of frequencies; a setof SSB for a list of cells; a set of CSI-RS resources for a list of cells; and a set of SS / PBCH block resource sets for the list of cells.

[0052] In an embodiment, the network-side / UE-side operational properties comprises one or more of: a mapping relationship of Set A and Set B, including a set of identifiers, IDs; an indication of consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B; a quasi-co-location, QCL, assumption; an order of model input and model output; transmission power; a UE distribution; antenna height; a deployment scenario information; and a UE speed.

[0053] In an embodiment, the inference related configurations comprise a list of identifiers, IDs, each referring to a specific configuration.

[0054] In an embodiment, the inference related configurations are candidate configuration for the AI / ML inference, wherein the applicability and inapplicability indications for different AI / ML models / functionalities are sent in different messages or in a single message.

[0055] In an embodiment, the inference related configurations are candidate configuration for the AI / ML inference.

[0056] In an embodiment, the method further comprises storing the one or more inference related configurations.

[0057] In an embodiment, user equipment for signaling an applicability of AI / ML functionalities is provided that includes processing circuitry configured to perform any of the above embodiments.

[0058] In an embodiment, a method performed by a network node for facilitating signaling of AI / ML functionalities is provided. The method includes transmitting a plurality of inference related configuration associated to at least one supported functionality, for which a UE has reported that it is capable of supporting; receiving a first indication comprising one or more of: an applicability indication indicating that the AI / ML model functionality is determined to be applicable by the UE; an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable by the UE according to one or more inference related configurations.

[0059] In an embodiment, a network node is provided that is configured to facilitating signaling an applicability of AI / ML functionalities and includes processing circuitry that is configured to perform any of the preceding embodiments.BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawing figures incorporated in and forming a part of this specification illustrate several aspects of the disclosure, and together with the description serve to explain the principles of the disclosure.

[0061] Figure 1 illustrates training and inference pipelines and their interactions within a model lifecycle management procedure according to one or more embodiments of the present disclosure;

[0062] Figure 2 illustrates a functional framework that can be used for studying different Network / User Equipment collaboration levels for Artificial Intelligence (Al) for Physical Layer (PHY) use cases according to one or more embodiments of the present disclosure;

[0063] Figure 3 illustrates Set A and Set B beams according to one or more embodiments of the present disclosure;

[0064] Figure 4 illustrates another example of Set A and Set B beams according to one or more embodiments of the present disclosure;

[0065] Figure 5 illustrates a flowchart of a method for reactive reporting according to one or more embodiments of the present disclosure;

[0066] Figure 6 illustrates a flowchart of a method for proactive reporting according to one or more embodiments of the present disclosure;

[0067] Figure 7 illustrates a flowchart of a method for signaling an applicability of Artificial Intelligence Machine Learning, AI / L. functionalities according to one or more embodiments of the present disclosure;

[0068] Figure 8 shows an example of a communication system in accordance with some embodiments of the present disclosure;

[0069] Figure 9 shows a User Equipment device (UE) in accordance with some embodiments of the present disclosure;

[0070] Figure 10 shows a network node in accordance with some embodiments of the present disclosure; and

[0071] Figure 11 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized in accordance with some embodiments of the present disclosure.DETAILED DESCRIPTION

[0072] The embodiments set forth below represent information to enable those skilled in the art to practice the embodiments and illustrate the best mode of practicing the embodiments.Upon reading the following description in light of the accompanying drawing figures, those skilled in the art will understand the concepts of the disclosure and will recognize applications of these concepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure.

[0073] 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.

[0074] There currently exist certain challenge(s). After the inference configuration and the applicable functionality reporting, it is not clear what is the initial state (active / deactive) of the functionality after Step 5 (in the previous figure), and how an applicable functionality becomes an activated functionality. Radio Access Network Working Group 2 (RAN2) is discussing the following three options.

[0075] Option 1 : The applicable functionality is activated by receiving configuration for applicable functionalities in Step 5 (if needed). If configuration is not provided by the network, it means the functionality is not activated.

[0076] Option 2: The applicable functionality is automatically activated if it is included in applicable functionality reporting (assuming the network configuration received in Step 3 is directly applied and the functionality is activated).

[0077] Option 3: A functionality is activated based on a field in Radio Resource Configuration (RRC) RRCReconfiguration in Step 3 or Step 5 (indicating the functionality activation status), and additionally via Layer 1 / Layer 2 (L1 / L2) based activation / deactivation signaling. L1 / L2 based activation / deactivation signaling is up to RAN Working Group 1 (RANI).

[0078] The problem of option 1 as it is described at the moment is that it requires two RRC Reconfiguration procedures plus an explicit activation command (e.g. possibly via a lower layer signaling) for a supported functionality (e.g. beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s))). In other words, a supported functionality for Artificial Intelligence / Machine Learning (AI / ML) could not be configured as other typical radio features, i.e. in a single RRC Reconfiguration loop.

[0079] In option 2 the supported functionality may be activated in a single RRC Reconfiguration procedure (step 3), even without the need to an explicit activation command for the supported functionality (e.g. beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s))). However, this only works when the network correctly guesses the exact “inference related configuration” required to make the AI / ML functionality upand running (e.g., including set A / B configuration) to be applicable, so that the User Equipment (UE) would consider it applicable and autonomously activate it.

[0080] In option 3, as in option 2, the supported functionality may be activated in a single RRC Reconfiguration procedure (step 3), even without the need to an explicit activation command for the supported functionality (e.g. beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s))), depending on a field in the RRC Reconfiguration. However, as in option 2, this only works when the network correctly guesses the exact “inference related configuration” required to make the AI / ML supported functionality up and running (e.g. including set A / B configuration) to be applicable, so that the UE would consider it applicable and autonomously activate it.

[0081] An additional problem is that the inference configuration may comprise multiple AI / ML radio measurement configurations, e.g. candidate AI / ML radio measurement configurations, that the gNB can configure to the UE for the AI / ML inference of a certain AI / ML model / functionality. Hence, whether an AI / ML model / functionality is applicable or not depends on such candidate AI / ML radio measurement configurations included in the inference configuration. More specifically, an AI / ML model / functionality may be applicable according to certain candidate AI / ML radio measurement configurations and inapplicable according to others. Therefore, an AI / ML model / functionality can be activated only if there is at least a suitable AI / ML radio configuration that can be applied such that it can make the AI / ML model / functionality applicable. Additionally, the suitable AI / ML radio configuration can change over time, depending on UE conditions (e g. speed, location, battery status, antenna layouts, UE sensors' inputs), and it is not clear which are the methods that the UE can adopt to report to the network such change in the suitability of the AI / ML radio configurations so that the AI / ML model / functionality can still be applicable

[0082] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges.

[0083] Various embodiments described herein provide for a method for signaling an applicability of AI / ML functionalities to a network node. The method includes receiving a plurality of inference related configurations associated with at least one supported functionality, then determining an applicability status for each of the inference related configurations. Then the UE can transmit an indication of the applicability indication, indicating whether the AI / ML model functionality is applicable or inapplicable, to the network. The method further includes storing one or more inference related configurations.

[0084] The present disclosure provides for a method in which a i) UE receives multiple inference AI / ML related configurations, e.g., config(l), config(2), .. . , config(N) associated to a supported functionality for AI / ML, such as beam management, mobility management or reporting of spatial domain and / or time domain prediction(s) of beam- cell- frequency- levels, or inference(s), wherein an AI / ML model / functionality is supported if indicated as a UE capability. The UE may receive the multiple inference related configurations in an RRC Reconfiguration message. The UE may store in a local variable all the received AI / ML related configurations.

[0085] Then, ii) the UE determines an applicability status (‘applicable’ or ‘non- applicable’) for each of the multiple inference related configurations, e.g. config(l) -> non- applicable, config(2) -> applicable, ... , config(N)-> non-applicable.

[0086] Then, iii) the UE transmits a first applicability indication based on the applicability status (‘applicable’ or ‘non-applicable’) for each of the multiple inference related configurations e.g. config(l) -> non-applicable, config(2) -> applicable, ... , config(N)-> non- applicable, or config(l) -> non-applicable, config(N)-> non-applicable (in case only non- applicable are explicitly indicated). One of “non-applicable” or “applicable” status may be transmitted implicitly in the first applicability indication.

[0087] Then, iv) when at least one of the multiple inference related configurations (e.g., config(2)) has an applicability status determined to be ‘applicable’, the UE performs one or more of the following operations:

[0088] a) the UE activates the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) for the at least one of the multiple inference related configurations and operates according to the at least one of the multiple inference related configurations

[0089] In one option, activating the supported functionality comprises the UE applying the at least one of the multiple inference related configurations (e.g. config(2)) for which the applicability status is determined to be ‘applicable’, and by the UE storing or keeping stored (if already stored) both the applied configuration and the other inference related configurations e g. UE applies config(2) and stores config(l), ... , config(N);

[0090] In one option, the UE includes in the first applicability indication an indication of the at least one of the multiple inference related configurations (e.g., an identifier associated to config(2)) which the UE has activated;

[0091] In one option, the UE activates the at least one the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) for the at least one of the multiple inference related configurations and operatesaccording to the at least one of the multiple inference related configurations upon reception of a command from the network, such as a Medium Access Control (MAC) Control Element (MAC CE), and / or a Downlink Control indication (DCI) and / or an RRC message, including an indication of at least one of the multiple inference related configuration(s) which the UE needs to activate. In one sub-option, the UE receives the command in response to the transmitted first applicability indication.

[0092] In one option, the UE activates the at least one the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) for the at least one of the multiple inference related configurations and operates according to the at least one of the multiple inference related configurations when the inference related configuration is associated to a configured indication (e g. a flag set to ‘true’) that the UE may activate the inference related configuration in case that is applicable (i.e. when that makes the supported functionality applicable).

[0093] In one option, when more than one of the multiple inference related configurations (e.g., config(2)) have an applicability status determined to be ‘applicable’ (e g., config(2) -> applicable, config(3)- applicable) the UE selects one of them to activate and perform the steps in the options above. For example, the UE selects one inference related configuration (e.g., config(2)) and activates the supported functionality for the selected inference related configuration and / or the UE includes in the first applicability indication an indication of the selected inference related configurations (e g., an identifier associated to config(2)) which the UE has activated. In an alternative option, the UE does not select which of the configurations that are determined to be applicable, rather it is the gNB on the basis of the applicability indication and the configurations therein indicated as “applicable”, that selects the configuration that the UE should apply. In this case the configuration that the UE should apply is included in a successive RRC reconfiguration message.

[0094] b) the UE monitors the stored AI / ML related configurations and determines whether the at least one inference related configuration determined to have the applicability status as ‘applicable’ (e.g., config(2)) becomes non-appli cable. When that occurs, the UE deactivates the at least one inference related configuration and transmits an indication to the network of the change (update) of the applicability status of that inference related configuration.

[0095] c) the UE monitors the stored AI / ML related configurations and determines whether the at least one inference related configuration determined to have the applicability status as ‘applicable’ (e.g. config(2)) at time TO but not selected / applied for the AI / ML inference, e.g. at time TO the UE selected / applied for the AI / ML inference config (3), it is selected / applied at timeT1 for the AI / ML inference. When that occurs, the UE deactivates the at least one inference related configuration that was selected / applied at time TO (config(3)) and transmits an indication to the network of the change (update) of the applicability status of that inference related configuration, i.e. that the UE has selected / applied config(2) and deactivated / not applied config(3).

[0096] Then, v) when the multiple inference related configurations (e.g., config(2)) has an applicability status determined to be ‘non-applicable’, the UE performs one or more of the following operations:

[0097] a) the UE deactivates (if previously activated) or keeps deactivated (if previously already deactive) the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) for the at least one of the multiple inference related configurations.

[0098] In one option, the UE includes in the first applicability indication an indication that the multiple inference related configurations are deactivated.

[0099] In one option, the UE deactivates the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) upon reception of a deactivation command from the network, such as a MAC CE, and / or a DCI and / or an RRC message, including an indication of deactivation of the multiple inference related configuration(s). In one sub-option, the UE receives the command in response to the transmitted first applicability indication.

[0100] In one option, the UE deactivates the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) when the inference related configuration(s) are associated to a configured indication (e.g. a flag set to ‘false’) that the UE needs to deactivate the supported functionality in case in which all are non-applicable (i.e. when that makes the supported functionality non-applicable).

[0101] b) the UE stores or keeps stored (if not already stored) the multiple inference related configurations which are non-applicable (and consisted them as not applied configuration(s)) and also the ones that are applicable.

[0102] c) the UE monitors the stored inference related configuration, and determines whether at least one of the multiple inference related configuration determined to have the applicability status as ‘non-applicable’ becomes applicable. When that occurs, the UE performs one or more of the steps above in step iv) e.g.:

[0103] The UE activates the supported functionality (such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s)) for the at least oneof the multiple inference related configurations and operates according to the at least one of the multiple inference related configurations.

[0104] The UE monitors whether the at least one inference related configuration determined to have the applicability status as ‘applicable’ (e g. config(2)) becomes non-applicable. When that occurs, the UE deactivates the at least one inference related configuration and transmits an indication to the network of the change (update) of the applicability status of that inference related configuration.

[0105] Certain embodiments may provide one or more of the following technical advantage(s). The proposed solutions use one designed mechanism, to support (inapplicability indication from one UE to one gNB for measurement and inference configuration from the gNB regarding AI / ML model / functionality(ies) available at the UE, and meanwhile to support the AI / ML model / functionality activation / deactivation at the UE side, and moreover to support measurement and inference configuration recommendation from the UE to the gNB.

[0106] Figure 7 illustrates a flowchart of a method for signaling an applicability of Artificial Intelligence Machine Learning, AI / L. functionalities according to one or more embodiments of the present disclosure.

[0107] The present disclosure discloses a method in which a i) UE 812 receives in step 702 from the network node 810 multiple inference related configurations, e.g., config(l), config(2), ... , config(N) associated to a supported functionality for AI / ML, such as beam management, or reporting of spatial domain and / or time domain prediction(s) or inference(s). The UE may receive the multiple inference related configurations in a single RRC Reconfiguration message, e.g. while the UE is in connected state (RRC CONNECTED).

[0108] The inference related configuration can be for example a CSI measurement configuration including set A / set B:• SSB identifiers associated to a serving cell and / or a neighbour cell;• CSLRS resource identifiers associated to a serving cell and / or a neighbour cell;• beam identifiers associated to a serving cell and / or a neighbour cell;• Mobility Reference Signal(s) identifiers associated to a serving cell and / or a neighbour cell;• Candidate configuration(s) Set A / B (1); Set A / B (2); Set A / B (3)

[0109] In another non-limiting option, the one or more inference related configurations (e.g., denoted Set B) comprise a mobility prediction configuration or Radio resource management (RRM) measurement configuration associated to a mobility procedure to run the inference and report the predictions. That may include one or more of:• Measurement configurations (e.g., measConfig) including one or more of a. a list of one or more measurement objects to add / modify / remove by the UE which may further includes i. Synchronization Signal Block (SSB) frequency ii. Channel State Information (CSI) Reference Signal (CSI-RS) frequency iii. SSB subcarrier spacing iv. measurement timing configuration v. SSB and or CSI-RS beam consolidation configuration / threshold vi. Number of SSB or CSI-RS measurements to average b. a list of one or more report configuration to add / modify / remove by the UE c. SpCell Reference Signal Received Power (RSRP) measurement controlling when the UE is required to perform measurements on non-serving cells d. Measurement gap configuration e.g., a measurement gap identifier (ID), identifying the measurement gap ID per FR. e. Measurement quantity configuration

[0110] According to the methods disclosed herein a UE is capable of performing inference related to a “supported functionality”, which refers to functionalities that UE can indicate by using UE capability signaling. A supported functionality is one or more functionalities for beam management or mobility operations, such as the reporting of time domain and / or spatial domain or frequency domain predictions (inference).

[0111] 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 LI RSRP values of one or more beams or one or more SSB indexes of a cell or predicted LI or L3 RSRP values of one or more cells) based on a set B of beams (e.g. 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.

[0112] 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 qualify of a set A of beams or cells (e.g. predicted LI RSRP values of one or more beams or one or more SSB indexes of acell or predicted LI or L3 RSRP values of one or more cells) based on a set B of beams (e.g. 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.

[0113] 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 a set B of beams or cells (e.g. 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.

[0114] According to the methods disclosed herein, a UE determines at step 704 whether a functionality (a supported functionality) is an "applicable functionality “ i.e. whether that is a functionality the UE is ready to apply for model inference. Or, in other words, when the UE is provided with “at least one inference related configuration” from the gNB for performing inference(s) using an AI / ML model (e.g. perform predicted LI RSRP for beams and / or SSB indexes and / o CSI-RS resource indicator(s) and / or LI RSRP measurements for beams and / or SSB indexes and / o CSI-RS resource indicator(s) to be used as input to an AI / ML model) and report inference information derived from the inference(s)), whether the UE can perform inference(s) using an AI / ML model and report inference information derived from the inference(s)) according to the at least one inference related configuration. In this context, the at least one inference related configuration may include one or more parameters for CSI resources (e.g., a CSI resource configuration) to be measured and / or predicted and / or one or more parameters for reporting (e.g., in a CSI reporting configuration); thus, it may be said that an inference related configuration includes a measurement configuration.

[0115] According to the method, the UE may use one or more “applicability condition(s)” which represent a set of conditions for determining whether an AI / ML model / functionality (also denoted a “supported functionality”) is applicable or not. An AI / ML model / functionality is applicable when there is at least one ’’inference related configuration” received by the UE (provided by the gNB) out of multiple inference related configurations received (e.g., in a single RRC Reconfiguration message) for which the AI / ML model / functionality (the supported functionality) is applicable.

[0116] An AI / ML model / functionality is not applicable when there is no “inference related configuration” received by the UE (provided by the gNB) for which the AI / ML model / functionality (the supported functionality) is applicable. As stated earlier an “inference related configuration” may include one or more parameters for CSI resources (e.g., a CSI resource configuration) to be measured and / or predicted and / or one or more parameters for reporting (e.g., in a CSI reporting configuration); thus, it could be said that the “inference related configuration” includes at least one radio measurement configuration and inference configuration.

[0117] The present disclosure comprises methods for a gNB to configure the UE with multiple inference related configurations in which the gNB configures the UE to perform AI / ML inference according to an AI / ML model / functionality.

[0118] An inference related configuration may be, for example, a first set (set A) of measurement resources (e g. beams, SSB indexes and / or CSI-RS resource identifiers, Mobility Refence Signal identifiers) in which the UE performs radio measurement predictions (inferences, such as predicted RSRP values), and a second set (set B) of radio measurement resources (e g. beams, SSB indexes and / or CSI-RS resource identifiers, Mobility Refence Signal identifiers) in which the UE can perform radio measurement in order to determine the radio measurement predictions on the first set. That may also include one or more configuration(s) associated to NW-side additional conditions reflecting the NW operational properties, such as:• Mapping relationship of Set A and Set B, including ordering to (a set of IDs, or resources);• Consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B;• Quasi Co-location (QCL) assumption;• The order of model input and model output;• between Reference Signals (RS) and Transmit (Tx) beams can be pre-defmed;• Transmission power;• UE distribution;• antenna height;• Deployment scenarios (e.g., Intersite Distance (ISD), Umi / Uma / rural / indoor / indoor office / indoor factory, specific area(s)); and• UE speed.

[0119] One inference related configuration may include a list of IDs referring to the set A and set B (or to the resources within the set A / B), and referring to one or more NW-side additional conditions.

[0120] Each of the multiple inference related configurations the UE receives can be considered by the UE in order to evaluate the (in)applicability of the AI / ML model / functionality and determine the applicability status (i.e. for the UE to determine whether a supported functionality is applicable or non-applicable). The multiple inference related configurations can be associated to one specific AI / ML model / functionality for which the UE is to determine the (in)applicability, i.e. the applicability status. In one option the UE receives from the gNB, for a given AI / ML model / functionality (i.e., for a supported functionality), a set of multiple inference related configurations. For example, the UE may receive a first set of multiple inference related configurations for a beam management function, such as the reporting of time-domain RSRP predictions for a set of beams / SSGB indexes, or CSI-RS resources; and / or a second set of multiple inference related configurations for a beam management function, such as the reporting of spatial-domain RSRP predictions for a set of beams / SSGB indexes, or CSI-RS resources; and / or a third set of multiple inference related configurations for a Mobility function, such as the reporting of time-domain RSRP predictions for neighbor cells.

[0121] The received multiple inference related configurations are stored in step 708 by the UE in a local variable and / or in the UE memory. The stored inference related configurations may be both the inference related configurations that at a given point are considered to make the AI / ML model / functionality applicable and the inference related configurations that at a given point are considered to make the AI / L model / functionality not applicable. The stored inference related configurations may be associated with the stored corresponding functionality configuration(s) and / or stored corresponding (in)applicability information.

[0122] Upon receiving the “at least one inference related configuration”, the UE may determine the applicability status (i.e., the applicability / inapplicability) of the concerned AI / ML model / functionality the UE is configured with, taking into account the multiple inference related configuration(s) the UE has received for the concerned AI / ML model / functionality.

[0123] The results of the above determination may be transmitted by the UE at step 706 in an applicability indication, e.g. indicating applicability and / or inapplicability, possibly per inference related configuration. In one example, the UE may include in the said indication an indication of which inference related configuration(s) of the multiple inference related configurations the UE has received make(s) the AI / ML model / functionality (supported functionality) applicable; in one example the UE indicate(s) an identifier (config ID) referring tothe concerned inference related configuration(s). In one method, in case there are multiple inference related configurations that make the AI / ML model / functionality applicable, the UE may select just one of them, and then indicate just that in the said applicability indication. In this case the UE applies, i.e. it considers itself to be configured, such selected configuration for the AI / ML inference of the concerned AI / ML model / functionality.

[0124] Hence, the multiple inference related configurations may be considered as “candidate configurations” or candidate inference related configuration(s) that the UE can select on the basis of the UE applicability conditions, i.e the UE selects the one or more inference related candidate configuration(s) that make the AI / ML model applicable (i.e. that makes the supported functionality applicable). Then UE does not select the other inference related candidate configurations the UE has received, i.e. it does not apply the AI / ML related configurations that are not considered to make the AI / ML model / functionality applicable.

[0125] In one option, the inference related configurations not included in the applicability indication from the UE to the network, are considered to be inference related configurations for which the concerned AI / ML model / functionality is not applicable. In such case, the inapplicability indication is sent implicitly, i.e. by the absence of an applicability indication indicating the status as ‘applicable’. In another example, the UE transmits an explicit inapplicability indication, indicating the inference related configurations for which the AI / ML model / functionality is not applicable.

[0126] In one example, if all the provided inference related configurations make the concerned AI / ML model / functionality applicable, the UE just indicates (e.g., through a flag) that all the inference related configurations are applicable for the concerned AI / ML model / functionality.

[0127] In another example, if none of the inference related configurations make the concerned AI / ML model / functionality applicable, the UE transmits just an inapplicability indication, e.g. through another flag. In another option the absence of an indication indicates to the network that the AI / ML functionality is not applicable for none of the configuration(s).

[0128] The UE transmits the first applicability indication (indicating an applicability status as ‘applicable’) (e.g., to the gNB) in response to one or more of:• Receiving the said multiple inference related configurations associated to the said AI / ML model / functionality (supported functionality) a. In this method, the applicability indication can be transmitted as part of an RRCReconfigurationComplete message in response of an RRCReconfiguration including the AI / ML related inference configurations.• Determining that the AI / ML model / functionality (supported functionality) is applicable according to at least one of the multiple inference related configurations for which the AI / ML model / functionality was determined to be inapplicable at a previous point in time. a. According to this method, for example at time TO the UE may have sent an inapplicability indication (implicit or explicit) for the entire AI / ML model / functionality or for one or more of the inference related configurations of such AI / ML model / functionality, e.g. config(2). Then at time Tl, the UE may determine that the AI / ML model / functionality is applicable, or at least one of the inference related configurations for which the inapplicability was previously sent at time TO is now applicable, i.e. config(2) is now applicable at time TL This may depend for example, on the UE changing its operating conditions (e.g. speed, antenna layout, orientation, battery status, etc.), or on radio factors (e.g. radio channel measurements, new configuration provided to the UE).• Determining that the AI / ML model / functionality is applicable according to at least one of the one or more AI / ML inference related configurations for which the applicability indication was not transmitted at a previous point in time. a. According to this method, for example, the UE may have determined at time TO that an AI / ML model / functionality was applicable according to a certain first inference related configuration, e g. config(2), but the applicability indication was not transmitted for it, i.e. the UE did not indicate in the applicability indication that the concerned first inference related configuration make the AI / ML model / functionality applicable. This can happen for example in case the UE decided instead to apply / select another inference related configuration, i.e. the UE considered itself to be configured / applied config(3). If at time Tl, the UE selects to apply config (2), and not applying any longer config(3). This can happen for example, if at time Tl, the config(3) does not make any longer the AI / ML model / functionality applicable, or if at time Tl, the UE determines that the config(2) can give more accurate AI / ML inference-based prediction compared than config(3). According to this method, the UE activates config(2) and deactivates config (3) and notifies the gNB.• The results of the above determination can be transmitted at any point in time as (inapplicability indication as part for example of a UE Assistance Information message.

[0129] The UE transmits the applicability indication (indicating an applicability status as ‘non-applicable’), i.e. an inapplicability indication, in response to one or more of:• Receiving the said one or more inference related configuration associated to the said AI / ML model / functionality. a. In this method, the inapplicability indication can be transmitted as part of an RRCReconfigurationComplete message in response of an RRCReconfiguration including the AI / ML related inference configurations.• Determining that the AI / ML model / functionality is unapplicable according to at least one of the inference related configurations for which the AI / ML model / functionality was determined to be applicable and for which applicability indication was transmitted at a previous point in time, or just determining that the AI / ML model / functionality is unapplicable according to at least one of the inference related configuration. a. According to this method, for example at time TO the UE may have sent an applicability indication for the entire AI / L model / functionality or for one or more of the inference related configurations of such AI / ML model / functionality, e.g. config(2). Then at time Tl, the UE may determine that the AI / ML model / functionality is not applicable any longer, or it is not any longer applicable according to the inference related configurations for which the applicability indication was previously sent at time TO. This may depend, for example, on the UE changing its operating conditions (e.g., speed, antenna layout, orientation, battery status, etc.), or on radio factors (e.g., radio channel measurements, new configuration provided to the UE). According to this method, the UE deactivates config(2), and notifies the gNB. In one method, the concerned AI / ML related configuration that was applicable at time TO, i.e. config(2), it was selected / applied by the UE for the AI / ML inference of the concerned AI / ML model / functionality.• Determining that the AI / ML model / functionality is unapplicable according to at least one of the inference related configurations for which the AI / ML model / functionality was determined to be applicable and for which applicability indication was transmitted at a previous point in time, and determining that there is another inference related configuration that can make the model applicable. For example, at time Tl, according to previous methods, the UE may determine that config(2) is not any longer applicable, wherein config(2) is the configuration applied / selected by the UE for the AI / ML inference, and that config(3) can make the AI / ML model applicable at time Tl. The deactivates config(2) and activates config(3), and notifies the network as part of the (inapplicability indication.• The results of the above determination can be transmitted at any point in time as (inapplicability indication as part for example of a UE Assistance Information message.

[0130] The method wherein in response of transmitting the applicability indication for an AI / ML model / functionality:• The UE activates at step 710 the concerned AI / ML model / functionality;• The UE considers itself to be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be applicable; a. According to this method, the UE considers itself to be configured only with the inference related configurations for which the AI / ML model / functionality is applicable. In case there are more inference related configurations for which the AI / ML model / functionality is applicable, the UE may just consider itself to be configured with one of them (which would require a selection by the UE). b. After the activating at step 710, the method further includes monitoring at step 712 whether at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO becomes non- applicable at time Tl; and monitoring at step 714 whether the at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO but not applied or selected for the AI / ML inference of the concerned AI / ML model functionality at time TO, it is selected to be applied for the AI / ML inference of the concerned AI / ML model functionality at time Tl

[0131] The method wherein in response of transmitting the inapplicability indication for an AI / ML model / functionality• The UE deactivates at step 716 the concerned AI / ML model / functionality;• The UE considers itself to not be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be not applicable; a. According to this method, the UE considers itself not to be configured with the inference related configurations for which the AI / ML model / functionality is not applicable. In case all the inference related configurations for the AI / ML model / functionality are not applicable, the UE may just consider itself not to be configured with the said AI / ML model / functionality. b. The method further includes, after the deactivating, the UE monitors at step 718 whether at least one of the multiple stored inference related configurationdetermined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl. The UE also at step 720 monitors whether at least one of the multiple stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl, and whether such of the east one of the multiple stored inference related configuration are to be applied at time Tl for the AI / ML inference of the concerned AI / ML functionality

[0132] The UE may evaluate at any point in time the applicability of the AI / ML model / functionality based on the said stored inference related configuration(s). For example, the UE could evaluate the applicability periodically (e g. according to a periodicity configured at the UE, or a requirement defined for evaluating the applicability status of the supported functionality and / or the inference related configuration associated to the supported functionality), or whenever the UE internal properties change (e.g. the battery status, the UE antenna layout, the UE power consumption, the speed etc.), or whenever the UE is reconfigured by the gNB, i.e. the UE applies an RRC reconfiguration, or based on the radio conditions (e g. coverage status). The results of the above evaluation can be transmitted at any point in time as (in)applicability indication as part for example of a UE Assistance Information message.

[0133] The stored configurations associated to the supported functionality (e g. including one or more of the associated inference related configuration(S) for that supported functionality) may be updated by the network, e.g. the gNB may provide the UE with one or more new inference related configurations, as part of a new configuration for the supported functionality, or the gNB may remove one or more inference related configurations from the configuration of the supported functionality e.g. AI / ML for beam management configuration. If UE was considered itself to be configured with at least one of the radio measurement configuration to be removed, i.e. the AI / ML model / functionality was applicable based on the removed radio measurement configuration, the UE deactivates the AI / ML model / functionality.

[0134] Figure 8 shows an example of a communication system 800 in accordance with some embodiments.

[0135] In the example, the communication system 800 includes a telecommunication network 802 that includes an access network 804, such as a Radio Access Network (RAN), and a core network 806, which includes one or more core network nodes 808. The access network 804 includes one or more access network nodes, such as network nodes 810A and 810B (one or more of which may be generally referred to as network nodes 810), or any other similar Third Generation Partnership Project (3GPP) access nodes or non-3GPP Access Points (APs). Moreover, as will be appreciated by those of skill in the art, a network node is not necessarilylimited 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 802 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 802 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 802, including one or more network nodes 810 and / or core network nodes 808. The network nodes 810, in various embodiments, perform the functionality as described herein in Fig. 7.

[0136] Examples of an ORAN network node include an Open Radio Unit (O-RU), an Open Distributed Unit (O-DU), an Open Central Unit (O-CU), including an O-CU Control Plane (O- CU-CP) or an O-CU User Plane (O-CU-UP), a RAN intelligent controller (near-real time or non- real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or anon-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 810 facilitate direct or indirect connection of User Equipment (UE), such as by connecting UEs 812A, 812B, 812C, and 812D (one or more of which may be generally referred to as UEs 812) to the core network 806 over one or more wireless connections.

[0137] 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 800 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 800 mayinclude and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0138] The UEs 812 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 810 and other communication devices. Similarly, the network nodes 810 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 812 and / or with other network nodes or equipment in the telecommunication network 802 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 802. The UEs 812 in various embodiments perform the functionality as described in Fig. 7.

[0139] In the depicted example, the core network 806 connects the network nodes 810 to one or more hosts, such as host 816. 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 806 includes one more core network nodes (e.g., core network node 808) 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 808. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-Concealing Function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0140] The host 816 may be under the ownership or control of a service provider other than an operator or provider of the access network 804 and / or the telecommunication network 802, and may be operated by the service provider or on behalf of the service provider. The host 816 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.

[0141] As a whole, the communication system 800 of Figure 8 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 800 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 Second, Third, Fourth, or Fifth Generation (2G, 3G, 4G, or 5G) standards, or any applicable future generation standard (e g., Sixth Generation (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.

[0142] In some examples, the telecommunication network 802 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunication network 802 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 802. For example, the telecommunication network 802 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 Internet of Things (loT) services to yet further UEs.

[0143] In some examples, the UEs 812 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 804 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 804. Additionally, a UE may be configured for operating in single- or multi-Radio Access Technology (RAT) or multi-standard mode. For example, a UE may operate with any one or combination of WiFi, New Radio (NR), and LTE, i.e. being configured for Multi-Radio Dual Connectivity (MR-DC), such as Evolved UMTS Terrestrial RAN (E-UTRAN) NR - Dual Connectivity (EN-DC).

[0144] In the example, a hub 814 communicates with the access network 804 to facilitate indirect communication between one or more UEs (e.g., UE 812C and / or 812D) and network nodes (e.g., network node 810B). In some examples, the hub 814 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 814 may be a broadband router enabling access to the core network 806 for the UEs. As another example, the hub 814 may be a controller that sendscommands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 810, or by executable code, script, process, or other instructions in the hub 814. As another example, the hub 814 may be a data collector that acts as temporaiy storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 814 may be a content source. For example, for a UE that is a Virtual Reality (VR) headset, display, loudspeaker or other media deliveiy device, the hub 814 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 814 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 814 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0145] The hub 814 may have a constant / persistent or intermittent connection to the network node 810B. The hub 814 may also allow for a different communication scheme and / or schedule between the hub 814 and UEs (e.g., UE 812C and / or 812D), and between the hub 814 and the core network 806. In other examples, the hub 814 is connected to the core network 806 and / or one or more UEs via a wired connection. Moreover, the hub 814 may be configured to connect to a Machme-to-Machine (M2M) service provider over the access network 804 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 810 while still connected via the hub 814 via a wired or wireless connection. In some embodiments, the hub 814 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 810B. In other embodiments, the hub 814 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and the network node 810B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0146] Figure 9 shows a UE 900 in accordance with some embodiments. The UE 900 is an example of the UE 812, as described herein in Figs. 7 and 8. 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 Internet Protocol (VoIP) phone, wireless local loop phone, desktop computer, Personal Digital Assistant (PDA), wireless camera, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, Laptop Embedded Equipment (LEE), Laptop Mounted Equipment (LME), smart device, wireless Customer Premise Equipment (CPE), vehicle, vehicle-mounted or vehicleembedded / integrated wireless device, etc. Other examples include any UE identified by the 3GPP, including a Narrowband Internet of Things (NB-IoT) UE, a Machine Type Communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0147] A UE may support Devi ce-to-D evice (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).

[0148] The UE 900 includes processing circuitry 902 that is operatively coupled via a bus 904 to an input / output interface 906, a power source 908, memory 910, a communication interface 912, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 9. 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.

[0149] The processing circuitry 902 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 910. The processing circuitiy 902 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 902 may include multiple Central Processing Units (CPUs).

[0150] In the example, the input / output interface 906 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 900.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.

[0151] In some embodiments, the power source 908 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 908 may further include power circuitry for delivering power from the power source 908 itself, and / or an external power source, to the various parts of the UE 900 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 908. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 908 to make the power suitable for the respective components of the UE 900 to which power is supplied.

[0152] The memory 910 may be or be configured to include memory such as Random Access Memory (RAM), Read Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 910 includes one or more application programs 914, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 916. The memory 910 may store, for use by the UE 900, any of a variety of various operating systems or combinations of operating systems.

[0153] The memory 910 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 RAM (SDRAM), external micro-DIMM SDRAM, smartcard memory such as a tamper resistant module in the form of a Universal Integrated Circuit Card (UICC) including one or more Subscriber Identity Modules (SIMs), such as a Universal SIM(USIM) and / or Internet Protocol Multimedia Services Identity Module (ISIM), other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as a ‘SIM card.’ The memory 910 may allow the UE 900 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 910, which may be or comprise a device-readable storage medium.

[0154] The processing circuitry 902 may be configured to communicate with an access network or other network using the communication interface 912. The communication interface 912 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 922. The communication interface 912 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 918 and / or a receiver 920 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 918 and receiver 920 may be coupled to one or more antennas (e.g., the antenna 922) and may share circuit components, software, or firmware, or alternatively be implemented separately.

[0155] In the illustrated embodiment, communication functions of the communication interface 912 may include cellular communication, WiFi communication, LPWAN communication, data communication, voice communication, multimedia communication, short- range communications such as Bluetooth, NFC, 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 according to one or more communication protocols and / or standards, such as IEEE 802. 11, Code Division Multiplexing Access (CDMA), Wideband CDMA (WCDMA), GSM, LTE, NR, UMTS, WiMax, Ethernet, Transmission Control Protocol / Intemet Protocol (TCP / IP), Synchronous Optical Networking (SONET), Asynchronous Transfer Mode (ATM), Quick User Datagram Protocol Internet Connection (QUIC), Hypertext Transfer Protocol (HTTP), and so forth.

[0156] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 912, 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 severalsensors), 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).

[0157] 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.

[0158] A UE, when in the form of an 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 television, 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 head-mounted display for Augmented Reality (AR) or VR, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 900 shown in Figure 9.

[0159] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship, an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0160] 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.

[0161] Figure 10 shows a network node 1000 in accordance with some embodiments. The network node 1000 is an example of the network node 810, as described herein in Figs. 7 and 8. 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, APs (e.g., radio APs), Base Stations (BSs) (e.g., radio BSs, Node Bs, evolved Node Bs (eNBs), NR Node Bs (gNBs)), and O-RAN nodes or components of an 0-RAN node (e.g., O-RU, O-DU, O-CU).

[0162] 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 RRUs 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).

[0163] 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 BS Controllers (BSCs), Base Transceiver Stations (BTSs), transmission points, transmission nodes, Multi-Cell / Multicast Coordination Entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0164] The network node 1000 includes processing circuitry 1002, memory 1004, a communication interface 1006, and a power source 1008. The network node 1000 may be composed of multiple physically separate components (e.g., aNodeB component and an 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 1000 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 1000 may be configured to support multiple RATs. In such embodiments, some components may be duplicated (e.g., separate memory 1004 for different RATs) and some components may be reused (e.g., a same antenna 1010 may be shared by different RATs). The network node 1000 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1000, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, Long Range Wide Area Network (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 the network node 1000.

[0165] The processing circuitry 1002 may comprise a combination of one or more of a microprocessor, controller, microcontroller, CPU, DSP, ASIC, FPGA, 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 1000 components, such as the memory 1004, to provide network node 1000 functionality.

[0166] In some embodiments, the processing circuitry 1002 includes a System on a Chip (SOC). In some embodiments, the processing circuitiy 1002 includes one or more of Radio Frequency (RF) transceiver circuitry 1012 and baseband processing circuitry 1014. In some embodiments, the RF transceiver circuitiy 1012 and the baseband processing circuitry 1014 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 the RF transceiver circuitiy 1012 and the baseband processing circuitiy 1014 may be on the same chip or set of chips, boards, or units.

[0167] The memory 1004 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, RAM, 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-transitorydevice-readable, and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1002. The memory 1004 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 1002 and utilized by the network node 1000. The memory 1004 may be used to store any calculations made by the processing circuitry 1002 and / or any data received via the communication interface 1006. In some embodiments, the processing circuitry 1002 and the memory 1004 are integrated.

[0168] The communication interface 1006 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 1006 comprises port(s) / terminal(s) 1016 to send and receive data, for example to and from a network over a wired connection. The communication interface 1006 also includes radio front-end circuitry 1018 that may be coupled to, or in certain embodiments a part of, the antenna 1010. The radio front-end circuitry 1018 comprises filters 1020 and amplifiers 1022. The radio front-end circuitry 1018 may be connected to the antenna 1010 and the processing circuitry 1002. The radio front-end circuitry 1018 may be configured to condition signals communicated between the antenna 1010 and the processing circuitry 1002. The radio front-end circuitry 1018 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 1018 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of the filters 1020 and / or the amplifiers 1022. The radio signal may then be transmitted via the antenna 1010. Similarly, when receiving data, the antenna 1010 may collect radio signals which are then converted into digital data by the radio front-end circuitiy 1018. The digital data may be passed to the processing circuitiy 1002. In other embodiments, the communication interface 1006 may comprise different components and / or different combinations of components.

[0169] In certain alternative embodiments, the network node 1000 does not include separate radio front-end circuitry 1018; instead, the processing circuitry 1002 includes radio front-end circuitry and is connected to the antenna 1010. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1012 is part of the communication interface 1006. In still other embodiments, the communication interface 1006 includes the one or more ports or terminals 1016, the radio front-end circuitry 1018, and the RF transceiver circuitry 1012 as part of a radio unit (not shown), and the communication interface 1006 communicates with the baseband processing circuitry 1014, which is part of a digital unit (not shown).

[0170] The antenna 1010 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1010 may be coupled to the radio front-end circuitry 1018 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1010 is separate from the network node 1000 and connectable to the network node 1000 through an interface or port.

[0171] The antenna 1010, the communication interface 1006, and / or the processing circuitry 1002 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node 1000 Any information, data, and / or signals may be received from a UE, another network node, and / or any other network equipment. Similarly, the antenna 1010, the communication interface 1006, and / or the processing circuitry 1002 may be configured to perform any transmitting operations described herein as being performed by the network node 1000. Any information, data, and / or signals may be transmitted to a UE, another network node, and / or any other network equipment.

[0172] The power source 1008 provides power to the various components of the network node 1000 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1008 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1000 with power for performing the functionality described herein. For example, the network node 1000 may be connectable to an external power source (e.g., the power grid or an electricity outlet) via input circuitry or an interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1008. As a further example, the power source 1008 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 batteiy may provide backup power should the external power source fail.

[0173] Embodiments of the network node 1000 may include additional components beyond those shown in Figure 10 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 1000 may include user interface equipment to allow input of information into the network node 1000 and to allow output of information from the network node 1000. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1000. In some embodiments providing a core network node, such as core network node 808 of FIG. 8, some components, such as the radio front-end circuitry 1018 and the RF transceiver circuitry 1012 may be omitted.

[0174] Figure 11 is a block diagram illustrating a virtualization environment 1100 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 virtualization environments 1100 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, a UE, a core network node, or a 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 1100 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface. Virtualization may facilitate distributed implementations of a network node, a UE, a core network node, or a host.

[0175] Applications 1102 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1100 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0176] Hardware 1104 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, an input / output interface, and so forth. Software may be executed by the processing circuitiy to instantiate one or more virtualization layers 1106 (also referred to as hypervisors or Virtual Machine Monitors (VMMs)), provide VMs 1108A and 1108B (one or more of which may be generally referred to as VMs 1108), and / or perform any of the functions, features, and / or benefits described in relation with some embodiments described herein. The virtualization layer 1106 may present a virtual operating platform that appears like networking hardware to the VMs 1108.

[0177] The VMs 1108 comprise virtual processing, virtual memory, virtual networking, or interface and virtual storage, and may be run by a corresponding virtualization layer 1106. Different embodiments of the instance of a virtual appliance 1102 may be implemented on one or more of VMs 1108, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as Network Function Virtualization (NFV). NFVmay 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.

[0178] In the context of NFV, a VM 1108 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 1108, and that part of the hardware 1104 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 1108 on top of the hardware 1104 and corresponds to the application 1102.

[0179] The hardware 1104 may be implemented in a standalone network node with generic or specific components. The hardware 1104 may implement some functions via virtualization. Alternatively, the hardware 1104 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 1110, which, among others, oversees lifecycle management of the applications 1102. In some embodiments, the hardware 1104 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 1112 which may alternatively be used for communication between hardware nodes and radio units.

[0180] 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 largerbox, 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.

[0181] 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.

[0182] Those skilled in the art will recognize improvements and modifications to the embodiments of the present disclosure. All such improvements and modifications are considered within the scope of the concepts disclosed herein.

[0183] Some of the embodiments of the present disclosure include:

[0184] Embodiment 1 : A method performed by a user equipment, UE, (812) for signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the method comprising: receiving (702), from a network node (810), a plurality of inference related configurations associated with at least one supported functionality; determining (704) an applicability status for each inference related configuration of the plurality of inference related configurations, wherein the applicability status indicates whether the inference related configuration is applicable or non-applicable; transmitting (706) a first indication comprising one or more of: an applicability indication indicating that an AI / ML model functionality is determined to be applicable; and an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable according to one or more inference related configurations, storing (708) the one or more inference related configurations.

[0185] Embodiment 2: The method of embodiment 1, wherein in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be applicable, the method further comprises: performing one or more of the following operations: activating (710) the supported functionality for the at least one of the plurality of inference related configurations, applying the at least one of the plurality of inference related configurations; monitoring (712) whether at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO becomes non-applicable at time Tl; and monitoring (714) whether the at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO but not applied or selected for the AI / ML inference of the concerned AI / ML model functionality at time TO, it is selected to be applied for the AI / ML inference of the concerned AI / ML model functionality at time TL

[0186] Embodiment 3: The method of embodiment 1, wherein in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be non-applicable, the method further comprises: deactivating (716) the supported functionality or inference(s)) for the at least one of the plurality of inference related configurations; monitoring (718) whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl; and monitoring (720) whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non- applicable’ at time TO becomes applicable at time Tl, and whether such of the east one of the one or more stored inference related configurations are to be applied at time Tl for the AI / ML inference of the concerned AI / ML functionality.

[0187] Embodiment 4: The method of embodiment 1, wherein the one or more inference related configurations for which a supported functionality is considered applicable are determined by the UE (812) on the basis of the training performed for the said AI / L model functionality or based on a provided UE (812) capabilities for different use cases of AI / ML.

[0188] Embodiment 5 : The method of embodiment 1 , wherein the one or more inference related configurations are determined by the UE (812) on the basis of the historical model inference performed for the said AI / ML model functionality.

[0189] Embodiment 6: The method of any of embodiments 3 to 4, wherein the one or more inference related configurations determined by the UE (812) are transmitted as part of the first indication.

[0190] Embodiment 7 : The method of embodiment 1 , wherein the applicability indication is transmitted to the network node (810) in response to one or more of: receiving (702) the one or more inference related configurations associated to the AI / ML model functionality; determining (704) that the AI / ML model functionality is applicable according to at least one of the one or more inference related configurations for which it was determined that the AI / ML model / functionality was not applicable at a previous point in time; and determining (704) that the AI / ML model / functionality is applicable according to at least one of the one or more AI / ML inference related configurations for which the applicability indication was not transmitted at a previous point in time.

[0191] Embodiment 8: The method of embodiment 7, wherein the inapplicability indication is transmitted implicitly as part of the applicability indication.

[0192] Embodiment 9: The method of embodiment 1, wherein the one or more inference related configurations are stored by the UE (812).

[0193] Embodiment 10: The method of embodiment 9, wherein the one or more stored inference related configurations may be associated with the stored corresponding configuration(s) for a supported functionality and / or stored corresponding (in)applicability information and / or stored inference performance.

[0194] Embodiment 11 : The method of embodiment 9, wherein the stored inference related configurations are considered in order to determine the applicability or inapplicability of the AI / ML model / functionality.

[0195] Embodiment 12: The method of embodiment 1, wherein in response to transmitting the applicability indication for an AI / ML model / functionality the method further comprises: deactivating (716) the concerned AI / ML model / functionality, wherein the UE (812) considers itself to not be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be not applicable, i.e. the UE (812) does not apply any longer the one or more inference related configurations.

[0196] Embodiment 13: The method of embodiment 1, wherein in response to transmitting the inapplicability indication for an AI / ML model / functionality, the method further comprises: activating (710) the concerned AI / ML model / functionality, wherein the UE (812) considers itself to be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be applicable, i.e. it applies the one or more inference related configurations.

[0197] Embodiment 14: The method of embodiment 1, wherein the inference related configuration comprises one or more of: a set A and / or set B of radio resources; network-side operation properties; and UE-side operation properties.

[0198] Embodiment 15: The method of embodiment 14, wherein the set A and / or set B of radio resources comprise one or more of: a set of Synchronization Signal Block, SSB, for a cell; a set of Channel State Information Reference Signal, CSI-RS, resources for a cell; a set of Synchronization Signal, SS, Physical Broadcast Channel, PBCH, block resource sets for a cell; a set of cells; a set of frequencies; a set of SSB for a list of cells; a set of CSI-RS resources for a list of cells; and a set of SS / PBCH block resource sets for the list of cells.

[0199] Embodiment 16: The method of embodiment 14, wherein the network-side / UE-side operational properties comprises one or more of: a mapping relationship of Set A and Set B; an indication of consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B; a quasi co-location, QCL, assumption; an order of model input and model output; transmission power; a UE distribution; antenna height; a deployment scenario information; and a UE speed.

[0200] Embodiment 17: The methods of any of embodiments 14 to 16, wherein the inference related configurations comprise a list of identifiers, IDs, each referring to a specific configuration.

[0201] Embodiment 18: The methods of any of embodiments 1 to 17, wherein the embodiments are executed for each of the AI / ML models / functionalities for which inference related configurations are configured.

[0202] Embodiment 19: The methods of any of embodiments 1 to 18, wherein the inference related configurations are candidate configuration for the AI / ML inference, wherein the applicability and inapplicability indications for different AI / ML models / functionalities are sent in different messages or in a single message

[0203] Embodiment 20: The method of embodiment 2, wherein the inference related configurations are candidate configuration for the AI / ML inference.

[0204] Embodiment 21 : A user equipment for signaling an applicability of Artificial Intelligence Machine Learning, AI / ML. functionalities, the UE (812) comprising processing circuitry configured to perform any of the steps of embodiments 1 to 20.

[0205] Embodiment 22: A method performed by a network node (810) for facilitating signaling an applicability of Artificial Intelligence Machine Learning, AI / ML. functionalities, the method comprising: transmitting (702) a plurality of inference related configuration associated to at least one supported functionality, for which a User Equipment, UE, (812) has reported that itis capable of supporting; receiving (706) a first indication comprising one or more of: an applicability indication indicating that the AI / ML model functionality is determined to be applicable by the UE (812); an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable by the UE (812) according to one or more inference related configurations.

[0206] Embodiment 23: A network node (810) for facilitating signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the network node (810) comprising processing circuitry configured to perform any of the steps of embodiment 22

Claims

CLAIMS1. A method performed by a user equipment, UE, (812) for signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the method comprising: receiving (702), from a network node (810), a plurality of inference related configurations associated with at least one supported functionality; determining (704) an applicability status for each inference related configuration of the plurality of inference related configurations, wherein the applicability status indicates whether the inference related configuration is applicable or non-applicable; transmitting (706) a first indication comprising one or more of: an applicability indication indicating that an AI / ML model functionality is determined to be applicable; and an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable according to one or more inference related configurations.

2. The method of claim 1, wherein in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be applicable, the method further comprises: performing one or more of the following operations: activating (710) the supported functionality for the at least one of the plurality of inference related configurations, applying the at least one of the plurality of inference related configurations; monitoring (712) whether at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO becomes non- applicable at time T1 ; and monitoring (714) whether the at least one of the stored inference related configurations that are determined to have the applicability status as applicable at time TO but not applied or selected for the AI / ML inference of the concerned AI / ML model functionality at time TO, it is selected to be applied for the AI / ML inference of the concerned AI / ML model functionality at time Tl.

3. The method of claim 1, wherein in response to determining that at least one of the plurality of inference related configurations has an applicability status determined to be non-applicable, the method further comprises:deactivating (716) the supported functionality or inference(s)) for the at least one of the plurality of inference related configurations; monitoring (718) whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl; and monitoring (720) whether at least one of the one or more stored inference related configuration determined to have the applicability status as ‘non-applicable’ at time TO becomes applicable at time Tl, and whether such of the east one of the one or more stored inference related configurations are to be applied at time Tl for the AI / ML inference of the concerned AI / ML functionality.

4. The method of claim 1, wherein the one or more inference related configurations for which a supported functionality is considered applicable are determined by the UE (812) on the basis of the training performed for the said AI / ML model functionality or based on a provided UE (812) capabilities for different use cases of AI / ML.

5. The method of claim 1, wherein the one or more inference related configurations are determined by the UE (812) on the basis of the historical model inference performed for the said AI / ML model functionality.

6. The method of any of claims 3 to 4, wherein the one or more inference related configurations determined by the UE (812) are transmitted as part of the first indication.

7. The method of claim 1, wherein the applicability indication is transmitted to the network node (810) in response to one or more of: receiving (702) the one or more inference related configurations associated to the AI / ML model functionality; determining (704) that the AI / ML model functionality is applicable according to at least one of the one or more inference related configurations for which it was determined that the AI / ML model / functionality was not applicable at a previous point in time; and determining (704) that the AI / ML model / functionality is applicable according to at least one of the one or more AI / ML inference related configurations for which the applicability indication was not transmitted at a previous point in time.

8. The method of claim 7, wherein the inapplicability indication is transmitted implicitly as part of the applicability indication.

9. The method of claim 1, wherein the one or more inference related configurations are stored by the UE (812).

10. The method of claim 9, wherein the one or more stored inference related configurations may be associated with the stored corresponding configuration(s) for a supported functionality and / or stored corresponding (in)applicability information and / or stored inference performance.

11. The method of claim 9, wherein the stored inference related configurations are considered in order to determine the applicability or inapplicability of the AI / ML model / functionality.

12. The method of claim 1, wherein in response to transmitting the inapplicability indication for an AI / ML model / functionality the method further comprises: deactivating (716) the concerned AI / ML model / functionality, wherein the UE (812) considers itself to not be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be not applicable, i.e. the UE (812) does not apply any longer the one or more inference related configurations.

13. The method of claim 1, wherein in response to transmitting the applicability indication for an AI / ML model / functionality, the method further comprises: activating (710) the concerned AI / ML model / functionality, wherein the UE (812) considers itself to be configured with the one or more inference related configurations for which the concerned AI / ML model / functionality is determined to be applicable, i.e. it applies the one or more inference related configurations.

14. The method of claim 1, wherein the inference related configuration comprises one or more of: a set A and / or set B of radio resources; network-side operation properties; and UE-side operation properties.

15. The method of claim 14, wherein the set A and / or set B of radio resources comprise one or more of: a set of Synchronization Signal Block, SSB, for a cell; a set of Channel State Information Reference Signal, CSI-RS, resources for a cell; a set of Synchronization Signal, SS, Physical Broadcast Channel, PBCH, block resource sets for a cell; a set of cells; a set of frequencies; a set of SSB for a list of cells; a set of CSI-RS resources for a list of cells; and a set of SS / PBCH block resource sets for the list of cells.

16. The method of claim 14, wherein the network-side / UE-side operational properties comprises one or more of: a mapping relationship of Set A and Set B, including a set of identifiers, IDs; an indication of consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B; a quasi-co-location, QCL, assumption; an order of model input and model output; transmission power; a UE distribution; antenna height; a deployment scenario information; and a UE speed.

17. The methods of any of claims 14 to 16, wherein the inference related configurations comprise a list of identifiers, IDs, each referring to a specific configuration.

18. The methods of any of claims 1 to 17, wherein the inference related configurations are candidate configuration for the AI / ML inference, wherein the applicability and inapplicability indications for different AI / ML models / functionalities are sent in different messages or in a single message.

19. The method of claim 2, wherein the inference related configurations are candidateconfiguration for the AI / ML inference.

20. The method of any of claims 1 to 19, further comprising: storing (708) the one or more inference related configurations.

21. A user equipment for signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the UE (812) comprising processing circuitry configured to perform any of the steps of claims 1 to 20.

22. A method performed by a network node (810) for facilitating signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the method comprising: transmitting (702) a plurality of inference related configuration associated to at least one supported functionality, for which a User Equipment, UE, (812) has reported that it is capable of supporting; receiving (706) a first indication comprising one or more of: an applicability indication indicating that the AI / ML model functionality is determined to be applicable by the UE (812); an inapplicability indication indicating that the AI / ML model functionality is not determined to be applicable by the UE (812) according to one or more inference related configurations.

23. A network node (810) for facilitating signaling an applicability of Artificial Intelligence Machine Learning, AI / ML, functionalities, the network node (810) comprising processing circuitry configured to perform any of the steps of claim 22.

Images